diff options
| author | Praneeth Bajjuri <praneeth@ti.com> | 2017-08-28 18:03:19 -0500 |
|---|---|---|
| committer | Praneeth Bajjuri <praneeth@ti.com> | 2017-08-28 18:03:19 -0500 |
| commit | dda8acaf6f2d9bddce62c305edf6b3071f04c136 (patch) | |
| tree | 612f8b7b18ff3a84184ddc0ce456b9b0287cace6 | |
| parent | b22bbe0c5fa4fd5eb4609108a750b28a744a643e (diff) | |
| parent | eabbcea7629d5f2ec91568f7bd104536614107db (diff) | |
| download | jacinto6evm-6AM.1.3-rvc-video.tar.gz | |
Merge branch 'p-ti-lsk-android-linux-4.4.y' of git://git.omapzoom.org/kernel/omap into 6AM.1.3-rvc-video6AM.1.3-rvc-video
* 'p-ti-lsk-android-linux-4.4.y' of git://git.omapzoom.org/kernel/omap: (2048 commits)
ARM: dts: dra7: Remove deprecated PCI compatible string
ARM: dts: dra76-evm: Enable x2 PCIe lanes
ARM: dts: DRA72x: Use PCIe compatible specific to dra72
ARM: dts: DRA74x: Use PCIe compatible specific to dra74
ARM: dts: dra7: Add properties to enable PCIe x2 lane mode
PCI: dwc: pci-dra7xx: Enable x2 mode support
PCI: dwc: dra7xx: Add support for SoC specific compatible strings
dt-bindings: PCI: dra7xx: Add properties to enable x2 lane in dra7
dt-bindings: PCI: dra7xx: Add SoC specific compatible strings
ARM: dts: dra7-evm: Move pcie RC node to common file
ARM: dts: dra76-evm: add higher speed MMC/SD modes
Linux 4.4.84
usb: qmi_wwan: add D-Link DWM-222 device ID
usb: optimize acpi companion search for usb port devices
perf/x86: Fix LBR related crashes on Intel Atom
pids: make task_tgid_nr_ns() safe
Sanitize 'move_pages()' permission checks
irqchip/atmel-aic: Fix unbalanced refcount in aic_common_rtc_irq_fixup()
irqchip/atmel-aic: Fix unbalanced of_node_put() in aic_common_irq_fixup()
x86/asm/64: Clear AC on NMI entries
...
Signed-off-by: Praneeth Bajjuri <praneeth@ti.com>
Conflicts:
arch/arm/boot/dts/Makefile
drivers/gpu/drm/omapdrm/dss/dispc.c
1759 files changed, 28806 insertions, 13638 deletions
diff --git a/Documentation/Makefile b/Documentation/Makefile index bc0548201755..fc759598c4c9 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -1,4 +1,4 @@ subdir-y := accounting auxdisplay blackfin connector \ - filesystems filesystems ia64 laptops mic misc-devices \ + filesystems filesystems ia64 laptops misc-devices \ networking pcmcia prctl ptp spi timers vDSO video4linux \ watchdog diff --git a/Documentation/arm64/tagged-pointers.txt b/Documentation/arm64/tagged-pointers.txt index d9995f1f51b3..a25a99e82bb1 100644 --- a/Documentation/arm64/tagged-pointers.txt +++ b/Documentation/arm64/tagged-pointers.txt @@ -11,24 +11,56 @@ in AArch64 Linux. The kernel configures the translation tables so that translations made via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of the virtual address ignored by the translation hardware. This frees up -this byte for application use, with the following caveats: +this byte for application use. - (1) The kernel requires that all user addresses passed to EL1 - are tagged with tag 0x00. This means that any syscall - parameters containing user virtual addresses *must* have - their top byte cleared before trapping to the kernel. - (2) Non-zero tags are not preserved when delivering signals. - This means that signal handlers in applications making use - of tags cannot rely on the tag information for user virtual - addresses being maintained for fields inside siginfo_t. - One exception to this rule is for signals raised in response - to watchpoint debug exceptions, where the tag information - will be preserved. +Passing tagged addresses to the kernel +-------------------------------------- - (3) Special care should be taken when using tagged pointers, - since it is likely that C compilers will not hazard two - virtual addresses differing only in the upper byte. +All interpretation of userspace memory addresses by the kernel assumes +an address tag of 0x00. + +This includes, but is not limited to, addresses found in: + + - pointer arguments to system calls, including pointers in structures + passed to system calls, + + - the stack pointer (sp), e.g. when interpreting it to deliver a + signal, + + - the frame pointer (x29) and frame records, e.g. when interpreting + them to generate a backtrace or call graph. + +Using non-zero address tags in any of these locations may result in an +error code being returned, a (fatal) signal being raised, or other modes +of failure. + +For these reasons, passing non-zero address tags to the kernel via +system calls is forbidden, and using a non-zero address tag for sp is +strongly discouraged. + +Programs maintaining a frame pointer and frame records that use non-zero +address tags may suffer impaired or inaccurate debug and profiling +visibility. + + +Preserving tags +--------------- + +Non-zero tags are not preserved when delivering signals. This means that +signal handlers in applications making use of tags cannot rely on the +tag information for user virtual addresses being maintained for fields +inside siginfo_t. One exception to this rule is for signals raised in +response to watchpoint debug exceptions, where the tag information will +be preserved. The architecture prevents the use of a tagged PC, so the upper byte will be set to a sign-extension of bit 55 on exception return. + + +Other considerations +-------------------- + +Special care should be taken when using tagged pointers, since it is +likely that C compilers will not hazard two virtual addresses differing +only in the upper byte. diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt index 6071ba28d279..c74ef6c457f0 100644 --- a/Documentation/devicetree/bindings/arm/omap/omap.txt +++ b/Documentation/devicetree/bindings/arm/omap/omap.txt @@ -80,6 +80,9 @@ SoCs: - OMAP5432 compatible = "ti,omap5432", "ti,omap5" +- DRA762 + compatible = "ti,dra762", "ti,dra7" + - DRA742 compatible = "ti,dra742", "ti,dra74", "ti,dra7" @@ -163,6 +166,9 @@ Boards: - AM5718 IDK compatible = "ti,am5718-idk", "ti,am5728", "ti,dra742", "ti,dra74", "ti,dra7" +- DRA762 EVM: Software Development Board for DRA762 + compatible = "ti,dra76-evm", "ti,dra76", "ti,dra7" + - DRA742 EVM: Software Development Board for DRA742 compatible = "ti,dra7-evm", "ti,dra742", "ti,dra74", "ti,dra7" diff --git a/Documentation/devicetree/bindings/chosen.txt b/Documentation/devicetree/bindings/chosen.txt index 6ae9d82d4c37..b5e39af4ddc0 100644 --- a/Documentation/devicetree/bindings/chosen.txt +++ b/Documentation/devicetree/bindings/chosen.txt @@ -52,3 +52,48 @@ This property is set (currently only on PowerPC, and only needed on book3e) by some versions of kexec-tools to tell the new kernel that it is being booted by kexec, as the booting environment may differ (e.g. a different secondary CPU release mechanism) + +linux,usable-memory-range +------------------------- + +This property (arm64 only) holds a base address and size, describing a +limited region in which memory may be considered available for use by +the kernel. Memory outside of this range is not available for use. + +This property describes a limitation: memory within this range is only +valid when also described through another mechanism that the kernel +would otherwise use to determine available memory (e.g. memory nodes +or the EFI memory map). Valid memory may be sparse within the range. +e.g. + +/ { + chosen { + linux,usable-memory-range = <0x9 0xf0000000 0x0 0x10000000>; + }; +}; + +The main usage is for crash dump kernel to identify its own usable +memory and exclude, at its boot time, any other memory areas that are +part of the panicked kernel's memory. + +While this property does not represent a real hardware, the address +and the size are expressed in #address-cells and #size-cells, +respectively, of the root node. + +linux,elfcorehdr +---------------- + +This property (currently used only on arm64) holds the memory range, +the address and the size, of the elf core header which mainly describes +the panicked kernel's memory layout as PT_LOAD segments of elf format. +e.g. + +/ { + chosen { + linux,elfcorehdr = <0x9 0xfffff000 0x0 0x800>; + }; +}; + +While this property does not represent a real hardware, the address +and the size are expressed in #address-cells and #size-cells, +respectively, of the root node. diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt index 8a47b77abfca..e8c74a6e738b 100644 --- a/Documentation/devicetree/bindings/clock/sunxi.txt +++ b/Documentation/devicetree/bindings/clock/sunxi.txt @@ -18,6 +18,7 @@ Required properties: "allwinner,sun4i-a10-cpu-clk" - for the CPU multiplexer clock "allwinner,sun4i-a10-axi-clk" - for the AXI clock "allwinner,sun8i-a23-axi-clk" - for the AXI clock on A23 + "allwinner,sun4i-a10-gates-clk" - for generic gates on all compatible SoCs "allwinner,sun4i-a10-axi-gates-clk" - for the AXI gates "allwinner,sun4i-a10-ahb-clk" - for the AHB clock "allwinner,sun5i-a13-ahb-clk" - for the AHB clock on A13 @@ -43,6 +44,7 @@ Required properties: "allwinner,sun6i-a31-apb0-gates-clk" - for the APB0 gates on A31 "allwinner,sun7i-a20-apb0-gates-clk" - for the APB0 gates on A20 "allwinner,sun8i-a23-apb0-gates-clk" - for the APB0 gates on A23 + "allwinner,sun8i-h3-apb0-gates-clk" - for the APB0 gates on H3 "allwinner,sun9i-a80-apb0-gates-clk" - for the APB0 gates on A80 "allwinner,sun4i-a10-apb1-clk" - for the APB1 clock "allwinner,sun9i-a80-apb1-clk" - for the APB1 bus clock on A80 diff --git a/Documentation/devicetree/bindings/mfd/lp87565.txt b/Documentation/devicetree/bindings/mfd/lp87565.txt new file mode 100644 index 000000000000..a48df7c08ab0 --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/lp87565.txt @@ -0,0 +1,43 @@ +TI LP87565 PMIC MFD driver + +Required properties: + - compatible: "ti,lp87565", "ti,lp87565-q1" + - reg: I2C slave address. + - gpio-controller: Marks the device node as a GPIO Controller. + - #gpio-cells: Should be two. The first cell is the pin number and + the second cell is used to specify flags. + See ../gpio/gpio.txt for more information. + - xxx-in-supply: Phandle to parent supply node of each regulator + populated under regulators node. xxx should match + the supply_name populated in driver. +Example: + +lp87565_pmic: pmic@60 { + compatible = "ti,lp87565-q1"; + reg = <0x60>; + gpio-controller; + #gpio-cells = <2>; + + buck10-in-supply = <&vsys_3v3>; + buck23-in-supply = <&vsys_3v3>; + + regulators: regulators { + buck10_reg: buck10 { + /* VDD_MPU */ + regulator-name = "buck10"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1250000>; + regulator-always-on; + regulator-boot-on; + }; + + buck23_reg: buck23 { + /* VDD_GPU */ + regulator-name = "buck23"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1250000>; + regulator-boot-on; + regulator-always-on; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/pci/ti-pci.txt b/Documentation/devicetree/bindings/pci/ti-pci.txt index 85746eca3632..57bf112a09be 100644 --- a/Documentation/devicetree/bindings/pci/ti-pci.txt +++ b/Documentation/devicetree/bindings/pci/ti-pci.txt @@ -1,14 +1,22 @@ TI PCI Controllers PCIe Designware Controller - - compatible: Should be "ti,dra7-pcie" for RC - Should be "ti,dra7-pcie-ep" for EP + - compatible: Should be "ti,dra7-pcie" for RC (deprecated) + Should be "ti,dra7-pcie-ep" for EP (deprecated) + Should be "ti,dra746-pcie-rc" for dra74x/dra76 in RC mode + Should be "ti,dra746-pcie-ep" for dra74x/dra76 in EP mode + Should be "ti,dra726-pcie-rc" for dra72x in RC mode + Should be "ti,dra726-pcie-ep" for dra72x in EP mode - phys : list of PHY specifiers (used by generic PHY framework) - phy-names : must be "pcie-phy0", "pcie-phy1", "pcie-phyN".. based on the number of PHYs as specified in *phys* property. - ti,hwmods : Name of the hwmod associated to the pcie, "pcie<X>", where <X> is the instance number of the pcie from the HW spec. - num-lanes as specified in ../designware-pcie.txt + - syscon-lane-conf : phandle/offset pair. Phandle to the system control module and the + register offset to specify 1 lane or 2 lane. + - syscon-lane-sel : phandle/offset pair. Phandle to the system control module and the + register offset to specify lane selection. HOST MODE ========= diff --git a/Documentation/devicetree/bindings/video/fpd3-serdes.txt b/Documentation/devicetree/bindings/video/fpd3-serdes.txt index e2afceeafacb..afa56806f7a5 100644 --- a/Documentation/devicetree/bindings/video/fpd3-serdes.txt +++ b/Documentation/devicetree/bindings/video/fpd3-serdes.txt @@ -32,6 +32,8 @@ Required Properties: - "ti,ds90ub914aq": For TI FPDlink3 12bit video de serializer - "ti,ds90uh925q": For TI FPDlink3 24bit video serializer - "ti,ds90uh928q": For TI FPDlink3 24bit video de serializer + - "ti,ds90ub924q": For TI FPDlink3 24bit video de serializer + - "ti,ds90ub921q": For TI FPDlink3 24bit video serializer - reg: I2C slave address This would be the alias adress for remote device. The CPU side diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index bc4bd5a44b88..b6fe6a885bf8 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -18,7 +18,7 @@ memory image to a dump file on the local disk, or across the network to a remote system. Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64, -s390x and arm architectures. +s390x, arm and arm64 architectures. When the system kernel boots, it reserves a small section of memory for the dump-capture kernel. This ensures that ongoing Direct Memory Access @@ -249,6 +249,13 @@ Dump-capture kernel config options (Arch Dependent, arm) AUTO_ZRELADDR=y +Dump-capture kernel config options (Arch Dependent, arm64) +---------------------------------------------------------- + +- Please note that kvm of the dump-capture kernel will not be enabled + on non-VHE systems even if it is configured. This is because the CPU + will not be reset to EL2 on panic. + Extended crashkernel syntax =========================== @@ -312,6 +319,8 @@ Boot into System Kernel any space below the alignment point may be overwritten by the dump-capture kernel, which means it is possible that the vmcore is not that precise as expected. + On arm64, use "crashkernel=Y[@X]". Note that the start address of + the kernel, X if explicitly specified, must be aligned to 2MiB (0x200000). Load the Dump-capture Kernel ============================ @@ -334,6 +343,8 @@ For s390x: - Use image or bzImage For arm: - Use zImage +For arm64: + - Use vmlinux or Image If you are using a uncompressed vmlinux image then use following command to load dump-capture kernel. @@ -377,6 +388,9 @@ For s390x: For arm: "1 maxcpus=1 reset_devices" +For arm64: + "1 maxcpus=1 reset_devices" + Notes on loading the dump-capture kernel: * By default, the ELF headers are stored in ELF64 format to support diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 583935f88ee8..21321b9acfb0 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1261,6 +1261,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. When zero, profiling data is discarded and associated debugfs files are removed at module unload time. + goldfish [X86] Enable the goldfish android emulator platform. + Don't use this when you are not running on the + android emulator + gpt [EFI] Forces disk with valid GPT signature but invalid Protective MBR to be treated as GPT. If the primary GPT is corrupted, it enables the backup/alternate @@ -3586,6 +3590,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. spia_pedr= spia_peddr= + stack_guard_gap= [MM] + override the default stack gap protection. The value + is in page units and it defines how many pages prior + to (for stacks growing down) resp. after (for stacks + growing up) the main stack are reserved for no other + mapping. Default value is 256 pages. + stacktrace [FTRACE] Enabled the stack tracer on boot up. diff --git a/Documentation/mic/Makefile b/Documentation/mic/Makefile deleted file mode 100644 index a191d453badf..000000000000 --- a/Documentation/mic/Makefile +++ /dev/null @@ -1 +0,0 @@ -subdir-y := mpssd diff --git a/Documentation/mic/mpssd/Makefile b/Documentation/mic/mpssd/Makefile deleted file mode 100644 index 06871b0c08a6..000000000000 --- a/Documentation/mic/mpssd/Makefile +++ /dev/null @@ -1,21 +0,0 @@ -ifndef CROSS_COMPILE -# List of programs to build -hostprogs-$(CONFIG_X86_64) := mpssd - -mpssd-objs := mpssd.o sysfs.o - -# Tell kbuild to always build the programs -always := $(hostprogs-y) - -HOSTCFLAGS += -I$(objtree)/usr/include -I$(srctree)/tools/include - -ifdef DEBUG -HOSTCFLAGS += -DDEBUG=$(DEBUG) -endif - -HOSTLOADLIBES_mpssd := -lpthread - -install: - install mpssd /usr/sbin/mpssd - install micctrl /usr/sbin/micctrl -endif diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 2042261408b9..5f1ea84ed72b 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1413,11 +1413,20 @@ accept_ra_pinfo - BOOLEAN Functional default: enabled if accept_ra is enabled. disabled if accept_ra is disabled. +accept_ra_rt_info_min_plen - INTEGER + Minimum prefix length of Route Information in RA. + + Route Information w/ prefix smaller than this variable shall + be ignored. + + Functional default: 0 if accept_ra_rtr_pref is enabled. + -1 if accept_ra_rtr_pref is disabled. + accept_ra_rt_info_max_plen - INTEGER Maximum prefix length of Route Information in RA. - Route Information w/ prefix larger than or equal to this - variable shall be ignored. + Route Information w/ prefix larger than this variable shall + be ignored. Functional default: 0 if accept_ra_rtr_pref is enabled. -1 if accept_ra_rtr_pref is disabled. diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt deleted file mode 100644 index 54f10478e8e3..000000000000 --- a/Documentation/networking/netlink_mmap.txt +++ /dev/null @@ -1,332 +0,0 @@ -This file documents how to use memory mapped I/O with netlink. - -Author: Patrick McHardy <kaber@trash.net> - -Overview --------- - -Memory mapped netlink I/O can be used to increase throughput and decrease -overhead of unicast receive and transmit operations. Some netlink subsystems -require high throughput, these are mainly the netfilter subsystems -nfnetlink_queue and nfnetlink_log, but it can also help speed up large -dump operations of f.i. the routing database. - -Memory mapped netlink I/O used two circular ring buffers for RX and TX which -are mapped into the processes address space. - -The RX ring is used by the kernel to directly construct netlink messages into -user-space memory without copying them as done with regular socket I/O, -additionally as long as the ring contains messages no recvmsg() or poll() -syscalls have to be issued by user-space to get more message. - -The TX ring is used to process messages directly from user-space memory, the -kernel processes all messages contained in the ring using a single sendmsg() -call. - -Usage overview --------------- - -In order to use memory mapped netlink I/O, user-space needs three main changes: - -- ring setup -- conversion of the RX path to get messages from the ring instead of recvmsg() -- conversion of the TX path to construct messages into the ring - -Ring setup is done using setsockopt() to provide the ring parameters to the -kernel, then a call to mmap() to map the ring into the processes address space: - -- setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, ¶ms, sizeof(params)); -- setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, ¶ms, sizeof(params)); -- ring = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0) - -Usage of either ring is optional, but even if only the RX ring is used the -mapping still needs to be writable in order to update the frame status after -processing. - -Conversion of the reception path involves calling poll() on the file -descriptor, once the socket is readable the frames from the ring are -processed in order until no more messages are available, as indicated by -a status word in the frame header. - -On kernel side, in order to make use of memory mapped I/O on receive, the -originating netlink subsystem needs to support memory mapped I/O, otherwise -it will use an allocated socket buffer as usual and the contents will be - copied to the ring on transmission, nullifying most of the performance gains. -Dumps of kernel databases automatically support memory mapped I/O. - -Conversion of the transmit path involves changing message construction to -use memory from the TX ring instead of (usually) a buffer declared on the -stack and setting up the frame header appropriately. Optionally poll() can -be used to wait for free frames in the TX ring. - -Structured and definitions for using memory mapped I/O are contained in -<linux/netlink.h>. - -RX and TX rings ----------------- - -Each ring contains a number of continuous memory blocks, containing frames of -fixed size dependent on the parameters used for ring setup. - -Ring: [ block 0 ] - [ frame 0 ] - [ frame 1 ] - [ block 1 ] - [ frame 2 ] - [ frame 3 ] - ... - [ block n ] - [ frame 2 * n ] - [ frame 2 * n + 1 ] - -The blocks are only visible to the kernel, from the point of view of user-space -the ring just contains the frames in a continuous memory zone. - -The ring parameters used for setting up the ring are defined as follows: - -struct nl_mmap_req { - unsigned int nm_block_size; - unsigned int nm_block_nr; - unsigned int nm_frame_size; - unsigned int nm_frame_nr; -}; - -Frames are grouped into blocks, where each block is a continuous region of memory -and holds nm_block_size / nm_frame_size frames. The total number of frames in -the ring is nm_frame_nr. The following invariants hold: - -- frames_per_block = nm_block_size / nm_frame_size - -- nm_frame_nr = frames_per_block * nm_block_nr - -Some parameters are constrained, specifically: - -- nm_block_size must be a multiple of the architectures memory page size. - The getpagesize() function can be used to get the page size. - -- nm_frame_size must be equal or larger to NL_MMAP_HDRLEN, IOW a frame must be - able to hold at least the frame header - -- nm_frame_size must be smaller or equal to nm_block_size - -- nm_frame_size must be a multiple of NL_MMAP_MSG_ALIGNMENT - -- nm_frame_nr must equal the actual number of frames as specified above. - -When the kernel can't allocate physically continuous memory for a ring block, -it will fall back to use physically discontinuous memory. This might affect -performance negatively, in order to avoid this the nm_frame_size parameter -should be chosen to be as small as possible for the required frame size and -the number of blocks should be increased instead. - -Ring frames ------------- - -Each frames contain a frame header, consisting of a synchronization word and some -meta-data, and the message itself. - -Frame: [ header message ] - -The frame header is defined as follows: - -struct nl_mmap_hdr { - unsigned int nm_status; - unsigned int nm_len; - __u32 nm_group; - /* credentials */ - __u32 nm_pid; - __u32 nm_uid; - __u32 nm_gid; -}; - -- nm_status is used for synchronizing processing between the kernel and user- - space and specifies ownership of the frame as well as the operation to perform - -- nm_len contains the length of the message contained in the data area - -- nm_group specified the destination multicast group of message - -- nm_pid, nm_uid and nm_gid contain the netlink pid, UID and GID of the sending - process. These values correspond to the data available using SOCK_PASSCRED in - the SCM_CREDENTIALS cmsg. - -The possible values in the status word are: - -- NL_MMAP_STATUS_UNUSED: - RX ring: frame belongs to the kernel and contains no message - for user-space. Approriate action is to invoke poll() - to wait for new messages. - - TX ring: frame belongs to user-space and can be used for - message construction. - -- NL_MMAP_STATUS_RESERVED: - RX ring only: frame is currently used by the kernel for message - construction and contains no valid message yet. - Appropriate action is to invoke poll() to wait for - new messages. - -- NL_MMAP_STATUS_VALID: - RX ring: frame contains a valid message. Approriate action is - to process the message and release the frame back to - the kernel by setting the status to - NL_MMAP_STATUS_UNUSED or queue the frame by setting the - status to NL_MMAP_STATUS_SKIP. - - TX ring: the frame contains a valid message from user-space to - be processed by the kernel. After completing processing - the kernel will release the frame back to user-space by - setting the status to NL_MMAP_STATUS_UNUSED. - -- NL_MMAP_STATUS_COPY: - RX ring only: a message is ready to be processed but could not be - stored in the ring, either because it exceeded the - frame size or because the originating subsystem does - not support memory mapped I/O. Appropriate action is - to invoke recvmsg() to receive the message and release - the frame back to the kernel by setting the status to - NL_MMAP_STATUS_UNUSED. - -- NL_MMAP_STATUS_SKIP: - RX ring only: user-space queued the message for later processing, but - processed some messages following it in the ring. The - kernel should skip this frame when looking for unused - frames. - -The data area of a frame begins at a offset of NL_MMAP_HDRLEN relative to the -frame header. - -TX limitations --------------- - -As of Jan 2015 the message is always copied from the ring frame to an -allocated buffer due to unresolved security concerns. -See commit 4682a0358639b29cf ("netlink: Always copy on mmap TX."). - -Example -------- - -Ring setup: - - unsigned int block_size = 16 * getpagesize(); - struct nl_mmap_req req = { - .nm_block_size = block_size, - .nm_block_nr = 64, - .nm_frame_size = 16384, - .nm_frame_nr = 64 * block_size / 16384, - }; - unsigned int ring_size; - void *rx_ring, *tx_ring; - - /* Configure ring parameters */ - if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0) - exit(1); - if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0) - exit(1) - - /* Calculate size of each individual ring */ - ring_size = req.nm_block_nr * req.nm_block_size; - - /* Map RX/TX rings. The TX ring is located after the RX ring */ - rx_ring = mmap(NULL, 2 * ring_size, PROT_READ | PROT_WRITE, - MAP_SHARED, fd, 0); - if ((long)rx_ring == -1L) - exit(1); - tx_ring = rx_ring + ring_size: - -Message reception: - -This example assumes some ring parameters of the ring setup are available. - - unsigned int frame_offset = 0; - struct nl_mmap_hdr *hdr; - struct nlmsghdr *nlh; - unsigned char buf[16384]; - ssize_t len; - - while (1) { - struct pollfd pfds[1]; - - pfds[0].fd = fd; - pfds[0].events = POLLIN | POLLERR; - pfds[0].revents = 0; - - if (poll(pfds, 1, -1) < 0 && errno != -EINTR) - exit(1); - - /* Check for errors. Error handling omitted */ - if (pfds[0].revents & POLLERR) - <handle error> - - /* If no new messages, poll again */ - if (!(pfds[0].revents & POLLIN)) - continue; - - /* Process all frames */ - while (1) { - /* Get next frame header */ - hdr = rx_ring + frame_offset; - - if (hdr->nm_status == NL_MMAP_STATUS_VALID) { - /* Regular memory mapped frame */ - nlh = (void *)hdr + NL_MMAP_HDRLEN; - len = hdr->nm_len; - - /* Release empty message immediately. May happen - * on error during message construction. - */ - if (len == 0) - goto release; - } else if (hdr->nm_status == NL_MMAP_STATUS_COPY) { - /* Frame queued to socket receive queue */ - len = recv(fd, buf, sizeof(buf), MSG_DONTWAIT); - if (len <= 0) - break; - nlh = buf; - } else - /* No more messages to process, continue polling */ - break; - - process_msg(nlh); -release: - /* Release frame back to the kernel */ - hdr->nm_status = NL_MMAP_STATUS_UNUSED; - - /* Advance frame offset to next frame */ - frame_offset = (frame_offset + frame_size) % ring_size; - } - } - -Message transmission: - -This example assumes some ring parameters of the ring setup are available. -A single message is constructed and transmitted, to send multiple messages -at once they would be constructed in consecutive frames before a final call -to sendto(). - - unsigned int frame_offset = 0; - struct nl_mmap_hdr *hdr; - struct nlmsghdr *nlh; - struct sockaddr_nl addr = { - .nl_family = AF_NETLINK, - }; - - hdr = tx_ring + frame_offset; - if (hdr->nm_status != NL_MMAP_STATUS_UNUSED) - /* No frame available. Use poll() to avoid. */ - exit(1); - - nlh = (void *)hdr + NL_MMAP_HDRLEN; - - /* Build message */ - build_message(nlh); - - /* Fill frame header: length and status need to be set */ - hdr->nm_len = nlh->nlmsg_len; - hdr->nm_status = NL_MMAP_STATUS_VALID; - - if (sendto(fd, NULL, 0, 0, &addr, sizeof(addr)) < 0) - exit(1); - - /* Advance frame offset to next frame */ - frame_offset = (frame_offset + frame_size) % ring_size; diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 302b5ed616a6..35e17f748ca7 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -265,6 +265,13 @@ aio-nr can grow to. ============================================================== +mount-max: + +This denotes the maximum number of mounts that may exist +in a mount namespace. + +============================================================== + 2. /proc/sys/fs/binfmt_misc ---------------------------------------------------------- diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 5728779df1ab..e7018fc62ffa 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -825,14 +825,13 @@ via the /proc/sys interface: Each write syscall must fully contain the sysctl value to be written, and multiple writes on the same sysctl file descriptor will rewrite the sysctl value, regardless of file position. - 0 - (default) Same behavior as above, but warn about processes that - perform writes to a sysctl file descriptor when the file position - is not 0. - 1 - Respect file position when writing sysctl strings. Multiple writes - will append to the sysctl value buffer. Anything past the max length - of the sysctl value buffer will be ignored. Writes to numeric sysctl - entries must always be at file position 0 and the value must be - fully contained in the buffer sent in the write syscall. + 0 - Same behavior as above, but warn about processes that perform writes + to a sysctl file descriptor when the file position is not 0. + 1 - (default) Respect file position when writing sysctl strings. Multiple + writes will append to the sysctl value buffer. Anything past the max + length of the sysctl value buffer will be ignored. Writes to numeric + sysctl entries must always be at file position 0 and the value must + be fully contained in the buffer sent in the write syscall. ============================================================== @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 45 +SUBLEVEL = 84 EXTRAVERSION = NAME = Blurry Fish Butt @@ -146,7 +146,7 @@ PHONY += $(MAKECMDGOALS) sub-make $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make @: -sub-make: FORCE +sub-make: $(Q)$(MAKE) -C $(KBUILD_OUTPUT) KBUILD_SRC=$(CURDIR) \ -f $(CURDIR)/Makefile $(filter-out _all sub-make,$(MAKECMDGOALS)) @@ -619,6 +619,9 @@ include arch/$(SRCARCH)/Makefile KBUILD_CFLAGS += $(call cc-option,-fno-delete-null-pointer-checks,) KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,) KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,) +KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) +KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) +KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context) ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os @@ -633,6 +636,12 @@ endif # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0) +# check for 'asm goto' +ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y) + KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO + KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO +endif + ifdef CONFIG_READABLE_ASM # Disable optimizations that make assembler listings hard to read. # reorder blocks reorders the control in the function @@ -788,12 +797,6 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=date-time) # use the deterministic mode of AR if available KBUILD_ARFLAGS := $(call ar-option,D) -# check for 'asm goto' -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y) - KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO - KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO -endif - include scripts/Makefile.kasan include scripts/Makefile.extrawarn @@ -1000,7 +1003,7 @@ prepare1: prepare2 $(version_h) include/generated/utsrelease.h \ archprepare: archheaders archscripts prepare1 scripts_basic -prepare0: archprepare FORCE +prepare0: archprepare $(Q)$(MAKE) $(build)=. # All the preparing.. @@ -1045,7 +1048,7 @@ INSTALL_FW_PATH=$(INSTALL_MOD_PATH)/lib/firmware export INSTALL_FW_PATH PHONY += firmware_install -firmware_install: FORCE +firmware_install: @mkdir -p $(objtree)/firmware $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.fwinst obj=firmware __fw_install @@ -1065,7 +1068,7 @@ PHONY += archscripts archscripts: PHONY += __headers -__headers: $(version_h) scripts_basic asm-generic archheaders archscripts FORCE +__headers: $(version_h) scripts_basic asm-generic archheaders archscripts $(Q)$(MAKE) $(build)=scripts build_unifdef PHONY += headers_install_all diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg index f10371a981b7..30e01074f64a 100644 --- a/android/configs/android-base.cfg +++ b/android/configs/android-base.cfg @@ -1,17 +1,19 @@ # KEEP ALPHABETICALLY SORTED # CONFIG_DEVKMEM is not set # CONFIG_DEVMEM is not set +# CONFIG_FHANDLE is not set # CONFIG_INET_LRO is not set # CONFIG_MODULES is not set # CONFIG_OABI_COMPAT is not set # CONFIG_SYSVIPC is not set +# CONFIG_USELIB is not set CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_DEVICES=binder,hwbinder,vndbinder CONFIG_ANDROID_BINDER_IPC=y CONFIG_ANDROID_LOW_MEMORY_KILLER=y CONFIG_ARMV8_DEPRECATED=y CONFIG_ASHMEM=y CONFIG_AUDIT=y -CONFIG_BLK_DEV_DM=y CONFIG_BLK_DEV_INITRD=y CONFIG_CGROUPS=y CONFIG_CGROUP_CPUACCT=y @@ -19,14 +21,15 @@ CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_SCHED=y CONFIG_CP15_BARRIER_EMULATION=y -CONFIG_DM_CRYPT=y -CONFIG_DM_VERITY=y -CONFIG_DM_VERITY_FEC=y +CONFIG_DEFAULT_SECURITY_SELINUX=y CONFIG_EMBEDDED=y CONFIG_FB=y CONFIG_HARDENED_USERCOPY=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y CONFIG_INET6_AH=y +CONFIG_INET6_DIAG_DESTROY=y CONFIG_INET6_ESP=y CONFIG_INET6_IPCOMP=y CONFIG_INET=y @@ -42,7 +45,6 @@ CONFIG_IPV6=y CONFIG_IPV6_MIP6=y CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_OPTIMISTIC_DAD=y -CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_IP_ADVANCED_ROUTER=y @@ -64,6 +66,9 @@ CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_TARGET_NETMAP=y CONFIG_IP_NF_TARGET_REDIRECT=y CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y CONFIG_NET=y CONFIG_NETDEVICES=y CONFIG_NETFILTER=y @@ -141,9 +146,9 @@ CONFIG_PREEMPT=y CONFIG_PROFILING=y CONFIG_QFMT_V2=y CONFIG_QUOTA=y +CONFIG_QUOTACTL=y CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_QUOTA_TREE=y -CONFIG_QUOTACTL=y CONFIG_RANDOMIZE_BASE=y CONFIG_RTC_CLASS=y CONFIG_RT_GROUP_SCHED=y @@ -157,16 +162,16 @@ CONFIG_STAGING=y CONFIG_SWP_EMULATION=y CONFIG_SYNC=y CONFIG_TUN=y -CONFIG_UID_CPUTIME=y +CONFIG_UID_SYS_STATS=y CONFIG_UNIX=y -CONFIG_USB_GADGET=y CONFIG_USB_CONFIGFS=y +CONFIG_USB_CONFIGFS_F_ACC=y +CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y CONFIG_USB_CONFIGFS_F_FS=y +CONFIG_USB_CONFIGFS_F_MIDI=y CONFIG_USB_CONFIGFS_F_MTP=y CONFIG_USB_CONFIGFS_F_PTP=y -CONFIG_USB_CONFIGFS_F_ACC=y -CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y CONFIG_USB_CONFIGFS_UEVENT=y -CONFIG_USB_CONFIGFS_F_MIDI=y +CONFIG_USB_GADGET=y CONFIG_USB_OTG_WAKELOCK=y CONFIG_XFRM_USER=y diff --git a/android/configs/android-recommended.cfg b/android/configs/android-recommended.cfg index 405bf5e3d22b..6fd099015525 100644 --- a/android/configs/android-recommended.cfg +++ b/android/configs/android-recommended.cfg @@ -7,15 +7,21 @@ # CONFIG_PM_WAKELOCKS_GC is not set # CONFIG_VT is not set CONFIG_ANDROID_TIMED_GPIO=y +CONFIG_ARM64_SW_TTBR0_PAN=y CONFIG_ARM_KERNMEM_PERMS=y CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_BLK_DEV_DM=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 CONFIG_CC_STACKPROTECTOR_STRONG=y CONFIG_COMPACTION=y +CONFIG_CPU_SW_DOMAIN_PAN=y CONFIG_DEBUG_RODATA=y +CONFIG_DM_CRYPT=y CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y CONFIG_DRAGONRISE_FF=y CONFIG_ENABLE_DEFAULT_TRACERS=y CONFIG_EXT4_FS=y @@ -91,6 +97,7 @@ CONFIG_LOGIRUMBLEPAD2_FF=y CONFIG_LOGITECH_FF=y CONFIG_MD=y CONFIG_MEDIA_SUPPORT=y +CONFIG_MEMORY_STATE_TIME=y CONFIG_MSDOS_FS=y CONFIG_PANIC_TIMEOUT=0 CONFIG_PANTHERLORD_FF=y @@ -120,7 +127,6 @@ CONFIG_TIMER_STATS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_UHID=y -CONFIG_MEMORY_STATE_TIME=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_HIDDEV=y diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 6cc08166ff00..63f06a2b1f7f 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1188,8 +1188,10 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur))) return -EFAULT; - err = 0; - err |= put_user(status, ustatus); + err = put_user(status, ustatus); + if (ret < 0) + return err ? err : ret; + err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec); err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec); err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec); diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index a36e8601114d..d5da2115d78a 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -26,7 +26,9 @@ static inline void __delay(unsigned long loops) " lp 1f \n" " nop \n" "1: \n" - : : "r"(loops)); + : + : "r"(loops) + : "lp_count"); } extern void __bad_udelay(void); diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h index b5ff87e6f4b7..aee1a77934cf 100644 --- a/arch/arc/include/asm/entry-arcv2.h +++ b/arch/arc/include/asm/entry-arcv2.h @@ -16,6 +16,7 @@ ; ; Now manually save: r12, sp, fp, gp, r25 + PUSH r30 PUSH r12 ; Saving pt_regs->sp correctly requires some extra work due to the way @@ -72,6 +73,7 @@ POPAX AUX_USER_SP 1: POP r12 + POP r30 .endm diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 69095da1fcfd..47111d565a95 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -84,7 +84,7 @@ struct pt_regs { unsigned long fp; unsigned long sp; /* user/kernel sp depending on where we came from */ - unsigned long r12; + unsigned long r12, r30; /*------- Below list auto saved by h/w -----------*/ unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11; diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index abd961f3e763..5f69c3bd59bb 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; + /* clear any remanants of delay slot */ if (delay_mode(regs)) { - regs->ret = regs->bta; + regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; } else { regs->ret += state.instr_len; diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index 2e06d56e987b..cf4ae6958240 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -64,7 +64,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index c1bff8a87485..4e037366a62f 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -494,11 +494,13 @@ dtb-$(CONFIG_SOC_OMAP5) += \ dtb-$(CONFIG_SOC_DRA7XX) += \ dra7-evm.dtb \ dra7-evm-lcd-lg.dtb \ + dra7-evm-fpd-lg.dtb \ dra7-evm-lcd-lg-late-attach.dtb \ dra7-evm-lcd-lg-late-attach-no-map.dtb \ dra7-evm-lcd-osd.dtb \ dra7-evm-lcd-osd101t2587.dtb \ dra7-evm-lcd-osd-late-attach.dtb \ + dra7-evm-fpd-auo-g101evn01.0.dtb \ dra7-evm-vision.dtb \ dra7-evm-robust-rvc.dtb \ dra7-evm-early-video.dtb \ @@ -516,6 +518,7 @@ dtb-$(CONFIG_SOC_DRA7XX) += \ dra72-evm-lcd-lg.dtb \ dra72-evm-lcd-osd.dtb \ dra72-evm-lcd-osd101t2587.dtb \ + dra72-evm-fpd-lg.dtb \ dra72-evm-revc.dtb \ dra72-evm-revc-lcd-osd101t2045.dtb \ dra72-evm-revc-lcd-osd101t2587.dtb \ @@ -524,7 +527,9 @@ dtb-$(CONFIG_SOC_DRA7XX) += \ dra71-evm.dtb \ dra71-evm-lcd-auo-g101evn01.0.dtb \ dra71-evm-robust-rvc.dtb \ - dra71-evm-early-video.dtb + dra71-evm-early-video.dtb \ + dra76-evm.dtb \ + dra76-evm-fpd-auo-g101evn01.0.dtb dtb-$(CONFIG_ARCH_ORION5X) += \ orion5x-lacie-d2-network.dtb \ orion5x-lacie-ethernet-disk-mini-v2.dtb \ diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index cd316021d6ce..6c1b45c1af66 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -89,7 +89,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pca0_pins>; interrupt-parent = <&gpio0>; - interrupts = <18 IRQ_TYPE_EDGE_FALLING>; + interrupts = <18 IRQ_TYPE_LEVEL_LOW>; gpio-controller; #gpio-cells = <2>; interrupt-controller; @@ -101,7 +101,7 @@ compatible = "nxp,pca9555"; pinctrl-names = "default"; interrupt-parent = <&gpio0>; - interrupts = <18 IRQ_TYPE_EDGE_FALLING>; + interrupts = <18 IRQ_TYPE_LEVEL_LOW>; gpio-controller; #gpio-cells = <2>; interrupt-controller; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index e74df327cdd3..20618a897c99 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -122,6 +122,8 @@ uart1: serial@f8020000 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart1_default>; + atmel,use-dma-rx; + atmel,use-dma-tx; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index f3e2b96c06a3..0bd325c314e1 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -162,9 +162,10 @@ }; adc0: adc@f8018000 { + atmel,adc-vref = <3300>; + atmel,adc-channels-used = <0xfe>; pinctrl-0 = < &pinctrl_adc0_adtrg - &pinctrl_adc0_ad0 &pinctrl_adc0_ad1 &pinctrl_adc0_ad2 &pinctrl_adc0_ad3 @@ -172,8 +173,6 @@ &pinctrl_adc0_ad5 &pinctrl_adc0_ad6 &pinctrl_adc0_ad7 - &pinctrl_adc0_ad8 - &pinctrl_adc0_ad9 >; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index da84e65b56ef..e27024cdf48b 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -110,6 +110,8 @@ }; usart3: serial@fc00c000 { + atmel,use-dma-rx; + atmel,use-dma-tx; status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 6f50f672efbd..de8ac998604d 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -54,14 +54,14 @@ timer@0200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x0200 0x100>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; clocks = <&clk_periph>; }; local-timer@0600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0x0600 0x100>; - interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 13 IRQ_TYPE_EDGE_RISING>; clocks = <&clk_periph>; }; diff --git a/arch/arm/boot/dts/dra7-evm-common.dtsi b/arch/arm/boot/dts/dra7-evm-common.dtsi new file mode 100644 index 000000000000..2bbc04791628 --- /dev/null +++ b/arch/arm/boot/dts/dra7-evm-common.dtsi @@ -0,0 +1,393 @@ +/* + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/clk/ti-dra7-atl.h> +#include <dt-bindings/input/input.h> + +/ { + aliases { + display0 = &hdmi0; + sound0 = &sound0; + sound1 = &hdmi; + }; + + chosen { + stdout-path = &uart1; + }; + + sound0: sound0 { + compatible = "simple-audio-card"; + simple-audio-card,name = "DRA7xx-EVM"; + simple-audio-card,widgets = + "Headphone", "Headphone Jack", + "Line", "Line Out", + "Microphone", "Mic Jack", + "Line", "Line In"; + simple-audio-card,routing = + "Headphone Jack", "HPLOUT", + "Headphone Jack", "HPROUT", + "Line Out", "LLOUT", + "Line Out", "RLOUT", + "MIC3L", "Mic Jack", + "MIC3R", "Mic Jack", + "Mic Jack", "Mic Bias", + "LINE1L", "Line In", + "LINE1R", "Line In"; + simple-audio-card,format = "dsp_b"; + simple-audio-card,bitclock-master = <&sound0_master>; + simple-audio-card,frame-master = <&sound0_master>; + simple-audio-card,bitclock-inversion; + + sound0_master: simple-audio-card,cpu { + sound-dai = <&mcasp3>; + system-clock-frequency = <11289600>; + }; + + simple-audio-card,codec { + sound-dai = <&tlv320aic3106>; + clocks = <&atl_clkin2_ck>; + }; + }; + + extcon_usb1: extcon_usb1 { + compatible = "linux,extcon-usb-gpio"; + id-gpio = <&pcf_gpio_21 1 GPIO_ACTIVE_HIGH>; + }; + + leds { + compatible = "gpio-leds"; + led0 { + label = "dra7:usr1"; + gpios = <&pcf_lcd 4 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + + led1 { + label = "dra7:usr2"; + gpios = <&pcf_lcd 5 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + + led2 { + label = "dra7:usr3"; + gpios = <&pcf_lcd 6 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + + led3 { + label = "dra7:usr4"; + gpios = <&pcf_lcd 7 GPIO_ACTIVE_LOW>; + default-state = "off"; + }; + }; + + gpio_keys { + compatible = "gpio-keys"; + #address-cells = <1>; + #size-cells = <0>; + autorepeat; + + USER1 { + label = "btnUser1"; + linux,code = <BTN_0>; + gpios = <&pcf_lcd 2 GPIO_ACTIVE_LOW>; + }; + + USER2 { + label = "btnUser2"; + linux,code = <BTN_1>; + gpios = <&pcf_lcd 3 GPIO_ACTIVE_LOW>; + }; + }; + + hdmi0: connector@1 { + compatible = "hdmi-connector"; + label = "hdmi"; + + type = "a"; + + port { + hdmi_connector_in: endpoint { + remote-endpoint = <&tpd12s015_out>; + }; + }; + }; + + tpd12s015: encoder@1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + tpd12s015_in: endpoint { + remote-endpoint = <&hdmi_out>; + }; + }; + + port@1 { + reg = <1>; + + tpd12s015_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; + }; + }; + }; + + clk_ov10633_fixed: clk_ov10633_fixed { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <24000000>; + }; +}; + +&dra7_pmx_core { + dcan1_pins_default: dcan1_pins_default { + pinctrl-single,pins = < + 0x3d0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* dcan1_tx */ + 0x418 (PULL_UP | MUX_MODE1) /* wakeup0.dcan1_rx */ + >; + }; + + dcan1_pins_sleep: dcan1_pins_sleep { + pinctrl-single,pins = < + 0x3d0 (MUX_MODE15 | PULL_UP) /* dcan1_tx.off */ + 0x418 (MUX_MODE15 | PULL_UP) /* wakeup0.off */ + >; + }; +}; + +&i2c3 { + status = "okay"; + clock-frequency = <400000>; +}; + +&mcspi1 { + status = "okay"; +}; + +&mcspi2 { + status = "okay"; +}; + +&uart1 { + status = "okay"; + interrupts-extended = <&crossbar_mpu GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>, + <&dra7_pmx_core 0x3e0>; +}; + +&uart2 { + status = "okay"; +}; + +&uart3 { + status = "okay"; +}; + +&qspi { + status = "okay"; + + spi-max-frequency = <76800000>; + m25p80@0 { + compatible = "s25fl256s1"; + spi-max-frequency = <76800000>; + reg = <0>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <4>; + #address-cells = <1>; + #size-cells = <1>; + + /* MTD partition table. + * The ROM checks the first four physical blocks + * for a valid file to boot and the flash here is + * 64KiB block size. + */ + partition@0 { + label = "QSPI.SPL"; + reg = <0x00000000 0x000040000>; + }; + partition@1 { + label = "QSPI.u-boot"; + reg = <0x00040000 0x00100000>; + }; + partition@2 { + label = "QSPI.u-boot-spl-os"; + reg = <0x00140000 0x00080000>; + }; + partition@3 { + label = "QSPI.u-boot-env"; + reg = <0x001c0000 0x00010000>; + }; + partition@4 { + label = "QSPI.u-boot-env.backup1"; + reg = <0x001d0000 0x0010000>; + }; + partition@5 { + label = "QSPI.kernel"; + reg = <0x001e0000 0x0800000>; + }; + partition@6 { + label = "QSPI.file-system"; + reg = <0x009e0000 0x01620000>; + }; + }; +}; + +&omap_dwc3_1 { + extcon = <&extcon_usb1>; +}; + +&usb1 { + dr_mode = "otg"; +}; + +&usb2 { + dr_mode = "host"; +}; + +&dcan1 { + status = "ok"; + pinctrl-names = "default", "sleep", "active"; + pinctrl-0 = <&dcan1_pins_sleep>; + pinctrl-1 = <&dcan1_pins_sleep>; + pinctrl-2 = <&dcan1_pins_default>; +}; + +&atl { + assigned-clocks = <&abe_dpll_sys_clk_mux>, + <&atl_gfclk_mux>, + <&dpll_abe_ck>, + <&dpll_abe_m2x2_ck>, + <&atl_clkin1_ck>, + <&atl_clkin2_ck>; + assigned-clock-parents = <&sys_clkin2>, <&dpll_abe_m2_ck>; + assigned-clock-rates = <0>, <0>, <180633600>, <361267200>, + <11289600>, <11289600>; + + status = "okay"; + + atl2 { + bws = <DRA7_ATL_WS_MCASP2_FSX>; + aws = <DRA7_ATL_WS_MCASP3_FSX>; + }; +}; + +&mcasp3 { + #sound-dai-cells = <0>; + + assigned-clocks = <&mcasp3_ahclkx_mux>; + assigned-clock-parents = <&atl_clkin2_ck>; + + status = "okay"; + + op-mode = <0>; /* MCASP_IIS_MODE */ + tdm-slots = <2>; + /* 4 serializer */ + serial-dir = < /* 0: INACTIVE, 1: TX, 2: RX */ + 1 2 0 0 + >; + tx-num-evt = <32>; + rx-num-evt = <32>; +}; + +&mailbox5 { + status = "okay"; + mbox_ipu1_ipc3x: mbox_ipu1_ipc3x { + status = "okay"; + }; + mbox_dsp1_ipc3x: mbox_dsp1_ipc3x { + status = "okay"; + }; +}; + +&mailbox6 { + status = "okay"; + mbox_ipu2_ipc3x: mbox_ipu2_ipc3x { + status = "okay"; + }; + mbox_dsp2_ipc3x: mbox_dsp2_ipc3x { + status = "okay"; + }; +}; + +&mmu0_dsp1 { + status = "okay"; +}; + +&mmu1_dsp1 { + status = "okay"; +}; + +&mmu0_dsp2 { + status = "okay"; +}; + +&mmu1_dsp2 { + status = "okay"; +}; + +&mmu_ipu1 { + status = "okay"; +}; + +&mmu_ipu2 { + status = "okay"; +}; + +&ipu2 { + status = "okay"; + memory-region = <&ipu2_cma_pool>; + mboxes = <&mailbox6 &mbox_ipu2_ipc3x>; + timers = <&timer3>; + watchdog-timers = <&timer4>, <&timer9>; +}; + +&ipu1 { + status = "okay"; + memory-region = <&ipu1_cma_pool>; + mboxes = <&mailbox5 &mbox_ipu1_ipc3x>; + timers = <&timer11>; + watchdog-timers = <&timer7>, <&timer8>; +}; + +&dsp1 { + status = "okay"; + memory-region = <&dsp1_cma_pool>; + mboxes = <&mailbox5 &mbox_dsp1_ipc3x>; + timers = <&timer5>; + watchdog-timers = <&timer10>; +}; + +&dsp2 { + status = "okay"; + memory-region = <&dsp2_cma_pool>; + mboxes = <&mailbox6 &mbox_dsp2_ipc3x>; + timers = <&timer6>; + watchdog-timers = <&timer13>; +}; + +&vip1 { + status = "okay"; +}; + +&hdmi { + status = "okay"; + + port { + hdmi_out: endpoint { + remote-endpoint = <&tpd12s015_in>; + }; + }; +}; + +&pcie1_rc { + status = "okay"; +}; diff --git a/arch/arm/boot/dts/dra7-evm-fpd-auo-g101evn01.0.dts b/arch/arm/boot/dts/dra7-evm-fpd-auo-g101evn01.0.dts new file mode 100644 index 000000000000..64e79754bb22 --- /dev/null +++ b/arch/arm/boot/dts/dra7-evm-fpd-auo-g101evn01.0.dts @@ -0,0 +1,37 @@ +#include "dra7-evm.dts" +#include "dra7x-evm-fpd-auo-g101evn01.0.dtsi" + +/ { + aliases { + display0 = &fpd_disp; + display1 = &hdmi0; + }; +}; + +&dss { + ports { + status = "ok"; + }; +}; + +&disp_ser { + status = "ok"; + ranges = <0x0 0x2d>; +}; + +/* Tie the end points of DSS and FPDLink together */ + +&fpd_in { + remote-endpoint = <&dpi_out3>; +}; + +&dpi_out3 { + remote-endpoint = <&fpd_in>; +}; + +&lcd_fpd { + enable-gpios = <&pcf_gpio_21 0 GPIO_ACTIVE_LOW>; + /* P0, SEL_GPMC_AD_VID_S0 */ + + status = "ok"; +}; diff --git a/arch/arm/boot/dts/dra7-evm-fpd-lg.dts b/arch/arm/boot/dts/dra7-evm-fpd-lg.dts new file mode 100644 index 000000000000..b8df0766ecff --- /dev/null +++ b/arch/arm/boot/dts/dra7-evm-fpd-lg.dts @@ -0,0 +1,38 @@ +#include "dra7-evm.dts" +#include "dra7x-evm-fpd-lg.dtsi" + +/ { + aliases { + display0 = &fpd_disp; + display1 = &hdmi0; + }; +}; + +&dss { + ports { + status = "ok"; + }; +}; + +&disp_ser { + status = "ok"; + ranges = <0x2c 0x2c>, + <0x1c 0x1c>; +}; + +/* Tie the end points of DSS and FPDLink together */ + +&fpd_in { + remote-endpoint = <&dpi_out3>; +}; + +&dpi_out3 { + remote-endpoint = <&fpd_in>; +}; + +&lcd_fpd { + enable-gpios = <&pcf_gpio_21 0 GPIO_ACTIVE_LOW>; + /* P0, SEL_GPMC_AD_VID_S0 */ + + status = "ok"; +}; diff --git a/arch/arm/boot/dts/dra7-evm-lcd-lg.dts b/arch/arm/boot/dts/dra7-evm-lcd-lg.dts index f67beaa8ff01..2b09d3a8839f 100644 --- a/arch/arm/boot/dts/dra7-evm-lcd-lg.dts +++ b/arch/arm/boot/dts/dra7-evm-lcd-lg.dts @@ -14,3 +14,11 @@ interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; }; + +/* Uncomment the below lines to enable the FPDLink display */ + +/* +&lcd_fpd { + status = "okay"; +}; +*/ diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index c2af973a17c2..4a8697306e7a 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -8,9 +8,7 @@ /dts-v1/; #include "dra74x.dtsi" -#include <dt-bindings/gpio/gpio.h> -#include <dt-bindings/clk/ti-dra7-atl.h> -#include <dt-bindings/input/input.h> +#include "dra7-evm-common.dtsi" / { model = "TI DRA742"; @@ -56,13 +54,17 @@ }; aliases { - display0 = &hdmi0; - display1 = &fpd_disp; - sound0 = &snd0; - sound1 = &hdmi; i2c7 = &disp_ser; }; + evm_1v8_sw: fixedregulator-evm_1v8 { + compatible = "regulator-fixed"; + regulator-name = "evm_1v8"; + vin-supply = <&smps9_reg>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + evm_3v3_sd: fixedregulator-sd { compatible = "regulator-fixed"; regulator-name = "evm_3v3_sd"; @@ -99,16 +101,6 @@ enable-active-high; }; - extcon_usb1: extcon_usb1 { - compatible = "linux,extcon-usb-gpio"; - id-gpio = <&pcf_gpio_21 1 GPIO_ACTIVE_HIGH>; - }; - - extcon_usb2: extcon_usb2 { - compatible = "linux,extcon-usb-gpio"; - id-gpio = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>; - }; - vtt_fixed: fixedregulator-vtt { compatible = "regulator-fixed"; regulator-name = "vtt_fixed"; @@ -121,151 +113,28 @@ gpio = <&gpio7 11 GPIO_ACTIVE_HIGH>; }; - snd0: sound@0 { - compatible = "simple-audio-card"; - simple-audio-card,name = "DRA7xx-EVM"; - simple-audio-card,widgets = - "Headphone", "Headphone Jack", - "Line", "Line Out", - "Microphone", "Mic Jack", - "Line", "Line In"; - simple-audio-card,routing = - "Headphone Jack", "HPLOUT", - "Headphone Jack", "HPROUT", - "Line Out", "LLOUT", - "Line Out", "RLOUT", - "MIC3L", "Mic Jack", - "MIC3R", "Mic Jack", - "Mic Jack", "Mic Bias", - "LINE1L", "Line In", - "LINE1R", "Line In"; - simple-audio-card,format = "dsp_b"; - simple-audio-card,bitclock-master = <&sound0_master>; - simple-audio-card,frame-master = <&sound0_master>; - simple-audio-card,bitclock-inversion; - - sound0_master: simple-audio-card,cpu { - sound-dai = <&mcasp3>; - system-clock-frequency = <11289600>; - }; - - simple-audio-card,codec { - sound-dai = <&tlv320aic3106>; - clocks = <&atl_clkin2_ck>; - }; - }; - - leds { - compatible = "gpio-leds"; - led@0 { - label = "dra7:usr1"; - gpios = <&pcf_lcd 4 GPIO_ACTIVE_LOW>; - default-state = "off"; - }; - - led@1 { - label = "dra7:usr2"; - gpios = <&pcf_lcd 5 GPIO_ACTIVE_LOW>; - default-state = "off"; - }; - - led@2 { - label = "dra7:usr3"; - gpios = <&pcf_lcd 6 GPIO_ACTIVE_LOW>; - default-state = "off"; - }; - - led@3 { - label = "dra7:usr4"; - gpios = <&pcf_lcd 7 GPIO_ACTIVE_LOW>; - default-state = "off"; - }; - }; - - gpio_keys { - compatible = "gpio-keys"; - #address-cells = <1>; - #size-cells = <0>; - autorepeat; - - USER1 { - label = "btnUser1"; - linux,code = <BTN_0>; - gpios = <&pcf_lcd 2 GPIO_ACTIVE_LOW>; - }; - - USER2 { - label = "btnUser2"; - linux,code = <BTN_1>; - gpios = <&pcf_lcd 3 GPIO_ACTIVE_LOW>; - }; - }; - - hdmi0: connector@1 { - compatible = "hdmi-connector"; - label = "hdmi"; - - type = "a"; - - port { - hdmi_connector_in: endpoint { - remote-endpoint = <&tpd12s015_out>; - }; - }; + extcon_usb2: extcon_usb2 { + compatible = "linux,extcon-usb-gpio"; + id-gpio = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>; }; - tpd12s015: encoder@1 { - compatible = "ti,dra7evm-tpd12s015"; - - pinctrl-names = "i2c", "ddc"; - pinctrl-0 = <&hdmi_i2c_sel_pin &hdmi_i2c_pins_i2c>; - pinctrl-1 = <&hdmi_i2c_sel_pin &hdmi_i2c_pins_ddc>; - - ddc-i2c-bus = <&i2c2>; - mcasp-gpio = <&mcasp8>; - - gpios = <&pcf_hdmi 4 0>, /* P4, CT CP HPD */ - <&pcf_hdmi 5 0>, /* P5, LS OE */ - <&gpio7 12 0>; /* gpio7_12/sp1_cs2, HPD */ - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; +}; - tpd12s015_in: endpoint@0 { - remote-endpoint = <&hdmi_out>; - }; - }; +&tpd12s015 { + compatible = "ti,dra7evm-tpd12s015"; + pinctrl-names = "i2c", "ddc"; + pinctrl-0 = <&hdmi_i2c_sel_pin &hdmi_i2c_pins_i2c>; + pinctrl-1 = <&hdmi_i2c_sel_pin &hdmi_i2c_pins_ddc>; - port@1 { - reg = <1>; + gpios = <&pcf_hdmi 4 GPIO_ACTIVE_HIGH>, /* P4, CT CP HPD */ + <&pcf_hdmi 5 GPIO_ACTIVE_HIGH>, /* P5, LS OE */ + <&gpio7 12 GPIO_ACTIVE_HIGH>; /* gpio7_12/sp1_cs2, HPD */ - tpd12s015_out: endpoint@0 { - remote-endpoint = <&hdmi_connector_in>; - }; - }; - }; - }; + ddc-i2c-bus = <&i2c2>; + mcasp-gpio = <&mcasp8>; }; &dra7_pmx_core { - dcan1_pins_default: dcan1_pins_default { - pinctrl-single,pins = < - 0x3d0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* dcan1_tx */ - 0x418 (PULL_UP | MUX_MODE1) /* wakeup0.dcan1_rx */ - >; - }; - - dcan1_pins_sleep: dcan1_pins_sleep { - pinctrl-single,pins = < - 0x3d0 (MUX_MODE15 | PULL_UP) /* dcan1_tx.off */ - 0x418 (MUX_MODE15 | PULL_UP) /* wakeup0.off */ - >; - }; - hdmi_i2c_sel_pin: pinmux_hdmi_i2c_sel_pin { pinctrl-single,pins = < /* this pin is used as a GPIO via mcasp */ @@ -758,6 +627,8 @@ tps659038: tps659038@58 { compatible = "ti,tps659038"; reg = <0x58>; + ti,palmas-override-powerhold; + ti,system-power-controller; tps659038_pmic { compatible = "ti,tps659038-pmic"; @@ -978,59 +849,10 @@ i2c_p3_exp: &i2c2 { #address-cells = <1>; #size-cells = <0>; - ranges = <0x2c 0x2c>, - <0x1c 0x1c>; - - disp_des: deserializer@2c { - compatible = "ti,ds90uh928q"; - reg = <0x2c>; - slave-mode; - }; - - /* TLC chip for LCD panel power and backlight */ - fpd_disp: tlc59108@1c { - status = "disabled"; - reg = <0x1c>; - compatible = "ti,tlc59108-fpddisp"; - enable-gpios = <&pcf_gpio_21 0 GPIO_ACTIVE_LOW>; - /* P0, SEL_GPMC_AD_VID_S0 */ - - port@lcd3 { - fpd_in: endpoint { - remote-endpoint = <&dpi_out3>; - }; - }; - }; + status = "disabled"; }; }; -&i2c3 { - status = "okay"; - clock-frequency = <400000>; -}; - -&mcspi1 { - status = "okay"; -}; - -&mcspi2 { - status = "okay"; -}; - -&uart1 { - status = "okay"; - interrupts-extended = <&crossbar_mpu GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>, - <&dra7_pmx_core 0x3e0>; -}; - -&uart2 { - status = "okay"; -}; - -&uart3 { - status = "okay"; -}; - &mmc1 { status = "okay"; vmmc-supply = <&evm_3v3_sd>; @@ -1088,7 +910,7 @@ i2c_p3_exp: &i2c2 { #address-cells = <1>; #size-cells = <0>; - wlcore: wlcore@0 { + wlcore: wlcore@2 { compatible = "ti,wl1835"; reg = <2>; interrupt-parent = <&gpio5>; @@ -1116,75 +938,10 @@ i2c_p3_exp: &i2c2 { vdd-supply = <&smps7_reg>; }; -&pcie1_rc { - status = "okay"; -}; - -&qspi { - status = "okay"; - - spi-max-frequency = <76800000>; - m25p80@0 { - compatible = "s25fl256s1"; - spi-max-frequency = <76800000>; - reg = <0>; - spi-tx-bus-width = <1>; - spi-rx-bus-width = <4>; - #address-cells = <1>; - #size-cells = <1>; - - /* MTD partition table. - * The ROM checks the first four physical blocks - * for a valid file to boot and the flash here is - * 64KiB block size. - */ - partition@0 { - label = "QSPI.SPL"; - reg = <0x00000000 0x000040000>; - }; - partition@1 { - label = "QSPI.u-boot"; - reg = <0x00040000 0x00100000>; - }; - partition@2 { - label = "QSPI.u-boot-spl-os"; - reg = <0x00140000 0x00080000>; - }; - partition@3 { - label = "QSPI.u-boot-env"; - reg = <0x001c0000 0x00010000>; - }; - partition@4 { - label = "QSPI.u-boot-env.backup1"; - reg = <0x001d0000 0x0010000>; - }; - partition@5 { - label = "QSPI.kernel"; - reg = <0x001e0000 0x0800000>; - }; - partition@6 { - label = "QSPI.file-system"; - reg = <0x009e0000 0x01620000>; - }; - }; -}; - -&omap_dwc3_1 { - extcon = <&extcon_usb1>; -}; - &omap_dwc3_2 { extcon = <&extcon_usb2>; }; -&usb1 { - dr_mode = "otg"; -}; - -&usb2 { - dr_mode = "host"; -}; - &elm { status = "okay"; }; @@ -1301,131 +1058,6 @@ i2c_p3_exp: &i2c2 { dual_emac_res_vlan = <2>; }; -&dcan1 { - status = "ok"; - pinctrl-names = "default", "sleep", "active"; - pinctrl-0 = <&dcan1_pins_sleep>; - pinctrl-1 = <&dcan1_pins_sleep>; - pinctrl-2 = <&dcan1_pins_default>; -}; - -&atl { - assigned-clocks = <&abe_dpll_sys_clk_mux>, - <&atl_gfclk_mux>, - <&dpll_abe_ck>, - <&dpll_abe_m2x2_ck>, - <&atl_clkin1_ck>, - <&atl_clkin2_ck>; - assigned-clock-parents = <&sys_clkin2>, <&dpll_abe_m2_ck>; - assigned-clock-rates = <0>, <0>, <180633600>, <361267200>, - <11289600>, <11289600>; - - status = "okay"; - - atl2 { - bws = <DRA7_ATL_WS_MCASP2_FSX>; - aws = <DRA7_ATL_WS_MCASP3_FSX>; - }; -}; - -&mcasp3 { - #sound-dai-cells = <0>; - - assigned-clocks = <&mcasp3_ahclkx_mux>; - assigned-clock-parents = <&atl_clkin2_ck>; - - status = "okay"; - - op-mode = <0>; /* MCASP_IIS_MODE */ - tdm-slots = <2>; - /* 4 serializer */ - serial-dir = < /* 0: INACTIVE, 1: TX, 2: RX */ - 1 2 0 0 - >; - tx-num-evt = <32>; - rx-num-evt = <32>; -}; - -&mcasp8 { - /* not used for audio. only the AXR2 pin is used as GPIO */ - status = "okay"; -}; - -&mailbox5 { - status = "okay"; - mbox_ipu1_ipc3x: mbox_ipu1_ipc3x { - status = "okay"; - }; - mbox_dsp1_ipc3x: mbox_dsp1_ipc3x { - status = "okay"; - }; -}; - -&mailbox6 { - status = "okay"; - mbox_ipu2_ipc3x: mbox_ipu2_ipc3x { - status = "okay"; - }; - mbox_dsp2_ipc3x: mbox_dsp2_ipc3x { - status = "okay"; - }; -}; - -&mmu0_dsp1 { - status = "okay"; -}; - -&mmu1_dsp1 { - status = "okay"; -}; - -&mmu0_dsp2 { - status = "okay"; -}; - -&mmu1_dsp2 { - status = "okay"; -}; - -&mmu_ipu1 { - status = "okay"; -}; - -&mmu_ipu2 { - status = "okay"; -}; - -&ipu2 { - status = "okay"; - memory-region = <&ipu2_cma_pool>; - mboxes = <&mailbox6 &mbox_ipu2_ipc3x>; - timers = <&timer3>; - watchdog-timers = <&timer4>, <&timer9>; -}; - -&ipu1 { - status = "okay"; - memory-region = <&ipu1_cma_pool>; - mboxes = <&mailbox5 &mbox_ipu1_ipc3x>; - timers = <&timer11>; - watchdog-timers = <&timer7>, <&timer8>; -}; - -&dsp1 { - status = "okay"; - memory-region = <&dsp1_cma_pool>; - mboxes = <&mailbox5 &mbox_dsp1_ipc3x>; - timers = <&timer5>; - watchdog-timers = <&timer10>; -}; - -&dsp2 { - status = "okay"; - memory-region = <&dsp2_cma_pool>; - mboxes = <&mailbox6 &mbox_dsp2_ipc3x>; - timers = <&timer6>; -}; - &dss { status = "okay"; @@ -1440,29 +1072,18 @@ i2c_p3_exp: &i2c2 { reg = <2>; dpi_out3: endpoint { - remote-endpoint = <&fpd_in>; data-lines = <24>; }; }; }; }; -&bb2d { - status = "okay"; -}; - &hdmi { - status = "ok"; vdda-supply = <&ldo3_reg>; - - port { - hdmi_out: endpoint { - remote-endpoint = <&tpd12s015_in>; - }; - }; }; -&vip1 { +&mcasp8 { + /* not used for audio. only the AXR2 pin is used as GPIO */ status = "okay"; }; @@ -1474,6 +1095,10 @@ video_in: &vin1a { }; }; +&bb2d { + status = "okay"; +}; + #include "dra7xx-jamr3.dtsi" &tvp_5158{ mux-gpios = <&pcf_hdmi 3 GPIO_ACTIVE_HIGH>, /*CAM_FPD_MUX_S0*/ diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 4a2b643bd60d..43316d454d41 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -300,7 +300,6 @@ * node and enable pcie1_ep mode. */ pcie1_rc: pcie_rc@51000000 { - compatible = "ti,dra7-pcie"; reg = <0x51000000 0x2000>, <0x51002000 0x14c>, <0x1000 0x2000>; reg-names = "rc_dbics", "ti_conf", "config"; interrupts = <0 232 0x4>, <0 233 0x4>; @@ -315,6 +314,8 @@ ti,hwmods = "pcie1"; phys = <&pcie1_phy>; phy-names = "pcie-phy0"; + syscon-lane-conf = <&scm_conf 0x558>; + syscon-lane-sel = <&scm_conf_pcie 0x18>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie1_intc 1>, <0 0 0 2 &pcie1_intc 2>, @@ -329,7 +330,6 @@ }; pcie1_ep: pcie_ep@51000000 { - compatible = "ti,dra7-pcie-ep"; reg = <0x51000000 0x28>, <0x51002000 0x14c>, <0x51001000 0x28>, <0x1000 0x10000000>; reg-names = "ep_dbics", "ti_conf", "ep_dbics2", "addr_space"; interrupts = <0 232 0x4>; @@ -351,8 +351,7 @@ ranges = <0x51800000 0x51800000 0x3000 0x0 0x30000000 0x10000000>; status = "disabled"; - pcie@51800000 { - compatible = "ti,dra7-pcie"; + pcie2_rc: pcie@51800000 { reg = <0x51800000 0x2000>, <0x51802000 0x14c>, <0x1000 0x2000>; reg-names = "rc_dbics", "ti_conf", "config"; interrupts = <0 355 0x4>, <0 356 0x4>; diff --git a/arch/arm/boot/dts/dra72-evm-common.dtsi b/arch/arm/boot/dts/dra72-evm-common.dtsi index 4ff5187da184..aa3b8abde63d 100644 --- a/arch/arm/boot/dts/dra72-evm-common.dtsi +++ b/arch/arm/boot/dts/dra72-evm-common.dtsi @@ -16,7 +16,6 @@ aliases { display0 = &hdmi0; - display1 = &fpd_disp; sound0 = &snd0; sound1 = &hdmi; i2c7 = &disp_ser; @@ -589,35 +588,14 @@ i2c_p3_exp: &i2c5 { disp_ser: serializer@1b { compatible = "ti,ds90uh925q"; reg = <0x1b>; + status = "disabled"; #address-cells = <1>; #size-cells = <0>; - ranges = <0x2c 0x2c>, - <0x1c 0x1c>; - - disp_des: deserializer@2c { - compatible = "ti,ds90uh928q"; - reg = <0x2c>; - slave-mode; - }; - - /* TLC chip for LCD panel power and backlight */ - fpd_disp: tlc59108@1c { - status = "disabled"; - reg = <0x1c>; - compatible = "ti,tlc59108-fpddisp"; - enable-gpios = <&pcf_gpio_21 0 GPIO_ACTIVE_LOW>; - /* P0, SEL_GPMC_AD_VID_S0 */ - - port@lcd3 { - fpd_in: endpoint { - remote-endpoint = <&dpi_out3>; - }; - }; - }; }; }; + &dss { status = "ok"; vdda_video-supply = <&ldo5_reg>; @@ -630,7 +608,6 @@ i2c_p3_exp: &i2c5 { reg = <2>; dpi_out3: endpoint { - remote-endpoint = <&fpd_in>; data-lines = <24>; }; }; diff --git a/arch/arm/boot/dts/dra72-evm-fpd-lg.dts b/arch/arm/boot/dts/dra72-evm-fpd-lg.dts new file mode 100644 index 000000000000..9ed0f66fdb76 --- /dev/null +++ b/arch/arm/boot/dts/dra72-evm-fpd-lg.dts @@ -0,0 +1,39 @@ +#include "dra72-evm.dts" +#include "dra7x-evm-fpd-lg.dtsi" + +/* Set display aliases for use by Android */ +/ { + aliases { + display0 = &fpd_disp; + display1 = &hdmi0; + }; +}; + +&dss { + ports { + status = "ok"; + }; +}; + +&disp_ser { + status = "ok"; + ranges = <0x2c 0x2c>, + <0x1c 0x1c>; +}; + +/* Tie the end points of DSS and FPDLink together */ + +&fpd_in { + remote-endpoint = <&dpi_out3>; +}; + +&dpi_out3 { + remote-endpoint = <&fpd_in>; +}; + +&lcd_fpd { + enable-gpios = <&pcf_gpio_21 0 GPIO_ACTIVE_LOW>; + /* P0, SEL_GPMC_AD_VID_S0 */ + + status = "ok"; +}; diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts index deef9b8520b2..cc108d2f9b09 100644 --- a/arch/arm/boot/dts/dra72-evm.dts +++ b/arch/arm/boot/dts/dra72-evm.dts @@ -11,7 +11,6 @@ aliases { display0 = &hdmi0; - display1 = &fpd_disp; sound1 = &hdmi; i2c7 = &disp_ser; }; @@ -215,39 +214,6 @@ }; }; -&i2c5 { - disp_ser: serializer@1b { - compatible = "ti,ds90uh925q"; - reg = <0x1b>; - - #address-cells = <1>; - #size-cells = <0>; - ranges = <0x2c 0x2c>, - <0x1c 0x1c>; - - disp_des: deserializer@2c { - compatible = "ti,ds90uh928q"; - reg = <0x2c>; - slave-mode; - }; - - /* TLC chip for LCD panel power and backlight */ - fpd_disp: tlc59108@1c { - status = "disabled"; - reg = <0x1c>; - compatible = "ti,tlc59108-fpddisp"; - enable-gpios = <&pcf_gpio_21 0 GPIO_ACTIVE_LOW>; - /* P0, SEL_GPMC_AD_VID_S0 */ - - port@lcd3 { - fpd_in: endpoint { - remote-endpoint = <&dpi_out3>; - }; - }; - }; - }; -}; - &hdmi { vdda_video-supply = <&ldo5_reg>; }; diff --git a/arch/arm/boot/dts/dra72x.dtsi b/arch/arm/boot/dts/dra72x.dtsi index 68341c30beb1..29705754460c 100644 --- a/arch/arm/boot/dts/dra72x.dtsi +++ b/arch/arm/boot/dts/dra72x.dtsi @@ -140,3 +140,15 @@ status = "disabled"; }; }; + +&pcie1_rc { + compatible = "ti,dra726-pcie-rc"; +}; + +&pcie1_ep { + compatible = "ti,dra726-pcie-ep"; +}; + +&pcie2_rc { + compatible = "ti,dra726-pcie-rc"; +}; diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi index b96f6c7f77d0..a95a1d17ad2d 100644 --- a/arch/arm/boot/dts/dra74x.dtsi +++ b/arch/arm/boot/dts/dra74x.dtsi @@ -259,3 +259,15 @@ status = "disabled"; }; }; + +&pcie1_rc { + compatible = "ti,dra746-pcie-rc"; +}; + +&pcie1_ep { + compatible = "ti,dra746-pcie-ep"; +}; + +&pcie2_rc { + compatible = "ti,dra746-pcie-rc"; +}; diff --git a/arch/arm/boot/dts/dra76-evm-fpd-auo-g101evn01.0.dts b/arch/arm/boot/dts/dra76-evm-fpd-auo-g101evn01.0.dts new file mode 100644 index 000000000000..69983d70d1f4 --- /dev/null +++ b/arch/arm/boot/dts/dra76-evm-fpd-auo-g101evn01.0.dts @@ -0,0 +1,67 @@ +#include "dra76-evm.dts" +#include "dra7x-evm-fpd-auo-g101evn01.0.dtsi" + +/ { + aliases { + display0 = &fpd_disp; + display1 = &hdmi0; + }; +}; + +&dss { + ports { + status = "ok"; + }; +}; + +&disp_ser { + status = "ok"; + ranges = <0x0 0x2d>; +}; + +/* Tie the end points of DSS and FPDLink together */ +&fpd_in { + remote-endpoint = <&dpi_out3>; +}; + +&dpi_out3 { + remote-endpoint = <&fpd_in>; +}; + +&lcd_fpd { + status = "ok"; +}; + +/* U21 on the EVM */ +/* gpmc_ad_vid_s0: high: GPMC , low: VOUT3 */ +&pcf_gpio_21 { + p0 { + gpio-hog; + gpios = <0 GPIO_ACTIVE_HIGH>; + output-low; + line-name = "gpmc_ad_vid_s0"; + }; +}; + + +/* U110 on the EVM. For Rev A boards */ +/* +&pcf_hdmi { + p11 { + gpio-hog; + gpios = <11 GPIO_ACTIVE_HIGH>; + output-low; + line-name = "disp1_vpoc_onn"; + }; +}; +*/ + +/* For supplying power to the display via FPDLink */ +&gpio2 { + p2 { + gpio-hog; + gpios = <2 GPIO_ACTIVE_HIGH>; + output-low; + line-name = "disp1_vpoc_onn"; + }; +}; diff --git a/arch/arm/boot/dts/dra76-evm.dts b/arch/arm/boot/dts/dra76-evm.dts new file mode 100644 index 000000000000..213f4b53f965 --- /dev/null +++ b/arch/arm/boot/dts/dra76-evm.dts @@ -0,0 +1,498 @@ +/* + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +/dts-v1/; + +#include "dra76x.dtsi" +#include "dra7-evm-common.dtsi" +#include "dra76x-mmc-iodelay.dtsi" +#include <dt-bindings/net/ti-dp83867.h> + +/ { + model = "TI DRA762 EVM"; + compatible = "ti,dra76-evm", "ti,dra76", "ti,dra7"; + + memory { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x80000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + ipu2_cma_pool: ipu2_cma@95800000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x95800000 0x0 0x3800000>; + reusable; + status = "okay"; + }; + + dsp1_cma_pool: dsp1_cma@99000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x99000000 0x0 0x4000000>; + reusable; + status = "okay"; + }; + + ipu1_cma_pool: ipu1_cma@9d000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x9d000000 0x0 0x2000000>; + reusable; + status = "okay"; + }; + + dsp2_cma_pool: dsp2_cma@9f000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x9f000000 0x0 0x800000>; + reusable; + status = "okay"; + }; + }; + + aliases { + i2c7 = &disp_ser; + }; + + vsys_12v0: fixedregulator-vsys12v0 { + /* main supply */ + compatible = "regulator-fixed"; + regulator-name = "vsys_12v0"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + regulator-always-on; + regulator-boot-on; + }; + + vsys_5v0: fixedregulator-vsys5v0 { + /* Output of Cntlr B of TPS43351-Q1 on dra76-evm */ + compatible = "regulator-fixed"; + regulator-name = "vsys_5v0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vsys_12v0>; + regulator-always-on; + regulator-boot-on; + }; + + vsys_3v3: fixedregulator-vsys3v3 { + /* Output of Cntlr A of TPS43351-Q1 on dra76-evm */ + compatible = "regulator-fixed"; + regulator-name = "vsys_3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vsys_12v0>; + regulator-always-on; + regulator-boot-on; + }; + + vio_3v3: fixedregulator-vio_3v3 { + compatible = "regulator-fixed"; + regulator-name = "vio_3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vsys_3v3>; + regulator-always-on; + regulator-boot-on; + }; + + vio_3v3_sd: fixedregulator-sd { + compatible = "regulator-fixed"; + regulator-name = "vio_3v3_sd"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vio_3v3>; + enable-active-high; + gpio = <&gpio4 21 GPIO_ACTIVE_HIGH>; + }; + + vio_1v8: fixedregulator-vio_1v8 { + compatible = "regulator-fixed"; + regulator-name = "vio_1v8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + vin-supply = <&smps5_reg>; + }; + + vtt_fixed: fixedregulator-vtt { + compatible = "regulator-fixed"; + regulator-name = "vtt_fixed"; + regulator-min-microvolt = <1350000>; + regulator-max-microvolt = <1350000>; + vin-supply = <&vsys_3v3>; + regulator-always-on; + regulator-boot-on; + }; + + aic_dvdd: fixedregulator-aic_dvdd { + /* TPS77018DBVT */ + compatible = "regulator-fixed"; + regulator-name = "aic_dvdd"; + vin-supply = <&vio_3v3>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; +}; + +&i2c1 { + status = "okay"; + clock-frequency = <400000>; + + tps65917: tps65917@58 { + compatible = "ti,tps65917"; + reg = <0x58>; + ti,system-power-controller; + interrupt-controller; + #interrupt-cells = <2>; + + tps65917_pmic { + compatible = "ti,tps65917-pmic"; + + smps12-in-supply = <&vsys_3v3>; + smps3-in-supply = <&vsys_3v3>; + smps4-in-supply = <&vsys_3v3>; + smps5-in-supply = <&vsys_3v3>; + ldo1-in-supply = <&vsys_3v3>; + ldo2-in-supply = <&vsys_3v3>; + ldo3-in-supply = <&vsys_5v0>; + ldo4-in-supply = <&vsys_5v0>; + ldo5-in-supply = <&vsys_3v3>; + + tps65917_regulators: regulators { + smps12_reg: smps12 { + /* VDD_DSPEVE */ + regulator-name = "smps12"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1250000>; + regulator-always-on; + regulator-boot-on; + }; + + smps3_reg: smps3 { + /* VDD_CORE */ + regulator-name = "smps3"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1250000>; + regulator-boot-on; + regulator-always-on; + }; + + smps4_reg: smps4 { + /* VDD_IVA */ + regulator-name = "smps4"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1250000>; + regulator-always-on; + regulator-boot-on; + }; + + smps5_reg: smps5 { + /* VDDS1V8 */ + regulator-name = "smps5"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo1_reg: ldo1 { + /* LDO1_OUT --> VDA_PHY1_1V8 */ + regulator-name = "ldo1"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + regulator-allow-bypass; + }; + + ldo2_reg: ldo2 { + /* LDO2_OUT --> VDA_PHY2_1V8 */ + regulator-name = "ldo2"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-allow-bypass; + regulator-always-on; + }; + + ldo3_reg: ldo3 { + /* VDA_USB_3V3 */ + regulator-name = "ldo3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo5_reg: ldo5 { + /* VDDA_1V8_PLL */ + regulator-name = "ldo5"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + + ldo4_reg: ldo4 { + /* VDD_SDIO_DV */ + regulator-name = "ldo4"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + }; + }; + + tps65917_power_button { + compatible = "ti,palmas-pwrbutton"; + interrupt-parent = <&tps65917>; + interrupts = <1 IRQ_TYPE_NONE>; + wakeup-source; + ti,palmas-long-press-seconds = <6>; + }; + }; + + lp87565: lp87565@60 { + compatible = "ti,lp87565-q1"; + reg = <0x60>; + + buck10-in-supply =<&vsys_3v3>; + buck23-in-supply =<&vsys_3v3>; + + regulators: regulators { + buck10_reg: buck10 { + /*VDD_MPU*/ + regulator-name = "buck10"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1250000>; + regulator-always-on; + regulator-boot-on; + }; + + buck23_reg: buck23 { + /* VDD_GPU*/ + regulator-name = "buck23"; + regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1250000>; + regulator-boot-on; + regulator-always-on; + }; + }; + }; + + pcf_lcd: pcf8757@20 { + compatible = "ti,pcf8575", "nxp,pcf8575"; + reg = <0x20>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&gpio1>; + interrupts = <3 IRQ_TYPE_EDGE_FALLING>; + }; + + pcf_gpio_21: pcf8757@21 { + compatible = "ti,pcf8575", "nxp,pcf8575"; + reg = <0x21>; + gpio-controller; + #gpio-cells = <2>; + interrupt-parent = <&gpio1>; + interrupts = <3 IRQ_TYPE_EDGE_FALLING>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pcf_hdmi: pcf8575@26 { + compatible = "ti,pcf8575", "nxp,pcf8575"; + reg = <0x26>; + gpio-controller; + #gpio-cells = <2>; + p1 { + /* vin6_sel_s0: high: VIN6, low: audio */ + gpio-hog; + gpios = <1 GPIO_ACTIVE_HIGH>; + output-low; + line-name = "vin6_sel_s0"; + }; + }; + + tlv320aic3106: tlv320aic3106@19 { + #sound-dai-cells = <0>; + compatible = "ti,tlv320aic3106"; + reg = <0x19>; + adc-settle-ms = <40>; + ai3x-micbias-vg = <1>; /* 2.0V */ + status = "okay"; + + /* Regulators */ + AVDD-supply = <&vio_3v3>; + IOVDD-supply = <&vio_3v3>; + DRVDD-supply = <&vio_3v3>; + DVDD-supply = <&aic_dvdd>; + }; +}; + +&tpd12s015 { + compatible = "ti,tpd12s015"; + + gpios = <&gpio7 30 GPIO_ACTIVE_HIGH>, /* gpio7_30, CT CP HPD */ + <&gpio7 31 GPIO_ACTIVE_HIGH>, /* gpio7_31, LS OE */ + <&gpio7 12 GPIO_ACTIVE_HIGH>; /* gpio7_12/sp1_cs2, HPD */ + +}; + +&mmc1 { + status = "okay"; + vmmc-supply = <&vio_3v3_sd>; + vmmc_aux-supply = <&ldo4_reg>; + bus-width = <4>; + /* + * SDCD signal is not being used here - using the fact that GPIO mode + * is always hardwired. + */ + cd-gpios = <&gpio6 27 GPIO_ACTIVE_LOW>; + max-frequency = <192000000>; + pinctrl-names = "default", "hs"; + pinctrl-0 = <&mmc1_pins_default>; + pinctrl-1 = <&mmc1_pins_hs>; +}; + +&mmc2 { + status = "okay"; + vmmc-supply = <&vio_1v8>; + bus-width = <8>; + max-frequency = <192000000>; + pinctrl-names = "default", "hs", "ddr_1_8v", "hs200_1_8v"; + pinctrl-0 = <&mmc2_pins_default>; + pinctrl-1 = <&mmc2_pins_hs>; + pinctrl-2 = <&mmc2_pins_ddr>; + pinctrl-3 = <&mmc2_pins_hs200 &mmc2_iodelay_hs200_conf>; +}; + +&oppdm_mpu { + vdd-supply = <&buck10_reg>; +}; + +&oppdm_dspeve { + vdd-supply = <&smps12_reg>; +}; + +&oppdm_gpu { + vdd-supply = <&buck23_reg>; +}; + +&oppdm_ivahd { + vdd-supply = <&smps4_reg>; +}; + +&oppdm_core { + vdd-supply = <&smps3_reg>; +}; + +/* No RTC on this device */ +&rtc { + status = "disabled"; +}; + +&mac { + status = "okay"; + + dual_emac; +}; + +&cpsw_emac0 { + phy_id = <&davinci_mdio>, <2>; + phy-mode = "rgmii-id"; + dual_emac_res_vlan = <1>; +}; + +&cpsw_emac1 { + phy_id = <&davinci_mdio>, <3>; + phy-mode = "rgmii-id"; + dual_emac_res_vlan = <2>; +}; + +&davinci_mdio { + dp83867_0: ethernet-phy@2 { + reg = <2>; + ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>; + ti,tx-internal-delay = <DP83867_RGMIIDCTL_250_PS>; + ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_8_B_NIB>; + ti,min-output-impedance; + ti,dp83867-rxctrl-strap-quirk; + }; + + dp83867_1: ethernet-phy@3 { + reg = <3>; + ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>; + ti,tx-internal-delay = <DP83867_RGMIIDCTL_250_PS>; + ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_8_B_NIB>; + ti,min-output-impedance; + ti,dp83867-rxctrl-strap-quirk; + }; +}; + +&usb2_phy1 { + phy-supply = <&ldo3_reg>; +}; + +&usb2_phy2 { + phy-supply = <&ldo3_reg>; +}; + +&i2c3 { + disp_ser: serializer@0c { + compatible = "ti,ds90ub921q"; + reg = <0x0c>; + + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; +}; + +&dss { + status = "ok"; + vdda_video-supply = <&ldo5_reg>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + + port@lcd3 { + reg = <2>; + + dpi_out3: endpoint { + data-lines = <24>; + }; + }; + }; +}; + +&hdmi { + vdda-supply = <&ldo1_reg>; +}; + +&qspi { + spi-max-frequency = <96000000>; + m25p80@0 { + spi-max-frequency = <96000000>; + }; +}; + +&pcie2_phy { + status = "okay"; +}; + +&pcie1_rc { + num-lanes = <2>; + phys = <&pcie1_phy>, <&pcie2_phy>; + phy-names = "pcie-phy0", "pcie-phy1"; +}; diff --git a/arch/arm/boot/dts/dra76x-mmc-iodelay.dtsi b/arch/arm/boot/dts/dra76x-mmc-iodelay.dtsi new file mode 100644 index 000000000000..c95a8a1091ab --- /dev/null +++ b/arch/arm/boot/dts/dra76x-mmc-iodelay.dtsi @@ -0,0 +1,435 @@ +/* + * MMC IOdelay values for TI's DRA76x and AM576x SoCs. + * + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Rules for modifying this file: + * a) Update of this file should typically correspond to a datamanual revision. + * Datamanual revision that was used should be updated in comment below. + * If there is no update to datamanual, do not update the values. If you + * need to use values different from that recommended by the datamanual + * for your design, then you should consider adding values to the device- + * -tree file for your board directly. + * b) We keep the mode names as close to the datamanual as possible. So + * if the manual calls a mode, DDR50, or DDR or DDR 1.8v or DDR 3.3v, + * we follow that in code too. + * c) If the values change between multiple revisions of silicon, we add + * a revision tag to both the new and old entry. Use 'rev11' for PG 1.1, + * 'rev20' for PG 2.0 and so on. + * d) The node name and node label should be the exact same string. This is + * to curb naming creativity and achieve consistency. + * + * Datamanual Revisions: + * + * DRA76x Silicon Revision 1.0: SPRS993A, Revised July 2017 + * + */ + +&dra7_pmx_core { + mmc1_pins_default: mmc1_pins_default { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x3754, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_clk.clk */ + DRA7XX_CORE_IOPAD(0x3758, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_cmd.cmd */ + DRA7XX_CORE_IOPAD(0x375c, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat0.dat0 */ + DRA7XX_CORE_IOPAD(0x3760, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat1.dat1 */ + DRA7XX_CORE_IOPAD(0x3764, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat2.dat2 */ + DRA7XX_CORE_IOPAD(0x3768, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat3.dat3 */ + >; + }; + + mmc1_pins_sdr12: mmc1_pins_sdr12 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x3754, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_clk.clk */ + DRA7XX_CORE_IOPAD(0x3758, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_cmd.cmd */ + DRA7XX_CORE_IOPAD(0x375c, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat0.dat0 */ + DRA7XX_CORE_IOPAD(0x3760, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat1.dat1 */ + DRA7XX_CORE_IOPAD(0x3764, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat2.dat2 */ + DRA7XX_CORE_IOPAD(0x3768, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc1_dat3.dat3 */ + >; + }; + + mmc1_pins_hs: mmc1_pins_hs { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x3754, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_clk.clk */ + DRA7XX_CORE_IOPAD(0x3758, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_cmd.cmd */ + DRA7XX_CORE_IOPAD(0x375c, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat0.dat0 */ + DRA7XX_CORE_IOPAD(0x3760, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat1.dat1 */ + DRA7XX_CORE_IOPAD(0x3764, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat2.dat2 */ + DRA7XX_CORE_IOPAD(0x3768, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat3.dat3 */ + >; + }; + + mmc1_pins_sdr25: mmc1_pins_sdr25 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x3754, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_clk.clk */ + DRA7XX_CORE_IOPAD(0x3758, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_cmd.cmd */ + DRA7XX_CORE_IOPAD(0x375c, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat0.dat0 */ + DRA7XX_CORE_IOPAD(0x3760, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat1.dat1 */ + DRA7XX_CORE_IOPAD(0x3764, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat2.dat2 */ + DRA7XX_CORE_IOPAD(0x3768, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE11 | MUX_MODE0) /* mmc1_dat3.dat3 */ + >; + }; + + mmc1_pins_sdr50: mmc1_pins_sdr50 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x3754, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE10 | MUX_MODE0) /* mmc1_clk.clk */ + DRA7XX_CORE_IOPAD(0x3758, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE10 | MUX_MODE0) /* mmc1_cmd.cmd */ + DRA7XX_CORE_IOPAD(0x375c, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE10 | MUX_MODE0) /* mmc1_dat0.dat0 */ + DRA7XX_CORE_IOPAD(0x3760, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE10 | MUX_MODE0) /* mmc1_dat1.dat1 */ + DRA7XX_CORE_IOPAD(0x3764, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE10 | MUX_MODE0) /* mmc1_dat2.dat2 */ + DRA7XX_CORE_IOPAD(0x3768, PIN_INPUT_PULLUP | MUX_VIRTUAL_MODE10 | MUX_MODE0) /* mmc1_dat3.dat3 */ + >; + }; + + mmc1_pins_ddr50: mmc1_pins_ddr50 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x3754, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_clk.clk */ + DRA7XX_CORE_IOPAD(0x3758, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_cmd.cmd */ + DRA7XX_CORE_IOPAD(0x375c, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat0.dat0 */ + DRA7XX_CORE_IOPAD(0x3760, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat1.dat1 */ + DRA7XX_CORE_IOPAD(0x3764, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat2.dat2 */ + DRA7XX_CORE_IOPAD(0x3768, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat3.dat3 */ + >; + }; + + mmc1_pins_sdr104: mmc1_pins_sdr104 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x3754, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_clk.clk */ + DRA7XX_CORE_IOPAD(0x3758, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_cmd.cmd */ + DRA7XX_CORE_IOPAD(0x375c, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat0.dat0 */ + DRA7XX_CORE_IOPAD(0x3760, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat1.dat1 */ + DRA7XX_CORE_IOPAD(0x3764, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat2.dat2 */ + DRA7XX_CORE_IOPAD(0x3768, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0) /* mmc1_dat3.dat3 */ + >; + }; + + mmc2_pins_default: mmc2_pins_default { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x349c, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a23.mmc2_clk */ + DRA7XX_CORE_IOPAD(0x34b0, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_cs1.mmc2_cmd */ + DRA7XX_CORE_IOPAD(0x34a0, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a24.mmc2_dat0 */ + DRA7XX_CORE_IOPAD(0x34a4, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a25.mmc2_dat1 */ + DRA7XX_CORE_IOPAD(0x34a8, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a26.mmc2_dat2 */ + DRA7XX_CORE_IOPAD(0x34ac, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a27.mmc2_dat3 */ + DRA7XX_CORE_IOPAD(0x348c, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a19.mmc2_dat4 */ + DRA7XX_CORE_IOPAD(0x3490, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a20.mmc2_dat5 */ + DRA7XX_CORE_IOPAD(0x3494, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a21.mmc2_dat6 */ + DRA7XX_CORE_IOPAD(0x3498, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a22.mmc2_dat7 */ + >; + }; + + mmc2_pins_hs: mmc2_pins_hs { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x349c, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a23.mmc2_clk */ + DRA7XX_CORE_IOPAD(0x34b0, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_cs1.mmc2_cmd */ + DRA7XX_CORE_IOPAD(0x34a0, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a24.mmc2_dat0 */ + DRA7XX_CORE_IOPAD(0x34a4, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a25.mmc2_dat1 */ + DRA7XX_CORE_IOPAD(0x34a8, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a26.mmc2_dat2 */ + DRA7XX_CORE_IOPAD(0x34ac, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a27.mmc2_dat3 */ + DRA7XX_CORE_IOPAD(0x348c, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a19.mmc2_dat4 */ + DRA7XX_CORE_IOPAD(0x3490, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a20.mmc2_dat5 */ + DRA7XX_CORE_IOPAD(0x3494, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a21.mmc2_dat6 */ + DRA7XX_CORE_IOPAD(0x3498, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a22.mmc2_dat7 */ + >; + }; + + mmc2_pins_ddr: mmc2_pins_ddr { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x349c, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a23.mmc2_clk */ + DRA7XX_CORE_IOPAD(0x34b0, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_cs1.mmc2_cmd */ + DRA7XX_CORE_IOPAD(0x34a0, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a24.mmc2_dat0 */ + DRA7XX_CORE_IOPAD(0x34a4, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a25.mmc2_dat1 */ + DRA7XX_CORE_IOPAD(0x34a8, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a26.mmc2_dat2 */ + DRA7XX_CORE_IOPAD(0x34ac, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a27.mmc2_dat3 */ + DRA7XX_CORE_IOPAD(0x348c, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a19.mmc2_dat4 */ + DRA7XX_CORE_IOPAD(0x3490, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a20.mmc2_dat5 */ + DRA7XX_CORE_IOPAD(0x3494, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a21.mmc2_dat6 */ + DRA7XX_CORE_IOPAD(0x3498, PIN_INPUT_PULLUP | MUX_MODE1) /* gpmc_a22.mmc2_dat7 */ + >; + }; + + mmc2_pins_hs200: mmc2_pins_hs200 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x349c, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a23.mmc2_clk */ + DRA7XX_CORE_IOPAD(0x34b0, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_cs1.mmc2_cmd */ + DRA7XX_CORE_IOPAD(0x34a0, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a24.mmc2_dat0 */ + DRA7XX_CORE_IOPAD(0x34a4, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a25.mmc2_dat1 */ + DRA7XX_CORE_IOPAD(0x34a8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a26.mmc2_dat2 */ + DRA7XX_CORE_IOPAD(0x34ac, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a27.mmc2_dat3 */ + DRA7XX_CORE_IOPAD(0x348c, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a19.mmc2_dat4 */ + DRA7XX_CORE_IOPAD(0x3490, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a20.mmc2_dat5 */ + DRA7XX_CORE_IOPAD(0x3494, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a21.mmc2_dat6 */ + DRA7XX_CORE_IOPAD(0x3498, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE1) /* gpmc_a22.mmc2_dat7 */ + >; + }; + + mmc3_pins_default: mmc3_pins_default { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + >; + }; + + mmc3_pins_hs: mmc3_pins_hs { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + >; + }; + + mmc3_pins_sdr12: mmc3_pins_sdr12 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + >; + }; + + mmc3_pins_sdr25: mmc3_pins_sdr25 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + >; + }; + + mmc3_pins_sdr50: mmc3_pins_sdr50 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */ + DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */ + DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */ + DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */ + DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */ + DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */ + >; + }; + + mmc4_pins_default: mmc4_pins_default { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x37e8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_ctsn.mmc4_clk */ + DRA7XX_CORE_IOPAD(0x37ec, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_rtsn.mmc4_cmd */ + DRA7XX_CORE_IOPAD(0x37f0, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rxd.mmc4_dat0 */ + DRA7XX_CORE_IOPAD(0x37f4, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_txd.mmc4_dat1 */ + DRA7XX_CORE_IOPAD(0x37f8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_ctsn.mmc4_dat2 */ + DRA7XX_CORE_IOPAD(0x37fc, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rtsn.mmc4_dat3 */ + >; + }; + + mmc4_pins_sdr12: mmc4_pins_sdr12 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x37e8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_ctsn.mmc4_clk */ + DRA7XX_CORE_IOPAD(0x37ec, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_rtsn.mmc4_cmd */ + DRA7XX_CORE_IOPAD(0x37f0, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rxd.mmc4_dat0 */ + DRA7XX_CORE_IOPAD(0x37f4, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_txd.mmc4_dat1 */ + DRA7XX_CORE_IOPAD(0x37f8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_ctsn.mmc4_dat2 */ + DRA7XX_CORE_IOPAD(0x37fc, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rtsn.mmc4_dat3 */ + >; + }; + + mmc4_pins_hs: mmc4_pins_hs { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x37e8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_ctsn.mmc4_clk */ + DRA7XX_CORE_IOPAD(0x37ec, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_rtsn.mmc4_cmd */ + DRA7XX_CORE_IOPAD(0x37f0, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rxd.mmc4_dat0 */ + DRA7XX_CORE_IOPAD(0x37f4, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_txd.mmc4_dat1 */ + DRA7XX_CORE_IOPAD(0x37f8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_ctsn.mmc4_dat2 */ + DRA7XX_CORE_IOPAD(0x37fc, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rtsn.mmc4_dat3 */ + >; + }; + + mmc4_pins_sdr25: mmc4_pins_sdr25 { + pinctrl-single,pins = < + DRA7XX_CORE_IOPAD(0x37e8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_ctsn.mmc4_clk */ + DRA7XX_CORE_IOPAD(0x37ec, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart1_rtsn.mmc4_cmd */ + DRA7XX_CORE_IOPAD(0x37f0, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rxd.mmc4_dat0 */ + DRA7XX_CORE_IOPAD(0x37f4, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_txd.mmc4_dat1 */ + DRA7XX_CORE_IOPAD(0x37f8, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_ctsn.mmc4_dat2 */ + DRA7XX_CORE_IOPAD(0x37fc, PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE3) /* uart2_rtsn.mmc4_dat3 */ + >; + }; +}; + +&dra7_iodelay_core { + + /* Corresponds to MMC1_DDR_MANUAL1 in datamanual */ + mmc1_iodelay_ddr_conf: mmc1_iodelay_ddr_conf { + pinctrl-single,pins = < + 0x618 (A_DELAY(489) | G_DELAY(0)) /* CFG_MMC1_CLK_IN */ + 0x624 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_CMD_IN */ + 0x630 (A_DELAY(374) | G_DELAY(0)) /* CFG_MMC1_DAT0_IN */ + 0x63c (A_DELAY(31) | G_DELAY(0)) /* CFG_MMC1_DAT1_IN */ + 0x648 (A_DELAY(56) | G_DELAY(0)) /* CFG_MMC1_DAT2_IN */ + 0x654 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT3_IN */ + 0x620 (A_DELAY(1355) | G_DELAY(0)) /* CFG_MMC1_CLK_OUT */ + 0x628 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_CMD_OEN */ + 0x62c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_CMD_OUT */ + 0x634 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT0_OEN */ + 0x638 (A_DELAY(0) | G_DELAY(4)) /* CFG_MMC1_DAT0_OUT */ + 0x640 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT1_OEN */ + 0x644 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT1_OUT */ + 0x64c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT2_OEN */ + 0x650 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT2_OUT */ + 0x658 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT3_OEN */ + 0x65c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT3_OUT */ + >; + }; + + /* Corresponds to MMC1_SDR104_MANUAL1 in datamanual */ + mmc1_iodelay_sdr104_conf: mmc1_iodelay_sdr104_conf { + pinctrl-single,pins = < + 0x620 (A_DELAY(892) | G_DELAY(0)) /* CFG_MMC1_CLK_OUT */ + 0x628 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_CMD_OEN */ + 0x62c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_CMD_OUT */ + 0x634 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT0_OEN */ + 0x638 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT0_OUT */ + 0x640 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT1_OEN */ + 0x644 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT1_OUT */ + 0x64c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT2_OEN */ + 0x650 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT2_OUT */ + 0x658 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT3_OEN */ + 0x65c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC1_DAT3_OUT */ + >; + }; + + /* Corresponds to MMC2_HS200_MANUAL1 in datamanual */ + mmc2_iodelay_hs200_conf: mmc2_iodelay_hs200_conf { + pinctrl-single,pins = < + 0x190 (A_DELAY(384) | G_DELAY(0)) /* CFG_GPMC_A19_OEN */ + 0x194 (A_DELAY(0) | G_DELAY(174)) /* CFG_GPMC_A19_OUT */ + 0x1a8 (A_DELAY(410) | G_DELAY(0)) /* CFG_GPMC_A20_OEN */ + 0x1ac (A_DELAY(85) | G_DELAY(0)) /* CFG_GPMC_A20_OUT */ + 0x1b4 (A_DELAY(468) | G_DELAY(0)) /* CFG_GPMC_A21_OEN */ + 0x1b8 (A_DELAY(139) | G_DELAY(0)) /* CFG_GPMC_A21_OUT */ + 0x1c0 (A_DELAY(676) | G_DELAY(0)) /* CFG_GPMC_A22_OEN */ + 0x1c4 (A_DELAY(69) | G_DELAY(0)) /* CFG_GPMC_A22_OUT */ + 0x1d0 (A_DELAY(1062) | G_DELAY(154)) /* CFG_GPMC_A23_OUT */ + 0x1d8 (A_DELAY(640) | G_DELAY(0)) /* CFG_GPMC_A24_OEN */ + 0x1dc (A_DELAY(0) | G_DELAY(0)) /* CFG_GPMC_A24_OUT */ + 0x1e4 (A_DELAY(356) | G_DELAY(0)) /* CFG_GPMC_A25_OEN */ + 0x1e8 (A_DELAY(0) | G_DELAY(0)) /* CFG_GPMC_A25_OUT */ + 0x1f0 (A_DELAY(579) | G_DELAY(0)) /* CFG_GPMC_A26_OEN */ + 0x1f4 (A_DELAY(0) | G_DELAY(0)) /* CFG_GPMC_A26_OUT */ + 0x1fc (A_DELAY(435) | G_DELAY(0)) /* CFG_GPMC_A27_OEN */ + 0x200 (A_DELAY(36) | G_DELAY(0)) /* CFG_GPMC_A27_OUT */ + 0x364 (A_DELAY(759) | G_DELAY(0)) /* CFG_GPMC_CS1_OEN */ + 0x368 (A_DELAY(72) | G_DELAY(0)) /* CFG_GPMC_CS1_OUT */ + >; + }; + + /* Corresponds to MMC3_MANUAL1 in datamanual */ + mmc3_iodelay_manual1_conf: mmc3_iodelay_manual1_conf { + pinctrl-single,pins = < + 0x678 (A_DELAY(0) | G_DELAY(386)) /* CFG_MMC3_CLK_IN */ + 0x680 (A_DELAY(605) | G_DELAY(0)) /* CFG_MMC3_CLK_OUT */ + 0x684 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_CMD_IN */ + 0x688 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_CMD_OEN */ + 0x68c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_CMD_OUT */ + 0x690 (A_DELAY(171) | G_DELAY(0)) /* CFG_MMC3_DAT0_IN */ + 0x694 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT0_OEN */ + 0x698 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT0_OUT */ + 0x69c (A_DELAY(221) | G_DELAY(0)) /* CFG_MMC3_DAT1_IN */ + 0x6a0 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT1_OEN */ + 0x6a4 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT1_OUT */ + 0x6a8 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT2_IN */ + 0x6ac (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT2_OEN */ + 0x6b0 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT2_OUT */ + 0x6b4 (A_DELAY(474) | G_DELAY(0)) /* CFG_MMC3_DAT3_IN */ + 0x6b8 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT3_OEN */ + 0x6bc (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT3_OUT */ + >; + }; + + /* Corresponds to MMC3_MANUAL2 in datamanual */ + mmc3_iodelay_sdr50_conf: mmc3_iodelay_sdr50_conf { + pinctrl-single,pins = < + 0x678 (A_DELAY(852) | G_DELAY(0)) /* CFG_MMC3_CLK_IN */ + 0x680 (A_DELAY(94) | G_DELAY(0)) /* CFG_MMC3_CLK_OUT */ + 0x684 (A_DELAY(122) | G_DELAY(0)) /* CFG_MMC3_CMD_IN */ + 0x688 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_CMD_OEN */ + 0x68c (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_CMD_OUT */ + 0x690 (A_DELAY(91) | G_DELAY(0)) /* CFG_MMC3_DAT0_IN */ + 0x694 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT0_OEN */ + 0x698 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT0_OUT */ + 0x69c (A_DELAY(57) | G_DELAY(0)) /* CFG_MMC3_DAT1_IN */ + 0x6a0 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT1_OEN */ + 0x6a4 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT1_OUT */ + 0x6a8 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT2_IN */ + 0x6ac (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT2_OEN */ + 0x6b0 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT2_OUT */ + 0x6b4 (A_DELAY(375) | G_DELAY(0)) /* CFG_MMC3_DAT3_IN */ + 0x6b8 (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT3_OEN */ + 0x6bc (A_DELAY(0) | G_DELAY(0)) /* CFG_MMC3_DAT3_OUT */ + >; + }; + + /* Corresponds to MMC4_MANUAL1 in datamanual */ + mmc4_iodelay_manual1_conf: mmc4_iodelay_manual1_conf { + pinctrl-single,pins = < + 0x840 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART1_CTSN_IN */ + 0x848 (A_DELAY(1147) | G_DELAY(0)) /* CFG_UART1_CTSN_OUT */ + 0x84c (A_DELAY(1834) | G_DELAY(0)) /* CFG_UART1_RTSN_IN */ + 0x850 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART1_RTSN_OEN */ + 0x854 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART1_RTSN_OUT */ + 0x870 (A_DELAY(2165) | G_DELAY(0)) /* CFG_UART2_CTSN_IN */ + 0x874 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_CTSN_OEN */ + 0x878 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_CTSN_OUT */ + 0x87c (A_DELAY(1929) | G_DELAY(64)) /* CFG_UART2_RTSN_IN */ + 0x880 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RTSN_OEN */ + 0x884 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RTSN_OUT */ + 0x888 (A_DELAY(1935) | G_DELAY(128)) /* CFG_UART2_RXD_IN */ + 0x88c (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RXD_OEN */ + 0x890 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RXD_OUT */ + 0x894 (A_DELAY(2172) | G_DELAY(44)) /* CFG_UART2_TXD_IN */ + 0x898 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_TXD_OEN */ + 0x89c (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_TXD_OUT */ + >; + }; + + /* Corresponds to MMC4_DS_MANUAL1 in datamanual */ + mmc4_iodelay_default_conf: mmc4_iodelay_default_conf { + pinctrl-single,pins = < + 0x840 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART1_CTSN_IN */ + 0x848 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART1_CTSN_OUT */ + 0x84c (A_DELAY(307) | G_DELAY(0)) /* CFG_UART1_RTSN_IN */ + 0x850 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART1_RTSN_OEN */ + 0x854 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART1_RTSN_OUT */ + 0x870 (A_DELAY(785) | G_DELAY(0)) /* CFG_UART2_CTSN_IN */ + 0x874 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_CTSN_OEN */ + 0x878 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_CTSN_OUT */ + 0x87c (A_DELAY(613) | G_DELAY(0)) /* CFG_UART2_RTSN_IN */ + 0x880 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RTSN_OEN */ + 0x884 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RTSN_OUT */ + 0x888 (A_DELAY(683) | G_DELAY(0)) /* CFG_UART2_RXD_IN */ + 0x88c (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RXD_OEN */ + 0x890 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_RXD_OUT */ + 0x894 (A_DELAY(835) | G_DELAY(0)) /* CFG_UART2_TXD_IN */ + 0x898 (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_TXD_OEN */ + 0x89c (A_DELAY(0) | G_DELAY(0)) /* CFG_UART2_TXD_OUT */ + >; + }; +}; diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi new file mode 100644 index 000000000000..6edc1d40fe19 --- /dev/null +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -0,0 +1,81 @@ +/* + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "dra74x.dtsi" + +/ { + compatible = "ti,dra762", "ti,dra7"; + + ocp { + cal: cal@4845b000 { + compatible = "ti,dra72-cal"; + ti,hwmods = "cal"; + reg = <0x489B0000 0x400>, + <0x489B0800 0x40>, + <0x489B0900 0x40>, + <0x4A0026DC 0x4>; + reg-names = "cal_top", + "cal_rx_core0", + "cal_rx_core1", + "camerrx_control"; + interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + csi2_0: port@0 { + reg = <0>; + }; + csi2_1: port@1 { + reg = <1>; + }; + }; + }; + }; +}; + +/* MCAN interrupts are hard-wired to irqs 67, 68 */ +&crossbar_mpu { + ti,irqs-skip = <10 67 68 133 139 140>; +}; + +&cpu0_opp_table { + opp_plus@1800000000 { + opp-hz = /bits/ 64 <1800000000>; + opp-microvolt = <1250000 950000 1250000>; + opp-supported-hw = <0xFF 0x08>; + }; +}; + +&oppdm_mpu { + ti,efuse-settings = < + /* uV offset */ + 1060000 0x0 + 1160000 0x4 + 1210000 0x8 + 1250000 0xC + >; +}; + +&abb_mpu { + ti,abb_info = < + /*uV ABB efuse rbb_m fbb_m vset_m*/ + 1060000 0 0x0 0 0x02000000 0x01F00000 + 1160000 0 0x4 0 0x02000000 0x01F00000 + 1210000 0 0x8 0 0x02000000 0x01F00000 + 1250000 0 0xC 0 0x02000000 0x01F00000 + >; +}; + +&mmc3 { + max-frequency = <96000000>; +}; diff --git a/arch/arm/boot/dts/dra7x-evm-fpd-auo-g101evn01.0.dtsi b/arch/arm/boot/dts/dra7x-evm-fpd-auo-g101evn01.0.dtsi new file mode 100644 index 000000000000..c928be92c1ac --- /dev/null +++ b/arch/arm/boot/dts/dra7x-evm-fpd-auo-g101evn01.0.dtsi @@ -0,0 +1,107 @@ +/* + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/ { + backlight { + compatible = "led-backlight"; + leds = <&backlight_led>; + brightness-levels = <0 2 38 74 110 146 182 218 255>; + default-brightness-level = <8>; + + enable-gpios = <&pcf_display_board 0 GPIO_ACTIVE_LOW>; + }; + + lcd_fpd: display { + compatible = "auo,g101evn01.0", "panel-dpi"; + + label = "lcd_fpd"; + status = "disabled"; + + panel-timing { + clock-frequency = <68930000>; + hactive = <1280>; + vactive = <800>; + + hfront-porch = <48>; + hsync-len = <32>; + hback-porch = <48>; + + vfront-porch = <4>; + vsync-len = <4>; + vback-porch = <8>; + + hsync-active = <0>; + vsync-active = <0>; + de-active = <1>; + pixelclk-active = <1>; + }; + + port { + fpd_in: endpoint { + }; + }; + }; +}; + +&disp_ser { + + /* + * 0x2c - deserializer + * 0x40 - TLC59108 + * 0x27 - PCF8575 + * 0x57 - EEPROM + * 0x14 - Goodix Touch Controller + * 0x28 - RF430CL330H + */ + + disp_des: deserializer@2c { + #address-cells = <1>; + #size-cells = <0>; + compatible = "ti,ds90ub924q"; + reg = <0x2c>; + slave-mode; + }; + + /* TLC chip for LCD panel power and backlight */ + fpd_disp: tlc59108@40 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "ti,tlc59108"; + reg = <0x40>; + + backlight_led: bl@2 { + label = "backlight"; + reg = <0x2>; + }; + }; + + pcf_display_board: gpio@27 { + compatible = "nxp,pcf8575"; + reg = <0x27>; + gpio-controller; + #gpio-cells = <2>; + }; + + touchscreen: goodix-gt9271@14 { + status = "okay"; + compatible = "goodix,gt9271"; + reg = <0x14>; + + touchscreen-size-x = <1280>; + touchscreen-size-y = <800>; + touchscreen-inverted-y; + + /* Reset gpio line is inverted before going to touch panel */ + reset-gpios = <&pcf_display_board 5 GPIO_ACTIVE_LOW>; + irq-gpios = <&pcf_display_board 6 GPIO_ACTIVE_HIGH>; + }; + + /* Below two slaves on the I2C bus are not yet defined */ + /* ID EEPROM 0x57 */ + /* RF430CL330H 0x28 */ +}; diff --git a/arch/arm/boot/dts/dra7x-evm-fpd-lg.dtsi b/arch/arm/boot/dts/dra7x-evm-fpd-lg.dtsi new file mode 100644 index 000000000000..b4760b4efdad --- /dev/null +++ b/arch/arm/boot/dts/dra7x-evm-fpd-lg.dtsi @@ -0,0 +1,59 @@ +/* + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <dt-bindings/gpio/gpio.h> + + +/ { + lcd_fpd: display_fpd { + /* + * This is not really a dpi panel, but panel-dpi driver + * works as dummy panel driver. + */ + compatible = "lg,lp101wx2", "panel-dpi"; + + label = "lcd_fpd"; + status = "disabled"; + + panel-timing { + clock-frequency = <69300404>; + hactive = <1280>; + vactive = <800>; + + hfront-porch = <48>; + hback-porch = <44>; + hsync-len = <32>; + + vfront-porch = <4>; + vback-porch = <7>; + vsync-len = <12>; + + hsync-active = <0>; + vsync-active = <0>; + de-active = <1>; + pixelclk-active = <0>; + }; + + port { + fpd_in: endpoint { + }; + }; + }; +}; + +&disp_ser { + disp_des: deserializer@2c { + compatible = "ti,ds90uh928q"; + reg = <0x2c>; + slave-mode; + }; + fpd_disp: tlc59108@1c { + compatible = "ti,tlc59108"; + reg = <0x1c>; + }; +}; diff --git a/arch/arm/boot/dts/dra7x-evm-lcd-lg.dtsi b/arch/arm/boot/dts/dra7x-evm-lcd-lg.dtsi index 97939eef7b94..23268b7a474f 100644 --- a/arch/arm/boot/dts/dra7x-evm-lcd-lg.dtsi +++ b/arch/arm/boot/dts/dra7x-evm-lcd-lg.dtsi @@ -12,7 +12,6 @@ aliases { display0 = &tlc59108; display1 = &hdmi0; - display2 = &fpd_disp; }; backlight { @@ -51,7 +50,7 @@ hsync-active = <0>; vsync-active = <0>; de-active = <1>; - pixelclk-active = <1>; + pixelclk-active = <0>; }; port { diff --git a/arch/arm/boot/dts/dra7x-evm-lcd-osd.dtsi b/arch/arm/boot/dts/dra7x-evm-lcd-osd.dtsi index 219e4f953797..7dc9c986a73a 100644 --- a/arch/arm/boot/dts/dra7x-evm-lcd-osd.dtsi +++ b/arch/arm/boot/dts/dra7x-evm-lcd-osd.dtsi @@ -10,7 +10,6 @@ aliases { display0 = &lcd; display1 = &hdmi0; - display2 = &fpd_disp; }; lcd_bl: backlight { diff --git a/arch/arm/boot/dts/dra7xx-jamr3.dtsi b/arch/arm/boot/dts/dra7xx-jamr3.dtsi index 994c6e735789..894e97f93775 100644 --- a/arch/arm/boot/dts/dra7xx-jamr3.dtsi +++ b/arch/arm/boot/dts/dra7xx-jamr3.dtsi @@ -47,7 +47,17 @@ <&hwspinlock 6>, <&hwspinlock 7>, <&hwspinlock 8>, - <&hwspinlock 9>; + <&hwspinlock 9>, + <&hwspinlock 10>, + <&hwspinlock 11>, + <&hwspinlock 12>, + <&hwspinlock 13>, + <&hwspinlock 14>, + <&hwspinlock 15>, + <&hwspinlock 16>, + <&hwspinlock 17>, + <&hwspinlock 18>, + <&hwspinlock 19>; }; sr0 { diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi index 4b0ec0703825..8ca9217204a0 100644 --- a/arch/arm/boot/dts/imx6dl.dtsi +++ b/arch/arm/boot/dts/imx6dl.dtsi @@ -30,7 +30,7 @@ /* kHz uV */ 996000 1250000 792000 1175000 - 396000 1075000 + 396000 1150000 >; fsl,soc-operating-points = < /* ARM kHz SOC-PU uV */ diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 5f5e0f3d5b64..27cd4abfc74d 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -697,6 +697,8 @@ vmmc_aux-supply = <&vsim>; bus-width = <8>; non-removable; + no-sdio; + no-sd; }; &mmc3 { diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index f648ec2dd5a6..304bcf9b630e 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -1022,6 +1022,7 @@ phy-names = "sata-phy"; clocks = <&sata_ref_clk>; ti,hwmods = "sata"; + ports-implemented = <0x1>; }; dss: dss@58000000 { diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index 4dfca8fc49b3..1bc61ece2589 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -856,6 +856,13 @@ compatible = "atmel,at91sam9260-usart"; reg = <0xf801c000 0x100>; interrupts = <24 IRQ_TYPE_LEVEL_HIGH 7>; + dmas = <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(35))>, + <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(36))>; + dma-names = "tx", "rx"; clocks = <&uart0_clk>; clock-names = "usart"; status = "disabled"; @@ -865,6 +872,13 @@ compatible = "atmel,at91sam9260-usart"; reg = <0xf8020000 0x100>; interrupts = <25 IRQ_TYPE_LEVEL_HIGH 7>; + dmas = <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(37))>, + <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(38))>; + dma-names = "tx", "rx"; clocks = <&uart1_clk>; clock-names = "usart"; status = "disabled"; @@ -874,6 +888,13 @@ compatible = "atmel,at91sam9260-usart"; reg = <0xf8024000 0x100>; interrupts = <26 IRQ_TYPE_LEVEL_HIGH 7>; + dmas = <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(39))>, + <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(40))>; + dma-names = "tx", "rx"; clocks = <&uart2_clk>; clock-names = "usart"; status = "disabled"; @@ -985,6 +1006,13 @@ compatible = "atmel,at91sam9260-usart"; reg = <0xfc008000 0x100>; interrupts = <27 IRQ_TYPE_LEVEL_HIGH 7>; + dmas = <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(41))>, + <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(42))>; + dma-names = "tx", "rx"; clocks = <&uart3_clk>; clock-names = "usart"; status = "disabled"; @@ -993,6 +1021,13 @@ uart4: serial@fc00c000 { compatible = "atmel,at91sam9260-usart"; reg = <0xfc00c000 0x100>; + dmas = <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(43))>, + <&dma0 + (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) | + AT91_XDMAC_DT_PERID(44))>; + dma-names = "tx", "rx"; interrupts = <28 IRQ_TYPE_LEVEL_HIGH 7>; clocks = <&uart4_clk>; clock-names = "usart"; diff --git a/arch/arm/boot/dts/tegra20-paz00.dts b/arch/arm/boot/dts/tegra20-paz00.dts index ed7e1009326c..d9ee0fd817e9 100644 --- a/arch/arm/boot/dts/tegra20-paz00.dts +++ b/arch/arm/boot/dts/tegra20-paz00.dts @@ -565,6 +565,7 @@ regulator-name = "+3VS,vdd_pnl"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + regulator-boot-on; gpio = <&gpio TEGRA_GPIO(A, 4) GPIO_ACTIVE_HIGH>; enable-active-high; }; diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig index f3142369f594..01116ee1284b 100644 --- a/arch/arm/configs/s3c2410_defconfig +++ b/arch/arm/configs/s3c2410_defconfig @@ -87,9 +87,9 @@ CONFIG_IPV6_TUNNEL=m CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_SCTP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index 679c589c4828..1f7b98e1a00d 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -369,7 +369,7 @@ static struct crypto_alg aes_algs[] = { { .cra_blkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = ce_aes_setkey, .encrypt = ecb_encrypt, .decrypt = ecb_decrypt, @@ -446,7 +446,7 @@ static struct crypto_alg aes_algs[] = { { .cra_ablkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = ablk_set_key, .encrypt = ablk_encrypt, .decrypt = ablk_decrypt, diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index d2315ffd8f12..f13ae153fb24 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -112,12 +112,8 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs); #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 -/* This is the location that an ET_DYN program is loaded if exec'ed. Typical - use of this is to invoke "./ld.so someprog" to test out a new version of - the loader. We need to make sure that it is out of the way of the program - that it will "exec", and that there is sufficient room for the brk. */ - -#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) +/* This is the base location for PIE (ET_DYN with INTERP) loads. */ +#define ELF_ET_DYN_BASE 0x400000UL /* When the program starts, a1 contains a pointer to a function to be registered with atexit, as per the SVR4 ABI. A value of 0 means we diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h index bfe2a2f5a644..22b73112b75f 100644 --- a/arch/arm/include/asm/ftrace.h +++ b/arch/arm/include/asm/ftrace.h @@ -54,6 +54,24 @@ static inline void *return_address(unsigned int level) #define ftrace_return_address(n) return_address(n) +#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME + +static inline bool arch_syscall_match_sym_name(const char *sym, + const char *name) +{ + if (!strcmp(sym, "sys_mmap2")) + sym = "sys_mmap_pgoff"; + else if (!strcmp(sym, "sys_statfs64_wrapper")) + sym = "sys_statfs64"; + else if (!strcmp(sym, "sys_fstatfs64_wrapper")) + sym = "sys_fstatfs64"; + else if (!strcmp(sym, "sys_arm_fadvise64_64")) + sym = "sys_fadvise64_64"; + + /* Ignore case since sym may start with "SyS" instead of "sys" */ + return !strcasecmp(sym, name); +} + #endif /* ifndef __ASSEMBLY__ */ #endif /* _ASM_ARM_FTRACE */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index c7ba9a42e857..ebf866a3a8c8 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -205,18 +205,12 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, * and iterate over the range. */ - bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached; - VM_BUG_ON(size & ~PAGE_MASK); - if (!need_flush && !icache_is_pipt()) - goto vipt_cache; - while (size) { void *va = kmap_atomic_pfn(pfn); - if (need_flush) - kvm_flush_dcache_to_poc(va, PAGE_SIZE); + kvm_flush_dcache_to_poc(va, PAGE_SIZE); if (icache_is_pipt()) __cpuc_coherent_user_range((unsigned long)va, @@ -228,7 +222,6 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, kunmap_atomic(va); } -vipt_cache: if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) { /* any kind of VIPT cache */ __flush_icache_all(); diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 80856def2465..82bdac0f2804 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -73,7 +73,6 @@ obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_xscale.o perf_event_v6.o \ perf_event_v7.o -CFLAGS_pj4-cp0.o := -marm AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o obj-$(CONFIG_VDSO) += vdso.o diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c index 8153e36b2491..7c9248b74d3f 100644 --- a/arch/arm/kernel/pj4-cp0.c +++ b/arch/arm/kernel/pj4-cp0.c @@ -66,9 +66,13 @@ static void __init pj4_cp_access_write(u32 value) __asm__ __volatile__ ( "mcr p15, 0, %1, c1, c0, 2\n\t" +#ifdef CONFIG_THUMB2_KERNEL + "isb\n\t" +#else "mrc p15, 0, %0, c1, c0, 2\n\t" "mov %0, %0\n\t" "sub pc, pc, #4\n\t" +#endif : "=r" (temp) : "r" (value)); } diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 4d9375814b53..d54c53b7ab63 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { int ret; - struct pt_regs newregs; + struct pt_regs newregs = *task_pt_regs(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index 54a5aeab988d..bbbffe946122 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -17,6 +17,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/cache.h> #include <linux/elf.h> #include <linux/err.h> #include <linux/kernel.h> @@ -39,7 +40,7 @@ static struct page **vdso_text_pagelist; /* Total number of pages needed for the data and text portions of the VDSO. */ -unsigned int vdso_total_pages __read_mostly; +unsigned int vdso_total_pages __ro_after_init; /* * The VDSO data page. @@ -47,13 +48,13 @@ unsigned int vdso_total_pages __read_mostly; static union vdso_data_store vdso_data_store __page_aligned_data; static struct vdso_data *vdso_data = &vdso_data_store.data; -static struct page *vdso_data_page; -static struct vm_special_mapping vdso_data_mapping = { +static struct page *vdso_data_page __ro_after_init; +static const struct vm_special_mapping vdso_data_mapping = { .name = "[vvar]", .pages = &vdso_data_page, }; -static struct vm_special_mapping vdso_text_mapping = { +static struct vm_special_mapping vdso_text_mapping __ro_after_init = { .name = "[vdso]", }; @@ -67,7 +68,7 @@ struct elfinfo { /* Cached result of boot-time check for whether the arch timer exists, * and if so, whether the virtual counter is useable. */ -static bool cntvct_ok __read_mostly; +static bool cntvct_ok __ro_after_init; static bool __init cntvct_functional(void) { @@ -224,7 +225,7 @@ static int install_vvar(struct mm_struct *mm, unsigned long addr) VM_READ | VM_MAYREAD, &vdso_data_mapping); - return IS_ERR(vma) ? PTR_ERR(vma) : 0; + return PTR_ERR_OR_ZERO(vma); } /* assumes mmap_sem is write-locked */ diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S index 3988e72d16ff..bfc5aae0c280 100644 --- a/arch/arm/kvm/init.S +++ b/arch/arm/kvm/init.S @@ -110,7 +110,6 @@ __do_hyp_init: @ - Write permission implies XN: disabled @ - Instruction cache: enabled @ - Data/Unified cache: enabled - @ - Memory alignment checks: enabled @ - MMU: enabled (this code must be run from an identity mapping) mrc p15, 4, r0, c1, c0, 0 @ HSCR ldr r2, =HSCTLR_MASK @@ -118,8 +117,8 @@ __do_hyp_init: mrc p15, 0, r1, c1, c0, 0 @ SCTLR ldr r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C) and r1, r1, r2 - ARM( ldr r2, =(HSCTLR_M | HSCTLR_A) ) - THUMB( ldr r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE) ) + ARM( ldr r2, =(HSCTLR_M) ) + THUMB( ldr r2, =(HSCTLR_M | HSCTLR_TE) ) orr r1, r1, r2 orr r0, r0, r1 isb diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 767872411d97..360cea172b06 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -301,6 +301,14 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, next = kvm_pgd_addr_end(addr, end); if (!pgd_none(*pgd)) unmap_puds(kvm, pgd, addr, next); + /* + * If we are dealing with a large range in + * stage2 table, release the kvm->mmu_lock + * to prevent starvation and lockup detector + * warnings. + */ + if (kvm && (next != end)) + cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } @@ -745,6 +753,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) */ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) { + assert_spin_locked(&kvm->mmu_lock); unmap_range(kvm, kvm->arch.pgd, start, size); } @@ -803,6 +812,7 @@ void stage2_unmap_vm(struct kvm *kvm) int idx; idx = srcu_read_lock(&kvm->srcu); + down_read(¤t->mm->mmap_sem); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); @@ -810,6 +820,7 @@ void stage2_unmap_vm(struct kvm *kvm) stage2_unmap_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); + up_read(¤t->mm->mmap_sem); srcu_read_unlock(&kvm->srcu, idx); } @@ -829,7 +840,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) if (kvm->arch.pgd == NULL) return; + spin_lock(&kvm->mmu_lock); unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + spin_unlock(&kvm->mmu_lock); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); if (KVM_PREALLOC_LEVEL > 0) kfree(kvm->arch.pgd); @@ -862,6 +876,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pmd_t *pmd; pud = stage2_get_pud(kvm, cache, addr); + if (!pud) + return NULL; + if (pud_none(*pud)) { if (!cache) return NULL; @@ -1619,12 +1636,16 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) { + if (!kvm->arch.pgd) + return 0; trace_kvm_age_hva(start, end); return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); } int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) { + if (!kvm->arch.pgd) + return 0; trace_kvm_test_age_hva(hva); return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); } @@ -1771,6 +1792,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, (KVM_PHYS_SIZE >> PAGE_SHIFT)) return -EFAULT; + down_read(¤t->mm->mmap_sem); /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them to find out if we can map @@ -1814,8 +1836,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) - return -EINVAL; + if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + ret = -EINVAL; + goto out; + } ret = kvm_phys_addr_ioremap(kvm, gpa, pa, vm_end - vm_start, @@ -1827,7 +1851,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } while (hva < reg_end); if (change == KVM_MR_FLAGS_ONLY) - return ret; + goto out; spin_lock(&kvm->mmu_lock); if (ret) @@ -1835,6 +1859,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, else stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); +out: + up_read(¤t->mm->mmap_sem); return ret; } diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index a9b3b905e661..443db0c43d7c 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -208,9 +208,10 @@ int kvm_psci_version(struct kvm_vcpu *vcpu) static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { - int ret = 1; + struct kvm *kvm = vcpu->kvm; unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); unsigned long val; + int ret = 1; switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: @@ -230,7 +231,9 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; case PSCI_0_2_FN_CPU_ON: case PSCI_0_2_FN64_CPU_ON: + mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); + mutex_unlock(&kvm->lock); break; case PSCI_0_2_FN_AFFINITY_INFO: case PSCI_0_2_FN64_AFFINITY_INFO: @@ -279,6 +282,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); unsigned long val; @@ -288,7 +292,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) val = PSCI_RET_SUCCESS; break; case KVM_PSCI_FN_CPU_ON: + mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); + mutex_unlock(&kvm->lock); break; default: val = PSCI_RET_NOT_SUPPORTED; diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 8ecfd15c3a02..df73914e81c8 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -67,7 +67,7 @@ ENTRY(__get_user_4) ENDPROC(__get_user_4) ENTRY(__get_user_8) - check_uaccess r0, 8, r1, r2, __get_user_bad + check_uaccess r0, 8, r1, r2, __get_user_bad8 #ifdef CONFIG_THUMB2_KERNEL 5: TUSER(ldr) r2, [r0] 6: TUSER(ldr) r3, [r0, #4] diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 23726fb31741..d687f860a2da 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -286,6 +286,22 @@ static void at91_ddr_standby(void) at91_ramc_write(1, AT91_DDRSDRC_LPR, saved_lpr1); } +static void sama5d3_ddr_standby(void) +{ + u32 lpr0; + u32 saved_lpr0; + + saved_lpr0 = at91_ramc_read(0, AT91_DDRSDRC_LPR); + lpr0 = saved_lpr0 & ~AT91_DDRSDRC_LPCB; + lpr0 |= AT91_DDRSDRC_LPCB_POWER_DOWN; + + at91_ramc_write(0, AT91_DDRSDRC_LPR, lpr0); + + cpu_do_idle(); + + at91_ramc_write(0, AT91_DDRSDRC_LPR, saved_lpr0); +} + /* We manage both DDRAM/SDRAM controllers, we need more than one value to * remember. */ @@ -320,7 +336,7 @@ static const struct of_device_id const ramc_ids[] __initconst = { { .compatible = "atmel,at91rm9200-sdramc", .data = at91rm9200_standby }, { .compatible = "atmel,at91sam9260-sdramc", .data = at91sam9_sdram_standby }, { .compatible = "atmel,at91sam9g45-ddramc", .data = at91_ddr_standby }, - { .compatible = "atmel,sama5d3-ddramc", .data = at91_ddr_standby }, + { .compatible = "atmel,sama5d3-ddramc", .data = sama5d3_ddr_standby }, { /*sentinel*/ } }; diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index e71fcd7b5acb..0cef41dc85e2 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -284,6 +284,7 @@ MACHINE_END #ifdef CONFIG_SOC_DRA7XX static const char *const dra74x_boards_compat[] __initconst = { + "ti,dra76", "ti,am5728", "ti,am5726", "ti,dra742", diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 84ee6027e20c..5a357f5a1b6c 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -647,6 +647,15 @@ void __init dra7xxx_check_revision(void) hawkeye = (idcode >> 12) & 0xffff; rev = (idcode >> 28) & 0xff; switch (hawkeye) { + case 0xbb50: + switch (rev) { + case 0: + default: + omap_revision = DRA762_REV_ES1_0; + break; + } + break; + case 0xb990: switch (rev) { case 0: @@ -668,9 +677,12 @@ void __init dra7xxx_check_revision(void) omap_revision = DRA722_REV_ES1_0; break; case 1: - default: omap_revision = DRA722_REV_ES2_0; break; + case 2: + default: + omap_revision = DRA722_REV_ES2_1; + break; } break; diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S index 6d1dffca6c7b..748dde9fa4a5 100644 --- a/arch/arm/mach-omap2/omap-headsmp.S +++ b/arch/arm/mach-omap2/omap-headsmp.S @@ -17,6 +17,7 @@ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include "omap44xx.h" @@ -56,7 +57,7 @@ wait_2: ldr r2, =AUX_CORE_BOOT0_PA @ read from AuxCoreBoot0 cmp r0, r4 bne wait_2 ldr r12, =API_HYP_ENTRY - adr r0, hyp_boot + badr r0, hyp_boot smc #0 hyp_boot: b secondary_startup diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index acc38a3213e7..6c3d89694b14 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -254,7 +254,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus) if (cpu_is_omap446x()) startup_addr = omap4460_secondary_startup; - if (soc_is_dra74x() || soc_is_omap54xx()) + if (soc_is_dra74x() || soc_is_omap54xx() || soc_is_dra76x()) omap5_erratum_workaround_801819(); /* diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index adcfe4642a04..2028a81e13e6 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -375,6 +375,21 @@ static struct omap_hwmod dra7xx_cal_hwmod = { }, }; +static struct omap_hwmod dra76x_cal_hwmod = { + .name = "cal", + .class = &dra7xx_cal_hwmod_class, + .clkdm_name = "cam_clkdm", + .main_clk = "vip3_gclk_mux", + .flags = (HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY), + .prcm = { + .omap4 = { + .clkctrl_offs = DRA7XX_CM_CAM_VIP3_CLKCTRL_OFFSET, + .context_offs = DRA7XX_RM_CAM_VIP3_CONTEXT_OFFSET, + .modulemode = MODULEMODE_HWCTRL, + }, + }, +}; + /* * 'counter' class * @@ -3276,6 +3291,28 @@ static struct omap_hwmod dra7xx_wd_timer2_hwmod = { }, }; +/* + * 'mcan' class + * + */ +static struct omap_hwmod_class dra76x_mcan_hwmod_class = { + .name = "mcan", +}; + +/* mcan */ +static struct omap_hwmod dra76x_mcan_hwmod = { + .name = "mcan", + .class = &dra76x_mcan_hwmod_class, + .clkdm_name = "wkupaon_clkdm", + .main_clk = "mcan_clk", + .prcm = { + .omap4 = { + .clkctrl_offs = DRA7XX_CM_WKUPAON_ADC_CLKCTRL_OFFSET, + .context_offs = DRA7XX_RM_WKUPAON_ADC_CONTEXT_OFFSET, + .modulemode = MODULEMODE_SWCTRL, + }, + }, +}; /* * Interfaces @@ -4542,6 +4579,14 @@ static struct omap_hwmod_ocp_if dra7xx_l4_per3__cal = { .user = OCP_USER_MPU | OCP_USER_SDMA, }; +/* l4_per3 -> dra76x_cal */ +static struct omap_hwmod_ocp_if dra76x_l4_per3__cal = { + .master = &dra7xx_l4_per3_hwmod, + .slave = &dra76x_cal_hwmod, + .clk = "l3_iclk_div", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + /* l4_wkup -> wd_timer2 */ static struct omap_hwmod_ocp_if dra7xx_l4_wkup__wd_timer2 = { .master = &dra7xx_l4_wkup_hwmod, @@ -4550,6 +4595,14 @@ static struct omap_hwmod_ocp_if dra7xx_l4_wkup__wd_timer2 = { .user = OCP_USER_MPU | OCP_USER_SDMA, }; +/* l3_main_1 -> mcan */ +static struct omap_hwmod_ocp_if dra76x_l3_main_1__mcan = { + .master = &dra7xx_l3_main_1_hwmod, + .slave = &dra76x_mcan_hwmod, + .clk = "l3_iclk_div", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { &dra7xx_l3_main_1__dmm, &dra7xx_l3_main_2__l3_instr, @@ -4700,6 +4753,17 @@ static struct omap_hwmod_ocp_if *dra7xx_gp_hwmod_ocp_ifs[] __initdata = { }; /* SoC variant specific hwmod links */ +static struct omap_hwmod_ocp_if *dra76x_hwmod_ocp_ifs[] __initdata = { + &dra7xx_l4_per3__usb_otg_ss4, + &dra7xx_l4_per3__vip2, + &dra7xx_l3_main_1__mmu0_dsp2, + &dra7xx_l3_main_1__mmu1_dsp2, + &dra7xx_dsp2__l3_main_1, + &dra76x_l3_main_1__mcan, + &dra76x_l4_per3__cal, + NULL, +}; + static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = { &dra7xx_l4_per3__usb_otg_ss4, &dra7xx_l4_per3__vip2, @@ -4731,12 +4795,14 @@ int __init dra7xx_hwmod_init(void) ret = omap_hwmod_register_links(dra74x_hwmod_ocp_ifs); else if (!ret && soc_is_dra72x()) ret = omap_hwmod_register_links(dra72x_hwmod_ocp_ifs); + else if (!ret && soc_is_dra76x()) + ret = omap_hwmod_register_links(dra76x_hwmod_ocp_ifs); if (!ret && omap_type() == OMAP2_DEVICE_TYPE_GP) ret = omap_hwmod_register_links(dra7xx_gp_hwmod_ocp_ifs); - /* now for the IPs *NOT* in dra71 */ - if (!ret && !of_machine_is_compatible("ti,dra718")) + /* now for the IPs available only in dra74 and dra72 */ + if (!ret && !of_machine_is_compatible("ti,dra718") && !soc_is_dra76x()) ret = omap_hwmod_register_links(dra74x_dra72x_hwmod_ocp_ifs); return ret; diff --git a/arch/arm/mach-omap2/powerdomains7xx_data.c b/arch/arm/mach-omap2/powerdomains7xx_data.c index 0a6caa6e14e5..2497e6f04ea0 100644 --- a/arch/arm/mach-omap2/powerdomains7xx_data.c +++ b/arch/arm/mach-omap2/powerdomains7xx_data.c @@ -29,6 +29,7 @@ #include "prcm44xx.h" #include "prm7xx.h" #include "prcm_mpu7xx.h" +#include "soc.h" /* iva_7xx_pwrdm: IVA-HD power domain */ static struct powerdomain iva_7xx_pwrdm = { @@ -63,6 +64,14 @@ static struct powerdomain custefuse_7xx_pwrdm = { .flags = PWRDM_HAS_LOWPOWERSTATECHANGE, }; +/* custefuse_aon_7xx_pwrdm: Customer efuse controller power domain */ +static struct powerdomain custefuse_aon_7xx_pwrdm = { + .name = "custefuse_pwrdm", + .prcm_offs = DRA7XX_PRM_CUSTEFUSE_INST, + .prcm_partition = DRA7XX_PRM_PARTITION, + .pwrsts = PWRSTS_ON, +}; + /* ipu_7xx_pwrdm: Audio back end power domain */ static struct powerdomain ipu_7xx_pwrdm = { .name = "ipu_pwrdm", @@ -350,7 +359,6 @@ static struct powerdomain eve1_7xx_pwrdm = { static struct powerdomain *powerdomains_dra7xx[] __initdata = { &iva_7xx_pwrdm, &rtc_7xx_pwrdm, - &custefuse_7xx_pwrdm, &ipu_7xx_pwrdm, &dss_7xx_pwrdm, &l4per_7xx_pwrdm, @@ -374,9 +382,32 @@ static struct powerdomain *powerdomains_dra7xx[] __initdata = { NULL }; +static struct powerdomain *powerdomains_dra76x[] __initdata = { + &custefuse_aon_7xx_pwrdm, + NULL +}; + +static struct powerdomain *powerdomains_dra74x[] __initdata = { + &custefuse_7xx_pwrdm, + NULL +}; + +static struct powerdomain *powerdomains_dra72x[] __initdata = { + &custefuse_aon_7xx_pwrdm, + NULL +}; + void __init dra7xx_powerdomains_init(void) { pwrdm_register_platform_funcs(&omap4_pwrdm_operations); pwrdm_register_pwrdms(powerdomains_dra7xx); + + if (soc_is_dra76x()) + pwrdm_register_pwrdms(powerdomains_dra76x); + else if (soc_is_dra74x()) + pwrdm_register_pwrdms(powerdomains_dra74x); + else if (soc_is_dra72x()) + pwrdm_register_pwrdms(powerdomains_dra72x); + pwrdm_complete_init(); } diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h index 1e11307fd766..1ae1b6fe0370 100644 --- a/arch/arm/mach-omap2/soc.h +++ b/arch/arm/mach-omap2/soc.h @@ -239,6 +239,7 @@ IS_TI_SUBCLASS(816x, 0x816) IS_TI_SUBCLASS(814x, 0x814) IS_AM_SUBCLASS(335x, 0x335) IS_AM_SUBCLASS(437x, 0x437) +IS_DRA_SUBCLASS(76x, 0x76) IS_DRA_SUBCLASS(75x, 0x75) IS_DRA_SUBCLASS(72x, 0x72) @@ -262,6 +263,7 @@ IS_DRA_SUBCLASS(72x, 0x72) #define soc_is_omap54xx() 0 #define soc_is_omap543x() 0 #define soc_is_dra7xx() 0 +#define soc_is_dra76x() 0 #define soc_is_dra74x() 0 #define soc_is_dra72x() 0 @@ -412,9 +414,11 @@ IS_OMAP_TYPE(3430, 0x3430) #if defined(CONFIG_SOC_DRA7XX) #undef soc_is_dra7xx +#undef soc_is_dra76x #undef soc_is_dra74x #undef soc_is_dra72x #define soc_is_dra7xx() is_dra7xx() +#define soc_is_dra76x() is_dra76x() #define soc_is_dra74x() is_dra75x() #define soc_is_dra72x() is_dra72x() #endif @@ -484,11 +488,13 @@ IS_OMAP_TYPE(3430, 0x3430) #define OMAP5432_REV_ES2_0 (OMAP54XX_CLASS | (0x32 << 16) | (0x20 << 8)) #define DRA7XX_CLASS 0x07000000 +#define DRA762_REV_ES1_0 (DRA7XX_CLASS | (0x62 << 16) | (0x10 << 8)) #define DRA752_REV_ES1_0 (DRA7XX_CLASS | (0x52 << 16) | (0x10 << 8)) #define DRA752_REV_ES1_1 (DRA7XX_CLASS | (0x52 << 16) | (0x11 << 8)) #define DRA752_REV_ES2_0 (DRA7XX_CLASS | (0x52 << 16) | (0x20 << 8)) #define DRA722_REV_ES1_0 (DRA7XX_CLASS | (0x22 << 16) | (0x10 << 8)) #define DRA722_REV_ES2_0 (DRA7XX_CLASS | (0x22 << 16) | (0x20 << 8)) +#define DRA722_REV_ES2_1 (DRA7XX_CLASS | (0x22 << 16) | (0x21 << 8)) void omap2xxx_check_revision(void); void omap3xxx_check_revision(void); diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 25f0eee33869..a67af98e532b 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -561,8 +561,7 @@ void __init omap_init_time(void) __omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon", 2, "timer_sys_ck", NULL, false); - if (of_have_populated_dt()) - clocksource_probe(); + clocksource_probe(); } #if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM43XX) @@ -570,6 +569,8 @@ void __init omap3_secure_sync32k_timer_init(void) { __omap_sync32k_timer_init(12, "secure_32k_fck", "ti,timer-secure", 2, "timer_sys_ck", NULL, false); + + clocksource_probe(); } #endif /* CONFIG_ARCH_OMAP3 */ @@ -579,6 +580,7 @@ void __init omap3_gptimer_timer_init(void) { __omap_sync32k_timer_init(2, "timer_sys_ck", NULL, 1, "timer_sys_ck", "ti,timer-alwon", true); + if (of_have_populated_dt()) clocksource_probe(); } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 506c225c66cc..c73f10c1984f 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -610,9 +610,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr, void __init early_abt_enable(void) { - fsr_info[22].fn = early_abort_handler; + fsr_info[FSR_FS_AEA].fn = early_abort_handler; local_abt_enable(); - fsr_info[22].fn = do_bad; + fsr_info[FSR_FS_AEA].fn = do_bad; } #ifndef CONFIG_ARM_LPAE diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index 05ec5e0df32d..78830657cab3 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -11,11 +11,15 @@ #define FSR_FS5_0 (0x3f) #ifdef CONFIG_ARM_LPAE +#define FSR_FS_AEA 17 + static inline int fsr_fs(unsigned int fsr) { return fsr & FSR_FS5_0; } #else +#define FSR_FS_AEA 22 + static inline int fsr_fs(unsigned int fsr) { return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6; diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 66353caa35b9..641334ebf46d 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -89,7 +89,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -140,7 +140,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index de9f8921e407..aead23f15213 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1184,15 +1184,15 @@ void __init sanity_check_meminfo(void) high_memory = __va(arm_lowmem_limit - 1) + 1; + if (!memblock_limit) + memblock_limit = arm_lowmem_limit; + /* * Round the memblock limit down to a pmd size. This * helps to ensure that we will allocate memory from the * last full pmd, which should be mapped. */ - if (memblock_limit) - memblock_limit = round_down(memblock_limit, PMD_SIZE); - if (!memblock_limit) - memblock_limit = arm_lowmem_limit; + memblock_limit = round_down(memblock_limit, PMD_SIZE); memblock_set_current_limit(memblock_limit); } diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 1160434eece0..59a8fa7b8a3b 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -74,5 +74,5 @@ $(MODLIB)/vdso: FORCE @mkdir -p $(MODLIB)/vdso PHONY += vdso_install -vdso_install: $(obj)/vdso.so.dbg $(MODLIB)/vdso FORCE +vdso_install: $(obj)/vdso.so.dbg $(MODLIB)/vdso $(call cmd,vdso_install) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 2543791ce8c2..049335584e0c 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -141,6 +141,18 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN config ARCH_MMAP_RND_COMPAT_BITS_MAX default 16 +config ARM64_PAGE_SHIFT + int + default 16 if ARM64_64K_PAGES + default 14 if ARM64_16K_PAGES + default 12 + +config ARM64_CONT_SHIFT + int + default 5 if ARM64_64K_PAGES + default 7 if ARM64_16K_PAGES + default 4 + config NO_IOPORT_MAP def_bool y if !PCI @@ -569,6 +581,7 @@ source kernel/Kconfig.preempt source kernel/Kconfig.hz config ARCH_SUPPORTS_DEBUG_PAGEALLOC + depends on !HIBERNATION def_bool y config ARCH_HAS_HOLES_MEMORYMODEL @@ -618,6 +631,27 @@ config SECCOMP and the task is only allowed to execute a few safe syscalls defined by each seccomp mode. +config KEXEC + depends on PM_SLEEP_SMP + select KEXEC_CORE + bool "kexec system call" + ---help--- + kexec is a system call that implements the ability to shutdown your + current kernel, and to start another kernel. It is like a reboot + but it is independent of the system firmware. And like a reboot + you can start any kernel with it, not just Linux. + +config CRASH_DUMP + bool "Build kdump crash kernel" + help + Generate crash dump after being started by kexec. This should + be normally only set in special crash dump kernels which are + loaded in the main kernel with kexec-tools into a specially + reserved region and then later executed after a crash by + kdump/kexec. + + For more details see Documentation/kdump/kdump.txt + config XEN_DOM0 def_bool y depends on XEN @@ -720,7 +754,7 @@ config SETEND_EMULATION endif config ARM64_SW_TTBR0_PAN - bool "Emulate Priviledged Access Never using TTBR0_EL1 switching" + bool "Emulate Privileged Access Never using TTBR0_EL1 switching" help Enabling this option prevents the kernel from accessing user-space memory directly by pointing TTBR0_EL1 to a reserved @@ -934,6 +968,26 @@ config BUILD_ARM64_APPENDED_DTB_IMAGE DTBs to be built by default (instead of a standalone Image.gz.) The image will built in arch/arm64/boot/Image.gz-dtb +choice + prompt "Appended DTB Kernel Image name" + depends on BUILD_ARM64_APPENDED_DTB_IMAGE + help + Enabling this option will cause a specific kernel image Image or + Image.gz to be used for final image creation. + The image will built in arch/arm64/boot/IMAGE-NAME-dtb + + config IMG_GZ_DTB + bool "Image.gz-dtb" + config IMG_DTB + bool "Image-dtb" +endchoice + +config BUILD_ARM64_APPENDED_KERNEL_IMAGE_NAME + string + depends on BUILD_ARM64_APPENDED_DTB_IMAGE + default "Image.gz-dtb" if IMG_GZ_DTB + default "Image-dtb" if IMG_DTB + config BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES string "Default dtb names" depends on BUILD_ARM64_APPENDED_DTB_IMAGE diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 101632379b8b..f1d8a05727cf 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -61,7 +61,9 @@ head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) -TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}') +TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \ + int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \ + rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}") else TEXT_OFFSET := 0x00080000 endif @@ -85,7 +87,7 @@ core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a # Default target when executing plain make ifeq ($(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE),y) -KBUILD_IMAGE := Image.gz-dtb +KBUILD_IMAGE := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_KERNEL_IMAGE_NAME)) else KBUILD_IMAGE := Image.gz endif @@ -128,6 +130,16 @@ archclean: $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=$(boot)/dts +# We need to generate vdso-offsets.h before compiling certain files in kernel/. +# In order to do that, we should use the archprepare target, but we can't since +# asm-offsets.h is included in some files used to generate vdso-offsets.h, and +# asm-offsets.h is built in prepare0, for which archprepare is a dependency. +# Therefore we need to generate the header after prepare0 has been made, hence +# this hack. +prepare: vdso_prepare +vdso_prepare: prepare0 + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h + define archhelp echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)' echo ' Image - Uncompressed kernel image (arch/$(ARCH)/boot/Image)' diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts index 93bc3d7d51c0..29315af22147 100644 --- a/arch/arm64/boot/dts/arm/juno-r1.dts +++ b/arch/arm64/boot/dts/arm/juno-r1.dts @@ -60,6 +60,28 @@ }; }; + idle-states { + entry-method = "arm,psci"; + + CPU_SLEEP_0: cpu-sleep-0 { + compatible = "arm,idle-state"; + arm,psci-suspend-param = <0x0010000>; + local-timer-stop; + entry-latency-us = <300>; + exit-latency-us = <1200>; + min-residency-us = <2000>; + }; + + CLUSTER_SLEEP_0: cluster-sleep-0 { + compatible = "arm,idle-state"; + arm,psci-suspend-param = <0x1010000>; + local-timer-stop; + entry-latency-us = <400>; + exit-latency-us = <1200>; + min-residency-us = <2500>; + }; + }; + A57_0: cpu@0 { compatible = "arm,cortex-a57","arm,armv8"; reg = <0x0 0x0>; @@ -67,6 +89,7 @@ enable-method = "psci"; next-level-cache = <&A57_L2>; clocks = <&scpi_dvfs 0>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; }; A57_1: cpu@1 { @@ -76,6 +99,7 @@ enable-method = "psci"; next-level-cache = <&A57_L2>; clocks = <&scpi_dvfs 0>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; }; A53_0: cpu@100 { @@ -85,6 +109,7 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; }; A53_1: cpu@101 { @@ -94,6 +119,7 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; }; A53_2: cpu@102 { @@ -103,6 +129,7 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; }; A53_3: cpu@103 { @@ -112,6 +139,7 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; }; A57_L2: l2-cache0 { diff --git a/arch/arm64/boot/dts/arm/juno-sched-energy.dtsi b/arch/arm64/boot/dts/arm/juno-sched-energy.dtsi new file mode 100644 index 000000000000..38207e4391ab --- /dev/null +++ b/arch/arm64/boot/dts/arm/juno-sched-energy.dtsi @@ -0,0 +1,147 @@ +/* + * ARM JUNO specific energy cost model data. There are no unit requirements for + * the data. Data can be normalized to any reference point, but the + * normalization must be consistent. That is, one bogo-joule/watt must be the + * same quantity for all data, but we don't care what it is. + */ + +/* static struct idle_state idle_states_cluster_a53[] = { */ +/* { .power = 56 }, /\* arch_cpu_idle() (active idle) = WFI *\/ */ +/* { .power = 56 }, /\* WFI *\/ */ +/* { .power = 56 }, /\* cpu-sleep-0 *\/ */ +/* { .power = 17 }, /\* cluster-sleep-0 *\/ */ +/* }; */ + +/* static struct idle_state idle_states_cluster_a57[] = { */ +/* { .power = 65 }, /\* arch_cpu_idle() (active idle) = WFI *\/ */ +/* { .power = 65 }, /\* WFI *\/ */ +/* { .power = 65 }, /\* cpu-sleep-0 *\/ */ +/* { .power = 24 }, /\* cluster-sleep-0 *\/ */ +/* }; */ + +/* static struct capacity_state cap_states_cluster_a53[] = { */ +/* /\* Power per cluster *\/ */ +/* { .cap = 235, .power = 26, }, /\* 450 MHz *\/ */ +/* { .cap = 303, .power = 30, }, /\* 575 MHz *\/ */ +/* { .cap = 368, .power = 39, }, /\* 700 MHz *\/ */ +/* { .cap = 406, .power = 47, }, /\* 775 MHz *\/ */ +/* { .cap = 447, .power = 57, }, /\* 850 Mhz *\/ */ +/* }; */ + +/* static struct capacity_state cap_states_cluster_a57[] = { */ +/* /\* Power per cluster *\/ */ +/* { .cap = 417, .power = 24, }, /\* 450 MHz *\/ */ +/* { .cap = 579, .power = 32, }, /\* 625 MHz *\/ */ +/* { .cap = 744, .power = 43, }, /\* 800 MHz *\/ */ +/* { .cap = 883, .power = 49, }, /\* 950 MHz *\/ */ +/* { .cap = 1024, .power = 64, }, /\* 1100 MHz *\/ */ +/* }; */ + +/* static struct sched_group_energy energy_cluster_a53 = { */ +/* .nr_idle_states = ARRAY_SIZE(idle_states_cluster_a53), */ +/* .idle_states = idle_states_cluster_a53, */ +/* .nr_cap_states = ARRAY_SIZE(cap_states_cluster_a53), */ +/* .cap_states = cap_states_cluster_a53, */ +/* }; */ + +/* static struct sched_group_energy energy_cluster_a57 = { */ +/* .nr_idle_states = ARRAY_SIZE(idle_states_cluster_a57), */ +/* .idle_states = idle_states_cluster_a57, */ +/* .nr_cap_states = ARRAY_SIZE(cap_states_cluster_a57), */ +/* .cap_states = cap_states_cluster_a57, */ +/* }; */ + +/* static struct idle_state idle_states_core_a53[] = { */ +/* { .power = 6 }, /\* arch_cpu_idle() (active idle) = WFI *\/ */ +/* { .power = 6 }, /\* WFI *\/ */ +/* { .power = 0 }, /\* cpu-sleep-0 *\/ */ +/* { .power = 0 }, /\* cluster-sleep-0 *\/ */ +/* }; */ + +/* static struct idle_state idle_states_core_a57[] = { */ +/* { .power = 15 }, /\* arch_cpu_idle() (active idle) = WFI *\/ */ +/* { .power = 15 }, /\* WFI *\/ */ +/* { .power = 0 }, /\* cpu-sleep-0 *\/ */ +/* { .power = 0 }, /\* cluster-sleep-0 *\/ */ +/* }; */ + +/* static struct capacity_state cap_states_core_a53[] = { */ +/* /\* Power per cpu *\/ */ +/* { .cap = 235, .power = 33, }, /\* 450 MHz *\/ */ +/* { .cap = 302, .power = 46, }, /\* 575 MHz *\/ */ +/* { .cap = 368, .power = 61, }, /\* 700 MHz *\/ */ +/* { .cap = 406, .power = 76, }, /\* 775 MHz *\/ */ +/* { .cap = 447, .power = 93, }, /\* 850 Mhz *\/ */ +/* }; */ + +/* static struct capacity_state cap_states_core_a57[] = { */ +/* /\* Power per cpu *\/ */ +/* { .cap = 417, .power = 168, }, /\* 450 MHz *\/ */ +/* { .cap = 579, .power = 251, }, /\* 625 MHz *\/ */ +/* { .cap = 744, .power = 359, }, /\* 800 MHz *\/ */ +/* { .cap = 883, .power = 479, }, /\* 950 MHz *\/ */ +/* { .cap = 1024, .power = 616, }, /\* 1100 MHz *\/ */ +/* }; */ + +energy-costs { + CPU_COST_A57: core-cost0 { + busy-cost-data = < + 417 168 + 579 251 + 744 359 + 883 479 + 1023 616 + >; + idle-cost-data = < + 15 + 15 + 0 + 0 + >; + }; + CPU_COST_A53: core-cost1 { + busy-cost-data = < + 235 33 + 302 46 + 368 61 + 406 76 + 447 93 + >; + idle-cost-data = < + 6 + 6 + 0 + 0 + >; + }; + CLUSTER_COST_A57: cluster-cost0 { + busy-cost-data = < + 417 24 + 579 32 + 744 43 + 883 49 + 1024 64 + >; + idle-cost-data = < + 65 + 65 + 65 + 24 + >; + }; + CLUSTER_COST_A53: cluster-cost1 { + busy-cost-data = < + 235 26 + 303 30 + 368 39 + 406 47 + 447 57 + >; + idle-cost-data = < + 56 + 56 + 56 + 17 + >; + }; +}; diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts index 3e1a84b01b50..68816f71fa51 100644 --- a/arch/arm64/boot/dts/arm/juno.dts +++ b/arch/arm64/boot/dts/arm/juno.dts @@ -60,6 +60,28 @@ }; }; + idle-states { + entry-method = "arm,psci"; + + CPU_SLEEP_0: cpu-sleep-0 { + compatible = "arm,idle-state"; + arm,psci-suspend-param = <0x0010000>; + local-timer-stop; + entry-latency-us = <300>; + exit-latency-us = <1200>; + min-residency-us = <2000>; + }; + + CLUSTER_SLEEP_0: cluster-sleep-0 { + compatible = "arm,idle-state"; + arm,psci-suspend-param = <0x1010000>; + local-timer-stop; + entry-latency-us = <400>; + exit-latency-us = <1200>; + min-residency-us = <2500>; + }; + }; + A57_0: cpu@0 { compatible = "arm,cortex-a57","arm,armv8"; reg = <0x0 0x0>; @@ -67,6 +89,8 @@ enable-method = "psci"; next-level-cache = <&A57_L2>; clocks = <&scpi_dvfs 0>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A57 &CLUSTER_COST_A57>; }; A57_1: cpu@1 { @@ -76,6 +100,8 @@ enable-method = "psci"; next-level-cache = <&A57_L2>; clocks = <&scpi_dvfs 0>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A57 &CLUSTER_COST_A57>; }; A53_0: cpu@100 { @@ -85,6 +111,8 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; }; A53_1: cpu@101 { @@ -94,6 +122,8 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; }; A53_2: cpu@102 { @@ -103,6 +133,8 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; }; A53_3: cpu@103 { @@ -112,6 +144,8 @@ enable-method = "psci"; next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; }; A57_L2: l2-cache0 { @@ -121,6 +155,8 @@ A53_L2: l2-cache1 { compatible = "cache"; }; + + /include/ "juno-sched-energy.dtsi" }; pmu_a57 { diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts index ce5d848251fa..7b34822d61e9 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts +++ b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts @@ -26,7 +26,7 @@ stdout-path = "serial0:115200n8"; }; - memory { + memory@0 { device_type = "memory"; reg = <0x0 0x0 0x40000000>; }; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 857eda5c7217..172402cc1a0f 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -71,7 +71,7 @@ <1 10 0xf01>; }; - amba_apu { + amba_apu: amba_apu@0 { compatible = "simple-bus"; #address-cells = <2>; #size-cells = <1>; @@ -191,7 +191,7 @@ }; i2c0: i2c@ff020000 { - compatible = "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 17 4>; @@ -202,7 +202,7 @@ }; i2c1: i2c@ff030000 { - compatible = "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 18 4>; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 79717faf2161..7dc5e58f7b7a 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -58,6 +58,8 @@ CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index 2cf32e9887e1..de1aab4b5da8 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -23,6 +23,11 @@ config CRYPTO_GHASH_ARM64_CE depends on ARM64 && KERNEL_MODE_NEON select CRYPTO_HASH +config CRYPTO_POLY_HASH_ARM64_CE + tristate "poly_hash (for HEH encryption mode) using ARMv8 Crypto Extensions" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_HASH + config CRYPTO_AES_ARM64_CE tristate "AES core cipher using ARMv8 Crypto Extensions" depends on ARM64 && KERNEL_MODE_NEON diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index abb79b3cfcfe..f0a8f2475ea3 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -17,6 +17,9 @@ sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o +obj-$(CONFIG_CRYPTO_POLY_HASH_ARM64_CE) += poly-hash-ce.o +poly-hash-ce-y := poly-hash-ce-glue.o poly-hash-ce-core.o + obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 6a51dfccfe71..448b874a4826 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -294,7 +294,7 @@ static struct crypto_alg aes_algs[] = { { .cra_blkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = aes_setkey, .encrypt = ecb_encrypt, .decrypt = ecb_decrypt, @@ -371,7 +371,7 @@ static struct crypto_alg aes_algs[] = { { .cra_ablkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = ablk_set_key, .encrypt = ablk_encrypt, .decrypt = ablk_decrypt, diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index c53dbeae79f2..838dad5c209f 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt) cbz w6, .Lcbcencloop ld1 {v0.16b}, [x5] /* get iv */ - enc_prepare w3, x2, x5 + enc_prepare w3, x2, x6 .Lcbcencloop: ld1 {v1.16b}, [x1], #16 /* get next pt block */ eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */ - encrypt_block v0, w3, x2, x5, w6 + encrypt_block v0, w3, x2, x6, w7 st1 {v0.16b}, [x0], #16 subs w4, w4, #1 bne .Lcbcencloop + st1 {v0.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_encrypt) @@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt) cbz w6, .LcbcdecloopNx ld1 {v7.16b}, [x5] /* get iv */ - dec_prepare w3, x2, x5 + dec_prepare w3, x2, x6 .LcbcdecloopNx: #if INTERLEAVE >= 2 @@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt) .Lcbcdecloop: ld1 {v1.16b}, [x1], #16 /* get next ct block */ mov v0.16b, v1.16b /* ...and copy to v0 */ - decrypt_block v0, w3, x2, x5, w6 + decrypt_block v0, w3, x2, x6, w7 eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */ mov v7.16b, v1.16b /* ct is next iv */ st1 {v0.16b}, [x0], #16 @@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt) bne .Lcbcdecloop .Lcbcdecout: FRAME_POP + st1 {v7.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_decrypt) @@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt) AES_ENTRY(aes_ctr_encrypt) FRAME_PUSH - cbnz w6, .Lctrfirst /* 1st time around? */ - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 -#if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ - bcs .Lctrinc - add x5, x5, #1 /* increment BE ctr */ - b .LctrincNx -#else - b .Lctrinc -#endif -.Lctrfirst: + cbz w6, .Lctrnotfirst /* 1st time around? */ enc_prepare w3, x2, x6 ld1 {v4.16b}, [x5] - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 + +.Lctrnotfirst: + umov x8, v4.d[1] /* keep swabbed ctr in reg */ + rev x8, x8 #if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ + cmn w8, w4 /* 32 bit overflow? */ bcs .Lctrloop .LctrloopNx: subs w4, w4, #INTERLEAVE @@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt) #if INTERLEAVE == 2 mov v0.8b, v4.8b mov v1.8b, v4.8b - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v0.d[1], x7 - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v1.d[1], x7 ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */ do_encrypt_block2x @@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt) st1 {v0.16b-v1.16b}, [x0], #32 #else ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ - dup v7.4s, w5 + dup v7.4s, w8 mov v0.16b, v4.16b add v7.4s, v7.4s, v8.4s mov v1.16b, v4.16b @@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt) eor v2.16b, v7.16b, v2.16b eor v3.16b, v5.16b, v3.16b st1 {v0.16b-v3.16b}, [x0], #64 - add x5, x5, #INTERLEAVE + add x8, x8, #INTERLEAVE #endif - cbz w4, .LctroutNx -.LctrincNx: - rev x7, x5 + rev x7, x8 ins v4.d[1], x7 + cbz w4, .Lctrout b .LctrloopNx -.LctroutNx: - sub x5, x5, #1 - rev x7, x5 - ins v4.d[1], x7 - b .Lctrout .Lctr1x: adds w4, w4, #INTERLEAVE beq .Lctrout @@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt) .Lctrloop: mov v0.16b, v4.16b encrypt_block v0, w3, x2, x6, w7 + + adds x8, x8, #1 /* increment BE ctr */ + rev x7, x8 + ins v4.d[1], x7 + bcs .Lctrcarry /* overflow? */ + +.Lctrcarrydone: subs w4, w4, #1 bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */ ld1 {v3.16b}, [x1], #16 eor v3.16b, v0.16b, v3.16b st1 {v3.16b}, [x0], #16 - beq .Lctrout -.Lctrinc: - adds x5, x5, #1 /* increment BE ctr */ - rev x7, x5 - ins v4.d[1], x7 - bcc .Lctrloop /* no overflow? */ - umov x7, v4.d[0] /* load upper word of ctr */ - rev x7, x7 /* ... to handle the carry */ - add x7, x7, #1 - rev x7, x7 - ins v4.d[0], x7 - b .Lctrloop + bne .Lctrloop + +.Lctrout: + st1 {v4.16b}, [x5] /* return next CTR value */ + FRAME_POP + ret + .Lctrhalfblock: ld1 {v3.8b}, [x1] eor v3.8b, v0.8b, v3.8b st1 {v3.8b}, [x0] -.Lctrout: FRAME_POP ret + +.Lctrcarry: + umov x7, v4.d[0] /* load upper word of ctr */ + rev x7, x7 /* ... to handle the carry */ + add x7, x7, #1 + rev x7, x7 + ins v4.d[0], x7 + b .Lctrcarrydone AES_ENDPROC(aes_ctr_encrypt) .ltorg diff --git a/arch/arm64/crypto/poly-hash-ce-core.S b/arch/arm64/crypto/poly-hash-ce-core.S new file mode 100644 index 000000000000..8ccb544c5526 --- /dev/null +++ b/arch/arm64/crypto/poly-hash-ce-core.S @@ -0,0 +1,163 @@ +/* + * Accelerated poly_hash implementation with ARMv8 PMULL instructions. + * + * Based on ghash-ce-core.S. + * + * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2017 Google, Inc. <ebiggers@google.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + + KEY .req v0 + KEY2 .req v1 + T1 .req v2 + T2 .req v3 + GSTAR .req v4 + XL .req v5 + XM .req v6 + XH .req v7 + + .text + .arch armv8-a+crypto + + /* 16-byte aligned (2**4 = 16); not required, but might as well */ + .align 4 +.Lgstar: + .quad 0x87, 0x87 + +/* + * void pmull_poly_hash_update(le128 *digest, const le128 *key, + * const u8 *src, unsigned int blocks, + * unsigned int partial); + */ +ENTRY(pmull_poly_hash_update) + + /* Load digest into XL */ + ld1 {XL.16b}, [x0] + + /* Load key into KEY */ + ld1 {KEY.16b}, [x1] + + /* Load g*(x) = g(x) + x^128 = x^7 + x^2 + x + 1 into both halves of + * GSTAR */ + adr x1, .Lgstar + ld1 {GSTAR.2d}, [x1] + + /* Set KEY2 to (KEY[1]+KEY[0]):(KEY[1]+KEY[0]). This is needed for + * Karatsuba multiplication. */ + ext KEY2.16b, KEY.16b, KEY.16b, #8 + eor KEY2.16b, KEY2.16b, KEY.16b + + /* If 'partial' is nonzero, then we're finishing a pending block and + * should go right to the multiplication. */ + cbnz w4, 1f + +0: + /* Add the next block from 'src' to the digest */ + ld1 {T1.16b}, [x2], #16 + eor XL.16b, XL.16b, T1.16b + sub w3, w3, #1 + +1: + /* + * Multiply the current 128-bit digest (a1:a0, in XL) by the 128-bit key + * (b1:b0, in KEY) using Karatsuba multiplication. + */ + + /* T1 = (a1+a0):(a1+a0) */ + ext T1.16b, XL.16b, XL.16b, #8 + eor T1.16b, T1.16b, XL.16b + + /* XH = a1 * b1 */ + pmull2 XH.1q, XL.2d, KEY.2d + + /* XL = a0 * b0 */ + pmull XL.1q, XL.1d, KEY.1d + + /* XM = (a1+a0) * (b1+b0) */ + pmull XM.1q, T1.1d, KEY2.1d + + /* XM += (XH[0]:XL[1]) + XL + XH */ + ext T1.16b, XL.16b, XH.16b, #8 + eor T2.16b, XL.16b, XH.16b + eor XM.16b, XM.16b, T1.16b + eor XM.16b, XM.16b, T2.16b + + /* + * Now the 256-bit product is in XH[1]:XM:XL[0]. It represents a + * polynomial over GF(2) with degree as large as 255. We need to + * compute its remainder modulo g(x) = x^128+x^7+x^2+x+1. For this it + * is sufficient to compute the remainder of the high half 'c(x)x^128' + * add it to the low half. To reduce the high half we use the Barrett + * reduction method. The basic idea is that we can express the + * remainder p(x) as g(x)q(x) mod x^128, where q(x) = (c(x)x^128)/g(x). + * As detailed in [1], to avoid having to divide by g(x) at runtime the + * following equivalent expression can be derived: + * + * p(x) = [ g*(x)((c(x)q+(x))/x^128) ] mod x^128 + * + * where g*(x) = x^128+g(x) = x^7+x^2+x+1, and q+(x) = x^256/g(x) = g(x) + * in this case. This is also equivalent to: + * + * p(x) = [ g*(x)((c(x)(x^128 + g*(x)))/x^128) ] mod x^128 + * = [ g*(x)(c(x) + (c(x)g*(x))/x^128) ] mod x^128 + * + * Since deg g*(x) < 64: + * + * p(x) = [ g*(x)(c(x) + ((c(x)/x^64)g*(x))/x^64) ] mod x^128 + * = [ g*(x)((c(x)/x^64)x^64 + (c(x) mod x^64) + + * ((c(x)/x^64)g*(x))/x^64) ] mod x^128 + * + * Letting t(x) = g*(x)(c(x)/x^64): + * + * p(x) = [ t(x)x^64 + g*(x)((c(x) mod x^64) + t(x)/x^64) ] mod x^128 + * + * Therefore, to do the reduction we only need to issue two 64-bit => + * 128-bit carryless multiplications: g*(x) times c(x)/x^64, and g*(x) + * times ((c(x) mod x^64) + t(x)/x^64). (Multiplication by x^64 doesn't + * count since it is simply a shift or move.) + * + * An alternate reduction method, also based on Barrett reduction and + * described in [1], uses only shifts and XORs --- no multiplications. + * However, the method with multiplications requires fewer instructions + * and is faster on processors with fast carryless multiplication. + * + * [1] "Intel Carry-Less Multiplication Instruction and its Usage for + * Computing the GCM Mode", + * https://software.intel.com/sites/default/files/managed/72/cc/clmul-wp-rev-2.02-2014-04-20.pdf + */ + + /* 256-bit product is XH[1]:XM:XL[0], so c(x) is XH[1]:XM[1] */ + + /* T1 = t(x) = g*(x)(c(x)/x^64) */ + pmull2 T1.1q, GSTAR.2d, XH.2d + + /* T2 = g*(x)((c(x) mod x^64) + t(x)/x^64) */ + eor T2.16b, XM.16b, T1.16b + pmull2 T2.1q, GSTAR.2d, T2.2d + + /* Make XL[0] be the low half of the 128-bit result by adding the low 64 + * bits of the T2 term to what was already there. The 't(x)x^64' term + * makes no difference, so skip it. */ + eor XL.16b, XL.16b, T2.16b + + /* Make XL[1] be the high half of the 128-bit result by adding the high + * 64 bits of the 't(x)x^64' and T2 terms to what was already in XM[0], + * then moving XM[0] to XL[1]. */ + eor XM.16b, XM.16b, T1.16b + ext T2.16b, T2.16b, T2.16b, #8 + eor XM.16b, XM.16b, T2.16b + mov XL.d[1], XM.d[0] + + /* If more blocks remain, then loop back to process the next block; + * else, store the digest and return. */ + cbnz w3, 0b + st1 {XL.16b}, [x0] + ret +ENDPROC(pmull_poly_hash_update) diff --git a/arch/arm64/crypto/poly-hash-ce-glue.c b/arch/arm64/crypto/poly-hash-ce-glue.c new file mode 100644 index 000000000000..e195740c9ecf --- /dev/null +++ b/arch/arm64/crypto/poly-hash-ce-glue.c @@ -0,0 +1,166 @@ +/* + * Accelerated poly_hash implementation with ARMv8 PMULL instructions. + * + * Based on ghash-ce-glue.c. + * + * poly_hash is part of the HEH (Hash-Encrypt-Hash) encryption mode, proposed in + * Internet Draft https://tools.ietf.org/html/draft-cope-heh-01. + * + * poly_hash is very similar to GHASH: both algorithms are keyed hashes which + * interpret their input data as coefficients of a polynomial over GF(2^128), + * then calculate a hash value by evaluating that polynomial at the point given + * by the key, e.g. using Horner's rule. The difference is that poly_hash uses + * the more natural "ble" convention to represent GF(2^128) elements, whereas + * GHASH uses the less natural "lle" convention (see include/crypto/gf128mul.h). + * The ble convention makes it simpler to implement GF(2^128) multiplication. + * + * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2017 Google Inc. <ebiggers@google.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <crypto/b128ops.h> +#include <crypto/internal/hash.h> +#include <linux/cpufeature.h> +#include <linux/crypto.h> +#include <linux/module.h> + +/* + * Note: in this algorithm we currently use 'le128' to represent GF(2^128) + * elements, even though poly_hash-generic uses 'be128'. Both types are + * actually "wrong" because the elements are actually in 'ble' format, and there + * should be a ble type to represent this --- as well as lle, bbe, and lbe types + * for the other conventions for representing GF(2^128) elements. But + * practically it doesn't matter which type we choose here, so we just use le128 + * since it's arguably more accurate, while poly_hash-generic still has to use + * be128 because the generic GF(2^128) multiplication functions all take be128. + */ + +struct poly_hash_desc_ctx { + le128 digest; + unsigned int count; +}; + +asmlinkage void pmull_poly_hash_update(le128 *digest, const le128 *key, + const u8 *src, unsigned int blocks, + unsigned int partial); + +static int poly_hash_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) +{ + if (keylen != sizeof(le128)) { + crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + + memcpy(crypto_shash_ctx(tfm), key, sizeof(le128)); + return 0; +} + +static int poly_hash_init(struct shash_desc *desc) +{ + struct poly_hash_desc_ctx *ctx = shash_desc_ctx(desc); + + ctx->digest = (le128) { 0 }; + ctx->count = 0; + return 0; +} + +static int poly_hash_update(struct shash_desc *desc, const u8 *src, + unsigned int len) +{ + struct poly_hash_desc_ctx *ctx = shash_desc_ctx(desc); + unsigned int partial = ctx->count % sizeof(le128); + u8 *dst = (u8 *)&ctx->digest + partial; + + ctx->count += len; + + /* Finishing at least one block? */ + if (partial + len >= sizeof(le128)) { + const le128 *key = crypto_shash_ctx(desc->tfm); + + if (partial) { + /* Finish the pending block. */ + unsigned int n = sizeof(le128) - partial; + + len -= n; + do { + *dst++ ^= *src++; + } while (--n); + } + + /* + * Do the real work. If 'partial' is nonzero, this starts by + * multiplying 'digest' by 'key'. Then for each additional full + * block it adds the block to 'digest' and multiplies by 'key'. + */ + kernel_neon_begin_partial(8); + pmull_poly_hash_update(&ctx->digest, key, src, + len / sizeof(le128), partial); + kernel_neon_end(); + + src += len - (len % sizeof(le128)); + len %= sizeof(le128); + dst = (u8 *)&ctx->digest; + } + + /* Continue adding the next block to 'digest'. */ + while (len--) + *dst++ ^= *src++; + return 0; +} + +static int poly_hash_final(struct shash_desc *desc, u8 *out) +{ + struct poly_hash_desc_ctx *ctx = shash_desc_ctx(desc); + unsigned int partial = ctx->count % sizeof(le128); + + /* Finish the last block if needed. */ + if (partial) { + const le128 *key = crypto_shash_ctx(desc->tfm); + + kernel_neon_begin_partial(8); + pmull_poly_hash_update(&ctx->digest, key, NULL, 0, partial); + kernel_neon_end(); + } + + memcpy(out, &ctx->digest, sizeof(le128)); + return 0; +} + +static struct shash_alg poly_hash_alg = { + .digestsize = sizeof(le128), + .init = poly_hash_init, + .update = poly_hash_update, + .final = poly_hash_final, + .setkey = poly_hash_setkey, + .descsize = sizeof(struct poly_hash_desc_ctx), + .base = { + .cra_name = "poly_hash", + .cra_driver_name = "poly_hash-ce", + .cra_priority = 300, + .cra_ctxsize = sizeof(le128), + .cra_module = THIS_MODULE, + }, +}; + +static int __init poly_hash_ce_mod_init(void) +{ + return crypto_register_shash(&poly_hash_alg); +} + +static void __exit poly_hash_ce_mod_exit(void) +{ + crypto_unregister_shash(&poly_hash_alg); +} + +MODULE_DESCRIPTION("Polynomial evaluation hash using ARMv8 Crypto Extensions"); +MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>"); +MODULE_LICENSE("GPL v2"); + +module_cpu_feature_match(PMULL, poly_hash_ce_mod_init); +module_exit(poly_hash_ce_mod_exit); diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index aee323b13802..0a11cd502dbc 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -22,9 +22,9 @@ #define ACPI_MADT_GICC_LENGTH \ (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) -#define BAD_MADT_GICC_ENTRY(entry, end) \ - (!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) || \ - (entry)->header.length != ACPI_MADT_GICC_LENGTH) +#define BAD_MADT_GICC_ENTRY(entry, end) \ + (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \ + (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end)) /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 8746ff6abd77..55101bd86b98 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -2,6 +2,7 @@ #define __ASM_ALTERNATIVE_H #include <asm/cpufeature.h> +#include <asm/insn.h> #ifndef __ASSEMBLY__ @@ -90,34 +91,55 @@ void apply_alternatives(void *start, size_t length); .endm /* - * Begin an alternative code sequence. + * Alternative sequences + * + * The code for the case where the capability is not present will be + * assembled and linked as normal. There are no restrictions on this + * code. + * + * The code for the case where the capability is present will be + * assembled into a special section to be used for dynamic patching. + * Code for that case must: + * + * 1. Be exactly the same length (in bytes) as the default code + * sequence. * - * The code that follows this macro will be assembled and linked as - * normal. There are no restrictions on this code. + * 2. Not contain a branch target that is used outside of the + * alternative sequence it is defined in (branches into an + * alternative sequence are not fixed up). + */ + +/* + * Begin an alternative code sequence. */ .macro alternative_if_not cap + .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f .popsection 661: .endm +.macro alternative_if cap + .set .Lasm_alt_mode, 1 + .pushsection .altinstructions, "a" + altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f + .popsection + .pushsection .altinstr_replacement, "ax" + .align 2 /* So GAS knows label 661 is suitably aligned */ +661: +.endm + /* - * Provide the alternative code sequence. - * - * The code that follows this macro is assembled into a special - * section to be used for dynamic patching. Code that follows this - * macro must: - * - * 1. Be exactly the same length (in bytes) as the default code - * sequence. - * - * 2. Not contain a branch target that is used outside of the - * alternative sequence it is defined in (branches into an - * alternative sequence are not fixed up). + * Provide the other half of the alternative code sequence. */ .macro alternative_else -662: .pushsection .altinstr_replacement, "ax" +662: + .if .Lasm_alt_mode==0 + .pushsection .altinstr_replacement, "ax" + .else + .popsection + .endif 663: .endm @@ -125,11 +147,25 @@ void apply_alternatives(void *start, size_t length); * Complete an alternative code sequence. */ .macro alternative_endif -664: .popsection +664: + .if .Lasm_alt_mode==0 + .popsection + .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .endm +/* + * Provides a trivial alternative or default sequence consisting solely + * of NOPs. The number of NOPs is chosen automatically to match the + * previous case. + */ +.macro alternative_else_nop_endif +alternative_else + nops (662b-661b) / AARCH64_INSN_SIZE +alternative_endif +.endm + #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h new file mode 100644 index 000000000000..be2d2347d995 --- /dev/null +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -0,0 +1,13 @@ +#ifndef __ASM_ASM_UACCESS_H +#define __ASM_ASM_UACCESS_H + +/* + * Remove the address tag from a virtual address, if present. + */ + .macro clear_address_tag, dst, addr + tst \addr, #(1 << 55) + bic \dst, \addr, #(0xff << 56) + csel \dst, \dst, \addr, eq + .endm + +#endif diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index aeb4554b3af3..d8855ca6068a 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -108,6 +108,15 @@ .endm /* + * NOP sequence + */ + .macro nops, num + .rept \num + nop + .endr + .endm + +/* * Emit an entry into the exception table */ .macro _asm_extable, from, to @@ -383,15 +392,11 @@ alternative_endif */ .macro post_ttbr0_update_workaround #ifdef CONFIG_CAVIUM_ERRATUM_27456 -alternative_if_not ARM64_WORKAROUND_CAVIUM_27456 - nop - nop - nop -alternative_else +alternative_if ARM64_WORKAROUND_CAVIUM_27456 ic iallu dsb nsh isb -alternative_endif +alternative_else_nop_endif #endif .endm diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 9622eb48f894..0671711b46ab 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -20,6 +20,9 @@ #ifndef __ASSEMBLY__ +#define __nops(n) ".rept " #n "\nnop\n.endr\n" +#define nops(n) asm volatile(__nops(n)) + #define sev() asm volatile("sev" : : : "memory") #define wfe() asm volatile("wfe" : : : "memory") #define wfi() asm volatile("wfi" : : : "memory") @@ -41,23 +44,33 @@ #define smp_store_release(p, v) \ do { \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (__force typeof(*p)) (v) }; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("stlrb %w1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u8 *)__u.__c) \ + : "memory"); \ break; \ case 2: \ asm volatile ("stlrh %w1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u16 *)__u.__c) \ + : "memory"); \ break; \ case 4: \ asm volatile ("stlr %w1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u32 *)__u.__c) \ + : "memory"); \ break; \ case 8: \ asm volatile ("stlr %1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u64 *)__u.__c) \ + : "memory"); \ break; \ } \ } while (0) diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 22dda613f9c9..22aabdeacc24 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -155,5 +155,6 @@ int set_memory_ro(unsigned long addr, int numpages); int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); +int set_memory_valid(unsigned long addr, unsigned long size, int enable); #endif diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 510c7b404454..270c6b7b0a61 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -48,7 +48,7 @@ static inline unsigned long __xchg_case_##name(unsigned long x, \ " swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \ " nop\n" \ " " #nop_lse) \ - : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) \ + : "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr) \ : "r" (x) \ : cl); \ \ diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 7875c886ad24..cd3dfa346649 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -113,12 +113,11 @@ #define ELF_EXEC_PAGESIZE PAGE_SIZE /* - * This is the location that an ET_DYN program is loaded if exec'ed. Typical - * use of this is to invoke "./ld.so someprog" to test out a new version of - * the loader. We need to make sure that it is out of the way of the program - * that it will "exec", and that there is sufficient room for the brk. + * This is the base location for PIE (ET_DYN with INTERP) loads. On + * 64-bit, this is above 4GB to leave the entire 32-bit address + * space open for things that want to use the area for 32-bit pointers. */ -#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3) +#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3) #ifndef __ASSEMBLY__ @@ -169,7 +168,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #ifdef CONFIG_COMPAT -#define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3) +/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */ +#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL /* AArch32 registers. */ #define COMPAT_ELF_NGREG 18 diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index c93023dc42cd..2cd3b3251d3c 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -21,10 +21,7 @@ #include <linux/futex.h> #include <linux/uaccess.h> -#include <asm/alternative.h> -#include <asm/cpufeature.h> #include <asm/errno.h> -#include <asm/sysreg.h> #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \ do { \ diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 8740297dac77..1473fc2f7ab7 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -20,7 +20,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 6 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 9732908bfc8a..c72b8e201ab4 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -68,7 +68,11 @@ static inline void decode_ctrl_reg(u32 reg, /* Lengths */ #define ARM_BREAKPOINT_LEN_1 0x1 #define ARM_BREAKPOINT_LEN_2 0x3 +#define ARM_BREAKPOINT_LEN_3 0x7 #define ARM_BREAKPOINT_LEN_4 0xf +#define ARM_BREAKPOINT_LEN_5 0x1f +#define ARM_BREAKPOINT_LEN_6 0x3f +#define ARM_BREAKPOINT_LEN_7 0x7f #define ARM_BREAKPOINT_LEN_8 0xff /* Kernel stepping */ @@ -110,7 +114,7 @@ struct perf_event; struct pmu; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type); + int *gen_len, int *gen_type, int *offset); extern int arch_check_bp_in_kernelspace(struct perf_event *bp); extern int arch_validate_hwbkpt_settings(struct perf_event *bp); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h new file mode 100644 index 000000000000..e17f0529a882 --- /dev/null +++ b/arch/arm64/include/asm/kexec.h @@ -0,0 +1,98 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARM64_KEXEC_H +#define _ARM64_KEXEC_H + +/* Maximum physical address we can use pages from */ + +#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) + +/* Maximum address we can reach in physical address mode */ + +#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL) + +/* Maximum address we can use for the control code buffer */ + +#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL) + +#define KEXEC_CONTROL_PAGE_SIZE 4096 + +#define KEXEC_ARCH KEXEC_ARCH_AARCH64 + +#ifndef __ASSEMBLY__ + +/** + * crash_setup_regs() - save registers for the panic kernel + * + * @newregs: registers are saved here + * @oldregs: registers to be saved (may be %NULL) + */ + +static inline void crash_setup_regs(struct pt_regs *newregs, + struct pt_regs *oldregs) +{ + if (oldregs) { + memcpy(newregs, oldregs, sizeof(*newregs)); + } else { + u64 tmp1, tmp2; + + __asm__ __volatile__ ( + "stp x0, x1, [%2, #16 * 0]\n" + "stp x2, x3, [%2, #16 * 1]\n" + "stp x4, x5, [%2, #16 * 2]\n" + "stp x6, x7, [%2, #16 * 3]\n" + "stp x8, x9, [%2, #16 * 4]\n" + "stp x10, x11, [%2, #16 * 5]\n" + "stp x12, x13, [%2, #16 * 6]\n" + "stp x14, x15, [%2, #16 * 7]\n" + "stp x16, x17, [%2, #16 * 8]\n" + "stp x18, x19, [%2, #16 * 9]\n" + "stp x20, x21, [%2, #16 * 10]\n" + "stp x22, x23, [%2, #16 * 11]\n" + "stp x24, x25, [%2, #16 * 12]\n" + "stp x26, x27, [%2, #16 * 13]\n" + "stp x28, x29, [%2, #16 * 14]\n" + "mov %0, sp\n" + "stp x30, %0, [%2, #16 * 15]\n" + + "/* faked current PSTATE */\n" + "mrs %0, CurrentEL\n" + "mrs %1, SPSEL\n" + "orr %0, %0, %1\n" + "mrs %1, DAIF\n" + "orr %0, %0, %1\n" + "mrs %1, NZCV\n" + "orr %0, %0, %1\n" + /* pc */ + "adr %1, 1f\n" + "1:\n" + "stp %1, %0, [%2, #16 * 16]\n" + : "=&r" (tmp1), "=&r" (tmp2) + : "r" (newregs) + : "memory" + ); + } +} + +#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION) +extern bool crash_is_nosave(unsigned long pfn); +extern void crash_prepare_suspend(void); +extern void crash_post_resume(void); +#else +static inline bool crash_is_nosave(unsigned long pfn) {return false; } +static inline void crash_prepare_suspend(void) {} +static inline void crash_post_resume(void) {} +#endif + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 342a5ac2f3da..320dc9c7e4f4 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -237,8 +237,7 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, { void *va = page_address(pfn_to_page(pfn)); - if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached) - kvm_flush_dcache_to_poc(va, size); + kvm_flush_dcache_to_poc(va, size); if (!icache_is_aliasing()) { /* PIPT */ flush_icache_range((unsigned long)va, diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 990124a67eeb..5472251c8e6c 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -33,7 +33,7 @@ extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, - pgprot_t prot); + pgprot_t prot, bool allow_block_mappings); extern void *fixmap_remap_fdt(phys_addr_t dt_phys); #endif diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 4a32fd5f101d..e53d30c6f779 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -218,9 +218,11 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, * Update the saved TTBR0_EL1 of the scheduled-in task as the previous * value may have not been initialised yet (activate_mm caller) or the * ASID has changed since the last run (following the context switch - * of another thread of the same process). + * of another thread of the same process). Avoid setting the reserved + * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit). */ - update_saved_ttbr0(tsk, next); + if (next != &init_mm) + update_saved_ttbr0(tsk, next); } #define deactivate_mm(tsk,mm) do { } while (0) diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index fbafd0ad16df..fb2617df2de9 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -23,16 +23,8 @@ /* PAGE_SHIFT determines the page size */ /* CONT_SHIFT determines the number of pages which can be tracked together */ -#ifdef CONFIG_ARM64_64K_PAGES -#define PAGE_SHIFT 16 -#define CONT_SHIFT 5 -#elif defined(CONFIG_ARM64_16K_PAGES) -#define PAGE_SHIFT 14 -#define CONT_SHIFT 7 -#else -#define PAGE_SHIFT 12 -#define CONT_SHIFT 4 -#endif +#define PAGE_SHIFT CONFIG_ARM64_PAGE_SHIFT +#define CONT_SHIFT CONFIG_ARM64_CONT_SHIFT #define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 5eedfd83acc7..1528d52eb8c0 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -21,8 +21,6 @@ #include <uapi/asm/ptrace.h> -#define _PSR_PAN_BIT 22 - /* Current Exception Level values, as contained in CurrentEL */ #define CurrentEL_EL1 (1 << 2) #define CurrentEL_EL2 (2 << 2) diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 2013a4dc5124..1d3ff7e4a6c2 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -16,6 +16,19 @@ #ifndef __ASM_SMP_H #define __ASM_SMP_H +/* Values for secondary_data.status */ + +#define CPU_MMU_OFF (-1) +#define CPU_BOOT_SUCCESS (0) +/* The cpu invoked ops->cpu_die, synchronise it with cpu_kill */ +#define CPU_KILL_ME (1) +/* The cpu couldn't die gracefully and is looping in the kernel */ +#define CPU_STUCK_IN_KERNEL (2) +/* Fatal system error detected by secondary CPU, crash the system */ +#define CPU_PANIC_KERNEL (3) + +#ifndef __ASSEMBLY__ + #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/thread_info.h> @@ -54,11 +67,17 @@ asmlinkage void secondary_start_kernel(void); /* * Initial data for bringing up a secondary CPU. + * @stack - sp for the secondary CPU + * @status - Result passed back from the secondary CPU to + * indicate failure. */ struct secondary_data { void *stack; + long status; }; + extern struct secondary_data secondary_data; +extern long __early_cpu_boot_status; extern void secondary_entry(void); extern void arch_send_call_function_single_ipi(int cpu); @@ -77,5 +96,38 @@ extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); extern void cpu_die(void); +extern void cpu_die_early(void); + +static inline void cpu_park_loop(void) +{ + for (;;) { + wfe(); + wfi(); + } +} + +static inline void update_cpu_boot_status(int val) +{ + WRITE_ONCE(secondary_data.status, val); + /* Ensure the visibility of the status update */ + dsb(ishst); +} + +/* + * If a secondary CPU enters the kernel but fails to come online, + * (e.g. due to mismatched features), and cannot exit the kernel, + * we increment cpus_stuck_in_kernel and leave the CPU in a + * quiesecent loop within the kernel text. The memory containing + * this loop must not be re-used for anything else as the 'stuck' + * core is executing it. + * + * This function is used to inhibit features like kexec and hibernate. + */ +bool cpus_are_stuck_in_kernel(void); + +extern void smp_send_crash_stop(void); +extern bool smp_crash_stop_failed(void); + +#endif /* ifndef __ASSEMBLY__ */ #endif /* ifndef __ASM_SMP_H */ diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 43a66881fd57..73f5d548bba1 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -31,6 +31,12 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) unsigned int tmp; arch_spinlock_t lockval; + /* + * Ensure prior spin_lock operations to other locks have completed + * on this CPU before we test whether "lock" is locked. + */ + smp_mb(); + asm volatile( " sevl\n" "1: wfe\n" @@ -152,6 +158,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { + smp_mb(); /* See arch_spin_unlock_wait */ return !arch_spin_value_unlocked(READ_ONCE(*lock)); } diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index b3325a9cb90f..794d22603f04 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -47,10 +47,10 @@ typedef unsigned long mm_segment_t; struct thread_info { unsigned long flags; /* low level flags */ mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ #ifdef CONFIG_ARM64_SW_TTBR0_PAN u64 ttbr0; /* saved TTBR0_EL1 */ #endif - struct task_struct *task; /* main task structure */ int preempt_count; /* 0 => preemptable, <0 => bug */ int cpu; /* cpu */ }; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index c37c064d7cdd..064cef9ae2d1 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -18,19 +18,21 @@ #ifndef __ASM_UACCESS_H #define __ASM_UACCESS_H +#include <asm/alternative.h> +#include <asm/kernel-pgtable.h> +#include <asm/sysreg.h> + #ifndef __ASSEMBLY__ /* * User space memory access functions */ +#include <linux/bitops.h> #include <linux/string.h> #include <linux/thread_info.h> -#include <asm/alternative.h> #include <asm/cpufeature.h> -#include <asm/kernel-pgtable.h> #include <asm/ptrace.h> -#include <asm/sysreg.h> #include <asm/errno.h> #include <asm/memory.h> #include <asm/compiler.h> @@ -107,16 +109,24 @@ static inline void set_fs(mm_segment_t fs) */ #define __range_ok(addr, size) \ ({ \ + unsigned long __addr = (unsigned long __force)(addr); \ unsigned long flag, roksum; \ __chk_user_ptr(addr); \ asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls" \ : "=&r" (flag), "=&r" (roksum) \ - : "1" (addr), "Ir" (size), \ + : "1" (__addr), "Ir" (size), \ "r" (current_thread_info()->addr_limit) \ : "cc"); \ flag; \ }) +/* + * When dealing with data aborts, watchpoints, or instruction traps we may end + * up with a tagged userland pointer. Clear the tag to get a sane pointer to + * pass on to access_ok(), for instance. + */ +#define untagged_addr(addr) sign_extend64(addr, 55) + #define access_ok(type, addr, size) __range_ok(addr, size) #define user_addr_max get_fs @@ -130,7 +140,7 @@ static inline void set_fs(mm_segment_t fs) * User access enabling/disabling. */ #ifdef CONFIG_ARM64_SW_TTBR0_PAN -static inline void uaccess_ttbr0_disable(void) +static inline void __uaccess_ttbr0_disable(void) { unsigned long ttbr; @@ -140,7 +150,7 @@ static inline void uaccess_ttbr0_disable(void) isb(); } -static inline void uaccess_ttbr0_enable(void) +static inline void __uaccess_ttbr0_enable(void) { unsigned long flags; @@ -154,30 +164,44 @@ static inline void uaccess_ttbr0_enable(void) isb(); local_irq_restore(flags); } + +static inline bool uaccess_ttbr0_disable(void) +{ + if (!system_uses_ttbr0_pan()) + return false; + __uaccess_ttbr0_disable(); + return true; +} + +static inline bool uaccess_ttbr0_enable(void) +{ + if (!system_uses_ttbr0_pan()) + return false; + __uaccess_ttbr0_enable(); + return true; +} #else -static inline void uaccess_ttbr0_disable(void) +static inline bool uaccess_ttbr0_disable(void) { + return false; } -static inline void uaccess_ttbr0_enable(void) +static inline bool uaccess_ttbr0_enable(void) { + return false; } #endif #define __uaccess_disable(alt) \ do { \ - if (system_uses_ttbr0_pan()) \ - uaccess_ttbr0_disable(); \ - else \ + if (!uaccess_ttbr0_disable()) \ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), alt, \ CONFIG_ARM64_PAN)); \ } while (0) #define __uaccess_enable(alt) \ do { \ - if (system_uses_ttbr0_pan()) \ - uaccess_ttbr0_enable(); \ - else \ + if (!uaccess_ttbr0_enable()) \ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), alt, \ CONFIG_ARM64_PAN)); \ } while (0) @@ -407,69 +431,62 @@ extern __must_check long strnlen_user(const char __user *str, long n); #else /* __ASSEMBLY__ */ -#include <asm/alternative.h> #include <asm/assembler.h> -#include <asm/kernel-pgtable.h> /* * User access enabling/disabling macros. */ - .macro uaccess_ttbr0_disable, tmp1 +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + .macro __uaccess_ttbr0_disable, tmp1 mrs \tmp1, ttbr1_el1 // swapper_pg_dir add \tmp1, \tmp1, #SWAPPER_DIR_SIZE // reserved_ttbr0 at the end of swapper_pg_dir msr ttbr0_el1, \tmp1 // set reserved TTBR0_EL1 isb .endm - .macro uaccess_ttbr0_enable, tmp1 + .macro __uaccess_ttbr0_enable, tmp1 get_thread_info \tmp1 - ldr \tmp1, [\tmp1, #TI_TTBR0] // load saved TTBR0_EL1 + ldr \tmp1, [\tmp1, #TSK_TI_TTBR0] // load saved TTBR0_EL1 msr ttbr0_el1, \tmp1 // set the non-PAN TTBR0_EL1 isb .endm + .macro uaccess_ttbr0_disable, tmp1 +alternative_if_not ARM64_HAS_PAN + __uaccess_ttbr0_disable \tmp1 +alternative_else_nop_endif + .endm + + .macro uaccess_ttbr0_enable, tmp1, tmp2 +alternative_if_not ARM64_HAS_PAN + save_and_disable_irq \tmp2 // avoid preemption + __uaccess_ttbr0_enable \tmp1 + restore_irq \tmp2 +alternative_else_nop_endif + .endm +#else + .macro uaccess_ttbr0_disable, tmp1 + .endm + + .macro uaccess_ttbr0_enable, tmp1, tmp2 + .endm +#endif + /* * These macros are no-ops when UAO is present. */ .macro uaccess_disable_not_uao, tmp1 -#ifdef CONFIG_ARM64_SW_TTBR0_PAN -alternative_if_not ARM64_HAS_PAN uaccess_ttbr0_disable \tmp1 -alternative_else - nop - nop - nop - nop -alternative_endif -#endif -alternative_if_not ARM64_ALT_PAN_NOT_UAO - nop -alternative_else +alternative_if ARM64_ALT_PAN_NOT_UAO SET_PSTATE_PAN(1) -alternative_endif +alternative_else_nop_endif .endm .macro uaccess_enable_not_uao, tmp1, tmp2 -#ifdef CONFIG_ARM64_SW_TTBR0_PAN -alternative_if_not ARM64_HAS_PAN - save_and_disable_irq \tmp2 // avoid preemption - uaccess_ttbr0_enable \tmp1 - restore_irq \tmp2 -alternative_else - nop - nop - nop - nop - nop - nop - nop -alternative_endif -#endif -alternative_if_not ARM64_ALT_PAN_NOT_UAO - nop -alternative_else + uaccess_ttbr0_enable \tmp1, \tmp2 +alternative_if ARM64_ALT_PAN_NOT_UAO SET_PSTATE_PAN(0) -alternative_endif +alternative_else_nop_endif .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h index de66199673d7..2b9a63771eda 100644 --- a/arch/arm64/include/asm/vdso_datapage.h +++ b/arch/arm64/include/asm/vdso_datapage.h @@ -22,6 +22,8 @@ struct vdso_data { __u64 cs_cycle_last; /* Timebase at clocksource init */ + __u64 raw_time_sec; /* Raw time */ + __u64 raw_time_nsec; __u64 xtime_clock_sec; /* Kernel time */ __u64 xtime_clock_nsec; __u64 xtime_coarse_sec; /* Coarse time */ @@ -29,8 +31,10 @@ struct vdso_data { __u64 wtm_clock_sec; /* Wall to monotonic time */ __u64 wtm_clock_nsec; __u32 tb_seq_count; /* Timebase sequence counter */ - __u32 cs_mult; /* Clocksource multiplier */ - __u32 cs_shift; /* Clocksource shift */ + /* cs_* members must be adjacent and in this order (ldp accesses) */ + __u32 cs_mono_mult; /* NTP-adjusted clocksource multiplier */ + __u32 cs_shift; /* Clocksource shift (mono = raw) */ + __u32 cs_raw_mult; /* Raw clocksource multiplier */ __u32 tz_minuteswest; /* Whacky timezone stuff */ __u32 tz_dsttime; __u32 use_syscall; diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 06e6a5238c4c..e6c27b8ce311 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -34,6 +34,11 @@ */ #define HVC_SET_VECTORS 1 +/* + * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine. + */ +#define HVC_SOFT_RESTART 2 + #define BOOT_CPU_MODE_EL1 (0xe11) #define BOOT_CPU_MODE_EL2 (0xe12) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 20bcc2db06bf..01c0b3881f88 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -44,13 +44,11 @@ arm64-obj-$(CONFIG_ACPI) += acpi.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o -arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o +arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ + cpu-reset.o +arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-y += $(arm64-obj-y) vdso/ probes/ obj-m += $(arm64-obj-m) head-y := head.o extra-y += $(head-y) vmlinux.lds - -# vDSO - this must be built first to generate the symbol offsets -$(call objectify,$(arm64-obj-y)): $(obj)/vdso/vdso-offsets.h -$(obj)/vdso/vdso-offsets.h: $(obj)/vdso diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index a0a0f2b20608..57e7d6e44c8b 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -14,7 +14,6 @@ #include <linux/slab.h> #include <linux/sysctl.h> -#include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/insn.h> #include <asm/opcodes.h> @@ -300,8 +299,9 @@ do { \ _ASM_EXTABLE(0b, 4b) \ _ASM_EXTABLE(1b, 4b) \ : "=&r" (res), "+r" (data), "=&r" (temp) \ - : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT) \ - : "memory"); \ + : "r" ((unsigned long)addr), "i" (-EAGAIN), \ + "i" (-EFAULT) \ + : "memory") \ uaccess_disable(); \ } while (0) diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index dac70c160289..7a3f34b15fb0 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -38,11 +38,11 @@ int main(void) DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); -#ifdef CONFIG_ARM64_SW_TTBR0_PAN - DEFINE(TI_TTBR0, offsetof(struct thread_info, ttbr0)); -#endif DEFINE(TI_TASK, offsetof(struct thread_info, task)); DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + DEFINE(TSK_TI_TTBR0, offsetof(struct thread_info, ttbr0)); +#endif BLANK(); DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context)); BLANK(); @@ -92,6 +92,7 @@ int main(void) BLANK(); DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(CLOCK_MONOTONIC_RAW, CLOCK_MONOTONIC_RAW); DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE); @@ -99,6 +100,8 @@ int main(void) DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); BLANK(); DEFINE(VDSO_CS_CYCLE_LAST, offsetof(struct vdso_data, cs_cycle_last)); + DEFINE(VDSO_RAW_TIME_SEC, offsetof(struct vdso_data, raw_time_sec)); + DEFINE(VDSO_RAW_TIME_NSEC, offsetof(struct vdso_data, raw_time_nsec)); DEFINE(VDSO_XTIME_CLK_SEC, offsetof(struct vdso_data, xtime_clock_sec)); DEFINE(VDSO_XTIME_CLK_NSEC, offsetof(struct vdso_data, xtime_clock_nsec)); DEFINE(VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec)); @@ -106,7 +109,8 @@ int main(void) DEFINE(VDSO_WTM_CLK_SEC, offsetof(struct vdso_data, wtm_clock_sec)); DEFINE(VDSO_WTM_CLK_NSEC, offsetof(struct vdso_data, wtm_clock_nsec)); DEFINE(VDSO_TB_SEQ_COUNT, offsetof(struct vdso_data, tb_seq_count)); - DEFINE(VDSO_CS_MULT, offsetof(struct vdso_data, cs_mult)); + DEFINE(VDSO_CS_MONO_MULT, offsetof(struct vdso_data, cs_mono_mult)); + DEFINE(VDSO_CS_RAW_MULT, offsetof(struct vdso_data, cs_raw_mult)); DEFINE(VDSO_CS_SHIFT, offsetof(struct vdso_data, cs_shift)); DEFINE(VDSO_TZ_MINWEST, offsetof(struct vdso_data, tz_minuteswest)); DEFINE(VDSO_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); @@ -120,6 +124,8 @@ int main(void) DEFINE(TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); BLANK(); + DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); + BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S new file mode 100644 index 000000000000..65f42d257414 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.S @@ -0,0 +1,54 @@ +/* + * CPU reset routines + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/sysreg.h> +#include <asm/virt.h> + +.text +.pushsection .idmap.text, "ax" + +/* + * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for + * cpu_soft_restart. + * + * @el2_switch: Flag to indicate a swich to EL2 is needed. + * @entry: Location to jump to for soft reset. + * arg0: First argument passed to @entry. + * arg1: Second argument passed to @entry. + * arg2: Third argument passed to @entry. + * + * Put the CPU into the same state as it would be if it had been reset, and + * branch to what would be the reset vector. It must be executed with the + * flat identity mapping. + */ +ENTRY(__cpu_soft_restart) + /* Clear sctlr_el1 flags. */ + mrs x12, sctlr_el1 + ldr x13, =SCTLR_ELx_FLAGS + bic x12, x12, x13 + msr sctlr_el1, x12 + isb + + cbz x0, 1f // el2_switch? + mov x0, #HVC_SOFT_RESTART + hvc #0 // no return + +1: mov x18, x1 // entry + mov x0, x2 // arg0 + mov x1, x3 // arg1 + mov x2, x4 // arg2 + br x18 +ENDPROC(__cpu_soft_restart) + +.popsection diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h new file mode 100644 index 000000000000..d4e9ecb264f0 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.h @@ -0,0 +1,34 @@ +/* + * CPU reset routines + * + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARM64_CPU_RESET_H +#define _ARM64_CPU_RESET_H + +#include <asm/virt.h> + +void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry, + unsigned long arg0, unsigned long arg1, unsigned long arg2); + +static inline void __noreturn cpu_soft_restart(unsigned long el2_switch, + unsigned long entry, unsigned long arg0, unsigned long arg1, + unsigned long arg2) +{ + typeof(__cpu_soft_restart) *restart; + + el2_switch = el2_switch && !is_kernel_in_hyp_mode() && + is_hyp_mode_available(); + restart = (void *)virt_to_phys(__cpu_soft_restart); + + cpu_install_idmap(); + restart(el2_switch, entry, arg0, arg1, arg2); + unreachable(); +} + +#endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index cdf1dca64133..53fab76d3c39 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -895,28 +895,6 @@ static u64 __raw_read_system_reg(u32 sys_id) } /* - * Park the CPU which doesn't have the capability as advertised - * by the system. - */ -static void fail_incapable_cpu(char *cap_type, - const struct arm64_cpu_capabilities *cap) -{ - int cpu = smp_processor_id(); - - pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc); - /* Mark this CPU absent */ - set_cpu_present(cpu, 0); - - /* Check if we can park ourselves */ - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) - cpu_ops[cpu]->cpu_die(cpu); - asm( - "1: wfe\n" - " wfi\n" - " b 1b"); -} - -/* * Run through the enabled system capabilities and enable() it on this CPU. * The capabilities were decided based on the available CPUs at the boot time. * Any new CPU should match the system wide status of the capability. If the @@ -944,8 +922,11 @@ void verify_local_cpu_capabilities(void) * If the new CPU misses an advertised feature, we cannot proceed * further, park the cpu. */ - if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) - fail_incapable_cpu("arm64_features", &caps[i]); + if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) { + pr_crit("CPU%d: missing feature: %s\n", + smp_processor_id(), caps[i].desc); + cpu_die_early(); + } if (caps[i].enable) caps[i].enable(NULL); } @@ -953,8 +934,11 @@ void verify_local_cpu_capabilities(void) for (i = 0, caps = arm64_hwcaps; caps[i].matches; i++) { if (!cpus_have_hwcap(&caps[i])) continue; - if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) - fail_incapable_cpu("arm64_hwcaps", &caps[i]); + if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) { + pr_crit("CPU%d: missing HWCAP: %s\n", + smp_processor_id(), caps[i].desc); + cpu_die_early(); + } } } diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c new file mode 100644 index 000000000000..f46d57c31443 --- /dev/null +++ b/arch/arm64/kernel/crash_dump.c @@ -0,0 +1,71 @@ +/* + * Routines for doing kexec-based kdump + * + * Copyright (C) 2017 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/crash_dump.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/memblock.h> +#include <linux/uaccess.h> +#include <asm/memory.h> + +/** + * copy_oldmem_page() - copy one page from old kernel memory + * @pfn: page frame number to be copied + * @buf: buffer where the copied page is placed + * @csize: number of bytes to copy + * @offset: offset in bytes into the page + * @userbuf: if set, @buf is in a user address space + * + * This function copies one page from old kernel memory into buffer pointed by + * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes + * copied or negative error in case of failure. + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, + int userbuf) +{ + void *vaddr; + + if (!csize) + return 0; + + vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB); + if (!vaddr) + return -ENOMEM; + + if (userbuf) { + if (copy_to_user((char __user *)buf, vaddr + offset, csize)) { + memunmap(vaddr); + return -EFAULT; + } + } else { + memcpy(buf, vaddr + offset, csize); + } + + memunmap(vaddr); + + return csize; +} + +/** + * elfcorehdr_read - read from ELF core header + * @buf: buffer where the data is placed + * @csize: number of bytes to read + * @ppos: address in the memory + * + * This function reads @count bytes from elf core header which exists + * on crash dump kernel's memory. + */ +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + return count; +} diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index db8a09331f2b..5472cedfe750 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -32,6 +32,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/uaccess.h> +#include <asm/asm-uaccess.h> #include <asm/unistd.h> /* @@ -120,11 +121,9 @@ * feature as all TTBR0_EL1 accesses are disabled, not just those to * user mappings. */ -alternative_if_not ARM64_HAS_PAN - nop -alternative_else +alternative_if ARM64_HAS_PAN b 1f // skip TTBR0 PAN -alternative_endif +alternative_else_nop_endif .if \el != 0 mrs x21, ttbr0_el1 @@ -134,7 +133,7 @@ alternative_endif and x23, x23, #~PSR_PAN_BIT // Clear the emulated PAN in the saved SPSR .endif - uaccess_ttbr0_disable x21 + __uaccess_ttbr0_disable x21 1: #endif @@ -181,17 +180,15 @@ alternative_endif * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR * PAN bit checking. */ -alternative_if_not ARM64_HAS_PAN - nop -alternative_else +alternative_if ARM64_HAS_PAN b 2f // skip TTBR0 PAN -alternative_endif +alternative_else_nop_endif .if \el != 0 - tbnz x22, #_PSR_PAN_BIT, 1f // Skip re-enabling TTBR0 access if previously disabled + tbnz x22, #22, 1f // Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set .endif - uaccess_ttbr0_enable x0 + __uaccess_ttbr0_enable x0 .if \el == 0 /* @@ -435,12 +432,13 @@ el1_da: /* * Data abort handling */ - mrs x0, far_el1 + mrs x3, far_el1 enable_dbg // re-enable interrupts if they were enabled in the aborted context tbnz x23, #7, 1f // PSR_I_BIT enable_irq 1: + clear_address_tag x0, x3 mov x2, sp // struct pt_regs bl do_mem_abort @@ -602,7 +600,7 @@ el0_da: // enable interrupts before calling the main handler enable_dbg_and_irq ct_user_exit - bic x0, x26, #(0xff << 56) + clear_address_tag x0, x26 mov x1, x25 mov x2, sp bl do_mem_abort diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 8cfd5ab37743..9c2e1564e9a7 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -36,6 +36,7 @@ #include <asm/pgtable-hwdef.h> #include <asm/pgtable.h> #include <asm/page.h> +#include <asm/smp.h> #include <asm/sysreg.h> #include <asm/thread_info.h> #include <asm/virt.h> @@ -643,7 +644,8 @@ __secondary_switched: msr vbar_el1, x5 isb - ldr_l x0, secondary_data // get secondary_data.stack + adr_l x0, secondary_data + ldr x0, [x0, #CPU_BOOT_STACK] // get secondary_data.stack mov sp, x0 and x0, x0, #~(THREAD_SIZE - 1) msr sp_el0, x0 // save thread_info @@ -652,6 +654,29 @@ __secondary_switched: ENDPROC(__secondary_switched) /* + * The booting CPU updates the failed status @__early_cpu_boot_status, + * with MMU turned off. + * + * update_early_cpu_boot_status tmp, status + * - Corrupts tmp1, tmp2 + * - Writes 'status' to __early_cpu_boot_status and makes sure + * it is committed to memory. + */ + + .macro update_early_cpu_boot_status status, tmp1, tmp2 + mov \tmp2, #\status + str_l \tmp2, __early_cpu_boot_status, \tmp1 + dmb sy + dc ivac, \tmp1 // Invalidate potentially stale cache line + .endm + + .pushsection .data..cacheline_aligned + .align L1_CACHE_SHIFT +ENTRY(__early_cpu_boot_status) + .long 0 + .popsection + +/* * Enable the MMU. * * x0 = SCTLR_EL1 value for turning on the MMU. @@ -669,6 +694,7 @@ ENTRY(__enable_mmu) ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4 cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED b.ne __no_granule_support + update_early_cpu_boot_status 0, x1, x2 msr ttbr0_el1, x25 // load TTBR0 msr ttbr1_el1, x26 // load TTBR1 isb @@ -708,8 +734,12 @@ ENTRY(__enable_mmu) ENDPROC(__enable_mmu) __no_granule_support: + /* Indicate that this CPU can't boot and is stuck in the kernel */ + update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2 +1: wfe - b __no_granule_support + wfi + b 1b ENDPROC(__no_granule_support) __primary_switch: diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f8df75d740f4..35a33d705536 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -27,6 +27,7 @@ #include <asm/barrier.h> #include <asm/cacheflush.h> #include <asm/irqflags.h> +#include <asm/kexec.h> #include <asm/memory.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> @@ -34,6 +35,7 @@ #include <asm/pgtable-hwdef.h> #include <asm/sections.h> #include <asm/suspend.h> +#include <asm/sysreg.h> #include <asm/virt.h> /* @@ -99,7 +101,8 @@ int pfn_is_nosave(unsigned long pfn) unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin); unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1); - return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn); + return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)) || + crash_is_nosave(pfn); } void notrace save_processor_state(void) @@ -216,12 +219,22 @@ static int create_safe_exec_page(void *src_start, size_t length, set_pte(pte, __pte(virt_to_phys((void *)dst) | pgprot_val(PAGE_KERNEL_EXEC))); - /* Load our new page tables */ - asm volatile("msr ttbr0_el1, %0;" - "isb;" - "tlbi vmalle1is;" - "dsb ish;" - "isb" : : "r"(virt_to_phys(pgd))); + /* + * Load our new page tables. A strict BBM approach requires that we + * ensure that TLBs are free of any entries that may overlap with the + * global mappings we are about to install. + * + * For a real hibernate/resume cycle TTBR0 currently points to a zero + * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI + * runtime services), while for a userspace-driven test_resume cycle it + * points to userspace page tables (and we must point it at a zero page + * ourselves). Elsewhere we only (un)install the idmap with preemption + * disabled, so T0SZ should be as required regardless. + */ + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + write_sysreg(virt_to_phys(pgd), ttbr0_el1); + isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -239,11 +252,17 @@ int swsusp_arch_suspend(void) local_dbg_save(flags); if (__cpu_suspend_enter(&state)) { + /* make the crash dump kernel image visible/saveable */ + crash_prepare_suspend(); + ret = swsusp_save(); } else { /* Clean kernel to PoC for secondary core startup */ __flush_dcache_area(LMADDR(KERNEL_START), KERNEL_END - KERNEL_START); + /* make the crash dump kernel image protected again */ + crash_post_resume(); + /* * Tell the hibernation core that we've just restored * the memory @@ -388,6 +407,38 @@ int swsusp_arch_resume(void) void *, phys_addr_t, phys_addr_t); /* + * Restoring the memory image will overwrite the ttbr1 page tables. + * Create a second copy of just the linear map, and use this when + * restoring. + */ + tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!tmp_pg_dir) { + pr_err("Failed to allocate memory for temporary page tables."); + rc = -ENOMEM; + goto out; + } + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + if (rc) + goto out; + + /* + * Since we only copied the linear map, we need to find restore_pblist's + * linear map address. + */ + lm_restore_pblist = LMADDR(restore_pblist); + + /* + * We need a zero page that is zero before & after resume in order to + * to break before make on the ttbr1 page tables. + */ + zero_page = (void *)get_safe_page(GFP_ATOMIC); + if (!zero_page) { + pr_err("Failed to allocate zero page."); + rc = -ENOMEM; + goto out; + } + + /* * Locate the exit code in the bottom-but-one page, so that *NULL * still has disastrous affects. */ @@ -413,27 +464,6 @@ int swsusp_arch_resume(void) __flush_dcache_area(hibernate_exit, exit_size); /* - * Restoring the memory image will overwrite the ttbr1 page tables. - * Create a second copy of just the linear map, and use this when - * restoring. - */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables."); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); - if (rc) - goto out; - - /* - * Since we only copied the linear map, we need to find restore_pblist's - * linear map address. - */ - lm_restore_pblist = LMADDR(restore_pblist); - - /* * KASLR will cause the el2 vectors to be in a different location in * the resumed kernel. Load hibernate's temporary copy into el2. * @@ -447,12 +477,6 @@ int swsusp_arch_resume(void) __hyp_set_vectors(el2_vectors); } - /* - * We need a zero page that is zero before & after resume in order to - * to break before make on the ttbr1 page tables. - */ - zero_page = (void *)get_safe_page(GFP_ATOMIC); - hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1, resume_hdr.reenter_kernel, lm_restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 367a954f9937..1c694f3c643c 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -36,6 +36,7 @@ #include <asm/traps.h> #include <asm/cputype.h> #include <asm/system_misc.h> +#include <asm/uaccess.h> /* Breakpoint currently in use for each BRP. */ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]); @@ -317,9 +318,21 @@ static int get_hbp_len(u8 hbp_len) case ARM_BREAKPOINT_LEN_2: len_in_bytes = 2; break; + case ARM_BREAKPOINT_LEN_3: + len_in_bytes = 3; + break; case ARM_BREAKPOINT_LEN_4: len_in_bytes = 4; break; + case ARM_BREAKPOINT_LEN_5: + len_in_bytes = 5; + break; + case ARM_BREAKPOINT_LEN_6: + len_in_bytes = 6; + break; + case ARM_BREAKPOINT_LEN_7: + len_in_bytes = 7; + break; case ARM_BREAKPOINT_LEN_8: len_in_bytes = 8; break; @@ -349,7 +362,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) * to generic breakpoint descriptions. */ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type) + int *gen_len, int *gen_type, int *offset) { /* Type */ switch (ctrl.type) { @@ -369,17 +382,33 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, return -EINVAL; } + if (!ctrl.len) + return -EINVAL; + *offset = __ffs(ctrl.len); + /* Len */ - switch (ctrl.len) { + switch (ctrl.len >> *offset) { case ARM_BREAKPOINT_LEN_1: *gen_len = HW_BREAKPOINT_LEN_1; break; case ARM_BREAKPOINT_LEN_2: *gen_len = HW_BREAKPOINT_LEN_2; break; + case ARM_BREAKPOINT_LEN_3: + *gen_len = HW_BREAKPOINT_LEN_3; + break; case ARM_BREAKPOINT_LEN_4: *gen_len = HW_BREAKPOINT_LEN_4; break; + case ARM_BREAKPOINT_LEN_5: + *gen_len = HW_BREAKPOINT_LEN_5; + break; + case ARM_BREAKPOINT_LEN_6: + *gen_len = HW_BREAKPOINT_LEN_6; + break; + case ARM_BREAKPOINT_LEN_7: + *gen_len = HW_BREAKPOINT_LEN_7; + break; case ARM_BREAKPOINT_LEN_8: *gen_len = HW_BREAKPOINT_LEN_8; break; @@ -423,9 +452,21 @@ static int arch_build_bp_info(struct perf_event *bp) case HW_BREAKPOINT_LEN_2: info->ctrl.len = ARM_BREAKPOINT_LEN_2; break; + case HW_BREAKPOINT_LEN_3: + info->ctrl.len = ARM_BREAKPOINT_LEN_3; + break; case HW_BREAKPOINT_LEN_4: info->ctrl.len = ARM_BREAKPOINT_LEN_4; break; + case HW_BREAKPOINT_LEN_5: + info->ctrl.len = ARM_BREAKPOINT_LEN_5; + break; + case HW_BREAKPOINT_LEN_6: + info->ctrl.len = ARM_BREAKPOINT_LEN_6; + break; + case HW_BREAKPOINT_LEN_7: + info->ctrl.len = ARM_BREAKPOINT_LEN_7; + break; case HW_BREAKPOINT_LEN_8: info->ctrl.len = ARM_BREAKPOINT_LEN_8; break; @@ -517,18 +558,17 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) default: return -EINVAL; } - - info->address &= ~alignment_mask; - info->ctrl.len <<= offset; } else { if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) alignment_mask = 0x3; else alignment_mask = 0x7; - if (info->address & alignment_mask) - return -EINVAL; + offset = info->address & alignment_mask; } + info->address &= ~alignment_mask; + info->ctrl.len <<= offset; + /* * Disallow per-task kernel breakpoints since these would * complicate the stepping code. @@ -661,12 +701,47 @@ unlock: } NOKPROBE_SYMBOL(breakpoint_handler); +/* + * Arm64 hardware does not always report a watchpoint hit address that matches + * one of the watchpoints set. It can also report an address "near" the + * watchpoint if a single instruction access both watched and unwatched + * addresses. There is no straight-forward way, short of disassembling the + * offending instruction, to map that address back to the watchpoint. This + * function computes the distance of the memory access from the watchpoint as a + * heuristic for the likelyhood that a given access triggered the watchpoint. + * + * See Section D2.10.5 "Determining the memory location that caused a Watchpoint + * exception" of ARMv8 Architecture Reference Manual for details. + * + * The function returns the distance of the address from the bytes watched by + * the watchpoint. In case of an exact match, it returns 0. + */ +static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, + struct arch_hw_breakpoint_ctrl *ctrl) +{ + u64 wp_low, wp_high; + u32 lens, lene; + + lens = __ffs(ctrl->len); + lene = __fls(ctrl->len); + + wp_low = val + lens; + wp_high = val + lene; + if (addr < wp_low) + return wp_low - addr; + else if (addr > wp_high) + return addr - wp_high; + else + return 0; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - int i, step = 0, *kernel_step, access; + int i, step = 0, *kernel_step, access, closest_match = 0; + u64 min_dist = -1, dist; u32 ctrl_reg; - u64 val, alignment_mask; + u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; struct arch_hw_breakpoint *info; @@ -675,35 +750,15 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, slots = this_cpu_ptr(wp_on_reg); debug_info = ¤t->thread.debug; + /* + * Find all watchpoints that match the reported address. If no exact + * match is found. Attribute the hit to the closest watchpoint. + */ + rcu_read_lock(); for (i = 0; i < core_num_wrps; ++i) { - rcu_read_lock(); - wp = slots[i]; - if (wp == NULL) - goto unlock; - - info = counter_arch_bp(wp); - /* AArch32 watchpoints are either 4 or 8 bytes aligned. */ - if (is_compat_task()) { - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) - alignment_mask = 0x7; - else - alignment_mask = 0x3; - } else { - alignment_mask = 0x7; - } - - /* Check if the watchpoint value matches. */ - val = read_wb_reg(AARCH64_DBG_REG_WVR, i); - if (val != (addr & ~alignment_mask)) - goto unlock; - - /* Possible match, check the byte address select to confirm. */ - ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i); - decode_ctrl_reg(ctrl_reg, &ctrl); - if (!((1 << (addr & alignment_mask)) & ctrl.len)) - goto unlock; + continue; /* * Check that the access type matches. @@ -712,18 +767,41 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, access = (esr & AARCH64_ESR_ACCESS_MASK) ? HW_BREAKPOINT_W : HW_BREAKPOINT_R; if (!(access & hw_breakpoint_type(wp))) - goto unlock; + continue; + /* Check if the watchpoint value and byte select match. */ + val = read_wb_reg(AARCH64_DBG_REG_WVR, i); + ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i); + decode_ctrl_reg(ctrl_reg, &ctrl); + dist = get_distance_from_watchpoint(addr, val, &ctrl); + if (dist < min_dist) { + min_dist = dist; + closest_match = i; + } + /* Is this an exact match? */ + if (dist != 0) + continue; + + info = counter_arch_bp(wp); info->trigger = addr; perf_bp_event(wp, regs); /* Do we need to handle the stepping? */ if (!wp->overflow_handler) step = 1; + } + if (min_dist > 0 && min_dist != -1) { + /* No exact match found. */ + wp = slots[closest_match]; + info = counter_arch_bp(wp); + info->trigger = addr; + perf_bp_event(wp, regs); -unlock: - rcu_read_unlock(); + /* Do we need to handle the stepping? */ + if (!wp->overflow_handler) + step = 1; } + rcu_read_unlock(); if (!step) return 0; diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 8727f4490772..d3b5f75e652e 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -71,8 +71,16 @@ el1_sync: msr vbar_el2, x1 b 9f +2: cmp x0, #HVC_SOFT_RESTART + b.ne 3f + mov x0, x2 + mov x2, x4 + mov x4, x1 + mov x1, x3 + br x4 // no return + /* Someone called kvm_call_hyp() against the hyp-stub... */ -2: mov x0, #ARM_EXCEPTION_HYP_GONE +3: mov x0, #ARM_EXCEPTION_HYP_GONE 9: eret ENDPROC(el1_sync) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c new file mode 100644 index 000000000000..481f54a866c5 --- /dev/null +++ b/arch/arm64/kernel/machine_kexec.c @@ -0,0 +1,364 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/page-flags.h> +#include <linux/smp.h> + +#include <asm/cacheflush.h> +#include <asm/cpu_ops.h> +#include <asm/memory.h> +#include <asm/mmu.h> +#include <asm/mmu_context.h> +#include <asm/page.h> + +#include "cpu-reset.h" + +/* Global variables for the arm64_relocate_new_kernel routine. */ +extern const unsigned char arm64_relocate_new_kernel[]; +extern const unsigned long arm64_relocate_new_kernel_size; + +/** + * kexec_image_info - For debugging output. + */ +#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i) +static void _kexec_image_info(const char *func, int line, + const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:%d:\n", func, line); + pr_debug(" kexec kimage info:\n"); + pr_debug(" type: %d\n", kimage->type); + pr_debug(" start: %lx\n", kimage->start); + pr_debug(" head: %lx\n", kimage->head); + pr_debug(" nr_segments: %lu\n", kimage->nr_segments); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + } +} + +void machine_kexec_cleanup(struct kimage *kimage) +{ + /* Empty routine needed to avoid build errors. */ +} + +/** + * machine_kexec_prepare - Prepare for a kexec reboot. + * + * Called from the core kexec code when a kernel image is loaded. + * Forbid loading a kexec kernel if we have no way of hotplugging cpus or cpus + * are stuck in the kernel. This avoids a panic once we hit machine_kexec(). + */ +int machine_kexec_prepare(struct kimage *kimage) +{ + kexec_image_info(kimage); + + if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) { + pr_err("Can't kexec: CPUs are stuck in the kernel.\n"); + return -EBUSY; + } + + return 0; +} + +/** + * kexec_list_flush - Helper to flush the kimage list and source pages to PoC. + */ +static void kexec_list_flush(struct kimage *kimage) +{ + kimage_entry_t *entry; + + for (entry = &kimage->head; ; entry++) { + unsigned int flag; + void *addr; + + /* flush the list entries. */ + __flush_dcache_area(entry, sizeof(kimage_entry_t)); + + flag = *entry & IND_FLAGS; + if (flag == IND_DONE) + break; + + addr = phys_to_virt(*entry & PAGE_MASK); + + switch (flag) { + case IND_INDIRECTION: + /* Set entry point just before the new list page. */ + entry = (kimage_entry_t *)addr - 1; + break; + case IND_SOURCE: + /* flush the source pages. */ + __flush_dcache_area(addr, PAGE_SIZE); + break; + case IND_DESTINATION: + break; + default: + BUG(); + } + } +} + +/** + * kexec_segment_flush - Helper to flush the kimage segments to PoC. + */ +static void kexec_segment_flush(const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:\n", __func__); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + + __flush_dcache_area(phys_to_virt(kimage->segment[i].mem), + kimage->segment[i].memsz); + } +} + +/** + * machine_kexec - Do the kexec reboot. + * + * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC. + */ +void machine_kexec(struct kimage *kimage) +{ + phys_addr_t reboot_code_buffer_phys; + void *reboot_code_buffer; + bool in_kexec_crash = (kimage == kexec_crash_image); + bool stuck_cpus = cpus_are_stuck_in_kernel(); + + /* + * New cpus may have become stuck_in_kernel after we loaded the image. + */ + BUG_ON(!in_kexec_crash && (stuck_cpus || (num_online_cpus() > 1))); + WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()), + "Some CPUs may be stale, kdump will be unreliable.\n"); + + reboot_code_buffer_phys = page_to_phys(kimage->control_code_page); + reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys); + + kexec_image_info(kimage); + + pr_debug("%s:%d: control_code_page: %p\n", __func__, __LINE__, + kimage->control_code_page); + pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__, + &reboot_code_buffer_phys); + pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__, + reboot_code_buffer); + pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__, + arm64_relocate_new_kernel); + pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n", + __func__, __LINE__, arm64_relocate_new_kernel_size, + arm64_relocate_new_kernel_size); + + /* + * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use + * after the kernel is shut down. + */ + memcpy(reboot_code_buffer, arm64_relocate_new_kernel, + arm64_relocate_new_kernel_size); + + /* Flush the reboot_code_buffer in preparation for its execution. */ + __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size); + flush_icache_range((uintptr_t)reboot_code_buffer, + arm64_relocate_new_kernel_size); + + /* Flush the kimage list and its buffers. */ + kexec_list_flush(kimage); + + /* Flush the new image if already in place. */ + if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE)) + kexec_segment_flush(kimage); + + pr_info("Bye!\n"); + + /* Disable all DAIF exceptions. */ + asm volatile ("msr daifset, #0xf" : : : "memory"); + + /* + * cpu_soft_restart will shutdown the MMU, disable data caches, then + * transfer control to the reboot_code_buffer which contains a copy of + * the arm64_relocate_new_kernel routine. arm64_relocate_new_kernel + * uses physical addressing to relocate the new image to its final + * position and transfers control to the image entry point when the + * relocation is complete. + */ + + cpu_soft_restart(kimage != kexec_crash_image, + reboot_code_buffer_phys, kimage->head, kimage->start, 0); + + BUG(); /* Should never get here. */ +} + +static void machine_kexec_mask_interrupts(void) +{ + unsigned int i; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + int ret; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + /* + * First try to remove the active state. If this + * fails, try to EOI the interrupt. + */ + ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); + + if (ret && irqd_irq_inprogress(&desc->irq_data) && + chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_mask) + chip->irq_mask(&desc->irq_data); + + if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) + chip->irq_disable(&desc->irq_data); + } +} + +/** + * machine_crash_shutdown - shutdown non-crashing cpus and save registers + */ +void machine_crash_shutdown(struct pt_regs *regs) +{ + local_irq_disable(); + + /* shutdown non-crashing cpus */ + smp_send_crash_stop(); + + /* for crashing cpu */ + crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + + pr_info("Starting crashdump kernel...\n"); +} + +void arch_kexec_protect_crashkres(void) +{ + int i; + + kexec_segment_flush(kexec_crash_image); + + for (i = 0; i < kexec_crash_image->nr_segments; i++) + set_memory_valid( + __phys_to_virt(kexec_crash_image->segment[i].mem), + kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0); +} + +void arch_kexec_unprotect_crashkres(void) +{ + int i; + + for (i = 0; i < kexec_crash_image->nr_segments; i++) + set_memory_valid( + __phys_to_virt(kexec_crash_image->segment[i].mem), + kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1); +} + +#ifdef CONFIG_HIBERNATION +/* + * To preserve the crash dump kernel image, the relevant memory segments + * should be mapped again around the hibernation. + */ +void crash_prepare_suspend(void) +{ + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); +} + +void crash_post_resume(void) +{ + if (kexec_crash_image) + arch_kexec_protect_crashkres(); +} + +/* + * crash_is_nosave + * + * Return true only if a page is part of reserved memory for crash dump kernel, + * but does not hold any data of loaded kernel image. + * + * Note that all the pages in crash dump kernel memory have been initially + * marked as Reserved in kexec_reserve_crashkres_pages(). + * + * In hibernation, the pages which are Reserved and yet "nosave" are excluded + * from the hibernation iamge. crash_is_nosave() does thich check for crash + * dump kernel and will reduce the total size of hibernation image. + */ + +bool crash_is_nosave(unsigned long pfn) +{ + int i; + phys_addr_t addr; + + if (!crashk_res.end) + return false; + + /* in reserved memory? */ + addr = __pfn_to_phys(pfn); + if ((addr < crashk_res.start) || (crashk_res.end < addr)) + return false; + + if (!kexec_crash_image) + return true; + + /* not part of loaded kernel image? */ + for (i = 0; i < kexec_crash_image->nr_segments; i++) + if (addr >= kexec_crash_image->segment[i].mem && + addr < (kexec_crash_image->segment[i].mem + + kexec_crash_image->segment[i].memsz)) + return false; + + return true; +} + +void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) +{ + unsigned long addr; + struct page *page; + + for (addr = begin; addr < end; addr += PAGE_SIZE) { + page = phys_to_page(addr); + ClearPageReserved(page); + free_reserved_page(page); + } +} +#endif /* CONFIG_HIBERNATION */ + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(VA_BITS); + /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ + vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", + kimage_voffset); + vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", + PHYS_OFFSET); +} diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index c5ef05959813..6204b7600d1b 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -327,13 +327,13 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { - int err, len, type, disabled = !ctrl.enabled; + int err, len, type, offset, disabled = !ctrl.enabled; attr->disabled = disabled; if (disabled) return 0; - err = arch_bp_generic_fields(ctrl, &len, &type); + err = arch_bp_generic_fields(ctrl, &len, &type, &offset); if (err) return err; @@ -352,6 +352,7 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, attr->bp_len = len; attr->bp_type = type; + attr->bp_addr += offset; return 0; } @@ -404,7 +405,7 @@ static int ptrace_hbp_get_addr(unsigned int note_type, if (IS_ERR(bp)) return PTR_ERR(bp); - *addr = bp ? bp->attr.bp_addr : 0; + *addr = bp ? counter_arch_bp(bp)->address : 0; return 0; } diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S new file mode 100644 index 000000000000..51b73cdde287 --- /dev/null +++ b/arch/arm64/kernel/relocate_kernel.S @@ -0,0 +1,130 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kexec.h> +#include <linux/linkage.h> + +#include <asm/assembler.h> +#include <asm/kexec.h> +#include <asm/page.h> +#include <asm/sysreg.h> + +/* + * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it. + * + * The memory that the old kernel occupies may be overwritten when coping the + * new image to its final location. To assure that the + * arm64_relocate_new_kernel routine which does that copy is not overwritten, + * all code and data needed by arm64_relocate_new_kernel must be between the + * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end. The + * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec + * control_code_page, a special page which has been set up to be preserved + * during the copy operation. + */ +ENTRY(arm64_relocate_new_kernel) + + /* Setup the list loop variables. */ + mov x17, x1 /* x17 = kimage_start */ + mov x16, x0 /* x16 = kimage_head */ + dcache_line_size x15, x0 /* x15 = dcache line size */ + mov x14, xzr /* x14 = entry ptr */ + mov x13, xzr /* x13 = copy dest */ + + /* Clear the sctlr_el2 flags. */ + mrs x0, CurrentEL + cmp x0, #CurrentEL_EL2 + b.ne 1f + mrs x0, sctlr_el2 + ldr x1, =SCTLR_ELx_FLAGS + bic x0, x0, x1 + msr sctlr_el2, x0 + isb +1: + + /* Check if the new image needs relocation. */ + tbnz x16, IND_DONE_BIT, .Ldone + +.Lloop: + and x12, x16, PAGE_MASK /* x12 = addr */ + + /* Test the entry flags. */ +.Ltest_source: + tbz x16, IND_SOURCE_BIT, .Ltest_indirection + + /* Invalidate dest page to PoC. */ + mov x0, x13 + add x20, x0, #PAGE_SIZE + sub x1, x15, #1 + bic x0, x0, x1 +2: dc ivac, x0 + add x0, x0, x15 + cmp x0, x20 + b.lo 2b + dsb sy + + mov x20, x13 + mov x21, x12 + copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7 + + /* dest += PAGE_SIZE */ + add x13, x13, PAGE_SIZE + b .Lnext + +.Ltest_indirection: + tbz x16, IND_INDIRECTION_BIT, .Ltest_destination + + /* ptr = addr */ + mov x14, x12 + b .Lnext + +.Ltest_destination: + tbz x16, IND_DESTINATION_BIT, .Lnext + + /* dest = addr */ + mov x13, x12 + +.Lnext: + /* entry = *ptr++ */ + ldr x16, [x14], #8 + + /* while (!(entry & DONE)) */ + tbz x16, IND_DONE_BIT, .Lloop + +.Ldone: + /* wait for writes from copy_page to finish */ + dsb nsh + ic iallu + dsb nsh + isb + + /* Start new image. */ + mov x0, xzr + mov x1, xzr + mov x2, xzr + mov x3, xzr + br x17 + +ENDPROC(arm64_relocate_new_kernel) + +.ltorg + +.align 3 /* To keep the 64-bit values below naturally aligned. */ + +.Lcopy_end: +.org KEXEC_CONTROL_PAGE_SIZE + +/* + * arm64_relocate_new_kernel_size - Number of bytes to copy to the + * control_code_page. + */ +.globl arm64_relocate_new_kernel_size +arm64_relocate_new_kernel_size: + .quad .Lcopy_end - arm64_relocate_new_kernel diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 0153c0d8ddb1..19749870c757 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -31,7 +31,6 @@ #include <linux/screen_info.h> #include <linux/init.h> #include <linux/kexec.h> -#include <linux/crash_dump.h> #include <linux/root_dev.h> #include <linux/cpu.h> #include <linux/interrupt.h> @@ -220,6 +219,12 @@ static void __init request_standard_resources(void) if (kernel_data.start >= res->start && kernel_data.end <= res->end) request_resource(res, &kernel_data); +#ifdef CONFIG_KEXEC_CORE + /* Userspace will find "Crash kernel" region in /proc/iomem. */ + if (crashk_res.end && crashk_res.start >= res->start && + crashk_res.end <= res->end) + request_resource(res, &crashk_res); +#endif } } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index a84623d91410..a1d06fc42048 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -37,6 +37,7 @@ #include <linux/completion.h> #include <linux/of.h> #include <linux/irq_work.h> +#include <linux/kexec.h> #include <asm/alternative.h> #include <asm/atomic.h> @@ -63,16 +64,29 @@ * where to place its SVC stack */ struct secondary_data secondary_data; +/* Number of CPUs which aren't online, but looping in kernel text. */ +int cpus_stuck_in_kernel; enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, + IPI_CPU_CRASH_STOP, IPI_TIMER, IPI_IRQ_WORK, IPI_WAKEUP }; +#ifdef CONFIG_HOTPLUG_CPU +static int op_cpu_kill(unsigned int cpu); +#else +static inline int op_cpu_kill(unsigned int cpu) +{ + return -ENOSYS; +} +#endif + + /* * Boot a secondary CPU, and assign it the specified idle task. * This also gives us the initial stack to use for this CPU. @@ -90,12 +104,14 @@ static DECLARE_COMPLETION(cpu_running); int __cpu_up(unsigned int cpu, struct task_struct *idle) { int ret; + long status; /* * We need to tell the secondary core where to find its stack and the * page tables. */ secondary_data.stack = task_stack_page(idle) + THREAD_START_SP; + update_cpu_boot_status(CPU_MMU_OFF); __flush_dcache_area(&secondary_data, sizeof(secondary_data)); /* @@ -119,6 +135,32 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) } secondary_data.stack = NULL; + status = READ_ONCE(secondary_data.status); + if (ret && status) { + + if (status == CPU_MMU_OFF) + status = READ_ONCE(__early_cpu_boot_status); + + switch (status) { + default: + pr_err("CPU%u: failed in unknown state : 0x%lx\n", + cpu, status); + break; + case CPU_KILL_ME: + if (!op_cpu_kill(cpu)) { + pr_crit("CPU%u: died during early boot\n", cpu); + break; + } + /* Fall through */ + pr_crit("CPU%u: may not have shut down cleanly\n", cpu); + case CPU_STUCK_IN_KERNEL: + pr_crit("CPU%u: is stuck in kernel\n", cpu); + cpus_stuck_in_kernel++; + break; + case CPU_PANIC_KERNEL: + panic("CPU%u detected unsupported configuration\n", cpu); + } + } return ret; } @@ -184,6 +226,9 @@ asmlinkage void secondary_start_kernel(void) */ pr_info("CPU%u: Booted secondary processor [%08x]\n", cpu, read_cpuid_id()); + update_cpu_boot_status(CPU_BOOT_SUCCESS); + /* Make sure the status update is visible before we complete */ + smp_wmb(); set_cpu_online(cpu, true); complete(&cpu_running); @@ -311,6 +356,30 @@ void cpu_die(void) } #endif +/* + * Kill the calling secondary CPU, early in bringup before it is turned + * online. + */ +void cpu_die_early(void) +{ + int cpu = smp_processor_id(); + + pr_crit("CPU%d: will not boot\n", cpu); + + /* Mark this CPU absent */ + set_cpu_present(cpu, 0); + +#ifdef CONFIG_HOTPLUG_CPU + update_cpu_boot_status(CPU_KILL_ME); + /* Check if we can park ourselves */ + if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) + cpu_ops[cpu]->cpu_die(cpu); +#endif + update_cpu_boot_status(CPU_STUCK_IN_KERNEL); + + cpu_park_loop(); +} + static void __init hyp_mode_check(void) { if (is_hyp_mode_available()) @@ -634,6 +703,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { S(IPI_RESCHEDULE, "Rescheduling interrupts"), S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"), S(IPI_TIMER, "Timer broadcast interrupts"), S(IPI_IRQ_WORK, "IRQ work interrupts"), S(IPI_WAKEUP, "CPU wake-up interrupts"), @@ -718,6 +788,29 @@ static void ipi_cpu_stop(unsigned int cpu) cpu_relax(); } +#ifdef CONFIG_KEXEC_CORE +static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); +#endif + +static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ +#ifdef CONFIG_KEXEC_CORE + crash_save_cpu(regs, cpu); + + atomic_dec(&waiting_for_crash_ipi); + + local_irq_disable(); + +#ifdef CONFIG_HOTPLUG_CPU + if (cpu_ops[cpu]->cpu_die) + cpu_ops[cpu]->cpu_die(cpu); +#endif + + /* just in case */ + cpu_park_loop(); +#endif +} + /* * Main handler for inter-processor interrupts */ @@ -748,6 +841,15 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; + case IPI_CPU_CRASH_STOP: + if (IS_ENABLED(CONFIG_KEXEC_CORE)) { + irq_enter(); + ipi_cpu_crash_stop(cpu, regs); + + unreachable(); + } + break; + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST case IPI_TIMER: irq_enter(); @@ -816,6 +918,39 @@ void smp_send_stop(void) pr_warning("SMP: failed to stop secondary CPUs\n"); } +#ifdef CONFIG_KEXEC_CORE +void smp_send_crash_stop(void) +{ + cpumask_t mask; + unsigned long timeout; + + if (num_online_cpus() == 1) + return; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + + pr_crit("SMP: stopping secondary CPUs\n"); + smp_cross_call(&mask, IPI_CPU_CRASH_STOP); + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) + udelay(1); + + if (atomic_read(&waiting_for_crash_ipi) > 0) + pr_warning("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(&mask)); +} + +bool smp_crash_stop_failed(void) +{ + return (atomic_read(&waiting_for_crash_ipi) > 0); +} +#endif + /* * not supported here */ @@ -823,3 +958,21 @@ int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; } + +static bool have_cpu_die(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + int any_cpu = raw_smp_processor_id(); + + if (cpu_ops[any_cpu]->cpu_die) + return true; +#endif + return false; +} + +bool cpus_are_stuck_in_kernel(void) +{ + bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die()); + + return !!cpus_stuck_in_kernel || smp_spin_tables; +} diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index cfd46c227c8c..a99eff9afc1f 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -43,6 +43,9 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) unsigned long fp = frame->fp; unsigned long irq_stack_ptr; + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -67,7 +70,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = *(unsigned long *)(fp + 8); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (tsk && tsk->ret_stack && + if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { /* * This is a case where function graph tracer has diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index f5c82c76cf7c..a1cfcaa562a2 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -149,6 +149,11 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) unsigned long irq_stack_ptr; int skip; + pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); + + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -158,11 +163,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) else irq_stack_ptr = 0; - pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); - - if (!tsk) - tsk = current; - if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 97bc68f4c689..3b8acfae7797 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -55,7 +55,7 @@ struct vdso_data *vdso_data = &vdso_data_store.data; */ static struct page *vectors_page[1]; -static int alloc_vectors_page(void) +static int __init alloc_vectors_page(void) { extern char __kuser_helper_start[], __kuser_helper_end[]; extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; @@ -88,7 +88,7 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; unsigned long addr = AARCH32_VECTORS_BASE; - static struct vm_special_mapping spec = { + static const struct vm_special_mapping spec = { .name = "[vectors]", .pages = vectors_page, @@ -212,10 +212,16 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { + /* tkr_mono.cycle_last == tkr_raw.cycle_last */ vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last; + vdso_data->raw_time_sec = tk->raw_time.tv_sec; + vdso_data->raw_time_nsec = tk->raw_time.tv_nsec; vdso_data->xtime_clock_sec = tk->xtime_sec; vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; - vdso_data->cs_mult = tk->tkr_mono.mult; + /* tkr_raw.xtime_nsec == 0 */ + vdso_data->cs_mono_mult = tk->tkr_mono.mult; + vdso_data->cs_raw_mult = tk->tkr_raw.mult; + /* tkr_mono.shift == tkr_raw.shift */ vdso_data->cs_shift = tk->tkr_mono.shift; } diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index b467fd0a384b..62c84f7cb01b 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,7 +23,7 @@ GCOV_PROFILE := n ccflags-y += -Wl,-shared obj-y += vdso.o -extra-y += vdso.lds vdso-offsets.h +extra-y += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) # Force dependency (incbin is bad) @@ -42,11 +42,10 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ define cmd_vdsosym - $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ && \ - cp $@ include/generated/ + $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ endef -$(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE +include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) # Assembly rules for the .S files diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index efa79e8d4196..e00b4671bd7c 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -26,24 +26,109 @@ #define NSEC_PER_SEC_HI16 0x3b9a vdso_data .req x6 -use_syscall .req w7 -seqcnt .req w8 +seqcnt .req w7 +w_tmp .req w8 +x_tmp .req x8 + +/* + * Conventions for macro arguments: + * - An argument is write-only if its name starts with "res". + * - All other arguments are read-only, unless otherwise specified. + */ .macro seqcnt_acquire 9999: ldr seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT] tbnz seqcnt, #0, 9999b dmb ishld - ldr use_syscall, [vdso_data, #VDSO_USE_SYSCALL] .endm - .macro seqcnt_read, cnt + .macro seqcnt_check fail dmb ishld - ldr \cnt, [vdso_data, #VDSO_TB_SEQ_COUNT] + ldr w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT] + cmp w_tmp, seqcnt + b.ne \fail .endm - .macro seqcnt_check, cnt, fail - cmp \cnt, seqcnt - b.ne \fail + .macro syscall_check fail + ldr w_tmp, [vdso_data, #VDSO_USE_SYSCALL] + cbnz w_tmp, \fail + .endm + + .macro get_nsec_per_sec res + mov \res, #NSEC_PER_SEC_LO16 + movk \res, #NSEC_PER_SEC_HI16, lsl #16 + .endm + + /* + * Returns the clock delta, in nanoseconds left-shifted by the clock + * shift. + */ + .macro get_clock_shifted_nsec res, cycle_last, mult + /* Read the virtual counter. */ + isb + mrs x_tmp, cntvct_el0 + /* Calculate cycle delta and convert to ns. */ + sub \res, x_tmp, \cycle_last + /* We can only guarantee 56 bits of precision. */ + movn x_tmp, #0xff00, lsl #48 + and \res, x_tmp, \res + mul \res, \res, \mult + .endm + + /* + * Returns in res_{sec,nsec} the REALTIME timespec, based on the + * "wall time" (xtime) and the clock_mono delta. + */ + .macro get_ts_realtime res_sec, res_nsec, \ + clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec + add \res_nsec, \clock_nsec, \xtime_nsec + udiv x_tmp, \res_nsec, \nsec_to_sec + add \res_sec, \xtime_sec, x_tmp + msub \res_nsec, x_tmp, \nsec_to_sec, \res_nsec + .endm + + /* + * Returns in res_{sec,nsec} the timespec based on the clock_raw delta, + * used for CLOCK_MONOTONIC_RAW. + */ + .macro get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec + udiv \res_sec, \clock_nsec, \nsec_to_sec + msub \res_nsec, \res_sec, \nsec_to_sec, \clock_nsec + .endm + + /* sec and nsec are modified in place. */ + .macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec + /* Add timespec. */ + add \sec, \sec, \ts_sec + add \nsec, \nsec, \ts_nsec + + /* Normalise the new timespec. */ + cmp \nsec, \nsec_to_sec + b.lt 9999f + sub \nsec, \nsec, \nsec_to_sec + add \sec, \sec, #1 +9999: + cmp \nsec, #0 + b.ge 9998f + add \nsec, \nsec, \nsec_to_sec + sub \sec, \sec, #1 +9998: + .endm + + .macro clock_gettime_return, shift=0 + .if \shift == 1 + lsr x11, x11, x12 + .endif + stp x10, x11, [x1, #TSPEC_TV_SEC] + mov x0, xzr + ret + .endm + + .macro jump_slot jumptable, index, label + .if (. - \jumptable) != 4 * (\index) + .error "Jump slot index mismatch" + .endif + b \label .endm .text @@ -51,18 +136,25 @@ seqcnt .req w8 /* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */ ENTRY(__kernel_gettimeofday) .cfi_startproc - mov x2, x30 - .cfi_register x30, x2 - - /* Acquire the sequence counter and get the timespec. */ adr vdso_data, _vdso_data -1: seqcnt_acquire - cbnz use_syscall, 4f - /* If tv is NULL, skip to the timezone code. */ cbz x0, 2f - bl __do_get_tspec - seqcnt_check w9, 1b + + /* Compute the time of day. */ +1: seqcnt_acquire + syscall_check fail=4f + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + seqcnt_check fail=1b + + get_nsec_per_sec res=x9 + lsl x9, x9, x12 + + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 /* Convert ns to us. */ mov x13, #1000 @@ -76,95 +168,126 @@ ENTRY(__kernel_gettimeofday) stp w4, w5, [x1, #TZ_MINWEST] 3: mov x0, xzr - ret x2 + ret 4: /* Syscall fallback. */ mov x8, #__NR_gettimeofday svc #0 - ret x2 + ret .cfi_endproc ENDPROC(__kernel_gettimeofday) +#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE + /* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */ ENTRY(__kernel_clock_gettime) .cfi_startproc - cmp w0, #CLOCK_REALTIME - ccmp w0, #CLOCK_MONOTONIC, #0x4, ne - b.ne 2f + cmp w0, #JUMPSLOT_MAX + b.hi syscall + adr vdso_data, _vdso_data + adr x_tmp, jumptable + add x_tmp, x_tmp, w0, uxtw #2 + br x_tmp + + ALIGN +jumptable: + jump_slot jumptable, CLOCK_REALTIME, realtime + jump_slot jumptable, CLOCK_MONOTONIC, monotonic + b syscall + b syscall + jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw + jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse + jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse + + .if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1) + .error "Wrong jumptable size" + .endif + + ALIGN +realtime: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + seqcnt_check fail=realtime - mov x2, x30 - .cfi_register x30, x2 + /* All computations are done with left-shifted nsecs. */ + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - /* Get kernel timespec. */ - adr vdso_data, _vdso_data -1: seqcnt_acquire - cbnz use_syscall, 7f + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 + clock_gettime_return, shift=1 - bl __do_get_tspec - seqcnt_check w9, 1b + ALIGN +monotonic: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + ldp x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC] + seqcnt_check fail=monotonic - mov x30, x2 + /* All computations are done with left-shifted nsecs. */ + lsl x4, x4, x12 + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - cmp w0, #CLOCK_MONOTONIC - b.ne 6f + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 - /* Get wtm timespec. */ - ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC] + add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9 + clock_gettime_return, shift=1 - /* Check the sequence counter. */ - seqcnt_read w9 - seqcnt_check w9, 1b - b 4f -2: - cmp w0, #CLOCK_REALTIME_COARSE - ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne - b.ne 8f + ALIGN +monotonic_raw: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_raw_mult, w12 = cs_shift */ + ldp w12, w11, [vdso_data, #VDSO_CS_SHIFT] + ldp x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC] + seqcnt_check fail=monotonic_raw - /* xtime_coarse_nsec is already right-shifted */ - mov x12, #0 + /* All computations are done with left-shifted nsecs. */ + lsl x14, x14, x12 + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - /* Get coarse timespec. */ - adr vdso_data, _vdso_data -3: seqcnt_acquire + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_clock_raw res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, nsec_to_sec=x9 + + add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 + clock_gettime_return, shift=1 + + ALIGN +realtime_coarse: + seqcnt_acquire ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] + seqcnt_check fail=realtime_coarse + clock_gettime_return - /* Get wtm timespec. */ + ALIGN +monotonic_coarse: + seqcnt_acquire + ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC] + seqcnt_check fail=monotonic_coarse - /* Check the sequence counter. */ - seqcnt_read w9 - seqcnt_check w9, 3b + /* Computations are done in (non-shifted) nsecs. */ + get_nsec_per_sec res=x9 + add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 + clock_gettime_return - cmp w0, #CLOCK_MONOTONIC_COARSE - b.ne 6f -4: - /* Add on wtm timespec. */ - add x10, x10, x13 - lsl x14, x14, x12 - add x11, x11, x14 - - /* Normalise the new timespec. */ - mov x15, #NSEC_PER_SEC_LO16 - movk x15, #NSEC_PER_SEC_HI16, lsl #16 - lsl x15, x15, x12 - cmp x11, x15 - b.lt 5f - sub x11, x11, x15 - add x10, x10, #1 -5: - cmp x11, #0 - b.ge 6f - add x11, x11, x15 - sub x10, x10, #1 - -6: /* Store to the user timespec. */ - lsr x11, x11, x12 - stp x10, x11, [x1, #TSPEC_TV_SEC] - mov x0, xzr - ret -7: - mov x30, x2 -8: /* Syscall fallback. */ + ALIGN +syscall: /* Syscall fallback. */ mov x8, #__NR_clock_gettime svc #0 ret @@ -176,6 +299,7 @@ ENTRY(__kernel_clock_getres) .cfi_startproc cmp w0, #CLOCK_REALTIME ccmp w0, #CLOCK_MONOTONIC, #0x4, ne + ccmp w0, #CLOCK_MONOTONIC_RAW, #0x4, ne b.ne 1f ldr x2, 5f @@ -203,46 +327,3 @@ ENTRY(__kernel_clock_getres) .quad CLOCK_COARSE_RES .cfi_endproc ENDPROC(__kernel_clock_getres) - -/* - * Read the current time from the architected counter. - * Expects vdso_data to be initialised. - * Clobbers the temporary registers (x9 - x15). - * Returns: - * - w9 = vDSO sequence counter - * - (x10, x11) = (ts->tv_sec, shifted ts->tv_nsec) - * - w12 = cs_shift - */ -ENTRY(__do_get_tspec) - .cfi_startproc - - /* Read from the vDSO data page. */ - ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] - ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] - ldp w11, w12, [vdso_data, #VDSO_CS_MULT] - seqcnt_read w9 - - /* Read the virtual counter. */ - isb - mrs x15, cntvct_el0 - - /* Calculate cycle delta and convert to ns. */ - sub x10, x15, x10 - /* We can only guarantee 56 bits of precision. */ - movn x15, #0xff00, lsl #48 - and x10, x15, x10 - mul x10, x10, x11 - - /* Use the kernel time to calculate the new timespec. */ - mov x11, #NSEC_PER_SEC_LO16 - movk x11, #NSEC_PER_SEC_HI16, lsl #16 - lsl x11, x11, x12 - add x15, x10, x14 - udiv x14, x15, x11 - add x10, x13, x14 - mul x13, x14, x11 - sub x11, x15, x13 - - ret - .cfi_endproc -ENDPROC(__do_get_tspec) diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 826032bc3945..acde4782621a 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -12,3 +12,7 @@ obj-$(CONFIG_KVM_ARM_HOST) += switch.o obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o obj-$(CONFIG_KVM_ARM_HOST) += tlb.o obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o + +GCOV_PROFILE := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index eec3598b4184..3ff507c177a5 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1055,8 +1055,8 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); - int Rt = (hsr >> 5) & 0xf; - int Rt2 = (hsr >> 10) & 0xf; + int Rt = (hsr >> 5) & 0x1f; + int Rt2 = (hsr >> 10) & 0x1f; params.is_aarch32 = true; params.is_32bit = false; @@ -1107,7 +1107,7 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); - int Rt = (hsr >> 5) & 0xf; + int Rt = (hsr >> 5) & 0x1f; params.is_aarch32 = true; params.is_32bit = true; diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 08b5f18ba604..d7150e30438a 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -17,9 +17,6 @@ */ #include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/cpufeature.h> -#include <asm/sysreg.h> #include <asm/uaccess.h> .text diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 6505ec81f1da..90154f3f7f2a 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -16,10 +16,7 @@ #include <linux/linkage.h> -#include <asm/assembler.h> #include <asm/cache.h> -#include <asm/cpufeature.h> -#include <asm/sysreg.h> #include <asm/uaccess.h> /* diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 9b04ff3ab610..718b1c4e2f85 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -18,10 +18,7 @@ #include <linux/linkage.h> -#include <asm/assembler.h> #include <asm/cache.h> -#include <asm/cpufeature.h> -#include <asm/sysreg.h> #include <asm/uaccess.h> /* diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 8077e4f34d56..e99e31c9acac 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -16,10 +16,7 @@ #include <linux/linkage.h> -#include <asm/assembler.h> #include <asm/cache.h> -#include <asm/cpufeature.h> -#include <asm/sysreg.h> #include <asm/uaccess.h> /* diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 07d7352d7c38..3be2cda5dbda 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -23,6 +23,7 @@ #include <asm/assembler.h> #include <asm/cpufeature.h> #include <asm/alternative.h> +#include <asm/uaccess.h> /* * flush_icache_range(start,end) @@ -48,6 +49,7 @@ ENTRY(flush_icache_range) * - end - virtual end address of region */ ENTRY(__flush_cache_user_range) + uaccess_ttbr0_enable x2, x3 dcache_line_size x2, x3 sub x3, x2, #1 bic x4, x0, x3 @@ -69,10 +71,12 @@ USER(9f, ic ivau, x4 ) // invalidate I line PoU dsb ish isb mov x0, #0 +1: + uaccess_ttbr0_disable x1 ret 9: mov x0, #-EFAULT - ret + b 1b ENDPROC(flush_icache_range) ENDPROC(__flush_cache_user_range) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 380e02941691..c7809f41d9d1 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -88,21 +88,21 @@ void show_pte(struct mm_struct *mm, unsigned long addr) break; pud = pud_offset(pgd, addr); - printk(", *pud=%016llx", pud_val(*pud)); + pr_cont(", *pud=%016llx", pud_val(*pud)); if (pud_none(*pud) || pud_bad(*pud)) break; pmd = pmd_offset(pud, addr); - printk(", *pmd=%016llx", pmd_val(*pmd)); + pr_cont(", *pmd=%016llx", pmd_val(*pmd)); if (pmd_none(*pmd) || pmd_bad(*pmd)) break; pte = pte_offset_map(pmd, addr); - printk(", *pte=%016llx", pte_val(*pte)); + pr_cont(", *pte=%016llx", pte_val(*pte)); pte_unmap(pte); } while(0); - printk("\n"); + pr_cont("\n"); } #ifdef CONFIG_ARM64_HW_AFDBM @@ -510,10 +510,10 @@ static const struct fault_info { { do_bad, SIGBUS, 0, "unknown 17" }, { do_bad, SIGBUS, 0, "unknown 18" }, { do_bad, SIGBUS, 0, "unknown 19" }, - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" }, - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" }, - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" }, - { do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, { do_bad, SIGBUS, 0, "synchronous parity error" }, { do_bad, SIGBUS, 0, "unknown 25" }, { do_bad, SIGBUS, 0, "unknown 26" }, @@ -686,5 +686,6 @@ int cpu_enable_pan(void *__unused) int cpu_enable_uao(void *__unused) { asm(SET_PSTATE_UAO(1)); + return 0; } #endif /* CONFIG_ARM64_UAO */ diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index da30529bb1f6..019f13637fae 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -51,20 +51,8 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr, *pgsize = PAGE_SIZE; if (!pte_cont(pte)) return 1; - if (!pgd_present(*pgd)) { - VM_BUG_ON(!pgd_present(*pgd)); - return 1; - } pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) { - VM_BUG_ON(!pud_present(*pud)); - return 1; - } pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - VM_BUG_ON(!pmd_present(*pmd)); - return 1; - } if ((pte_t *)pmd == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; @@ -212,7 +200,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); /* save the 1st pte to return */ pte = ptep_get_and_clear(mm, addr, cpte); - for (i = 1; i < ncontig; ++i) { + for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) { /* * If HW_AFDBM is enabled, then the HW could * turn on the dirty bit for any of the page @@ -250,8 +238,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, pfn = pte_pfn(*cpte); ncontig = find_num_contig(vma->vm_mm, addr, cpte, *cpte, &pgsize); - for (i = 0; i < ncontig; ++i, ++cpte) { - changed = ptep_set_access_flags(vma, addr, cpte, + for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) { + changed |= ptep_set_access_flags(vma, addr, cpte, pfn_pte(pfn, hugeprot), dirty); @@ -273,7 +261,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, cpte = huge_pte_offset(mm, addr); ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); - for (i = 0; i < ncontig; ++i, ++cpte) + for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) ptep_set_wrprotect(mm, addr, cpte); } else { ptep_set_wrprotect(mm, addr, ptep); @@ -291,7 +279,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, cpte = huge_pte_offset(vma->vm_mm, addr); ncontig = find_num_contig(vma->vm_mm, addr, cpte, *cpte, &pgsize); - for (i = 0; i < ncontig; ++i, ++cpte) + for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) ptep_clear_flush(vma, addr, cpte); } else { ptep_clear_flush(vma, addr, ptep); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 678878077996..74ac8a90ba3f 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -29,11 +29,14 @@ #include <linux/gfp.h> #include <linux/memblock.h> #include <linux/sort.h> +#include <linux/of.h> #include <linux/of_fdt.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/efi.h> #include <linux/swiotlb.h> +#include <linux/kexec.h> +#include <linux/crash_dump.h> #include <asm/boot.h> #include <asm/fixmap.h> @@ -75,6 +78,142 @@ static int __init early_initrd(char *p) early_param("initrd", early_initrd); #endif +#ifdef CONFIG_KEXEC_CORE +/* + * reserve_crashkernel() - reserves memory for crash kernel + * + * This function reserves memory area given in "crashkernel=" kernel command + * line parameter. The memory reserved is used by dump capture kernel when + * primary kernel is crashing. + */ +static void __init reserve_crashkernel(void) +{ + unsigned long long crash_base, crash_size; + int ret; + + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + &crash_size, &crash_base); + /* no crashkernel= or invalid value specified */ + if (ret || !crash_size) + return; + + crash_size = PAGE_ALIGN(crash_size); + + if (crash_base == 0) { + /* Current arm64 boot protocol requires 2MB alignment */ + crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT, + crash_size, SZ_2M); + if (crash_base == 0) { + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", + crash_size); + return; + } + } else { + /* User specifies base address explicitly. */ + if (!memblock_is_region_memory(crash_base, crash_size)) { + pr_warn("cannot reserve crashkernel: region is not memory\n"); + return; + } + + if (memblock_is_region_reserved(crash_base, crash_size)) { + pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n"); + return; + } + + if (!IS_ALIGNED(crash_base, SZ_2M)) { + pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n"); + return; + } + } + memblock_reserve(crash_base, crash_size); + + pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + crash_base, crash_base + crash_size, crash_size >> 20); + + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; +} + +static void __init kexec_reserve_crashkres_pages(void) +{ +#ifdef CONFIG_HIBERNATION + phys_addr_t addr; + struct page *page; + + if (!crashk_res.end) + return; + + /* + * To reduce the size of hibernation image, all the pages are + * marked as Reserved initially. + */ + for (addr = crashk_res.start; addr < (crashk_res.end + 1); + addr += PAGE_SIZE) { + page = phys_to_page(addr); + SetPageReserved(page); + } +#endif +} +#else +static void __init reserve_crashkernel(void) +{ +} + +static void __init kexec_reserve_crashkres_pages(void) +{ +} +#endif /* CONFIG_KEXEC_CORE */ + +#ifdef CONFIG_CRASH_DUMP +static int __init early_init_dt_scan_elfcorehdr(unsigned long node, + const char *uname, int depth, void *data) +{ + const __be32 *reg; + int len; + + if (depth != 1 || strcmp(uname, "chosen") != 0) + return 0; + + reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len); + if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells))) + return 1; + + elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, ®); + elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, ®); + + return 1; +} + +/* + * reserve_elfcorehdr() - reserves memory for elf core header + * + * This function reserves the memory occupied by an elf core header + * described in the device tree. This region contains all the + * information about primary kernel's core image and is used by a dump + * capture kernel to access the system memory on primary kernel. + */ +static void __init reserve_elfcorehdr(void) +{ + of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL); + + if (!elfcorehdr_size) + return; + + if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) { + pr_warn("elfcorehdr is overlapped\n"); + return; + } + + memblock_reserve(elfcorehdr_addr, elfcorehdr_size); + + pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n", + elfcorehdr_size >> 10, elfcorehdr_addr); +} +#else +static void __init reserve_elfcorehdr(void) +{ +} +#endif /* CONFIG_CRASH_DUMP */ /* * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It * currently assumes that for memory starting above 4G, 32-bit devices will @@ -168,10 +307,45 @@ static int __init early_mem(char *p) } early_param("mem", early_mem); +static int __init early_init_dt_scan_usablemem(unsigned long node, + const char *uname, int depth, void *data) +{ + struct memblock_region *usablemem = data; + const __be32 *reg; + int len; + + if (depth != 1 || strcmp(uname, "chosen") != 0) + return 0; + + reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len); + if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells))) + return 1; + + usablemem->base = dt_mem_next_cell(dt_root_addr_cells, ®); + usablemem->size = dt_mem_next_cell(dt_root_size_cells, ®); + + return 1; +} + +static void __init fdt_enforce_memory_region(void) +{ + struct memblock_region reg = { + .size = 0, + }; + + of_scan_flat_dt(early_init_dt_scan_usablemem, ®); + + if (reg.size) + memblock_cap_memory_range(reg.base, reg.size); +} + void __init arm64_memblock_init(void) { const s64 linear_region_size = -(s64)PAGE_OFFSET; + /* Handle linux,usable-memory-range property */ + fdt_enforce_memory_region(); + /* * Ensure that the linear region takes up exactly half of the kernel * virtual address space. This way, we can distinguish a linear address @@ -248,6 +422,11 @@ void __init arm64_memblock_init(void) arm64_dma_phys_limit = max_zone_dma_phys(); else arm64_dma_phys_limit = PHYS_MASK + 1; + + reserve_crashkernel(); + + reserve_elfcorehdr(); + dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); @@ -361,6 +540,8 @@ void __init mem_init(void) /* this will put all unused low memory onto the freelists */ free_all_bootmem(); + kexec_reserve_crashkres_pages(); + mem_init_print_info(NULL); #define MLK(b, t) b, t, ((t) - (b)) >> 10 diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1cab2703f5a8..aeadc2c0a6c8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -21,6 +21,8 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/init.h> +#include <linux/ioport.h> +#include <linux/kexec.h> #include <linux/libfdt.h> #include <linux/mman.h> #include <linux/nodemask.h> @@ -156,29 +158,10 @@ static void split_pud(pud_t *old_pud, pmd_t *pmd) } while (pmd++, i++, i < PTRS_PER_PMD); } -#ifdef CONFIG_DEBUG_PAGEALLOC -static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) -{ - - /* - * If debug_page_alloc is enabled we must map the linear map - * using pages. However, other mappings created by - * create_mapping_noalloc must use sections in some cases. Allow - * sections to be used in those cases, where no pgtable_alloc - * function is provided. - */ - return !pgtable_alloc || !debug_pagealloc_enabled(); -} -#else -static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) -{ - return true; -} -#endif - static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { pmd_t *pmd; unsigned long next; @@ -209,7 +192,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && - block_mappings_allowed(pgtable_alloc)) { + (!pgtable_alloc || allow_block_mappings)) { pmd_t old_pmd =*pmd; pmd_set_huge(pmd, phys, prot); /* @@ -248,7 +231,8 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { pud_t *pud; unsigned long next; @@ -269,7 +253,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, * For 4K granule only, attempt to put down a 1GB block */ if (use_1G_block(addr, next, phys) && - block_mappings_allowed(pgtable_alloc)) { + (!pgtable_alloc || allow_block_mappings)) { pud_t old_pud = *pud; pud_set_huge(pud, phys, prot); @@ -290,7 +274,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, } } else { alloc_init_pmd(pud, addr, next, phys, prot, - pgtable_alloc); + pgtable_alloc, allow_block_mappings); } phys += next - addr; } while (pud++, addr = next, addr != end); @@ -304,7 +288,8 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, */ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { unsigned long addr, length, end, next; @@ -322,7 +307,8 @@ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc); + alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, + (!pgtable_alloc || allow_block_mappings)); phys += next - addr; } while (pgd++, addr = next, addr != end); } @@ -340,9 +326,11 @@ static phys_addr_t late_pgtable_alloc(void) static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, - phys_addr_t (*alloc)(void)) + phys_addr_t (*alloc)(void), + bool allow_block_mappings) { - init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc); + init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc, + allow_block_mappings); } /* @@ -358,16 +346,15 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, - NULL); + __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, - pgprot_t prot) + pgprot_t prot, bool allow_block_mappings) { __create_pgd_mapping(mm->pgd, phys, virt, size, prot, - late_pgtable_alloc); + late_pgtable_alloc, allow_block_mappings); } static void create_mapping_late(phys_addr_t phys, unsigned long virt, @@ -380,10 +367,18 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, } __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, - late_pgtable_alloc); + late_pgtable_alloc, !debug_pagealloc_enabled()); +} + +static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, + phys_addr_t end, pgprot_t prot, + bool allow_block_mappings) +{ + __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, + prot, early_pgtable_alloc, allow_block_mappings); } -static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end) +static void __init map_mem(pgd_t *pgd) { unsigned long kernel_start = __pa(_text); unsigned long kernel_end = __pa(__init_begin); @@ -391,45 +386,15 @@ static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end /* * Take care not to create a writable alias for the * read-only text and rodata sections of the kernel image. + * So temporarily mark them as NOMAP to skip mappings in + * the following for-loop */ - - /* No overlap with the kernel text/rodata */ - if (end < kernel_start || start >= kernel_end) { - __create_pgd_mapping(pgd, start, __phys_to_virt(start), - end - start, PAGE_KERNEL, - early_pgtable_alloc); - return; - } - - /* - * This block overlaps the kernel text/rodata mappings. - * Map the portion(s) which don't overlap. - */ - if (start < kernel_start) - __create_pgd_mapping(pgd, start, - __phys_to_virt(start), - kernel_start - start, PAGE_KERNEL, - early_pgtable_alloc); - if (kernel_end < end) - __create_pgd_mapping(pgd, kernel_end, - __phys_to_virt(kernel_end), - end - kernel_end, PAGE_KERNEL, - early_pgtable_alloc); - - /* - * Map the linear alias of the [_text, __init_begin) interval as - * read-only/non-executable. This makes the contents of the - * region accessible to subsystems such as hibernate, but - * protects it from inadvertent modification or execution. - */ - __create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start), - kernel_end - kernel_start, PAGE_KERNEL_RO, - early_pgtable_alloc); -} - -static void __init map_mem(pgd_t *pgd) -{ - struct memblock_region *reg; + memblock_mark_nomap(kernel_start, kernel_end - kernel_start); +#ifdef CONFIG_KEXEC_CORE + if (crashk_res.end) + memblock_mark_nomap(crashk_res.start, + resource_size(&crashk_res)); +#endif /* map all the memory banks */ for_each_memblock(memory, reg) { @@ -441,8 +406,33 @@ static void __init map_mem(pgd_t *pgd) if (memblock_is_nomap(reg)) continue; - __map_memblock(pgd, start, end); + __map_memblock(pgd, start, end, + PAGE_KERNEL, !debug_pagealloc_enabled()); } + + /* + * Map the linear alias of the [_text, __init_begin) interval as + * read-only/non-executable. This makes the contents of the + * region accessible to subsystems such as hibernate, but + * protects it from inadvertent modification or execution. + */ + __map_memblock(pgd, kernel_start, kernel_end, + PAGE_KERNEL_RO, !debug_pagealloc_enabled()); + memblock_clear_nomap(kernel_start, kernel_end - kernel_start); + +#ifdef CONFIG_KEXEC_CORE + /* + * Use page-level mappings here so that we can shrink the region + * in page granularity and put back unused memory to buddy system + * through /sys/kernel/kexec_crash_size interface. + */ + if (crashk_res.end) { + __map_memblock(pgd, crashk_res.start, crashk_res.end + 1, + PAGE_KERNEL, false); + memblock_clear_nomap(crashk_res.start, + resource_size(&crashk_res)); + } +#endif } void mark_rodata_ro(void) @@ -481,7 +471,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(size)); __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, - early_pgtable_alloc); + early_pgtable_alloc, !debug_pagealloc_enabled()); vma->addr = va_start; vma->phys_addr = pa_start; diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index ca6d268e3313..f4e39dbdd36b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -125,6 +125,19 @@ int set_memory_x(unsigned long addr, int numpages) } EXPORT_SYMBOL_GPL(set_memory_x); + +int set_memory_valid(unsigned long addr, int numpages, int enable) +{ + if (enable) + return __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(PTE_VALID), + __pgprot(0)); + else + return __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(0), + __pgprot(PTE_VALID)); +} + #ifdef CONFIG_DEBUG_PAGEALLOC void __kernel_map_pages(struct page *page, int numpages, int enable) { diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 8292784d44c9..d88a2a80ada8 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -100,7 +100,16 @@ ENTRY(cpu_do_resume) msr tcr_el1, x8 msr vbar_el1, x9 + + /* + * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking + * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug + * exception. Mask them until local_dbg_restore() in cpu_suspend() + * resets them. + */ + disable_dbg msr mdscr_el1, x10 + msr sctlr_el1, x12 /* * Restore oslsr_el1 by writing oslar_el1 diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index b162ad70effc..6297140dd84f 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -728,14 +728,14 @@ static int build_body(struct jit_ctx *ctx) int ret; ret = build_insn(insn, ctx); - - if (ctx->image == NULL) - ctx->offset[i] = ctx->idx; - if (ret > 0) { i++; + if (ctx->image == NULL) + ctx->offset[i] = ctx->idx; continue; } + if (ctx->image == NULL) + ctx->offset[i] = ctx->idx; if (ret) return ret; } diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S index 6d6e4af1a4bf..b96db5dafec4 100644 --- a/arch/arm64/xen/hypercall.S +++ b/arch/arm64/xen/hypercall.S @@ -90,7 +90,6 @@ ENTRY(privcmd_call) mov x2, x3 mov x3, x4 mov x4, x5 -#ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Privcmd calls are issued by the userspace. The kernel needs to * enable access to TTBR0_EL1 as the hypervisor would issue stage 1 @@ -99,15 +98,12 @@ ENTRY(privcmd_call) * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation * is enabled (it implies that hardware UAO and PAN disabled). */ - uaccess_enable_not_uao x6, x7 -#endif + uaccess_ttbr0_enable x6, x7 hvc XEN_IMM -#ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Disable userspace access from kernel once the hyp call completed. */ - uaccess_disable_not_uao x6 -#endif + uaccess_ttbr0_disable x6 ret ENDPROC(privcmd_call); diff --git a/arch/c6x/kernel/ptrace.c b/arch/c6x/kernel/ptrace.c index 3c494e84444d..a511ac16a8e3 100644 --- a/arch/c6x/kernel/ptrace.c +++ b/arch/c6x/kernel/ptrace.c @@ -69,46 +69,6 @@ static int gpr_get(struct task_struct *target, 0, sizeof(*regs)); } -static int gpr_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret; - struct pt_regs *regs = task_pt_regs(target); - - /* Don't copyin TSR or CSR */ - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s, - 0, PT_TSR * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - PT_TSR * sizeof(long), - (PT_TSR + 1) * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s, - (PT_TSR + 1) * sizeof(long), - PT_CSR * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - PT_CSR * sizeof(long), - (PT_CSR + 1) * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s, - (PT_CSR + 1) * sizeof(long), -1); - return ret; -} - enum c6x_regset { REGSET_GPR, }; @@ -120,7 +80,6 @@ static const struct user_regset c6x_regsets[] = { .size = sizeof(u32), .align = sizeof(u32), .get = gpr_get, - .set = gpr_set }, }; diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c index 836f14707a62..efa59f1f8022 100644 --- a/arch/frv/mm/elf-fdpic.c +++ b/arch/frv/mm/elf-fdpic.c @@ -74,7 +74,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi addr = PAGE_ALIGN(addr); vma = find_vma(current->mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) goto success; } diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c index 92075544a19a..0dc1c8f622bc 100644 --- a/arch/h8300/kernel/ptrace.c +++ b/arch/h8300/kernel/ptrace.c @@ -95,7 +95,8 @@ static int regs_get(struct task_struct *target, long *reg = (long *)®s; /* build user regs in buffer */ - for (r = 0; r < ARRAY_SIZE(register_offset); r++) + BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0); + for (r = 0; r < sizeof(regs) / sizeof(long); r++) *reg++ = h8300_get_reg(target, r); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -113,7 +114,8 @@ static int regs_set(struct task_struct *target, long *reg; /* build user regs in buffer */ - for (reg = (long *)®s, r = 0; r < ARRAY_SIZE(register_offset); r++) + BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0); + for (reg = (long *)®s, r = 0; r < sizeof(regs) / sizeof(long); r++) *reg++ = h8300_get_reg(target, r); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -122,7 +124,7 @@ static int regs_set(struct task_struct *target, return ret; /* write back to pt_regs */ - for (reg = (long *)®s, r = 0; r < ARRAY_SIZE(register_offset); r++) + for (reg = (long *)®s, r = 0; r < sizeof(regs) / sizeof(long); r++) h8300_put_reg(target, r, *reg++); return 0; } diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 970d0bd99621..648f1cef33fa 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -95,8 +95,8 @@ define archhelp echo '* unwcheck - Check vmlinux for invalid unwind info' endef -archprepare: make_nr_irqs_h FORCE +archprepare: make_nr_irqs_h PHONY += make_nr_irqs_h FORCE -make_nr_irqs_h: FORCE +make_nr_irqs_h: $(Q)$(MAKE) $(build)=arch/ia64/kernel include/generated/nr-irqs.h diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h index 273e61225c27..3db381205928 100644 --- a/arch/metag/include/asm/uaccess.h +++ b/arch/metag/include/asm/uaccess.h @@ -28,24 +28,32 @@ #define segment_eq(a, b) ((a).seg == (b).seg) -#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS)) -/* - * Explicitly allow NULL pointers here. Parts of the kernel such - * as readv/writev use access_ok to validate pointers, but want - * to allow NULL pointers for various reasons. NULL pointers are - * safe to allow through because the first page is not mappable on - * Meta. - * - * We also wish to avoid letting user code access the system area - * and the kernel half of the address space. - */ -#define __user_bad(addr, size) (((addr) > 0 && (addr) < META_MEMORY_BASE) || \ - ((addr) > PAGE_OFFSET && \ - (addr) < LINCORE_BASE)) - static inline int __access_ok(unsigned long addr, unsigned long size) { - return __kernel_ok || !__user_bad(addr, size); + /* + * Allow access to the user mapped memory area, but not the system area + * before it. The check extends to the top of the address space when + * kernel access is allowed (there's no real reason to user copy to the + * system area in any case). + */ + if (likely(addr >= META_MEMORY_BASE && addr < get_fs().seg && + size <= get_fs().seg - addr)) + return true; + /* + * Explicitly allow NULL pointers here. Parts of the kernel such + * as readv/writev use access_ok to validate pointers, but want + * to allow NULL pointers for various reasons. NULL pointers are + * safe to allow through because the first page is not mappable on + * Meta. + */ + if (!addr) + return true; + /* Allow access to core code memory area... */ + if (addr >= LINCORE_CODE_BASE && addr <= LINCORE_CODE_LIMIT && + size <= LINCORE_CODE_LIMIT + 1 - addr) + return true; + /* ... but no other areas. */ + return false; } #define access_ok(type, addr, size) __access_ok((unsigned long)(addr), \ @@ -186,8 +194,13 @@ do { \ extern long __must_check __strncpy_from_user(char *dst, const char __user *src, long count); -#define strncpy_from_user(dst, src, count) __strncpy_from_user(dst, src, count) - +static inline long +strncpy_from_user(char *dst, const char __user *src, long count) +{ + if (!access_ok(VERIFY_READ, src, 1)) + return -EFAULT; + return __strncpy_from_user(dst, src, count); +} /* * Return the size of a string (including the ending 0) * @@ -197,20 +210,21 @@ extern long __must_check strnlen_user(const char __user *src, long count); #define strlen_user(str) strnlen_user(str, 32767) -extern unsigned long __must_check __copy_user_zeroing(void *to, - const void __user *from, - unsigned long n); +extern unsigned long raw_copy_from_user(void *to, const void __user *from, + unsigned long n); static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { + unsigned long res = n; if (likely(access_ok(VERIFY_READ, from, n))) - return __copy_user_zeroing(to, from, n); - memset(to, 0, n); - return n; + res = raw_copy_from_user(to, from, n); + if (unlikely(res)) + memset(to + (n - res), 0, res); + return res; } -#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n) +#define __copy_from_user(to, from, n) raw_copy_from_user(to, from, n) #define __copy_from_user_inatomic __copy_from_user extern unsigned long __must_check __copy_user(void __user *to, diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c index 7563628822bd..5e2dc7defd2c 100644 --- a/arch/metag/kernel/ptrace.c +++ b/arch/metag/kernel/ptrace.c @@ -24,6 +24,16 @@ * user_regset definitions. */ +static unsigned long user_txstatus(const struct pt_regs *regs) +{ + unsigned long data = (unsigned long)regs->ctx.Flags; + + if (regs->ctx.SaveMask & TBICTX_CBUF_BIT) + data |= USER_GP_REGS_STATUS_CATCH_BIT; + + return data; +} + int metag_gp_regs_copyout(const struct pt_regs *regs, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -62,9 +72,7 @@ int metag_gp_regs_copyout(const struct pt_regs *regs, if (ret) goto out; /* TXSTATUS */ - data = (unsigned long)regs->ctx.Flags; - if (regs->ctx.SaveMask & TBICTX_CBUF_BIT) - data |= USER_GP_REGS_STATUS_CATCH_BIT; + data = user_txstatus(regs); ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &data, 4*25, 4*26); if (ret) @@ -119,6 +127,7 @@ int metag_gp_regs_copyin(struct pt_regs *regs, if (ret) goto out; /* TXSTATUS */ + data = user_txstatus(regs); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &data, 4*25, 4*26); if (ret) @@ -244,6 +253,8 @@ int metag_rp_state_copyin(struct pt_regs *regs, unsigned long long *ptr; int ret, i; + if (count < 4*13) + return -EINVAL; /* Read the entire pipeline before making any changes */ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &rp, 0, 4*13); @@ -303,7 +314,7 @@ static int metag_tls_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { int ret; - void __user *tls; + void __user *tls = target->thread.tls_ptr; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); if (ret) diff --git a/arch/metag/lib/usercopy.c b/arch/metag/lib/usercopy.c index b3ebfe9c8e88..2792fc621088 100644 --- a/arch/metag/lib/usercopy.c +++ b/arch/metag/lib/usercopy.c @@ -29,7 +29,6 @@ COPY \ "1:\n" \ " .section .fixup,\"ax\"\n" \ - " MOV D1Ar1,#0\n" \ FIXUP \ " MOVT D1Ar1,#HI(1b)\n" \ " JUMP D1Ar1,#LO(1b)\n" \ @@ -260,27 +259,31 @@ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ "22:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ - "SUB %3, %3, #32\n" \ "23:\n" \ - "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ + "SUB %3, %3, #32\n" \ "24:\n" \ + "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ + "25:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "26:\n" \ "SUB %3, %3, #32\n" \ "DCACHE [%1+#-64], D0Ar6\n" \ "BR $Lloop"id"\n" \ \ "MOV RAPF, %1\n" \ - "25:\n" \ + "27:\n" \ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "26:\n" \ + "28:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "29:\n" \ "SUB %3, %3, #32\n" \ - "27:\n" \ + "30:\n" \ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "28:\n" \ + "31:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "32:\n" \ "SUB %0, %0, #8\n" \ - "29:\n" \ + "33:\n" \ "SETL [%0++], D0.7, D1.7\n" \ "SUB %3, %3, #32\n" \ "1:" \ @@ -312,11 +315,15 @@ " .long 26b,3b\n" \ " .long 27b,3b\n" \ " .long 28b,3b\n" \ - " .long 29b,4b\n" \ + " .long 29b,3b\n" \ + " .long 30b,3b\n" \ + " .long 31b,3b\n" \ + " .long 32b,3b\n" \ + " .long 33b,4b\n" \ " .previous\n" \ : "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \ : "0" (to), "1" (from), "2" (ret), "3" (n) \ - : "D1Ar1", "D0Ar2", "memory") + : "D1Ar1", "D0Ar2", "cc", "memory") /* rewind 'to' and 'from' pointers when a fault occurs * @@ -342,7 +349,7 @@ #define __asm_copy_to_user_64bit_rapf_loop(to, from, ret, n, id)\ __asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \ "LSR D0Ar2, D0Ar2, #8\n" \ - "AND D0Ar2, D0Ar2, #0x7\n" \ + "ANDS D0Ar2, D0Ar2, #0x7\n" \ "ADDZ D0Ar2, D0Ar2, #4\n" \ "SUB D0Ar2, D0Ar2, #1\n" \ "MOV D1Ar1, #4\n" \ @@ -403,47 +410,55 @@ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ "22:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ - "SUB %3, %3, #16\n" \ "23:\n" \ - "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "24:\n" \ - "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ "SUB %3, %3, #16\n" \ - "25:\n" \ + "24:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "26:\n" \ + "25:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "26:\n" \ "SUB %3, %3, #16\n" \ "27:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ "28:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "29:\n" \ + "SUB %3, %3, #16\n" \ + "30:\n" \ + "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ + "31:\n" \ + "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "32:\n" \ "SUB %3, %3, #16\n" \ "DCACHE [%1+#-64], D0Ar6\n" \ "BR $Lloop"id"\n" \ \ "MOV RAPF, %1\n" \ - "29:\n" \ + "33:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "30:\n" \ + "34:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "35:\n" \ "SUB %3, %3, #16\n" \ - "31:\n" \ + "36:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "32:\n" \ + "37:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "38:\n" \ "SUB %3, %3, #16\n" \ - "33:\n" \ + "39:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "34:\n" \ + "40:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "41:\n" \ "SUB %3, %3, #16\n" \ - "35:\n" \ + "42:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "36:\n" \ + "43:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "44:\n" \ "SUB %0, %0, #4\n" \ - "37:\n" \ + "45:\n" \ "SETD [%0++], D0.7\n" \ "SUB %3, %3, #16\n" \ "1:" \ @@ -483,11 +498,19 @@ " .long 34b,3b\n" \ " .long 35b,3b\n" \ " .long 36b,3b\n" \ - " .long 37b,4b\n" \ + " .long 37b,3b\n" \ + " .long 38b,3b\n" \ + " .long 39b,3b\n" \ + " .long 40b,3b\n" \ + " .long 41b,3b\n" \ + " .long 42b,3b\n" \ + " .long 43b,3b\n" \ + " .long 44b,3b\n" \ + " .long 45b,4b\n" \ " .previous\n" \ : "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \ : "0" (to), "1" (from), "2" (ret), "3" (n) \ - : "D1Ar1", "D0Ar2", "memory") + : "D1Ar1", "D0Ar2", "cc", "memory") /* rewind 'to' and 'from' pointers when a fault occurs * @@ -513,7 +536,7 @@ #define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\ __asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \ "LSR D0Ar2, D0Ar2, #8\n" \ - "AND D0Ar2, D0Ar2, #0x7\n" \ + "ANDS D0Ar2, D0Ar2, #0x7\n" \ "ADDZ D0Ar2, D0Ar2, #4\n" \ "SUB D0Ar2, D0Ar2, #1\n" \ "MOV D1Ar1, #4\n" \ @@ -538,23 +561,31 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, if ((unsigned long) src & 1) { __asm_copy_to_user_1(dst, src, retn); n--; + if (retn) + return retn + n; } if ((unsigned long) dst & 1) { /* Worst case - byte copy */ while (n > 0) { __asm_copy_to_user_1(dst, src, retn); n--; + if (retn) + return retn + n; } } if (((unsigned long) src & 2) && n >= 2) { __asm_copy_to_user_2(dst, src, retn); n -= 2; + if (retn) + return retn + n; } if ((unsigned long) dst & 2) { /* Second worst case - word copy */ while (n >= 2) { __asm_copy_to_user_2(dst, src, retn); n -= 2; + if (retn) + return retn + n; } } @@ -569,6 +600,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, while (n >= 8) { __asm_copy_to_user_8x64(dst, src, retn); n -= 8; + if (retn) + return retn + n; } } if (n >= RAPF_MIN_BUF_SIZE) { @@ -581,6 +614,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, while (n >= 8) { __asm_copy_to_user_8x64(dst, src, retn); n -= 8; + if (retn) + return retn + n; } } #endif @@ -588,11 +623,15 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, while (n >= 16) { __asm_copy_to_user_16(dst, src, retn); n -= 16; + if (retn) + return retn + n; } while (n >= 4) { __asm_copy_to_user_4(dst, src, retn); n -= 4; + if (retn) + return retn + n; } switch (n) { @@ -609,6 +648,10 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, break; } + /* + * If we get here, retn correctly reflects the number of failing + * bytes. + */ return retn; } EXPORT_SYMBOL(__copy_user); @@ -617,16 +660,14 @@ EXPORT_SYMBOL(__copy_user); __asm_copy_user_cont(to, from, ret, \ " GETB D1Ar1,[%1++]\n" \ "2: SETB [%0++],D1Ar1\n", \ - "3: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ + "3: ADD %2,%2,#1\n", \ " .long 2b,3b\n") #define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ __asm_copy_user_cont(to, from, ret, \ " GETW D1Ar1,[%1++]\n" \ "2: SETW [%0++],D1Ar1\n" COPY, \ - "3: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ + "3: ADD %2,%2,#2\n" FIXUP, \ " .long 2b,3b\n" TENTRY) #define __asm_copy_from_user_2(to, from, ret) \ @@ -636,145 +677,26 @@ EXPORT_SYMBOL(__copy_user); __asm_copy_from_user_2x_cont(to, from, ret, \ " GETB D1Ar1,[%1++]\n" \ "4: SETB [%0++],D1Ar1\n", \ - "5: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ + "5: ADD %2,%2,#1\n", \ " .long 4b,5b\n") #define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ __asm_copy_user_cont(to, from, ret, \ " GETD D1Ar1,[%1++]\n" \ "2: SETD [%0++],D1Ar1\n" COPY, \ - "3: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ + "3: ADD %2,%2,#4\n" FIXUP, \ " .long 2b,3b\n" TENTRY) #define __asm_copy_from_user_4(to, from, ret) \ __asm_copy_from_user_4x_cont(to, from, ret, "", "", "") -#define __asm_copy_from_user_5(to, from, ret) \ - __asm_copy_from_user_4x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "4: SETB [%0++],D1Ar1\n", \ - "5: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 4b,5b\n") - -#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_4x_cont(to, from, ret, \ - " GETW D1Ar1,[%1++]\n" \ - "4: SETW [%0++],D1Ar1\n" COPY, \ - "5: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ - " .long 4b,5b\n" TENTRY) - -#define __asm_copy_from_user_6(to, from, ret) \ - __asm_copy_from_user_6x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_7(to, from, ret) \ - __asm_copy_from_user_6x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "6: SETB [%0++],D1Ar1\n", \ - "7: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 6b,7b\n") - -#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_4x_cont(to, from, ret, \ - " GETD D1Ar1,[%1++]\n" \ - "4: SETD [%0++],D1Ar1\n" COPY, \ - "5: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ - " .long 4b,5b\n" TENTRY) - -#define __asm_copy_from_user_8(to, from, ret) \ - __asm_copy_from_user_8x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_9(to, from, ret) \ - __asm_copy_from_user_8x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "6: SETB [%0++],D1Ar1\n", \ - "7: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 6b,7b\n") - -#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_8x_cont(to, from, ret, \ - " GETW D1Ar1,[%1++]\n" \ - "6: SETW [%0++],D1Ar1\n" COPY, \ - "7: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ - " .long 6b,7b\n" TENTRY) - -#define __asm_copy_from_user_10(to, from, ret) \ - __asm_copy_from_user_10x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_11(to, from, ret) \ - __asm_copy_from_user_10x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "8: SETB [%0++],D1Ar1\n", \ - "9: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 8b,9b\n") - -#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_8x_cont(to, from, ret, \ - " GETD D1Ar1,[%1++]\n" \ - "6: SETD [%0++],D1Ar1\n" COPY, \ - "7: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ - " .long 6b,7b\n" TENTRY) - -#define __asm_copy_from_user_12(to, from, ret) \ - __asm_copy_from_user_12x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_13(to, from, ret) \ - __asm_copy_from_user_12x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "8: SETB [%0++],D1Ar1\n", \ - "9: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 8b,9b\n") - -#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_12x_cont(to, from, ret, \ - " GETW D1Ar1,[%1++]\n" \ - "8: SETW [%0++],D1Ar1\n" COPY, \ - "9: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ - " .long 8b,9b\n" TENTRY) - -#define __asm_copy_from_user_14(to, from, ret) \ - __asm_copy_from_user_14x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_15(to, from, ret) \ - __asm_copy_from_user_14x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "10: SETB [%0++],D1Ar1\n", \ - "11: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 10b,11b\n") - -#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_12x_cont(to, from, ret, \ - " GETD D1Ar1,[%1++]\n" \ - "8: SETD [%0++],D1Ar1\n" COPY, \ - "9: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ - " .long 8b,9b\n" TENTRY) - -#define __asm_copy_from_user_16(to, from, ret) \ - __asm_copy_from_user_16x_cont(to, from, ret, "", "", "") - #define __asm_copy_from_user_8x64(to, from, ret) \ asm volatile ( \ " GETL D0Ar2,D1Ar1,[%1++]\n" \ "2: SETL [%0++],D0Ar2,D1Ar1\n" \ "1:\n" \ " .section .fixup,\"ax\"\n" \ - " MOV D1Ar1,#0\n" \ - " MOV D0Ar2,#0\n" \ "3: ADD %2,%2,#8\n" \ - " SETL [%0++],D0Ar2,D1Ar1\n" \ " MOVT D0Ar2,#HI(1b)\n" \ " JUMP D0Ar2,#LO(1b)\n" \ " .previous\n" \ @@ -789,36 +711,57 @@ EXPORT_SYMBOL(__copy_user); * * Rationale: * A fault occurs while reading from user buffer, which is the - * source. Since the fault is at a single address, we only - * need to rewind by 8 bytes. + * source. * Since we don't write to kernel buffer until we read first, * the kernel buffer is at the right state and needn't be - * corrected. + * corrected, but the source must be rewound to the beginning of + * the block, which is LSM_STEP*8 bytes. + * LSM_STEP is bits 10:8 in TXSTATUS which is already read + * and stored in D0Ar2 + * + * NOTE: If a fault occurs at the last operation in M{G,S}ETL + * LSM_STEP will be 0. ie: we do 4 writes in our case, if + * a fault happens at the 4th write, LSM_STEP will be 0 + * instead of 4. The code copes with that. */ #define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id) \ __asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \ - "SUB %1, %1, #8\n") + "LSR D0Ar2, D0Ar2, #5\n" \ + "ANDS D0Ar2, D0Ar2, #0x38\n" \ + "ADDZ D0Ar2, D0Ar2, #32\n" \ + "SUB %1, %1, D0Ar2\n") /* rewind 'from' pointer when a fault occurs * * Rationale: * A fault occurs while reading from user buffer, which is the - * source. Since the fault is at a single address, we only - * need to rewind by 4 bytes. + * source. * Since we don't write to kernel buffer until we read first, * the kernel buffer is at the right state and needn't be - * corrected. + * corrected, but the source must be rewound to the beginning of + * the block, which is LSM_STEP*4 bytes. + * LSM_STEP is bits 10:8 in TXSTATUS which is already read + * and stored in D0Ar2 + * + * NOTE: If a fault occurs at the last operation in M{G,S}ETL + * LSM_STEP will be 0. ie: we do 4 writes in our case, if + * a fault happens at the 4th write, LSM_STEP will be 0 + * instead of 4. The code copes with that. */ #define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id) \ __asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \ - "SUB %1, %1, #4\n") + "LSR D0Ar2, D0Ar2, #6\n" \ + "ANDS D0Ar2, D0Ar2, #0x1c\n" \ + "ADDZ D0Ar2, D0Ar2, #16\n" \ + "SUB %1, %1, D0Ar2\n") -/* Copy from user to kernel, zeroing the bytes that were inaccessible in - userland. The return-value is the number of bytes that were - inaccessible. */ -unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, - unsigned long n) +/* + * Copy from user to kernel. The return-value is the number of bytes that were + * inaccessible. + */ +unsigned long raw_copy_from_user(void *pdst, const void __user *psrc, + unsigned long n) { register char *dst asm ("A0.2") = pdst; register const char __user *src asm ("A1.2") = psrc; @@ -830,6 +773,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, if ((unsigned long) src & 1) { __asm_copy_from_user_1(dst, src, retn); n--; + if (retn) + return retn + n; } if ((unsigned long) dst & 1) { /* Worst case - byte copy */ @@ -837,12 +782,14 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_1(dst, src, retn); n--; if (retn) - goto copy_exception_bytes; + return retn + n; } } if (((unsigned long) src & 2) && n >= 2) { __asm_copy_from_user_2(dst, src, retn); n -= 2; + if (retn) + return retn + n; } if ((unsigned long) dst & 2) { /* Second worst case - word copy */ @@ -850,16 +797,10 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_2(dst, src, retn); n -= 2; if (retn) - goto copy_exception_bytes; + return retn + n; } } - /* We only need one check after the unalignment-adjustments, - because if both adjustments were done, either both or - neither reference had an exception. */ - if (retn != 0) - goto copy_exception_bytes; - #ifdef USE_RAPF /* 64 bit copy loop */ if (!(((unsigned long) src | (unsigned long) dst) & 7)) { @@ -872,7 +813,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_8x64(dst, src, retn); n -= 8; if (retn) - goto copy_exception_bytes; + return retn + n; } } @@ -888,7 +829,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_8x64(dst, src, retn); n -= 8; if (retn) - goto copy_exception_bytes; + return retn + n; } } #endif @@ -898,7 +839,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, n -= 4; if (retn) - goto copy_exception_bytes; + return retn + n; } /* If we get here, there were no memory read faults. */ @@ -924,21 +865,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, /* If we get here, retn correctly reflects the number of failing bytes. */ return retn; - - copy_exception_bytes: - /* We already have "retn" bytes cleared, and need to clear the - remaining "n" bytes. A non-optimized simple byte-for-byte in-line - memset is preferred here, since this isn't speed-critical code and - we'd rather have this a leaf-function than calling memset. */ - { - char *endp; - for (endp = dst + n; dst < endp; dst++) - *dst = 0; - } - - return retn + n; } -EXPORT_SYMBOL(__copy_user_zeroing); +EXPORT_SYMBOL(raw_copy_from_user); #define __asm_clear_8x64(to, ret) \ asm volatile ( \ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index db459612de44..8b0424abc84c 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -9,6 +9,7 @@ config MIPS select HAVE_CONTEXT_TRACKING select HAVE_GENERIC_DMA_COHERENT select HAVE_IDE + select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_OPROFILE select HAVE_PERF_EVENTS select PERF_USE_VMALLOC @@ -1463,7 +1464,7 @@ config CPU_MIPS64_R6 select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_MSA select GENERIC_CSUM - select MIPS_O32_FP64_SUPPORT if MIPS32_O32 + select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32 help Choose this option to build a kernel for release 6 or later of the MIPS64 architecture. New MIPS processors, starting with the Warrior diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c index 3cedd1f95e0f..8ae4067a5eda 100644 --- a/arch/mips/ath79/common.c +++ b/arch/mips/ath79/common.c @@ -76,14 +76,14 @@ void ath79_ddr_set_pci_windows(void) { BUG_ON(!ath79_ddr_pci_win_base); - __raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0); - __raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 1); - __raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 2); - __raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 3); - __raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 4); - __raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 5); - __raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 6); - __raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 7); + __raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0x0); + __raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 0x4); + __raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 0x8); + __raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 0xc); + __raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 0x10); + __raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 0x14); + __raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 0x18); + __raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 0x1c); } EXPORT_SYMBOL_GPL(ath79_ddr_set_pci_windows); diff --git a/arch/mips/bcm47xx/buttons.c b/arch/mips/bcm47xx/buttons.c index 52caa75bfe4e..e2f50d690624 100644 --- a/arch/mips/bcm47xx/buttons.c +++ b/arch/mips/bcm47xx/buttons.c @@ -17,6 +17,12 @@ .active_low = 1, \ } +#define BCM47XX_GPIO_KEY_H(_gpio, _code) \ + { \ + .code = _code, \ + .gpio = _gpio, \ + } + /* Asus */ static const struct gpio_keys_button @@ -79,8 +85,8 @@ bcm47xx_buttons_asus_wl500gpv2[] __initconst = { static const struct gpio_keys_button bcm47xx_buttons_asus_wl500w[] __initconst = { - BCM47XX_GPIO_KEY(6, KEY_RESTART), - BCM47XX_GPIO_KEY(7, KEY_WPS_BUTTON), + BCM47XX_GPIO_KEY_H(6, KEY_RESTART), + BCM47XX_GPIO_KEY_H(7, KEY_WPS_BUTTON), }; static const struct gpio_keys_button diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S index 64e08df51d65..8b7004132491 100644 --- a/arch/mips/cavium-octeon/octeon-memcpy.S +++ b/arch/mips/cavium-octeon/octeon-memcpy.S @@ -208,18 +208,18 @@ EXC( STORE t2, UNIT(6)(dst), s_exc_p10u) ADD src, src, 16*NBYTES EXC( STORE t3, UNIT(7)(dst), s_exc_p9u) ADD dst, dst, 16*NBYTES -EXC( LOAD t0, UNIT(-8)(src), l_exc_copy) -EXC( LOAD t1, UNIT(-7)(src), l_exc_copy) -EXC( LOAD t2, UNIT(-6)(src), l_exc_copy) -EXC( LOAD t3, UNIT(-5)(src), l_exc_copy) +EXC( LOAD t0, UNIT(-8)(src), l_exc_copy_rewind16) +EXC( LOAD t1, UNIT(-7)(src), l_exc_copy_rewind16) +EXC( LOAD t2, UNIT(-6)(src), l_exc_copy_rewind16) +EXC( LOAD t3, UNIT(-5)(src), l_exc_copy_rewind16) EXC( STORE t0, UNIT(-8)(dst), s_exc_p8u) EXC( STORE t1, UNIT(-7)(dst), s_exc_p7u) EXC( STORE t2, UNIT(-6)(dst), s_exc_p6u) EXC( STORE t3, UNIT(-5)(dst), s_exc_p5u) -EXC( LOAD t0, UNIT(-4)(src), l_exc_copy) -EXC( LOAD t1, UNIT(-3)(src), l_exc_copy) -EXC( LOAD t2, UNIT(-2)(src), l_exc_copy) -EXC( LOAD t3, UNIT(-1)(src), l_exc_copy) +EXC( LOAD t0, UNIT(-4)(src), l_exc_copy_rewind16) +EXC( LOAD t1, UNIT(-3)(src), l_exc_copy_rewind16) +EXC( LOAD t2, UNIT(-2)(src), l_exc_copy_rewind16) +EXC( LOAD t3, UNIT(-1)(src), l_exc_copy_rewind16) EXC( STORE t0, UNIT(-4)(dst), s_exc_p4u) EXC( STORE t1, UNIT(-3)(dst), s_exc_p3u) EXC( STORE t2, UNIT(-2)(dst), s_exc_p2u) @@ -383,6 +383,10 @@ done: nop END(memcpy) +l_exc_copy_rewind16: + /* Rewind src and dst by 16*NBYTES for l_exc_copy */ + SUB src, src, 16*NBYTES + SUB dst, dst, 16*NBYTES l_exc_copy: /* * Copy bytes from src until faulting load address (or until a diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig index 57ed466e00db..2f140d75d01c 100644 --- a/arch/mips/configs/ip22_defconfig +++ b/arch/mips/configs/ip22_defconfig @@ -68,8 +68,8 @@ CONFIG_NETFILTER_NETLINK_QUEUE=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index 48e16d98b2cc..b15508447366 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -134,7 +134,7 @@ CONFIG_LIBFC=m CONFIG_SCSI_QLOGIC_1280=y CONFIG_SCSI_PMCRAID=m CONFIG_SCSI_BFA_FC=m -CONFIG_SCSI_DH=m +CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m @@ -206,7 +206,6 @@ CONFIG_MLX4_EN=m # CONFIG_MLX4_DEBUG is not set CONFIG_TEHUTI=m CONFIG_BNX2X=m -CONFIG_QLGE=m CONFIG_SFC=m CONFIG_BE2NET=m CONFIG_LIBERTAS_THINFIRM=m diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index 004cf52d1b7d..c24b87819ccb 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -39,7 +39,7 @@ CONFIG_HIBERNATION=y CONFIG_PM_STD_PARTITION="/dev/hda3" CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_DEBUG=y -CONFIG_CPU_FREQ_STAT=m +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_STAT_DETAILS=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig index 5afb4840aec7..739ccd0dca64 100644 --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@ -59,8 +59,8 @@ CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig index 98f13879bb8f..47f4ecf125ba 100644 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@ -60,8 +60,8 @@ CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig index 3b5d5913f548..e79d325aa085 100644 --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@ -59,8 +59,8 @@ CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig index 732215732751..ae87ad86243b 100644 --- a/arch/mips/configs/maltaup_xpa_defconfig +++ b/arch/mips/configs/maltaup_xpa_defconfig @@ -61,8 +61,8 @@ CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig index b3d1d37f85ea..47492fee2952 100644 --- a/arch/mips/configs/nlm_xlp_defconfig +++ b/arch/mips/configs/nlm_xlp_defconfig @@ -111,7 +111,7 @@ CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig index 3d8016d6cf3e..472a818f1eb8 100644 --- a/arch/mips/configs/nlm_xlr_defconfig +++ b/arch/mips/configs/nlm_xlr_defconfig @@ -91,7 +91,7 @@ CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S index 8c6f508e59de..554d1da97743 100644 --- a/arch/mips/dec/int-handler.S +++ b/arch/mips/dec/int-handler.S @@ -146,7 +146,25 @@ /* * Find irq with highest priority */ - PTR_LA t1,cpu_mask_nr_tbl + # open coded PTR_LA t1, cpu_mask_nr_tbl +#if (_MIPS_SZPTR == 32) + # open coded la t1, cpu_mask_nr_tbl + lui t1, %hi(cpu_mask_nr_tbl) + addiu t1, %lo(cpu_mask_nr_tbl) + +#endif +#if (_MIPS_SZPTR == 64) + # open coded dla t1, cpu_mask_nr_tbl + .set push + .set noat + lui t1, %highest(cpu_mask_nr_tbl) + lui AT, %hi(cpu_mask_nr_tbl) + daddiu t1, t1, %higher(cpu_mask_nr_tbl) + daddiu AT, AT, %lo(cpu_mask_nr_tbl) + dsll t1, 32 + daddu t1, t1, AT + .set pop +#endif 1: lw t2,(t1) nop and t2,t0 @@ -195,7 +213,25 @@ /* * Find irq with highest priority */ - PTR_LA t1,asic_mask_nr_tbl + # open coded PTR_LA t1,asic_mask_nr_tbl +#if (_MIPS_SZPTR == 32) + # open coded la t1, asic_mask_nr_tbl + lui t1, %hi(asic_mask_nr_tbl) + addiu t1, %lo(asic_mask_nr_tbl) + +#endif +#if (_MIPS_SZPTR == 64) + # open coded dla t1, asic_mask_nr_tbl + .set push + .set noat + lui t1, %highest(asic_mask_nr_tbl) + lui AT, %hi(asic_mask_nr_tbl) + daddiu t1, t1, %higher(asic_mask_nr_tbl) + daddiu AT, AT, %lo(asic_mask_nr_tbl) + dsll t1, 32 + daddu t1, t1, AT + .set pop +#endif 2: lw t2,(t1) nop and t2,t0 diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h index de781cf54bc7..da80878f2c0d 100644 --- a/arch/mips/include/asm/branch.h +++ b/arch/mips/include/asm/branch.h @@ -74,10 +74,7 @@ static inline int compute_return_epc(struct pt_regs *regs) return __microMIPS_compute_return_epc(regs); if (cpu_has_mips16) return __MIPS16e_compute_return_epc(regs); - return regs->cp0_epc; - } - - if (!delay_slot(regs)) { + } else if (!delay_slot(regs)) { regs->cp0_epc += 4; return 0; } diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 3ceacde5eb6e..17f89f9670b2 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -186,7 +186,9 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, " daddu %0, %4 \n" " dsll32 $1, %0, 0 \n" " daddu %0, $1 \n" + " sltu $1, %0, $1 \n" " dsra32 %0, %0, 0 \n" + " addu %0, $1 \n" #endif " .set pop" : "=r" (sum) diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 15e0fecbc300..ebb9efb02502 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -17,6 +17,18 @@ #include <irq.h> +#define IRQ_STACK_SIZE THREAD_SIZE + +extern void *irq_stack[NR_CPUS]; + +static inline bool on_irq_stack(int cpu, unsigned long sp) +{ + unsigned long low = (unsigned long)irq_stack[cpu]; + unsigned long high = low + IRQ_STACK_SIZE; + + return (low <= sp && sp <= high); +} + #ifdef CONFIG_I8259 static inline int irq_canonicalize(int irq) { diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 40196bebe849..2365ce0ad8f2 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -112,7 +112,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) " andi %[ticket], %[ticket], 0xffff \n" " bne %[ticket], %[my_ticket], 4f \n" " subu %[ticket], %[my_ticket], %[ticket] \n" - "2: \n" + "2: .insn \n" " .subsection 2 \n" "4: andi %[ticket], %[ticket], 0xffff \n" " sll %[ticket], 5 \n" @@ -187,7 +187,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) " sc %[ticket], %[ticket_ptr] \n" " beqz %[ticket], 1b \n" " li %[ticket], 1 \n" - "2: \n" + "2: .insn \n" " .subsection 2 \n" "3: b 2b \n" " li %[ticket], 0 \n" @@ -367,7 +367,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) " .set reorder \n" __WEAK_LLSC_MB " li %2, 1 \n" - "2: \n" + "2: .insn \n" : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) : GCC_OFF_SMALL_ASM() (rw->lock) : "memory"); @@ -407,7 +407,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) " lui %1, 0x8000 \n" " sc %1, %0 \n" " li %2, 1 \n" - "2: \n" + "2: .insn \n" : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) : GCC_OFF_SMALL_ASM() (rw->lock) diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h index a71da576883c..5347f130f536 100644 --- a/arch/mips/include/asm/stackframe.h +++ b/arch/mips/include/asm/stackframe.h @@ -216,12 +216,19 @@ LONG_S $25, PT_R25(sp) LONG_S $28, PT_R28(sp) LONG_S $31, PT_R31(sp) + + /* Set thread_info if we're coming from user mode */ + mfc0 k0, CP0_STATUS + sll k0, 3 /* extract cu0 bit */ + bltz k0, 9f + ori $28, sp, _THREAD_MASK xori $28, _THREAD_MASK #ifdef CONFIG_CPU_CAVIUM_OCTEON .set mips64 pref 0, 0($28) /* Prefetch the current pointer */ #endif +9: .set pop .endm diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 154e2039ea5e..ec053ce7bb38 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -101,6 +101,7 @@ void output_thread_info_defines(void) OFFSET(TI_REGS, thread_info, regs); DEFINE(_THREAD_SIZE, THREAD_SIZE); DEFINE(_THREAD_MASK, THREAD_MASK); + DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE); BLANK(); } diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index d8f9b357b222..71e8f4c0b8da 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -399,7 +399,7 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs) * * @regs: Pointer to pt_regs * @insn: branch instruction to decode - * @returns: -EFAULT on error and forces SIGBUS, and on success + * @returns: -EFAULT on error and forces SIGILL, and on success * returns 0 or BRANCH_LIKELY_TAKEN as appropriate after * evaluating the branch. * @@ -431,7 +431,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* Fall through */ case jr_op: if (NO_R6EMU && insn.r_format.func == jr_op) - goto sigill_r6; + goto sigill_r2r6; regs->cp0_epc = regs->regs[insn.r_format.rs]; break; } @@ -446,7 +446,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, switch (insn.i_format.rt) { case bltzl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bltz_op: if ((long)regs->regs[insn.i_format.rs] < 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -459,7 +459,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgez_op: if ((long)regs->regs[insn.i_format.rs] >= 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -473,10 +473,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bltzal_op: case bltzall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bltzall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bltzall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a NAL @@ -507,10 +505,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezal_op: case bgezall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bgezall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bgezall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a BAL @@ -556,6 +552,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* * These are unconditional and in j_format. */ + case jalx_op: case jal_op: regs->regs[31] = regs->cp0_epc + 8; case j_op: @@ -573,7 +570,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, */ case beql_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case beq_op: if (regs->regs[insn.i_format.rs] == regs->regs[insn.i_format.rt]) { @@ -587,7 +584,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bnel_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bne_op: if (regs->regs[insn.i_format.rs] != regs->regs[insn.i_format.rt]) { @@ -601,7 +598,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case blezl_op: /* not really i_format */ if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case blez_op: /* * Compact branches for R6 for the @@ -636,7 +633,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgtzl_op: if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgtz_op: /* * Compact branches for R6 for the @@ -816,8 +813,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, break; } /* Compact branch: BNEZC || JIALC */ - if (insn.i_format.rs) + if (!insn.i_format.rs) { + /* JIALC: set $31/ra */ regs->regs[31] = epc + 4; + } regs->cp0_epc += 8; break; #endif @@ -841,11 +840,12 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, return ret; sigill_dsp: - printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm); - force_sig(SIGBUS, current); + pr_info("%s: DSP branch but not DSP ASE - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); return -EFAULT; -sigill_r6: - pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n", +sigill_r2r6: + pr_info("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n", current->comm); force_sig(SIGILL, current); return -EFAULT; diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c index d434d5d5ae6e..610f0f3bdb34 100644 --- a/arch/mips/kernel/crash.c +++ b/arch/mips/kernel/crash.c @@ -14,12 +14,22 @@ static int crashing_cpu = -1; static cpumask_t cpus_in_crash = CPU_MASK_NONE; #ifdef CONFIG_SMP -static void crash_shutdown_secondary(void *ignore) +static void crash_shutdown_secondary(void *passed_regs) { - struct pt_regs *regs; + struct pt_regs *regs = passed_regs; int cpu = smp_processor_id(); - regs = task_pt_regs(current); + /* + * If we are passed registers, use those. Otherwise get the + * regs from the last interrupt, which should be correct, as + * we are in an interrupt. But if the regs are not there, + * pull them from the top of the stack. They are probably + * wrong, but we need something to keep from crashing again. + */ + if (!regs) + regs = get_irq_regs(); + if (!regs) + regs = task_pt_regs(current); if (!cpu_online(cpu)) return; diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index 4a4d9e067c89..3afffc30ee12 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -206,7 +206,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, else if ((prog_req.fr1 && prog_req.frdefault) || (prog_req.single && !prog_req.frdefault)) /* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */ - state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) && + state->overall_fp_mode = ((raw_current_cpu_data.fpu_id & MIPS_FPIR_F64) && cpu_has_mips_r2_r6) ? FP_FR1 : FP_FR0; else if (prog_req.fr1) diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index 7791840cf22c..db07793f7b43 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -11,6 +11,7 @@ #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/compiler.h> +#include <asm/irqflags.h> #include <asm/regdef.h> #include <asm/mipsregs.h> #include <asm/stackframe.h> @@ -137,6 +138,7 @@ work_pending: andi t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS beqz t0, work_notifysig work_resched: + TRACE_IRQS_OFF jal schedule local_irq_disable # make sure need_resched and @@ -173,6 +175,7 @@ syscall_exit_work: beqz t0, work_pending # trace bit set? local_irq_enable # could let syscall_trace_leave() # call schedule() instead + TRACE_IRQS_ON move a0, sp jal syscall_trace_leave b resume_userspace diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index baa7b6fc0a60..619e30e2c4f0 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -188,9 +188,44 @@ NESTED(handle_int, PT_SIZE, sp) LONG_L s0, TI_REGS($28) LONG_S sp, TI_REGS($28) - PTR_LA ra, ret_from_irq - PTR_LA v0, plat_irq_dispatch - jr v0 + + /* + * SAVE_ALL ensures we are using a valid kernel stack for the thread. + * Check if we are already using the IRQ stack. + */ + move s1, sp # Preserve the sp + + /* Get IRQ stack for this CPU */ + ASM_CPUID_MFC0 k0, ASM_SMP_CPUID_REG +#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32) + lui k1, %hi(irq_stack) +#else + lui k1, %highest(irq_stack) + daddiu k1, %higher(irq_stack) + dsll k1, 16 + daddiu k1, %hi(irq_stack) + dsll k1, 16 +#endif + LONG_SRL k0, SMP_CPUID_PTRSHIFT + LONG_ADDU k1, k0 + LONG_L t0, %lo(irq_stack)(k1) + + # Check if already on IRQ stack + PTR_LI t1, ~(_THREAD_SIZE-1) + and t1, t1, sp + beq t0, t1, 2f + + /* Switch to IRQ stack */ + li t1, _IRQ_STACK_SIZE + PTR_ADD sp, t0, t1 + +2: + jal plat_irq_dispatch + + /* Restore sp */ + move sp, s1 + + j ret_from_irq #ifdef CONFIG_CPU_MICROMIPS nop #endif @@ -263,8 +298,44 @@ NESTED(except_vec_vi_handler, 0, sp) LONG_L s0, TI_REGS($28) LONG_S sp, TI_REGS($28) - PTR_LA ra, ret_from_irq - jr v0 + + /* + * SAVE_ALL ensures we are using a valid kernel stack for the thread. + * Check if we are already using the IRQ stack. + */ + move s1, sp # Preserve the sp + + /* Get IRQ stack for this CPU */ + ASM_CPUID_MFC0 k0, ASM_SMP_CPUID_REG +#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32) + lui k1, %hi(irq_stack) +#else + lui k1, %highest(irq_stack) + daddiu k1, %higher(irq_stack) + dsll k1, 16 + daddiu k1, %hi(irq_stack) + dsll k1, 16 +#endif + LONG_SRL k0, SMP_CPUID_PTRSHIFT + LONG_ADDU k1, k0 + LONG_L t0, %lo(irq_stack)(k1) + + # Check if already on IRQ stack + PTR_LI t1, ~(_THREAD_SIZE-1) + and t1, t1, sp + beq t0, t1, 2f + + /* Switch to IRQ stack */ + li t1, _IRQ_STACK_SIZE + PTR_ADD sp, t0, t1 + +2: + jalr v0 + + /* Restore sp */ + move sp, s1 + + j ret_from_irq END(except_vec_vi_handler) /* diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index 8eb5af805964..dc1180a8bfa1 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -25,6 +25,8 @@ #include <linux/atomic.h> #include <asm/uaccess.h> +void *irq_stack[NR_CPUS]; + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -55,6 +57,15 @@ void __init init_IRQ(void) irq_set_noprobe(i); arch_init_irq(); + + for_each_possible_cpu(i) { + int irq_pages = IRQ_STACK_SIZE / PAGE_SIZE; + void *s = (void *)__get_free_pages(GFP_KERNEL, irq_pages); + + irq_stack[i] = s; + pr_debug("CPU%d IRQ stack at 0x%p - 0x%p\n", i, + irq_stack[i], irq_stack[i] + IRQ_STACK_SIZE); + } } #ifdef CONFIG_DEBUG_STACKOVERFLOW diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index de63d36af895..732d6171ac6a 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -244,9 +244,6 @@ static int compute_signal(int tt) void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) { int reg; - struct thread_info *ti = task_thread_info(p); - unsigned long ksp = (unsigned long)ti + THREAD_SIZE - 32; - struct pt_regs *regs = (struct pt_regs *)ksp - 1; #if (KGDB_GDB_REG_SIZE == 32) u32 *ptr = (u32 *)gdb_regs; #else @@ -254,25 +251,46 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) #endif for (reg = 0; reg < 16; reg++) - *(ptr++) = regs->regs[reg]; + *(ptr++) = 0; /* S0 - S7 */ - for (reg = 16; reg < 24; reg++) - *(ptr++) = regs->regs[reg]; + *(ptr++) = p->thread.reg16; + *(ptr++) = p->thread.reg17; + *(ptr++) = p->thread.reg18; + *(ptr++) = p->thread.reg19; + *(ptr++) = p->thread.reg20; + *(ptr++) = p->thread.reg21; + *(ptr++) = p->thread.reg22; + *(ptr++) = p->thread.reg23; for (reg = 24; reg < 28; reg++) *(ptr++) = 0; /* GP, SP, FP, RA */ - for (reg = 28; reg < 32; reg++) - *(ptr++) = regs->regs[reg]; - - *(ptr++) = regs->cp0_status; - *(ptr++) = regs->lo; - *(ptr++) = regs->hi; - *(ptr++) = regs->cp0_badvaddr; - *(ptr++) = regs->cp0_cause; - *(ptr++) = regs->cp0_epc; + *(ptr++) = (long)p; + *(ptr++) = p->thread.reg29; + *(ptr++) = p->thread.reg30; + *(ptr++) = p->thread.reg31; + + *(ptr++) = p->thread.cp0_status; + + /* lo, hi */ + *(ptr++) = 0; + *(ptr++) = 0; + + /* + * BadVAddr, Cause + * Ideally these would come from the last exception frame up the stack + * but that requires unwinding, otherwise we can't know much for sure. + */ + *(ptr++) = 0; + *(ptr++) = 0; + + /* + * PC + * use return address (RA), i.e. the moment after return from resume() + */ + *(ptr++) = p->thread.reg31; } void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index af27334d6809..e3384065f5e7 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -434,8 +434,8 @@ static int multu_func(struct pt_regs *regs, u32 ir) rs = regs->regs[MIPSInst_RS(ir)]; res = (u64)rt * (u64)rs; rt = res; - regs->lo = (s64)rt; - regs->hi = (s64)(res >> 32); + regs->lo = (s64)(s32)rt; + regs->hi = (s64)(s32)(res >> 32); MIPS_R2_STATS(muls); @@ -671,9 +671,9 @@ static int maddu_func(struct pt_regs *regs, u32 ir) res += ((((s64)rt) << 32) | (u32)rs); rt = res; - regs->lo = (s64)rt; + regs->lo = (s64)(s32)rt; rs = res >> 32; - regs->hi = (s64)rs; + regs->hi = (s64)(s32)rs; MIPS_R2_STATS(dsps); @@ -729,9 +729,9 @@ static int msubu_func(struct pt_regs *regs, u32 ir) res = ((((s64)rt) << 32) | (u32)rs) - res; rt = res; - regs->lo = (s64)rt; + regs->lo = (s64)(s32)rt; rs = res >> 32; - regs->hi = (s64)rs; + regs->hi = (s64)(s32)rs; MIPS_R2_STATS(dsps); diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index f63a289977cc..0b3e58a3189f 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -55,7 +55,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT); * state. Actually per-core rather than per-CPU. */ static DEFINE_PER_CPU_ALIGNED(u32*, ready_count); -static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc); /* Indicates online CPUs coupled with the current CPU */ static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled); @@ -625,7 +624,6 @@ static int __init cps_gen_core_entries(unsigned cpu) { enum cps_pm_state state; unsigned core = cpu_data[cpu].core; - unsigned dlinesz = cpu_data[cpu].dcache.linesz; void *entry_fn, *core_rc; for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) { @@ -645,16 +643,11 @@ static int __init cps_gen_core_entries(unsigned cpu) } if (!per_cpu(ready_count, core)) { - core_rc = kmalloc(dlinesz * 2, GFP_KERNEL); + core_rc = kmalloc(sizeof(u32), GFP_KERNEL); if (!core_rc) { pr_err("Failed allocate core %u ready_count\n", core); return -ENOMEM; } - per_cpu(ready_count_alloc, core) = core_rc; - - /* Ensure ready_count is aligned to a cacheline boundary */ - core_rc += dlinesz - 1; - core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1)); per_cpu(ready_count, core) = core_rc; } diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 298b2b773d12..f1fab6ff53e6 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -83,7 +83,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) } seq_printf(m, "isa\t\t\t:"); - if (cpu_has_mips_r1) + if (cpu_has_mips_1) seq_printf(m, " mips1"); if (cpu_has_mips_2) seq_printf(m, "%s", " mips2"); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 44a6f25e902e..8c26ecac930d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -32,6 +32,7 @@ #include <asm/cpu.h> #include <asm/dsp.h> #include <asm/fpu.h> +#include <asm/irq.h> #include <asm/msa.h> #include <asm/pgtable.h> #include <asm/mipsregs.h> @@ -191,11 +192,9 @@ struct mips_frame_info { #define J_TARGET(pc,target) \ (((unsigned long)(pc) & 0xf0000000) | ((target) << 2)) -static inline int is_ra_save_ins(union mips_instruction *ip) +static inline int is_ra_save_ins(union mips_instruction *ip, int *poff) { #ifdef CONFIG_CPU_MICROMIPS - union mips_instruction mmi; - /* * swsp ra,offset * swm16 reglist,offset(sp) @@ -205,29 +204,71 @@ static inline int is_ra_save_ins(union mips_instruction *ip) * * microMIPS is way more fun... */ - if (mm_insn_16bit(ip->halfword[0])) { - mmi.word = (ip->halfword[0] << 16); - return (mmi.mm16_r5_format.opcode == mm_swsp16_op && - mmi.mm16_r5_format.rt == 31) || - (mmi.mm16_m_format.opcode == mm_pool16c_op && - mmi.mm16_m_format.func == mm_swm16_op); + if (mm_insn_16bit(ip->halfword[1])) { + switch (ip->mm16_r5_format.opcode) { + case mm_swsp16_op: + if (ip->mm16_r5_format.rt != 31) + return 0; + + *poff = ip->mm16_r5_format.simmediate; + *poff = (*poff << 2) / sizeof(ulong); + return 1; + + case mm_pool16c_op: + switch (ip->mm16_m_format.func) { + case mm_swm16_op: + *poff = ip->mm16_m_format.imm; + *poff += 1 + ip->mm16_m_format.rlist; + *poff = (*poff << 2) / sizeof(ulong); + return 1; + + default: + return 0; + } + + default: + return 0; + } } - else { - mmi.halfword[0] = ip->halfword[1]; - mmi.halfword[1] = ip->halfword[0]; - return (mmi.mm_m_format.opcode == mm_pool32b_op && - mmi.mm_m_format.rd > 9 && - mmi.mm_m_format.base == 29 && - mmi.mm_m_format.func == mm_swm32_func) || - (mmi.i_format.opcode == mm_sw32_op && - mmi.i_format.rs == 29 && - mmi.i_format.rt == 31); + + switch (ip->i_format.opcode) { + case mm_sw32_op: + if (ip->i_format.rs != 29) + return 0; + if (ip->i_format.rt != 31) + return 0; + + *poff = ip->i_format.simmediate / sizeof(ulong); + return 1; + + case mm_pool32b_op: + switch (ip->mm_m_format.func) { + case mm_swm32_func: + if (ip->mm_m_format.rd < 0x10) + return 0; + if (ip->mm_m_format.base != 29) + return 0; + + *poff = ip->mm_m_format.simmediate; + *poff += (ip->mm_m_format.rd & 0xf) * sizeof(u32); + *poff /= sizeof(ulong); + return 1; + default: + return 0; + } + + default: + return 0; } #else /* sw / sd $ra, offset($sp) */ - return (ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op) && - ip->i_format.rs == 29 && - ip->i_format.rt == 31; + if ((ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op) && + ip->i_format.rs == 29 && ip->i_format.rt == 31) { + *poff = ip->i_format.simmediate / sizeof(ulong); + return 1; + } + + return 0; #endif } @@ -242,13 +283,16 @@ static inline int is_jump_ins(union mips_instruction *ip) * * microMIPS is kind of more fun... */ - union mips_instruction mmi; - - mmi.word = (ip->halfword[0] << 16); + if (mm_insn_16bit(ip->halfword[1])) { + if ((ip->mm16_r5_format.opcode == mm_pool16c_op && + (ip->mm16_r5_format.rt & mm_jr16_op) == mm_jr16_op)) + return 1; + return 0; + } - if ((mmi.mm16_r5_format.opcode == mm_pool16c_op && - (mmi.mm16_r5_format.rt & mm_jr16_op) == mm_jr16_op) || - ip->j_format.opcode == mm_jal32_op) + if (ip->j_format.opcode == mm_j32_op) + return 1; + if (ip->j_format.opcode == mm_jal32_op) return 1; if (ip->r_format.opcode != mm_pool32a_op || ip->r_format.func != mm_pool32axf_op) @@ -276,15 +320,13 @@ static inline int is_sp_move_ins(union mips_instruction *ip) * * microMIPS is not more fun... */ - if (mm_insn_16bit(ip->halfword[0])) { - union mips_instruction mmi; - - mmi.word = (ip->halfword[0] << 16); - return (mmi.mm16_r3_format.opcode == mm_pool16d_op && - mmi.mm16_r3_format.simmediate && mm_addiusp_func) || - (mmi.mm16_r5_format.opcode == mm_pool16d_op && - mmi.mm16_r5_format.rt == 29); + if (mm_insn_16bit(ip->halfword[1])) { + return (ip->mm16_r3_format.opcode == mm_pool16d_op && + ip->mm16_r3_format.simmediate && mm_addiusp_func) || + (ip->mm16_r5_format.opcode == mm_pool16d_op && + ip->mm16_r5_format.rt == 29); } + return ip->mm_i_format.opcode == mm_addiu32_op && ip->mm_i_format.rt == 29 && ip->mm_i_format.rs == 29; #else @@ -299,30 +341,36 @@ static inline int is_sp_move_ins(union mips_instruction *ip) static int get_frame_info(struct mips_frame_info *info) { -#ifdef CONFIG_CPU_MICROMIPS - union mips_instruction *ip = (void *) (((char *) info->func) - 1); -#else - union mips_instruction *ip = info->func; -#endif - unsigned max_insns = info->func_size / sizeof(union mips_instruction); - unsigned i; + bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS); + union mips_instruction insn, *ip, *ip_end; + const unsigned int max_insns = 128; + unsigned int i; info->pc_offset = -1; info->frame_size = 0; + ip = (void *)msk_isa16_mode((ulong)info->func); if (!ip) goto err; - if (max_insns == 0) - max_insns = 128U; /* unknown function size */ - max_insns = min(128U, max_insns); + ip_end = (void *)ip + info->func_size; - for (i = 0; i < max_insns; i++, ip++) { + for (i = 0; i < max_insns && ip < ip_end; i++, ip++) { + if (is_mmips && mm_insn_16bit(ip->halfword[0])) { + insn.halfword[0] = 0; + insn.halfword[1] = ip->halfword[0]; + } else if (is_mmips) { + insn.halfword[0] = ip->halfword[1]; + insn.halfword[1] = ip->halfword[0]; + } else { + insn.word = ip->word; + } - if (is_jump_ins(ip)) + if (is_jump_ins(&insn)) break; + if (!info->frame_size) { - if (is_sp_move_ins(ip)) + if (is_sp_move_ins(&insn)) { #ifdef CONFIG_CPU_MICROMIPS if (mm_insn_16bit(ip->halfword[0])) @@ -345,11 +393,9 @@ static int get_frame_info(struct mips_frame_info *info) } continue; } - if (info->pc_offset == -1 && is_ra_save_ins(ip)) { - info->pc_offset = - ip->i_format.simmediate / sizeof(long); + if (info->pc_offset == -1 && + is_ra_save_ins(&insn, &info->pc_offset)) break; - } } if (info->frame_size && info->pc_offset >= 0) /* nested */ return 0; @@ -507,7 +553,19 @@ EXPORT_SYMBOL(unwind_stack_by_address); unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, unsigned long pc, unsigned long *ra) { - unsigned long stack_page = (unsigned long)task_stack_page(task); + unsigned long stack_page = 0; + int cpu; + + for_each_possible_cpu(cpu) { + if (on_irq_stack(cpu, *sp)) { + stack_page = (unsigned long)irq_stack[cpu]; + break; + } + } + + if (!stack_page) + stack_page = (unsigned long)task_stack_page(task); + return unwind_stack_by_address(stack_page, sp, pc, ra); } #endif diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 74d581569778..24c115a0721a 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -485,7 +485,8 @@ static int fpr_set(struct task_struct *target, &target->thread.fpu, 0, sizeof(elf_fpregset_t)); - for (i = 0; i < NUM_FPU_REGS; i++) { + BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); + for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) { err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpr_val, i * sizeof(elf_fpreg_t), (i + 1) * sizeof(elf_fpreg_t)); @@ -926,7 +927,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_exit(regs, regs->regs[2]); + trace_sys_exit(regs, regs_return_value(regs)); if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 2d23c834ba96..29b0c5f978e4 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -372,7 +372,7 @@ EXPORT(sys_call_table) PTR sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index deac63315d0e..a6323a969919 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -312,7 +312,7 @@ EXPORT(sys_call_table) PTR sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_io_setup /* 5200 */ PTR sys_io_destroy PTR sys_io_getevents diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index ee93d5fe61d7..e0fdca8d3abe 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -298,7 +298,7 @@ EXPORT(sysn32_call_table) PTR compat_sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR compat_sys_io_setup /* 6200 */ PTR sys_io_destroy PTR compat_sys_io_getevents diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index b77052ec6fb2..87c697181d25 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -367,7 +367,7 @@ EXPORT(sys32_call_table) PTR compat_sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 53a7ef9a8f32..4234b2d726c5 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -28,6 +28,7 @@ #include <linux/elf.h> #include <asm/asm.h> +#include <asm/asm-eva.h> #include <asm/branch.h> #include <asm/cachectl.h> #include <asm/cacheflush.h> @@ -138,10 +139,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) __asm__ __volatile__ ( " .set "MIPS_ISA_ARCH_LEVEL" \n" " li %[err], 0 \n" - "1: ll %[old], (%[addr]) \n" + "1: \n" + user_ll("%[old]", "(%[addr])") " move %[tmp], %[new] \n" - "2: sc %[tmp], (%[addr]) \n" - " bnez %[tmp], 4f \n" + "2: \n" + user_sc("%[tmp]", "(%[addr])") + " beqz %[tmp], 4f \n" "3: \n" " .insn \n" " .subsection 2 \n" @@ -199,6 +202,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) unreachable(); } +/* + * mips_atomic_set() normally returns directly via syscall_exit potentially + * clobbering static registers, so be sure to preserve them. + */ +save_static_function(sys_sysmips); + SYSCALL_DEFINE3(sysmips, long, cmd, long, arg1, long, arg2) { switch (cmd) { diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 99a402231f4d..31ca2edd7218 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -194,6 +194,8 @@ void show_stack(struct task_struct *task, unsigned long *sp) { struct pt_regs regs; mm_segment_t old_fs = get_fs(); + + regs.cp0_status = KSU_KERNEL; if (sp) { regs.regs[29] = (unsigned long)sp; regs.regs[31] = 0; diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index 80554e8f6037..daf580ce5ca2 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -467,7 +467,7 @@ void __init ltq_soc_init(void) if (!np_xbar) panic("Failed to load xbar nodes from devicetree"); - if (of_address_to_resource(np_pmu, 0, &res_xbar)) + if (of_address_to_resource(np_xbar, 0, &res_xbar)) panic("Failed to get xbar resources"); if (request_mem_region(res_xbar.start, resource_size(&res_xbar), res_xbar.name) < 0) @@ -545,7 +545,7 @@ void __init ltq_soc_init(void) clkdev_add_pmu("1a800000.pcie", "msi", 1, 1, PMU1_PCIE2_MSI); clkdev_add_pmu("1a800000.pcie", "pdi", 1, 1, PMU1_PCIE2_PDI); clkdev_add_pmu("1a800000.pcie", "ctl", 1, 1, PMU1_PCIE2_CTL); - clkdev_add_pmu("1e108000.eth", NULL, 1, 0, PMU_SWITCH | PMU_PPE_DP); + clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); } else if (of_machine_is_compatible("lantiq,ar10")) { @@ -553,7 +553,7 @@ void __init ltq_soc_init(void) ltq_ar10_fpi_hz(), ltq_ar10_pp32_hz()); clkdev_add_pmu("1e101000.usb", "ctl", 1, 0, PMU_USB0); clkdev_add_pmu("1e106000.usb", "ctl", 1, 0, PMU_USB1); - clkdev_add_pmu("1e108000.eth", NULL, 1, 0, PMU_SWITCH | + clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP | PMU_PPE_TC); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); clkdev_add_pmu("1f203000.rcu", "gphy", 1, 0, PMU_GPHY); @@ -575,11 +575,11 @@ void __init ltq_soc_init(void) clkdev_add_pmu(NULL, "ahb", 1, 0, PMU_AHBM | PMU_AHBS); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1e108000.eth", NULL, 1, 0, + clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM | PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 | PMU_PPE_QSB | PMU_PPE_TOP); - clkdev_add_pmu("1f203000.rcu", "gphy", 1, 0, PMU_GPHY); + clkdev_add_pmu("1f203000.rcu", "gphy", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 734a2c7665ec..6da2e4a6ba39 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -2496,6 +2496,35 @@ dcopuop: return 0; } +/* + * Emulate FPU instructions. + * + * If we use FPU hardware, then we have been typically called to handle + * an unimplemented operation, such as where an operand is a NaN or + * denormalized. In that case exit the emulation loop after a single + * iteration so as to let hardware execute any subsequent instructions. + * + * If we have no FPU hardware or it has been disabled, then continue + * emulating floating-point instructions until one of these conditions + * has occurred: + * + * - a non-FPU instruction has been encountered, + * + * - an attempt to emulate has ended with a signal, + * + * - the ISA mode has been switched. + * + * We need to terminate the emulation loop if we got switched to the + * MIPS16 mode, whether supported or not, so that we do not attempt + * to emulate a MIPS16 instruction as a regular MIPS FPU instruction. + * Similarly if we got switched to the microMIPS mode and only the + * regular MIPS mode is supported, so that we do not attempt to emulate + * a microMIPS instruction as a regular MIPS FPU instruction. Or if + * we got switched to the regular MIPS mode and only the microMIPS mode + * is supported, so that we do not attempt to emulate a regular MIPS + * instruction that should cause an Address Error exception instead. + * For simplicity we always terminate upon an ISA mode switch. + */ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr) { @@ -2581,6 +2610,15 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; if (sig) break; + /* + * We have to check for the ISA bit explicitly here, + * because `get_isa16_mode' may return 0 if support + * for code compression has been globally disabled, + * or otherwise we may produce the wrong signal or + * even proceed successfully where we must not. + */ + if ((xcp->cp0_epc ^ prevepc) & 0x1) + break; cond_resched(); } while (xcp->cp0_epc > prevepc); diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 353037699512..c5fdea5debe5 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -92,7 +92,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/mips/mm/sc-ip22.c b/arch/mips/mm/sc-ip22.c index dc7c5a5214a9..efaf364fe581 100644 --- a/arch/mips/mm/sc-ip22.c +++ b/arch/mips/mm/sc-ip22.c @@ -31,26 +31,40 @@ static inline void indy_sc_wipe(unsigned long first, unsigned long last) unsigned long tmp; __asm__ __volatile__( - ".set\tpush\t\t\t# indy_sc_wipe\n\t" - ".set\tnoreorder\n\t" - ".set\tmips3\n\t" - ".set\tnoat\n\t" - "mfc0\t%2, $12\n\t" - "li\t$1, 0x80\t\t\t# Go 64 bit\n\t" - "mtc0\t$1, $12\n\t" - - "dli\t$1, 0x9000000080000000\n\t" - "or\t%0, $1\t\t\t# first line to flush\n\t" - "or\t%1, $1\t\t\t# last line to flush\n\t" - ".set\tat\n\t" - - "1:\tsw\t$0, 0(%0)\n\t" - "bne\t%0, %1, 1b\n\t" - " daddu\t%0, 32\n\t" - - "mtc0\t%2, $12\t\t\t# Back to 32 bit\n\t" - "nop; nop; nop; nop;\n\t" - ".set\tpop" + " .set push # indy_sc_wipe \n" + " .set noreorder \n" + " .set mips3 \n" + " .set noat \n" + " mfc0 %2, $12 \n" + " li $1, 0x80 # Go 64 bit \n" + " mtc0 $1, $12 \n" + " \n" + " # \n" + " # Open code a dli $1, 0x9000000080000000 \n" + " # \n" + " # Required because binutils 2.25 will happily accept \n" + " # 64 bit instructions in .set mips3 mode but puke on \n" + " # 64 bit constants when generating 32 bit ELF \n" + " # \n" + " lui $1,0x9000 \n" + " dsll $1,$1,0x10 \n" + " ori $1,$1,0x8000 \n" + " dsll $1,$1,0x10 \n" + " \n" + " or %0, $1 # first line to flush \n" + " or %1, $1 # last line to flush \n" + " .set at \n" + " \n" + "1: sw $0, 0(%0) \n" + " bne %0, %1, 1b \n" + " daddu %0, 32 \n" + " \n" + " mtc0 %2, $12 # Back to 32 bit \n" + " nop # pipeline hazard \n" + " nop \n" + " nop \n" + " nop \n" + " .set pop \n" : "=r" (first), "=r" (last), "=&r" (tmp) : "0" (first), "1" (last)); } diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 29f73e00253d..63b7d6f82d24 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -757,7 +757,8 @@ static void build_huge_update_entries(u32 **p, unsigned int pte, static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r, struct uasm_label **l, unsigned int pte, - unsigned int ptr) + unsigned int ptr, + unsigned int flush) { #ifdef CONFIG_SMP UASM_i_SC(p, pte, 0, ptr); @@ -766,6 +767,22 @@ static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r, #else UASM_i_SW(p, pte, 0, ptr); #endif + if (cpu_has_ftlb && flush) { + BUG_ON(!cpu_has_tlbinv); + + UASM_i_MFC0(p, ptr, C0_ENTRYHI); + uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV); + UASM_i_MTC0(p, ptr, C0_ENTRYHI); + build_tlb_write_entry(p, l, r, tlb_indexed); + + uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV); + UASM_i_MTC0(p, ptr, C0_ENTRYHI); + build_huge_update_entries(p, pte, ptr); + build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0); + + return; + } + build_huge_update_entries(p, pte, ptr); build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0); } @@ -2082,7 +2099,7 @@ static void build_r4000_tlb_load_handler(void) uasm_l_tlbl_goaround2(&l, p); } uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID)); - build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2); + build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1); #endif uasm_l_nopage_tlbl(&l, p); @@ -2137,7 +2154,7 @@ static void build_r4000_tlb_store_handler(void) build_tlb_probe_entry(&p); uasm_i_ori(&p, wr.r1, wr.r1, _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY); - build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2); + build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1); #endif uasm_l_nopage_tlbs(&l, p); @@ -2193,7 +2210,7 @@ static void build_r4000_tlb_modify_handler(void) build_tlb_probe_entry(&p); uasm_i_ori(&p, wr.r1, wr.r1, _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY); - build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2); + build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0); #endif uasm_l_nopage_tlbm(&l, p); diff --git a/arch/mips/netlogic/common/reset.S b/arch/mips/netlogic/common/reset.S index edbab9b8691f..c474981a6c0d 100644 --- a/arch/mips/netlogic/common/reset.S +++ b/arch/mips/netlogic/common/reset.S @@ -50,7 +50,6 @@ #include <asm/netlogic/xlp-hal/sys.h> #include <asm/netlogic/xlp-hal/cpucontrol.h> -#define CP0_EBASE $15 #define SYS_CPU_COHERENT_BASE CKSEG1ADDR(XLP_DEFAULT_IO_BASE) + \ XLP_IO_SYS_OFFSET(0) + XLP_IO_PCI_HDRSZ + \ SYS_CPU_NONCOHERENT_MODE * 4 @@ -92,7 +91,7 @@ * registers. On XLPII CPUs, usual cache instructions work. */ .macro xlp_flush_l1_dcache - mfc0 t0, CP0_EBASE, 0 + mfc0 t0, CP0_PRID andi t0, t0, PRID_IMP_MASK slt t1, t0, 0x1200 beqz t1, 15f @@ -171,7 +170,7 @@ FEXPORT(nlm_reset_entry) nop 1: /* Entry point on core wakeup */ - mfc0 t0, CP0_EBASE, 0 /* processor ID */ + mfc0 t0, CP0_PRID /* processor ID */ andi t0, PRID_IMP_MASK li t1, 0x1500 /* XLP 9xx */ beq t0, t1, 2f /* does not need to set coherent */ @@ -182,8 +181,8 @@ FEXPORT(nlm_reset_entry) nop /* set bit in SYS coherent register for the core */ - mfc0 t0, CP0_EBASE, 1 - mfc0 t1, CP0_EBASE, 1 + mfc0 t0, CP0_EBASE + mfc0 t1, CP0_EBASE srl t1, 5 andi t1, 0x3 /* t1 <- node */ li t2, 0x40000 @@ -232,7 +231,7 @@ EXPORT(nlm_boot_siblings) * NOTE: All GPR contents are lost after the mtcr above! */ - mfc0 v0, CP0_EBASE, 1 + mfc0 v0, CP0_EBASE andi v0, 0x3ff /* v0 <- node/core */ /* diff --git a/arch/mips/netlogic/common/smpboot.S b/arch/mips/netlogic/common/smpboot.S index 805355b0bd05..f0cc4c9de2bb 100644 --- a/arch/mips/netlogic/common/smpboot.S +++ b/arch/mips/netlogic/common/smpboot.S @@ -48,8 +48,6 @@ #include <asm/netlogic/xlp-hal/sys.h> #include <asm/netlogic/xlp-hal/cpucontrol.h> -#define CP0_EBASE $15 - .set noreorder .set noat .set arch=xlr /* for mfcr/mtcr, XLR is sufficient */ @@ -86,7 +84,7 @@ NESTED(nlm_boot_secondary_cpus, 16, sp) PTR_L gp, 0(t1) /* a0 has the processor id */ - mfc0 a0, CP0_EBASE, 1 + mfc0 a0, CP0_EBASE andi a0, 0x3ff /* a0 <- node/core */ PTR_LA t0, nlm_early_init_secondary jalr t0 diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index dfb04fcedb04..48d6349fd9d7 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -107,31 +107,31 @@ static struct rt2880_pmx_group mt7620a_pinmux_data[] = { }; static struct rt2880_pmx_func pwm1_grp_mt7628[] = { - FUNC("sdcx", 3, 19, 1), + FUNC("sdxc d6", 3, 19, 1), FUNC("utif", 2, 19, 1), FUNC("gpio", 1, 19, 1), - FUNC("pwm", 0, 19, 1), + FUNC("pwm1", 0, 19, 1), }; static struct rt2880_pmx_func pwm0_grp_mt7628[] = { - FUNC("sdcx", 3, 18, 1), + FUNC("sdxc d7", 3, 18, 1), FUNC("utif", 2, 18, 1), FUNC("gpio", 1, 18, 1), - FUNC("pwm", 0, 18, 1), + FUNC("pwm0", 0, 18, 1), }; static struct rt2880_pmx_func uart2_grp_mt7628[] = { - FUNC("sdcx", 3, 20, 2), + FUNC("sdxc d5 d4", 3, 20, 2), FUNC("pwm", 2, 20, 2), FUNC("gpio", 1, 20, 2), - FUNC("uart", 0, 20, 2), + FUNC("uart2", 0, 20, 2), }; static struct rt2880_pmx_func uart1_grp_mt7628[] = { - FUNC("sdcx", 3, 45, 2), + FUNC("sw_r", 3, 45, 2), FUNC("pwm", 2, 45, 2), FUNC("gpio", 1, 45, 2), - FUNC("uart", 0, 45, 2), + FUNC("uart1", 0, 45, 2), }; static struct rt2880_pmx_func i2c_grp_mt7628[] = { @@ -143,21 +143,21 @@ static struct rt2880_pmx_func i2c_grp_mt7628[] = { static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("reclk", 0, 36, 1) }; static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 37, 1) }; -static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 15, 38) }; +static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) }; static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) }; static struct rt2880_pmx_func sd_mode_grp_mt7628[] = { FUNC("jtag", 3, 22, 8), FUNC("utif", 2, 22, 8), FUNC("gpio", 1, 22, 8), - FUNC("sdcx", 0, 22, 8), + FUNC("sdxc", 0, 22, 8), }; static struct rt2880_pmx_func uart0_grp_mt7628[] = { FUNC("-", 3, 12, 2), FUNC("-", 2, 12, 2), FUNC("gpio", 1, 12, 2), - FUNC("uart", 0, 12, 2), + FUNC("uart0", 0, 12, 2), }; static struct rt2880_pmx_func i2s_grp_mt7628[] = { @@ -171,7 +171,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = { FUNC("-", 3, 6, 1), FUNC("refclk", 2, 6, 1), FUNC("gpio", 1, 6, 1), - FUNC("spi", 0, 6, 1), + FUNC("spi cs1", 0, 6, 1), }; static struct rt2880_pmx_func spis_grp_mt7628[] = { @@ -188,28 +188,44 @@ static struct rt2880_pmx_func gpio_grp_mt7628[] = { FUNC("gpio", 0, 11, 1), }; -#define MT7628_GPIO_MODE_MASK 0x3 - -#define MT7628_GPIO_MODE_PWM1 30 -#define MT7628_GPIO_MODE_PWM0 28 -#define MT7628_GPIO_MODE_UART2 26 -#define MT7628_GPIO_MODE_UART1 24 -#define MT7628_GPIO_MODE_I2C 20 -#define MT7628_GPIO_MODE_REFCLK 18 -#define MT7628_GPIO_MODE_PERST 16 -#define MT7628_GPIO_MODE_WDT 14 -#define MT7628_GPIO_MODE_SPI 12 -#define MT7628_GPIO_MODE_SDMODE 10 -#define MT7628_GPIO_MODE_UART0 8 -#define MT7628_GPIO_MODE_I2S 6 -#define MT7628_GPIO_MODE_CS1 4 -#define MT7628_GPIO_MODE_SPIS 2 -#define MT7628_GPIO_MODE_GPIO 0 +static struct rt2880_pmx_func wled_kn_grp_mt7628[] = { + FUNC("rsvd", 3, 35, 1), + FUNC("rsvd", 2, 35, 1), + FUNC("gpio", 1, 35, 1), + FUNC("wled_kn", 0, 35, 1), +}; + +static struct rt2880_pmx_func wled_an_grp_mt7628[] = { + FUNC("rsvd", 3, 44, 1), + FUNC("rsvd", 2, 44, 1), + FUNC("gpio", 1, 44, 1), + FUNC("wled_an", 0, 44, 1), +}; + +#define MT7628_GPIO_MODE_MASK 0x3 + +#define MT7628_GPIO_MODE_WLED_KN 48 +#define MT7628_GPIO_MODE_WLED_AN 32 +#define MT7628_GPIO_MODE_PWM1 30 +#define MT7628_GPIO_MODE_PWM0 28 +#define MT7628_GPIO_MODE_UART2 26 +#define MT7628_GPIO_MODE_UART1 24 +#define MT7628_GPIO_MODE_I2C 20 +#define MT7628_GPIO_MODE_REFCLK 18 +#define MT7628_GPIO_MODE_PERST 16 +#define MT7628_GPIO_MODE_WDT 14 +#define MT7628_GPIO_MODE_SPI 12 +#define MT7628_GPIO_MODE_SDMODE 10 +#define MT7628_GPIO_MODE_UART0 8 +#define MT7628_GPIO_MODE_I2S 6 +#define MT7628_GPIO_MODE_CS1 4 +#define MT7628_GPIO_MODE_SPIS 2 +#define MT7628_GPIO_MODE_GPIO 0 static struct rt2880_pmx_group mt7628an_pinmux_data[] = { - GRP_G("pmw1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK, + GRP_G("pwm1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK, 1, MT7628_GPIO_MODE_PWM1), - GRP_G("pmw1", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK, + GRP_G("pwm0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK, 1, MT7628_GPIO_MODE_PWM0), GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK, 1, MT7628_GPIO_MODE_UART2), @@ -233,6 +249,10 @@ static struct rt2880_pmx_group mt7628an_pinmux_data[] = { 1, MT7628_GPIO_MODE_SPIS), GRP_G("gpio", gpio_grp_mt7628, MT7628_GPIO_MODE_MASK, 1, MT7628_GPIO_MODE_GPIO), + GRP_G("wled_an", wled_an_grp_mt7628, MT7628_GPIO_MODE_MASK, + 1, MT7628_GPIO_MODE_WLED_AN), + GRP_G("wled_kn", wled_kn_grp_mt7628, MT7628_GPIO_MODE_MASK, + 1, MT7628_GPIO_MODE_WLED_KN), { 0 } }; @@ -439,7 +459,7 @@ void __init ralink_clk_init(void) ralink_clk_add("10000c00.uartlite", periph_rate); ralink_clk_add("10180000.wmac", xtal_rate); - if (IS_ENABLED(CONFIG_USB) && is_mt76x8()) { + if (IS_ENABLED(CONFIG_USB) && !is_mt76x8()) { /* * When the CPU goes into sleep mode, the BUS clock will be * too low for USB to function properly. Adjust the busses diff --git a/arch/mips/ralink/prom.c b/arch/mips/ralink/prom.c index 39a9142f71be..7ecb4af79b7b 100644 --- a/arch/mips/ralink/prom.c +++ b/arch/mips/ralink/prom.c @@ -30,8 +30,10 @@ const char *get_system_type(void) return soc_info.sys_type; } -static __init void prom_init_cmdline(int argc, char **argv) +static __init void prom_init_cmdline(void) { + int argc; + char **argv; int i; pr_debug("prom: fw_arg0=%08x fw_arg1=%08x fw_arg2=%08x fw_arg3=%08x\n", @@ -60,14 +62,11 @@ static __init void prom_init_cmdline(int argc, char **argv) void __init prom_init(void) { - int argc; - char **argv; - prom_soc_init(&soc_info); pr_info("SoC Type: %s\n", get_system_type()); - prom_init_cmdline(argc, argv); + prom_init_cmdline(); } void __init prom_free_prom_memory(void) diff --git a/arch/mips/ralink/rt288x.c b/arch/mips/ralink/rt288x.c index 844f5cd55c8f..9dd67749c592 100644 --- a/arch/mips/ralink/rt288x.c +++ b/arch/mips/ralink/rt288x.c @@ -40,16 +40,6 @@ static struct rt2880_pmx_group rt2880_pinmux_data_act[] = { { 0 } }; -static void rt288x_wdt_reset(void) -{ - u32 t; - - /* enable WDT reset output on pin SRAM_CS_N */ - t = rt_sysc_r32(SYSC_REG_CLKCFG); - t |= CLKCFG_SRAM_CS_N_WDT; - rt_sysc_w32(t, SYSC_REG_CLKCFG); -} - void __init ralink_clk_init(void) { unsigned long cpu_rate, wmac_rate = 40000000; @@ -119,5 +109,5 @@ void prom_soc_init(struct ralink_soc_info *soc_info) soc_info->mem_size_max = RT2880_MEM_SIZE_MAX; rt2880_pinmux_data = rt2880_pinmux_data_act; - ralink_soc == RT2880_SOC; + ralink_soc = RT2880_SOC; } diff --git a/arch/mips/ralink/rt305x.c b/arch/mips/ralink/rt305x.c index 9e4572592065..15b32cd01906 100644 --- a/arch/mips/ralink/rt305x.c +++ b/arch/mips/ralink/rt305x.c @@ -89,17 +89,6 @@ static struct rt2880_pmx_group rt5350_pinmux_data[] = { { 0 } }; -static void rt305x_wdt_reset(void) -{ - u32 t; - - /* enable WDT reset output on pin SRAM_CS_N */ - t = rt_sysc_r32(SYSC_REG_SYSTEM_CONFIG); - t |= RT305X_SYSCFG_SRAM_CS0_MODE_WDT << - RT305X_SYSCFG_SRAM_CS0_MODE_SHIFT; - rt_sysc_w32(t, SYSC_REG_SYSTEM_CONFIG); -} - static unsigned long rt5350_get_mem_size(void) { void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT305X_SYSC_BASE); diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c index 582995aaaf4e..3c575093f8f1 100644 --- a/arch/mips/ralink/rt3883.c +++ b/arch/mips/ralink/rt3883.c @@ -36,7 +36,7 @@ static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) }; static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) }; static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) }; static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) }; -static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) }; +static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) }; static struct rt2880_pmx_func pci_func[] = { FUNC("pci-dev", 0, 40, 32), FUNC("pci-host2", 1, 40, 32), @@ -44,7 +44,7 @@ static struct rt2880_pmx_func pci_func[] = { FUNC("pci-fnc", 3, 40, 32) }; static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) }; -static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) }; +static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) }; static struct rt2880_pmx_group rt3883_pinmux_data[] = { GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C), @@ -63,16 +63,6 @@ static struct rt2880_pmx_group rt3883_pinmux_data[] = { { 0 } }; -static void rt3883_wdt_reset(void) -{ - u32 t; - - /* enable WDT reset output on GPIO 2 */ - t = rt_sysc_r32(RT3883_SYSC_REG_SYSCFG1); - t |= RT3883_SYSCFG1_GPIO2_AS_WDT_OUT; - rt_sysc_w32(t, RT3883_SYSC_REG_SYSCFG1); -} - void __init ralink_clk_init(void) { unsigned long cpu_rate, sys_rate; diff --git a/arch/mips/sgi-ip22/Platform b/arch/mips/sgi-ip22/Platform index b7a4b7e04c38..e8f6b3a42a48 100644 --- a/arch/mips/sgi-ip22/Platform +++ b/arch/mips/sgi-ip22/Platform @@ -25,7 +25,7 @@ endif # Simplified: what IP22 does at 128MB+ in ksegN, IP28 does at 512MB+ in xkphys # ifdef CONFIG_SGI_IP28 - ifeq ($(call cc-option-yn,-mr10k-cache-barrier=store), n) + ifeq ($(call cc-option-yn,-march=r10000 -mr10k-cache-barrier=store), n) $(error gcc doesn't support needed option -mr10k-cache-barrier=store) endif endif diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c index 718dd197909f..de73beb36910 100644 --- a/arch/nios2/kernel/prom.c +++ b/arch/nios2/kernel/prom.c @@ -48,6 +48,13 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return alloc_bootmem_align(size, align); } +int __init early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, + bool nomap) +{ + reserve_bootmem(base, size, BOOTMEM_DEFAULT); + return 0; +} + void __init early_init_devtree(void *params) { __be32 *dtb = (u32 *)__dtb_start; diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index a4ff86d58d5c..6c4e351a7930 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -195,6 +195,9 @@ void __init setup_arch(char **cmdline_p) } #endif /* CONFIG_BLK_DEV_INITRD */ + early_init_fdt_reserve_self(); + early_init_fdt_scan_reserved_mem(); + unflatten_and_copy_device_tree(); setup_cpuinfo(); diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 2d69a853b742..3a08b55609b6 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -38,6 +38,8 @@ SECTIONS /* Read-only sections, merged into text segment: */ . = LOAD_BASE ; + _text = .; + /* _s_kernel_ro must be page aligned */ . = ALIGN(PAGE_SIZE); _s_kernel_ro = .; diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index 3f9406d9b9d6..da87943328a5 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -6,7 +6,7 @@ #endif #include <linux/compiler.h> -#include <asm/types.h> /* for BITS_PER_LONG/SHIFT_PER_LONG */ +#include <asm/types.h> #include <asm/byteorder.h> #include <asm/barrier.h> #include <linux/atomic.h> @@ -17,6 +17,12 @@ * to include/asm-i386/bitops.h or kerneldoc */ +#if __BITS_PER_LONG == 64 +#define SHIFT_PER_LONG 6 +#else +#define SHIFT_PER_LONG 5 +#endif + #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1)) diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h index d8d60a57183f..f53725202955 100644 --- a/arch/parisc/include/asm/dma-mapping.h +++ b/arch/parisc/include/asm/dma-mapping.h @@ -39,6 +39,8 @@ struct hppa_dma_ops { ** flush/purge and allocate "regular" cacheable pages for everything. */ +#define DMA_ERROR_CODE (~(dma_addr_t)0) + #ifdef CONFIG_PA11 extern struct hppa_dma_ops pcxl_dma_ops; extern struct hppa_dma_ops pcx_dma_ops; @@ -209,12 +211,13 @@ parisc_walk_tree(struct device *dev) break; } } - BUG_ON(!dev->platform_data); return dev->platform_data; } - -#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu) - + +#define GET_IOC(dev) ({ \ + void *__pdata = parisc_walk_tree(dev); \ + __pdata ? HBA_DATA(__pdata)->iommu : NULL; \ +}) #ifdef CONFIG_IOMMU_CCIO struct parisc_device; diff --git a/arch/parisc/include/asm/mmu_context.h b/arch/parisc/include/asm/mmu_context.h index 59be25764433..a81226257878 100644 --- a/arch/parisc/include/asm/mmu_context.h +++ b/arch/parisc/include/asm/mmu_context.h @@ -49,15 +49,26 @@ static inline void load_context(mm_context_t context) mtctl(__space_to_prot(context), 8); } -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) +static inline void switch_mm_irqs_off(struct mm_struct *prev, + struct mm_struct *next, struct task_struct *tsk) { - if (prev != next) { mtctl(__pa(next->pgd), 25); load_context(next->context); } } +static inline void switch_mm(struct mm_struct *prev, + struct mm_struct *next, struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + switch_mm_irqs_off(prev, next, tsk); + local_irq_restore(flags); +} +#define switch_mm_irqs_off switch_mm_irqs_off + #define deactivate_mm(tsk,mm) do { } while (0) static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h index e0a23c7bdd43..07fa7e50bdc0 100644 --- a/arch/parisc/include/uapi/asm/bitsperlong.h +++ b/arch/parisc/include/uapi/asm/bitsperlong.h @@ -3,10 +3,8 @@ #if defined(__LP64__) #define __BITS_PER_LONG 64 -#define SHIFT_PER_LONG 6 #else #define __BITS_PER_LONG 32 -#define SHIFT_PER_LONG 5 #endif #include <asm-generic/bitsperlong.h> diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h index e78403b129ef..928e1bbac98f 100644 --- a/arch/parisc/include/uapi/asm/swab.h +++ b/arch/parisc/include/uapi/asm/swab.h @@ -1,6 +1,7 @@ #ifndef _PARISC_SWAB_H #define _PARISC_SWAB_H +#include <asm/bitsperlong.h> #include <linux/types.h> #include <linux/compiler.h> @@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x) } #define __arch_swab32 __arch_swab32 -#if BITS_PER_LONG > 32 +#if __BITS_PER_LONG > 32 /* ** From "PA-RISC 2.0 Architecture", HP Professional Books. ** See Appendix I page 8 , "Endian Byte Swapping". @@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x) return x; } #define __arch_swab64 __arch_swab64 -#endif /* BITS_PER_LONG > 32 */ +#endif /* __BITS_PER_LONG > 32 */ #endif /* _PARISC_SWAB_H */ diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 5aba01ac457f..4dda73c44fee 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -88,7 +88,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; unsigned long task_size = TASK_SIZE; int do_color_align, last_mmap; struct vm_unmapped_area_info info; @@ -115,9 +115,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, else addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) goto found_addr; } @@ -141,7 +142,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; unsigned long addr = addr0; int do_color_align, last_mmap; @@ -175,9 +176,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = COLOR_ALIGN(addr, last_mmap, pgoff); else addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) goto found_addr; } diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index d4ffcfbc9885..041e1f9ec129 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -361,7 +361,7 @@ ENTRY_SAME(ni_syscall) /* 263: reserved for vserver */ ENTRY_SAME(add_key) ENTRY_SAME(request_key) /* 265 */ - ENTRY_SAME(keyctl) + ENTRY_COMP(keyctl) ENTRY_SAME(ioprio_set) ENTRY_SAME(ioprio_get) ENTRY_SAME(inotify_init) diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 16dbe81c97c9..2f33a67bc531 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -298,7 +298,7 @@ bad_area: case 15: /* Data TLB miss fault/Data page fault */ /* send SIGSEGV when outside of vma */ if (!vma || - address < vma->vm_start || address > vma->vm_end) { + address < vma->vm_start || address >= vma->vm_end) { si.si_signo = SIGSEGV; si.si_code = SEGV_MAPERR; break; diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S index 861e72109df2..f080abfc2f83 100644 --- a/arch/powerpc/boot/zImage.lds.S +++ b/arch/powerpc/boot/zImage.lds.S @@ -68,6 +68,7 @@ SECTIONS } #ifdef CONFIG_PPC64_BOOT_WRAPPER + . = ALIGN(256); .got : { __toc_start = .; diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 55f106ed12bf..039c4b910615 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -460,7 +460,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) * Atomically increments @v by 1, so long as @v is non-zero. * Returns non-zero if @v was non-zero, and zero otherwise. */ -static __inline__ long atomic64_inc_not_zero(atomic64_t *v) +static __inline__ int atomic64_inc_not_zero(atomic64_t *v) { long t1, t2; @@ -479,7 +479,7 @@ static __inline__ long atomic64_inc_not_zero(atomic64_t *v) : "r" (&v->counter) : "cc", "xer", "memory"); - return t1; + return t1 != 0; } #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index ee46ffef608e..743ad7a400d6 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -23,12 +23,13 @@ #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE PAGE_SIZE -/* This is the location that an ET_DYN program is loaded if exec'ed. Typical - use of this is to invoke "./ld.so someprog" to test out a new version of - the loader. We need to make sure that it is out of the way of the program - that it will "exec", and that there is sufficient room for the brk. */ - -#define ELF_ET_DYN_BASE 0x20000000 +/* + * This is the base location for PIE (ET_DYN with INTERP) loads. On + * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * space open for things that want to use the area for 32-bit pointers. + */ +#define ELF_ET_DYN_BASE (is_32bit_task() ? 0x000400000UL : \ + 0x100000000UL) #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 627d129d7fcb..ca372bbc0ffe 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1236,7 +1236,7 @@ static inline unsigned long mfvtb (void) " .llong 0\n" \ ".previous" \ : "=r" (rval) \ - : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL)); \ + : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ rval;}) #else #define mftb() ({unsigned long rval; \ diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 86150fbb42c3..91e5c1758b5c 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -808,14 +808,25 @@ int fix_alignment(struct pt_regs *regs) nb = aligninfo[instr].len; flags = aligninfo[instr].flags; - /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */ - if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) { - nb = 8; - flags = LD+SW; - } else if (IS_XFORM(instruction) && - ((instruction >> 1) & 0x3ff) == 660) { - nb = 8; - flags = ST+SW; + /* + * Handle some cases which give overlaps in the DSISR values. + */ + if (IS_XFORM(instruction)) { + switch (get_xop(instruction)) { + case 532: /* ldbrx */ + nb = 8; + flags = LD+SW; + break; + case 660: /* stdbrx */ + nb = 8; + flags = ST+SW; + break; + case 20: /* lwarx */ + case 84: /* ldarx */ + case 116: /* lharx */ + case 276: /* lqarx */ + return 0; /* not emulated ever */ + } } /* Byteswap little endian loads and stores */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 98949b0df00a..6696c1986844 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -304,9 +304,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) * * For pHyp, we have to enable IO for log retrieval. Otherwise, * 0xFF's is always returned from PCI config space. + * + * When the @severity is EEH_LOG_PERM, the PE is going to be + * removed. Prior to that, the drivers for devices included in + * the PE will be closed. The drivers rely on working IO path + * to bring the devices to quiet state. Otherwise, PCI traffic + * from those devices after they are removed is like to cause + * another unexpected EEH error. */ if (!(pe->type & EEH_PE_PHB)) { - if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG)) + if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) || + severity == EEH_LOG_PERM) eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); /* diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 300382e5a2cc..9837c98caabe 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -485,7 +485,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) static void *__eeh_clear_pe_frozen_state(void *data, void *flag) { struct eeh_pe *pe = (struct eeh_pe *)data; - bool *clear_sw_state = flag; + bool clear_sw_state = *(bool *)flag; int i, rc = 1; for (i = 0; rc && i < 3; i++) @@ -655,7 +655,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ #define MAX_WAIT_FOR_RECOVERY 300 -static void eeh_handle_normal_event(struct eeh_pe *pe) +static bool eeh_handle_normal_event(struct eeh_pe *pe) { struct pci_bus *frozen_bus; int rc = 0; @@ -665,7 +665,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) if (!frozen_bus) { pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n", __func__, pe->phb->global_number, pe->addr); - return; + return false; } eeh_pe_update_time_stamp(pe); @@ -790,7 +790,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Notify device driver to resume\n"); eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); - return; + return false; excess_failures: /* @@ -831,7 +831,11 @@ perm_error: pci_lock_rescan_remove(); pcibios_remove_pci_devices(frozen_bus); pci_unlock_rescan_remove(); + + /* The passed PE should no longer be used */ + return true; } + return false; } static void eeh_handle_special_event(void) @@ -897,7 +901,14 @@ static void eeh_handle_special_event(void) */ if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { - eeh_handle_normal_event(pe); + /* + * eeh_handle_normal_event() can make the PE stale if it + * determines that the PE cannot possibly be recovered. + * Don't modify the PE state if that's the case. + */ + if (eeh_handle_normal_event(pe)) + continue; + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } else { pci_lock_rescan_remove(); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index edba294620db..f6fd0332c3a2 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -716,7 +716,7 @@ resume_kernel: addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ - lwz r3,GPR1(r1) + ld r3,GPR1(r1) subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ mr r4,r1 /* src: current exception frame */ mr r1,r3 /* Reroute the trampoline frame to r1 */ @@ -730,8 +730,8 @@ resume_kernel: addi r6,r6,8 bdnz 2b - /* Do real store operation to complete stwu */ - lwz r5,GPR1(r1) + /* Do real store operation to complete stdu */ + ld r5,GPR1(r1) std r8,0(r5) /* Clear _TIF_EMULATE_STACK_STORE flag */ diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 488e6314f993..5cc93f0b52ca 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -735,8 +735,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f +#ifdef CONFIG_RELOCATABLE + ld r15,PACATOC(r13) + ld r14,interrupt_base_book3e@got(r15) + ld r15,__end_interrupts@got(r15) +#else LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) LOAD_REG_IMMEDIATE(r15,__end_interrupts) +#endif cmpld cr0,r10,r14 cmpld cr1,r10,r15 blt+ cr0,1f @@ -799,8 +805,14 @@ kernel_dbg_exc: andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f +#ifdef CONFIG_RELOCATABLE + ld r15,PACATOC(r13) + ld r14,interrupt_base_book3e@got(r15) + ld r15,__end_interrupts@got(r15) +#else LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) LOAD_REG_IMMEDIATE(r15,__end_interrupts) +#endif cmpld cr0,r10,r14 cmpld cr1,r10,r15 blt+ cr0,1f diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 05e804cdecaa..fdf48785d3e9 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -227,8 +227,10 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) rcu_read_lock(); bp = __this_cpu_read(bp_per_reg); - if (!bp) + if (!bp) { + rc = NOTIFY_DONE; goto out; + } info = counter_arch_bp(bp); /* diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 7c053f281406..1138fec3dd65 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -514,6 +514,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) #endif #endif + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); + return 1; } @@ -536,6 +545,8 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) * saved regs... */ memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); preempt_enable_no_resched(); return 1; } diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index b2eb4686bd8f..da3c4c3f4ec8 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -204,6 +204,8 @@ static void machine_check_process_queued_event(struct irq_work *work) { int index; + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + /* * For now just print it to console. * TODO: log this error event to FSP or nvram. diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 7b89e7b305e6..3139533640fc 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2664,6 +2664,9 @@ static void __init prom_find_boot_cpu(void) cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); + if (!PHANDLE_VALID(cpu_pkg)) + return; + prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5c03a6a9b054..a20823210ac0 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -220,6 +220,15 @@ static void cpu_ready_for_interrupts(void) unsigned long lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); } + + /* + * Fixup HFSCR:TM based on CPU features. The bit is set by our + * early asm init because at that point we haven't updated our + * CPU features from firmware and device-tree. Here we have, + * so let's do it. + */ + if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP)) + mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM); } /* diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 37de90f8a845..e4dcb0a43e3f 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -297,8 +297,6 @@ long machine_check_early(struct pt_regs *regs) __this_cpu_inc(irq_stat.mce_exceptions); - add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - if (cur_cpu_spec && cur_cpu_spec->machine_check_early) handled = cur_cpu_spec->machine_check_early(regs); return handled; @@ -704,6 +702,8 @@ void machine_check_exception(struct pt_regs *regs) __this_cpu_inc(irq_stat.mce_exceptions); + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + /* See if any machine dependent calls. In theory, we would want * to call the CPU first, and call the ppc_md. one if the CPU * one returns a positive number. However there is existing code diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 3c3a367b6e59..428563b195c3 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2687,12 +2687,38 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) { int r; int srcu_idx; + unsigned long ebb_regs[3] = {}; /* shut up GCC */ + unsigned long user_tar = 0; + unsigned long proc_fscr = 0; + unsigned int user_vrsave; if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } + /* + * Don't allow entry with a suspended transaction, because + * the guest entry/exit code will lose it. + * If the guest has TM enabled, save away their TM-related SPRs + * (they will get restored by the TM unavailable interrupt). + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && + (current->thread.regs->msr & MSR_TM)) { + if (MSR_TM_ACTIVE(current->thread.regs->msr)) { + run->exit_reason = KVM_EXIT_FAIL_ENTRY; + run->fail_entry.hardware_entry_failure_reason = 0; + return -EINVAL; + } + /* Enable TM so we can read the TM SPRs */ + mtmsr(mfmsr() | MSR_TM); + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + } +#endif + kvmppc_core_prepare_to_enter(vcpu); /* No need to go into the guest when all we'll do is come back out */ @@ -2715,6 +2741,17 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) flush_fp_to_thread(current); flush_altivec_to_thread(current); flush_vsx_to_thread(current); + + /* Save userspace EBB and other register values */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + ebb_regs[0] = mfspr(SPRN_EBBHR); + ebb_regs[1] = mfspr(SPRN_EBBRR); + ebb_regs[2] = mfspr(SPRN_BESCR); + user_tar = mfspr(SPRN_TAR); + proc_fscr = mfspr(SPRN_FSCR); + } + user_vrsave = mfspr(SPRN_VRSAVE); + vcpu->arch.wqp = &vcpu->arch.vcore->wq; vcpu->arch.pgdir = current->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; @@ -2736,6 +2773,29 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) } } while (is_kvmppc_resume_guest(r)); + /* Restore userspace EBB and other register values */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + mtspr(SPRN_EBBHR, ebb_regs[0]); + mtspr(SPRN_EBBRR, ebb_regs[1]); + mtspr(SPRN_BESCR, ebb_regs[2]); + mtspr(SPRN_TAR, user_tar); + mtspr(SPRN_FSCR, proc_fscr); + } + mtspr(SPRN_VRSAVE, user_vrsave); + + /* + * Since we don't do lazy TM reload, we need to reload + * the TM registers here. + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && + (current->thread.regs->msr & MSR_TM)) { + mtspr(SPRN_TFHAR, current->thread.tm_tfhar); + mtspr(SPRN_TFIAR, current->thread.tm_tfiar); + mtspr(SPRN_TEXASR, current->thread.tm_texasr); + } +#endif + out: vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&vcpu->kvm->arch.vcpus_running); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 1a743f87b37d..ffab9269bfe4 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -36,6 +36,13 @@ #define NAPPING_CEDE 1 #define NAPPING_NOVCPU 2 +/* Stack frame offsets for kvmppc_hv_entry */ +#define SFS 112 +#define STACK_SLOT_TRAP (SFS-4) +#define STACK_SLOT_CIABR (SFS-16) +#define STACK_SLOT_DAWR (SFS-24) +#define STACK_SLOT_DAWRX (SFS-32) + /* * Call kvmppc_hv_entry in real mode. * Must be called with interrupts hard-disabled. @@ -274,10 +281,10 @@ kvm_novcpu_exit: bl kvmhv_accumulate_time #endif 13: mr r3, r12 - stw r12, 112-4(r1) + stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, 112-4(r1) + lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -489,7 +496,7 @@ kvmppc_hv_entry: */ mflr r0 std r0, PPC_LR_STKOFF(r1) - stdu r1, -112(r1) + stdu r1, -SFS(r1) /* Save R1 in the PACA */ std r1, HSTATE_HOST_R1(r13) @@ -643,6 +650,16 @@ kvmppc_got_guest: mtspr SPRN_PURR,r7 mtspr SPRN_SPURR,r8 + /* Save host values of some registers */ +BEGIN_FTR_SECTION + mfspr r5, SPRN_CIABR + mfspr r6, SPRN_DAWR + mfspr r7, SPRN_DAWRX + std r5, STACK_SLOT_CIABR(r1) + std r6, STACK_SLOT_DAWR(r1) + std r7, STACK_SLOT_DAWRX(r1) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + BEGIN_FTR_SECTION /* Set partition DABR */ /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */ @@ -1266,8 +1283,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) */ li r0, 0 mtspr SPRN_IAMR, r0 - mtspr SPRN_CIABR, r0 - mtspr SPRN_DAWRX, r0 + mtspr SPRN_PSPB, r0 mtspr SPRN_TCSCR, r0 mtspr SPRN_WORT, r0 /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ @@ -1283,6 +1299,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6,VCPU_UAMOR(r9) li r6,0 mtspr SPRN_AMR,r6 + mtspr SPRN_UAMOR, r6 /* Switch DSCR back to host value */ mfspr r8, SPRN_DSCR @@ -1424,6 +1441,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) slbia ptesync + /* Restore host values of some registers */ +BEGIN_FTR_SECTION + ld r5, STACK_SLOT_CIABR(r1) + ld r6, STACK_SLOT_DAWR(r1) + ld r7, STACK_SLOT_DAWRX(r1) + mtspr SPRN_CIABR, r5 + mtspr SPRN_DAWR, r6 + mtspr SPRN_DAWRX, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + /* * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do @@ -1533,8 +1560,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) - ld r0, 112+PPC_LR_STKOFF(r1) - addi r1, r1, 112 + ld r0, SFS+PPC_LR_STKOFF(r1) + addi r1, r1, SFS mtlr r0 blr diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 5cc2e7af3a7b..b379146de55b 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -302,7 +302,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) advance = 0; printk(KERN_ERR "Couldn't emulate instruction 0x%08x " "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst)); - kvmppc_core_queue_program(vcpu, 0); } } diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index dc885b30f7a6..e37162d356d8 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -687,8 +687,10 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 19: switch ((instr >> 1) & 0x3ff) { case 0: /* mcrf */ - rd = (instr >> 21) & 0x1c; - ra = (instr >> 16) & 0x1c; + rd = 7 - ((instr >> 23) & 0x7); + ra = 7 - ((instr >> 18) & 0x7); + rd *= 4; + ra *= 4; val = (regs->ccr >> ra) & 0xf; regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd); goto instr_done; @@ -967,6 +969,19 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs, #endif case 19: /* mfcr */ + if ((instr >> 20) & 1) { + imm = 0xf0000000UL; + for (sh = 0; sh < 8; ++sh) { + if (instr & (0x80000 >> sh)) { + regs->gpr[rd] = regs->ccr & imm; + break; + } + imm >>= 4; + } + + goto instr_done; + } + regs->gpr[rd] = regs->ccr; regs->gpr[rd] &= 0xffffffffUL; goto instr_done; @@ -1806,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto instr_done; case LARX: - if (regs->msr & MSR_LE) - return 0; if (op.ea & (size - 1)) break; /* can't handle misaligned */ err = -EFAULT; @@ -1829,8 +1842,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto ldst_done; case STCX: - if (regs->msr & MSR_LE) - return 0; if (op.ea & (size - 1)) break; /* can't handle misaligned */ err = -EFAULT; @@ -1854,8 +1865,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto ldst_done; case LOAD: - if (regs->msr & MSR_LE) - return 0; err = read_mem(®s->gpr[op.reg], op.ea, size, regs); if (!err) { if (op.type & SIGNEXT) @@ -1867,8 +1876,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #ifdef CONFIG_PPC_FPU case LOAD_FP: - if (regs->msr & MSR_LE) - return 0; if (size == 4) err = do_fp_load(op.reg, do_lfs, op.ea, size, regs); else @@ -1877,15 +1884,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #endif #ifdef CONFIG_ALTIVEC case LOAD_VMX: - if (regs->msr & MSR_LE) - return 0; err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs); goto ldst_done; #endif #ifdef CONFIG_VSX case LOAD_VSX: - if (regs->msr & MSR_LE) - return 0; err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs); goto ldst_done; #endif @@ -1908,8 +1911,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) goto instr_done; case STORE: - if (regs->msr & MSR_LE) - return 0; if ((op.type & UPDATE) && size == sizeof(long) && op.reg == 1 && op.update_reg == 1 && !(regs->msr & MSR_PR) && @@ -1922,8 +1923,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #ifdef CONFIG_PPC_FPU case STORE_FP: - if (regs->msr & MSR_LE) - return 0; if (size == 4) err = do_fp_store(op.reg, do_stfs, op.ea, size, regs); else @@ -1932,15 +1931,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) #endif #ifdef CONFIG_ALTIVEC case STORE_VMX: - if (regs->msr & MSR_LE) - return 0; err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs); goto ldst_done; #endif #ifdef CONFIG_VSX case STORE_VSX: - if (regs->msr & MSR_LE) - return 0; err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs); goto ldst_done; #endif diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index c8822af10a58..19d9b2d2d212 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -645,6 +645,10 @@ static void native_flush_hash_range(unsigned long number, int local) unsigned long psize = batch->psize; int ssize = batch->ssize; int i; + unsigned int use_local; + + use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && + mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use(); local_irq_save(flags); @@ -671,8 +675,7 @@ static void native_flush_hash_range(unsigned long number, int local) } pte_iterate_hashed_end(); } - if (mmu_has_feature(MMU_FTR_TLBIEL) && - mmu_psize_defs[psize].tlbiel && local) { + if (use_local) { asm volatile("ptesync":::"memory"); for (i = 0; i < number; i++) { vpn = batch->vpn[i]; diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 4c48b487698c..0b48ce40d351 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -179,6 +179,16 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) b slb_finish_load 8: /* invalid EA */ + /* + * It's possible the bad EA is too large to fit in the SLB cache, which + * would mean we'd fail to invalidate it on context switch. So mark the + * SLB cache as full so we force a full flush. We also set cr7+eq to + * mark the address as a kernel address, so slb_finish_load() skips + * trying to insert it into the SLB cache. + */ + li r9,SLB_CACHE_ENTRIES + 1 + sth r9,PACASLBCACHEPTR(r13) + crset 4*cr7+eq li r10,0 /* BAD_VSID */ li r9,0 /* BAD_VSID */ li r11,SLB_VSID_USER /* flags don't much matter */ diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 0f432a702870..6ad12b244770 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -105,7 +105,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr, if ((mm->task_size - len) < addr) return 0; vma = find_vma(mm, addr); - return (!vma || (addr + len) <= vma->vm_start); + return (!vma || (addr + len) <= vm_start_gap(vma)); } static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice) diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index e45b88a5d7e0..ae877c7b3905 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -148,7 +148,7 @@ opal_tracepoint_entry: opal_tracepoint_return: std r3,STK_REG(R31)(r1) mr r4,r3 - ld r0,STK_REG(R23)(r1) + ld r3,STK_REG(R23)(r1) bl __trace_opal_exit ld r3,STK_REG(R31)(r1) addi r1,r1,STACKFRAMESIZE diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index f244dcb4f2cf..96536c969c9c 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -280,7 +280,6 @@ int dlpar_detach_node(struct device_node *dn) if (rc) return rc; - of_node_put(dn); /* Must decrement the refcount */ return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index e9ff44cd5d86..e8b1027e1b5b 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -110,6 +110,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn) for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr); lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index); + lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index); lmbs[i].flags = be32_to_cpu(lmbs[i].flags); } @@ -553,6 +554,7 @@ static void dlpar_update_drconf_property(struct device_node *dn, for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr); lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index); + lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index); lmbs[i].flags = cpu_to_be32(lmbs[i].flags); } diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 7c7fcc042549..fb695f142563 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -82,7 +82,6 @@ static int pSeries_reconfig_remove_node(struct device_node *np) of_detach_node(np); of_node_put(parent); - of_node_put(np); /* Must decrement the refcount */ return 0; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 60530fd93d6d..06176328f83d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -62,6 +62,9 @@ config PCI_QUIRKS config ARCH_SUPPORTS_UPROBES def_bool y +config DEBUG_RODATA + def_bool y + config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 4da604ebf6fd..ca15613eaaa4 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -141,31 +141,34 @@ static void check_ipl_parmblock(void *start, unsigned long size) unsigned long decompress_kernel(void) { - unsigned long output_addr; - unsigned char *output; + void *output, *kernel_end; - output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL; - check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start); - memset(&_bss, 0, &_ebss - &_bss); - free_mem_ptr = (unsigned long)&_end; - free_mem_end_ptr = free_mem_ptr + HEAP_SIZE; - output = (unsigned char *) output_addr; + output = (void *) ALIGN((unsigned long) &_end + HEAP_SIZE, PAGE_SIZE); + kernel_end = output + SZ__bss_start; + check_ipl_parmblock((void *) 0, (unsigned long) kernel_end); #ifdef CONFIG_BLK_DEV_INITRD /* * Move the initrd right behind the end of the decompressed - * kernel image. + * kernel image. This also prevents initrd corruption caused by + * bss clearing since kernel_end will always be located behind the + * current bss section.. */ - if (INITRD_START && INITRD_SIZE && - INITRD_START < (unsigned long) output + SZ__bss_start) { - check_ipl_parmblock(output + SZ__bss_start, - INITRD_START + INITRD_SIZE); - memmove(output + SZ__bss_start, - (void *) INITRD_START, INITRD_SIZE); - INITRD_START = (unsigned long) output + SZ__bss_start; + if (INITRD_START && INITRD_SIZE && kernel_end > (void *) INITRD_START) { + check_ipl_parmblock(kernel_end, INITRD_SIZE); + memmove(kernel_end, (void *) INITRD_START, INITRD_SIZE); + INITRD_START = (unsigned long) kernel_end; } #endif + /* + * Clear bss section. free_mem_ptr and free_mem_end_ptr need to be + * initialized afterwards since they reside in bss. + */ + memset(&_bss, 0, &_ebss - &_bss); + free_mem_ptr = (unsigned long) &_end; + free_mem_end_ptr = free_mem_ptr + HEAP_SIZE; + puts("Uncompressing Linux... "); __decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error); puts("Ok, booting the kernel.\n"); diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index d7697ab802f6..8e136b88cdf4 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -15,7 +15,9 @@ BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\ asm volatile( \ " lctlg %1,%2,%0\n" \ - : : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\ + : \ + : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high) \ + : "memory"); \ } #define __ctl_store(array, low, high) { \ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index bab6739a1154..b9eb7b1a49d2 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -154,14 +154,13 @@ extern unsigned int vdso_enabled; #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 -/* This is the location that an ET_DYN program is loaded if exec'ed. Typical - use of this is to invoke "./ld.so someprog" to test out a new version of - the loader. We need to make sure that it is out of the way of the program - that it will "exec", and that there is sufficient room for the brk. 64-bit - tasks are aligned to 4GB. */ -#define ELF_ET_DYN_BASE (is_32bit_task() ? \ - (STACK_TOP / 3 * 2) : \ - (STACK_TOP / 3 * 2) & ~((1UL << 32) - 1)) +/* + * This is the base location for PIE (ET_DYN with INTERP) loads. On + * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * space open for things that want to use the area for 32-bit pointers. + */ +#define ELF_ET_DYN_BASE (is_compat_task() ? 0x000400000UL : \ + 0x100000000UL) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. */ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 024f85f947ae..e2c0e4eab037 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -829,6 +829,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, { pgste_t pgste; + if (pte_present(entry)) + pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste_val(pgste) &= ~_PGSTE_GPS_ZERO; diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index c1ea67db8404..c61ed7890cef 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -74,7 +74,8 @@ extern void execve_tail(void); * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit. */ -#define TASK_SIZE_OF(tsk) ((tsk)->mm->context.asce_limit) +#define TASK_SIZE_OF(tsk) ((tsk)->mm ? \ + (tsk)->mm->context.asce_limit : TASK_MAX_SIZE) #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 6ba0bf928909..6bc941be6921 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -64,6 +64,12 @@ static inline void syscall_get_arguments(struct task_struct *task, { unsigned long mask = -1UL; + /* + * No arguments for this syscall, there's nothing to do. + */ + if (!n) + return; + BUG_ON(i + n > 6); #ifdef CONFIG_COMPAT if (test_tsk_thread_flag(task, TIF_31BIT)) diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 5c7381c5ad7f..c8d837f0fbbc 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -150,7 +150,7 @@ unsigned long __must_check __copy_to_user(void __user *to, const void *from, " jg 2b\n" \ ".popsection\n" \ EX_TABLE(0b,3b) EX_TABLE(1b,3b) \ - : "=d" (__rc), "=Q" (*(to)) \ + : "=d" (__rc), "+Q" (*(to)) \ : "d" (size), "Q" (*(from)), \ "d" (__reg0), "K" (-EFAULT) \ : "cc"); \ diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 171e09bb8ea2..df4685905015 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -23,6 +23,8 @@ #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) #define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y)))) +#define LINUX_NOTE_NAME "LINUX" + static struct memblock_region oldmem_region; static struct memblock_type oldmem_type = { @@ -312,7 +314,7 @@ static void *nt_fpregset(void *ptr, struct save_area *sa) static void *nt_s390_timer(void *ptr, struct save_area *sa) { return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer), - KEXEC_CORE_NOTE_NAME); + LINUX_NOTE_NAME); } /* @@ -321,7 +323,7 @@ static void *nt_s390_timer(void *ptr, struct save_area *sa) static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa) { return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp, - sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME); + sizeof(sa->clk_cmp), LINUX_NOTE_NAME); } /* @@ -330,7 +332,7 @@ static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa) static void *nt_s390_tod_preg(void *ptr, struct save_area *sa) { return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg, - sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME); + sizeof(sa->tod_reg), LINUX_NOTE_NAME); } /* @@ -339,7 +341,7 @@ static void *nt_s390_tod_preg(void *ptr, struct save_area *sa) static void *nt_s390_ctrs(void *ptr, struct save_area *sa) { return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs, - sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME); + sizeof(sa->ctrl_regs), LINUX_NOTE_NAME); } /* @@ -348,7 +350,7 @@ static void *nt_s390_ctrs(void *ptr, struct save_area *sa) static void *nt_s390_prefix(void *ptr, struct save_area *sa) { return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg, - sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME); + sizeof(sa->pref_reg), LINUX_NOTE_NAME); } /* @@ -357,7 +359,7 @@ static void *nt_s390_prefix(void *ptr, struct save_area *sa) static void *nt_s390_vx_high(void *ptr, __vector128 *vx_regs) { return nt_init(ptr, NT_S390_VXRS_HIGH, &vx_regs[16], - 16 * sizeof(__vector128), KEXEC_CORE_NOTE_NAME); + 16 * sizeof(__vector128), LINUX_NOTE_NAME); } /* @@ -370,12 +372,12 @@ static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs) int i; note = (Elf64_Nhdr *)ptr; - note->n_namesz = strlen(KEXEC_CORE_NOTE_NAME) + 1; + note->n_namesz = strlen(LINUX_NOTE_NAME) + 1; note->n_descsz = 16 * 8; note->n_type = NT_S390_VXRS_LOW; len = sizeof(Elf64_Nhdr); - memcpy(ptr + len, KEXEC_CORE_NOTE_NAME, note->n_namesz); + memcpy(ptr + len, LINUX_NOTE_NAME, note->n_namesz); len = roundup(len + note->n_namesz, 4); ptr += len; @@ -462,6 +464,20 @@ static void *nt_vmcoreinfo(void *ptr) } /* + * Initialize final note (needed for /proc/vmcore code) + */ +static void *nt_final(void *ptr) +{ + Elf64_Nhdr *note; + + note = (Elf64_Nhdr *) ptr; + note->n_namesz = 0; + note->n_descsz = 0; + note->n_type = 0; + return PTR_ADD(ptr, sizeof(Elf64_Nhdr)); +} + +/* * Initialize ELF header (new kernel) */ static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) @@ -551,6 +567,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) ptr = fill_cpu_elf_notes(ptr, &sa_ext->sa, sa_ext->vx_regs); } ptr = nt_vmcoreinfo(ptr); + ptr = nt_final(ptr); memset(phdr, 0, sizeof(*phdr)); phdr->p_type = PT_NOTE; phdr->p_offset = notes_offset; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 424e6809ad07..4612ed7ec2e5 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -229,12 +229,17 @@ ENTRY(sie64a) lctlg %c1,%c1,__LC_USER_ASCE # load primary asce .Lsie_done: # some program checks are suppressing. C code (e.g. do_protection_exception) -# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other -# instructions between sie64a and .Lsie_done should not cause program -# interrupts. So lets use a nop (47 00 00 00) as a landing pad. +# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There +# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable. +# Other instructions between sie64a and .Lsie_done should not cause program +# interrupts. So lets use 3 nops as a landing pad for all possible rewinds. # See also .Lcleanup_sie -.Lrewind_pad: - nop 0 +.Lrewind_pad6: + nopr 7 +.Lrewind_pad4: + nopr 7 +.Lrewind_pad2: + nopr 7 .globl sie_exit sie_exit: lg %r14,__SF_EMPTY+8(%r15) # load guest register save area @@ -247,7 +252,9 @@ sie_exit: stg %r14,__SF_EMPTY+16(%r15) # set exit reason code j sie_exit - EX_TABLE(.Lrewind_pad,.Lsie_fault) + EX_TABLE(.Lrewind_pad6,.Lsie_fault) + EX_TABLE(.Lrewind_pad4,.Lsie_fault) + EX_TABLE(.Lrewind_pad2,.Lsie_fault) EX_TABLE(sie_exit,.Lsie_fault) #endif @@ -308,6 +315,7 @@ ENTRY(system_call) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) +.Lsysc_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) @@ -593,6 +601,7 @@ ENTRY(io_int_handler) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) +.Lio_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) @@ -1118,15 +1127,23 @@ cleanup_critical: br %r14 .Lcleanup_sysc_restore: + # check if stpt has been executed clg %r9,BASED(.Lcleanup_sysc_restore_insn) + jh 0f + mvc __LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER + cghi %r11,__LC_SAVE_AREA_ASYNC je 0f + mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER +0: clg %r9,BASED(.Lcleanup_sysc_restore_insn+8) + je 1f lg %r9,24(%r11) # get saved pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) -0: lmg %r8,%r9,__LC_RETURN_PSW +1: lmg %r8,%r9,__LC_RETURN_PSW br %r14 .Lcleanup_sysc_restore_insn: + .quad .Lsysc_exit_timer .quad .Lsysc_done - 4 .Lcleanup_io_tif: @@ -1134,15 +1151,20 @@ cleanup_critical: br %r14 .Lcleanup_io_restore: + # check if stpt has been executed clg %r9,BASED(.Lcleanup_io_restore_insn) - je 0f + jh 0f + mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER +0: clg %r9,BASED(.Lcleanup_io_restore_insn+8) + je 1f lg %r9,24(%r11) # get saved r11 pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) -0: lmg %r8,%r9,__LC_RETURN_PSW +1: lmg %r8,%r9,__LC_RETURN_PSW br %r14 .Lcleanup_io_restore_insn: + .quad .Lio_exit_timer .quad .Lio_done - 4 .Lcleanup_idle: diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 01c37b36caf9..02bd587b610b 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target, if (target == current) save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp(fprs, target->thread.fpu.vxrs); + else + memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs)); + /* If setting FPC, must validate it first. */ if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { u32 ufpc[2] = { target->thread.fpu.fpc, 0 }; @@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target, if (target == current) save_fpu_regs(); + for (i = 0; i < __NUM_VXRS_LOW; i++) + vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1); + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1); if (rc == 0) for (i = 0; i < __NUM_VXRS_LOW; i++) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 1f581eb61bc2..d097d71685df 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -805,10 +805,10 @@ static void __init setup_randomness(void) { struct sysinfo_3_2_2 *vmms; - vmms = (struct sysinfo_3_2_2 *) alloc_page(GFP_KERNEL); - if (vmms && stsi(vmms, 3, 2, 2) == 0 && vmms->count) - add_device_randomness(&vmms, vmms->count); - free_page((unsigned long) vmms); + vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) + add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); + memblock_free((unsigned long) vmms, PAGE_SIZE); } /* diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 575dc123bda2..23e3f5d77a24 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -295,6 +295,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; int is_dirty = 0; + if (kvm_is_ucontrol(kvm)) + return -EINVAL; + mutex_lock(&kvm->slots_lock); r = -EINVAL; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index feff9caf89b5..91376d9e4286 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -109,6 +109,13 @@ void __init paging_init(void) free_area_init_nodes(max_zone_pfns); } +void mark_rodata_ro(void) +{ + /* Text and rodata are already protected. Nothing to do here. */ + pr_info("Write protecting the kernel read-only data: %luk\n", + ((unsigned long)&_eshared - (unsigned long)&_stext) >> 10); +} + void __init mem_init(void) { if (MACHINE_HAS_TLB_LC) @@ -127,9 +134,6 @@ void __init mem_init(void) setup_zero_pages(); /* Setup zeroed pages. */ mem_init_print_info(NULL); - printk("Write protected kernel read-only data: %#lx - %#lx\n", - (unsigned long)&_stext, - PFN_ALIGN((unsigned long)&_eshared) - 1); } void free_initmem(void) diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index f2b6b1d9c804..126c4a9b9bf9 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -97,7 +97,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -135,7 +135,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 8345ae1f117d..05ae254f84cf 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1237,11 +1237,28 @@ EXPORT_SYMBOL_GPL(s390_reset_cmma); */ bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap) { + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; pte_t *pte; spinlock_t *ptl; bool dirty = false; - pte = get_locked_pte(gmap->mm, address, &ptl); + pgd = pgd_offset(gmap->mm, address); + pud = pud_alloc(gmap->mm, pgd, address); + if (!pud) + return false; + pmd = pmd_alloc(gmap->mm, pud, address); + if (!pmd) + return false; + /* We can't run guests backed by huge pages, but userspace can + * still set them up and then try to migrate them without any + * migration support. + */ + if (pmd_large(*pmd)) + return true; + + pte = pte_alloc_map_lock(gmap->mm, pmd, address, &ptl); if (unlikely(!pte)) return false; diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index ef7d6c8fea66..f354fd84adeb 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -372,7 +372,7 @@ void __init vmem_map_init(void) ro_end = (unsigned long)&_eshared & PAGE_MASK; for_each_memblock(memory, reg) { start = reg->base; - end = reg->base + reg->size - 1; + end = reg->base + reg->size; if (start >= ro_end || end <= ro_start) vmem_add_mem(start, end - start, 0); else if (start >= ro_start && end <= ro_end) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 0e2919dd8df3..1395eeb6005f 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1250,7 +1250,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp) insn_count = bpf_jit_insn(jit, fp, i); if (insn_count < 0) return -1; - jit->addrs[i + 1] = jit->prg; /* Next instruction address */ + /* Next instruction address */ + jit->addrs[i + insn_count] = jit->prg; } bpf_jit_epilogue(jit); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 3a40f718baef..4004e03267cd 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -455,7 +455,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->dma_table = dma_alloc_cpu_table(); if (!zdev->dma_table) { rc = -ENOMEM; - goto out_clean; + goto out; } /* @@ -475,18 +475,22 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); if (!zdev->iommu_bitmap) { rc = -ENOMEM; - goto out_reg; + goto free_dma_table; } rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, (u64) zdev->dma_table); if (rc) - goto out_reg; - return 0; + goto free_bitmap; -out_reg: + return 0; +free_bitmap: + vfree(zdev->iommu_bitmap); + zdev->iommu_bitmap = NULL; +free_dma_table: dma_free_cpu_table(zdev->dma_table); -out_clean: + zdev->dma_table = NULL; +out: return rc; } diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c index 6777177807c2..7df7d5944188 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -63,7 +63,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -113,7 +113,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 3736be630113..894bcaed002e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -183,9 +183,9 @@ config NR_CPUS int "Maximum number of CPUs" depends on SMP range 2 32 if SPARC32 - range 2 1024 if SPARC64 + range 2 4096 if SPARC64 default 32 if SPARC32 - default 64 if SPARC64 + default 4096 if SPARC64 source kernel/Kconfig.hz diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h index f7de0dbc38af..83b36a5371ff 100644 --- a/arch/sparc/include/asm/mmu_64.h +++ b/arch/sparc/include/asm/mmu_64.h @@ -52,7 +52,7 @@ #define CTX_NR_MASK TAG_CONTEXT_BITS #define CTX_HW_MASK (CTX_NR_MASK | CTX_PGSZ_MASK) -#define CTX_FIRST_VERSION ((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL)) +#define CTX_FIRST_VERSION BIT(CTX_VERSION_SHIFT) #define CTX_VALID(__ctx) \ (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK)) #define CTX_HWBITS(__ctx) ((__ctx.sparc64_ctx_val) & CTX_HW_MASK) diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index b84be675e507..0cdeb2b483a0 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -17,22 +17,19 @@ extern spinlock_t ctx_alloc_lock; extern unsigned long tlb_context_cache; extern unsigned long mmu_context_bmap[]; +DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm); void get_new_mmu_context(struct mm_struct *mm); -#ifdef CONFIG_SMP -void smp_new_mmu_context_version(void); -#else -#define smp_new_mmu_context_version() do { } while (0) -#endif - int init_new_context(struct task_struct *tsk, struct mm_struct *mm); void destroy_context(struct mm_struct *mm); void __tsb_context_switch(unsigned long pgd_pa, struct tsb_config *tsb_base, struct tsb_config *tsb_huge, - unsigned long tsb_descr_pa); + unsigned long tsb_descr_pa, + unsigned long secondary_ctx); -static inline void tsb_context_switch(struct mm_struct *mm) +static inline void tsb_context_switch_ctx(struct mm_struct *mm, + unsigned long ctx) { __tsb_context_switch(__pa(mm->pgd), &mm->context.tsb_block[0], @@ -43,9 +40,12 @@ static inline void tsb_context_switch(struct mm_struct *mm) #else NULL #endif - , __pa(&mm->context.tsb_descr[0])); + , __pa(&mm->context.tsb_descr[0]), + ctx); } +#define tsb_context_switch(X) tsb_context_switch_ctx(X, 0) + void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long mm_rss); @@ -74,8 +74,9 @@ void __flush_tlb_mm(unsigned long, unsigned long); static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk) { unsigned long ctx_valid, flags; - int cpu; + int cpu = smp_processor_id(); + per_cpu(per_cpu_secondary_mm, cpu) = mm; if (unlikely(mm == &init_mm)) return; @@ -114,14 +115,12 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str * cpu0 to update it's TSB because at that point the cpu_vm_mask * only had cpu1 set in it. */ - load_secondary_context(mm); - tsb_context_switch(mm); + tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context)); /* Any time a processor runs a context on an address space * for the first time, we must flush that context out of the * local TLB. */ - cpu = smp_processor_id(); if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) { cpumask_set_cpu(cpu, mm_cpumask(mm)); __flush_tlb_mm(CTX_HWBITS(mm->context), @@ -131,26 +130,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str } #define deactivate_mm(tsk,mm) do { } while (0) - -/* Activate a new MM instance for the current task. */ -static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm) -{ - unsigned long flags; - int cpu; - - spin_lock_irqsave(&mm->context.lock, flags); - if (!CTX_VALID(mm->context)) - get_new_mmu_context(mm); - cpu = smp_processor_id(); - if (!cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_set_cpu(cpu, mm_cpumask(mm)); - - load_secondary_context(mm); - __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT); - tsb_context_switch(mm); - spin_unlock_irqrestore(&mm->context.lock, flags); -} - +#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL) #endif /* !(__ASSEMBLY__) */ #endif /* !(__SPARC64_MMU_CONTEXT_H) */ diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index 91b963a887b7..29c3b400f949 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -91,9 +91,9 @@ extern unsigned long pfn_base; * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page)) +#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) /* * In general all page table modifications should use the V8 atomic diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 408b715c95a5..9d81579f3d54 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -668,26 +668,27 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return pte_pfn(pte); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline unsigned long pmd_dirty(pmd_t pmd) +#define __HAVE_ARCH_PMD_WRITE +static inline unsigned long pmd_write(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_dirty(pte); + return pte_write(pte); } -static inline unsigned long pmd_young(pmd_t pmd) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline unsigned long pmd_dirty(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_young(pte); + return pte_dirty(pte); } -static inline unsigned long pmd_write(pmd_t pmd) +static inline unsigned long pmd_young(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_write(pte); + return pte_young(pte); } static inline unsigned long pmd_trans_huge(pmd_t pmd) diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h index 266937030546..522b43db2ed3 100644 --- a/arch/sparc/include/asm/pil.h +++ b/arch/sparc/include/asm/pil.h @@ -20,7 +20,6 @@ #define PIL_SMP_CALL_FUNC 1 #define PIL_SMP_RECEIVE_SIGNAL 2 #define PIL_SMP_CAPTURE 3 -#define PIL_SMP_CTX_NEW_VERSION 4 #define PIL_DEVICE_IRQ 5 #define PIL_SMP_CALL_FUNC_SNGL 6 #define PIL_DEFERRED_PCR_WORK 7 diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 29d64b1758ed..be0cc1beed41 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -16,7 +16,7 @@ extern char reboot_command[]; */ extern unsigned char boot_cpu_id; -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; extern int serial_console; static inline int con_is_present(void) diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h index ec9c04de3664..ff05992dae7a 100644 --- a/arch/sparc/include/asm/trap_block.h +++ b/arch/sparc/include/asm/trap_block.h @@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS]; void init_cur_cpu_trap(struct thread_info *); void setup_tba(void); extern int ncpus_probed; +extern u64 cpu_mondo_counter[NR_CPUS]; unsigned long real_hard_smp_processor_id(void); diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h index 8174f6cdbbbb..9dca7a892978 100644 --- a/arch/sparc/include/asm/vio.h +++ b/arch/sparc/include/asm/vio.h @@ -327,6 +327,7 @@ struct vio_dev { int compat_len; u64 dev_no; + u64 id; unsigned long channel_id; diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e22416ce56ea..bfbde8c4ffb2 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb) { #ifdef CONFIG_SMP unsigned long page; + void *mondo, *p; - BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64)); + BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE); + + /* Make sure mondo block is 64byte aligned */ + p = kzalloc(127, GFP_KERNEL); + if (!p) { + prom_printf("SUN4V: Error, cannot allocate mondo block.\n"); + prom_halt(); + } + mondo = (void *)(((unsigned long)p + 63) & ~0x3f); + tb->cpu_mondo_block_pa = __pa(mondo); page = get_zeroed_page(GFP_KERNEL); if (!page) { - prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n"); + prom_printf("SUN4V: Error, cannot allocate cpu list page.\n"); prom_halt(); } - tb->cpu_mondo_block_pa = __pa(page); - tb->cpu_list_pa = __pa(page + 64); + tb->cpu_list_pa = __pa(page); #endif } diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h index e7f652be9e61..44f32dd4477f 100644 --- a/arch/sparc/kernel/kernel.h +++ b/arch/sparc/kernel/kernel.h @@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr /* smp_64.c */ void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs); void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs); -void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs); void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs); void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs); diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index 9ddc4928a089..c1566170964f 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -311,7 +311,7 @@ static int genregs64_set(struct task_struct *target, } if (!ret) { - unsigned long y; + unsigned long y = regs->y; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &y, diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 19cd08d18672..4511caa3b7e9 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -617,22 +617,48 @@ retry: } } -/* Multi-cpu list version. */ +#define CPU_MONDO_COUNTER(cpuid) (cpu_mondo_counter[cpuid]) +#define MONDO_USEC_WAIT_MIN 2 +#define MONDO_USEC_WAIT_MAX 100 +#define MONDO_RETRY_LIMIT 500000 + +/* Multi-cpu list version. + * + * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'. + * Sometimes not all cpus receive the mondo, requiring us to re-send + * the mondo until all cpus have received, or cpus are truly stuck + * unable to receive mondo, and we timeout. + * Occasionally a target cpu strand is borrowed briefly by hypervisor to + * perform guest service, such as PCIe error handling. Consider the + * service time, 1 second overall wait is reasonable for 1 cpu. + * Here two in-between mondo check wait time are defined: 2 usec for + * single cpu quick turn around and up to 100usec for large cpu count. + * Deliver mondo to large number of cpus could take longer, we adjusts + * the retry count as long as target cpus are making forward progress. + */ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) { - int retries, this_cpu, prev_sent, i, saw_cpu_error; + int this_cpu, tot_cpus, prev_sent, i, rem; + int usec_wait, retries, tot_retries; + u16 first_cpu = 0xffff; + unsigned long xc_rcvd = 0; unsigned long status; + int ecpuerror_id = 0; + int enocpu_id = 0; u16 *cpu_list; + u16 cpu; this_cpu = smp_processor_id(); - cpu_list = __va(tb->cpu_list_pa); - - saw_cpu_error = 0; - retries = 0; + usec_wait = cnt * MONDO_USEC_WAIT_MIN; + if (usec_wait > MONDO_USEC_WAIT_MAX) + usec_wait = MONDO_USEC_WAIT_MAX; + retries = tot_retries = 0; + tot_cpus = cnt; prev_sent = 0; + do { - int forward_progress, n_sent; + int n_sent, mondo_delivered, target_cpu_busy; status = sun4v_cpu_mondo_send(cnt, tb->cpu_list_pa, @@ -640,94 +666,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) /* HV_EOK means all cpus received the xcall, we're done. */ if (likely(status == HV_EOK)) - break; + goto xcall_done; + + /* If not these non-fatal errors, panic */ + if (unlikely((status != HV_EWOULDBLOCK) && + (status != HV_ECPUERROR) && + (status != HV_ENOCPU))) + goto fatal_errors; /* First, see if we made any forward progress. * + * Go through the cpu_list, count the target cpus that have + * received our mondo (n_sent), and those that did not (rem). + * Re-pack cpu_list with the cpus remain to be retried in the + * front - this simplifies tracking the truly stalled cpus. + * * The hypervisor indicates successful sends by setting * cpu list entries to the value 0xffff. + * + * EWOULDBLOCK means some target cpus did not receive the + * mondo and retry usually helps. + * + * ECPUERROR means at least one target cpu is in error state, + * it's usually safe to skip the faulty cpu and retry. + * + * ENOCPU means one of the target cpu doesn't belong to the + * domain, perhaps offlined which is unexpected, but not + * fatal and it's okay to skip the offlined cpu. */ + rem = 0; n_sent = 0; for (i = 0; i < cnt; i++) { - if (likely(cpu_list[i] == 0xffff)) + cpu = cpu_list[i]; + if (likely(cpu == 0xffff)) { n_sent++; + } else if ((status == HV_ECPUERROR) && + (sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) { + ecpuerror_id = cpu + 1; + } else if (status == HV_ENOCPU && !cpu_online(cpu)) { + enocpu_id = cpu + 1; + } else { + cpu_list[rem++] = cpu; + } } - forward_progress = 0; - if (n_sent > prev_sent) - forward_progress = 1; + /* No cpu remained, we're done. */ + if (rem == 0) + break; - prev_sent = n_sent; + /* Otherwise, update the cpu count for retry. */ + cnt = rem; - /* If we get a HV_ECPUERROR, then one or more of the cpus - * in the list are in error state. Use the cpu_state() - * hypervisor call to find out which cpus are in error state. + /* Record the overall number of mondos received by the + * first of the remaining cpus. */ - if (unlikely(status == HV_ECPUERROR)) { - for (i = 0; i < cnt; i++) { - long err; - u16 cpu; + if (first_cpu != cpu_list[0]) { + first_cpu = cpu_list[0]; + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); + } - cpu = cpu_list[i]; - if (cpu == 0xffff) - continue; + /* Was any mondo delivered successfully? */ + mondo_delivered = (n_sent > prev_sent); + prev_sent = n_sent; - err = sun4v_cpu_state(cpu); - if (err == HV_CPU_STATE_ERROR) { - saw_cpu_error = (cpu + 1); - cpu_list[i] = 0xffff; - } - } - } else if (unlikely(status != HV_EWOULDBLOCK)) - goto fatal_mondo_error; + /* or, was any target cpu busy processing other mondos? */ + target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu)); + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); - /* Don't bother rewriting the CPU list, just leave the - * 0xffff and non-0xffff entries in there and the - * hypervisor will do the right thing. - * - * Only advance timeout state if we didn't make any - * forward progress. + /* Retry count is for no progress. If we're making progress, + * reset the retry count. */ - if (unlikely(!forward_progress)) { - if (unlikely(++retries > 10000)) - goto fatal_mondo_timeout; - - /* Delay a little bit to let other cpus catch up - * on their cpu mondo queue work. - */ - udelay(2 * cnt); + if (likely(mondo_delivered || target_cpu_busy)) { + tot_retries += retries; + retries = 0; + } else if (unlikely(retries > MONDO_RETRY_LIMIT)) { + goto fatal_mondo_timeout; } - } while (1); - if (unlikely(saw_cpu_error)) - goto fatal_mondo_cpu_error; + /* Delay a little bit to let other cpus catch up on + * their cpu mondo queue work. + */ + if (!mondo_delivered) + udelay(usec_wait); - return; + retries++; + } while (1); -fatal_mondo_cpu_error: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus " - "(including %d) were in error state\n", - this_cpu, saw_cpu_error - 1); +xcall_done: + if (unlikely(ecpuerror_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n", + this_cpu, ecpuerror_id - 1); + } else if (unlikely(enocpu_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n", + this_cpu, enocpu_id - 1); + } return; +fatal_errors: + /* fatal errors include bad alignment, etc */ + pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n", + this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa); + panic("Unexpected SUN4V mondo error %lu\n", status); + fatal_mondo_timeout: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward " - " progress after %d retries.\n", - this_cpu, retries); - goto dump_cpu_list_and_out; - -fatal_mondo_error: - printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n", - this_cpu, status); - printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) " - "mondo_block_pa(%lx)\n", - this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa); - -dump_cpu_list_and_out: - printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu); - for (i = 0; i < cnt; i++) - printk("%u ", cpu_list[i]); - printk("]\n"); + /* some cpus being non-responsive to the cpu mondo */ + pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n", + this_cpu, first_cpu, (tot_retries + retries), tot_cpus); + panic("SUN4V mondo timeout panic\n"); } static void (*xcall_deliver_impl)(struct trap_per_cpu *, int); @@ -959,37 +1004,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page) preempt_enable(); } -void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) -{ - struct mm_struct *mm; - unsigned long flags; - - clear_softint(1 << irq); - - /* See if we need to allocate a new TLB context because - * the version of the one we are using is now out of date. - */ - mm = current->active_mm; - if (unlikely(!mm || (mm == &init_mm))) - return; - - spin_lock_irqsave(&mm->context.lock, flags); - - if (unlikely(!CTX_VALID(mm->context))) - get_new_mmu_context(mm); - - spin_unlock_irqrestore(&mm->context.lock, flags); - - load_secondary_context(mm); - __flush_tlb_mm(CTX_HWBITS(mm->context), - SECONDARY_CONTEXT); -} - -void smp_new_mmu_context_version(void) -{ - smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0); -} - #ifdef CONFIG_KGDB void kgdb_roundup_cpus(unsigned long flags) { diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S index 559bc5e9c199..34631995859a 100644 --- a/arch/sparc/kernel/sun4v_ivec.S +++ b/arch/sparc/kernel/sun4v_ivec.S @@ -26,6 +26,21 @@ sun4v_cpu_mondo: ldxa [%g0] ASI_SCRATCHPAD, %g4 sub %g4, TRAP_PER_CPU_FAULT_INFO, %g4 + /* Get smp_processor_id() into %g3 */ + sethi %hi(trap_block), %g5 + or %g5, %lo(trap_block), %g5 + sub %g4, %g5, %g3 + srlx %g3, TRAP_BLOCK_SZ_SHIFT, %g3 + + /* Increment cpu_mondo_counter[smp_processor_id()] */ + sethi %hi(cpu_mondo_counter), %g5 + or %g5, %lo(cpu_mondo_counter), %g5 + sllx %g3, 3, %g3 + add %g5, %g3, %g5 + ldx [%g5], %g3 + add %g3, 1, %g3 + stx %g3, [%g5] + /* Get CPU mondo queue base phys address into %g7. */ ldx [%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7 diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index b489e9759518..98a5cf313d39 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -118,7 +118,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -181,7 +181,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index d21cd625c0de..d883c5951e8b 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -85,7 +85,7 @@ static void dump_tl1_traplog(struct tl1_traplog *p) void bad_trap(struct pt_regs *regs, long lvl) { - char buffer[32]; + char buffer[36]; siginfo_t info; if (notify_die(DIE_TRAP, "bad trap", regs, @@ -116,7 +116,7 @@ void bad_trap(struct pt_regs *regs, long lvl) void bad_trap_tl1(struct pt_regs *regs, long lvl) { - char buffer[32]; + char buffer[36]; if (notify_die(DIE_TRAP_TL1, "bad trap tl1", regs, 0, lvl, SIGTRAP) == NOTIFY_STOP) @@ -2659,6 +2659,7 @@ void do_getpsr(struct pt_regs *regs) } } +u64 cpu_mondo_counter[NR_CPUS] = {0}; struct trap_per_cpu trap_block[NR_CPUS]; EXPORT_SYMBOL(trap_block); diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index d568c8207af7..7d961f6e3907 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -375,6 +375,7 @@ tsb_flush: * %o1: TSB base config pointer * %o2: TSB huge config pointer, or NULL if none * %o3: Hypervisor TSB descriptor physical address + * %o4: Secondary context to load, if non-zero * * We have to run this whole thing with interrupts * disabled so that the current cpu doesn't change @@ -387,6 +388,17 @@ __tsb_context_switch: rdpr %pstate, %g1 wrpr %g1, PSTATE_IE, %pstate + brz,pn %o4, 1f + mov SECONDARY_CONTEXT, %o5 + +661: stxa %o4, [%o5] ASI_DMMU + .section .sun4v_1insn_patch, "ax" + .word 661b + stxa %o4, [%o5] ASI_MMU + .previous + flush %g6 + +1: TRAP_LOAD_TRAP_BLOCK(%g2, %g3) stx %o0, [%g2 + TRAP_PER_CPU_PGD_PADDR] @@ -470,13 +482,16 @@ __tsb_context_switch: .type copy_tsb,#function copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size * %o2=new_tsb_base, %o3=new_tsb_size + * %o4=page_size_shift */ sethi %uhi(TSB_PASS_BITS), %g7 srlx %o3, 4, %o3 - add %o0, %o1, %g1 /* end of old tsb */ + add %o0, %o1, %o1 /* end of old tsb */ sllx %g7, 32, %g7 sub %o3, 1, %o3 /* %o3 == new tsb hash mask */ + mov %o4, %g1 /* page_size_shift */ + 661: prefetcha [%o0] ASI_N, #one_read .section .tsb_phys_patch, "ax" .word 661b @@ -501,9 +516,9 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size /* This can definitely be computed faster... */ srlx %o0, 4, %o5 /* Build index */ and %o5, 511, %o5 /* Mask index */ - sllx %o5, PAGE_SHIFT, %o5 /* Put into vaddr position */ + sllx %o5, %g1, %o5 /* Put into vaddr position */ or %o4, %o5, %o4 /* Full VADDR. */ - srlx %o4, PAGE_SHIFT, %o4 /* Shift down to create index */ + srlx %o4, %g1, %o4 /* Shift down to create index */ and %o4, %o3, %o4 /* Mask with new_tsb_nents-1 */ sllx %o4, 4, %o4 /* Shift back up into tsb ent offset */ TSB_STORE(%o2 + %o4, %g2) /* Store TAG */ @@ -511,7 +526,7 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size TSB_STORE(%o2 + %o4, %g3) /* Store TTE */ 80: add %o0, 16, %o0 - cmp %o0, %g1 + cmp %o0, %o1 bne,pt %xcc, 90b nop diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S index c6dfdaa29e20..170ead662f2a 100644 --- a/arch/sparc/kernel/ttable_64.S +++ b/arch/sparc/kernel/ttable_64.S @@ -50,7 +50,7 @@ tl0_resv03e: BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40) tl0_irq1: TRAP_IRQ(smp_call_function_client, 1) tl0_irq2: TRAP_IRQ(smp_receive_signal_client, 2) tl0_irq3: TRAP_IRQ(smp_penguin_jailcell, 3) -tl0_irq4: TRAP_IRQ(smp_new_mmu_context_version_client, 4) +tl0_irq4: BTRAP(0x44) #else tl0_irq1: BTRAP(0x41) tl0_irq2: BTRAP(0x42) diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index cb5789c9f961..34824ca396f0 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -284,13 +284,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, if (!id) { dev_set_name(&vdev->dev, "%s", bus_id_name); vdev->dev_no = ~(u64)0; + vdev->id = ~(u64)0; } else if (!cfg_handle) { dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id); vdev->dev_no = *id; + vdev->id = ~(u64)0; } else { dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name, *cfg_handle, *id); vdev->dev_no = *cfg_handle; + vdev->id = *id; } vdev->dev.parent = parent; @@ -333,27 +336,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node) (void) vio_create_one(hp, node, &root_vdev->dev); } +struct vio_md_node_query { + const char *type; + u64 dev_no; + u64 id; +}; + static int vio_md_node_match(struct device *dev, void *arg) { + struct vio_md_node_query *query = (struct vio_md_node_query *) arg; struct vio_dev *vdev = to_vio_dev(dev); - if (vdev->mp == (u64) arg) - return 1; + if (vdev->dev_no != query->dev_no) + return 0; + if (vdev->id != query->id) + return 0; + if (strcmp(vdev->type, query->type)) + return 0; - return 0; + return 1; } static void vio_remove(struct mdesc_handle *hp, u64 node) { + const char *type; + const u64 *id, *cfg_handle; + u64 a; + struct vio_md_node_query query; struct device *dev; - dev = device_find_child(&root_vdev->dev, (void *) node, + type = mdesc_get_property(hp, node, "device-type", NULL); + if (!type) { + type = mdesc_get_property(hp, node, "name", NULL); + if (!type) + type = mdesc_node_name(hp, node); + } + + query.type = type; + + id = mdesc_get_property(hp, node, "id", NULL); + cfg_handle = NULL; + mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) { + u64 target; + + target = mdesc_arc_target(hp, a); + cfg_handle = mdesc_get_property(hp, target, + "cfg-handle", NULL); + if (cfg_handle) + break; + } + + if (!id) { + query.dev_no = ~(u64)0; + query.id = ~(u64)0; + } else if (!cfg_handle) { + query.dev_no = *id; + query.id = ~(u64)0; + } else { + query.dev_no = *cfg_handle; + query.id = *id; + } + + dev = device_find_child(&root_vdev->dev, &query, vio_md_node_match); if (dev) { printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev)); device_unregister(dev); put_device(dev); + } else { + if (!id) + printk(KERN_ERR "VIO: Removed unknown %s node.\n", + type); + else if (!cfg_handle) + printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n", + type, *id); + else + printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n", + type, *cfg_handle, *id); } } diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index da1142401bf4..ffa842b4d7d4 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -115,7 +115,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, HPAGE_SIZE); vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index eb8287155279..3b7092d9ea8f 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -301,7 +301,7 @@ void __init mem_init(void) /* Saves us work later. */ - memset((void *)&empty_zero_page, 0, PAGE_SIZE); + memset((void *)empty_zero_page, 0, PAGE_SIZE); i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5); i += 1; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 3d3414c14792..384aba109d7c 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -656,10 +656,58 @@ EXPORT_SYMBOL(__flush_dcache_range); /* get_new_mmu_context() uses "cache + 1". */ DEFINE_SPINLOCK(ctx_alloc_lock); -unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1; +unsigned long tlb_context_cache = CTX_FIRST_VERSION; #define MAX_CTX_NR (1UL << CTX_NR_BITS) #define CTX_BMAP_SLOTS BITS_TO_LONGS(MAX_CTX_NR) DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR); +DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0}; + +static void mmu_context_wrap(void) +{ + unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK; + unsigned long new_ver, new_ctx, old_ctx; + struct mm_struct *mm; + int cpu; + + bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS); + + /* Reserve kernel context */ + set_bit(0, mmu_context_bmap); + + new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION; + if (unlikely(new_ver == 0)) + new_ver = CTX_FIRST_VERSION; + tlb_context_cache = new_ver; + + /* + * Make sure that any new mm that are added into per_cpu_secondary_mm, + * are going to go through get_new_mmu_context() path. + */ + mb(); + + /* + * Updated versions to current on those CPUs that had valid secondary + * contexts + */ + for_each_online_cpu(cpu) { + /* + * If a new mm is stored after we took this mm from the array, + * it will go into get_new_mmu_context() path, because we + * already bumped the version in tlb_context_cache. + */ + mm = per_cpu(per_cpu_secondary_mm, cpu); + + if (unlikely(!mm || mm == &init_mm)) + continue; + + old_ctx = mm->context.sparc64_ctx_val; + if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) { + new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver; + set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap); + mm->context.sparc64_ctx_val = new_ctx; + } + } +} /* Caller does TLB context flushing on local CPU if necessary. * The caller also ensures that CTX_VALID(mm->context) is false. @@ -675,48 +723,30 @@ void get_new_mmu_context(struct mm_struct *mm) { unsigned long ctx, new_ctx; unsigned long orig_pgsz_bits; - int new_version; spin_lock(&ctx_alloc_lock); +retry: + /* wrap might have happened, test again if our context became valid */ + if (unlikely(CTX_VALID(mm->context))) + goto out; orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK); ctx = (tlb_context_cache + 1) & CTX_NR_MASK; new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx); - new_version = 0; if (new_ctx >= (1 << CTX_NR_BITS)) { new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1); if (new_ctx >= ctx) { - int i; - new_ctx = (tlb_context_cache & CTX_VERSION_MASK) + - CTX_FIRST_VERSION; - if (new_ctx == 1) - new_ctx = CTX_FIRST_VERSION; - - /* Don't call memset, for 16 entries that's just - * plain silly... - */ - mmu_context_bmap[0] = 3; - mmu_context_bmap[1] = 0; - mmu_context_bmap[2] = 0; - mmu_context_bmap[3] = 0; - for (i = 4; i < CTX_BMAP_SLOTS; i += 4) { - mmu_context_bmap[i + 0] = 0; - mmu_context_bmap[i + 1] = 0; - mmu_context_bmap[i + 2] = 0; - mmu_context_bmap[i + 3] = 0; - } - new_version = 1; - goto out; + mmu_context_wrap(); + goto retry; } } + if (mm->context.sparc64_ctx_val) + cpumask_clear(mm_cpumask(mm)); mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63)); new_ctx |= (tlb_context_cache & CTX_VERSION_MASK); -out: tlb_context_cache = new_ctx; mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits; +out: spin_unlock(&ctx_alloc_lock); - - if (unlikely(new_version)) - smp_new_mmu_context_version(); } static int numa_enabled = 1; @@ -1493,7 +1523,7 @@ bool kern_addr_valid(unsigned long addr) if ((long)addr < 0L) { unsigned long pa = __pa(addr); - if ((addr >> max_phys_bits) != 0UL) + if ((pa >> max_phys_bits) != 0UL) return false; return pfn_valid(pa >> PAGE_SHIFT); diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 9cdeca0fa955..266411291634 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -451,7 +451,8 @@ retry_tsb_alloc: extern void copy_tsb(unsigned long old_tsb_base, unsigned long old_tsb_size, unsigned long new_tsb_base, - unsigned long new_tsb_size); + unsigned long new_tsb_size, + unsigned long page_size_shift); unsigned long old_tsb_base = (unsigned long) old_tsb; unsigned long new_tsb_base = (unsigned long) new_tsb; @@ -459,7 +460,9 @@ retry_tsb_alloc: old_tsb_base = __pa(old_tsb_base); new_tsb_base = __pa(new_tsb_base); } - copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size); + copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size, + tsb_index == MM_TSB_BASE ? + PAGE_SHIFT : REAL_HPAGE_SHIFT); } mm->context.tsb_block[tsb_index].tsb = new_tsb; diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index 5d2fd6cd3189..fcf4d27a38fb 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -971,11 +971,6 @@ xcall_capture: wr %g0, (1 << PIL_SMP_CAPTURE), %set_softint retry - .globl xcall_new_mmu_context_version -xcall_new_mmu_context_version: - wr %g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint - retry - #ifdef CONFIG_KGDB .globl xcall_kgdb_capture xcall_kgdb_capture: diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c index 17bd2e167e07..df707a8ad311 100644 --- a/arch/sparc/power/hibernate.c +++ b/arch/sparc/power/hibernate.c @@ -35,6 +35,5 @@ void restore_processor_state(void) { struct mm_struct *mm = current->active_mm; - load_secondary_context(mm); - tsb_context_switch(mm); + tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context)); } diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c index bdc126faf741..6239aa155f6d 100644 --- a/arch/tile/kernel/ptrace.c +++ b/arch/tile/kernel/ptrace.c @@ -111,7 +111,7 @@ static int tile_gpr_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { int ret; - struct pt_regs regs; + struct pt_regs regs = *task_pt_regs(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0, sizeof(regs)); diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index c034dc3fe2d4..c97ee6c7f949 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -232,7 +232,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (current->mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 9011a88353de..ed1e9206f830 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -16,7 +16,7 @@ #ifndef BOOT_BOOT_H #define BOOT_BOOT_H -#define STACK_SIZE 512 /* Minimum number of bytes for stack */ +#define STACK_SIZE 1024 /* Minimum number of bytes for stack */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 318b8465d302..06ceddb3a22e 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include "ctype.h" +#include "string.h" int memcmp(const void *s1, const void *s2, size_t len) { diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 725e820602b1..113588ddb43f 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -18,4 +18,13 @@ int memcmp(const void *s1, const void *s2, size_t len); #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp +extern int strcmp(const char *str1, const char *str2); +extern int strncmp(const char *cs, const char *ct, size_t count); +extern size_t strlen(const char *s); +extern char *strstr(const char *s1, const char *s2); +extern size_t strnlen(const char *s, size_t maxlen); +extern unsigned int atou(const char *s); +extern unsigned long long simple_strtoull(const char *cp, char **endp, + unsigned int base); + #endif /* BOOT_STRING_H */ diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 440df0c7a2ee..a69321a77783 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -219,6 +219,29 @@ static int ghash_async_final(struct ahash_request *req) } } +static int ghash_async_import(struct ahash_request *req, const void *in) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + ghash_async_init(req); + memcpy(dctx, in, sizeof(*dctx)); + return 0; + +} + +static int ghash_async_export(struct ahash_request *req, void *out) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + memcpy(out, dctx, sizeof(*dctx)); + return 0; + +} + static int ghash_async_digest(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); @@ -288,8 +311,11 @@ static struct ahash_alg ghash_async_alg = { .final = ghash_async_final, .setkey = ghash_async_setkey, .digest = ghash_async_digest, + .export = ghash_async_export, + .import = ghash_async_import, .halg = { .digestsize = GHASH_DIGEST_SIZE, + .statesize = sizeof(struct ghash_desc_ctx), .base = { .cra_name = "ghash", .cra_driver_name = "ghash-clmulni", diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 1cd792db15ef..1eab79c9ac48 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -117,11 +117,10 @@ .set T1, REG_T1 .endm -#define K_BASE %r8 #define HASH_PTR %r9 +#define BLOCKS_CTR %r8 #define BUFFER_PTR %r10 #define BUFFER_PTR2 %r13 -#define BUFFER_END %r11 #define PRECALC_BUF %r14 #define WK_BUF %r15 @@ -205,14 +204,14 @@ * blended AVX2 and ALU instruction scheduling * 1 vector iteration per 8 rounds */ - vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP + vmovdqu (i * 2)(BUFFER_PTR), W_TMP .elseif ((i & 7) == 1) - vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\ + vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\ WY_TMP, WY_TMP .elseif ((i & 7) == 2) vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY .elseif ((i & 7) == 4) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP .elseif ((i & 7) == 7) vmovdqu WY_TMP, PRECALC_WK(i&~7) @@ -255,7 +254,7 @@ vpxor WY, WY_TMP, WY_TMP .elseif ((i & 7) == 7) vpxor WY_TMP2, WY_TMP, WY - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -291,7 +290,7 @@ vpsrld $30, WY, WY vpor WY, WY_TMP, WY .elseif ((i & 7) == 7) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -446,6 +445,16 @@ .endm +/* Add constant only if (%2 > %3) condition met (uses RTA as temp) + * %1 + %2 >= %3 ? %4 : 0 + */ +.macro ADD_IF_GE a, b, c, d + mov \a, RTA + add $\d, RTA + cmp $\c, \b + cmovge RTA, \a +.endm + /* * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining */ @@ -463,13 +472,16 @@ lea (2*4*80+32)(%rsp), WK_BUF # Precalc WK for first 2 blocks - PRECALC_OFFSET = 0 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64 .set i, 0 .rept 160 PRECALC i .set i, i + 1 .endr - PRECALC_OFFSET = 128 + + /* Go to next block if needed */ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 xchg WK_BUF, PRECALC_BUF .align 32 @@ -479,8 +491,8 @@ _loop: * we use K_BASE value as a signal of a last block, * it is set below by: cmovae BUFFER_PTR, K_BASE */ - cmp K_BASE, BUFFER_PTR - jne _begin + test BLOCKS_CTR, BLOCKS_CTR + jnz _begin .align 32 jmp _end .align 32 @@ -512,10 +524,10 @@ _loop0: .set j, j+2 .endr - add $(2*64), BUFFER_PTR /* move to next odd-64-byte block */ - cmp BUFFER_END, BUFFER_PTR /* is current block the last one? */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ - + /* Update Counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128 /* * rounds * 60,62,64,66,68 @@ -532,8 +544,8 @@ _loop0: UPDATE_HASH 12(HASH_PTR), D UPDATE_HASH 16(HASH_PTR), E - cmp K_BASE, BUFFER_PTR /* is current block the last one? */ - je _loop + test BLOCKS_CTR, BLOCKS_CTR + jz _loop mov TB, B @@ -575,10 +587,10 @@ _loop2: .set j, j+2 .endr - add $(2*64), BUFFER_PTR2 /* move to next even-64-byte block */ - - cmp BUFFER_END, BUFFER_PTR2 /* is current block the last one */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ + /* update counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 jmp _loop3 _loop3: @@ -641,19 +653,12 @@ _loop3: avx2_zeroupper - lea K_XMM_AR(%rip), K_BASE - + /* Setup initial values */ mov CTX, HASH_PTR mov BUF, BUFFER_PTR - lea 64(BUF), BUFFER_PTR2 - - shl $6, CNT /* mul by 64 */ - add BUF, CNT - add $64, CNT - mov CNT, BUFFER_END - cmp BUFFER_END, BUFFER_PTR2 - cmovae K_BASE, BUFFER_PTR2 + mov BUF, BUFFER_PTR2 + mov CNT, BLOCKS_CTR xmm_mov BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a55697d19824..cc0f2f5da19b 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1190,6 +1190,8 @@ ENTRY(nmi) * other IST entries. */ + ASM_CLAC + /* Use %rdx as our temp variable throughout */ pushq %rdx diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 265c0ed68118..7af017a8958f 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -187,10 +187,10 @@ vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) $(MODLIB)/vdso: FORCE @mkdir -p $(MODLIB)/vdso -$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE +$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso $(call cmd,vdso_install) PHONY += vdso_install $(vdso_img_insttargets) -vdso_install: $(vdso_img_insttargets) FORCE +vdso_install: $(vdso_img_insttargets) clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 08a317a9ae4b..a7508d7e20b7 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -31,8 +31,10 @@ static int __init vdso32_setup(char *s) { vdso32_enabled = simple_strtoul(s, NULL, 0); - if (vdso32_enabled > 1) + if (vdso32_enabled > 1) { pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n"); + vdso32_enabled = 0; + } return 1; } @@ -63,13 +65,18 @@ subsys_initcall(sysenter_setup); /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> +static const int zero; +static const int one = 1; + static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", .data = &vdso32_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = (int *)&zero, + .extra2 = (int *)&one, }, {} }; diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1514753fd435..bcd3d6199464 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -245,12 +245,13 @@ extern int force_personality32; #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 -/* This is the location that an ET_DYN program is loaded if exec'ed. Typical - use of this is to invoke "./ld.so someprog" to test out a new version of - the loader. We need to make sure that it is out of the way of the program - that it will "exec", and that there is sufficient room for the brk. */ - -#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) +/* + * This is the base location for PIE (ET_DYN with INTERP) loads. On + * 64-bit, this is above 4GB to leave the entire 32-bit address + * space open for things that want to use the area for 32-bit pointers. + */ +#define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ + (TASK_SIZE / 3 * 2)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, @@ -278,7 +279,7 @@ struct task_struct; #define ARCH_DLINFO_IA32 \ do { \ - if (vdso32_enabled) { \ + if (VDSO_CURRENT_BASE) { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index e9cd7befcb76..19d14ac23ef9 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -221,6 +221,9 @@ struct x86_emulate_ops { void (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); + + unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); + void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -290,7 +293,6 @@ struct x86_emulate_ctxt { /* interruptibility state, as a result of execution of STI or MOV SS */ int interruptibility; - int emul_flags; bool perm_ok; /* do not check permissions if true */ bool ud; /* inject an #UD if host doesn't support insn */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 690b4027e17c..37db36fddc88 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -405,6 +405,8 @@ #define MSR_IA32_TSC_ADJUST 0x0000003b #define MSR_IA32_BNDCFGS 0x00000d90 +#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc + #define MSR_IA32_XSS 0x00000da0 #define FEATURE_CONTROL_LOCKED (1<<0) diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 0b1ff4c1c14e..fffb2794dd89 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -7,6 +7,7 @@ bool pat_enabled(void); void pat_disable(const char *reason); extern void pat_init(void); +extern void init_cache_modes(void); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index d8ce3ec816ab..6503526d7b24 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -72,8 +72,8 @@ static inline void arch_wmb_pmem(void) * @size: number of bytes to write back * * Write back a cache range using the CLWB (cache line write back) - * instruction. This function requires explicit ordering with an - * arch_wmb_pmem() call. This API is internal to the x86 PMEM implementation. + * instruction. Note that @size is internally rounded up to be cache + * line size aligned. */ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size) { @@ -87,15 +87,6 @@ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size) clwb(p); } -/* - * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec - * iterators, so for other types (bvec & kvec) we must do a cache write-back. - */ -static inline bool __iter_needs_pmem_wb(struct iov_iter *i) -{ - return iter_is_iovec(i) == false; -} - /** * arch_copy_from_iter_pmem - copy data from an iterator to PMEM * @addr: PMEM destination address @@ -114,8 +105,36 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, /* TODO: skip the write-back by always using non-temporal stores */ len = copy_from_iter_nocache(vaddr, bytes, i); - if (__iter_needs_pmem_wb(i)) - __arch_wb_cache_pmem(vaddr, bytes); + /* + * In the iovec case on x86_64 copy_from_iter_nocache() uses + * non-temporal stores for the bulk of the transfer, but we need + * to manually flush if the transfer is unaligned. A cached + * memory copy is used when destination or size is not naturally + * aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. + * + * In the non-iovec case the entire destination needs to be + * flushed. + */ + if (iter_is_iovec(i)) { + unsigned long flushed, dest = (unsigned long) addr; + + if (bytes < 8) { + if (!IS_ALIGNED(dest, 4) || (bytes != 4)) + __arch_wb_cache_pmem(addr, bytes); + } else { + if (!IS_ALIGNED(dest, 8)) { + dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); + __arch_wb_cache_pmem(addr, 1); + } + + flushed = dest - (unsigned long) addr; + if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8)) + __arch_wb_cache_pmem(addr + bytes - 1, 1); + } + } else + __arch_wb_cache_pmem(addr, bytes); return len; } diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 4c20dd333412..85133b2b8e99 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -43,6 +43,7 @@ #include <asm/page.h> #include <asm/pgtable.h> +#include <asm/smap.h> #include <xen/interface/xen.h> #include <xen/interface/sched.h> @@ -213,10 +214,12 @@ privcmd_call(unsigned call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); + stac(); asm volatile("call *%[call]" : __HYPERCALL_5PARAM : [call] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); + clac(); return (long)__res; } diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e75907601a41..1e5eb9f2ff5f 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -329,6 +329,14 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, struct mpc_intsrc mp_irq; /* + * Check bus_irq boundary. + */ + if (bus_irq >= NR_IRQS_LEGACY) { + pr_warn("Invalid bus_irq %u for legacy override\n", bus_irq); + return; + } + + /* * Convert 'gsi' to 'ioapic.pin'. */ ioapic = mp_find_ioapic(gsi); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index aaacbd667212..fc91c98bee01 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2115,8 +2115,9 @@ static inline void __init check_timer(void) int idx; idx = find_irq_entry(apic1, pin1, mp_INT); if (idx != -1 && irq_trigger(idx)) - unmask_ioapic_irq(irq_get_chip_data(0)); + unmask_ioapic_irq(irq_get_irq_data(0)); } + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) @@ -2138,6 +2139,7 @@ static inline void __init check_timer(void) * legacy devices should be connected to IO APIC #0 */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index e99b15077e94..2116176c1721 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -53,7 +53,7 @@ static const char * const th_names[] = { "load_store", "insn_fetch", "combined_unit", - "", + "decode_unit", "northbridge", "execution_unit", }; @@ -682,6 +682,9 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) const char *name = th_names[bank]; int err = 0; + if (!dev) + return -ENODEV; + if (is_shared_bank(bank)) { nb = node_to_amd_nb(amd_get_nb_id(cpu)); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index cfc4a966e2b9..83b5f7a323a9 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -30,6 +30,7 @@ #include <asm/apic.h> #include <asm/timer.h> #include <asm/reboot.h> +#include <asm/nmi.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -157,6 +158,26 @@ static unsigned char hv_get_nmi_reason(void) return 0; } +#ifdef CONFIG_X86_LOCAL_APIC +/* + * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes + * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle + * unknown NMI on the first CPU which gets it. + */ +static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) +{ + static atomic_t nmi_cpu = ATOMIC_INIT(-1); + + if (!unknown_nmi_panic) + return NMI_DONE; + + if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1) + return NMI_HANDLED; + + return NMI_DONE; +} +#endif + static void __init ms_hyperv_init_platform(void) { /* @@ -182,6 +203,9 @@ static void __init ms_hyperv_init_platform(void) printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n", lapic_timer_frequency); } + + register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST, + "hv_nmi_unknown"); #endif if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1a8256dd6729..5b2f2306fbcc 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1996,8 +1996,8 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - if (current->mm) - load_mm_cr4(current->mm); + if (current->active_mm) + load_mm_cr4(current->active_mm); } static void x86_pmu_event_mapped(struct perf_event *event) diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 659f01e165d5..2cdae69d7e0b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -153,7 +153,7 @@ static void __intel_pmu_lbr_enable(bool pmi) */ if (cpuc->lbr_sel) lbr_select = cpuc->lbr_sel->config; - if (!pmi) + if (!pmi && cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, lbr_select); rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); @@ -410,6 +410,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].to = msr_lastbranch.to; cpuc->lbr_entries[i].mispred = 0; cpuc->lbr_entries[i].predicted = 0; + cpuc->lbr_entries[i].in_tx = 0; + cpuc->lbr_entries[i].abort = 0; + cpuc->lbr_entries[i].cycles = 0; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; @@ -429,8 +432,10 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) int out = 0; int num = x86_pmu.lbr_nr; - if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + if (cpuc->lbr_sel) { + if (cpuc->lbr_sel->config & LBR_CALL_STACK) + num = tos; + } for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index be39b5fde4b9..1011c05b1bd5 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -96,6 +96,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) * Boot time FPU feature detection code: */ unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +EXPORT_SYMBOL_GPL(mxcsr_feature_mask); static void __init fpu__init_system_mxcsr(void) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index eb6bd34582c6..1b96bfe09d42 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -977,6 +977,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long return_hooker = (unsigned long) &return_to_handler; + /* + * When resuming from suspend-to-ram, this function can be indirectly + * called from early CPU startup code while the CPU is in real mode, + * which would fail miserably. Make sure the stack pointer is a + * virtual address. + * + * This check isn't as accurate as virt_addr_valid(), but it should be + * good enough for this purpose, and it's fast. + */ + if (unlikely((long)__builtin_frame_address(0) >= 0)) + return; + if (unlikely(ftrace_graph_is_dead())) return; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f129a9af6357..b6b0077da1af 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -4,6 +4,7 @@ * Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE */ +#define DISABLE_BRANCH_PROFILING #include <linux/init.h> #include <linux/linkage.h> #include <linux/types.h> diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index b8e6ff5cd5d0..acc9b8f19ca8 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -351,6 +351,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index c6ee63f927ab..d688826e5736 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -67,7 +67,7 @@ #endif /* Ensure if the instruction can be boostable */ -extern int can_boost(kprobe_opcode_t *instruction); +extern int can_boost(kprobe_opcode_t *instruction, void *addr); /* Recover instruction if given address is probed */ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 023c442c33bb..99d293ea2b49 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -163,12 +163,12 @@ NOKPROBE_SYMBOL(skip_prefixes); * Returns non-zero if opcode is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int can_boost(kprobe_opcode_t *opcodes) +int can_boost(kprobe_opcode_t *opcodes, void *addr) { kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; - if (search_exception_tables((unsigned long)opcodes)) + if (search_exception_tables((unsigned long)addr)) return 0; /* Page fault may occur on this address. */ retry: @@ -413,7 +413,7 @@ static int arch_copy_kprobe(struct kprobe *p) * __copy_instruction can modify the displacement of the instruction, * but it doesn't affect boostable check. */ - if (can_boost(p->ainsn.insn)) + if (can_boost(p->ainsn.insn, p->addr)) p->ainsn.boostable = 0; else p->ainsn.boostable = -1; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 7b3b9d15c47a..c9d488f3e4cd 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -177,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src) while (len < RELATIVEJUMP_SIZE) { ret = __copy_instruction(dest + len, src + len); - if (!ret || !can_boost(dest + len)) + if (!ret || !can_boost(dest + len, src + len)) return -EINVAL; len += ret; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 47190bd399e7..32187f8a49b4 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token) if (hlist_unhashed(&n.link)) break; + rcu_irq_exit(); + if (!n.halted) { local_irq_enable(); schedule(); @@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token) /* * We cannot reschedule. So halt. */ - rcu_irq_exit(); native_safe_halt(); - rcu_irq_enter(); local_irq_disable(); } + + rcu_irq_enter(); } if (!n.halted) finish_wait(&n.wq, &wait); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 0497f719977d..c055e9a4e547 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, /* were we called with bad_dma_address? */ badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE); - if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) { + if (unlikely(dma_addr < badend)) { WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); return; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d2bbe343fda7..e67b834279b2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1048,6 +1048,13 @@ void __init setup_arch(char **cmdline_p) if (mtrr_trim_uncached_memory(max_pfn)) max_pfn = e820_end_of_ram_pfn(); + /* + * This call is required when the CPU does not support PAT. If + * mtrr_bp_init() invoked it already via pat_init() the call has no + * effect. + */ + init_cache_modes(); + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 10e0272d789a..136ad7c1ce7b 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -143,7 +143,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (end - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -186,7 +186,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2e1fd586b895..83d6369c45f5 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -46,11 +46,18 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } +bool kvm_mpx_supported(void) +{ + return ((host_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) + && kvm_x86_ops->mpx_supported()); +} +EXPORT_SYMBOL_GPL(kvm_mpx_supported); + u64 kvm_supported_xcr0(void) { u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0; - if (!kvm_x86_ops->mpx_supported()) + if (!kvm_mpx_supported()) xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); return xcr0; @@ -97,7 +104,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu); + vcpu->arch.eager_fpu = use_eager_fpu(); if (vcpu->arch.eager_fpu) kvm_x86_ops->fpu_activate(vcpu); @@ -295,7 +302,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, #endif unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; - unsigned f_mpx = kvm_x86_ops->mpx_supported() ? F(MPX) : 0; + unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0; unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0; /* cpuid 1.edx */ @@ -737,18 +744,20 @@ out: static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) { struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - int j, nent = vcpu->arch.cpuid_nent; + struct kvm_cpuid_entry2 *ej; + int j = i; + int nent = vcpu->arch.cpuid_nent; e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; ; j = (j + 1) % nent) { - struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; - if (ej->function == e->function) { - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - return j; - } - } - return 0; /* silence gcc, even though control never reaches here */ + do { + j = (j + 1) % nent; + ej = &vcpu->arch.cpuid_entries[j]; + } while (ej->function != e->function); + + ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + + return j; } /* find an entry with matching function, matching index (if needed), and that @@ -818,12 +827,6 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) if (!best) best = check_cpuid_limit(vcpu, function, index); - /* - * Perfmon not yet supported for L2 guest. - */ - if (is_guest_mode(vcpu) && function == 0xa) - best = NULL; - if (best) { *eax = best->eax; *ebx = best->ebx; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 3f5c48ddba45..d1534feefcfe 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -4,6 +4,7 @@ #include "x86.h" int kvm_update_cpuid(struct kvm_vcpu *vcpu); +bool kvm_mpx_supported(void); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, @@ -134,20 +135,20 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_RTM)); } -static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) +static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->ebx & bit(X86_FEATURE_MPX)); + return best && (best->ebx & bit(X86_FEATURE_PCOMMIT)); } -static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu) +static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->ebx & bit(X86_FEATURE_PCOMMIT)); + return best && (best->ebx & bit(X86_FEATURE_MPX)); } static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1dcea225977d..04b2f3cad7ba 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2531,7 +2531,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) u64 smbase; int ret; - if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0) + if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) return emulate_ud(ctxt); /* @@ -2580,11 +2580,11 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) return X86EMUL_UNHANDLEABLE; } - if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) + if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) ctxt->ops->set_nmi_mask(ctxt, false); - ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK; - ctxt->emul_flags &= ~X86EMUL_SMM_MASK; + ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & + ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); return X86EMUL_CONTINUE; } @@ -5296,6 +5296,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) const struct x86_emulate_ops *ops = ctxt->ops; int rc = X86EMUL_CONTINUE; int saved_dst_type = ctxt->dst.type; + unsigned emul_flags; ctxt->mem_read.pos = 0; @@ -5310,6 +5311,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } + emul_flags = ctxt->ops->get_hflags(ctxt); if (unlikely(ctxt->d & (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) { if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) || @@ -5343,7 +5345,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) fetch_possible_mmx_operand(ctxt, &ctxt->dst); } - if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { + if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5372,7 +5374,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5426,7 +5428,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: - if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8eb8a934b531..1049c3c9b877 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3433,12 +3433,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } -static bool can_do_async_pf(struct kvm_vcpu *vcpu) +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu))) return false; + if (is_guest_mode(vcpu)) + return false; + return kvm_x86_ops->interrupt_allowed(vcpu); } @@ -3454,7 +3457,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, if (!async) return false; /* *pfn has correct page already */ - if (!prefault && can_do_async_pf(vcpu)) { + if (!prefault && kvm_can_do_async_pf(vcpu)) { trace_kvm_try_async_get_page(gva, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { trace_kvm_async_pf_doublefault(gva, gfn); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 55ffb7b0f95e..e60fc80f8a9c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -74,6 +74,7 @@ enum { int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index ab38af4f4947..23a7c7ba377a 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) ((u64)1 << edx.split.bit_width_fixed) - 1; } - pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) | (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); pmu->global_ctrl_mask = ~pmu->global_ctrl; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bb620df05d0d..b12391119ce8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -863,7 +863,6 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); static u64 construct_eptp(unsigned long root_hpa); static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); -static bool vmx_mpx_supported(void); static bool vmx_xsaves_supported(void); static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); @@ -2264,7 +2263,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) if (!(vmcs12->exception_bitmap & (1u << nr))) return 0; - nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, vmcs_read32(VM_EXIT_INTR_INFO), vmcs_readl(EXIT_QUALIFICATION)); return 1; @@ -2541,7 +2540,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; - if (vmx_mpx_supported()) + if (kvm_mpx_supported()) vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; /* We support free control of debug control saving. */ @@ -2562,7 +2561,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) VM_ENTRY_LOAD_IA32_PAT; vmx->nested.nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); - if (vmx_mpx_supported()) + if (kvm_mpx_supported()) vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; /* We support free control of debug control loading. */ @@ -2813,7 +2812,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: - if (!vmx_mpx_supported()) + if (!kvm_mpx_supported() || + (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -2890,7 +2890,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_BNDCFGS: - if (!vmx_mpx_supported()) + if (!kvm_mpx_supported() || + (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu))) + return 1; + if (is_noncanonical_address(data & PAGE_MASK) || + (data & MSR_IA32_BNDCFGS_RSVD)) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; @@ -3363,7 +3367,7 @@ static void init_vmcs_shadow_fields(void) for (i = j = 0; i < max_shadow_read_write_fields; i++) { switch (shadow_read_write_fields[i]) { case GUEST_BNDCFGS: - if (!vmx_mpx_supported()) + if (!kvm_mpx_supported()) continue; break; default: @@ -3499,7 +3503,7 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) } vmcs_write16(sf->selector, var.selector); - vmcs_write32(sf->base, var.base); + vmcs_writel(sf->base, var.base); vmcs_write32(sf->limit, var.limit); vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } @@ -4867,6 +4871,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) if (vmx_xsaves_supported()) vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); + if (enable_pml) { + ASSERT(vmx->pml_pg); + vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); + vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + } + return 0; } @@ -6247,7 +6257,6 @@ static __init int hardware_setup(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); memcpy(vmx_msr_bitmap_legacy_x2apic, vmx_msr_bitmap_legacy, PAGE_SIZE); @@ -6672,14 +6681,20 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, } page = nested_get_page(vcpu, vmptr); - if (page == NULL || - *(u32 *)kmap(page) != VMCS12_REVISION) { + if (page == NULL) { nested_vmx_failInvalid(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + if (*(u32 *)kmap(page) != VMCS12_REVISION) { kunmap(page); + nested_release_page_clean(page); + nested_vmx_failInvalid(vcpu); skip_emulated_instruction(vcpu); return 1; } kunmap(page); + nested_release_page_clean(page); vmx->nested.vmxon_ptr = vmptr; break; case EXIT_REASON_VMCLEAR: @@ -7742,8 +7757,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: - if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return false; return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); @@ -7828,6 +7841,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); case EXIT_REASON_PCOMMIT: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT); + case EXIT_REASON_PML_FULL: + /* We don't expose PML support to L1. */ + return false; default: return true; } @@ -7839,22 +7855,6 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = vmcs_read32(VM_EXIT_INTR_INFO); } -static int vmx_create_pml_buffer(struct vcpu_vmx *vmx) -{ - struct page *pml_pg; - - pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!pml_pg) - return -ENOMEM; - - vmx->pml_pg = pml_pg; - - vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); - - return 0; -} - static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { if (vmx->pml_pg) { @@ -7915,7 +7915,7 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", - name, vmcs_read32(sel), + name, vmcs_read16(sel), vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); @@ -8789,14 +8789,26 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (err) goto free_vcpu; + err = -ENOMEM; + + /* + * If PML is turned on, failure on enabling PML just results in failure + * of creating the vcpu, therefore we can simplify PML logic (by + * avoiding dealing with cases, such as enabling PML partially on vcpus + * for the guest, etc. + */ + if (enable_pml) { + vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!vmx->pml_pg) + goto uninit_vcpu; + } + vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0]) > PAGE_SIZE); - err = -ENOMEM; - if (!vmx->guest_msrs) { - goto uninit_vcpu; - } + if (!vmx->guest_msrs) + goto free_pml; vmx->loaded_vmcs = &vmx->vmcs01; vmx->loaded_vmcs->vmcs = alloc_vmcs(); @@ -8840,18 +8852,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->nested.current_vmptr = -1ull; vmx->nested.current_vmcs12 = NULL; - /* - * If PML is turned on, failure on enabling PML just results in failure - * of creating the vcpu, therefore we can simplify PML logic (by - * avoiding dealing with cases, such as enabling PML partially on vcpus - * for the guest, etc. - */ - if (enable_pml) { - err = vmx_create_pml_buffer(vmx); - if (err) - goto free_vmcs; - } - return &vmx->vcpu; free_vmcs: @@ -8859,6 +8859,8 @@ free_vmcs: free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); +free_pml: + vmx_destroy_pml_buffer(vmx); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); free_vcpu: @@ -9761,6 +9763,18 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } + if (enable_pml) { + /* + * Conceptually we want to copy the PML address and index from + * vmcs01 here, and then back to vmcs01 on nested vmexit. But, + * since we always flush the log on each vmexit, this happens + * to be equivalent to simply resetting the fields in vmcs02. + */ + ASSERT(vmx->pml_pg); + vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); + vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + } + if (nested_cpu_has_ept(vmcs12)) { kvm_mmu_unload(vcpu); nested_ept_init_mmu_context(vcpu); @@ -10254,7 +10268,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); - if (vmx_mpx_supported()) + if (kvm_mpx_supported()) vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); if (nested_cpu_has_xsaves(vmcs12)) vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 25a6efcfdf7f..8e526c6fd784 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2960,6 +2960,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SMM)) return -EINVAL; + /* INITs are latched while in SMM */ + if (events->flags & KVM_VCPUEVENT_VALID_SMM && + (events->smi.smm || events->smi.pending) && + vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) + return -EINVAL; + process_nmi(vcpu); vcpu->arch.exception.pending = events->exception.injected; vcpu->arch.exception.nr = events->exception.nr; @@ -3057,6 +3063,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) memcpy(dest, xsave, XSAVE_HDR_OFFSET); /* Set XSTATE_BV */ + xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; /* @@ -3133,11 +3140,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, } } +#define XSAVE_MXCSR_OFFSET 24 + static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; if (cpu_has_xsave) { /* @@ -3145,11 +3155,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility * with old userspace. */ - if (xstate_bv & ~kvm_supported_xcr0()) + if (xstate_bv & ~kvm_supported_xcr0() || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { - if (xstate_bv & ~XFEATURE_MASK_FPSSE) + if (xstate_bv & ~XFEATURE_MASK_FPSSE || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state.fxsave, guest_xsave->region, sizeof(struct fxregs_state)); @@ -4596,16 +4608,20 @@ emul_write: static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) { - /* TODO: String I/O for in kernel device */ - int r; + int r = 0, i; - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); - else - r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, - vcpu->arch.pio.port, vcpu->arch.pio.size, - pd); + for (i = 0; i < vcpu->arch.pio.count; i++) { + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + if (r) + break; + pd += vcpu->arch.pio.size; + } return r; } @@ -4643,6 +4659,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (vcpu->arch.pio.count) goto data_avail; + memset(vcpu->arch.pio_data, 0, size * count); + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); if (ret) { data_avail: @@ -4826,6 +4844,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, if (var.unusable) { memset(desc, 0, sizeof(*desc)); + if (base3) + *base3 = 0; return false; } @@ -4981,6 +5001,16 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked); } +static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) +{ + return emul_to_vcpu(ctxt)->arch.hflags; +} + +static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) +{ + kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags); +} + static const struct x86_emulate_ops emulate_ops = { .read_gpr = emulator_read_gpr, .write_gpr = emulator_write_gpr, @@ -5020,6 +5050,8 @@ static const struct x86_emulate_ops emulate_ops = { .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, .set_nmi_mask = emulator_set_nmi_mask, + .get_hflags = emulator_get_hflags, + .set_hflags = emulator_set_hflags, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -5072,7 +5104,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); - ctxt->emul_flags = vcpu->arch.hflags; init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; @@ -5468,8 +5499,6 @@ restart: unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; - if (vcpu->arch.hflags != ctxt->emul_flags) - kvm_set_hflags(vcpu, ctxt->emul_flags); kvm_rip_write(vcpu, ctxt->eip); if (r == EMULATE_DONE) kvm_vcpu_check_singlestep(vcpu, rflags, &r); @@ -5956,7 +5985,8 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) kvm_x86_ops->patch_hypercall(vcpu, instruction); - return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); + return emulator_write_emulated(ctxt, rip, instruction, 3, + &ctxt->exception); } static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) @@ -6992,6 +7022,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, mp_state->mp_state != KVM_MP_STATE_RUNNABLE) return -EINVAL; + /* INITs are latched while in SMM */ + if ((is_smm(vcpu) || vcpu->arch.smi_pending) && + (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || + mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) + return -EINVAL; + if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); @@ -8221,8 +8257,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) return true; else - return !kvm_event_needs_reinjection(vcpu) && - kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_can_do_async_pf(vcpu); } void kvm_arch_start_assignment(struct kvm *kvm) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 27f89c79a44b..423644c230e7 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -80,7 +80,7 @@ ENTRY(copy_user_generic_unrolled) movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_copy_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -101,7 +101,8 @@ ENTRY(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -17: movl %edx,%ecx +.L_copy_short_string: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx jz 20f @@ -215,6 +216,8 @@ ENDPROC(copy_user_generic_string) */ ENTRY(copy_user_enhanced_fast_string) ASM_STAC + cmpl $64,%edx + jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */ movl %edx,%ecx 1: rep movsb diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 42982b26e32b..39bdaf3ac44a 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -144,7 +144,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 493f54172b4a..3aebbd6c6f5f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -628,21 +628,40 @@ void __init init_mem_mapping(void) * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains BIOS code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. + * On x86, access has to be given to the first megabyte of RAM because that + * area traditionally contains BIOS code and data regions used by X, dosemu, + * and similar apps. Since they map the entire memory range, the whole range + * must be allowed (for mapping), but any areas that would otherwise be + * disallowed are flagged as being "zero filled" instead of rejected. + * Access has to be given to non-kernel-ram areas as well, these contain the + * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr < 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + if (page_is_ram(pagenr)) { + /* + * For disallowed memory regions in the low 1MB range, + * request that the page be shown as all zeros. + */ + if (pagenr < 256) + return 2; + + return 0; + } + + /* + * This must follow RAM test, since System RAM is considered a + * restricted resource under CONFIG_STRICT_IOMEM. + */ + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { + /* Low 1MB bypasses iomem restrictions. */ + if (pagenr < 256) + return 1; + return 0; - if (!page_is_ram(pagenr)) - return 1; - return 0; + } + + return 1; } void free_init_pages(char *what, unsigned long begin, unsigned long end) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index d470cf219a2d..4e5ac46adc9d 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,3 +1,4 @@ +#define DISABLE_BRANCH_PROFILING #define pr_fmt(fmt) "kasan: " fmt #include <linux/bootmem.h> #include <linux/kasan.h> diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index ef05755a1900..7ed47b1e6f42 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) * We were not able to extract an address from the instruction, * probably because there was something invalid in it. */ - if (info->si_addr == (void *)-1) { + if (info->si_addr == (void __user *)-1) { err = -EINVAL; goto err_out; } @@ -525,15 +525,7 @@ int mpx_handle_bd_fault(void) if (!kernel_managing_mpx_tables(current->mm)) return -EINVAL; - if (do_mpx_bt_fault()) { - force_sig(SIGSEGV, current); - /* - * The force_sig() is essentially "handling" this - * exception, so we do not pass up the error - * from do_mpx_bt_fault(). - */ - } - return 0; + return do_mpx_bt_fault(); } /* diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 47b6436e41c2..3686a1db25b2 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -100,5 +100,6 @@ void __init initmem_init(void) printk(KERN_DEBUG "High memory starts at vaddr %08lx\n", (ulong) pfn_to_kaddr(highstart_pfn)); + __vmalloc_start_set = true; setup_bootmem_allocator(); } diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 6ad687d104ca..3f1bb4f93a5a 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -36,14 +36,14 @@ #undef pr_fmt #define pr_fmt(fmt) "" fmt -static bool boot_cpu_done; - -static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); -static void init_cache_modes(void); +static bool __read_mostly boot_cpu_done; +static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); +static bool __read_mostly pat_initialized; +static bool __read_mostly init_cm_done; void pat_disable(const char *reason) { - if (!__pat_enabled) + if (pat_disabled) return; if (boot_cpu_done) { @@ -51,10 +51,8 @@ void pat_disable(const char *reason) return; } - __pat_enabled = 0; + pat_disabled = true; pr_info("x86/PAT: %s\n", reason); - - init_cache_modes(); } static int __init nopat(char *str) @@ -66,7 +64,7 @@ early_param("nopat", nopat); bool pat_enabled(void) { - return !!__pat_enabled; + return pat_initialized; } EXPORT_SYMBOL_GPL(pat_enabled); @@ -204,6 +202,8 @@ static void __init_cache_modes(u64 pat) update_cache_mode_entry(i, cache); } pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); + + init_cm_done = true; } #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) @@ -224,6 +224,7 @@ static void pat_bsp_init(u64 pat) } wrmsrl(MSR_IA32_CR_PAT, pat); + pat_initialized = true; __init_cache_modes(pat); } @@ -241,10 +242,9 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -static void init_cache_modes(void) +void init_cache_modes(void) { u64 pat = 0; - static int init_cm_done; if (init_cm_done) return; @@ -286,8 +286,6 @@ static void init_cache_modes(void) } __init_cache_modes(pat); - - init_cm_done = 1; } /** @@ -305,10 +303,8 @@ void pat_init(void) u64 pat; struct cpuinfo_x86 *c = &boot_cpu_data; - if (!pat_enabled()) { - init_cache_modes(); + if (pat_disabled) return; - } if ((c->x86_vendor == X86_VENDOR_INTEL) && (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5fb6adaaa796..5a760fd66bec 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -134,8 +134,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, { struct flush_tlb_info info; - if (end == 0) - end = start + PAGE_SIZE; info.flush_mm = mm; info.flush_start = start; info.flush_end = end; @@ -264,7 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, 0UL); + flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE); preempt_enable(); } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index c6d6efed392a..7575f0798194 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -231,23 +231,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 1; for_each_pci_msi_entry(msidesc, dev) { - __pci_read_msi_msg(msidesc, &msg); - pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | - ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); - if (msg.data != XEN_PIRQ_MSI_DATA || - xen_irq_from_pirq(pirq) < 0) { - pirq = xen_allocate_pirq_msi(dev, msidesc); - if (pirq < 0) { - irq = -ENODEV; - goto error; - } - xen_msi_compose_msg(dev, pirq, &msg); - __pci_write_msi_msg(msidesc, &msg); - dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); - } else { - dev_dbg(&dev->dev, - "xen: msi already bound to pirq=%d\n", pirq); + pirq = xen_allocate_pirq_msi(dev, msidesc); + if (pirq < 0) { + irq = -ENODEV; + goto error; } + xen_msi_compose_msg(dev, pirq, &msg); + __pci_write_msi_msg(msidesc, &msg); + dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, (type == PCI_CAP_ID_MSI) ? nvec : 1, (type == PCI_CAP_ID_MSIX) ? diff --git a/arch/x86/platform/goldfish/goldfish.c b/arch/x86/platform/goldfish/goldfish.c index 1693107a518e..0d17c0aafeb1 100644 --- a/arch/x86/platform/goldfish/goldfish.c +++ b/arch/x86/platform/goldfish/goldfish.c @@ -42,10 +42,22 @@ static struct resource goldfish_pdev_bus_resources[] = { } }; +static bool goldfish_enable __initdata; + +static int __init goldfish_setup(char *str) +{ + goldfish_enable = true; + return 0; +} +__setup("goldfish", goldfish_setup); + static int __init goldfish_init(void) { + if (!goldfish_enable) + return -ENODEV; + platform_device_register_simple("goldfish_pdev_bus", -1, - goldfish_pdev_bus_resources, 2); + goldfish_pdev_bus_resources, 2); return 0; } device_initcall(goldfish_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c index de734134bc8d..40c616495da7 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c @@ -17,7 +17,7 @@ #include <asm/intel-mid.h> #include <asm/io_apic.h> -#define TANGIER_EXT_TIMER0_MSI 15 +#define TANGIER_EXT_TIMER0_MSI 12 static struct platform_device wdt_dev = { .name = "intel_mid_wdt", diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 0c2fae8d929d..73eb7fd4aec4 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -992,11 +992,12 @@ static void emit_relocs(int as_text, int use_real_mode) die("Segment relocations found but --realmode not specified\n"); /* Order the relocations for more efficient processing */ - sort_relocs(&relocs16); sort_relocs(&relocs32); #if ELF_BITS == 64 sort_relocs(&relocs32neg); sort_relocs(&relocs64); +#else + sort_relocs(&relocs16); #endif /* Print the relocations */ diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c index a629694ee750..e14c43a2d187 100644 --- a/arch/x86/um/ptrace_64.c +++ b/arch/x86/um/ptrace_64.c @@ -121,7 +121,7 @@ int poke_user(struct task_struct *child, long addr, long data) else if ((addr >= offsetof(struct user, u_debugreg[0])) && (addr <= offsetof(struct user, u_debugreg[7]))) { addr -= offsetof(struct user, u_debugreg[0]); - addr = addr >> 2; + addr = addr >> 3; if ((addr == 4) || (addr == 5)) return -EIO; child->thread.arch.debugregs[addr] = data; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 1e56ff583459..63146c378f1e 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2038,7 +2038,8 @@ static unsigned long __init xen_read_phys_ulong(phys_addr_t addr) /* * Translate a virtual address to a physical one without relying on mapped - * page tables. + * page tables. Don't rely on big pages being aligned in (guest) physical + * space! */ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) { @@ -2059,7 +2060,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) sizeof(pud))); if (!pud_present(pud)) return 0; - pa = pud_pfn(pud) << PAGE_SHIFT; + pa = pud_val(pud) & PTE_PFN_MASK; if (pud_large(pud)) return pa + (vaddr & ~PUD_MASK); @@ -2067,7 +2068,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) sizeof(pmd))); if (!pmd_present(pmd)) return 0; - pa = pmd_pfn(pmd) << PAGE_SHIFT; + pa = pmd_val(pmd) & PTE_PFN_MASK; if (pmd_large(pmd)) return pa + (vaddr & ~PMD_MASK); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index e345891450c3..df8844a1853a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -713,10 +713,9 @@ static void __init xen_reserve_xen_mfnlist(void) size = PFN_PHYS(xen_start_info->nr_p2m_frames); } - if (!xen_is_e820_reserved(start, size)) { - memblock_reserve(start, size); + memblock_reserve(start, size); + if (!xen_is_e820_reserved(start, size)) return; - } #ifdef CONFIG_X86_32 /* @@ -727,6 +726,7 @@ static void __init xen_reserve_xen_mfnlist(void) BUG(); #else xen_relocate_p2m(); + memblock_free(start, size); #endif } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 9e2ba5c6e1dd..f42e78de1e10 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -27,6 +27,12 @@ static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) { + int irq = per_cpu(lock_kicker_irq, cpu); + + /* Don't kick if the target's kicker interrupt is not initialized. */ + if (irq == -1) + return; + xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index f1ba6a092854..8846257d8792 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -343,11 +343,11 @@ static int xen_vcpuop_set_next_event(unsigned long delta, WARN_ON(!clockevent_state_oneshot(evt)); single.timeout_abs_ns = get_abs_timeout(delta); - single.flags = VCPU_SSHOTTMR_future; + /* Get an event anyway, even if the timeout is already expired */ + single.flags = 0; ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, cpu, &single); - - BUG_ON(ret != 0 && ret != -ETIME); + BUG_ON(ret != 0); return ret; } diff --git a/arch/xtensa/include/asm/irq.h b/arch/xtensa/include/asm/irq.h index f71f88ea7646..19707db966f1 100644 --- a/arch/xtensa/include/asm/irq.h +++ b/arch/xtensa/include/asm/irq.h @@ -29,7 +29,8 @@ static inline void variant_irq_disable(unsigned int irq) { } # define PLATFORM_NR_IRQS 0 #endif #define XTENSA_NR_IRQS XCHAL_NUM_INTERRUPTS -#define NR_IRQS (XTENSA_NR_IRQS + VARIANT_NR_IRQS + PLATFORM_NR_IRQS) +#define NR_IRQS (XTENSA_NR_IRQS + VARIANT_NR_IRQS + PLATFORM_NR_IRQS + 1) +#define XTENSA_PIC_LINUX_IRQ(hwirq) ((hwirq) + 1) #if VARIANT_NR_IRQS == 0 static inline void variant_init_irq(void) { } diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c index 4ac3d23161cf..441694464b1e 100644 --- a/arch/xtensa/kernel/irq.c +++ b/arch/xtensa/kernel/irq.c @@ -34,11 +34,6 @@ asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs) { int irq = irq_find_mapping(NULL, hwirq); - if (hwirq >= NR_IRQS) { - printk(KERN_EMERG "%s: cannot handle IRQ %d\n", - __func__, hwirq); - } - #ifdef CONFIG_DEBUG_STACKOVERFLOW /* Debugging check for stack overflow: is there less than 1KB free? */ { diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 9735691f37f1..49ccbd9022f6 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -133,6 +133,8 @@ static int __init parse_tag_initrd(const bp_tag_t* tag) __tagtable(BP_TAG_INITRD, parse_tag_initrd); +#endif /* CONFIG_BLK_DEV_INITRD */ + #ifdef CONFIG_OF static int __init parse_tag_fdt(const bp_tag_t *tag) @@ -145,8 +147,6 @@ __tagtable(BP_TAG_FDT, parse_tag_fdt); #endif /* CONFIG_OF */ -#endif /* CONFIG_BLK_DEV_INITRD */ - static int __init parse_tag_cmdline(const bp_tag_t* tag) { strlcpy(command_line, (char *)(tag->data), COMMAND_LINE_SIZE); diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c index 83cf49685373..3aaaae18417c 100644 --- a/arch/xtensa/kernel/syscall.c +++ b/arch/xtensa/kernel/syscall.c @@ -87,7 +87,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, /* At this point: (!vmm || addr < vmm->vm_end). */ if (TASK_SIZE - len < addr) return -ENOMEM; - if (!vmm || addr + len <= vmm->vm_start) + if (!vmm || addr + len <= vm_start_gap(vmm)) return addr; addr = vmm->vm_end; if (flags & MAP_SHARED) diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h index dbeea2b440a1..1fda7e20dfcb 100644 --- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h +++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h @@ -24,16 +24,18 @@ /* Interrupt configuration. */ -#define PLATFORM_NR_IRQS 10 +#define PLATFORM_NR_IRQS 0 /* Default assignment of LX60 devices to external interrupts. */ #ifdef CONFIG_XTENSA_MX #define DUART16552_INTNUM XCHAL_EXTINT3_NUM #define OETH_IRQ XCHAL_EXTINT4_NUM +#define C67X00_IRQ XCHAL_EXTINT8_NUM #else #define DUART16552_INTNUM XCHAL_EXTINT0_NUM #define OETH_IRQ XCHAL_EXTINT1_NUM +#define C67X00_IRQ XCHAL_EXTINT5_NUM #endif /* @@ -63,5 +65,5 @@ #define C67X00_PADDR (XCHAL_KIO_PADDR + 0x0D0D0000) #define C67X00_SIZE 0x10 -#define C67X00_IRQ 5 + #endif /* __XTENSA_XTAVNET_HARDWARE_H */ diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c index e9f65f79cf2e..d1e9439fad45 100644 --- a/arch/xtensa/platforms/xtfpga/setup.c +++ b/arch/xtensa/platforms/xtfpga/setup.c @@ -209,8 +209,8 @@ static struct resource ethoc_res[] = { .flags = IORESOURCE_MEM, }, [2] = { /* IRQ number */ - .start = OETH_IRQ, - .end = OETH_IRQ, + .start = XTENSA_PIC_LINUX_IRQ(OETH_IRQ), + .end = XTENSA_PIC_LINUX_IRQ(OETH_IRQ), .flags = IORESOURCE_IRQ, }, }; @@ -246,8 +246,8 @@ static struct resource c67x00_res[] = { .flags = IORESOURCE_MEM, }, [1] = { /* IRQ number */ - .start = C67X00_IRQ, - .end = C67X00_IRQ, + .start = XTENSA_PIC_LINUX_IRQ(C67X00_IRQ), + .end = XTENSA_PIC_LINUX_IRQ(C67X00_IRQ), .flags = IORESOURCE_IRQ, }, }; @@ -280,7 +280,7 @@ static struct resource serial_resource = { static struct plat_serial8250_port serial_platform_data[] = { [0] = { .mapbase = DUART16552_PADDR, - .irq = DUART16552_INTNUM, + .irq = XTENSA_PIC_LINUX_IRQ(DUART16552_INTNUM), .flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_IOREMAP, .iotype = UPIO_MEM32, diff --git a/block/bio.c b/block/bio.c index 46e2cc1d4016..14263fab94d3 100644 --- a/block/bio.c +++ b/block/bio.c @@ -373,10 +373,14 @@ static void punt_bios_to_rescuer(struct bio_set *bs) bio_list_init(&punt); bio_list_init(&nopunt); - while ((bio = bio_list_pop(current->bio_list))) + while ((bio = bio_list_pop(¤t->bio_list[0]))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); + current->bio_list[0] = nopunt; - *current->bio_list = nopunt; + bio_list_init(&nopunt); + while ((bio = bio_list_pop(¤t->bio_list[1]))) + bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); + current->bio_list[1] = nopunt; spin_lock(&bs->rescue_lock); bio_list_merge(&bs->rescue_list, &punt); @@ -464,7 +468,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs) * we retry with the original gfp_flags. */ - if (current->bio_list && !bio_list_empty(current->bio_list)) + if (current->bio_list && + (!bio_list_empty(¤t->bio_list[0]) || + !bio_list_empty(¤t->bio_list[1]))) gfp_mask &= ~__GFP_DIRECT_RECLAIM; p = mempool_alloc(bs->bio_pool, gfp_mask); diff --git a/block/blk-core.c b/block/blk-core.c index 25f25271b42a..be43481bcb12 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2023,7 +2023,14 @@ end_io: */ blk_qc_t generic_make_request(struct bio *bio) { - struct bio_list bio_list_on_stack; + /* + * bio_list_on_stack[0] contains bios submitted by the current + * make_request_fn. + * bio_list_on_stack[1] contains bios that were submitted before + * the current make_request_fn, but that haven't been processed + * yet. + */ + struct bio_list bio_list_on_stack[2]; blk_qc_t ret = BLK_QC_T_NONE; if (!generic_make_request_checks(bio)) @@ -2040,7 +2047,7 @@ blk_qc_t generic_make_request(struct bio *bio) * should be added at the tail */ if (current->bio_list) { - bio_list_add(current->bio_list, bio); + bio_list_add(¤t->bio_list[0], bio); goto out; } @@ -2059,24 +2066,39 @@ blk_qc_t generic_make_request(struct bio *bio) * bio_list, and call into ->make_request() again. */ BUG_ON(bio->bi_next); - bio_list_init(&bio_list_on_stack); - current->bio_list = &bio_list_on_stack; + bio_list_init(&bio_list_on_stack[0]); + current->bio_list = bio_list_on_stack; do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) { + struct bio_list lower, same; + + /* Create a fresh bio_list for all subordinate requests */ + bio_list_on_stack[1] = bio_list_on_stack[0]; + bio_list_init(&bio_list_on_stack[0]); ret = q->make_request_fn(q, bio); blk_queue_exit(q); - - bio = bio_list_pop(current->bio_list); + /* sort new bios into those for a lower level + * and those for the same level + */ + bio_list_init(&lower); + bio_list_init(&same); + while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) + if (q == bdev_get_queue(bio->bi_bdev)) + bio_list_add(&same, bio); + else + bio_list_add(&lower, bio); + /* now assemble so we handle the lowest level first */ + bio_list_merge(&bio_list_on_stack[0], &lower); + bio_list_merge(&bio_list_on_stack[0], &same); + bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } else { - struct bio *bio_next = bio_list_pop(current->bio_list); - bio_io_error(bio); - bio = bio_next; } + bio = bio_list_pop(&bio_list_on_stack[0]); } while (bio); current->bio_list = NULL; /* deactivate */ diff --git a/block/blk-integrity.c b/block/blk-integrity.c index d69c5c79f98e..478f572cb1e7 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -412,12 +412,13 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE | template->flags; - bi->interval_exp = ilog2(queue_logical_block_size(disk->queue)); + bi->interval_exp = template->interval_exp ? : + ilog2(queue_logical_block_size(disk->queue)); bi->profile = template->profile ? template->profile : &nop_profile; bi->tuple_size = template->tuple_size; bi->tag_size = template->tag_size; - blk_integrity_revalidate(disk); + disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES; } EXPORT_SYMBOL(blk_integrity_register); @@ -430,26 +431,11 @@ EXPORT_SYMBOL(blk_integrity_register); */ void blk_integrity_unregister(struct gendisk *disk) { - blk_integrity_revalidate(disk); + disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES; memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity)); } EXPORT_SYMBOL(blk_integrity_unregister); -void blk_integrity_revalidate(struct gendisk *disk) -{ - struct blk_integrity *bi = &disk->queue->integrity; - - if (!(disk->flags & GENHD_FL_UP)) - return; - - if (bi->profile) - disk->queue->backing_dev_info.capabilities |= - BDI_CAP_STABLE_WRITES; - else - disk->queue->backing_dev_info.capabilities &= - ~BDI_CAP_STABLE_WRITES; -} - void blk_integrity_add(struct gendisk *disk) { if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype, diff --git a/block/blk-mq.c b/block/blk-mq.c index 6cfc6b200366..0d1af3e44efb 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1259,12 +1259,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (!is_flush_fua && !blk_queue_nomerges(q)) { - if (blk_attempt_plug_merge(q, bio, &request_count, - &same_queue_rq)) - return BLK_QC_T_NONE; - } else - request_count = blk_plug_queued_count(q); + if (!is_flush_fua && !blk_queue_nomerges(q) && + blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) + return BLK_QC_T_NONE; rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) @@ -1355,9 +1352,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (!is_flush_fua && !blk_queue_nomerges(q) && - blk_attempt_plug_merge(q, bio, &request_count, NULL)) - return BLK_QC_T_NONE; + if (!is_flush_fua && !blk_queue_nomerges(q)) { + if (blk_attempt_plug_merge(q, bio, &request_count, NULL)) + return BLK_QC_T_NONE; + } else + request_count = blk_plug_queued_count(q); rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) @@ -1471,7 +1470,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, INIT_LIST_HEAD(&tags->page_list); tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *), - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, + GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, set->numa_node); if (!tags->rqs) { blk_mq_free_tags(tags); @@ -1497,7 +1496,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, do { page = alloc_pages_node(set->numa_node, - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, + GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; @@ -1518,7 +1517,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ - kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL); + kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, set->queue_depth - i); left -= to_do * rq_size; diff --git a/block/genhd.c b/block/genhd.c index fad9db981675..a87e77626504 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -664,7 +664,6 @@ void del_gendisk(struct gendisk *disk) kobject_put(disk->part0.holder_dir); kobject_put(disk->slave_dir); - disk->driverfs_dev = NULL; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); diff --git a/block/partition-generic.c b/block/partition-generic.c index 91327dbfbb1d..19cf33b91a5a 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -446,7 +446,6 @@ rescan: if (disk->fops->revalidate_disk) disk->fops->revalidate_disk(disk); - blk_integrity_revalidate(disk); check_disk_size_change(disk, bdev); bdev->bd_invalidated = 0; if (!get_capacity(disk) || !(state = check_partition(disk, bdev))) diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c index 93e7c1b32edd..5610cd537da7 100644 --- a/block/partitions/msdos.c +++ b/block/partitions/msdos.c @@ -300,6 +300,8 @@ static void parse_bsd(struct parsed_partitions *state, continue; bsd_start = le32_to_cpu(p->p_offset); bsd_size = le32_to_cpu(p->p_size); + if (memcmp(flavour, "bsd\0", 4) == 0) + bsd_start += offset; if (offset == bsd_start && size == bsd_size) /* full parent partition, we have it already */ continue; diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 0774799942e0..c6fee7437be4 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -182,6 +182,9 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter) __set_bit(WRITE_16, filter->write_ok); __set_bit(WRITE_LONG, filter->write_ok); __set_bit(WRITE_LONG_2, filter->write_ok); + __set_bit(WRITE_SAME, filter->write_ok); + __set_bit(WRITE_SAME_16, filter->write_ok); + __set_bit(WRITE_SAME_32, filter->write_ok); __set_bit(ERASE, filter->write_ok); __set_bit(GPCMD_MODE_SELECT_10, filter->write_ok); __set_bit(MODE_SELECT, filter->write_ok); diff --git a/crypto/Kconfig b/crypto/Kconfig index 7240821137fd..3240d394426c 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -289,6 +289,24 @@ config CRYPTO_CBC CBC: Cipher Block Chaining mode This block cipher algorithm is required for IPSec. +config CRYPTO_HEH + tristate "HEH support" + select CRYPTO_CMAC + select CRYPTO_ECB + select CRYPTO_GF128MUL + select CRYPTO_MANAGER + select CRYPTO_POLY_HASH_ARM64_CE if ARM64 && KERNEL_MODE_NEON + help + HEH: Hash-Encrypt-Hash mode + HEH is a proposed block cipher mode of operation which extends the + strong pseudo-random permutation (SPRP) property of block ciphers to + arbitrary-length input strings. This provides a stronger notion of + security than existing block cipher modes of operation (e.g. CBC, CTR, + XTS), though it is usually less performant. Applications include disk + encryption and encryption of file names and contents. Currently, this + implementation only provides a symmetric cipher interface, so it can't + yet be used as an AEAD. + config CRYPTO_CTR tristate "CTR support" select CRYPTO_BLKCIPHER diff --git a/crypto/Makefile b/crypto/Makefile index 82fbff180ad3..8507d1fab3ac 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -62,10 +62,12 @@ obj-$(CONFIG_CRYPTO_SHA1) += sha1_generic.o obj-$(CONFIG_CRYPTO_SHA256) += sha256_generic.o obj-$(CONFIG_CRYPTO_SHA512) += sha512_generic.o obj-$(CONFIG_CRYPTO_WP512) += wp512.o +CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149 obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o obj-$(CONFIG_CRYPTO_ECB) += ecb.o obj-$(CONFIG_CRYPTO_CBC) += cbc.o +obj-$(CONFIG_CRYPTO_HEH) += heh.o obj-$(CONFIG_CRYPTO_PCBC) += pcbc.o obj-$(CONFIG_CRYPTO_CTS) += cts.o obj-$(CONFIG_CRYPTO_LRW) += lrw.o @@ -85,6 +87,7 @@ obj-$(CONFIG_CRYPTO_BLOWFISH_COMMON) += blowfish_common.o obj-$(CONFIG_CRYPTO_TWOFISH) += twofish_generic.o obj-$(CONFIG_CRYPTO_TWOFISH_COMMON) += twofish_common.o obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o +CFLAGS_serpent_generic.o := $(call cc-option,-fsched-pressure) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia_generic.o obj-$(CONFIG_CRYPTO_CAST_COMMON) += cast_common.o diff --git a/crypto/ahash.c b/crypto/ahash.c index dac1c24e9c3e..f9caf0f74199 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -31,6 +31,7 @@ struct ahash_request_priv { crypto_completion_t complete; void *data; u8 *result; + u32 flags; void *ubuf[] CRYPTO_MINALIGN_ATTR; }; @@ -270,6 +271,8 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt) priv->result = req->result; priv->complete = req->base.complete; priv->data = req->base.data; + priv->flags = req->base.flags; + /* * WARNING: We do not backup req->priv here! The req->priv * is for internal use of the Crypto API and the @@ -284,38 +287,44 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt) return 0; } -static void ahash_restore_req(struct ahash_request *req) +static void ahash_restore_req(struct ahash_request *req, int err) { struct ahash_request_priv *priv = req->priv; + if (!err) + memcpy(priv->result, req->result, + crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); + /* Restore the original crypto request. */ req->result = priv->result; - req->base.complete = priv->complete; - req->base.data = priv->data; + + ahash_request_set_callback(req, priv->flags, + priv->complete, priv->data); req->priv = NULL; /* Free the req->priv.priv from the ADJUSTED request. */ kzfree(priv); } -static void ahash_op_unaligned_finish(struct ahash_request *req, int err) +static void ahash_notify_einprogress(struct ahash_request *req) { struct ahash_request_priv *priv = req->priv; + struct crypto_async_request oreq; - if (err == -EINPROGRESS) - return; - - if (!err) - memcpy(priv->result, req->result, - crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); + oreq.data = priv->data; - ahash_restore_req(req); + priv->complete(&oreq, -EINPROGRESS); } static void ahash_op_unaligned_done(struct crypto_async_request *req, int err) { struct ahash_request *areq = req->data; + if (err == -EINPROGRESS) { + ahash_notify_einprogress(areq); + return; + } + /* * Restore the original request, see ahash_op_unaligned() for what * goes where. @@ -326,7 +335,7 @@ static void ahash_op_unaligned_done(struct crypto_async_request *req, int err) */ /* First copy req->result into req->priv.result */ - ahash_op_unaligned_finish(areq, err); + ahash_restore_req(areq, err); /* Complete the ORIGINAL request. */ areq->base.complete(&areq->base, err); @@ -342,7 +351,12 @@ static int ahash_op_unaligned(struct ahash_request *req, return err; err = op(req); - ahash_op_unaligned_finish(req, err); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; + + ahash_restore_req(req, err); return err; } @@ -377,25 +391,14 @@ int crypto_ahash_digest(struct ahash_request *req) } EXPORT_SYMBOL_GPL(crypto_ahash_digest); -static void ahash_def_finup_finish2(struct ahash_request *req, int err) +static void ahash_def_finup_done2(struct crypto_async_request *req, int err) { - struct ahash_request_priv *priv = req->priv; + struct ahash_request *areq = req->data; if (err == -EINPROGRESS) return; - if (!err) - memcpy(priv->result, req->result, - crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); - - ahash_restore_req(req); -} - -static void ahash_def_finup_done2(struct crypto_async_request *req, int err) -{ - struct ahash_request *areq = req->data; - - ahash_def_finup_finish2(areq, err); + ahash_restore_req(areq, err); areq->base.complete(&areq->base, err); } @@ -406,11 +409,15 @@ static int ahash_def_finup_finish1(struct ahash_request *req, int err) goto out; req->base.complete = ahash_def_finup_done2; - req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + err = crypto_ahash_reqtfm(req)->final(req); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; out: - ahash_def_finup_finish2(req, err); + ahash_restore_req(req, err); return err; } @@ -418,7 +425,16 @@ static void ahash_def_finup_done1(struct crypto_async_request *req, int err) { struct ahash_request *areq = req->data; + if (err == -EINPROGRESS) { + ahash_notify_einprogress(areq); + return; + } + + areq->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + err = ahash_def_finup_finish1(areq, err); + if (areq->priv) + return; areq->base.complete(&areq->base, err); } @@ -433,6 +449,11 @@ static int ahash_def_finup(struct ahash_request *req) return err; err = tfm->update(req); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; + return ahash_def_finup_finish1(req, err); } diff --git a/crypto/algapi.c b/crypto/algapi.c index 59bf491fe3d8..43f5bdb6b570 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -357,6 +357,7 @@ int crypto_register_alg(struct crypto_alg *alg) struct crypto_larval *larval; int err; + alg->cra_flags &= ~CRYPTO_ALG_DEAD; err = crypto_check_alg(alg); if (err) return err; diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 6d4d4569447e..faea9d728fd2 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -29,6 +29,11 @@ struct aead_sg_list { struct scatterlist sg[ALG_MAX_PAGES]; }; +struct aead_tfm { + struct crypto_aead *aead; + bool has_key; +}; + struct aead_ctx { struct aead_sg_list tsgl; /* @@ -513,24 +518,146 @@ static struct proto_ops algif_aead_ops = { .poll = aead_poll, }; +static int aead_check_key(struct socket *sock) +{ + int err = 0; + struct sock *psk; + struct alg_sock *pask; + struct aead_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + lock_sock(sk); + if (ask->refcnt) + goto unlock_child; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); +unlock_child: + release_sock(sk); + + return err; +} + +static int aead_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = aead_check_key(sock); + if (err) + return err; + + return aead_sendmsg(sock, msg, size); +} + +static ssize_t aead_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = aead_check_key(sock); + if (err) + return err; + + return aead_sendpage(sock, page, offset, size, flags); +} + +static int aead_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = aead_check_key(sock); + if (err) + return err; + + return aead_recvmsg(sock, msg, ignored, flags); +} + +static struct proto_ops algif_aead_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .accept = sock_no_accept, + .setsockopt = sock_no_setsockopt, + + .release = af_alg_release, + .sendmsg = aead_sendmsg_nokey, + .sendpage = aead_sendpage_nokey, + .recvmsg = aead_recvmsg_nokey, + .poll = aead_poll, +}; + static void *aead_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_aead(name, type, mask); + struct aead_tfm *tfm; + struct crypto_aead *aead; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + aead = crypto_alloc_aead(name, type, mask); + if (IS_ERR(aead)) { + kfree(tfm); + return ERR_CAST(aead); + } + + tfm->aead = aead; + + return tfm; } static void aead_release(void *private) { - crypto_free_aead(private); + struct aead_tfm *tfm = private; + + crypto_free_aead(tfm->aead); + kfree(tfm); } static int aead_setauthsize(void *private, unsigned int authsize) { - return crypto_aead_setauthsize(private, authsize); + struct aead_tfm *tfm = private; + + return crypto_aead_setauthsize(tfm->aead, authsize); } static int aead_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_aead_setkey(private, key, keylen); + struct aead_tfm *tfm = private; + int err; + + err = crypto_aead_setkey(tfm->aead, key, keylen); + tfm->has_key = !err; + + return err; } static void aead_sock_destruct(struct sock *sk) @@ -546,12 +673,14 @@ static void aead_sock_destruct(struct sock *sk) af_alg_release_parent(sk); } -static int aead_accept_parent(void *private, struct sock *sk) +static int aead_accept_parent_nokey(void *private, struct sock *sk) { struct aead_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned int len = sizeof(*ctx) + crypto_aead_reqsize(private); - unsigned int ivlen = crypto_aead_ivsize(private); + struct aead_tfm *tfm = private; + struct crypto_aead *aead = tfm->aead; + unsigned int len = sizeof(*ctx) + crypto_aead_reqsize(aead); + unsigned int ivlen = crypto_aead_ivsize(aead); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) @@ -577,7 +706,7 @@ static int aead_accept_parent(void *private, struct sock *sk) ask->private = ctx; - aead_request_set_tfm(&ctx->aead_req, private); + aead_request_set_tfm(&ctx->aead_req, aead); aead_request_set_callback(&ctx->aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); @@ -586,13 +715,25 @@ static int aead_accept_parent(void *private, struct sock *sk) return 0; } +static int aead_accept_parent(void *private, struct sock *sk) +{ + struct aead_tfm *tfm = private; + + if (!tfm->has_key) + return -ENOKEY; + + return aead_accept_parent_nokey(private, sk); +} + static const struct af_alg_type algif_type_aead = { .bind = aead_bind, .release = aead_release, .setkey = aead_setkey, .setauthsize = aead_setauthsize, .accept = aead_accept_parent, + .accept_nokey = aead_accept_parent_nokey, .ops = &algif_aead_ops, + .ops_nokey = &algif_aead_ops_nokey, .name = "aead", .owner = THIS_MODULE }; diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 68a5ceaa04c8..8d8b3eeba725 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -184,7 +184,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags) struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; struct ahash_request *req = &ctx->req; - char state[crypto_ahash_statesize(crypto_ahash_reqtfm(req))]; + char state[crypto_ahash_statesize(crypto_ahash_reqtfm(req)) ? : 1]; struct sock *sk2; struct alg_sock *ask2; struct hash_ctx *ctx2; diff --git a/crypto/authencesn.c b/crypto/authencesn.c index 0c0468869e25..52154ef21b5e 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -245,6 +245,9 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req, u8 *ihash = ohash + crypto_ahash_digestsize(auth); u32 tmp[2]; + if (!authsize) + goto decrypt; + /* Move high-order bits of sequence number back. */ scatterwalk_map_and_copy(tmp, dst, 4, 4, 0); scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0); @@ -253,6 +256,8 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req, if (crypto_memneq(ihash, ohash, authsize)) return -EBADMSG; +decrypt: + sg_init_table(areq_ctx->dst, 2); dst = scatterwalk_ffwd(areq_ctx->dst, dst, assoclen); diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c index dca7bc87dad9..7bbfadc195a6 100644 --- a/crypto/blkcipher.c +++ b/crypto/blkcipher.c @@ -373,6 +373,27 @@ int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc, } EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block); +/* + * This function allows ablkcipher algorithms to use the blkcipher_walk API to + * walk over their data. The specified crypto_ablkcipher tfm is used to + * initialize the struct blkcipher_walk, and the crypto_blkcipher specified in + * desc->tfm is never used so it can be left NULL. (Yes, this design is ugly, + * but it parallels blkcipher_aead_walk_virt_block() above. In the 4.10 kernel + * this is starting to be cleaned up...) + */ +int blkcipher_ablkcipher_walk_virt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk, + struct crypto_ablkcipher *tfm) +{ + walk->flags &= ~BLKCIPHER_WALK_PHYS; + walk->walk_blocksize = crypto_ablkcipher_blocksize(tfm); + walk->cipher_blocksize = walk->walk_blocksize; + walk->ivsize = crypto_ablkcipher_ivsize(tfm); + walk->alignmask = crypto_ablkcipher_alignmask(tfm); + return blkcipher_walk_first(desc, walk); +} +EXPORT_SYMBOL_GPL(blkcipher_ablkcipher_walk_virt); + static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen) { diff --git a/crypto/cryptd.c b/crypto/cryptd.c index e7aa904cb20b..26a504db3f53 100644 --- a/crypto/cryptd.c +++ b/crypto/cryptd.c @@ -642,6 +642,7 @@ static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb, inst->alg.halg.base.cra_flags = type; inst->alg.halg.digestsize = salg->digestsize; + inst->alg.halg.statesize = salg->statesize; inst->alg.halg.base.cra_ctxsize = sizeof(struct cryptd_hash_ctx); inst->alg.halg.base.cra_init = cryptd_hash_init_tfm; diff --git a/crypto/gcm.c b/crypto/gcm.c index 1238b3c5a321..0a12c09d7cb2 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -152,10 +152,8 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key, err = crypto_ablkcipher_encrypt(&data->req); if (err == -EINPROGRESS || err == -EBUSY) { - err = wait_for_completion_interruptible( - &data->result.completion); - if (!err) - err = data->result.err; + wait_for_completion(&data->result.completion); + err = data->result.err; } if (err) diff --git a/crypto/gf128mul.c b/crypto/gf128mul.c index 5276607c72d0..f3d9f6da0767 100644 --- a/crypto/gf128mul.c +++ b/crypto/gf128mul.c @@ -44,7 +44,7 @@ --------------------------------------------------------------------------- Issue 31/01/2006 - This file provides fast multiplication in GF(128) as required by several + This file provides fast multiplication in GF(2^128) as required by several cryptographic authentication modes */ @@ -88,37 +88,52 @@ q(0xf8), q(0xf9), q(0xfa), q(0xfb), q(0xfc), q(0xfd), q(0xfe), q(0xff) \ } -/* Given the value i in 0..255 as the byte overflow when a field element - in GHASH is multiplied by x^8, this function will return the values that - are generated in the lo 16-bit word of the field value by applying the - modular polynomial. The values lo_byte and hi_byte are returned via the - macro xp_fun(lo_byte, hi_byte) so that the values can be assembled into - memory as required by a suitable definition of this macro operating on - the table above -*/ - -#define xx(p, q) 0x##p##q +/* + * Given a value i in 0..255 as the byte overflow when a field element + * in GF(2^128) is multiplied by x^8, the following macro returns the + * 16-bit value that must be XOR-ed into the low-degree end of the + * product to reduce it modulo the irreducible polynomial x^128 + x^7 + + * x^2 + x + 1. + * + * There are two versions of the macro, and hence two tables: one for + * the "be" convention where the highest-order bit is the coefficient of + * the highest-degree polynomial term, and one for the "le" convention + * where the highest-order bit is the coefficient of the lowest-degree + * polynomial term. In both cases the values are stored in CPU byte + * endianness such that the coefficients are ordered consistently across + * bytes, i.e. in the "be" table bits 15..0 of the stored value + * correspond to the coefficients of x^15..x^0, and in the "le" table + * bits 15..0 correspond to the coefficients of x^0..x^15. + * + * Therefore, provided that the appropriate byte endianness conversions + * are done by the multiplication functions (and these must be in place + * anyway to support both little endian and big endian CPUs), the "be" + * table can be used for multiplications of both "bbe" and "ble" + * elements, and the "le" table can be used for multiplications of both + * "lle" and "lbe" elements. + */ -#define xda_bbe(i) ( \ - (i & 0x80 ? xx(43, 80) : 0) ^ (i & 0x40 ? xx(21, c0) : 0) ^ \ - (i & 0x20 ? xx(10, e0) : 0) ^ (i & 0x10 ? xx(08, 70) : 0) ^ \ - (i & 0x08 ? xx(04, 38) : 0) ^ (i & 0x04 ? xx(02, 1c) : 0) ^ \ - (i & 0x02 ? xx(01, 0e) : 0) ^ (i & 0x01 ? xx(00, 87) : 0) \ +#define xda_be(i) ( \ + (i & 0x80 ? 0x4380 : 0) ^ (i & 0x40 ? 0x21c0 : 0) ^ \ + (i & 0x20 ? 0x10e0 : 0) ^ (i & 0x10 ? 0x0870 : 0) ^ \ + (i & 0x08 ? 0x0438 : 0) ^ (i & 0x04 ? 0x021c : 0) ^ \ + (i & 0x02 ? 0x010e : 0) ^ (i & 0x01 ? 0x0087 : 0) \ ) -#define xda_lle(i) ( \ - (i & 0x80 ? xx(e1, 00) : 0) ^ (i & 0x40 ? xx(70, 80) : 0) ^ \ - (i & 0x20 ? xx(38, 40) : 0) ^ (i & 0x10 ? xx(1c, 20) : 0) ^ \ - (i & 0x08 ? xx(0e, 10) : 0) ^ (i & 0x04 ? xx(07, 08) : 0) ^ \ - (i & 0x02 ? xx(03, 84) : 0) ^ (i & 0x01 ? xx(01, c2) : 0) \ +#define xda_le(i) ( \ + (i & 0x80 ? 0xe100 : 0) ^ (i & 0x40 ? 0x7080 : 0) ^ \ + (i & 0x20 ? 0x3840 : 0) ^ (i & 0x10 ? 0x1c20 : 0) ^ \ + (i & 0x08 ? 0x0e10 : 0) ^ (i & 0x04 ? 0x0708 : 0) ^ \ + (i & 0x02 ? 0x0384 : 0) ^ (i & 0x01 ? 0x01c2 : 0) \ ) -static const u16 gf128mul_table_lle[256] = gf128mul_dat(xda_lle); -static const u16 gf128mul_table_bbe[256] = gf128mul_dat(xda_bbe); +static const u16 gf128mul_table_le[256] = gf128mul_dat(xda_le); +static const u16 gf128mul_table_be[256] = gf128mul_dat(xda_be); -/* These functions multiply a field element by x, by x^4 and by x^8 - * in the polynomial field representation. It uses 32-bit word operations - * to gain speed but compensates for machine endianess and hence works +/* + * The following functions multiply a field element by x or by x^8 in + * the polynomial field representation. They use 64-bit word operations + * to gain speed but compensate for machine endianness and hence work * correctly on both styles of machine. */ @@ -126,7 +141,7 @@ static void gf128mul_x_lle(be128 *r, const be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_lle[(b << 7) & 0xff]; + u64 _tt = gf128mul_table_le[(b << 7) & 0xff]; r->b = cpu_to_be64((b >> 1) | (a << 63)); r->a = cpu_to_be64((a >> 1) ^ (_tt << 48)); @@ -136,7 +151,7 @@ static void gf128mul_x_bbe(be128 *r, const be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_bbe[a >> 63]; + u64 _tt = gf128mul_table_be[a >> 63]; r->a = cpu_to_be64((a << 1) | (b >> 63)); r->b = cpu_to_be64((b << 1) ^ _tt); @@ -146,7 +161,7 @@ void gf128mul_x_ble(be128 *r, const be128 *x) { u64 a = le64_to_cpu(x->a); u64 b = le64_to_cpu(x->b); - u64 _tt = gf128mul_table_bbe[b >> 63]; + u64 _tt = gf128mul_table_be[b >> 63]; r->a = cpu_to_le64((a << 1) ^ _tt); r->b = cpu_to_le64((b << 1) | (a >> 63)); @@ -157,7 +172,7 @@ static void gf128mul_x8_lle(be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_lle[b & 0xff]; + u64 _tt = gf128mul_table_le[b & 0xff]; x->b = cpu_to_be64((b >> 8) | (a << 56)); x->a = cpu_to_be64((a >> 8) ^ (_tt << 48)); @@ -167,12 +182,22 @@ static void gf128mul_x8_bbe(be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_bbe[a >> 56]; + u64 _tt = gf128mul_table_be[a >> 56]; x->a = cpu_to_be64((a << 8) | (b >> 56)); x->b = cpu_to_be64((b << 8) ^ _tt); } +static void gf128mul_x8_ble(be128 *x) +{ + u64 a = le64_to_cpu(x->b); + u64 b = le64_to_cpu(x->a); + u64 _tt = gf128mul_table_be[a >> 56]; + + x->b = cpu_to_le64((a << 8) | (b >> 56)); + x->a = cpu_to_le64((b << 8) ^ _tt); +} + void gf128mul_lle(be128 *r, const be128 *b) { be128 p[8]; @@ -249,9 +274,48 @@ void gf128mul_bbe(be128 *r, const be128 *b) } EXPORT_SYMBOL(gf128mul_bbe); +void gf128mul_ble(be128 *r, const be128 *b) +{ + be128 p[8]; + int i; + + p[0] = *r; + for (i = 0; i < 7; ++i) + gf128mul_x_ble((be128 *)&p[i + 1], (be128 *)&p[i]); + + memset(r, 0, sizeof(*r)); + for (i = 0;;) { + u8 ch = ((u8 *)b)[15 - i]; + + if (ch & 0x80) + be128_xor(r, r, &p[7]); + if (ch & 0x40) + be128_xor(r, r, &p[6]); + if (ch & 0x20) + be128_xor(r, r, &p[5]); + if (ch & 0x10) + be128_xor(r, r, &p[4]); + if (ch & 0x08) + be128_xor(r, r, &p[3]); + if (ch & 0x04) + be128_xor(r, r, &p[2]); + if (ch & 0x02) + be128_xor(r, r, &p[1]); + if (ch & 0x01) + be128_xor(r, r, &p[0]); + + if (++i >= 16) + break; + + gf128mul_x8_ble(r); + } +} +EXPORT_SYMBOL(gf128mul_ble); + + /* This version uses 64k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key - value in GF(128). If we consider a GF(128) value in + value in GF(2^128). If we consider a GF(2^128) value in the buffer's lowest byte, we can construct a table of the 256 16 byte values that result from the 256 values of this byte. This requires 4096 bytes. But we also @@ -352,8 +416,8 @@ void gf128mul_free_64k(struct gf128mul_64k *t) int i; for (i = 0; i < 16; i++) - kfree(t->t[i]); - kfree(t); + kzfree(t->t[i]); + kzfree(t); } EXPORT_SYMBOL(gf128mul_free_64k); @@ -385,7 +449,7 @@ EXPORT_SYMBOL(gf128mul_64k_bbe); /* This version uses 4k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key - value in GF(128). If we consider a GF(128) value in a + value in GF(2^128). If we consider a GF(2^128) value in a single byte, we can construct a table of the 256 16 byte values that result from the 256 values of this byte. This requires 4096 bytes. If we take the highest byte in @@ -443,6 +507,28 @@ out: } EXPORT_SYMBOL(gf128mul_init_4k_bbe); +struct gf128mul_4k *gf128mul_init_4k_ble(const be128 *g) +{ + struct gf128mul_4k *t; + int j, k; + + t = kzalloc(sizeof(*t), GFP_KERNEL); + if (!t) + goto out; + + t->t[1] = *g; + for (j = 1; j <= 64; j <<= 1) + gf128mul_x_ble(&t->t[j + j], &t->t[j]); + + for (j = 2; j < 256; j += j) + for (k = 1; k < j; ++k) + be128_xor(&t->t[j + k], &t->t[j], &t->t[k]); + +out: + return t; +} +EXPORT_SYMBOL(gf128mul_init_4k_ble); + void gf128mul_4k_lle(be128 *a, struct gf128mul_4k *t) { u8 *ap = (u8 *)a; @@ -473,5 +559,20 @@ void gf128mul_4k_bbe(be128 *a, struct gf128mul_4k *t) } EXPORT_SYMBOL(gf128mul_4k_bbe); +void gf128mul_4k_ble(be128 *a, struct gf128mul_4k *t) +{ + u8 *ap = (u8 *)a; + be128 r[1]; + int i = 15; + + *r = t->t[ap[15]]; + while (i--) { + gf128mul_x8_ble(r); + be128_xor(r, r, &t->t[ap[i]]); + } + *a = *r; +} +EXPORT_SYMBOL(gf128mul_4k_ble); + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Functions for multiplying elements of GF(2^128)"); diff --git a/crypto/heh.c b/crypto/heh.c new file mode 100644 index 000000000000..10c00aaf797e --- /dev/null +++ b/crypto/heh.c @@ -0,0 +1,1033 @@ +/* + * HEH: Hash-Encrypt-Hash mode + * + * Copyright (c) 2016 Google Inc. + * + * Authors: + * Alex Cope <alexcope@google.com> + * Eric Biggers <ebiggers@google.com> + */ + +/* + * Hash-Encrypt-Hash (HEH) is a proposed block cipher mode of operation which + * extends the strong pseudo-random permutation (SPRP) property of block ciphers + * (e.g. AES) to arbitrary length input strings. It uses two keyed invertible + * hash functions with a layer of ECB encryption applied in-between. The + * algorithm is specified by the following Internet Draft: + * + * https://tools.ietf.org/html/draft-cope-heh-01 + * + * Although HEH can be used as either a regular symmetric cipher or as an AEAD, + * currently this module only provides it as a symmetric cipher. Additionally, + * only 16-byte nonces are supported. + */ + +#include <crypto/gf128mul.h> +#include <crypto/internal/hash.h> +#include <crypto/internal/skcipher.h> +#include <crypto/scatterwalk.h> +#include <crypto/skcipher.h> +#include "internal.h" + +/* + * The block size is the size of GF(2^128) elements and also the required block + * size of the underlying block cipher. + */ +#define HEH_BLOCK_SIZE 16 + +struct heh_instance_ctx { + struct crypto_shash_spawn cmac; + struct crypto_shash_spawn poly_hash; + struct crypto_skcipher_spawn ecb; +}; + +struct heh_tfm_ctx { + struct crypto_shash *cmac; + struct crypto_shash *poly_hash; /* keyed with tau_key */ + struct crypto_ablkcipher *ecb; +}; + +struct heh_cmac_data { + u8 nonce[HEH_BLOCK_SIZE]; + __le32 nonce_length; + __le32 aad_length; + __le32 message_length; + __le32 padding; +}; + +struct heh_req_ctx { /* aligned to alignmask */ + be128 beta1_key; + be128 beta2_key; + union { + struct { + struct heh_cmac_data data; + struct shash_desc desc; + /* + crypto_shash_descsize(cmac) */ + } cmac; + struct { + struct shash_desc desc; + /* + crypto_shash_descsize(poly_hash) */ + } poly_hash; + struct { + u8 keystream[HEH_BLOCK_SIZE]; + u8 tmp[HEH_BLOCK_SIZE]; + struct scatterlist tmp_sgl[2]; + struct ablkcipher_request req; + /* + crypto_ablkcipher_reqsize(ecb) */ + } ecb; + } u; +}; + +/* + * Get the offset in bytes to the last full block, or equivalently the length of + * all full blocks excluding the last + */ +static inline unsigned int get_tail_offset(unsigned int len) +{ + len -= len % HEH_BLOCK_SIZE; + return len - HEH_BLOCK_SIZE; +} + +static inline struct heh_req_ctx *heh_req_ctx(struct ablkcipher_request *req) +{ + unsigned int alignmask = crypto_ablkcipher_alignmask( + crypto_ablkcipher_reqtfm(req)); + + return (void *)PTR_ALIGN((u8 *)ablkcipher_request_ctx(req), + alignmask + 1); +} + +static inline void async_done(struct crypto_async_request *areq, int err, + int (*next_step)(struct ablkcipher_request *, + u32)) +{ + struct ablkcipher_request *req = areq->data; + + if (err) + goto out; + + err = next_step(req, req->base.flags & ~CRYPTO_TFM_REQ_MAY_SLEEP); + if (err == -EINPROGRESS || + (err == -EBUSY && (req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))) + return; +out: + ablkcipher_request_complete(req, err); +} + +/* + * Generate the per-message "beta" keys used by the hashing layers of HEH. The + * first beta key is the CMAC of the nonce, the additional authenticated data + * (AAD), and the lengths in bytes of the nonce, AAD, and message. The nonce + * and AAD are each zero-padded to the next 16-byte block boundary, and the + * lengths are serialized as 4-byte little endian integers and zero-padded to + * the next 16-byte block boundary. + * The second beta key is the first one interpreted as an element in GF(2^128) + * and multiplied by x. + * + * Note that because the nonce and AAD may, in general, be variable-length, the + * key generation must be done by a pseudo-random function (PRF) on + * variable-length inputs. CBC-MAC does not satisfy this, as it is only a PRF + * on fixed-length inputs. CMAC remedies this flaw. Including the lengths of + * the nonce, AAD, and message is also critical to avoid collisions. + * + * That being said, this implementation does not yet operate as an AEAD and + * therefore there is never any AAD, nor are variable-length nonces supported. + */ +static int generate_betas(struct ablkcipher_request *req, + be128 *beta1_key, be128 *beta2_key) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct heh_tfm_ctx *ctx = crypto_ablkcipher_ctx(tfm); + struct heh_req_ctx *rctx = heh_req_ctx(req); + struct heh_cmac_data *data = &rctx->u.cmac.data; + struct shash_desc *desc = &rctx->u.cmac.desc; + int err; + + BUILD_BUG_ON(sizeof(*data) != 2 * HEH_BLOCK_SIZE); + memcpy(data->nonce, req->info, HEH_BLOCK_SIZE); + data->nonce_length = cpu_to_le32(HEH_BLOCK_SIZE); + data->aad_length = cpu_to_le32(0); + data->message_length = cpu_to_le32(req->nbytes); + data->padding = cpu_to_le32(0); + + desc->tfm = ctx->cmac; + desc->flags = req->base.flags; + + err = crypto_shash_digest(desc, (const u8 *)data, sizeof(*data), + (u8 *)beta1_key); + if (err) + return err; + + gf128mul_x_ble(beta2_key, beta1_key); + return 0; +} + +/*****************************************************************************/ + +/* + * This is the generic version of poly_hash. It does the GF(2^128) + * multiplication by 'tau_key' using a precomputed table, without using any + * special CPU instructions. On some platforms, an accelerated version (with + * higher cra_priority) may be used instead. + */ + +struct poly_hash_tfm_ctx { + struct gf128mul_4k *tau_key; +}; + +struct poly_hash_desc_ctx { + be128 digest; + unsigned int count; +}; + +static int poly_hash_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) +{ + struct poly_hash_tfm_ctx *tctx = crypto_shash_ctx(tfm); + be128 key128; + + if (keylen != HEH_BLOCK_SIZE) { + crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + + if (tctx->tau_key) + gf128mul_free_4k(tctx->tau_key); + memcpy(&key128, key, HEH_BLOCK_SIZE); + tctx->tau_key = gf128mul_init_4k_ble(&key128); + if (!tctx->tau_key) + return -ENOMEM; + return 0; +} + +static int poly_hash_init(struct shash_desc *desc) +{ + struct poly_hash_desc_ctx *ctx = shash_desc_ctx(desc); + + ctx->digest = (be128) { 0 }; + ctx->count = 0; + return 0; +} + +static int poly_hash_update(struct shash_desc *desc, const u8 *src, + unsigned int len) +{ + struct poly_hash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + struct poly_hash_desc_ctx *ctx = shash_desc_ctx(desc); + unsigned int partial = ctx->count % HEH_BLOCK_SIZE; + u8 *dst = (u8 *)&ctx->digest + partial; + + ctx->count += len; + + /* Finishing at least one block? */ + if (partial + len >= HEH_BLOCK_SIZE) { + + if (partial) { + /* Finish the pending block. */ + unsigned int n = HEH_BLOCK_SIZE - partial; + + len -= n; + do { + *dst++ ^= *src++; + } while (--n); + + gf128mul_4k_ble(&ctx->digest, tctx->tau_key); + } + + /* Process zero or more full blocks. */ + while (len >= HEH_BLOCK_SIZE) { + be128 coeff; + + memcpy(&coeff, src, HEH_BLOCK_SIZE); + be128_xor(&ctx->digest, &ctx->digest, &coeff); + src += HEH_BLOCK_SIZE; + len -= HEH_BLOCK_SIZE; + gf128mul_4k_ble(&ctx->digest, tctx->tau_key); + } + dst = (u8 *)&ctx->digest; + } + + /* Continue adding the next block to 'digest'. */ + while (len--) + *dst++ ^= *src++; + return 0; +} + +static int poly_hash_final(struct shash_desc *desc, u8 *out) +{ + struct poly_hash_desc_ctx *ctx = shash_desc_ctx(desc); + + /* Finish the last block if needed. */ + if (ctx->count % HEH_BLOCK_SIZE) { + struct poly_hash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + + gf128mul_4k_ble(&ctx->digest, tctx->tau_key); + } + + memcpy(out, &ctx->digest, HEH_BLOCK_SIZE); + return 0; +} + +static void poly_hash_exit(struct crypto_tfm *tfm) +{ + struct poly_hash_tfm_ctx *tctx = crypto_tfm_ctx(tfm); + + gf128mul_free_4k(tctx->tau_key); +} + +static struct shash_alg poly_hash_alg = { + .digestsize = HEH_BLOCK_SIZE, + .init = poly_hash_init, + .update = poly_hash_update, + .final = poly_hash_final, + .setkey = poly_hash_setkey, + .descsize = sizeof(struct poly_hash_desc_ctx), + .base = { + .cra_name = "poly_hash", + .cra_driver_name = "poly_hash-generic", + .cra_priority = 100, + .cra_ctxsize = sizeof(struct poly_hash_tfm_ctx), + .cra_exit = poly_hash_exit, + .cra_module = THIS_MODULE, + }, +}; + +/*****************************************************************************/ + +/* + * Split the message into 16 byte blocks, padding out the last block, and use + * the blocks as coefficients in the evaluation of a polynomial over GF(2^128) + * at the secret point 'tau_key'. For ease of implementing the higher-level + * heh_hash_inv() function, the constant and degree-1 coefficients are swapped + * if there is a partial block. + * + * Mathematically, compute: + * if (no partial block) + * k^{N-1} * m_0 + ... + k * m_{N-2} + m_{N-1} + * else if (partial block) + * k^N * m_0 + ... + k^2 * m_{N-2} + k * m_N + m_{N-1} + * + * where: + * t is tau_key + * N is the number of full blocks in the message + * m_i is the i-th full block in the message for i = 0 to N-1 inclusive + * m_N is the partial block of the message zero-padded up to 16 bytes + * + * Note that most of this is now separated out into its own keyed hash + * algorithm, to allow optimized implementations. However, we still handle the + * swapping of the last two coefficients here in the HEH template because this + * simplifies the poly_hash algorithms: they don't have to buffer an extra + * block, don't have to duplicate as much code, and are more similar to GHASH. + */ +static int poly_hash(struct ablkcipher_request *req, struct scatterlist *sgl, + be128 *hash) +{ + struct heh_req_ctx *rctx = heh_req_ctx(req); + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct heh_tfm_ctx *ctx = crypto_ablkcipher_ctx(tfm); + struct shash_desc *desc = &rctx->u.poly_hash.desc; + unsigned int tail_offset = get_tail_offset(req->nbytes); + unsigned int tail_len = req->nbytes - tail_offset; + be128 tail[2]; + unsigned int i, n; + struct sg_mapping_iter miter; + int err; + + desc->tfm = ctx->poly_hash; + desc->flags = req->base.flags; + + /* Handle all full blocks except the last */ + err = crypto_shash_init(desc); + sg_miter_start(&miter, sgl, sg_nents(sgl), + SG_MITER_FROM_SG | SG_MITER_ATOMIC); + for (i = 0; i < tail_offset && !err; i += n) { + sg_miter_next(&miter); + n = min_t(unsigned int, miter.length, tail_offset - i); + err = crypto_shash_update(desc, miter.addr, n); + } + sg_miter_stop(&miter); + if (err) + return err; + + /* Handle the last full block and the partial block */ + scatterwalk_map_and_copy(tail, sgl, tail_offset, tail_len, 0); + + if (tail_len != HEH_BLOCK_SIZE) { + /* handle the partial block */ + memset((u8 *)tail + tail_len, 0, sizeof(tail) - tail_len); + err = crypto_shash_update(desc, (u8 *)&tail[1], HEH_BLOCK_SIZE); + if (err) + return err; + } + err = crypto_shash_final(desc, (u8 *)hash); + if (err) + return err; + be128_xor(hash, hash, &tail[0]); + return 0; +} + +/* + * Transform all full blocks except the last. + * This is used by both the hash and inverse hash phases. + */ +static int heh_tfm_blocks(struct ablkcipher_request *req, + struct scatterlist *src_sgl, + struct scatterlist *dst_sgl, unsigned int len, + const be128 *hash, const be128 *beta_key) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct blkcipher_desc desc = { .flags = req->base.flags }; + struct blkcipher_walk walk; + be128 e = *beta_key; + int err; + unsigned int nbytes; + + blkcipher_walk_init(&walk, dst_sgl, src_sgl, len); + + err = blkcipher_ablkcipher_walk_virt(&desc, &walk, tfm); + + while ((nbytes = walk.nbytes)) { + const be128 *src = (be128 *)walk.src.virt.addr; + be128 *dst = (be128 *)walk.dst.virt.addr; + + do { + gf128mul_x_ble(&e, &e); + be128_xor(dst, src, hash); + be128_xor(dst, dst, &e); + src++; + dst++; + } while ((nbytes -= HEH_BLOCK_SIZE) >= HEH_BLOCK_SIZE); + err = blkcipher_walk_done(&desc, &walk, nbytes); + } + return err; +} + +/* + * The hash phase of HEH. Given a message, compute: + * + * (m_0 + H, ..., m_{N-2} + H, H, m_N) + (xb, x^2b, ..., x^{N-1}b, b, 0) + * + * where: + * N is the number of full blocks in the message + * m_i is the i-th full block in the message for i = 0 to N-1 inclusive + * m_N is the unpadded partial block, possibly empty + * H is the poly_hash() of the message, keyed by tau_key + * b is beta_key + * x is the element x in our representation of GF(2^128) + * + * Note that the partial block remains unchanged, but it does affect the result + * of poly_hash() and therefore the transformation of all the full blocks. + */ +static int heh_hash(struct ablkcipher_request *req, const be128 *beta_key) +{ + be128 hash; + unsigned int tail_offset = get_tail_offset(req->nbytes); + unsigned int partial_len = req->nbytes % HEH_BLOCK_SIZE; + int err; + + /* poly_hash() the full message including the partial block */ + err = poly_hash(req, req->src, &hash); + if (err) + return err; + + /* Transform all full blocks except the last */ + err = heh_tfm_blocks(req, req->src, req->dst, tail_offset, &hash, + beta_key); + if (err) + return err; + + /* Set the last full block to hash XOR beta_key */ + be128_xor(&hash, &hash, beta_key); + scatterwalk_map_and_copy(&hash, req->dst, tail_offset, HEH_BLOCK_SIZE, + 1); + + /* Copy the partial block if needed */ + if (partial_len != 0 && req->src != req->dst) { + unsigned int offs = tail_offset + HEH_BLOCK_SIZE; + + scatterwalk_map_and_copy(&hash, req->src, offs, partial_len, 0); + scatterwalk_map_and_copy(&hash, req->dst, offs, partial_len, 1); + } + return 0; +} + +/* + * The inverse hash phase of HEH. This undoes the result of heh_hash(). + */ +static int heh_hash_inv(struct ablkcipher_request *req, const be128 *beta_key) +{ + be128 hash; + be128 tmp; + struct scatterlist tmp_sgl[2]; + struct scatterlist *tail_sgl; + unsigned int tail_offset = get_tail_offset(req->nbytes); + struct scatterlist *sgl = req->dst; + int err; + + /* + * The last full block was computed as hash XOR beta_key, so XOR it with + * beta_key to recover hash. + */ + tail_sgl = scatterwalk_ffwd(tmp_sgl, sgl, tail_offset); + scatterwalk_map_and_copy(&hash, tail_sgl, 0, HEH_BLOCK_SIZE, 0); + be128_xor(&hash, &hash, beta_key); + + /* Transform all full blocks except the last */ + err = heh_tfm_blocks(req, sgl, sgl, tail_offset, &hash, beta_key); + if (err) + return err; + + /* + * Recover the last full block. We know 'hash', i.e. the poly_hash() of + * the the original message. The last full block was the constant term + * of the polynomial. To recover the last full block, temporarily zero + * it, compute the poly_hash(), and take the difference from 'hash'. + */ + memset(&tmp, 0, sizeof(tmp)); + scatterwalk_map_and_copy(&tmp, tail_sgl, 0, HEH_BLOCK_SIZE, 1); + err = poly_hash(req, sgl, &tmp); + if (err) + return err; + be128_xor(&tmp, &tmp, &hash); + scatterwalk_map_and_copy(&tmp, tail_sgl, 0, HEH_BLOCK_SIZE, 1); + return 0; +} + +static int heh_hash_inv_step(struct ablkcipher_request *req, u32 flags) +{ + struct heh_req_ctx *rctx = heh_req_ctx(req); + + return heh_hash_inv(req, &rctx->beta2_key); +} + +static int heh_ecb_step_3(struct ablkcipher_request *req, u32 flags) +{ + struct heh_req_ctx *rctx = heh_req_ctx(req); + u8 partial_block[HEH_BLOCK_SIZE] __aligned(__alignof__(u32)); + unsigned int tail_offset = get_tail_offset(req->nbytes); + unsigned int partial_offset = tail_offset + HEH_BLOCK_SIZE; + unsigned int partial_len = req->nbytes - partial_offset; + + /* + * Extract the pad in req->dst at tail_offset, and xor the partial block + * with it to create encrypted partial block + */ + scatterwalk_map_and_copy(rctx->u.ecb.keystream, req->dst, tail_offset, + HEH_BLOCK_SIZE, 0); + scatterwalk_map_and_copy(partial_block, req->dst, partial_offset, + partial_len, 0); + crypto_xor(partial_block, rctx->u.ecb.keystream, partial_len); + + /* + * Store the encrypted final block and partial block back in dst_sg + */ + scatterwalk_map_and_copy(&rctx->u.ecb.tmp, req->dst, tail_offset, + HEH_BLOCK_SIZE, 1); + scatterwalk_map_and_copy(partial_block, req->dst, partial_offset, + partial_len, 1); + + return heh_hash_inv_step(req, flags); +} + +static void heh_ecb_step_2_done(struct crypto_async_request *areq, int err) +{ + return async_done(areq, err, heh_ecb_step_3); +} + +static int heh_ecb_step_2(struct ablkcipher_request *req, u32 flags) +{ + struct heh_req_ctx *rctx = heh_req_ctx(req); + unsigned int partial_len = req->nbytes % HEH_BLOCK_SIZE; + struct scatterlist *tmp_sgl; + int err; + unsigned int tail_offset = get_tail_offset(req->nbytes); + + if (partial_len == 0) + return heh_hash_inv_step(req, flags); + + /* + * Extract the final full block, store it in tmp, and then xor that with + * the value saved in u.ecb.keystream + */ + scatterwalk_map_and_copy(rctx->u.ecb.tmp, req->dst, tail_offset, + HEH_BLOCK_SIZE, 0); + crypto_xor(rctx->u.ecb.keystream, rctx->u.ecb.tmp, HEH_BLOCK_SIZE); + + /* + * Encrypt the value in rctx->u.ecb.keystream to create the pad for the + * partial block. + * We cannot encrypt stack buffers, so re-use the dst_sg to do this + * encryption to avoid a malloc. The value at tail_offset is stored in + * tmp, and will be restored later. + */ + scatterwalk_map_and_copy(rctx->u.ecb.keystream, req->dst, tail_offset, + HEH_BLOCK_SIZE, 1); + tmp_sgl = scatterwalk_ffwd(rctx->u.ecb.tmp_sgl, req->dst, tail_offset); + ablkcipher_request_set_callback(&rctx->u.ecb.req, flags, + heh_ecb_step_2_done, req); + ablkcipher_request_set_crypt(&rctx->u.ecb.req, tmp_sgl, tmp_sgl, + HEH_BLOCK_SIZE, NULL); + err = crypto_ablkcipher_encrypt(&rctx->u.ecb.req); + if (err) + return err; + return heh_ecb_step_3(req, flags); +} + +static void heh_ecb_full_done(struct crypto_async_request *areq, int err) +{ + return async_done(areq, err, heh_ecb_step_2); +} + +/* + * The encrypt phase of HEH. This uses ECB encryption, with special handling + * for the partial block at the end if any. The source data is already in + * req->dst, so the encryption happens in-place. + * + * After the encrypt phase we continue on to the inverse hash phase. The + * functions calls are chained to support asynchronous ECB algorithms. + */ +static int heh_ecb(struct ablkcipher_request *req, bool decrypt) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct heh_tfm_ctx *ctx = crypto_ablkcipher_ctx(tfm); + struct heh_req_ctx *rctx = heh_req_ctx(req); + struct ablkcipher_request *ecb_req = &rctx->u.ecb.req; + unsigned int tail_offset = get_tail_offset(req->nbytes); + unsigned int full_len = tail_offset + HEH_BLOCK_SIZE; + int err; + + /* + * Save the last full block before it is encrypted/decrypted. This will + * be used later to encrypt/decrypt the partial block + */ + scatterwalk_map_and_copy(rctx->u.ecb.keystream, req->dst, tail_offset, + HEH_BLOCK_SIZE, 0); + + /* Encrypt/decrypt all full blocks */ + ablkcipher_request_set_tfm(ecb_req, ctx->ecb); + ablkcipher_request_set_callback(ecb_req, req->base.flags, + heh_ecb_full_done, req); + ablkcipher_request_set_crypt(ecb_req, req->dst, req->dst, full_len, + NULL); + if (decrypt) + err = crypto_ablkcipher_decrypt(ecb_req); + else + err = crypto_ablkcipher_encrypt(ecb_req); + if (err) + return err; + + return heh_ecb_step_2(req, req->base.flags); +} + +static int heh_crypt(struct ablkcipher_request *req, bool decrypt) +{ + struct heh_req_ctx *rctx = heh_req_ctx(req); + int err; + + /* Inputs must be at least one full block */ + if (req->nbytes < HEH_BLOCK_SIZE) + return -EINVAL; + + err = generate_betas(req, &rctx->beta1_key, &rctx->beta2_key); + if (err) + return err; + + if (decrypt) + swap(rctx->beta1_key, rctx->beta2_key); + + err = heh_hash(req, &rctx->beta1_key); + if (err) + return err; + + return heh_ecb(req, decrypt); +} + +static int heh_encrypt(struct ablkcipher_request *req) +{ + return heh_crypt(req, false); +} + +static int heh_decrypt(struct ablkcipher_request *req) +{ + return heh_crypt(req, true); +} + +static int heh_setkey(struct crypto_ablkcipher *parent, const u8 *key, + unsigned int keylen) +{ + struct heh_tfm_ctx *ctx = crypto_ablkcipher_ctx(parent); + struct crypto_shash *cmac = ctx->cmac; + struct crypto_ablkcipher *ecb = ctx->ecb; + SHASH_DESC_ON_STACK(desc, cmac); + u8 *derived_keys; + u8 digest[HEH_BLOCK_SIZE]; + unsigned int i; + int err; + + /* set prf_key = key */ + crypto_shash_clear_flags(cmac, CRYPTO_TFM_REQ_MASK); + crypto_shash_set_flags(cmac, crypto_ablkcipher_get_flags(parent) & + CRYPTO_TFM_REQ_MASK); + err = crypto_shash_setkey(cmac, key, keylen); + crypto_ablkcipher_set_flags(parent, crypto_shash_get_flags(cmac) & + CRYPTO_TFM_RES_MASK); + if (err) + return err; + + /* + * Generate tau_key and ecb_key as follows: + * tau_key = cmac(prf_key, 0x00...01) + * ecb_key = cmac(prf_key, 0x00...02) || cmac(prf_key, 0x00...03) || ... + * truncated to keylen bytes + */ + derived_keys = kzalloc(round_up(HEH_BLOCK_SIZE + keylen, + HEH_BLOCK_SIZE), GFP_KERNEL); + if (!derived_keys) + return -ENOMEM; + desc->tfm = cmac; + desc->flags = (crypto_shash_get_flags(cmac) & CRYPTO_TFM_REQ_MASK); + for (i = 0; i < keylen + HEH_BLOCK_SIZE; i += HEH_BLOCK_SIZE) { + derived_keys[i + HEH_BLOCK_SIZE - 1] = + 0x01 + i / HEH_BLOCK_SIZE; + err = crypto_shash_digest(desc, derived_keys + i, + HEH_BLOCK_SIZE, digest); + if (err) + goto out; + memcpy(derived_keys + i, digest, HEH_BLOCK_SIZE); + } + + err = crypto_shash_setkey(ctx->poly_hash, derived_keys, HEH_BLOCK_SIZE); + if (err) + goto out; + + crypto_ablkcipher_clear_flags(ecb, CRYPTO_TFM_REQ_MASK); + crypto_ablkcipher_set_flags(ecb, crypto_ablkcipher_get_flags(parent) & + CRYPTO_TFM_REQ_MASK); + err = crypto_ablkcipher_setkey(ecb, derived_keys + HEH_BLOCK_SIZE, + keylen); + crypto_ablkcipher_set_flags(parent, crypto_ablkcipher_get_flags(ecb) & + CRYPTO_TFM_RES_MASK); +out: + kzfree(derived_keys); + return err; +} + +static int heh_init_tfm(struct crypto_tfm *tfm) +{ + struct crypto_instance *inst = crypto_tfm_alg_instance(tfm); + struct heh_instance_ctx *ictx = crypto_instance_ctx(inst); + struct heh_tfm_ctx *ctx = crypto_tfm_ctx(tfm); + struct crypto_shash *cmac; + struct crypto_shash *poly_hash; + struct crypto_ablkcipher *ecb; + unsigned int reqsize; + int err; + + cmac = crypto_spawn_shash(&ictx->cmac); + if (IS_ERR(cmac)) + return PTR_ERR(cmac); + + poly_hash = crypto_spawn_shash(&ictx->poly_hash); + err = PTR_ERR(poly_hash); + if (IS_ERR(poly_hash)) + goto err_free_cmac; + + ecb = crypto_spawn_skcipher(&ictx->ecb); + err = PTR_ERR(ecb); + if (IS_ERR(ecb)) + goto err_free_poly_hash; + + ctx->cmac = cmac; + ctx->poly_hash = poly_hash; + ctx->ecb = ecb; + + reqsize = crypto_tfm_alg_alignmask(tfm) & + ~(crypto_tfm_ctx_alignment() - 1); + reqsize += max3(offsetof(struct heh_req_ctx, u.cmac.desc) + + sizeof(struct shash_desc) + + crypto_shash_descsize(cmac), + offsetof(struct heh_req_ctx, u.poly_hash.desc) + + sizeof(struct shash_desc) + + crypto_shash_descsize(poly_hash), + offsetof(struct heh_req_ctx, u.ecb.req) + + sizeof(struct ablkcipher_request) + + crypto_ablkcipher_reqsize(ecb)); + tfm->crt_ablkcipher.reqsize = reqsize; + + return 0; + +err_free_poly_hash: + crypto_free_shash(poly_hash); +err_free_cmac: + crypto_free_shash(cmac); + return err; +} + +static void heh_exit_tfm(struct crypto_tfm *tfm) +{ + struct heh_tfm_ctx *ctx = crypto_tfm_ctx(tfm); + + crypto_free_shash(ctx->cmac); + crypto_free_shash(ctx->poly_hash); + crypto_free_ablkcipher(ctx->ecb); +} + +static void heh_free_instance(struct crypto_instance *inst) +{ + struct heh_instance_ctx *ctx = crypto_instance_ctx(inst); + + crypto_drop_shash(&ctx->cmac); + crypto_drop_shash(&ctx->poly_hash); + crypto_drop_skcipher(&ctx->ecb); + kfree(inst); +} + +/* + * Create an instance of HEH as a ablkcipher. + * + * This relies on underlying CMAC and ECB algorithms, usually cmac(aes) and + * ecb(aes). For performance reasons we support asynchronous ECB algorithms. + * However, we do not yet support asynchronous CMAC algorithms because CMAC is + * only used on a small fixed amount of data per request, independent of the + * request length. This would change if AEAD or variable-length nonce support + * were to be exposed. + */ +static int heh_create_common(struct crypto_template *tmpl, struct rtattr **tb, + const char *full_name, const char *cmac_name, + const char *poly_hash_name, const char *ecb_name) +{ + struct crypto_attr_type *algt; + struct crypto_instance *inst; + struct heh_instance_ctx *ctx; + struct shash_alg *cmac; + struct shash_alg *poly_hash; + struct crypto_alg *ecb; + int err; + + algt = crypto_get_attr_type(tb); + if (IS_ERR(algt)) + return PTR_ERR(algt); + + /* User must be asking for something compatible with ablkcipher */ + if ((algt->type ^ CRYPTO_ALG_TYPE_ABLKCIPHER) & algt->mask) + return -EINVAL; + + /* Allocate the ablkcipher instance */ + inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL); + if (!inst) + return -ENOMEM; + + ctx = crypto_instance_ctx(inst); + + /* Set up the cmac spawn */ + ctx->cmac.base.inst = inst; + err = crypto_grab_shash(&ctx->cmac, cmac_name, 0, 0); + if (err) + goto err_free_inst; + cmac = crypto_spawn_shash_alg(&ctx->cmac); + err = -EINVAL; + if (cmac->digestsize != HEH_BLOCK_SIZE) + goto err_drop_cmac; + + /* Set up the poly_hash spawn */ + ctx->poly_hash.base.inst = inst; + err = crypto_grab_shash(&ctx->poly_hash, poly_hash_name, 0, 0); + if (err) + goto err_drop_cmac; + poly_hash = crypto_spawn_shash_alg(&ctx->poly_hash); + err = -EINVAL; + if (poly_hash->digestsize != HEH_BLOCK_SIZE) + goto err_drop_poly_hash; + + /* Set up the ecb spawn */ + ctx->ecb.base.inst = inst; + err = crypto_grab_skcipher(&ctx->ecb, ecb_name, 0, + crypto_requires_sync(algt->type, + algt->mask)); + if (err) + goto err_drop_poly_hash; + ecb = crypto_skcipher_spawn_alg(&ctx->ecb); + + /* HEH only supports block ciphers with 16 byte block size */ + err = -EINVAL; + if (ecb->cra_blocksize != HEH_BLOCK_SIZE) + goto err_drop_ecb; + + /* The underlying "ECB" algorithm must not require an IV */ + err = -EINVAL; + if ((ecb->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_BLKCIPHER) { + if (ecb->cra_blkcipher.ivsize != 0) + goto err_drop_ecb; + } else { + if (ecb->cra_ablkcipher.ivsize != 0) + goto err_drop_ecb; + } + + /* Set the instance names */ + err = -ENAMETOOLONG; + if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, + "heh_base(%s,%s,%s)", cmac->base.cra_driver_name, + poly_hash->base.cra_driver_name, + ecb->cra_driver_name) >= CRYPTO_MAX_ALG_NAME) + goto err_drop_ecb; + + err = -ENAMETOOLONG; + if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, + "%s", full_name) >= CRYPTO_MAX_ALG_NAME) + goto err_drop_ecb; + + /* Finish initializing the instance */ + + inst->alg.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | + (ecb->cra_flags & CRYPTO_ALG_ASYNC); + inst->alg.cra_blocksize = HEH_BLOCK_SIZE; + inst->alg.cra_ctxsize = sizeof(struct heh_tfm_ctx); + inst->alg.cra_alignmask = ecb->cra_alignmask | (__alignof__(be128) - 1); + inst->alg.cra_priority = ecb->cra_priority; + inst->alg.cra_type = &crypto_ablkcipher_type; + inst->alg.cra_init = heh_init_tfm; + inst->alg.cra_exit = heh_exit_tfm; + + inst->alg.cra_ablkcipher.setkey = heh_setkey; + inst->alg.cra_ablkcipher.encrypt = heh_encrypt; + inst->alg.cra_ablkcipher.decrypt = heh_decrypt; + if ((ecb->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_BLKCIPHER) { + inst->alg.cra_ablkcipher.min_keysize = ecb->cra_blkcipher.min_keysize; + inst->alg.cra_ablkcipher.max_keysize = ecb->cra_blkcipher.max_keysize; + } else { + inst->alg.cra_ablkcipher.min_keysize = ecb->cra_ablkcipher.min_keysize; + inst->alg.cra_ablkcipher.max_keysize = ecb->cra_ablkcipher.max_keysize; + } + inst->alg.cra_ablkcipher.ivsize = HEH_BLOCK_SIZE; + + /* Register the instance */ + err = crypto_register_instance(tmpl, inst); + if (err) + goto err_drop_ecb; + return 0; + +err_drop_ecb: + crypto_drop_skcipher(&ctx->ecb); +err_drop_poly_hash: + crypto_drop_shash(&ctx->poly_hash); +err_drop_cmac: + crypto_drop_shash(&ctx->cmac); +err_free_inst: + kfree(inst); + return err; +} + +static int heh_create(struct crypto_template *tmpl, struct rtattr **tb) +{ + const char *cipher_name; + char full_name[CRYPTO_MAX_ALG_NAME]; + char cmac_name[CRYPTO_MAX_ALG_NAME]; + char ecb_name[CRYPTO_MAX_ALG_NAME]; + + /* Get the name of the requested block cipher (e.g. aes) */ + cipher_name = crypto_attr_alg_name(tb[1]); + if (IS_ERR(cipher_name)) + return PTR_ERR(cipher_name); + + if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "heh(%s)", cipher_name) >= + CRYPTO_MAX_ALG_NAME) + return -ENAMETOOLONG; + + if (snprintf(cmac_name, CRYPTO_MAX_ALG_NAME, "cmac(%s)", cipher_name) >= + CRYPTO_MAX_ALG_NAME) + return -ENAMETOOLONG; + + if (snprintf(ecb_name, CRYPTO_MAX_ALG_NAME, "ecb(%s)", cipher_name) >= + CRYPTO_MAX_ALG_NAME) + return -ENAMETOOLONG; + + return heh_create_common(tmpl, tb, full_name, cmac_name, "poly_hash", + ecb_name); +} + +static struct crypto_template heh_tmpl = { + .name = "heh", + .create = heh_create, + .free = heh_free_instance, + .module = THIS_MODULE, +}; + +static int heh_base_create(struct crypto_template *tmpl, struct rtattr **tb) +{ + char full_name[CRYPTO_MAX_ALG_NAME]; + const char *cmac_name; + const char *poly_hash_name; + const char *ecb_name; + + cmac_name = crypto_attr_alg_name(tb[1]); + if (IS_ERR(cmac_name)) + return PTR_ERR(cmac_name); + + poly_hash_name = crypto_attr_alg_name(tb[2]); + if (IS_ERR(poly_hash_name)) + return PTR_ERR(poly_hash_name); + + ecb_name = crypto_attr_alg_name(tb[3]); + if (IS_ERR(ecb_name)) + return PTR_ERR(ecb_name); + + if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "heh_base(%s,%s,%s)", + cmac_name, poly_hash_name, ecb_name) >= + CRYPTO_MAX_ALG_NAME) + return -ENAMETOOLONG; + + return heh_create_common(tmpl, tb, full_name, cmac_name, poly_hash_name, + ecb_name); +} + +/* + * If HEH is instantiated as "heh_base" instead of "heh", then specific + * implementations of cmac, poly_hash, and ecb can be specified instead of just + * the cipher. + */ +static struct crypto_template heh_base_tmpl = { + .name = "heh_base", + .create = heh_base_create, + .free = heh_free_instance, + .module = THIS_MODULE, +}; + +static int __init heh_module_init(void) +{ + int err; + + err = crypto_register_template(&heh_tmpl); + if (err) + return err; + + err = crypto_register_template(&heh_base_tmpl); + if (err) + goto out_undo_heh; + + err = crypto_register_shash(&poly_hash_alg); + if (err) + goto out_undo_heh_base; + + return 0; + +out_undo_heh_base: + crypto_unregister_template(&heh_base_tmpl); +out_undo_heh: + crypto_unregister_template(&heh_tmpl); + return err; +} + +static void __exit heh_module_exit(void) +{ + crypto_unregister_template(&heh_tmpl); + crypto_unregister_template(&heh_base_tmpl); + crypto_unregister_shash(&poly_hash_alg); +} + +module_init(heh_module_init); +module_exit(heh_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Hash-Encrypt-Hash block cipher mode"); +MODULE_ALIAS_CRYPTO("heh"); +MODULE_ALIAS_CRYPTO("heh_base"); diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c index a0ceb41d5ccc..b4f3930266b1 100644 --- a/crypto/mcryptd.c +++ b/crypto/mcryptd.c @@ -531,6 +531,7 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb, inst->alg.halg.base.cra_flags = type; inst->alg.halg.digestsize = salg->digestsize; + inst->alg.halg.statesize = salg->statesize; inst->alg.halg.base.cra_ctxsize = sizeof(struct mcryptd_hash_ctx); inst->alg.halg.base.cra_init = mcryptd_hash_init_tfm; diff --git a/crypto/shash.c b/crypto/shash.c index 359754591653..9ae1e891308d 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -683,6 +683,14 @@ void shash_free_instance(struct crypto_instance *inst) } EXPORT_SYMBOL_GPL(shash_free_instance); +int crypto_grab_shash(struct crypto_shash_spawn *spawn, + const char *name, u32 type, u32 mask) +{ + spawn->base.frontend = &crypto_shash_type; + return crypto_grab_spawn(&spawn->base, name, type, mask); +} +EXPORT_SYMBOL_GPL(crypto_grab_shash); + int crypto_init_shash_spawn(struct crypto_shash_spawn *spawn, struct shash_alg *alg, struct crypto_instance *inst) diff --git a/crypto/testmgr.c b/crypto/testmgr.c index d4944318ca1f..6d4da8fd24fd 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -488,6 +488,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc, aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, tcrypt_complete, &result); + iv_len = crypto_aead_ivsize(tfm); + for (i = 0, j = 0; i < tcount; i++) { if (template[i].np) continue; @@ -508,7 +510,6 @@ static int __test_aead(struct crypto_aead *tfm, int enc, memcpy(input, template[i].input, template[i].ilen); memcpy(assoc, template[i].assoc, template[i].alen); - iv_len = crypto_aead_ivsize(tfm); if (template[i].iv) memcpy(iv, template[i].iv, iv_len); else @@ -617,7 +618,7 @@ static int __test_aead(struct crypto_aead *tfm, int enc, j++; if (template[i].iv) - memcpy(iv, template[i].iv, MAX_IVLEN); + memcpy(iv, template[i].iv, iv_len); else memset(iv, 0, MAX_IVLEN); @@ -3214,6 +3215,21 @@ static const struct alg_test_desc alg_test_descs[] = { } } }, { + .alg = "heh(aes)", + .test = alg_test_skcipher, + .suite = { + .cipher = { + .enc = { + .vecs = aes_heh_enc_tv_template, + .count = AES_HEH_ENC_TEST_VECTORS + }, + .dec = { + .vecs = aes_heh_dec_tv_template, + .count = AES_HEH_DEC_TEST_VECTORS + } + } + } + }, { .alg = "hmac(crc32)", .test = alg_test_hash, .suite = { diff --git a/crypto/testmgr.h b/crypto/testmgr.h index da0a8fd765f4..ba6530d8ba58 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -14139,6 +14139,8 @@ static struct cipher_testvec cast6_xts_dec_tv_template[] = { #define AES_DEC_TEST_VECTORS 4 #define AES_CBC_ENC_TEST_VECTORS 5 #define AES_CBC_DEC_TEST_VECTORS 5 +#define AES_HEH_ENC_TEST_VECTORS 4 +#define AES_HEH_DEC_TEST_VECTORS 4 #define HMAC_MD5_ECB_CIPHER_NULL_ENC_TEST_VECTORS 2 #define HMAC_MD5_ECB_CIPHER_NULL_DEC_TEST_VECTORS 2 #define HMAC_SHA1_ECB_CIPHER_NULL_ENC_TEST_VEC 2 @@ -14511,6 +14513,198 @@ static struct cipher_testvec aes_dec_tv_template[] = { }, }; +static struct cipher_testvec aes_heh_enc_tv_template[] = { + { + .key = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .klen = 16, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .ilen = 16, + .result = "\xd8\xbd\x40\xbf\xca\xe5\xee\x81" + "\x0f\x3d\x1f\x1f\xae\x89\x07\x55", + .rlen = 16, + .also_non_np = 1, + .np = 2, + .tap = { 8, 8 }, + }, { + .key = "\xa8\xda\x24\x9b\x5e\xfa\x13\xc2" + "\xc1\x94\xbf\x32\xba\x38\xa3\x77", + .klen = 16, + .iv = "\x4d\x47\x61\x37\x2b\x47\x86\xf0" + "\xd6\x47\xb5\xc2\xe8\xcf\x85\x27", + .input = "\xb8\xee\x29\xe4\xa5\xd1\xe7\x55" + "\xd0\xfd\xe7\x22\x63\x76\x36\xe2" + "\xf8\x0c\xf8\xfe\x65\x76\xe7\xca" + "\xc1\x42\xf5\xca\x5a\xa8\xac\x2a", + .ilen = 32, + .result = "\x59\xf2\x78\x4e\x10\x94\xf9\x5c" + "\x22\x23\x78\x2a\x30\x48\x11\x97" + "\xb1\xfe\x70\xc4\xef\xdf\x04\xef" + "\x16\x39\x04\xcf\xc0\x95\x9a\x98", + .rlen = 32, + .also_non_np = 1, + .np = 3, + .tap = { 16, 13, 3 }, + }, { + .key = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .klen = 16, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00", + .ilen = 63, + .result = "\xe0\x40\xeb\xe9\x52\xbe\x65\x60" + "\xe4\x68\x68\xa3\x73\x75\xb8\x52" + "\xef\x38\x6a\x87\x25\x25\xf6\x04" + "\xe5\x8e\xbe\x14\x8b\x02\x14\x1f" + "\xa9\x73\xb7\xad\x15\xbe\x9c\xa0" + "\xd2\x8a\x2c\xdc\xd4\xe3\x05\x55" + "\x0a\xf5\xf8\x51\xee\xe5\x62\xa5" + "\x71\xa7\x7c\x15\x5d\x7a\x9e", + .rlen = 63, + .also_non_np = 1, + .np = 8, + .tap = { 20, 20, 10, 8, 2, 1, 1, 1 }, + }, { + .key = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F" + "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F" + "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .klen = 16, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x01" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00", + .ilen = 63, + .result = "\x4b\x1a\x15\xa0\xaf\x08\x6d\x70" + "\xf0\xa7\x97\xb5\x31\x4b\x8c\xc3" + "\x4d\xf2\x7a\x9d\xdd\xd4\x15\x99" + "\x57\xad\xc6\xb1\x35\x69\xf5\x6a" + "\x2d\x70\xe4\x97\x49\xb2\x9f\x71" + "\xde\x22\xb5\x70\x8c\x69\x24\xd3" + "\xad\x80\x58\x48\x90\xe4\xed\xba" + "\x76\x3d\x71\x7c\x57\x25\x87", + .rlen = 63, + .also_non_np = 1, + .np = 8, + .tap = { 20, 20, 10, 8, 2, 1, 1, 1 }, + } +}; + +static struct cipher_testvec aes_heh_dec_tv_template[] = { + { + .key = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .klen = 16, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\xd8\xbd\x40\xbf\xca\xe5\xee\x81" + "\x0f\x3d\x1f\x1f\xae\x89\x07\x55", + .ilen = 16, + .result = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .rlen = 16, + .also_non_np = 1, + .np = 2, + .tap = { 8, 8 }, + }, { + .key = "\xa8\xda\x24\x9b\x5e\xfa\x13\xc2" + "\xc1\x94\xbf\x32\xba\x38\xa3\x77", + .klen = 16, + .iv = "\x4d\x47\x61\x37\x2b\x47\x86\xf0" + "\xd6\x47\xb5\xc2\xe8\xcf\x85\x27", + .input = "\x59\xf2\x78\x4e\x10\x94\xf9\x5c" + "\x22\x23\x78\x2a\x30\x48\x11\x97" + "\xb1\xfe\x70\xc4\xef\xdf\x04\xef" + "\x16\x39\x04\xcf\xc0\x95\x9a\x98", + .ilen = 32, + .result = "\xb8\xee\x29\xe4\xa5\xd1\xe7\x55" + "\xd0\xfd\xe7\x22\x63\x76\x36\xe2" + "\xf8\x0c\xf8\xfe\x65\x76\xe7\xca" + "\xc1\x42\xf5\xca\x5a\xa8\xac\x2a", + .rlen = 32, + .also_non_np = 1, + .np = 3, + .tap = { 16, 13, 3 }, + }, { + .key = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .klen = 16, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\xe0\x40\xeb\xe9\x52\xbe\x65\x60" + "\xe4\x68\x68\xa3\x73\x75\xb8\x52" + "\xef\x38\x6a\x87\x25\x25\xf6\x04" + "\xe5\x8e\xbe\x14\x8b\x02\x14\x1f" + "\xa9\x73\xb7\xad\x15\xbe\x9c\xa0" + "\xd2\x8a\x2c\xdc\xd4\xe3\x05\x55" + "\x0a\xf5\xf8\x51\xee\xe5\x62\xa5" + "\x71\xa7\x7c\x15\x5d\x7a\x9e", + .ilen = 63, + .result = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00", + .rlen = 63, + .also_non_np = 1, + .np = 8, + .tap = { 20, 20, 10, 8, 2, 1, 1, 1 }, + }, { + .key = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F" + "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F" + "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F", + .klen = 16, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x4b\x1a\x15\xa0\xaf\x08\x6d\x70" + "\xf0\xa7\x97\xb5\x31\x4b\x8c\xc3" + "\x4d\xf2\x7a\x9d\xdd\xd4\x15\x99" + "\x57\xad\xc6\xb1\x35\x69\xf5\x6a" + "\x2d\x70\xe4\x97\x49\xb2\x9f\x71" + "\xde\x22\xb5\x70\x8c\x69\x24\xd3" + "\xad\x80\x58\x48\x90\xe4\xed\xba" + "\x76\x3d\x71\x7c\x57\x25\x87", + .ilen = 63, + .result = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x01" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00", + .rlen = 63, + .also_non_np = 1, + .np = 8, + .tap = { 20, 20, 10, 8, 2, 1, 1, 1 }, + } +}; + static struct cipher_testvec aes_cbc_enc_tv_template[] = { { /* From RFC 3602 */ .key = "\x06\xa9\x21\x40\x36\xb8\xa1\x5b" @@ -21778,7 +21972,7 @@ static struct aead_testvec aes_ccm_enc_tv_template[] = { "\x09\x75\x9a\x9b\x3c\x9b\x27\x39", .klen = 32, .iv = "\x03\xf9\xd9\x4e\x63\xb5\x3d\x9d" - "\x43\xf6\x1e\x50", + "\x43\xf6\x1e\x50\0\0\0\0", .assoc = "\x57\xf5\x6b\x8b\x57\x5c\x3d\x3b" "\x13\x02\x01\x0c\x83\x4c\x96\x35" "\x8e\xd6\x39\xcf\x7d\x14\x9b\x94" diff --git a/drivers/Makefile b/drivers/Makefile index 303512561cec..1d70931d6752 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -102,6 +102,7 @@ obj-$(CONFIG_USB_PHY) += usb/ obj-$(CONFIG_USB) += usb/ obj-$(CONFIG_PCI) += usb/ obj-$(CONFIG_USB_GADGET) += usb/ +obj-$(CONFIG_OF) += usb/ obj-$(CONFIG_SERIO) += input/serio/ obj-$(CONFIG_GAMEPORT) += input/gameport/ obj-$(CONFIG_INPUT) += input/ diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 675eaf337178..b9cebca376f9 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -2,7 +2,6 @@ # Makefile for the Linux ACPI interpreter # -ccflags-y := -Os ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT # diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index b6f7fa3a1d40..8d075d8fd8bf 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -24,9 +24,11 @@ ACPI_MODULE_NAME("platform"); static const struct acpi_device_id forbidden_id_list[] = { - {"PNP0000", 0}, /* PIC */ - {"PNP0100", 0}, /* Timer */ - {"PNP0200", 0}, /* AT DMA Controller */ + {"PNP0000", 0}, /* PIC */ + {"PNP0100", 0}, /* Timer */ + {"PNP0200", 0}, /* AT DMA Controller */ + {"ACPI0009", 0}, /* IOxAPIC */ + {"ACPI000A", 0}, /* IOAPIC */ {"", 0}, }; diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 5fdac394207a..549cdbed7b0e 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -1211,6 +1211,9 @@ static int acpi_video_device_enumerate(struct acpi_video_bus *video) union acpi_object *dod = NULL; union acpi_object *obj; + if (!video->cap._DOD) + return AE_NOT_EXIST; + status = acpi_evaluate_object(video->device->handle, "_DOD", NULL, &buffer); if (!ACPI_SUCCESS(status)) { ACPI_EXCEPTION((AE_INFO, status, "Evaluating _DOD")); diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c index 96809cd99ace..2f24b578bcaf 100644 --- a/drivers/acpi/blacklist.c +++ b/drivers/acpi/blacklist.c @@ -346,6 +346,34 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9343"), }, }, + { + .callback = dmi_enable_rev_override, + .ident = "DELL Precision 5520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision 5520"), + }, + }, + { + .callback = dmi_enable_rev_override, + .ident = "DELL Precision 3520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3520"), + }, + }, + /* + * Resolves a quirk with the Dell Latitude 3350 that + * causes the ethernet adapter to not function. + */ + { + .callback = dmi_enable_rev_override, + .ident = "DELL Latitude 3350", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3350"), + }, + }, #endif {} }; diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 5ea5dc219f56..73c9c7fa9001 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -98,7 +98,15 @@ static int find_child_checks(struct acpi_device *adev, bool check_children) if (check_children && list_empty(&adev->children)) return -ENODEV; - return sta_present ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE; + /* + * If the device has a _HID (or _CID) returning a valid ACPI/PNP + * device ID, it is better to make it look less attractive here, so that + * the other device with the same _ADR value (that may not have a valid + * device ID) can be matched going forward. [This means a second spec + * violation in a row, so whatever we do here is best effort anyway.] + */ + return sta_present && list_empty(&adev->pnp.ids) ? + FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE; } struct acpi_device *acpi_find_child_device(struct acpi_device *parent, diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index c097f477c74c..67d7489ced01 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -965,7 +965,7 @@ static size_t sizeof_nfit_set_info(int num_mappings) + num_mappings * sizeof(struct nfit_set_info_map); } -static int cmp_map(const void *m0, const void *m1) +static int cmp_map_compat(const void *m0, const void *m1) { const struct nfit_set_info_map *map0 = m0; const struct nfit_set_info_map *map1 = m1; @@ -974,6 +974,18 @@ static int cmp_map(const void *m0, const void *m1) sizeof(u64)); } +static int cmp_map(const void *m0, const void *m1) +{ + const struct nfit_set_info_map *map0 = m0; + const struct nfit_set_info_map *map1 = m1; + + if (map0->region_offset < map1->region_offset) + return -1; + else if (map0->region_offset > map1->region_offset) + return 1; + return 0; +} + /* Retrieve the nth entry referencing this spa */ static struct acpi_nfit_memory_map *memdev_from_spa( struct acpi_nfit_desc *acpi_desc, u16 range_index, int n) @@ -1029,6 +1041,12 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc, sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map), cmp_map, NULL); nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0); + + /* support namespaces created with the wrong sort order */ + sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map), + cmp_map_compat, NULL); + nd_set->altcookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0); + ndr_desc->nd_set = nd_set; devm_kfree(dev, info); diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index fcd4ce6f78d5..1c2b846c5776 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -200,6 +200,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return -EINVAL; /* The state of the list is 'on' IFF all resources are 'on'. */ + cur_state = 0; list_for_each_entry(entry, list, node) { struct acpi_power_resource *resource = entry->resource; acpi_handle handle = resource->device.handle; diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig index a82fc022d34b..4d4cdc1a6e25 100644 --- a/drivers/android/Kconfig +++ b/drivers/android/Kconfig @@ -22,7 +22,7 @@ config ANDROID_BINDER_IPC config ANDROID_BINDER_DEVICES string "Android Binder devices" depends on ANDROID_BINDER_IPC - default "binder" + default "binder,hwbinder,vndbinder" ---help--- Default value for the binder.devices parameter. diff --git a/drivers/android/binder.c b/drivers/android/binder.c index a4a4268ff53e..48cae6cb9b7b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -18,6 +18,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/cacheflush.h> +#include <linux/atomic.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/freezer.h> @@ -46,19 +47,11 @@ #include <uapi/linux/android/binder.h> #include "binder_trace.h" -static DEFINE_MUTEX(binder_main_lock); -static DEFINE_MUTEX(binder_deferred_lock); -static DEFINE_MUTEX(binder_mmap_lock); - static HLIST_HEAD(binder_devices); -static HLIST_HEAD(binder_procs); -static HLIST_HEAD(binder_deferred_list); -static HLIST_HEAD(binder_dead_nodes); static struct dentry *binder_debugfs_dir_entry_root; static struct dentry *binder_debugfs_dir_entry_proc; -static int binder_last_id; -static struct workqueue_struct *binder_deferred_workqueue; +atomic_t binder_last_id; #define BINDER_DEBUG_ENTRY(name) \ static int binder_##name##_open(struct inode *inode, struct file *file) \ @@ -173,20 +166,24 @@ enum binder_stat_types { struct binder_stats { int br[_IOC_NR(BR_FAILED_REPLY) + 1]; int bc[_IOC_NR(BC_REPLY_SG) + 1]; - int obj_created[BINDER_STAT_COUNT]; - int obj_deleted[BINDER_STAT_COUNT]; }; -static struct binder_stats binder_stats; +/* These are still global, since it's not always easy to get the context */ +struct binder_obj_stats { + atomic_t obj_created[BINDER_STAT_COUNT]; + atomic_t obj_deleted[BINDER_STAT_COUNT]; +}; + +static struct binder_obj_stats binder_obj_stats; static inline void binder_stats_deleted(enum binder_stat_types type) { - binder_stats.obj_deleted[type]++; + atomic_inc(&binder_obj_stats.obj_deleted[type]); } static inline void binder_stats_created(enum binder_stat_types type) { - binder_stats.obj_created[type]++; + atomic_inc(&binder_obj_stats.obj_created[type]); } struct binder_transaction_log_entry { @@ -207,8 +204,6 @@ struct binder_transaction_log { int full; struct binder_transaction_log_entry entry[32]; }; -static struct binder_transaction_log binder_transaction_log; -static struct binder_transaction_log binder_transaction_log_failed; static struct binder_transaction_log_entry *binder_transaction_log_add( struct binder_transaction_log *log) @@ -229,6 +224,21 @@ struct binder_context { struct binder_node *binder_context_mgr_node; kuid_t binder_context_mgr_uid; const char *name; + + struct mutex binder_main_lock; + struct mutex binder_deferred_lock; + struct mutex binder_mmap_lock; + + struct hlist_head binder_procs; + struct hlist_head binder_dead_nodes; + struct hlist_head binder_deferred_list; + + struct work_struct deferred_work; + struct workqueue_struct *binder_deferred_workqueue; + struct binder_transaction_log transaction_log; + struct binder_transaction_log transaction_log_failed; + + struct binder_stats binder_stats; }; struct binder_device { @@ -451,17 +461,18 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd) return retval; } -static inline void binder_lock(const char *tag) +static inline void binder_lock(struct binder_context *context, const char *tag) { trace_binder_lock(tag); - mutex_lock(&binder_main_lock); + mutex_lock(&context->binder_main_lock); trace_binder_locked(tag); } -static inline void binder_unlock(const char *tag) +static inline void binder_unlock(struct binder_context *context, + const char *tag) { trace_binder_unlock(tag); - mutex_unlock(&binder_main_lock); + mutex_unlock(&context->binder_main_lock); } static void binder_set_nice(long nice) @@ -946,7 +957,7 @@ static struct binder_node *binder_new_node(struct binder_proc *proc, binder_stats_created(BINDER_STAT_NODE); rb_link_node(&node->rb_node, parent, p); rb_insert_color(&node->rb_node, &proc->nodes); - node->debug_id = ++binder_last_id; + node->debug_id = atomic_inc_return(&binder_last_id); node->proc = proc; node->ptr = ptr; node->cookie = cookie; @@ -1088,7 +1099,7 @@ static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc, if (new_ref == NULL) return NULL; binder_stats_created(BINDER_STAT_REF); - new_ref->debug_id = ++binder_last_id; + new_ref->debug_id = atomic_inc_return(&binder_last_id); new_ref->proc = proc; new_ref->node = node; rb_link_node(&new_ref->rb_node_node, parent, p); @@ -1849,7 +1860,7 @@ static void binder_transaction(struct binder_proc *proc, binder_size_t last_fixup_min_off = 0; struct binder_context *context = proc->context; - e = binder_transaction_log_add(&binder_transaction_log); + e = binder_transaction_log_add(&context->transaction_log); e->call_type = reply ? 2 : !!(tr->flags & TF_ONE_WAY); e->from_proc = proc->pid; e->from_thread = thread->pid; @@ -1971,7 +1982,7 @@ static void binder_transaction(struct binder_proc *proc, } binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE); - t->debug_id = ++binder_last_id; + t->debug_id = atomic_inc_return(&binder_last_id); e->debug_id = t->debug_id; if (reply) @@ -2048,7 +2059,7 @@ static void binder_transaction(struct binder_proc *proc, if (!IS_ALIGNED(extra_buffers_size, sizeof(u64))) { binder_user_error("%d:%d got transaction with unaligned buffers size, %lld\n", proc->pid, thread->pid, - extra_buffers_size); + (u64)extra_buffers_size); return_error = BR_FAILED_REPLY; goto err_bad_offset; } @@ -2235,7 +2246,8 @@ err_no_context_mgr_node: { struct binder_transaction_log_entry *fe; - fe = binder_transaction_log_add(&binder_transaction_log_failed); + fe = binder_transaction_log_add( + &context->transaction_log_failed); *fe = *e; } @@ -2263,8 +2275,8 @@ static int binder_thread_write(struct binder_proc *proc, return -EFAULT; ptr += sizeof(uint32_t); trace_binder_command(cmd); - if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.bc)) { - binder_stats.bc[_IOC_NR(cmd)]++; + if (_IOC_NR(cmd) < ARRAY_SIZE(context->binder_stats.bc)) { + context->binder_stats.bc[_IOC_NR(cmd)]++; proc->stats.bc[_IOC_NR(cmd)]++; thread->stats.bc[_IOC_NR(cmd)]++; } @@ -2629,8 +2641,8 @@ static void binder_stat_br(struct binder_proc *proc, struct binder_thread *thread, uint32_t cmd) { trace_binder_return(cmd); - if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.br)) { - binder_stats.br[_IOC_NR(cmd)]++; + if (_IOC_NR(cmd) < ARRAY_SIZE(proc->stats.br)) { + proc->context->binder_stats.br[_IOC_NR(cmd)]++; proc->stats.br[_IOC_NR(cmd)]++; thread->stats.br[_IOC_NR(cmd)]++; } @@ -2694,7 +2706,7 @@ retry: if (wait_for_proc_work) proc->ready_threads++; - binder_unlock(__func__); + binder_unlock(proc->context, __func__); trace_binder_wait_for_work(wait_for_proc_work, !!thread->transaction_stack, @@ -2721,7 +2733,7 @@ retry: ret = wait_event_freezable(thread->wait, binder_has_thread_work(thread)); } - binder_lock(__func__); + binder_lock(proc->context, __func__); if (wait_for_proc_work) proc->ready_threads--; @@ -3108,14 +3120,14 @@ static unsigned int binder_poll(struct file *filp, struct binder_thread *thread = NULL; int wait_for_proc_work; - binder_lock(__func__); + binder_lock(proc->context, __func__); thread = binder_get_thread(proc); wait_for_proc_work = thread->transaction_stack == NULL && list_empty(&thread->todo) && thread->return_error == BR_OK; - binder_unlock(__func__); + binder_unlock(proc->context, __func__); if (wait_for_proc_work) { if (binder_has_proc_work(proc, thread)) @@ -3242,6 +3254,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int ret; struct binder_proc *proc = filp->private_data; + struct binder_context *context = proc->context; struct binder_thread *thread; unsigned int size = _IOC_SIZE(cmd); void __user *ubuf = (void __user *)arg; @@ -3255,7 +3268,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (ret) goto err_unlocked; - binder_lock(__func__); + binder_lock(context, __func__); thread = binder_get_thread(proc); if (thread == NULL) { ret = -ENOMEM; @@ -3307,7 +3320,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) err: if (thread) thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN; - binder_unlock(__func__); + binder_unlock(context, __func__); wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2); if (ret && ret != -ERESTARTSYS) pr_info("%d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret); @@ -3360,7 +3373,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) const char *failure_string; struct binder_buffer *buffer; - if (proc->tsk != current) + if (proc->tsk != current->group_leader) return -EINVAL; if ((vma->vm_end - vma->vm_start) > SZ_4M) @@ -3379,7 +3392,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) } vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE; - mutex_lock(&binder_mmap_lock); + mutex_lock(&proc->context->binder_mmap_lock); if (proc->buffer) { ret = -EBUSY; failure_string = "already mapped"; @@ -3394,7 +3407,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) } proc->buffer = area->addr; proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer; - mutex_unlock(&binder_mmap_lock); + mutex_unlock(&proc->context->binder_mmap_lock); #ifdef CONFIG_CPU_CACHE_VIPT if (cache_is_vipt_aliasing()) { @@ -3439,12 +3452,12 @@ err_alloc_small_buf_failed: kfree(proc->pages); proc->pages = NULL; err_alloc_pages_failed: - mutex_lock(&binder_mmap_lock); + mutex_lock(&proc->context->binder_mmap_lock); vfree(proc->buffer); proc->buffer = NULL; err_get_vm_area_failed: err_already_mapped: - mutex_unlock(&binder_mmap_lock); + mutex_unlock(&proc->context->binder_mmap_lock); err_bad_arg: pr_err("binder_mmap: %d %lx-%lx %s failed %d\n", proc->pid, vma->vm_start, vma->vm_end, failure_string, ret); @@ -3462,8 +3475,8 @@ static int binder_open(struct inode *nodp, struct file *filp) proc = kzalloc(sizeof(*proc), GFP_KERNEL); if (proc == NULL) return -ENOMEM; - get_task_struct(current); - proc->tsk = current; + get_task_struct(current->group_leader); + proc->tsk = current->group_leader; INIT_LIST_HEAD(&proc->todo); init_waitqueue_head(&proc->wait); proc->default_priority = task_nice(current); @@ -3471,15 +3484,15 @@ static int binder_open(struct inode *nodp, struct file *filp) miscdev); proc->context = &binder_dev->context; - binder_lock(__func__); + binder_lock(proc->context, __func__); binder_stats_created(BINDER_STAT_PROC); - hlist_add_head(&proc->proc_node, &binder_procs); + hlist_add_head(&proc->proc_node, &proc->context->binder_procs); proc->pid = current->group_leader->pid; INIT_LIST_HEAD(&proc->delivered_death); filp->private_data = proc; - binder_unlock(__func__); + binder_unlock(proc->context, __func__); if (binder_debugfs_dir_entry_proc) { char strbuf[11]; @@ -3544,6 +3557,7 @@ static int binder_release(struct inode *nodp, struct file *filp) static int binder_node_release(struct binder_node *node, int refs) { struct binder_ref *ref; + struct binder_context *context = node->proc->context; int death = 0; list_del_init(&node->work.entry); @@ -3559,7 +3573,7 @@ static int binder_node_release(struct binder_node *node, int refs) node->proc = NULL; node->local_strong_refs = 0; node->local_weak_refs = 0; - hlist_add_head(&node->dead_node, &binder_dead_nodes); + hlist_add_head(&node->dead_node, &context->binder_dead_nodes); hlist_for_each_entry(ref, &node->refs, node_entry) { refs++; @@ -3624,7 +3638,8 @@ static void binder_deferred_release(struct binder_proc *proc) node = rb_entry(n, struct binder_node, rb_node); nodes++; rb_erase(&node->rb_node, &proc->nodes); - incoming_refs = binder_node_release(node, incoming_refs); + incoming_refs = binder_node_release(node, + incoming_refs); } outgoing_refs = 0; @@ -3696,14 +3711,16 @@ static void binder_deferred_func(struct work_struct *work) { struct binder_proc *proc; struct files_struct *files; + struct binder_context *context = + container_of(work, struct binder_context, deferred_work); int defer; do { - binder_lock(__func__); - mutex_lock(&binder_deferred_lock); - if (!hlist_empty(&binder_deferred_list)) { - proc = hlist_entry(binder_deferred_list.first, + binder_lock(context, __func__); + mutex_lock(&context->binder_deferred_lock); + if (!hlist_empty(&context->binder_deferred_list)) { + proc = hlist_entry(context->binder_deferred_list.first, struct binder_proc, deferred_work_node); hlist_del_init(&proc->deferred_work_node); defer = proc->deferred_work; @@ -3712,7 +3729,7 @@ static void binder_deferred_func(struct work_struct *work) proc = NULL; defer = 0; } - mutex_unlock(&binder_deferred_lock); + mutex_unlock(&context->binder_deferred_lock); files = NULL; if (defer & BINDER_DEFERRED_PUT_FILES) { @@ -3727,24 +3744,24 @@ static void binder_deferred_func(struct work_struct *work) if (defer & BINDER_DEFERRED_RELEASE) binder_deferred_release(proc); /* frees proc */ - binder_unlock(__func__); + binder_unlock(context, __func__); if (files) put_files_struct(files); } while (proc); } -static DECLARE_WORK(binder_deferred_work, binder_deferred_func); static void binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer) { - mutex_lock(&binder_deferred_lock); + mutex_lock(&proc->context->binder_deferred_lock); proc->deferred_work |= defer; if (hlist_unhashed(&proc->deferred_work_node)) { hlist_add_head(&proc->deferred_work_node, - &binder_deferred_list); - queue_work(binder_deferred_workqueue, &binder_deferred_work); + &proc->context->binder_deferred_list); + queue_work(proc->context->binder_deferred_workqueue, + &proc->context->deferred_work); } - mutex_unlock(&binder_deferred_lock); + mutex_unlock(&proc->context->binder_deferred_lock); } static void print_binder_transaction(struct seq_file *m, const char *prefix, @@ -3975,8 +3992,20 @@ static const char * const binder_objstat_strings[] = { "transaction_complete" }; +static void add_binder_stats(struct binder_stats *from, struct binder_stats *to) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(to->bc); i++) + to->bc[i] += from->bc[i]; + + for (i = 0; i < ARRAY_SIZE(to->br); i++) + to->br[i] += from->br[i]; +} + static void print_binder_stats(struct seq_file *m, const char *prefix, - struct binder_stats *stats) + struct binder_stats *stats, + struct binder_obj_stats *obj_stats) { int i; @@ -3996,16 +4025,21 @@ static void print_binder_stats(struct seq_file *m, const char *prefix, binder_return_strings[i], stats->br[i]); } - BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) != + if (!obj_stats) + return; + + BUILD_BUG_ON(ARRAY_SIZE(obj_stats->obj_created) != ARRAY_SIZE(binder_objstat_strings)); - BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) != - ARRAY_SIZE(stats->obj_deleted)); - for (i = 0; i < ARRAY_SIZE(stats->obj_created); i++) { - if (stats->obj_created[i] || stats->obj_deleted[i]) + BUILD_BUG_ON(ARRAY_SIZE(obj_stats->obj_created) != + ARRAY_SIZE(obj_stats->obj_deleted)); + for (i = 0; i < ARRAY_SIZE(obj_stats->obj_created); i++) { + int obj_created = atomic_read(&obj_stats->obj_created[i]); + int obj_deleted = atomic_read(&obj_stats->obj_deleted[i]); + + if (obj_created || obj_deleted) seq_printf(m, "%s%s: active %d total %d\n", prefix, - binder_objstat_strings[i], - stats->obj_created[i] - stats->obj_deleted[i], - stats->obj_created[i]); + binder_objstat_strings[i], + obj_created - obj_deleted, obj_created); } } @@ -4060,85 +4094,131 @@ static void print_binder_proc_stats(struct seq_file *m, } seq_printf(m, " pending transactions: %d\n", count); - print_binder_stats(m, " ", &proc->stats); + print_binder_stats(m, " ", &proc->stats, NULL); } static int binder_state_show(struct seq_file *m, void *unused) { + struct binder_device *device; + struct binder_context *context; struct binder_proc *proc; struct binder_node *node; int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); + bool wrote_dead_nodes_header = false; seq_puts(m, "binder state:\n"); - if (!hlist_empty(&binder_dead_nodes)) - seq_puts(m, "dead nodes:\n"); - hlist_for_each_entry(node, &binder_dead_nodes, dead_node) - print_binder_node(m, node); + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + if (do_lock) + binder_lock(context, __func__); + if (!wrote_dead_nodes_header && + !hlist_empty(&context->binder_dead_nodes)) { + seq_puts(m, "dead nodes:\n"); + wrote_dead_nodes_header = true; + } + hlist_for_each_entry(node, &context->binder_dead_nodes, + dead_node) + print_binder_node(m, node); + + if (do_lock) + binder_unlock(context, __func__); + } - hlist_for_each_entry(proc, &binder_procs, proc_node) - print_binder_proc(m, proc, 1); - if (do_lock) - binder_unlock(__func__); + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + if (do_lock) + binder_lock(context, __func__); + + hlist_for_each_entry(proc, &context->binder_procs, proc_node) + print_binder_proc(m, proc, 1); + if (do_lock) + binder_unlock(context, __func__); + } return 0; } static int binder_stats_show(struct seq_file *m, void *unused) { + struct binder_device *device; + struct binder_context *context; struct binder_proc *proc; + struct binder_stats total_binder_stats; int do_lock = !binder_debug_no_lock; - if (do_lock) - binder_lock(__func__); + memset(&total_binder_stats, 0, sizeof(struct binder_stats)); + + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + if (do_lock) + binder_lock(context, __func__); + + add_binder_stats(&context->binder_stats, &total_binder_stats); + + if (do_lock) + binder_unlock(context, __func__); + } seq_puts(m, "binder stats:\n"); + print_binder_stats(m, "", &total_binder_stats, &binder_obj_stats); - print_binder_stats(m, "", &binder_stats); + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + if (do_lock) + binder_lock(context, __func__); - hlist_for_each_entry(proc, &binder_procs, proc_node) - print_binder_proc_stats(m, proc); - if (do_lock) - binder_unlock(__func__); + hlist_for_each_entry(proc, &context->binder_procs, proc_node) + print_binder_proc_stats(m, proc); + if (do_lock) + binder_unlock(context, __func__); + } return 0; } static int binder_transactions_show(struct seq_file *m, void *unused) { + struct binder_device *device; + struct binder_context *context; struct binder_proc *proc; int do_lock = !binder_debug_no_lock; - if (do_lock) - binder_lock(__func__); - seq_puts(m, "binder transactions:\n"); - hlist_for_each_entry(proc, &binder_procs, proc_node) - print_binder_proc(m, proc, 0); - if (do_lock) - binder_unlock(__func__); + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + if (do_lock) + binder_lock(context, __func__); + + hlist_for_each_entry(proc, &context->binder_procs, proc_node) + print_binder_proc(m, proc, 0); + if (do_lock) + binder_unlock(context, __func__); + } return 0; } static int binder_proc_show(struct seq_file *m, void *unused) { + struct binder_device *device; + struct binder_context *context; struct binder_proc *itr; int pid = (unsigned long)m->private; int do_lock = !binder_debug_no_lock; - if (do_lock) - binder_lock(__func__); + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + if (do_lock) + binder_lock(context, __func__); - hlist_for_each_entry(itr, &binder_procs, proc_node) { - if (itr->pid == pid) { - seq_puts(m, "binder proc state:\n"); - print_binder_proc(m, itr, 1); + hlist_for_each_entry(itr, &context->binder_procs, proc_node) { + if (itr->pid == pid) { + seq_puts(m, "binder proc state:\n"); + print_binder_proc(m, itr, 1); + } } + if (do_lock) + binder_unlock(context, __func__); } - if (do_lock) - binder_unlock(__func__); return 0; } @@ -4153,11 +4233,10 @@ static void print_binder_transaction_log_entry(struct seq_file *m, e->to_node, e->target_handle, e->data_size, e->offsets_size); } -static int binder_transaction_log_show(struct seq_file *m, void *unused) +static int print_binder_transaction_log(struct seq_file *m, + struct binder_transaction_log *log) { - struct binder_transaction_log *log = m->private; int i; - if (log->full) { for (i = log->next; i < ARRAY_SIZE(log->entry); i++) print_binder_transaction_log_entry(m, &log->entry[i]); @@ -4167,6 +4246,31 @@ static int binder_transaction_log_show(struct seq_file *m, void *unused) return 0; } +static int binder_transaction_log_show(struct seq_file *m, void *unused) +{ + struct binder_device *device; + struct binder_context *context; + + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + print_binder_transaction_log(m, &context->transaction_log); + } + return 0; +} + +static int binder_failed_transaction_log_show(struct seq_file *m, void *unused) +{ + struct binder_device *device; + struct binder_context *context; + + hlist_for_each_entry(device, &binder_devices, hlist) { + context = &device->context; + print_binder_transaction_log(m, + &context->transaction_log_failed); + } + return 0; +} + static const struct file_operations binder_fops = { .owner = THIS_MODULE, .poll = binder_poll, @@ -4182,11 +4286,20 @@ BINDER_DEBUG_ENTRY(state); BINDER_DEBUG_ENTRY(stats); BINDER_DEBUG_ENTRY(transactions); BINDER_DEBUG_ENTRY(transaction_log); +BINDER_DEBUG_ENTRY(failed_transaction_log); + +static void __init free_binder_device(struct binder_device *device) +{ + if (device->context.binder_deferred_workqueue) + destroy_workqueue(device->context.binder_deferred_workqueue); + kfree(device); +} static int __init init_binder_device(const char *name) { int ret; struct binder_device *binder_device; + struct binder_context *context; binder_device = kzalloc(sizeof(*binder_device), GFP_KERNEL); if (!binder_device) @@ -4196,31 +4309,65 @@ static int __init init_binder_device(const char *name) binder_device->miscdev.minor = MISC_DYNAMIC_MINOR; binder_device->miscdev.name = name; - binder_device->context.binder_context_mgr_uid = INVALID_UID; - binder_device->context.name = name; + context = &binder_device->context; + context->binder_context_mgr_uid = INVALID_UID; + context->name = name; + + mutex_init(&context->binder_main_lock); + mutex_init(&context->binder_deferred_lock); + mutex_init(&context->binder_mmap_lock); + + context->binder_deferred_workqueue = + create_singlethread_workqueue(name); + + if (!context->binder_deferred_workqueue) { + ret = -ENOMEM; + goto err_create_singlethread_workqueue_failed; + } + + INIT_HLIST_HEAD(&context->binder_procs); + INIT_HLIST_HEAD(&context->binder_dead_nodes); + INIT_HLIST_HEAD(&context->binder_deferred_list); + INIT_WORK(&context->deferred_work, binder_deferred_func); ret = misc_register(&binder_device->miscdev); if (ret < 0) { - kfree(binder_device); - return ret; + goto err_misc_register_failed; } hlist_add_head(&binder_device->hlist, &binder_devices); + return ret; + +err_create_singlethread_workqueue_failed: +err_misc_register_failed: + free_binder_device(binder_device); return ret; } static int __init binder_init(void) { - int ret; + int ret = 0; char *device_name, *device_names; struct binder_device *device; struct hlist_node *tmp; - binder_deferred_workqueue = create_singlethread_workqueue("binder"); - if (!binder_deferred_workqueue) + /* + * Copy the module_parameter string, because we don't want to + * tokenize it in-place. + */ + device_names = kzalloc(strlen(binder_devices_param) + 1, GFP_KERNEL); + if (!device_names) return -ENOMEM; + strcpy(device_names, binder_devices_param); + + while ((device_name = strsep(&device_names, ","))) { + ret = init_binder_device(device_name); + if (ret) + goto err_init_binder_device_failed; + } + binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL); if (binder_debugfs_dir_entry_root) binder_debugfs_dir_entry_proc = debugfs_create_dir("proc", @@ -4245,30 +4392,13 @@ static int __init binder_init(void) debugfs_create_file("transaction_log", S_IRUGO, binder_debugfs_dir_entry_root, - &binder_transaction_log, + NULL, &binder_transaction_log_fops); debugfs_create_file("failed_transaction_log", S_IRUGO, binder_debugfs_dir_entry_root, - &binder_transaction_log_failed, - &binder_transaction_log_fops); - } - - /* - * Copy the module_parameter string, because we don't want to - * tokenize it in-place. - */ - device_names = kzalloc(strlen(binder_devices_param) + 1, GFP_KERNEL); - if (!device_names) { - ret = -ENOMEM; - goto err_alloc_device_names_failed; - } - strcpy(device_names, binder_devices_param); - - while ((device_name = strsep(&device_names, ","))) { - ret = init_binder_device(device_name); - if (ret) - goto err_init_binder_device_failed; + NULL, + &binder_failed_transaction_log_fops); } return ret; @@ -4277,12 +4407,8 @@ err_init_binder_device_failed: hlist_for_each_entry_safe(device, tmp, &binder_devices, hlist) { misc_deregister(&device->miscdev); hlist_del(&device->hlist); - kfree(device); + free_binder_device(device); } -err_alloc_device_names_failed: - debugfs_remove_recursive(binder_debugfs_dir_entry_root); - - destroy_workqueue(binder_deferred_workqueue); return ret; } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index bd370c98f77d..b0b77b61c40c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4139,10 +4139,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, /* - * Device times out with higher max sects. + * These devices time out with higher max sects. * https://bugzilla.kernel.org/show_bug.cgi?id=121671 */ - { "LITEON CX1-JB256-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + { "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, /* Devices we expect to fail diagnostics */ diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index e417e1a1d02c..5b2aee83d776 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2832,10 +2832,12 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc) static struct ata_device *ata_find_dev(struct ata_port *ap, int devno) { if (!sata_pmp_attached(ap)) { - if (likely(devno < ata_link_max_devices(&ap->link))) + if (likely(devno >= 0 && + devno < ata_link_max_devices(&ap->link))) return &ap->link.device[devno]; } else { - if (likely(devno < ap->nr_pmp_links)) + if (likely(devno >= 0 && + devno < ap->nr_pmp_links)) return &ap->pmp_link[devno].device[0]; } diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index bd74ee555278..729f26322095 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4121,6 +4121,9 @@ static int mv_platform_probe(struct platform_device *pdev) host->iomap = NULL; hpriv->base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); + if (!hpriv->base) + return -ENOMEM; + hpriv->base -= SATAHC0_REG_BASE; hpriv->clk = clk_get(&pdev->dev, NULL); diff --git a/drivers/base/core.c b/drivers/base/core.c index f18856f5954b..afe045792796 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2094,7 +2094,11 @@ void device_shutdown(void) pm_runtime_get_noresume(dev); pm_runtime_barrier(dev); - if (dev->bus && dev->bus->shutdown) { + if (dev->class && dev->class->shutdown) { + if (initcall_debug) + dev_info(dev, "shutdown\n"); + dev->class->shutdown(dev); + } else if (dev->bus && dev->bus->shutdown) { if (initcall_debug) dev_info(dev, "shutdown\n"); dev->bus->shutdown(dev); diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 25425d3f2575..48c0a1d0dd3a 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -388,30 +388,29 @@ static ssize_t show_valid_zones(struct device *dev, { struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn, end_pfn; + unsigned long valid_start, valid_end; unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; - struct page *first_page; struct zone *zone; start_pfn = section_nr_to_pfn(mem->start_section_nr); end_pfn = start_pfn + nr_pages; - first_page = pfn_to_page(start_pfn); /* The block contains more than one zone can not be offlined. */ - if (!test_pages_in_a_zone(start_pfn, end_pfn)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) return sprintf(buf, "none\n"); - zone = page_zone(first_page); + zone = page_zone(pfn_to_page(valid_start)); if (zone_idx(zone) == ZONE_MOVABLE - 1) { /*The mem block is the last memoryblock of this zone.*/ - if (end_pfn == zone_end_pfn(zone)) + if (valid_end == zone_end_pfn(zone)) return sprintf(buf, "%s %s\n", zone->name, (zone + 1)->name); } if (zone_idx(zone) == ZONE_MOVABLE) { /*The mem block is the first memoryblock of ZONE_MOVABLE.*/ - if (start_pfn == zone->zone_start_pfn) + if (valid_start == zone->zone_start_pfn) return sprintf(buf, "%s %s\n", zone->name, (zone - 1)->name); } diff --git a/drivers/base/platform.c b/drivers/base/platform.c index ba66330cea67..cb4ad6e98b28 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -807,7 +807,7 @@ static ssize_t driver_override_store(struct device *dev, const char *buf, size_t count) { struct platform_device *pdev = to_platform_device(dev); - char *driver_override, *old = pdev->driver_override, *cp; + char *driver_override, *old, *cp; if (count > PATH_MAX) return -EINVAL; @@ -820,12 +820,15 @@ static ssize_t driver_override_store(struct device *dev, if (cp) *cp = '\0'; + device_lock(dev); + old = pdev->driver_override; if (strlen(driver_override)) { pdev->driver_override = driver_override; } else { kfree(driver_override); pdev->driver_override = NULL; } + device_unlock(dev); kfree(old); @@ -836,8 +839,12 @@ static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { struct platform_device *pdev = to_platform_device(dev); + ssize_t len; - return sprintf(buf, "%s\n", pdev->driver_override); + device_lock(dev); + len = sprintf(buf, "%s\n", pdev->driver_override); + device_unlock(dev); + return len; } static DEVICE_ATTR_RW(driver_override); diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index a48824deabc5..78b0ece0c867 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1188,7 +1188,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, } dev->power.subsys_data->domain_data = &gpd_data->base; - dev->pm_domain = &genpd->domain; spin_unlock_irq(&dev->power.lock); @@ -1207,7 +1206,6 @@ static void genpd_free_dev_data(struct device *dev, { spin_lock_irq(&dev->power.lock); - dev->pm_domain = NULL; dev->power.subsys_data->domain_data = NULL; spin_unlock_irq(&dev->power.lock); @@ -1248,6 +1246,8 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (ret) goto out; + dev->pm_domain = &genpd->domain; + genpd->device_count++; genpd->max_off_time_changed = true; @@ -1299,6 +1299,8 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, if (genpd->detach_dev) genpd->detach_dev(genpd, dev); + dev->pm_domain = NULL; + list_del_init(&pdd->list_node); mutex_unlock(&genpd->lock); @@ -1373,7 +1375,7 @@ EXPORT_SYMBOL_GPL(pm_genpd_add_subdomain); int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *subdomain) { - struct gpd_link *link; + struct gpd_link *l, *link; int ret = -EINVAL; if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)) @@ -1388,7 +1390,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, goto out; } - list_for_each_entry(link, &genpd->master_links, master_node) { + list_for_each_entry_safe(link, l, &genpd->master_links, master_node) { if (link->slave != subdomain) continue; @@ -1642,10 +1644,10 @@ EXPORT_SYMBOL_GPL(__of_genpd_add_provider); */ void of_genpd_del_provider(struct device_node *np) { - struct of_genpd_provider *cp; + struct of_genpd_provider *cp, *tmp; mutex_lock(&of_genpd_mutex); - list_for_each_entry(cp, &of_genpd_providers, link) { + list_for_each_entry_safe(cp, tmp, &of_genpd_providers, link) { if (cp->node == np) { list_del(&cp->link); of_node_put(cp->node); diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 4b19cda8b761..78adce03180a 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -242,6 +242,7 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) { struct opp_table *opp_table; struct dev_pm_opp *opp, *min_opp = NULL, *max_opp = NULL; + struct regulator *reg; struct pm_opp_domain *pod; unsigned long latency_ns = 0; unsigned long old_min_uV, old_uV, old_max_uV; @@ -256,6 +257,13 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) return 0; } + reg = opp_table->regulator; + if (IS_ERR(reg)) { + /* Regulator may not be required for device */ + rcu_read_unlock(); + return 0; + } + list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { if (!opp->available) continue; diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index 47746802ad54..cf98cae2582d 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -168,6 +168,7 @@ struct opp_table { unsigned int *supported_hw; unsigned int supported_hw_count; const char *prop_name; + struct regulator *regulator; struct pm_opp_domain *opp_domain; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 3252429f96af..3a20dc594338 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -889,13 +889,13 @@ int __pm_runtime_idle(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); - if (rpmflags & RPM_GET_PUT) { if (!atomic_dec_and_test(&dev->power.usage_count)) return 0; } + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_idle(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); @@ -921,13 +921,13 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); - if (rpmflags & RPM_GET_PUT) { if (!atomic_dec_and_test(&dev->power.usage_count)) return 0; } + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); @@ -952,7 +952,8 @@ int __pm_runtime_resume(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe && + dev->power.runtime_status != RPM_ACTIVE); if (rpmflags & RPM_GET_PUT) atomic_inc(&dev->power.usage_count); diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index a7b46798c81d..39efa7e6c0c0 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -268,6 +268,8 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev, value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (!strcmp(buf, "any") || !strcmp(buf, "any\n")) value = PM_QOS_LATENCY_ANY; + else + return -EINVAL; } ret = dev_pm_qos_update_user_latency_tolerance(dev, value); return ret < 0 ? ret : n; diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 404d94c6c8bc..ae0429827f31 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -141,6 +141,13 @@ static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq) struct wake_irq *wirq = _wirq; int res; + /* Maybe abort suspend? */ + if (irqd_is_wakeup_set(irq_get_irq_data(irq))) { + pm_wakeup_event(wirq->dev, 0); + + return IRQ_HANDLED; + } + /* We don't want RPM_ASYNC or RPM_NOWAIT here */ res = pm_runtime_resume(wirq->dev); if (res < 0) @@ -183,6 +190,9 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) wirq->irq = irq; irq_set_status_flags(irq, IRQ_NOAUTOEN); + /* Prevent deferred spurious wakeirqs with disable_irq_nosync() */ + irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY); + /* * Consumer device may need to power up and restore state * so we use a threaded irq. @@ -312,8 +322,12 @@ void dev_pm_arm_wake_irq(struct wake_irq *wirq) if (!wirq) return; - if (device_may_wakeup(wirq->dev)) + if (device_may_wakeup(wirq->dev)) { + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) + enable_irq(wirq->irq); + enable_irq_wake(wirq->irq); + } } /** @@ -328,6 +342,10 @@ void dev_pm_disarm_wake_irq(struct wake_irq *wirq) if (!wirq) return; - if (device_may_wakeup(wirq->dev)) + if (device_may_wakeup(wirq->dev)) { disable_irq_wake(wirq->irq); + + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) + disable_irq_nosync(wirq->irq); + } } diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 4435e78e9fc4..bbc8362ec458 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -61,6 +61,8 @@ static LIST_HEAD(wakeup_sources); static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue); +DEFINE_STATIC_SRCU(wakeup_srcu); + static struct wakeup_source deleted_ws = { .name = "deleted", .lock = __SPIN_LOCK_UNLOCKED(deleted_ws.lock), @@ -199,7 +201,7 @@ void wakeup_source_remove(struct wakeup_source *ws) spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); spin_unlock_irqrestore(&events_lock, flags); - synchronize_rcu(); + synchronize_srcu(&wakeup_srcu); } EXPORT_SYMBOL_GPL(wakeup_source_remove); @@ -333,13 +335,14 @@ void device_wakeup_detach_irq(struct device *dev) void device_wakeup_arm_wake_irqs(void) { struct wakeup_source *ws; + int srcuidx; - rcu_read_lock(); + srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { if (ws->wakeirq) dev_pm_arm_wake_irq(ws->wakeirq); } - rcu_read_unlock(); + srcu_read_unlock(&wakeup_srcu, srcuidx); } /** @@ -350,13 +353,14 @@ void device_wakeup_arm_wake_irqs(void) void device_wakeup_disarm_wake_irqs(void) { struct wakeup_source *ws; + int srcuidx; - rcu_read_lock(); + srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { if (ws->wakeirq) dev_pm_disarm_wake_irq(ws->wakeirq); } - rcu_read_unlock(); + srcu_read_unlock(&wakeup_srcu, srcuidx); } /** @@ -841,10 +845,10 @@ EXPORT_SYMBOL_GPL(pm_get_active_wakeup_sources); void pm_print_active_wakeup_sources(void) { struct wakeup_source *ws; - int active = 0; + int srcuidx, active = 0; struct wakeup_source *last_activity_ws = NULL; - rcu_read_lock(); + srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { if (ws->active) { pr_info("active wakeup source: %s\n", ws->name); @@ -860,7 +864,7 @@ void pm_print_active_wakeup_sources(void) if (!active && last_activity_ws) pr_info("last active wakeup source: %s\n", last_activity_ws->name); - rcu_read_unlock(); + srcu_read_unlock(&wakeup_srcu, srcuidx); } EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources); @@ -987,8 +991,9 @@ void pm_wakep_autosleep_enabled(bool set) { struct wakeup_source *ws; ktime_t now = ktime_get(); + int srcuidx; - rcu_read_lock(); + srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { spin_lock_irq(&ws->lock); if (ws->autosleep_enabled != set) { @@ -1002,7 +1007,7 @@ void pm_wakep_autosleep_enabled(bool set) } spin_unlock_irq(&ws->lock); } - rcu_read_unlock(); + srcu_read_unlock(&wakeup_srcu, srcuidx); } #endif /* CONFIG_PM_AUTOSLEEP */ @@ -1044,7 +1049,7 @@ static int print_wakeup_source_stats(struct seq_file *m, active_time = ktime_set(0, 0); } - seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", + seq_printf(m, "%-32s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", ws->name, active_count, ws->event_count, ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), @@ -1063,15 +1068,16 @@ static int print_wakeup_source_stats(struct seq_file *m, static int wakeup_sources_stats_show(struct seq_file *m, void *unused) { struct wakeup_source *ws; + int srcuidx; - seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" + seq_puts(m, "name\t\t\t\t\tactive_count\tevent_count\twakeup_count\t" "expire_count\tactive_since\ttotal_time\tmax_time\t" "last_change\tprevent_suspend_time\n"); - rcu_read_lock(); + srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) print_wakeup_source_stats(m, ws); - rcu_read_unlock(); + srcu_read_unlock(&wakeup_srcu, srcuidx); print_wakeup_source_stats(m, &deleted_ws); diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 59d8d0d14824..327f9e374b44 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -640,8 +640,11 @@ static int bcma_device_probe(struct device *dev) drv); int err = 0; + get_device(dev); if (adrv->probe) err = adrv->probe(core); + if (err) + put_device(dev); return err; } @@ -654,6 +657,7 @@ static int bcma_device_remove(struct device *dev) if (adrv->remove) adrv->remove(core); + put_device(dev); return 0; } diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 9462d2752850..8bdc34dbaedf 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -479,8 +479,14 @@ void drbd_bm_cleanup(struct drbd_device *device) * this masks out the remaining bits. * Returns the number of bits cleared. */ +#ifndef BITS_PER_PAGE #define BITS_PER_PAGE (1UL << (PAGE_SHIFT + 3)) #define BITS_PER_PAGE_MASK (BITS_PER_PAGE - 1) +#else +# if BITS_PER_PAGE != (1UL << (PAGE_SHIFT + 3)) +# error "ambiguous BITS_PER_PAGE" +# endif +#endif #define BITS_PER_LONG_MASK (BITS_PER_LONG - 1) static int bm_clear_surplus(struct drbd_bitmap *b) { diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ab0b2dd3f629..cec36d5c24f5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1108,9 +1108,12 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) return -EINVAL; + /* I/O need to be drained during transfer transition */ + blk_mq_freeze_queue(lo->lo_queue); + err = loop_release_xfer(lo); if (err) - return err; + goto exit; if (info->lo_encrypt_type) { unsigned int type = info->lo_encrypt_type; @@ -1125,12 +1128,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) err = loop_init_xfer(lo, xfer, info); if (err) - return err; + goto exit; if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) - if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) - return -EFBIG; + if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { + err = -EFBIG; + goto exit; + } loop_config_discard(lo); @@ -1148,13 +1153,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) (info->lo_flags & LO_FLAGS_AUTOCLEAR)) lo->lo_flags ^= LO_FLAGS_AUTOCLEAR; - if ((info->lo_flags & LO_FLAGS_PARTSCAN) && - !(lo->lo_flags & LO_FLAGS_PARTSCAN)) { - lo->lo_flags |= LO_FLAGS_PARTSCAN; - lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; - loop_reread_partitions(lo, lo->lo_device); - } - lo->lo_encrypt_key_size = info->lo_encrypt_key_size; lo->lo_init[0] = info->lo_init[0]; lo->lo_init[1] = info->lo_init[1]; @@ -1167,7 +1165,17 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) /* update dio if lo_offset or transfer is changed */ __loop_update_dio(lo, lo->use_dio); - return 0; + exit: + blk_mq_unfreeze_queue(lo->lo_queue); + + if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) && + !(lo->lo_flags & LO_FLAGS_PARTSCAN)) { + lo->lo_flags |= LO_FLAGS_PARTSCAN; + lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; + loop_reread_partitions(lo, lo->lo_device); + } + + return err; } static int diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 6ca35495a5be..1e5cd39d0cc2 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -641,11 +641,12 @@ static int virtblk_probe(struct virtio_device *vdev) if (err) goto out_put_disk; - q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set); + q = blk_mq_init_queue(&vblk->tag_set); if (IS_ERR(q)) { err = -ENOMEM; goto out_free_tags; } + vblk->disk->queue = q; q->queuedata = vblk; diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 41fb1a917b17..33e23a7a691f 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -595,8 +595,6 @@ int xen_blkif_schedule(void *arg) unsigned long timeout; int ret; - xen_blkif_get(blkif); - while (!kthread_should_stop()) { if (try_to_freeze()) continue; @@ -650,7 +648,6 @@ purge_gnt_list: print_stats(blkif); blkif->xenblkd = NULL; - xen_blkif_put(blkif); return 0; } diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index f53cff42f8da..923308201375 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -221,7 +221,6 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) if (blkif->xenblkd) { kthread_stop(blkif->xenblkd); wake_up(&blkif->shutdown_wq); - blkif->xenblkd = NULL; } /* The above kthread_stop() guarantees that at this point we @@ -266,9 +265,10 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) static void xen_blkif_free(struct xen_blkif *blkif) { - - xen_blkif_disconnect(blkif); + WARN_ON(xen_blkif_disconnect(blkif)); xen_vbd_free(&blkif->vbd); + kfree(blkif->be->mode); + kfree(blkif->be); /* Make sure everything is drained before shutting down */ BUG_ON(blkif->persistent_gnt_c != 0); @@ -445,8 +445,6 @@ static int xen_blkbk_remove(struct xenbus_device *dev) xen_blkif_put(be->blkif); } - kfree(be->mode); - kfree(be); return 0; } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 1648de80e230..62a93b685c54 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -574,13 +574,13 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index) if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) { bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); - clear_page(mem); + memset(mem, 0, PAGE_SIZE); return 0; } cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO); if (size == PAGE_SIZE) - copy_page(mem, cmem); + memcpy(mem, cmem, PAGE_SIZE); else ret = zcomp_decompress(zram->comp, cmem, size, mem); zs_unmap_object(meta->mem_pool, handle); @@ -738,7 +738,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) { src = kmap_atomic(page); - copy_page(cmem, src); + memcpy(cmem, src, PAGE_SIZE); kunmap_atomic(src); } else { memcpy(cmem, src, clen); diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 0beaa52df66b..5df8e1234505 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -94,6 +94,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x04CA, 0x300f) }, { USB_DEVICE(0x04CA, 0x3010) }, { USB_DEVICE(0x04CA, 0x3014) }, + { USB_DEVICE(0x04CA, 0x3018) }, { USB_DEVICE(0x0930, 0x0219) }, { USB_DEVICE(0x0930, 0x021c) }, { USB_DEVICE(0x0930, 0x0220) }, @@ -160,6 +161,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3018), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index c306b483de60..cd6b141b9825 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -208,6 +208,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3018), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index cb852cc750b7..f9b569ef3dd7 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -287,6 +287,9 @@ static int bcm_open(struct hci_uart *hu) hu->priv = bcm; + if (!hu->tty->dev) + goto out; + mutex_lock(&bcm_device_lock); list_for_each(p, &bcm_device_list) { struct bcm_device *dev = list_entry(p, struct bcm_device, list); @@ -307,7 +310,7 @@ static int bcm_open(struct hci_uart *hu) } mutex_unlock(&bcm_device_lock); - +out: return 0; } diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index b9065506a847..0c63fce0c1e0 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -307,6 +307,9 @@ static int intel_set_power(struct hci_uart *hu, bool powered) struct list_head *p; int err = -ENODEV; + if (!hu->tty->dev) + return err; + mutex_lock(&intel_device_list_lock); list_for_each(p, &intel_device_list) { @@ -379,6 +382,9 @@ static void intel_busy_work(struct work_struct *work) struct intel_data *intel = container_of(work, struct intel_data, busy_work); + if (!intel->hu->tty->dev) + return; + /* Link is busy, delay the suspend */ mutex_lock(&intel_device_list_lock); list_for_each(p, &intel_device_list) { @@ -913,6 +919,8 @@ done: list_for_each(p, &intel_device_list) { struct intel_device *dev = list_entry(p, struct intel_device, list); + if (!hu->tty->dev) + break; if (hu->tty->dev->parent == dev->pdev->dev.parent) { if (device_may_wakeup(&dev->pdev->dev)) idev = dev; @@ -1094,6 +1102,9 @@ static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb) BT_DBG("hu %p skb %p", hu, skb); + if (!hu->tty->dev) + goto out_enqueue; + /* Be sure our controller is resumed and potential LPM transaction * completed before enqueuing any packet. */ @@ -1110,7 +1121,7 @@ static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb) } } mutex_unlock(&intel_device_list_lock); - +out_enqueue: skb_queue_tail(&intel->txq, skb); return 0; diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index a043107da2af..3143db57ce44 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -583,10 +583,12 @@ config TELCLOCK controlling the behavior of this hardware. config DEVPORT - bool - depends on !M68K + bool "/dev/port character device" depends on ISA || PCI default y + help + Say Y here if you want to support the /dev/port device. The /dev/port + device is similar to /dev/mem, but for I/O ports. source "drivers/s390/char/Kconfig" diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index a084a4751fa9..25372dc381d4 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3877,6 +3877,9 @@ static void smi_recv_tasklet(unsigned long val) * because the lower layer is allowed to hold locks while calling * message delivery. */ + + rcu_read_lock(); + if (!run_to_completion) spin_lock_irqsave(&intf->xmit_msgs_lock, flags); if (intf->curr_msg == NULL && !intf->in_shutdown) { @@ -3899,6 +3902,8 @@ static void smi_recv_tasklet(unsigned long val) if (newmsg) intf->handlers->sender(intf->send_info, newmsg); + rcu_read_unlock(); + handle_new_recv_msgs(intf); } diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 90e624662257..f53e8ba2c718 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -758,6 +758,11 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, result, len, data[2]); } else if (data[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 || data[1] != IPMI_GET_MSG_FLAGS_CMD) { + /* + * Don't abort here, maybe it was a queued + * response to a previous command. + */ + ipmi_ssif_unlock_cond(ssif_info, flags); pr_warn(PFX "Invalid response getting flags: %x %x\n", data[0], data[1]); } else { @@ -888,6 +893,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, * for details on the intricacies of this. */ int left; + unsigned char *data_to_send; ssif_inc_stat(ssif_info, sent_messages_parts); @@ -896,6 +902,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, left = 32; /* Length byte. */ ssif_info->multi_data[ssif_info->multi_pos] = left; + data_to_send = ssif_info->multi_data + ssif_info->multi_pos; ssif_info->multi_pos += left; if (left < 32) /* @@ -909,7 +916,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, rv = ssif_i2c_send(ssif_info, msg_written_handler, I2C_SMBUS_WRITE, SSIF_IPMI_MULTI_PART_REQUEST_MIDDLE, - ssif_info->multi_data + ssif_info->multi_pos, + data_to_send, I2C_SMBUS_BLOCK_DATA); if (rv < 0) { /* request failed, just return the error. */ diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 096f0cef4da1..40d400fe5bb7 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -1162,10 +1162,11 @@ static int wdog_reboot_handler(struct notifier_block *this, ipmi_watchdog_state = WDOG_TIMEOUT_NONE; ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB); } else if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) { - /* Set a long timer to let the reboot happens, but - reboot if it hangs, but only if the watchdog + /* Set a long timer to let the reboot happen or + reset if it hangs, but only if the watchdog timer was already running. */ - timeout = 120; + if (timeout < 120) + timeout = 120; pretimeout = 0; ipmi_watchdog_state = WDOG_TIMEOUT_RESET; ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB); diff --git a/drivers/char/lp.c b/drivers/char/lp.c index c4094c4e22c1..34ef474a3923 100644 --- a/drivers/char/lp.c +++ b/drivers/char/lp.c @@ -859,7 +859,11 @@ static int __init lp_setup (char *str) } else if (!strcmp(str, "auto")) { parport_nr[0] = LP_PARPORT_AUTO; } else if (!strcmp(str, "none")) { - parport_nr[parport_ptr++] = LP_PARPORT_NONE; + if (parport_ptr < LP_NO) + parport_nr[parport_ptr++] = LP_PARPORT_NONE; + else + printk(KERN_INFO "lp: too many ports, %s ignored.\n", + str); } else if (!strcmp(str, "reset")) { reset = 1; } diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 6b1721f978c2..2898d19fadf5 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -59,6 +59,10 @@ static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) #endif #ifdef CONFIG_STRICT_DEVMEM +static inline int page_is_allowed(unsigned long pfn) +{ + return devmem_is_allowed(pfn); +} static inline int range_is_allowed(unsigned long pfn, unsigned long size) { u64 from = ((u64)pfn) << PAGE_SHIFT; @@ -78,6 +82,10 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) return 1; } #else +static inline int page_is_allowed(unsigned long pfn) +{ + return 1; +} static inline int range_is_allowed(unsigned long pfn, unsigned long size) { return 1; @@ -125,23 +133,31 @@ static ssize_t read_mem(struct file *file, char __user *buf, while (count > 0) { unsigned long remaining; + int allowed; sz = size_inside_page(p, count); - if (!range_is_allowed(p >> PAGE_SHIFT, count)) + allowed = page_is_allowed(p >> PAGE_SHIFT); + if (!allowed) return -EPERM; + if (allowed == 2) { + /* Show zeros for restricted memory. */ + remaining = clear_user(buf, sz); + } else { + /* + * On ia64 if a page has been mapped somewhere as + * uncached, then it must also be accessed uncached + * by the kernel or data corruption may occur. + */ + ptr = xlate_dev_mem_ptr(p); + if (!ptr) + return -EFAULT; - /* - * On ia64 if a page has been mapped somewhere as uncached, then - * it must also be accessed uncached by the kernel or data - * corruption may occur. - */ - ptr = xlate_dev_mem_ptr(p); - if (!ptr) - return -EFAULT; + remaining = copy_to_user(buf, ptr, sz); + + unxlate_dev_mem_ptr(p, ptr); + } - remaining = copy_to_user(buf, ptr, sz); - unxlate_dev_mem_ptr(p, ptr); if (remaining) return -EFAULT; @@ -184,30 +200,36 @@ static ssize_t write_mem(struct file *file, const char __user *buf, #endif while (count > 0) { + int allowed; + sz = size_inside_page(p, count); - if (!range_is_allowed(p >> PAGE_SHIFT, sz)) + allowed = page_is_allowed(p >> PAGE_SHIFT); + if (!allowed) return -EPERM; - /* - * On ia64 if a page has been mapped somewhere as uncached, then - * it must also be accessed uncached by the kernel or data - * corruption may occur. - */ - ptr = xlate_dev_mem_ptr(p); - if (!ptr) { - if (written) - break; - return -EFAULT; - } + /* Skip actual writing when a page is marked as restricted. */ + if (allowed == 1) { + /* + * On ia64 if a page has been mapped somewhere as + * uncached, then it must also be accessed uncached + * by the kernel or data corruption may occur. + */ + ptr = xlate_dev_mem_ptr(p); + if (!ptr) { + if (written) + break; + return -EFAULT; + } - copied = copy_from_user(ptr, buf, sz); - unxlate_dev_mem_ptr(p, ptr); - if (copied) { - written += sz - copied; - if (written) - break; - return -EFAULT; + copied = copy_from_user(ptr, buf, sz); + unxlate_dev_mem_ptr(p, ptr); + if (copied) { + written += sz - copied; + if (written) + break; + return -EFAULT; + } } buf += sz; @@ -321,6 +343,11 @@ static const struct vm_operations_struct mmap_mem_ops = { static int mmap_mem(struct file *file, struct vm_area_struct *vma) { size_t size = vma->vm_end - vma->vm_start; + phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; + + /* It's illegal to wrap around the end of the physical address space. */ + if (offset + (phys_addr_t)size - 1 < offset) + return -EINVAL; if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size)) return -EINVAL; diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c index fc061f7c2bd1..a7de8ae185a5 100644 --- a/drivers/char/pcmcia/cm4040_cs.c +++ b/drivers/char/pcmcia/cm4040_cs.c @@ -374,7 +374,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf, rc = write_sync_reg(SCR_HOST_TO_READER_START, dev); if (rc <= 0) { - DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc); + DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc); DEBUGP(2, dev, "<- cm4040_write (failed)\n"); if (rc == -ERESTARTSYS) return rc; @@ -387,7 +387,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf, for (i = 0; i < bytes_to_write; i++) { rc = wait_for_bulk_out_ready(dev); if (rc <= 0) { - DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2Zx\n", + DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2zx\n", rc); DEBUGP(2, dev, "<- cm4040_write (failed)\n"); if (rc == -ERESTARTSYS) @@ -403,7 +403,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf, rc = write_sync_reg(SCR_HOST_TO_READER_DONE, dev); if (rc <= 0) { - DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc); + DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc); DEBUGP(2, dev, "<- cm4040_write (failed)\n"); if (rc == -ERESTARTSYS) return rc; diff --git a/drivers/char/random.c b/drivers/char/random.c index d93dfebae0bb..1822472dffab 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1798,13 +1798,15 @@ int random_int_secret_init(void) return 0; } +static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash) + __aligned(sizeof(unsigned long)); + /* * Get a random word for internal kernel use only. Similar to urandom but * with the goal of minimal entropy pool depletion. As a result, the random * value is not cryptographically secure but for several uses the cost of * depleting entropy is too high */ -static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash); unsigned int get_random_int(void) { __u32 *hash; diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 252142524ff2..a0d9ac6b6cc9 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -29,33 +29,92 @@ #include "tpm.h" #include "tpm_eventlog.h" -static DECLARE_BITMAP(dev_mask, TPM_NUM_DEVICES); -static LIST_HEAD(tpm_chip_list); -static DEFINE_SPINLOCK(driver_lock); +DEFINE_IDR(dev_nums_idr); +static DEFINE_MUTEX(idr_lock); struct class *tpm_class; dev_t tpm_devt; -/* - * tpm_chip_find_get - return tpm_chip for a given chip number - * @chip_num the device number for the chip +/** + * tpm_try_get_ops() - Get a ref to the tpm_chip + * @chip: Chip to ref + * + * The caller must already have some kind of locking to ensure that chip is + * valid. This function will lock the chip so that the ops member can be + * accessed safely. The locking prevents tpm_chip_unregister from + * completing, so it should not be held for long periods. + * + * Returns -ERRNO if the chip could not be got. */ -struct tpm_chip *tpm_chip_find_get(int chip_num) +int tpm_try_get_ops(struct tpm_chip *chip) { - struct tpm_chip *pos, *chip = NULL; + int rc = -EIO; - rcu_read_lock(); - list_for_each_entry_rcu(pos, &tpm_chip_list, list) { - if (chip_num != TPM_ANY_NUM && chip_num != pos->dev_num) - continue; + get_device(&chip->dev); - if (try_module_get(pos->pdev->driver->owner)) { - chip = pos; - break; - } + down_read(&chip->ops_sem); + if (!chip->ops) + goto out_lock; + + if (!try_module_get(chip->dev.parent->driver->owner)) + goto out_lock; + + return 0; +out_lock: + up_read(&chip->ops_sem); + put_device(&chip->dev); + return rc; +} +EXPORT_SYMBOL_GPL(tpm_try_get_ops); + +/** + * tpm_put_ops() - Release a ref to the tpm_chip + * @chip: Chip to put + * + * This is the opposite pair to tpm_try_get_ops(). After this returns chip may + * be kfree'd. + */ +void tpm_put_ops(struct tpm_chip *chip) +{ + module_put(chip->dev.parent->driver->owner); + up_read(&chip->ops_sem); + put_device(&chip->dev); +} +EXPORT_SYMBOL_GPL(tpm_put_ops); + +/** + * tpm_chip_find_get() - return tpm_chip for a given chip number + * @chip_num: id to find + * + * The return'd chip has been tpm_try_get_ops'd and must be released via + * tpm_put_ops + */ +struct tpm_chip *tpm_chip_find_get(int chip_num) +{ + struct tpm_chip *chip, *res = NULL; + int chip_prev; + + mutex_lock(&idr_lock); + + if (chip_num == TPM_ANY_NUM) { + chip_num = 0; + do { + chip_prev = chip_num; + chip = idr_get_next(&dev_nums_idr, &chip_num); + if (chip && !tpm_try_get_ops(chip)) { + res = chip; + break; + } + } while (chip_prev != chip_num); + } else { + chip = idr_find_slowpath(&dev_nums_idr, chip_num); + if (chip && !tpm_try_get_ops(chip)) + res = chip; } - rcu_read_unlock(); - return chip; + + mutex_unlock(&idr_lock); + + return res; } /** @@ -68,12 +127,48 @@ static void tpm_dev_release(struct device *dev) { struct tpm_chip *chip = container_of(dev, struct tpm_chip, dev); - spin_lock(&driver_lock); - clear_bit(chip->dev_num, dev_mask); - spin_unlock(&driver_lock); + mutex_lock(&idr_lock); + idr_remove(&dev_nums_idr, chip->dev_num); + mutex_unlock(&idr_lock); + kfree(chip); } + +/** + * tpm_class_shutdown() - prepare the TPM device for loss of power. + * @dev: device to which the chip is associated. + * + * Issues a TPM2_Shutdown command prior to loss of power, as required by the + * TPM 2.0 spec. + * Then, calls bus- and device- specific shutdown code. + * + * XXX: This codepath relies on the fact that sysfs is not enabled for + * TPM2: sysfs uses an implicit lock on chip->ops, so this could race if TPM2 + * has sysfs support enabled before TPM sysfs's implicit locking is fixed. + */ +static int tpm_class_shutdown(struct device *dev) +{ + struct tpm_chip *chip = container_of(dev, struct tpm_chip, dev); + + if (chip->flags & TPM_CHIP_FLAG_TPM2) { + down_write(&chip->ops_sem); + tpm2_shutdown(chip, TPM2_SU_CLEAR); + chip->ops = NULL; + up_write(&chip->ops_sem); + } + /* Allow bus- and device-specific code to run. Note: since chip->ops + * is NULL, more-specific shutdown code will not be able to issue TPM + * commands. + */ + if (dev->bus && dev->bus->shutdown) + dev->bus->shutdown(dev); + else if (dev->driver && dev->driver->shutdown) + dev->driver->shutdown(dev); + return 0; +} + + /** * tpmm_chip_alloc() - allocate a new struct tpm_chip instance * @dev: device to which the chip is associated @@ -88,37 +183,35 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev, const struct tpm_class_ops *ops) { struct tpm_chip *chip; + int rc; chip = kzalloc(sizeof(*chip), GFP_KERNEL); if (chip == NULL) return ERR_PTR(-ENOMEM); mutex_init(&chip->tpm_mutex); - INIT_LIST_HEAD(&chip->list); + init_rwsem(&chip->ops_sem); chip->ops = ops; - spin_lock(&driver_lock); - chip->dev_num = find_first_zero_bit(dev_mask, TPM_NUM_DEVICES); - spin_unlock(&driver_lock); - - if (chip->dev_num >= TPM_NUM_DEVICES) { + mutex_lock(&idr_lock); + rc = idr_alloc(&dev_nums_idr, NULL, 0, TPM_NUM_DEVICES, GFP_KERNEL); + mutex_unlock(&idr_lock); + if (rc < 0) { dev_err(dev, "No available tpm device numbers\n"); kfree(chip); - return ERR_PTR(-ENOMEM); + return ERR_PTR(rc); } - - set_bit(chip->dev_num, dev_mask); + chip->dev_num = rc; scnprintf(chip->devname, sizeof(chip->devname), "tpm%d", chip->dev_num); - chip->pdev = dev; - dev_set_drvdata(dev, chip); chip->dev.class = tpm_class; + chip->dev.class->shutdown = tpm_class_shutdown; chip->dev.release = tpm_dev_release; - chip->dev.parent = chip->pdev; + chip->dev.parent = dev; #ifdef CONFIG_ACPI chip->dev.groups = chip->groups; #endif @@ -133,7 +226,7 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev, device_initialize(&chip->dev); cdev_init(&chip->cdev, &tpm_fops); - chip->cdev.owner = chip->pdev->driver->owner; + chip->cdev.owner = dev->driver->owner; chip->cdev.kobj.parent = &chip->dev.kobj; devm_add_action(dev, (void (*)(void *)) put_device, &chip->dev); @@ -167,6 +260,11 @@ static int tpm_add_char_device(struct tpm_chip *chip) return rc; } + /* Make the chip available. */ + mutex_lock(&idr_lock); + idr_replace(&dev_nums_idr, chip, chip->dev_num); + mutex_unlock(&idr_lock); + return rc; } @@ -174,6 +272,16 @@ static void tpm_del_char_device(struct tpm_chip *chip) { cdev_del(&chip->cdev); device_del(&chip->dev); + + /* Make the chip unavailable. */ + mutex_lock(&idr_lock); + idr_replace(&dev_nums_idr, NULL, chip->dev_num); + mutex_unlock(&idr_lock); + + /* Make the driver uncallable. */ + down_write(&chip->ops_sem); + chip->ops = NULL; + up_write(&chip->ops_sem); } static int tpm1_chip_register(struct tpm_chip *chip) @@ -228,17 +336,11 @@ int tpm_chip_register(struct tpm_chip *chip) if (rc) goto out_err; - /* Make the chip available. */ - spin_lock(&driver_lock); - list_add_tail_rcu(&chip->list, &tpm_chip_list); - spin_unlock(&driver_lock); - chip->flags |= TPM_CHIP_FLAG_REGISTERED; if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { - rc = __compat_only_sysfs_link_entry_to_kobj(&chip->pdev->kobj, - &chip->dev.kobj, - "ppi"); + rc = __compat_only_sysfs_link_entry_to_kobj( + &chip->dev.parent->kobj, &chip->dev.kobj, "ppi"); if (rc && rc != -ENOENT) { tpm_chip_unregister(chip); return rc; @@ -259,6 +361,9 @@ EXPORT_SYMBOL_GPL(tpm_chip_register); * Takes the chip first away from the list of available TPM chips and then * cleans up all the resources reserved by tpm_chip_register(). * + * Once this function returns the driver call backs in 'op's will not be + * running and will no longer start. + * * NOTE: This function should be only called before deinitializing chip * resources. */ @@ -267,13 +372,8 @@ void tpm_chip_unregister(struct tpm_chip *chip) if (!(chip->flags & TPM_CHIP_FLAG_REGISTERED)) return; - spin_lock(&driver_lock); - list_del_rcu(&chip->list); - spin_unlock(&driver_lock); - synchronize_rcu(); - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) - sysfs_remove_link(&chip->pdev->kobj, "ppi"); + sysfs_remove_link(&chip->dev.parent->kobj, "ppi"); tpm1_chip_unregister(chip); tpm_del_char_device(chip); diff --git a/drivers/char/tpm/tpm-dev.c b/drivers/char/tpm/tpm-dev.c index 4f3137d9a35e..912ad30be585 100644 --- a/drivers/char/tpm/tpm-dev.c +++ b/drivers/char/tpm/tpm-dev.c @@ -61,7 +61,7 @@ static int tpm_open(struct inode *inode, struct file *file) * by the check of is_open variable, which is protected * by driver_lock. */ if (test_and_set_bit(0, &chip->is_open)) { - dev_dbg(chip->pdev, "Another process owns this TPM\n"); + dev_dbg(&chip->dev, "Another process owns this TPM\n"); return -EBUSY; } @@ -79,7 +79,6 @@ static int tpm_open(struct inode *inode, struct file *file) INIT_WORK(&priv->work, timeout_work); file->private_data = priv; - get_device(chip->pdev); return 0; } @@ -137,9 +136,18 @@ static ssize_t tpm_write(struct file *file, const char __user *buf, return -EFAULT; } - /* atomic tpm command send and result receive */ + /* atomic tpm command send and result receive. We only hold the ops + * lock during this period so that the tpm can be unregistered even if + * the char dev is held open. + */ + if (tpm_try_get_ops(priv->chip)) { + mutex_unlock(&priv->buffer_mutex); + return -EPIPE; + } out_size = tpm_transmit(priv->chip, priv->data_buffer, sizeof(priv->data_buffer), 0); + + tpm_put_ops(priv->chip); if (out_size < 0) { mutex_unlock(&priv->buffer_mutex); return out_size; @@ -166,7 +174,6 @@ static int tpm_release(struct inode *inode, struct file *file) file->private_data = NULL; atomic_set(&priv->data_pending, 0); clear_bit(0, &priv->chip->is_open); - put_device(priv->chip->pdev); kfree(priv); return 0; } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 17abe52e6365..aaa5fa95dede 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -343,7 +343,7 @@ ssize_t tpm_transmit(struct tpm_chip *chip, const u8 *buf, size_t bufsiz, if (count == 0) return -ENODATA; if (count > bufsiz) { - dev_err(chip->pdev, + dev_err(&chip->dev, "invalid count value %x %zx\n", count, bufsiz); return -E2BIG; } @@ -353,7 +353,7 @@ ssize_t tpm_transmit(struct tpm_chip *chip, const u8 *buf, size_t bufsiz, rc = chip->ops->send(chip, (u8 *) buf, count); if (rc < 0) { - dev_err(chip->pdev, + dev_err(&chip->dev, "tpm_transmit: tpm_send: error %zd\n", rc); goto out; } @@ -372,7 +372,7 @@ ssize_t tpm_transmit(struct tpm_chip *chip, const u8 *buf, size_t bufsiz, goto out_recv; if (chip->ops->req_canceled(chip, status)) { - dev_err(chip->pdev, "Operation Canceled\n"); + dev_err(&chip->dev, "Operation Canceled\n"); rc = -ECANCELED; goto out; } @@ -382,14 +382,14 @@ ssize_t tpm_transmit(struct tpm_chip *chip, const u8 *buf, size_t bufsiz, } while (time_before(jiffies, stop)); chip->ops->cancel(chip); - dev_err(chip->pdev, "Operation Timed out\n"); + dev_err(&chip->dev, "Operation Timed out\n"); rc = -ETIME; goto out; out_recv: rc = chip->ops->recv(chip, (u8 *) buf, bufsiz); if (rc < 0) - dev_err(chip->pdev, + dev_err(&chip->dev, "tpm_transmit: tpm_recv: error %zd\n", rc); out: if (!(flags & TPM_TRANSMIT_UNLOCKED)) @@ -416,7 +416,7 @@ ssize_t tpm_transmit_cmd(struct tpm_chip *chip, const void *cmd, err = be32_to_cpu(header->return_code); if (err != 0 && desc) - dev_err(chip->pdev, "A TPM error (%d) occurred %s\n", err, + dev_err(&chip->dev, "A TPM error (%d) occurred %s\n", err, desc); return err; @@ -514,7 +514,7 @@ int tpm_get_timeouts(struct tpm_chip *chip) if (rc == TPM_ERR_INVALID_POSTINIT) { /* The TPM is not started, we are the first to talk to it. Execute a startup command. */ - dev_info(chip->pdev, "Issuing TPM_STARTUP"); + dev_info(&chip->dev, "Issuing TPM_STARTUP"); if (tpm_startup(chip, TPM_ST_CLEAR)) return rc; @@ -526,7 +526,7 @@ int tpm_get_timeouts(struct tpm_chip *chip) 0, NULL); } if (rc) { - dev_err(chip->pdev, + dev_err(&chip->dev, "A TPM error (%zd) occurred attempting to determine the timeouts\n", rc); goto duration; @@ -565,7 +565,7 @@ int tpm_get_timeouts(struct tpm_chip *chip) /* Report adjusted timeouts */ if (chip->vendor.timeout_adjusted) { - dev_info(chip->pdev, + dev_info(&chip->dev, HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n", old_timeout[0], new_timeout[0], old_timeout[1], new_timeout[1], @@ -612,7 +612,7 @@ duration: chip->vendor.duration[TPM_MEDIUM] *= 1000; chip->vendor.duration[TPM_LONG] *= 1000; chip->vendor.duration_adjusted = true; - dev_info(chip->pdev, "Adjusting TPM timeout parameters."); + dev_info(&chip->dev, "Adjusting TPM timeout parameters."); } return 0; } @@ -687,7 +687,7 @@ int tpm_is_tpm2(u32 chip_num) rc = (chip->flags & TPM_CHIP_FLAG_TPM2) != 0; - tpm_chip_put(chip); + tpm_put_ops(chip); return rc; } @@ -716,7 +716,7 @@ int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf) rc = tpm2_pcr_read(chip, pcr_idx, res_buf); else rc = tpm_pcr_read_dev(chip, pcr_idx, res_buf); - tpm_chip_put(chip); + tpm_put_ops(chip); return rc; } EXPORT_SYMBOL_GPL(tpm_pcr_read); @@ -751,7 +751,7 @@ int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash) if (chip->flags & TPM_CHIP_FLAG_TPM2) { rc = tpm2_pcr_extend(chip, pcr_idx, hash); - tpm_chip_put(chip); + tpm_put_ops(chip); return rc; } @@ -761,7 +761,7 @@ int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash) rc = tpm_transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE, 0, "attempting extend a PCR value"); - tpm_chip_put(chip); + tpm_put_ops(chip); return rc; } EXPORT_SYMBOL_GPL(tpm_pcr_extend); @@ -802,7 +802,9 @@ int tpm_do_selftest(struct tpm_chip *chip) * around 300ms while the self test is ongoing, keep trying * until the self test duration expires. */ if (rc == -ETIME) { - dev_info(chip->pdev, HW_ERR "TPM command timed out during continue self test"); + dev_info( + &chip->dev, HW_ERR + "TPM command timed out during continue self test"); msleep(delay_msec); continue; } @@ -812,7 +814,7 @@ int tpm_do_selftest(struct tpm_chip *chip) rc = be32_to_cpu(cmd.header.out.return_code); if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) { - dev_info(chip->pdev, + dev_info(&chip->dev, "TPM is disabled/deactivated (0x%X)\n", rc); /* TPM is disabled and/or deactivated; driver can * proceed and TPM does handle commands for @@ -840,7 +842,7 @@ int tpm_send(u32 chip_num, void *cmd, size_t buflen) rc = tpm_transmit_cmd(chip, cmd, buflen, 0, "attempting tpm_cmd"); - tpm_chip_put(chip); + tpm_put_ops(chip); return rc; } EXPORT_SYMBOL_GPL(tpm_send); @@ -966,10 +968,10 @@ int tpm_pm_suspend(struct device *dev) } if (rc) - dev_err(chip->pdev, + dev_err(&chip->dev, "Error (%d) sending savestate before suspend\n", rc); else if (try > 0) - dev_warn(chip->pdev, "TPM savestate took %dms\n", + dev_warn(&chip->dev, "TPM savestate took %dms\n", try * TPM_TIMEOUT_RETRY); return rc; @@ -1023,7 +1025,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max) if (chip->flags & TPM_CHIP_FLAG_TPM2) { err = tpm2_get_random(chip, out, max); - tpm_chip_put(chip); + tpm_put_ops(chip); return err; } @@ -1045,7 +1047,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max) num_bytes -= recd; } while (retries-- && total < max); - tpm_chip_put(chip); + tpm_put_ops(chip); return total ? total : -EIO; } EXPORT_SYMBOL_GPL(tpm_get_random); @@ -1071,7 +1073,7 @@ int tpm_seal_trusted(u32 chip_num, struct trusted_key_payload *payload, rc = tpm2_seal_trusted(chip, payload, options); - tpm_chip_put(chip); + tpm_put_ops(chip); return rc; } EXPORT_SYMBOL_GPL(tpm_seal_trusted); @@ -1097,7 +1099,8 @@ int tpm_unseal_trusted(u32 chip_num, struct trusted_key_payload *payload, rc = tpm2_unseal_trusted(chip, payload, options); - tpm_chip_put(chip); + tpm_put_ops(chip); + return rc; } EXPORT_SYMBOL_GPL(tpm_unseal_trusted); @@ -1124,6 +1127,7 @@ static int __init tpm_init(void) static void __exit tpm_exit(void) { + idr_destroy(&dev_nums_idr); class_destroy(tpm_class); unregister_chrdev_region(tpm_devt, TPM_NUM_DEVICES); } diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index f880856aa75e..06ac6e9657d2 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -38,6 +38,8 @@ static ssize_t pubek_show(struct device *dev, struct device_attribute *attr, struct tpm_chip *chip = dev_get_drvdata(dev); + memset(&tpm_cmd, 0, sizeof(tpm_cmd)); + tpm_cmd.header.in = tpm_readpubek_header; err = tpm_transmit_cmd(chip, &tpm_cmd, READ_PUBEK_RESULT_SIZE, 0, "attempting to read the PUBEK"); @@ -284,16 +286,28 @@ static const struct attribute_group tpm_dev_group = { int tpm_sysfs_add_device(struct tpm_chip *chip) { int err; - err = sysfs_create_group(&chip->pdev->kobj, + + /* XXX: If you wish to remove this restriction, you must first update + * tpm_sysfs to explicitly lock chip->ops. + */ + if (chip->flags & TPM_CHIP_FLAG_TPM2) + return 0; + + err = sysfs_create_group(&chip->dev.parent->kobj, &tpm_dev_group); if (err) - dev_err(chip->pdev, + dev_err(&chip->dev, "failed to create sysfs attributes, %d\n", err); return err; } void tpm_sysfs_del_device(struct tpm_chip *chip) { - sysfs_remove_group(&chip->pdev->kobj, &tpm_dev_group); + /* The sysfs routines rely on an implicit tpm_try_get_ops, this + * function is called before ops is null'd and the sysfs core + * synchronizes this removal so that no callbacks are running or can + * run again + */ + sysfs_remove_group(&chip->dev.parent->kobj, &tpm_dev_group); } diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 2216861f89f1..772d99b3a8e4 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -34,7 +34,7 @@ enum tpm_const { TPM_MINOR = 224, /* officially assigned */ TPM_BUFSIZE = 4096, - TPM_NUM_DEVICES = 256, + TPM_NUM_DEVICES = 65536, TPM_RETRY = 50, /* 5 seconds */ }; @@ -171,11 +171,16 @@ enum tpm_chip_flags { }; struct tpm_chip { - struct device *pdev; /* Device stuff */ struct device dev; struct cdev cdev; + /* A driver callback under ops cannot be run unless ops_sem is held + * (sometimes implicitly, eg for the sysfs code). ops becomes null + * when the driver is unregistered, see tpm_try_get_ops. + */ + struct rw_semaphore ops_sem; const struct tpm_class_ops *ops; + unsigned int flags; int dev_num; /* /dev/tpm# */ @@ -195,17 +200,10 @@ struct tpm_chip { acpi_handle acpi_dev_handle; char ppi_version[TPM_PPI_VERSION_LEN + 1]; #endif /* CONFIG_ACPI */ - - struct list_head list; }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -static inline void tpm_chip_put(struct tpm_chip *chip) -{ - module_put(chip->pdev->driver->owner); -} - static inline int tpm_read_index(int base, int index) { outb(index, base); @@ -497,6 +495,7 @@ static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) extern struct class *tpm_class; extern dev_t tpm_devt; extern const struct file_operations tpm_fops; +extern struct idr dev_nums_idr; enum tpm_transmit_flags { TPM_TRANSMIT_UNLOCKED = BIT(0), @@ -517,6 +516,9 @@ extern int wait_for_tpm_stat(struct tpm_chip *, u8, unsigned long, wait_queue_head_t *, bool); struct tpm_chip *tpm_chip_find_get(int chip_num); +__must_check int tpm_try_get_ops(struct tpm_chip *chip); +void tpm_put_ops(struct tpm_chip *chip); + extern struct tpm_chip *tpmm_chip_alloc(struct device *dev, const struct tpm_class_ops *ops); extern int tpm_chip_register(struct tpm_chip *chip); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index cb7e4f6b70ba..286bd090a488 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -570,7 +570,7 @@ static void tpm2_flush_context_cmd(struct tpm_chip *chip, u32 handle, rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_FLUSH_CONTEXT); if (rc) { - dev_warn(chip->pdev, "0x%08x was not flushed, out of memory\n", + dev_warn(&chip->dev, "0x%08x was not flushed, out of memory\n", handle); return; } @@ -580,7 +580,7 @@ static void tpm2_flush_context_cmd(struct tpm_chip *chip, u32 handle, rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, flags, "flushing context"); if (rc) - dev_warn(chip->pdev, "0x%08x was not flushed, rc=%d\n", handle, + dev_warn(&chip->dev, "0x%08x was not flushed, rc=%d\n", handle, rc); tpm_buf_destroy(&buf); @@ -753,7 +753,7 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type) * except print the error code on a system failure. */ if (rc < 0) - dev_warn(chip->pdev, "transmit returned %d while stopping the TPM", + dev_warn(&chip->dev, "transmit returned %d while stopping the TPM", rc); } EXPORT_SYMBOL_GPL(tpm2_shutdown); @@ -820,7 +820,7 @@ static int tpm2_start_selftest(struct tpm_chip *chip, bool full) * immediately. This is a workaround for that. */ if (rc == TPM2_RC_TESTING) { - dev_warn(chip->pdev, "Got RC_TESTING, ignoring\n"); + dev_warn(&chip->dev, "Got RC_TESTING, ignoring\n"); rc = 0; } diff --git a/drivers/char/tpm/tpm_atmel.c b/drivers/char/tpm/tpm_atmel.c index dfadad0916a1..a48a878f791d 100644 --- a/drivers/char/tpm/tpm_atmel.c +++ b/drivers/char/tpm/tpm_atmel.c @@ -49,7 +49,7 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count) for (i = 0; i < 6; i++) { status = ioread8(chip->vendor.iobase + 1); if ((status & ATML_STATUS_DATA_AVAIL) == 0) { - dev_err(chip->pdev, "error reading header\n"); + dev_err(&chip->dev, "error reading header\n"); return -EIO; } *buf++ = ioread8(chip->vendor.iobase); @@ -60,12 +60,12 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count) size = be32_to_cpu(*native_size); if (count < size) { - dev_err(chip->pdev, + dev_err(&chip->dev, "Recv size(%d) less than available space\n", size); for (; i < size; i++) { /* clear the waiting data anyway */ status = ioread8(chip->vendor.iobase + 1); if ((status & ATML_STATUS_DATA_AVAIL) == 0) { - dev_err(chip->pdev, "error reading data\n"); + dev_err(&chip->dev, "error reading data\n"); return -EIO; } } @@ -76,7 +76,7 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count) for (; i < size; i++) { status = ioread8(chip->vendor.iobase + 1); if ((status & ATML_STATUS_DATA_AVAIL) == 0) { - dev_err(chip->pdev, "error reading data\n"); + dev_err(&chip->dev, "error reading data\n"); return -EIO; } *buf++ = ioread8(chip->vendor.iobase); @@ -86,7 +86,7 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count) status = ioread8(chip->vendor.iobase + 1); if (status & ATML_STATUS_DATA_AVAIL) { - dev_err(chip->pdev, "data available is stuck\n"); + dev_err(&chip->dev, "data available is stuck\n"); return -EIO; } @@ -97,9 +97,9 @@ static int tpm_atml_send(struct tpm_chip *chip, u8 *buf, size_t count) { int i; - dev_dbg(chip->pdev, "tpm_atml_send:\n"); + dev_dbg(&chip->dev, "tpm_atml_send:\n"); for (i = 0; i < count; i++) { - dev_dbg(chip->pdev, "%d 0x%x(%d)\n", i, buf[i], buf[i]); + dev_dbg(&chip->dev, "%d 0x%x(%d)\n", i, buf[i], buf[i]); iowrite8(buf[i], chip->vendor.iobase); } diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 2b21398c3adc..35308dfff754 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -118,8 +118,7 @@ static int crb_recv(struct tpm_chip *chip, u8 *buf, size_t count) memcpy_fromio(buf, priv->rsp, 6); expected = be32_to_cpup((__be32 *) &buf[2]); - - if (expected > count) + if (expected > count || expected < 6) return -EIO; memcpy_fromio(&buf[6], &priv->rsp[6], expected - 6); diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c index 8dfb88b9739c..dd8f0eb3170a 100644 --- a/drivers/char/tpm/tpm_i2c_atmel.c +++ b/drivers/char/tpm/tpm_i2c_atmel.c @@ -52,7 +52,7 @@ struct priv_data { static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len) { struct priv_data *priv = chip->vendor.priv; - struct i2c_client *client = to_i2c_client(chip->pdev); + struct i2c_client *client = to_i2c_client(chip->dev.parent); s32 status; priv->len = 0; @@ -62,7 +62,7 @@ static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len) status = i2c_master_send(client, buf, len); - dev_dbg(chip->pdev, + dev_dbg(&chip->dev, "%s(buf=%*ph len=%0zx) -> sts=%d\n", __func__, (int)min_t(size_t, 64, len), buf, len, status); return status; @@ -71,7 +71,7 @@ static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len) static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count) { struct priv_data *priv = chip->vendor.priv; - struct i2c_client *client = to_i2c_client(chip->pdev); + struct i2c_client *client = to_i2c_client(chip->dev.parent); struct tpm_output_header *hdr = (struct tpm_output_header *)priv->buffer; u32 expected_len; @@ -88,7 +88,7 @@ static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count) return -ENOMEM; if (priv->len >= expected_len) { - dev_dbg(chip->pdev, + dev_dbg(&chip->dev, "%s early(buf=%*ph count=%0zx) -> ret=%d\n", __func__, (int)min_t(size_t, 64, expected_len), buf, count, expected_len); @@ -97,7 +97,7 @@ static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count) } rc = i2c_master_recv(client, buf, expected_len); - dev_dbg(chip->pdev, + dev_dbg(&chip->dev, "%s reread(buf=%*ph count=%0zx) -> ret=%d\n", __func__, (int)min_t(size_t, 64, expected_len), buf, count, expected_len); @@ -106,13 +106,13 @@ static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count) static void i2c_atmel_cancel(struct tpm_chip *chip) { - dev_err(chip->pdev, "TPM operation cancellation was requested, but is not supported"); + dev_err(&chip->dev, "TPM operation cancellation was requested, but is not supported"); } static u8 i2c_atmel_read_status(struct tpm_chip *chip) { struct priv_data *priv = chip->vendor.priv; - struct i2c_client *client = to_i2c_client(chip->pdev); + struct i2c_client *client = to_i2c_client(chip->dev.parent); int rc; /* The TPM fails the I2C read until it is ready, so we do the entire @@ -125,7 +125,7 @@ static u8 i2c_atmel_read_status(struct tpm_chip *chip) /* Once the TPM has completed the command the command remains readable * until another command is issued. */ rc = i2c_master_recv(client, priv->buffer, sizeof(priv->buffer)); - dev_dbg(chip->pdev, + dev_dbg(&chip->dev, "%s: sts=%d", __func__, rc); if (rc <= 0) return 0; diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c index 63d5d22e9e60..f2aa99e34b4b 100644 --- a/drivers/char/tpm/tpm_i2c_infineon.c +++ b/drivers/char/tpm/tpm_i2c_infineon.c @@ -446,7 +446,7 @@ static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count) /* read first 10 bytes, including tag, paramsize, and result */ size = recv_data(chip, buf, TPM_HEADER_SIZE); if (size < TPM_HEADER_SIZE) { - dev_err(chip->pdev, "Unable to read header\n"); + dev_err(&chip->dev, "Unable to read header\n"); goto out; } @@ -459,14 +459,14 @@ static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count) size += recv_data(chip, &buf[TPM_HEADER_SIZE], expected - TPM_HEADER_SIZE); if (size < expected) { - dev_err(chip->pdev, "Unable to read remainder of result\n"); + dev_err(&chip->dev, "Unable to read remainder of result\n"); size = -ETIME; goto out; } wait_for_stat(chip, TPM_STS_VALID, chip->vendor.timeout_c, &status); if (status & TPM_STS_DATA_AVAIL) { /* retry? */ - dev_err(chip->pdev, "Error left over data\n"); + dev_err(&chip->dev, "Error left over data\n"); size = -EIO; goto out; } diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index 847f1597fe9b..a1e1474dda30 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -96,13 +96,13 @@ static s32 i2c_nuvoton_write_buf(struct i2c_client *client, u8 offset, u8 size, /* read TPM_STS register */ static u8 i2c_nuvoton_read_status(struct tpm_chip *chip) { - struct i2c_client *client = to_i2c_client(chip->pdev); + struct i2c_client *client = to_i2c_client(chip->dev.parent); s32 status; u8 data; status = i2c_nuvoton_read_buf(client, TPM_STS, 1, &data); if (status <= 0) { - dev_err(chip->pdev, "%s() error return %d\n", __func__, + dev_err(&chip->dev, "%s() error return %d\n", __func__, status); data = TPM_STS_ERR_VAL; } @@ -127,13 +127,13 @@ static s32 i2c_nuvoton_write_status(struct i2c_client *client, u8 data) /* write commandReady to TPM_STS register */ static void i2c_nuvoton_ready(struct tpm_chip *chip) { - struct i2c_client *client = to_i2c_client(chip->pdev); + struct i2c_client *client = to_i2c_client(chip->dev.parent); s32 status; /* this causes the current command to be aborted */ status = i2c_nuvoton_write_status(client, TPM_STS_COMMAND_READY); if (status < 0) - dev_err(chip->pdev, + dev_err(&chip->dev, "%s() fail to write TPM_STS.commandReady\n", __func__); } @@ -212,7 +212,7 @@ static int i2c_nuvoton_wait_for_stat(struct tpm_chip *chip, u8 mask, u8 value, return 0; } while (time_before(jiffies, stop)); } - dev_err(chip->pdev, "%s(%02x, %02x) -> timeout\n", __func__, mask, + dev_err(&chip->dev, "%s(%02x, %02x) -> timeout\n", __func__, mask, value); return -ETIMEDOUT; } @@ -240,7 +240,7 @@ static int i2c_nuvoton_recv_data(struct i2c_client *client, &chip->vendor.read_queue) == 0) { burst_count = i2c_nuvoton_get_burstcount(client, chip); if (burst_count < 0) { - dev_err(chip->pdev, + dev_err(&chip->dev, "%s() fail to read burstCount=%d\n", __func__, burst_count); return -EIO; @@ -249,12 +249,12 @@ static int i2c_nuvoton_recv_data(struct i2c_client *client, rc = i2c_nuvoton_read_buf(client, TPM_DATA_FIFO_R, bytes2read, &buf[size]); if (rc < 0) { - dev_err(chip->pdev, + dev_err(&chip->dev, "%s() fail on i2c_nuvoton_read_buf()=%d\n", __func__, rc); return -EIO; } - dev_dbg(chip->pdev, "%s(%d):", __func__, bytes2read); + dev_dbg(&chip->dev, "%s(%d):", __func__, bytes2read); size += bytes2read; } @@ -264,7 +264,7 @@ static int i2c_nuvoton_recv_data(struct i2c_client *client, /* Read TPM command results */ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count) { - struct device *dev = chip->pdev; + struct device *dev = chip->dev.parent; struct i2c_client *client = to_i2c_client(dev); s32 rc; int expected, status, burst_count, retries, size = 0; @@ -334,7 +334,7 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count) break; } i2c_nuvoton_ready(chip); - dev_dbg(chip->pdev, "%s() -> %d\n", __func__, size); + dev_dbg(&chip->dev, "%s() -> %d\n", __func__, size); return size; } @@ -347,7 +347,7 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count) */ static int i2c_nuvoton_send(struct tpm_chip *chip, u8 *buf, size_t len) { - struct device *dev = chip->pdev; + struct device *dev = chip->dev.parent; struct i2c_client *client = to_i2c_client(dev); u32 ordinal; size_t count = 0; diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c index 6c488e635fdd..e3cf9f3545c5 100644 --- a/drivers/char/tpm/tpm_infineon.c +++ b/drivers/char/tpm/tpm_infineon.c @@ -195,9 +195,9 @@ static int wait(struct tpm_chip *chip, int wait_for_bit) } if (i == TPM_MAX_TRIES) { /* timeout occurs */ if (wait_for_bit == STAT_XFE) - dev_err(chip->pdev, "Timeout in wait(STAT_XFE)\n"); + dev_err(&chip->dev, "Timeout in wait(STAT_XFE)\n"); if (wait_for_bit == STAT_RDA) - dev_err(chip->pdev, "Timeout in wait(STAT_RDA)\n"); + dev_err(&chip->dev, "Timeout in wait(STAT_RDA)\n"); return -EIO; } return 0; @@ -220,7 +220,7 @@ static void wait_and_send(struct tpm_chip *chip, u8 sendbyte) static void tpm_wtx(struct tpm_chip *chip) { number_of_wtx++; - dev_info(chip->pdev, "Granting WTX (%02d / %02d)\n", + dev_info(&chip->dev, "Granting WTX (%02d / %02d)\n", number_of_wtx, TPM_MAX_WTX_PACKAGES); wait_and_send(chip, TPM_VL_VER); wait_and_send(chip, TPM_CTRL_WTX); @@ -231,7 +231,7 @@ static void tpm_wtx(struct tpm_chip *chip) static void tpm_wtx_abort(struct tpm_chip *chip) { - dev_info(chip->pdev, "Aborting WTX\n"); + dev_info(&chip->dev, "Aborting WTX\n"); wait_and_send(chip, TPM_VL_VER); wait_and_send(chip, TPM_CTRL_WTX_ABORT); wait_and_send(chip, 0x00); @@ -257,7 +257,7 @@ recv_begin: } if (buf[0] != TPM_VL_VER) { - dev_err(chip->pdev, + dev_err(&chip->dev, "Wrong transport protocol implementation!\n"); return -EIO; } @@ -272,7 +272,7 @@ recv_begin: } if ((size == 0x6D00) && (buf[1] == 0x80)) { - dev_err(chip->pdev, "Error handling on vendor layer!\n"); + dev_err(&chip->dev, "Error handling on vendor layer!\n"); return -EIO; } @@ -284,7 +284,7 @@ recv_begin: } if (buf[1] == TPM_CTRL_WTX) { - dev_info(chip->pdev, "WTX-package received\n"); + dev_info(&chip->dev, "WTX-package received\n"); if (number_of_wtx < TPM_MAX_WTX_PACKAGES) { tpm_wtx(chip); goto recv_begin; @@ -295,14 +295,14 @@ recv_begin: } if (buf[1] == TPM_CTRL_WTX_ABORT_ACK) { - dev_info(chip->pdev, "WTX-abort acknowledged\n"); + dev_info(&chip->dev, "WTX-abort acknowledged\n"); return size; } if (buf[1] == TPM_CTRL_ERROR) { - dev_err(chip->pdev, "ERROR-package received:\n"); + dev_err(&chip->dev, "ERROR-package received:\n"); if (buf[4] == TPM_INF_NAK) - dev_err(chip->pdev, + dev_err(&chip->dev, "-> Negative acknowledgement" " - retransmit command!\n"); return -EIO; @@ -321,7 +321,7 @@ static int tpm_inf_send(struct tpm_chip *chip, u8 * buf, size_t count) ret = empty_fifo(chip, 1); if (ret) { - dev_err(chip->pdev, "Timeout while clearing FIFO\n"); + dev_err(&chip->dev, "Timeout while clearing FIFO\n"); return -EIO; } diff --git a/drivers/char/tpm/tpm_nsc.c b/drivers/char/tpm/tpm_nsc.c index 289389ecef84..766370bed60c 100644 --- a/drivers/char/tpm/tpm_nsc.c +++ b/drivers/char/tpm/tpm_nsc.c @@ -113,7 +113,7 @@ static int nsc_wait_for_ready(struct tpm_chip *chip) } while (time_before(jiffies, stop)); - dev_info(chip->pdev, "wait for ready failed\n"); + dev_info(&chip->dev, "wait for ready failed\n"); return -EBUSY; } @@ -129,12 +129,12 @@ static int tpm_nsc_recv(struct tpm_chip *chip, u8 * buf, size_t count) return -EIO; if (wait_for_stat(chip, NSC_STATUS_F0, NSC_STATUS_F0, &data) < 0) { - dev_err(chip->pdev, "F0 timeout\n"); + dev_err(&chip->dev, "F0 timeout\n"); return -EIO; } if ((data = inb(chip->vendor.base + NSC_DATA)) != NSC_COMMAND_NORMAL) { - dev_err(chip->pdev, "not in normal mode (0x%x)\n", + dev_err(&chip->dev, "not in normal mode (0x%x)\n", data); return -EIO; } @@ -143,7 +143,7 @@ static int tpm_nsc_recv(struct tpm_chip *chip, u8 * buf, size_t count) for (p = buffer; p < &buffer[count]; p++) { if (wait_for_stat (chip, NSC_STATUS_OBF, NSC_STATUS_OBF, &data) < 0) { - dev_err(chip->pdev, + dev_err(&chip->dev, "OBF timeout (while reading data)\n"); return -EIO; } @@ -154,11 +154,11 @@ static int tpm_nsc_recv(struct tpm_chip *chip, u8 * buf, size_t count) if ((data & NSC_STATUS_F0) == 0 && (wait_for_stat(chip, NSC_STATUS_F0, NSC_STATUS_F0, &data) < 0)) { - dev_err(chip->pdev, "F0 not set\n"); + dev_err(&chip->dev, "F0 not set\n"); return -EIO; } if ((data = inb(chip->vendor.base + NSC_DATA)) != NSC_COMMAND_EOC) { - dev_err(chip->pdev, + dev_err(&chip->dev, "expected end of command(0x%x)\n", data); return -EIO; } @@ -189,19 +189,19 @@ static int tpm_nsc_send(struct tpm_chip *chip, u8 * buf, size_t count) return -EIO; if (wait_for_stat(chip, NSC_STATUS_IBF, 0, &data) < 0) { - dev_err(chip->pdev, "IBF timeout\n"); + dev_err(&chip->dev, "IBF timeout\n"); return -EIO; } outb(NSC_COMMAND_NORMAL, chip->vendor.base + NSC_COMMAND); if (wait_for_stat(chip, NSC_STATUS_IBR, NSC_STATUS_IBR, &data) < 0) { - dev_err(chip->pdev, "IBR timeout\n"); + dev_err(&chip->dev, "IBR timeout\n"); return -EIO; } for (i = 0; i < count; i++) { if (wait_for_stat(chip, NSC_STATUS_IBF, 0, &data) < 0) { - dev_err(chip->pdev, + dev_err(&chip->dev, "IBF timeout (while writing data)\n"); return -EIO; } @@ -209,7 +209,7 @@ static int tpm_nsc_send(struct tpm_chip *chip, u8 * buf, size_t count) } if (wait_for_stat(chip, NSC_STATUS_IBF, 0, &data) < 0) { - dev_err(chip->pdev, "IBF timeout\n"); + dev_err(&chip->dev, "IBF timeout\n"); return -EIO; } outb(NSC_COMMAND_EOC, chip->vendor.base + NSC_COMMAND); diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 65f7eecc45b0..7f13221aeb30 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -293,7 +293,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count) /* read first 10 bytes, including tag, paramsize, and result */ if ((size = recv_data(chip, buf, TPM_HEADER_SIZE)) < TPM_HEADER_SIZE) { - dev_err(chip->pdev, "Unable to read header\n"); + dev_err(&chip->dev, "Unable to read header\n"); goto out; } @@ -306,7 +306,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count) if ((size += recv_data(chip, &buf[TPM_HEADER_SIZE], expected - TPM_HEADER_SIZE)) < expected) { - dev_err(chip->pdev, "Unable to read remainder of result\n"); + dev_err(&chip->dev, "Unable to read remainder of result\n"); size = -ETIME; goto out; } @@ -315,7 +315,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count) &chip->vendor.int_queue, false); status = tpm_tis_status(chip); if (status & TPM_STS_DATA_AVAIL) { /* retry? */ - dev_err(chip->pdev, "Error left over data\n"); + dev_err(&chip->dev, "Error left over data\n"); size = -EIO; goto out; } @@ -401,7 +401,7 @@ static void disable_interrupts(struct tpm_chip *chip) iowrite32(intmask, chip->vendor.iobase + TPM_INT_ENABLE(chip->vendor.locality)); - free_irq(chip->vendor.irq, chip); + devm_free_irq(&chip->dev, chip->vendor.irq, chip); chip->vendor.irq = 0; } @@ -463,7 +463,7 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) msleep(1); if (!priv->irq_tested) { disable_interrupts(chip); - dev_err(chip->pdev, + dev_err(&chip->dev, FW_BUG "TPM interrupt not working, polling instead\n"); } priv->irq_tested = true; @@ -533,7 +533,7 @@ static int probe_itpm(struct tpm_chip *chip) rc = tpm_tis_send_data(chip, cmd_getticks, len); if (rc == 0) { - dev_info(chip->pdev, "Detected an iTPM.\n"); + dev_info(&chip->dev, "Detected an iTPM.\n"); rc = 1; } else rc = -EFAULT; @@ -766,7 +766,7 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, if (devm_request_irq (dev, i, tis_int_probe, IRQF_SHARED, chip->devname, chip) != 0) { - dev_info(chip->pdev, + dev_info(&chip->dev, "Unable to request irq: %d for probe\n", i); continue; @@ -818,7 +818,7 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, if (devm_request_irq (dev, chip->vendor.irq, tis_int_handler, IRQF_SHARED, chip->devname, chip) != 0) { - dev_info(chip->pdev, + dev_info(&chip->dev, "Unable to request irq: %d for use\n", chip->vendor.irq); chip->vendor.irq = 0; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 090183f812be..be0b09a0fb44 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1130,6 +1130,8 @@ static int put_chars(u32 vtermno, const char *buf, int count) { struct port *port; struct scatterlist sg[1]; + void *data; + int ret; if (unlikely(early_put_chars)) return early_put_chars(vtermno, buf, count); @@ -1138,8 +1140,14 @@ static int put_chars(u32 vtermno, const char *buf, int count) if (!port) return -EPIPE; - sg_init_one(sg, buf, count); - return __send_to_port(port, sg, 1, count, (void *)buf, false); + data = kmemdup(buf, count, GFP_ATOMIC); + if (!data) + return -ENOMEM; + + sg_init_one(sg, data, count); + ret = __send_to_port(port, sg, 1, count, data, false); + kfree(data); + return ret; } /* @@ -1856,7 +1864,7 @@ static void config_work_handler(struct work_struct *work) { struct ports_device *portdev; - portdev = container_of(work, struct ports_device, control_work); + portdev = container_of(work, struct ports_device, config_work); if (!use_multiport(portdev)) { struct virtio_device *vdev; struct port *port; diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index 820714c72d36..af9e9aff49e5 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -78,7 +78,9 @@ obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-$(CONFIG_ARCH_OMAP2PLUS) += ti/ obj-$(CONFIG_ARCH_U8500) += ux500/ obj-$(CONFIG_COMMON_CLK_VERSATILE) += versatile/ +ifeq ($(CONFIG_COMMON_CLK), y) obj-$(CONFIG_X86) += x86/ +endif obj-$(CONFIG_ARCH_ZX) += zte/ obj-$(CONFIG_ARCH_ZYNQ) += zynq/ obj-$(CONFIG_H8300) += h8300/ diff --git a/drivers/clk/sunxi/clk-simple-gates.c b/drivers/clk/sunxi/clk-simple-gates.c index 0214c6548afd..97cb4221de25 100644 --- a/drivers/clk/sunxi/clk-simple-gates.c +++ b/drivers/clk/sunxi/clk-simple-gates.c @@ -98,6 +98,8 @@ static void __init sunxi_simple_gates_init(struct device_node *node) sunxi_simple_gates_setup(node, NULL, 0); } +CLK_OF_DECLARE(sun4i_a10_gates, "allwinner,sun4i-a10-gates-clk", + sunxi_simple_gates_init); CLK_OF_DECLARE(sun4i_a10_apb0, "allwinner,sun4i-a10-apb0-gates-clk", sunxi_simple_gates_init); CLK_OF_DECLARE(sun4i_a10_apb1, "allwinner,sun4i-a10-apb1-gates-clk", diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7b728143440d..3c2a3bd94dc7 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -688,9 +688,11 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, char *buf) { unsigned int cur_freq = __cpufreq_get(policy); - if (!cur_freq) - return sprintf(buf, "<unknown>"); - return sprintf(buf, "%u\n", cur_freq); + + if (cur_freq) + return sprintf(buf, "%u\n", cur_freq); + + return sprintf(buf, "<unknown>\n"); } /** @@ -1246,6 +1248,9 @@ static int cpufreq_online(unsigned int cpu) for_each_cpu(j, policy->related_cpus) per_cpu(cpufreq_cpu_data, j) = policy; write_unlock_irqrestore(&cpufreq_driver_lock, flags); + } else { + policy->min = policy->user_policy.min; + policy->max = policy->user_policy.max; } if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { @@ -2511,6 +2516,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (!(cpufreq_driver->flags & CPUFREQ_STICKY) && list_empty(&cpufreq_policy_list)) { /* if all ->init() calls failed, unregister */ + ret = -ENODEV; pr_debug("%s: No CPU initialized for driver %s\n", __func__, driver_data->name); goto err_if_unreg; diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 1fa1deb6e91f..c395f9198fd2 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -212,8 +212,8 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf, int ret; ret = sscanf(buf, "%u", &input); - /* cannot be lower than 11 otherwise freq will not fall */ - if (ret != 1 || input < 11 || input > 100 || + /* cannot be lower than 1 otherwise freq will not fall */ + if (ret != 1 || input < 1 || input > 100 || input >= cs_tuners->up_threshold) return -EINVAL; diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c index f2929e628820..889c9b8b2237 100644 --- a/drivers/cpufreq/cpufreq_interactive.c +++ b/drivers/cpufreq/cpufreq_interactive.c @@ -312,13 +312,13 @@ static u64 update_load(int cpu) pcpu->policy->governor_data; u64 now; u64 now_idle; - unsigned int delta_idle; - unsigned int delta_time; + u64 delta_idle; + u64 delta_time; u64 active_time; now_idle = get_cpu_idle_time(cpu, &now, tunables->io_is_busy); - delta_idle = (unsigned int)(now_idle - pcpu->time_in_idle); - delta_time = (unsigned int)(now - pcpu->time_in_idle_timestamp); + delta_idle = (now_idle - pcpu->time_in_idle); + delta_time = (now - pcpu->time_in_idle_timestamp); if (delta_time <= delta_idle) active_time = 0; diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c index d6d425773fa4..5b2db3c6568f 100644 --- a/drivers/cpufreq/s3c2416-cpufreq.c +++ b/drivers/cpufreq/s3c2416-cpufreq.c @@ -400,7 +400,6 @@ static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy) rate = clk_get_rate(s3c_freq->hclk); if (rate < 133 * 1000 * 1000) { pr_err("cpufreq: HCLK not at 133MHz\n"); - clk_put(s3c_freq->hclk); ret = -EINVAL; goto err_armclk; } diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index 3179342277b8..593b18d475a3 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -28,11 +28,14 @@ #define DRA7_EFUSE_HAS_OD_MPU_OPP 11 #define DRA7_EFUSE_HAS_HIGH_MPU_OPP 15 +#define DRA76_EFUSE_HAS_PLUS_MPU_OPP 18 #define DRA7_EFUSE_HAS_ALL_MPU_OPP 23 +#define DRA76_EFUSE_HAS_ALL_MPU_OPP 24 #define DRA7_EFUSE_NOM_MPU_OPP BIT(0) #define DRA7_EFUSE_OD_MPU_OPP BIT(1) #define DRA7_EFUSE_HIGH_MPU_OPP BIT(2) +#define DRA76_EFUSE_PLUS_MPU_OPP BIT(3) #define VERSION_COUNT 2 @@ -86,6 +89,9 @@ static unsigned long dra7_efuse_xlate(unsigned long efuse, u32 rev) */ switch (efuse) { + case DRA76_EFUSE_HAS_PLUS_MPU_OPP: + case DRA76_EFUSE_HAS_ALL_MPU_OPP: + calculated_efuse |= DRA76_EFUSE_PLUS_MPU_OPP; case DRA7_EFUSE_HAS_ALL_MPU_OPP: case DRA7_EFUSE_HAS_HIGH_MPU_OPP: calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP; diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 0dadb6332f0e..7abe908427df 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -963,7 +963,9 @@ static int atmel_sha_finup(struct ahash_request *req) ctx->flags |= SHA_FLAGS_FINUP; err1 = atmel_sha_update(req); - if (err1 == -EINPROGRESS || err1 == -EBUSY) + if (err1 == -EINPROGRESS || + (err1 == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) return err1; /* diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 99d5e11db194..e06cc5df30be 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -498,7 +498,7 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in, ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result); if (!ret) { /* in progress */ - wait_for_completion_interruptible(&result.completion); + wait_for_completion(&result.completion); ret = result.err; #ifdef DEBUG print_hex_dump(KERN_ERR, diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 69d4a1326fee..53e61459c69f 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -278,7 +278,8 @@ static int deinstantiate_rng(struct device *ctrldev, int state_handle_mask) /* Try to run it through DECO0 */ ret = run_descriptor_deco0(ctrldev, desc, &status); - if (ret || status) { + if (ret || + (status && status != JRSTA_SSRC_JUMP_HALT_CC)) { dev_err(ctrldev, "Failed to deinstantiate RNG4 SH%d\n", sh_idx); diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c index e1eaf4ff9762..3ce1d5cdcbd2 100644 --- a/drivers/crypto/caam/key_gen.c +++ b/drivers/crypto/caam/key_gen.c @@ -103,7 +103,7 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result); if (!ret) { /* in progress */ - wait_for_completion_interruptible(&result.completion); + wait_for_completion(&result.completion); ret = result.err; #ifdef DEBUG print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ", diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 9a8a18aafd5c..6a60936b46e0 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -804,7 +804,7 @@ static void talitos_unregister_rng(struct device *dev) * crypto alg */ #define TALITOS_CRA_PRIORITY 3000 -#define TALITOS_MAX_KEY_SIZE 96 +#define TALITOS_MAX_KEY_SIZE (AES_MAX_KEY_SIZE + SHA512_BLOCK_SIZE) #define TALITOS_MAX_IV_LENGTH 16 /* max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */ struct talitos_ctx { @@ -1388,6 +1388,11 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher, { struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher); + if (keylen > TALITOS_MAX_KEY_SIZE) { + crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + memcpy(&ctx->key, key, keylen); ctx->keylen = keylen; diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c index 57ff46284f15..c97336a2ba92 100644 --- a/drivers/dma/ep93xx_dma.c +++ b/drivers/dma/ep93xx_dma.c @@ -325,6 +325,8 @@ static int m2p_hw_setup(struct ep93xx_dma_chan *edmac) | M2P_CONTROL_ENABLE; m2p_set_control(edmac, control); + edmac->buffer = 0; + return 0; } diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h index 690e3b4f8202..b36da3c1073f 100644 --- a/drivers/dma/ioat/hw.h +++ b/drivers/dma/ioat/hw.h @@ -64,6 +64,8 @@ #define PCI_DEVICE_ID_INTEL_IOAT_BDX8 0x6f2e #define PCI_DEVICE_ID_INTEL_IOAT_BDX9 0x6f2f +#define PCI_DEVICE_ID_INTEL_IOAT_SKX 0x2021 + #define IOAT_VER_1_2 0x12 /* Version 1.2 */ #define IOAT_VER_2_0 0x20 /* Version 2.0 */ #define IOAT_VER_3_0 0x30 /* Version 3.0 */ diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 4ef0c5e07912..abb75ebd65ea 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -105,6 +105,8 @@ static struct pci_device_id ioat_pci_tbl[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX8) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX9) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SKX) }, + /* I/OAT v3.3 platforms */ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) }, @@ -250,10 +252,15 @@ static bool is_bdx_ioat(struct pci_dev *pdev) } } +static inline bool is_skx_ioat(struct pci_dev *pdev) +{ + return (pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SKX) ? true : false; +} + static bool is_xeon_cb32(struct pci_dev *pdev) { return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) || - is_hsw_ioat(pdev) || is_bdx_ioat(pdev); + is_hsw_ioat(pdev) || is_bdx_ioat(pdev) || is_skx_ioat(pdev); } bool is_bwd_ioat(struct pci_dev *pdev) @@ -1350,6 +1357,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) device->version = readb(device->reg_base + IOAT_VER_OFFSET); if (device->version >= IOAT_VER_3_0) { + if (is_skx_ioat(pdev)) + device->version = IOAT_VER_3_2; err = ioat3_dma_probe(device, ioat_dca_enabled); if (device->version >= IOAT_VER_3_3) diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c index dd184b50e5b4..284627806b88 100644 --- a/drivers/dma/ipu/ipu_irq.c +++ b/drivers/dma/ipu/ipu_irq.c @@ -272,7 +272,7 @@ static void ipu_irq_handler(struct irq_desc *desc) u32 status; int i, line; - for (i = IPU_IRQ_NR_FN_BANKS; i < IPU_IRQ_NR_BANKS; i++) { + for (i = 0; i < IPU_IRQ_NR_BANKS; i++) { struct ipu_irq_bank *bank = irq_bank + i; raw_spin_lock(&bank_lock); diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c index b1bc945f008f..56410ea75ac5 100644 --- a/drivers/dma/sh/usb-dmac.c +++ b/drivers/dma/sh/usb-dmac.c @@ -117,7 +117,7 @@ struct usb_dmac { #define USB_DMASWR 0x0008 #define USB_DMASWR_SWR (1 << 0) #define USB_DMAOR 0x0060 -#define USB_DMAOR_AE (1 << 2) +#define USB_DMAOR_AE (1 << 1) #define USB_DMAOR_DME (1 << 0) #define USB_DMASAR 0x0000 diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c index e107779b1a2e..7a9f5ea495e5 100644 --- a/drivers/dma/ti-dma-crossbar.c +++ b/drivers/dma/ti-dma-crossbar.c @@ -145,6 +145,7 @@ static int ti_am335x_xbar_probe(struct platform_device *pdev) match = of_match_node(ti_am335x_master_match, dma_node); if (!match) { dev_err(&pdev->dev, "DMA master is not supported\n"); + of_node_put(dma_node); return -EINVAL; } @@ -331,6 +332,7 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev) match = of_match_node(ti_dra7_master_match, dma_node); if (!match) { dev_err(&pdev->dev, "DMA master is not supported\n"); + of_node_put(dma_node); return -EINVAL; } diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index b1c22cf18f7d..9ee9973b5c3e 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -16,6 +16,22 @@ #include "efistub.h" +#define EFI_DT_ADDR_CELLS_DEFAULT 2 +#define EFI_DT_SIZE_CELLS_DEFAULT 2 + +static void fdt_update_cell_size(efi_system_table_t *sys_table, void *fdt) +{ + int offset; + + offset = fdt_path_offset(fdt, "/"); + /* Set the #address-cells and #size-cells values for an empty tree */ + + fdt_setprop_u32(fdt, offset, "#address-cells", + EFI_DT_ADDR_CELLS_DEFAULT); + + fdt_setprop_u32(fdt, offset, "#size-cells", EFI_DT_SIZE_CELLS_DEFAULT); +} + efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, unsigned long orig_fdt_size, void *fdt, int new_fdt_size, char *cmdline_ptr, @@ -45,10 +61,18 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, } } - if (orig_fdt) + if (orig_fdt) { status = fdt_open_into(orig_fdt, fdt, new_fdt_size); - else + } else { status = fdt_create_empty_tree(fdt, new_fdt_size); + if (status == 0) { + /* + * Any failure from the following function is non + * critical + */ + fdt_update_cell_size(sys_table, fdt); + } + } if (status != 0) goto fdt_set_fail; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 51a9942cdb40..f4cae5357e40 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -681,6 +681,10 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev) DRM_INFO("Changing default dispclk from %dMhz to 600Mhz\n", adev->clock.default_dispclk / 100); adev->clock.default_dispclk = 60000; + } else if (adev->clock.default_dispclk <= 60000) { + DRM_INFO("Changing default dispclk from %dMhz to 625Mhz\n", + adev->clock.default_dispclk / 100); + adev->clock.default_dispclk = 62500; } adev->clock.dp_extclk = le16_to_cpu(firmware_info->info_21.usUniphyDPModeExtClkFreq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 25a3e2485cc2..2bc17a907ecf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -124,6 +124,13 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, } break; } + + if (!(*out_ring && (*out_ring)->adev)) { + DRM_ERROR("Ring %d is not initialized on IP %d\n", + ring, ip_type); + return -EINVAL; + } + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 7c42ff670080..a0924330d125 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -25,6 +25,7 @@ * Alex Deucher * Jerome Glisse */ +#include <linux/irq.h> #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> #include <drm/amdgpu_drm.h> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 475c38fe9245..e40a6d8b0b92 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1126,6 +1126,9 @@ static ssize_t amdgpu_ttm_vram_read(struct file *f, char __user *buf, if (size & 0x3 || *pos & 0x3) return -EINVAL; + if (*pos >= adev->mc.mc_vram_size) + return -ENXIO; + while (size) { unsigned long flags; uint32_t value; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c index 49aa35016653..247b088990dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c @@ -164,7 +164,7 @@ void amdgpu_atombios_crtc_powergate(struct drm_crtc *crtc, int state) struct drm_device *dev = crtc->dev; struct amdgpu_device *adev = dev->dev_private; int index = GetIndexIntoMasterTable(COMMAND, EnableDispPowerGating); - ENABLE_DISP_POWER_GATING_PARAMETERS_V2_1 args; + ENABLE_DISP_POWER_GATING_PS_ALLOCATION args; memset(&args, 0, sizeof(args)); @@ -177,7 +177,7 @@ void amdgpu_atombios_crtc_powergate(struct drm_crtc *crtc, int state) void amdgpu_atombios_crtc_powergate_init(struct amdgpu_device *adev) { int index = GetIndexIntoMasterTable(COMMAND, EnableDispPowerGating); - ENABLE_DISP_POWER_GATING_PARAMETERS_V2_1 args; + ENABLE_DISP_POWER_GATING_PS_ALLOCATION args; memset(&args, 0, sizeof(args)); diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index 57a2e347f04d..0f0094b58d1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -893,6 +893,12 @@ static bool ci_dpm_vblank_too_short(struct amdgpu_device *adev) u32 vblank_time = amdgpu_dpm_get_vblank_time(adev); u32 switch_limit = adev->mc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 300; + /* disable mclk switching if the refresh is >120Hz, even if the + * blanking period would allow it + */ + if (amdgpu_dpm_get_vrefresh(adev) > 120) + return true; + if (vblank_time < switch_limit) return true; else diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 5b261adb4b69..3a25da4a6e60 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -1126,23 +1126,10 @@ static u32 dce_v10_0_latency_watermark(struct dce10_wm_params *wm) a.full = dfixed_const(available_bandwidth); b.full = dfixed_const(wm->num_heads); a.full = dfixed_div(a, b); + tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512); + tmp = min(dfixed_trunc(a), tmp); - b.full = dfixed_const(mc_latency + 512); - c.full = dfixed_const(wm->disp_clk); - b.full = dfixed_div(b, c); - - c.full = dfixed_const(dmif_size); - b.full = dfixed_div(c, b); - - tmp = min(dfixed_trunc(a), dfixed_trunc(b)); - - b.full = dfixed_const(1000); - c.full = dfixed_const(wm->disp_clk); - b.full = dfixed_div(c, b); - c.full = dfixed_const(wm->bytes_per_pixel); - b.full = dfixed_mul(b, c); - - lb_fill_bw = min(tmp, dfixed_trunc(b)); + lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000); a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel); b.full = dfixed_const(1000); @@ -1250,14 +1237,14 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev, { struct drm_display_mode *mode = &amdgpu_crtc->base.mode; struct dce10_wm_params wm_low, wm_high; - u32 pixel_period; + u32 active_time; u32 line_time = 0; u32 latency_watermark_a = 0, latency_watermark_b = 0; u32 tmp, wm_mask, lb_vblank_lead_lines = 0; if (amdgpu_crtc->base.enabled && num_heads && mode) { - pixel_period = 1000000 / (u32)mode->clock; - line_time = min((u32)mode->crtc_htotal * pixel_period, (u32)65535); + active_time = 1000000UL * (u32)mode->crtc_hdisplay / (u32)mode->clock; + line_time = min((u32) (1000000UL * (u32)mode->crtc_htotal / (u32)mode->clock), (u32)65535); /* watermark for high clocks */ if (adev->pm.dpm_enabled) { @@ -1272,7 +1259,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev, wm_high.disp_clk = mode->clock; wm_high.src_width = mode->crtc_hdisplay; - wm_high.active_time = mode->crtc_hdisplay * pixel_period; + wm_high.active_time = active_time; wm_high.blank_time = line_time - wm_high.active_time; wm_high.interlaced = false; if (mode->flags & DRM_MODE_FLAG_INTERLACE) @@ -1311,7 +1298,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev, wm_low.disp_clk = mode->clock; wm_low.src_width = mode->crtc_hdisplay; - wm_low.active_time = mode->crtc_hdisplay * pixel_period; + wm_low.active_time = active_time; wm_low.blank_time = line_time - wm_low.active_time; wm_low.interlaced = false; if (mode->flags & DRM_MODE_FLAG_INTERLACE) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index c161eeda417b..d6d3cda77762 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -1114,23 +1114,10 @@ static u32 dce_v11_0_latency_watermark(struct dce10_wm_params *wm) a.full = dfixed_const(available_bandwidth); b.full = dfixed_const(wm->num_heads); a.full = dfixed_div(a, b); + tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512); + tmp = min(dfixed_trunc(a), tmp); - b.full = dfixed_const(mc_latency + 512); - c.full = dfixed_const(wm->disp_clk); - b.full = dfixed_div(b, c); - - c.full = dfixed_const(dmif_size); - b.full = dfixed_div(c, b); - - tmp = min(dfixed_trunc(a), dfixed_trunc(b)); - - b.full = dfixed_const(1000); - c.full = dfixed_const(wm->disp_clk); - b.full = dfixed_div(c, b); - c.full = dfixed_const(wm->bytes_per_pixel); - b.full = dfixed_mul(b, c); - - lb_fill_bw = min(tmp, dfixed_trunc(b)); + lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000); a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel); b.full = dfixed_const(1000); @@ -1238,14 +1225,14 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev, { struct drm_display_mode *mode = &amdgpu_crtc->base.mode; struct dce10_wm_params wm_low, wm_high; - u32 pixel_period; + u32 active_time; u32 line_time = 0; u32 latency_watermark_a = 0, latency_watermark_b = 0; u32 tmp, wm_mask, lb_vblank_lead_lines = 0; if (amdgpu_crtc->base.enabled && num_heads && mode) { - pixel_period = 1000000 / (u32)mode->clock; - line_time = min((u32)mode->crtc_htotal * pixel_period, (u32)65535); + active_time = 1000000UL * (u32)mode->crtc_hdisplay / (u32)mode->clock; + line_time = min((u32) (1000000UL * (u32)mode->crtc_htotal / (u32)mode->clock), (u32)65535); /* watermark for high clocks */ if (adev->pm.dpm_enabled) { @@ -1260,7 +1247,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev, wm_high.disp_clk = mode->clock; wm_high.src_width = mode->crtc_hdisplay; - wm_high.active_time = mode->crtc_hdisplay * pixel_period; + wm_high.active_time = active_time; wm_high.blank_time = line_time - wm_high.active_time; wm_high.interlaced = false; if (mode->flags & DRM_MODE_FLAG_INTERLACE) @@ -1299,7 +1286,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev, wm_low.disp_clk = mode->clock; wm_low.src_width = mode->crtc_hdisplay; - wm_low.active_time = mode->crtc_hdisplay * pixel_period; + wm_low.active_time = active_time; wm_low.blank_time = line_time - wm_low.active_time; wm_low.interlaced = false; if (mode->flags & DRM_MODE_FLAG_INTERLACE) @@ -3704,9 +3691,15 @@ static void dce_v11_0_encoder_add(struct amdgpu_device *adev, default: encoder->possible_crtcs = 0x3; break; + case 3: + encoder->possible_crtcs = 0x7; + break; case 4: encoder->possible_crtcs = 0xf; break; + case 5: + encoder->possible_crtcs = 0x1f; + break; case 6: encoder->possible_crtcs = 0x3f; break; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 9b4dcf76ce6c..d6e51d4b04f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1096,23 +1096,10 @@ static u32 dce_v8_0_latency_watermark(struct dce8_wm_params *wm) a.full = dfixed_const(available_bandwidth); b.full = dfixed_const(wm->num_heads); a.full = dfixed_div(a, b); + tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512); + tmp = min(dfixed_trunc(a), tmp); - b.full = dfixed_const(mc_latency + 512); - c.full = dfixed_const(wm->disp_clk); - b.full = dfixed_div(b, c); - - c.full = dfixed_const(dmif_size); - b.full = dfixed_div(c, b); - - tmp = min(dfixed_trunc(a), dfixed_trunc(b)); - - b.full = dfixed_const(1000); - c.full = dfixed_const(wm->disp_clk); - b.full = dfixed_div(c, b); - c.full = dfixed_const(wm->bytes_per_pixel); - b.full = dfixed_mul(b, c); - - lb_fill_bw = min(tmp, dfixed_trunc(b)); + lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000); a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel); b.full = dfixed_const(1000); @@ -1220,14 +1207,14 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev, { struct drm_display_mode *mode = &amdgpu_crtc->base.mode; struct dce8_wm_params wm_low, wm_high; - u32 pixel_period; + u32 active_time; u32 line_time = 0; u32 latency_watermark_a = 0, latency_watermark_b = 0; u32 tmp, wm_mask, lb_vblank_lead_lines = 0; if (amdgpu_crtc->base.enabled && num_heads && mode) { - pixel_period = 1000000 / (u32)mode->clock; - line_time = min((u32)mode->crtc_htotal * pixel_period, (u32)65535); + active_time = 1000000UL * (u32)mode->crtc_hdisplay / (u32)mode->clock; + line_time = min((u32) (1000000UL * (u32)mode->crtc_htotal / (u32)mode->clock), (u32)65535); /* watermark for high clocks */ if (adev->pm.dpm_enabled) { @@ -1242,7 +1229,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev, wm_high.disp_clk = mode->clock; wm_high.src_width = mode->crtc_hdisplay; - wm_high.active_time = mode->crtc_hdisplay * pixel_period; + wm_high.active_time = active_time; wm_high.blank_time = line_time - wm_high.active_time; wm_high.interlaced = false; if (mode->flags & DRM_MODE_FLAG_INTERLACE) @@ -1281,7 +1268,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev, wm_low.disp_clk = mode->clock; wm_low.src_width = mode->crtc_hdisplay; - wm_low.active_time = mode->crtc_hdisplay * pixel_period; + wm_low.active_time = active_time; wm_low.blank_time = line_time - wm_low.active_time; wm_low.interlaced = false; if (mode->flags & DRM_MODE_FLAG_INTERLACE) diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index 7e9154c7f1db..d1c9525d81eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -2258,7 +2258,7 @@ static void kv_apply_state_adjust_rules(struct amdgpu_device *adev, if (pi->caps_stable_p_state) { stable_p_state_sclk = (max_limits->sclk * 75) / 100; - for (i = table->count - 1; i >= 0; i++) { + for (i = table->count - 1; i >= 0; i--) { if (stable_p_state_sclk >= table->entries[i].clk) { stable_p_state_sclk = table->entries[i].clk; break; diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 05f6522c0457..b5c64edeb668 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -113,6 +113,11 @@ struct ast_private { struct ttm_bo_kmap_obj cache_kmap; int next_cursor; bool support_wide_screen; + enum { + ast_use_p2a, + ast_use_dt, + ast_use_defaults + } config_mode; enum ast_tx_chip tx_chip_type; u8 dp501_maxclk; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 9b8f0b975ca6..498a94069e6b 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -62,13 +62,84 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast, return ret; } +static void ast_detect_config_mode(struct drm_device *dev, u32 *scu_rev) +{ + struct device_node *np = dev->pdev->dev.of_node; + struct ast_private *ast = dev->dev_private; + uint32_t data, jregd0, jregd1; + + /* Defaults */ + ast->config_mode = ast_use_defaults; + *scu_rev = 0xffffffff; + + /* Check if we have device-tree properties */ + if (np && !of_property_read_u32(np, "aspeed,scu-revision-id", + scu_rev)) { + /* We do, disable P2A access */ + ast->config_mode = ast_use_dt; + DRM_INFO("Using device-tree for configuration\n"); + return; + } + + /* Not all families have a P2A bridge */ + if (dev->pdev->device != PCI_CHIP_AST2000) + return; + + /* + * The BMC will set SCU 0x40 D[12] to 1 if the P2 bridge + * is disabled. We force using P2A if VGA only mode bit + * is set D[7] + */ + jregd0 = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff); + jregd1 = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff); + if (!(jregd0 & 0x80) || !(jregd1 & 0x10)) { + /* Double check it's actually working */ + data = ast_read32(ast, 0xf004); + if (data != 0xFFFFFFFF) { + /* P2A works, grab silicon revision */ + ast->config_mode = ast_use_p2a; + + DRM_INFO("Using P2A bridge for configuration\n"); + + /* Read SCU7c (silicon revision register) */ + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + *scu_rev = ast_read32(ast, 0x1207c); + return; + } + } + + /* We have a P2A bridge but it's disabled */ + DRM_INFO("P2A bridge disabled, using default configuration\n"); +} static int ast_detect_chip(struct drm_device *dev, bool *need_post) { struct ast_private *ast = dev->dev_private; - uint32_t data, jreg; + uint32_t jreg, scu_rev; + + /* + * If VGA isn't enabled, we need to enable now or subsequent + * access to the scratch registers will fail. We also inform + * our caller that it needs to POST the chip + * (Assumption: VGA not enabled -> need to POST) + */ + if (!ast_is_vga_enabled(dev)) { + ast_enable_vga(dev); + DRM_INFO("VGA not enabled on entry, requesting chip POST\n"); + *need_post = true; + } else + *need_post = false; + + + /* Enable extended register access */ + ast_enable_mmio(dev); ast_open_key(ast); + /* Find out whether P2A works or whether to use device-tree */ + ast_detect_config_mode(dev, &scu_rev); + + /* Identify chipset */ if (dev->pdev->device == PCI_CHIP_AST1180) { ast->chip = AST1100; DRM_INFO("AST 1180 detected\n"); @@ -80,12 +151,7 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) ast->chip = AST2300; DRM_INFO("AST 2300 detected\n"); } else if (dev->pdev->revision >= 0x10) { - uint32_t data; - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - - data = ast_read32(ast, 0x1207c); - switch (data & 0x0300) { + switch (scu_rev & 0x0300) { case 0x0200: ast->chip = AST1100; DRM_INFO("AST 1100 detected\n"); @@ -110,20 +176,6 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) } } - /* - * If VGA isn't enabled, we need to enable now or subsequent - * access to the scratch registers will fail. We also inform - * our caller that it needs to POST the chip - * (Assumption: VGA not enabled -> need to POST) - */ - if (!ast_is_vga_enabled(dev)) { - ast_enable_vga(dev); - ast_enable_mmio(dev); - DRM_INFO("VGA not enabled on entry, requesting chip POST\n"); - *need_post = true; - } else - *need_post = false; - /* Check if we support wide screen */ switch (ast->chip) { case AST1180: @@ -140,14 +192,11 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) ast->support_wide_screen = true; else { ast->support_wide_screen = false; - /* Read SCU7c (silicon revision register) */ - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - data = ast_read32(ast, 0x1207c); - data &= 0x300; - if (ast->chip == AST2300 && data == 0x0) /* ast1300 */ + if (ast->chip == AST2300 && + (scu_rev & 0x300) == 0x0) /* ast1300 */ ast->support_wide_screen = true; - if (ast->chip == AST2400 && data == 0x100) /* ast1400 */ + if (ast->chip == AST2400 && + (scu_rev & 0x300) == 0x100) /* ast1400 */ ast->support_wide_screen = true; } break; @@ -212,29 +261,49 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) static int ast_get_dram_info(struct drm_device *dev) { + struct device_node *np = dev->pdev->dev.of_node; struct ast_private *ast = dev->dev_private; - uint32_t data, data2; - uint32_t denum, num, div, ref_pll; - - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - - - ast_write32(ast, 0x10000, 0xfc600309); + uint32_t mcr_cfg, mcr_scu_mpll, mcr_scu_strap; + uint32_t denum, num, div, ref_pll, dsel; - do { - if (pci_channel_offline(dev->pdev)) - return -EIO; - } while (ast_read32(ast, 0x10000) != 0x01); - data = ast_read32(ast, 0x10004); + switch (ast->config_mode) { + case ast_use_dt: + /* + * If some properties are missing, use reasonable + * defaults for AST2400 + */ + if (of_property_read_u32(np, "aspeed,mcr-configuration", + &mcr_cfg)) + mcr_cfg = 0x00000577; + if (of_property_read_u32(np, "aspeed,mcr-scu-mpll", + &mcr_scu_mpll)) + mcr_scu_mpll = 0x000050C0; + if (of_property_read_u32(np, "aspeed,mcr-scu-strap", + &mcr_scu_strap)) + mcr_scu_strap = 0; + break; + case ast_use_p2a: + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + mcr_cfg = ast_read32(ast, 0x10004); + mcr_scu_mpll = ast_read32(ast, 0x10120); + mcr_scu_strap = ast_read32(ast, 0x10170); + break; + case ast_use_defaults: + default: + ast->dram_bus_width = 16; + ast->dram_type = AST_DRAM_1Gx16; + ast->mclk = 396; + return 0; + } - if (data & 0x40) + if (mcr_cfg & 0x40) ast->dram_bus_width = 16; else ast->dram_bus_width = 32; if (ast->chip == AST2300 || ast->chip == AST2400) { - switch (data & 0x03) { + switch (mcr_cfg & 0x03) { case 0: ast->dram_type = AST_DRAM_512Mx16; break; @@ -250,13 +319,13 @@ static int ast_get_dram_info(struct drm_device *dev) break; } } else { - switch (data & 0x0c) { + switch (mcr_cfg & 0x0c) { case 0: case 4: ast->dram_type = AST_DRAM_512Mx16; break; case 8: - if (data & 0x40) + if (mcr_cfg & 0x40) ast->dram_type = AST_DRAM_1Gx16; else ast->dram_type = AST_DRAM_512Mx32; @@ -267,17 +336,15 @@ static int ast_get_dram_info(struct drm_device *dev) } } - data = ast_read32(ast, 0x10120); - data2 = ast_read32(ast, 0x10170); - if (data2 & 0x2000) + if (mcr_scu_strap & 0x2000) ref_pll = 14318; else ref_pll = 12000; - denum = data & 0x1f; - num = (data & 0x3fe0) >> 5; - data = (data & 0xc000) >> 14; - switch (data) { + denum = mcr_scu_mpll & 0x1f; + num = (mcr_scu_mpll & 0x3fe0) >> 5; + dsel = (mcr_scu_mpll & 0xc000) >> 14; + switch (dsel) { case 3: div = 0x4; break; diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 810c51d92b99..c7c58becb25d 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -58,13 +58,9 @@ bool ast_is_vga_enabled(struct drm_device *dev) /* TODO 1180 */ } else { ch = ast_io_read8(ast, AST_IO_VGA_ENABLE_PORT); - if (ch) { - ast_open_key(ast); - ch = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb6, 0xff); - return ch & 0x04; - } + return !!(ch & 0x01); } - return 0; + return false; } static const u8 extreginfo[] = { 0x0f, 0x04, 0x1c, 0xff }; @@ -375,16 +371,21 @@ void ast_post_gpu(struct drm_device *dev) pci_write_config_dword(ast->dev->pdev, 0x04, reg); ast_enable_vga(dev); - ast_enable_mmio(dev); ast_open_key(ast); + ast_enable_mmio(dev); ast_set_def_ext_reg(dev); - if (ast->chip == AST2300 || ast->chip == AST2400) - ast_init_dram_2300(dev); - else - ast_init_dram_reg(dev); + if (ast->config_mode == ast_use_p2a) { + if (ast->chip == AST2300 || ast->chip == AST2400) + ast_init_dram_2300(dev); + else + ast_init_dram_reg(dev); - ast_init_3rdtx(dev); + ast_init_3rdtx(dev); + } else { + if (ast->tx_chip_type != AST_TX_NONE) + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80); /* Enable DVO */ + } } /* AST 2300 DRAM settings */ @@ -1630,12 +1631,44 @@ static void ast_init_dram_2300(struct drm_device *dev) temp |= 0x73; ast_write32(ast, 0x12008, temp); + param.dram_freq = 396; param.dram_type = AST_DDR3; + temp = ast_mindwm(ast, 0x1e6e2070); if (temp & 0x01000000) param.dram_type = AST_DDR2; - param.dram_chipid = ast->dram_type; - param.dram_freq = ast->mclk; - param.vram_size = ast->vram_size; + switch (temp & 0x18000000) { + case 0: + param.dram_chipid = AST_DRAM_512Mx16; + break; + default: + case 0x08000000: + param.dram_chipid = AST_DRAM_1Gx16; + break; + case 0x10000000: + param.dram_chipid = AST_DRAM_2Gx16; + break; + case 0x18000000: + param.dram_chipid = AST_DRAM_4Gx16; + break; + } + switch (temp & 0x0c) { + default: + case 0x00: + param.vram_size = AST_VIDMEM_SIZE_8M; + break; + + case 0x04: + param.vram_size = AST_VIDMEM_SIZE_16M; + break; + + case 0x08: + param.vram_size = AST_VIDMEM_SIZE_32M; + break; + + case 0x0c: + param.vram_size = AST_VIDMEM_SIZE_64M; + break; + } if (param.dram_type == AST_DDR3) { get_ddr3_info(ast, ¶m); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 0659a8849219..9e424f967f2f 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -265,7 +265,7 @@ mode_fixup(struct drm_atomic_state *state) struct drm_connector *connector; struct drm_connector_state *conn_state; int i; - bool ret; + int ret; for_each_crtc_in_state(state, crtc, crtc_state, i) { if (!crtc_state->mode_changed && @@ -1797,7 +1797,7 @@ int __drm_atomic_helper_set_config(struct drm_mode_set *set, primary_state->crtc_w = hdisplay; primary_state->src_x = set->x << 16; primary_state->src_y = set->y << 16; - if (primary_state->rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270))) { + if (drm_rotation_90_or_270(primary_state->rotation)) { primary_state->src_h = hdisplay << 16; primary_state->src_w = vdisplay << 16; } else { diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index c6b1ef490fc4..ea6332bdbaa8 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2628,8 +2628,7 @@ int drm_crtc_check_viewport(const struct drm_crtc *crtc, drm_crtc_get_hv_timing(mode, &hdisplay, &vdisplay); if (crtc->state && - crtc->primary->state->rotation & (BIT(DRM_ROTATE_90) | - BIT(DRM_ROTATE_270))) + drm_rotation_90_or_270(crtc->primary->state->rotation)) swap(hdisplay, vdisplay); return check_src_coords(x << 16, y << 16, diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 7cb2815e815e..58bf94b69186 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -330,6 +330,13 @@ static bool drm_dp_sideband_msg_build(struct drm_dp_sideband_msg_rx *msg, return false; } + /* + * ignore out-of-order messages or messages that are part of a + * failed transaction + */ + if (!recv_hdr.somt && !msg->have_somt) + return false; + /* get length contained in this portion */ msg->curchunk_len = recv_hdr.msg_len; msg->curchunk_hdrlen = hdrlen; @@ -1812,7 +1819,7 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) mgr->payloads[i].num_slots = req_payload.num_slots; } else if (mgr->payloads[i].num_slots) { mgr->payloads[i].num_slots = 0; - drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]); + drm_dp_destroy_payload_step1(mgr, port, mgr->payloads[i].vcpi, &mgr->payloads[i]); req_payload.payload_state = mgr->payloads[i].payload_state; mgr->payloads[i].start_slot = 0; } @@ -2163,7 +2170,7 @@ out_unlock: } EXPORT_SYMBOL(drm_dp_mst_topology_mgr_resume); -static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) +static bool drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) { int len; u8 replyblock[32]; @@ -2178,12 +2185,12 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) replyblock, len); if (ret != len) { DRM_DEBUG_KMS("failed to read DPCD down rep %d %d\n", len, ret); - return; + return false; } ret = drm_dp_sideband_msg_build(msg, replyblock, len, true); if (!ret) { DRM_DEBUG_KMS("sideband msg build failed %d\n", replyblock[0]); - return; + return false; } replylen = msg->curchunk_len + msg->curchunk_hdrlen; @@ -2195,21 +2202,32 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) ret = drm_dp_dpcd_read(mgr->aux, basereg + curreply, replyblock, len); if (ret != len) { - DRM_DEBUG_KMS("failed to read a chunk\n"); + DRM_DEBUG_KMS("failed to read a chunk (len %d, ret %d)\n", + len, ret); + return false; } + ret = drm_dp_sideband_msg_build(msg, replyblock, len, false); - if (ret == false) + if (!ret) { DRM_DEBUG_KMS("failed to build sideband msg\n"); + return false; + } + curreply += len; replylen -= len; } + return true; } static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) { int ret = 0; - drm_dp_get_one_sb_msg(mgr, false); + if (!drm_dp_get_one_sb_msg(mgr, false)) { + memset(&mgr->down_rep_recv, 0, + sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } if (mgr->down_rep_recv.have_eomt) { struct drm_dp_sideband_msg_tx *txmsg; @@ -2265,7 +2283,12 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) { int ret = 0; - drm_dp_get_one_sb_msg(mgr, true); + + if (!drm_dp_get_one_sb_msg(mgr, true)) { + memset(&mgr->up_req_recv, 0, + sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } if (mgr->up_req_recv.have_eomt) { struct drm_dp_sideband_msg_req_body msg; @@ -2317,7 +2340,9 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n", msg.u.resource_stat.port_number, msg.u.resource_stat.available_pbn); } - drm_dp_put_mst_branch_device(mstb); + if (mstb) + drm_dp_put_mst_branch_device(mstb); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); } return ret; diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 8c9ac021608f..c0106fd9fae9 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -75,6 +75,8 @@ #define EDID_QUIRK_FORCE_12BPC (1 << 9) /* Force 6bpc */ #define EDID_QUIRK_FORCE_6BPC (1 << 10) +/* Force 10bpc */ +#define EDID_QUIRK_FORCE_10BPC (1 << 11) struct detailed_mode_closure { struct drm_connector *connector; @@ -117,6 +119,9 @@ static struct edid_quirk { { "FCM", 13600, EDID_QUIRK_PREFER_LARGE_75 | EDID_QUIRK_DETAILED_IN_CM }, + /* LGD panel of HP zBook 17 G2, eDP 10 bpc, but reports unknown bpc */ + { "LGD", 764, EDID_QUIRK_FORCE_10BPC }, + /* LG Philips LCD LP154W01-A5 */ { "LPL", 0, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE }, { "LPL", 0x2a00, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE }, @@ -144,6 +149,9 @@ static struct edid_quirk { /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */ { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC }, + + /* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/ + { "ETR", 13896, EDID_QUIRK_FORCE_8BPC }, }; /* @@ -3831,6 +3839,9 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) if (quirks & EDID_QUIRK_FORCE_8BPC) connector->display_info.bpc = 8; + if (quirks & EDID_QUIRK_FORCE_10BPC) + connector->display_info.bpc = 10; + if (quirks & EDID_QUIRK_FORCE_12BPC) connector->display_info.bpc = 12; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 39e30abddf08..71a10f08522e 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1401,6 +1401,13 @@ drm_mode_create_from_cmdline_mode(struct drm_device *dev, return NULL; mode->type |= DRM_MODE_TYPE_USERDEF; + /* fix up 1368x768: GFT/CVT can't express 1366 width due to alignment */ + if (cmd->xres == 1366 && mode->hdisplay == 1368) { + mode->hdisplay = 1366; + mode->hsync_start--; + mode->hsync_end--; + drm_mode_set_name(mode); + } drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V); return mode; } diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c index ce0645d0c1e5..61e3a097a478 100644 --- a/drivers/gpu/drm/gma500/psb_intel_lvds.c +++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c @@ -783,20 +783,23 @@ void psb_intel_lvds_init(struct drm_device *dev, if (scan->type & DRM_MODE_TYPE_PREFERRED) { mode_dev->panel_fixed_mode = drm_mode_duplicate(dev, scan); + DRM_DEBUG_KMS("Using mode from DDC\n"); goto out; /* FIXME: check for quirks */ } } /* Failed to get EDID, what about VBT? do we need this? */ - if (mode_dev->vbt_mode) + if (dev_priv->lfp_lvds_vbt_mode) { mode_dev->panel_fixed_mode = - drm_mode_duplicate(dev, mode_dev->vbt_mode); + drm_mode_duplicate(dev, dev_priv->lfp_lvds_vbt_mode); - if (!mode_dev->panel_fixed_mode) - if (dev_priv->lfp_lvds_vbt_mode) - mode_dev->panel_fixed_mode = - drm_mode_duplicate(dev, - dev_priv->lfp_lvds_vbt_mode); + if (mode_dev->panel_fixed_mode) { + mode_dev->panel_fixed_mode->type |= + DRM_MODE_TYPE_PREFERRED; + DRM_DEBUG_KMS("Using mode from VBT\n"); + goto out; + } + } /* * If we didn't get EDID, try checking if the panel is already turned @@ -813,6 +816,7 @@ void psb_intel_lvds_init(struct drm_device *dev, if (mode_dev->panel_fixed_mode) { mode_dev->panel_fixed_mode->type |= DRM_MODE_TYPE_PREFERRED; + DRM_DEBUG_KMS("Using pre-programmed mode\n"); goto out; /* FIXME: check for quirks */ } } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index fb9f647bb5cd..6fca39e1c419 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1159,7 +1159,7 @@ struct intel_gen6_power_mgmt { struct intel_rps_client semaphores, mmioflips; /* manual wa residency calculations */ - struct intel_rps_ei up_ei, down_ei; + struct intel_rps_ei ei; /* * Protects RPS/RC6 register access and PCU communication. @@ -3475,11 +3475,6 @@ static inline uint32_t i915_vgacntrl_reg(struct drm_device *dev) return VGACNTRL; } -static inline void __user *to_user_ptr(u64 address) -{ - return (void __user *)(uintptr_t)address; -} - static inline unsigned long msecs_to_jiffies_timeout(const unsigned int m) { unsigned long j = msecs_to_jiffies(m); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index f56af0aaafde..659b90657f36 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -324,7 +324,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; void *vaddr = obj->phys_handle->vaddr + args->offset; - char __user *user_data = to_user_ptr(args->data_ptr); + char __user *user_data = u64_to_user_ptr(args->data_ptr); int ret = 0; /* We manually control the domain here and pretend that it @@ -605,7 +605,7 @@ i915_gem_shmem_pread(struct drm_device *dev, int needs_clflush = 0; struct sg_page_iter sg_iter; - user_data = to_user_ptr(args->data_ptr); + user_data = u64_to_user_ptr(args->data_ptr); remain = args->size; obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); @@ -692,7 +692,7 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, return 0; if (!access_ok(VERIFY_WRITE, - to_user_ptr(args->data_ptr), + u64_to_user_ptr(args->data_ptr), args->size)) return -EFAULT; @@ -783,7 +783,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, if (ret) goto out_unpin; - user_data = to_user_ptr(args->data_ptr); + user_data = u64_to_user_ptr(args->data_ptr); remain = args->size; offset = i915_gem_obj_ggtt_offset(obj) + args->offset; @@ -907,7 +907,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev, int needs_clflush_before = 0; struct sg_page_iter sg_iter; - user_data = to_user_ptr(args->data_ptr); + user_data = u64_to_user_ptr(args->data_ptr); remain = args->size; obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); @@ -1036,12 +1036,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, return 0; if (!access_ok(VERIFY_READ, - to_user_ptr(args->data_ptr), + u64_to_user_ptr(args->data_ptr), args->size)) return -EFAULT; if (likely(!i915.prefault_disable)) { - ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr), + ret = fault_in_multipages_readable(u64_to_user_ptr(args->data_ptr), args->size); if (ret) return -EFAULT; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 201947b4377c..8800f410b2d2 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -492,7 +492,7 @@ i915_gem_execbuffer_relocate_vma(struct i915_vma *vma, struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; int remain, ret; - user_relocs = to_user_ptr(entry->relocs_ptr); + user_relocs = u64_to_user_ptr(entry->relocs_ptr); remain = entry->relocation_count; while (remain) { @@ -831,7 +831,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, u64 invalid_offset = (u64)-1; int j; - user_relocs = to_user_ptr(exec[i].relocs_ptr); + user_relocs = u64_to_user_ptr(exec[i].relocs_ptr); if (copy_from_user(reloc+total, user_relocs, exec[i].relocation_count * sizeof(*reloc))) { @@ -975,7 +975,7 @@ validate_exec_list(struct drm_device *dev, invalid_flags |= EXEC_OBJECT_NEEDS_GTT; for (i = 0; i < count; i++) { - char __user *ptr = to_user_ptr(exec[i].relocs_ptr); + char __user *ptr = u64_to_user_ptr(exec[i].relocs_ptr); int length; /* limited by fault_in_pages_readable() */ if (exec[i].flags & invalid_flags) @@ -1633,7 +1633,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, return -ENOMEM; } ret = copy_from_user(exec_list, - to_user_ptr(args->buffers_ptr), + u64_to_user_ptr(args->buffers_ptr), sizeof(*exec_list) * args->buffer_count); if (ret != 0) { DRM_DEBUG("copy %d exec entries failed %d\n", @@ -1669,7 +1669,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list); if (!ret) { struct drm_i915_gem_exec_object __user *user_exec_list = - to_user_ptr(args->buffers_ptr); + u64_to_user_ptr(args->buffers_ptr); /* Copy the new buffer offsets back to the user's exec list. */ for (i = 0; i < args->buffer_count; i++) { @@ -1721,7 +1721,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, return -ENOMEM; } ret = copy_from_user(exec2_list, - to_user_ptr(args->buffers_ptr), + u64_to_user_ptr(args->buffers_ptr), sizeof(*exec2_list) * args->buffer_count); if (ret != 0) { DRM_DEBUG("copy %d exec entries failed %d\n", @@ -1734,7 +1734,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, if (!ret) { /* Copy the new buffer offsets back to the user's exec list. */ struct drm_i915_gem_exec_object2 __user *user_exec_list = - to_user_ptr(args->buffers_ptr); + u64_to_user_ptr(args->buffers_ptr); int i; for (i = 0; i < args->buffer_count; i++) { diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 0f42a2782afc..b7b0a38acd67 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -994,68 +994,51 @@ static void vlv_c0_read(struct drm_i915_private *dev_priv, ei->media_c0 = I915_READ(VLV_MEDIA_C0_COUNT); } -static bool vlv_c0_above(struct drm_i915_private *dev_priv, - const struct intel_rps_ei *old, - const struct intel_rps_ei *now, - int threshold) -{ - u64 time, c0; - unsigned int mul = 100; - - if (old->cz_clock == 0) - return false; - - if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) - mul <<= 8; - - time = now->cz_clock - old->cz_clock; - time *= threshold * dev_priv->czclk_freq; - - /* Workload can be split between render + media, e.g. SwapBuffers - * being blitted in X after being rendered in mesa. To account for - * this we need to combine both engines into our activity counter. - */ - c0 = now->render_c0 - old->render_c0; - c0 += now->media_c0 - old->media_c0; - c0 *= mul * VLV_CZ_CLOCK_TO_MILLI_SEC; - - return c0 >= time; -} - void gen6_rps_reset_ei(struct drm_i915_private *dev_priv) { - vlv_c0_read(dev_priv, &dev_priv->rps.down_ei); - dev_priv->rps.up_ei = dev_priv->rps.down_ei; + memset(&dev_priv->rps.ei, 0, sizeof(dev_priv->rps.ei)); } static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir) { + const struct intel_rps_ei *prev = &dev_priv->rps.ei; struct intel_rps_ei now; u32 events = 0; - if ((pm_iir & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED)) == 0) + if ((pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) == 0) return 0; vlv_c0_read(dev_priv, &now); if (now.cz_clock == 0) return 0; - if (pm_iir & GEN6_PM_RP_DOWN_EI_EXPIRED) { - if (!vlv_c0_above(dev_priv, - &dev_priv->rps.down_ei, &now, - dev_priv->rps.down_threshold)) - events |= GEN6_PM_RP_DOWN_THRESHOLD; - dev_priv->rps.down_ei = now; - } + if (prev->cz_clock) { + u64 time, c0; + unsigned int mul; - if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) { - if (vlv_c0_above(dev_priv, - &dev_priv->rps.up_ei, &now, - dev_priv->rps.up_threshold)) - events |= GEN6_PM_RP_UP_THRESHOLD; - dev_priv->rps.up_ei = now; + mul = VLV_CZ_CLOCK_TO_MILLI_SEC * 100; /* scale to threshold% */ + if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) + mul <<= 8; + + time = now.cz_clock - prev->cz_clock; + time *= dev_priv->czclk_freq; + + /* Workload can be split between render + media, + * e.g. SwapBuffers being blitted in X after being rendered in + * mesa. To account for this we need to combine both engines + * into our activity counter. + */ + c0 = now.render_c0 - prev->render_c0; + c0 += now.media_c0 - prev->media_c0; + c0 *= mul; + + if (c0 > time * dev_priv->rps.up_threshold) + events = GEN6_PM_RP_UP_THRESHOLD; + else if (c0 < time * dev_priv->rps.down_threshold) + events = GEN6_PM_RP_DOWN_THRESHOLD; } + dev_priv->rps.ei = now; return events; } @@ -4390,7 +4373,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) /* Let's track the enabled rps events */ if (IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) /* WaGsvRC0ResidencyMethod:vlv */ - dev_priv->pm_rps_events = GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED; + dev_priv->pm_rps_events = GEN6_PM_RP_UP_EI_EXPIRED; else dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS; diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 97d1ed20418b..63fea6a2869c 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -445,6 +445,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector) struct drm_i915_private *dev_priv = crt->base.base.dev->dev_private; struct edid *edid; struct i2c_adapter *i2c; + bool ret = false; BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG); @@ -461,17 +462,17 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector) */ if (!is_digital) { DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n"); - return true; + ret = true; + } else { + DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n"); } - - DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n"); } else { DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n"); } kfree(edid); - return false; + return ret; } static enum drm_connector_status diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 909d1d71d130..4f5d07bb3511 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -3948,10 +3948,10 @@ static void page_flip_completed(struct intel_crtc *intel_crtc) drm_crtc_vblank_put(&intel_crtc->base); wake_up_all(&dev_priv->pending_flip_queue); - queue_work(dev_priv->wq, &work->work); - trace_i915_flip_complete(intel_crtc->plane, work->pending_flip_obj); + + queue_work(dev_priv->wq, &work->work); } void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 3f802163f7d4..fd4690ed93c0 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4376,6 +4376,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) break; } + /* When byt can survive without system hang with dynamic + * sw freq adjustments, this restriction can be lifted. + */ + if (IS_VALLEYVIEW(dev_priv)) + goto skip_hw_write; + I915_WRITE(GEN6_RP_UP_EI, GT_INTERVAL_FROM_US(dev_priv, ei_up)); I915_WRITE(GEN6_RP_UP_THRESHOLD, @@ -4394,6 +4400,7 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) GEN6_RP_UP_BUSY_AVG | GEN6_RP_DOWN_IDLE_AVG); +skip_hw_write: dev_priv->rps.power = new_power; dev_priv->rps.up_threshold = threshold_up; dev_priv->rps.down_threshold = threshold_down; @@ -4404,8 +4411,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val) { u32 mask = 0; + /* We use UP_EI_EXPIRED interupts for both up/down in manual mode */ if (val > dev_priv->rps.min_freq_softlimit) - mask |= GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT; + mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT; if (val < dev_priv->rps.max_freq_softlimit) mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD; @@ -4509,7 +4517,7 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv) { mutex_lock(&dev_priv->rps.hw_lock); if (dev_priv->rps.enabled) { - if (dev_priv->pm_rps_events & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED)) + if (dev_priv->pm_rps_events & GEN6_PM_RP_UP_EI_EXPIRED) gen6_rps_reset_ei(dev_priv); I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq)); @@ -6803,7 +6811,18 @@ static void ivybridge_init_clock_gating(struct drm_device *dev) static void vlv_init_display_clock_gating(struct drm_i915_private *dev_priv) { - I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE); + u32 val; + + /* + * On driver load, a pipe may be active and driving a DSI display. + * Preserve DPOUNIT_CLOCK_GATE_DISABLE to avoid the pipe getting stuck + * (and never recovering) in this case. intel_dsi_post_disable() will + * clear it when we turn off the display. + */ + val = I915_READ(DSPCLK_GATE_D); + val &= DPOUNIT_CLOCK_GATE_DISABLE; + val |= VRHUNIT_CLOCK_GATE_DISABLE; + I915_WRITE(DSPCLK_GATE_D, val); /* * Disable trickle feed and enable pnd deadline calculation diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index a3b54cc76495..b66ffd44ff26 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -204,7 +204,14 @@ int adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, void adreno_flush(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - uint32_t wptr = get_wptr(gpu->rb); + uint32_t wptr; + + /* + * Mask wptr value that we calculate to fit in the HW range. This is + * to account for the possibility that the last command fit exactly into + * the ringbuffer and rb->next hasn't wrapped to zero yet + */ + wptr = get_wptr(gpu->rb) & ((gpu->rb->size / 4) - 1); /* ensure writes to ringbuffer have hit system memory: */ mb(); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index b88ce514eb8e..24d45fc7716c 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -986,6 +986,7 @@ static struct drm_driver msm_driver = { .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, + .gem_prime_res_obj = msm_gem_prime_res_obj, .gem_prime_pin = msm_gem_prime_pin, .gem_prime_unpin = msm_gem_prime_unpin, .gem_prime_get_sg_table = msm_gem_prime_get_sg_table, diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 3be7a56b14f1..026e156e519c 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -212,6 +212,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj); void *msm_gem_prime_vmap(struct drm_gem_object *obj); void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); +struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj); struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); int msm_gem_prime_pin(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index 121975b07cd4..1fbddc5c7281 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -70,3 +70,10 @@ void msm_gem_prime_unpin(struct drm_gem_object *obj) if (!obj->import_attach) msm_gem_put_pages(obj); } + +struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj) +{ + struct msm_gem_object *msm_obj = to_msm_bo(obj); + + return msm_obj->resv; +} diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 1847f83b1e33..ed1efae0c3f2 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -28,11 +28,6 @@ #define BO_LOCKED 0x4000 #define BO_PINNED 0x2000 -static inline void __user *to_user_ptr(u64 address) -{ - return (void __user *)(uintptr_t)address; -} - static struct msm_gem_submit *submit_create(struct drm_device *dev, struct msm_gpu *gpu, int nr) { @@ -77,7 +72,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, struct drm_gem_object *obj; struct msm_gem_object *msm_obj; void __user *userptr = - to_user_ptr(args->bos + (i * sizeof(submit_bo))); + u64_to_user_ptr(args->bos + (i * sizeof(submit_bo))); ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo)); if (unlikely(ret)) { @@ -90,7 +85,8 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, pagefault_disable(); } - if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) { + if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) || + !(submit_bo.flags & MSM_SUBMIT_BO_FLAGS)) { DRM_ERROR("invalid flags: %x\n", submit_bo.flags); ret = -EINVAL; goto out_unlock; @@ -274,7 +270,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob for (i = 0; i < nr_relocs; i++) { struct drm_msm_gem_submit_reloc submit_reloc; void __user *userptr = - to_user_ptr(relocs + (i * sizeof(submit_reloc))); + u64_to_user_ptr(relocs + (i * sizeof(submit_reloc))); uint32_t iova, off; bool valid; @@ -374,7 +370,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, for (i = 0; i < args->nr_cmds; i++) { struct drm_msm_gem_submit_cmd submit_cmd; void __user *userptr = - to_user_ptr(args->cmds + (i * sizeof(submit_cmd))); + u64_to_user_ptr(args->cmds + (i * sizeof(submit_cmd))); struct msm_gem_object *msm_obj; uint32_t iova; diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 1f14b908b221..ae317271cf81 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -23,7 +23,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size) struct msm_ringbuffer *ring; int ret; - size = ALIGN(size, 4); /* size should be dword aligned */ + if (WARN_ON(!is_power_of_2(size))) + return ERR_PTR(-EINVAL); ring = kzalloc(sizeof(*ring), GFP_KERNEL); if (!ring) { diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c index 956a833b8200..57c7389feee4 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c @@ -222,6 +222,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype) uint32_t mpllP; pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP); + mpllP = (mpllP >> 8) & 0xf; if (!mpllP) mpllP = 4; @@ -232,7 +233,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype) uint32_t clock; pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock); - return clock; + return clock / 1000; } ret = nouveau_hw_get_pllvals(dev, plltype, &pllvals); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h index 82d3e28918fd..7e4f24ae7de8 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h @@ -4,6 +4,7 @@ struct nvkm_alarm { struct list_head head; + struct list_head exec; u64 timestamp; void (*func)(struct nvkm_alarm *); }; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 58a3f7cf2fb3..00de1bf81519 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -370,7 +370,8 @@ nouveau_display_init(struct drm_device *dev) return ret; /* enable polling for external displays */ - drm_kms_helper_poll_enable(dev); + if (!dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); /* enable hotplug interrupts */ list_for_each_entry(connector, &dev->mode_config.connector_list, head) { diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index d236fc7c425b..91a61d2cca88 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -743,7 +743,10 @@ nouveau_pmops_runtime_resume(struct device *dev) pci_set_master(pdev); ret = nouveau_do_resume(drm_dev, true); - drm_kms_helper_poll_enable(drm_dev); + + if (!drm_dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(drm_dev); + /* do magic */ nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25)); vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 2e3a62d38fe9..1621c8ae0fa0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -99,6 +99,7 @@ struct nv84_fence_priv { struct nouveau_bo *bo; struct nouveau_bo *bo_gart; u32 *suspend; + struct mutex mutex; }; u64 nv84_fence_crtc(struct nouveau_channel *, int); diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c index 6ae1b3494bcd..b7b961233949 100644 --- a/drivers/gpu/drm/nouveau/nouveau_usif.c +++ b/drivers/gpu/drm/nouveau/nouveau_usif.c @@ -313,7 +313,8 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc) if (nvif_unpack(argv->v0, 0, 0, true)) { /* block access to objects not created via this interface */ owner = argv->v0.owner; - if (argv->v0.object == 0ULL) + if (argv->v0.object == 0ULL && + argv->v0.type != NVIF_IOCTL_V0_DEL) argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */ else argv->v0.owner = NVDRM_OBJECT_USIF; diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c index 412c5be5a9ca..7bc26eceda66 100644 --- a/drivers/gpu/drm/nouveau/nv84_fence.c +++ b/drivers/gpu/drm/nouveau/nv84_fence.c @@ -121,8 +121,10 @@ nv84_fence_context_del(struct nouveau_channel *chan) } nouveau_bo_wr32(priv->bo, chan->chid * 16 / 4, fctx->base.sequence); + mutex_lock(&priv->mutex); nouveau_bo_vma_del(priv->bo, &fctx->vma_gart); nouveau_bo_vma_del(priv->bo, &fctx->vma); + mutex_unlock(&priv->mutex); nouveau_fence_context_del(&fctx->base); chan->fence = NULL; nouveau_fence_context_free(&fctx->base); @@ -148,11 +150,13 @@ nv84_fence_context_new(struct nouveau_channel *chan) fctx->base.sync32 = nv84_fence_sync32; fctx->base.sequence = nv84_fence_read(chan); + mutex_lock(&priv->mutex); ret = nouveau_bo_vma_add(priv->bo, cli->vm, &fctx->vma); if (ret == 0) { ret = nouveau_bo_vma_add(priv->bo_gart, cli->vm, &fctx->vma_gart); } + mutex_unlock(&priv->mutex); /* map display semaphore buffers into channel's vm */ for (i = 0; !ret && i < chan->drm->dev->mode_config.num_crtc; i++) { @@ -232,6 +236,8 @@ nv84_fence_create(struct nouveau_drm *drm) priv->base.context_base = fence_context_alloc(priv->base.contexts); priv->base.uevent = true; + mutex_init(&priv->mutex); + /* Use VRAM if there is any ; otherwise fallback to system memory */ domain = drm->device.info.ram_size != 0 ? TTM_PL_FLAG_VRAM : /* diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index ece9f4102c0e..7f8acb3ebfcd 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -714,7 +714,7 @@ nv4a_chipset = { .i2c = nv04_i2c_new, .imem = nv40_instmem_new, .mc = nv44_mc_new, - .mmu = nv44_mmu_new, + .mmu = nv04_mmu_new, .pci = nv40_pci_new, .therm = nv40_therm_new, .timer = nv41_timer_new, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c index c1590b746f13..eb58cd7bfbc9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c @@ -59,7 +59,7 @@ gt215_hda_eld(NV50_DISP_MTHD_V1) ); } for (i = 0; i < size; i++) - nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[0]); + nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[i]); for (; i < 0x60; i++) nvkm_wr32(device, 0x61c440 + soff, (i << 8)); nvkm_mask(device, 0x61c448 + soff, 0x80000003, 0x80000003); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c index d4d8942b1347..e55f8302d08a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c @@ -198,7 +198,7 @@ nv31_mpeg_intr(struct nvkm_engine *engine) } if (type == 0x00000010) { - if (!nv31_mpeg_mthd(mpeg, mthd, data)) + if (nv31_mpeg_mthd(mpeg, mthd, data)) show &= ~0x01000000; } } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c index d433cfa4a8ab..36af0a8927fc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c @@ -172,7 +172,7 @@ nv44_mpeg_intr(struct nvkm_engine *engine) } if (type == 0x00000010) { - if (!nv44_mpeg_mthd(subdev->device, mthd, data)) + if (nv44_mpeg_mthd(subdev->device, mthd, data)) show &= ~0x01000000; } } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c index c794b2c2d21e..6d8f21290aa2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c @@ -129,7 +129,7 @@ gf100_bar_init(struct nvkm_bar *base) if (bar->bar[0].mem) { addr = nvkm_memory_addr(bar->bar[0].mem) >> 12; - nvkm_wr32(device, 0x001714, 0xc0000000 | addr); + nvkm_wr32(device, 0x001714, 0x80000000 | addr); } return 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c index 949dc6101a58..7c0b58613747 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c @@ -130,7 +130,7 @@ nvkm_therm_update(struct nvkm_therm *therm, int mode) poll = false; } - if (list_empty(&therm->alarm.head) && poll) + if (poll) nvkm_timer_alarm(tmr, 1000000000ULL, &therm->alarm); spin_unlock_irqrestore(&therm->lock, flags); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c index 91198d79393a..e2feccec25f5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c @@ -83,7 +83,7 @@ nvkm_fan_update(struct nvkm_fan *fan, bool immediate, int target) spin_unlock_irqrestore(&fan->lock, flags); /* schedule next fan update, if not at target speed already */ - if (list_empty(&fan->alarm.head) && target != duty) { + if (target != duty) { u16 bump_period = fan->bios.bump_period; u16 slow_down_period = fan->bios.slow_down_period; u64 delay; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c index 59701b7a6597..ff9fbe7950e5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c @@ -53,7 +53,7 @@ nvkm_fantog_update(struct nvkm_fantog *fan, int percent) duty = !nvkm_gpio_get(gpio, 0, DCB_GPIO_FAN, 0xff); nvkm_gpio_set(gpio, 0, DCB_GPIO_FAN, 0xff, duty); - if (list_empty(&fan->alarm.head) && percent != (duty * 100)) { + if (percent != (duty * 100)) { u64 next_change = (percent * fan->period_us) / 100; if (!duty) next_change = fan->period_us - next_change; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c index b9703c02d8ca..9a79e91fdfdc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c @@ -185,7 +185,7 @@ alarm_timer_callback(struct nvkm_alarm *alarm) spin_unlock_irqrestore(&therm->sensor.alarm_program_lock, flags); /* schedule the next poll in one second */ - if (therm->func->temp_get(therm) >= 0 && list_empty(&alarm->head)) + if (therm->func->temp_get(therm) >= 0) nvkm_timer_alarm(tmr, 1000000000ULL, alarm); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c index d4dae1f12d62..46033909d950 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c @@ -36,25 +36,32 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr) unsigned long flags; LIST_HEAD(exec); - /* move any due alarms off the pending list */ + /* Process pending alarms. */ spin_lock_irqsave(&tmr->lock, flags); list_for_each_entry_safe(alarm, atemp, &tmr->alarms, head) { - if (alarm->timestamp <= nvkm_timer_read(tmr)) - list_move_tail(&alarm->head, &exec); + /* Have we hit the earliest alarm that hasn't gone off? */ + if (alarm->timestamp > nvkm_timer_read(tmr)) { + /* Schedule it. If we didn't race, we're done. */ + tmr->func->alarm_init(tmr, alarm->timestamp); + if (alarm->timestamp > nvkm_timer_read(tmr)) + break; + } + + /* Move to completed list. We'll drop the lock before + * executing the callback so it can reschedule itself. + */ + list_del_init(&alarm->head); + list_add(&alarm->exec, &exec); } - /* reschedule interrupt for next alarm time */ - if (!list_empty(&tmr->alarms)) { - alarm = list_first_entry(&tmr->alarms, typeof(*alarm), head); - tmr->func->alarm_init(tmr, alarm->timestamp); - } else { + /* Shut down interrupt if no more pending alarms. */ + if (list_empty(&tmr->alarms)) tmr->func->alarm_fini(tmr); - } spin_unlock_irqrestore(&tmr->lock, flags); - /* execute any pending alarm handlers */ - list_for_each_entry_safe(alarm, atemp, &exec, head) { - list_del_init(&alarm->head); + /* Execute completed callbacks. */ + list_for_each_entry_safe(alarm, atemp, &exec, exec) { + list_del(&alarm->exec); alarm->func(alarm); } } @@ -65,24 +72,37 @@ nvkm_timer_alarm(struct nvkm_timer *tmr, u32 nsec, struct nvkm_alarm *alarm) struct nvkm_alarm *list; unsigned long flags; - alarm->timestamp = nvkm_timer_read(tmr) + nsec; - - /* append new alarm to list, in soonest-alarm-first order */ + /* Remove alarm from pending list. + * + * This both protects against the corruption of the list, + * and implements alarm rescheduling/cancellation. + */ spin_lock_irqsave(&tmr->lock, flags); - if (!nsec) { - if (!list_empty(&alarm->head)) - list_del(&alarm->head); - } else { + list_del_init(&alarm->head); + + if (nsec) { + /* Insert into pending list, ordered earliest to latest. */ + alarm->timestamp = nvkm_timer_read(tmr) + nsec; list_for_each_entry(list, &tmr->alarms, head) { if (list->timestamp > alarm->timestamp) break; } + list_add_tail(&alarm->head, &list->head); + + /* Update HW if this is now the earliest alarm. */ + list = list_first_entry(&tmr->alarms, typeof(*list), head); + if (list == alarm) { + tmr->func->alarm_init(tmr, alarm->timestamp); + /* This shouldn't happen if callers aren't stupid. + * + * Worst case scenario is that it'll take roughly + * 4 seconds for the next alarm to trigger. + */ + WARN_ON(alarm->timestamp <= nvkm_timer_read(tmr)); + } } spin_unlock_irqrestore(&tmr->lock, flags); - - /* process pending alarms */ - nvkm_timer_alarm_trigger(tmr); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c index 7b9ce87f0617..7f48249f41de 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c @@ -76,8 +76,8 @@ nv04_timer_intr(struct nvkm_timer *tmr) u32 stat = nvkm_rd32(device, NV04_PTIMER_INTR_0); if (stat & 0x00000001) { - nvkm_timer_alarm_trigger(tmr); nvkm_wr32(device, NV04_PTIMER_INTR_0, 0x00000001); + nvkm_timer_alarm_trigger(tmr); stat &= ~0x00000001; } diff --git a/drivers/gpu/drm/omapdrm/displays/dra7-evm-encoder-tpd12s015.c b/drivers/gpu/drm/omapdrm/displays/dra7-evm-encoder-tpd12s015.c index cdbc75f0c916..72f982aca521 100644 --- a/drivers/gpu/drm/omapdrm/displays/dra7-evm-encoder-tpd12s015.c +++ b/drivers/gpu/drm/omapdrm/displays/dra7-evm-encoder-tpd12s015.c @@ -53,7 +53,6 @@ struct panel_drv_data { struct pinctrl_state *pin_state_ddc; struct i2c_adapter *ddc_i2c_adapter; - dss_hdmi_hpd_cb hpd_func; }; static struct platform_device *mcasp; @@ -316,19 +315,6 @@ static int tpd_set_hdmi_mode(struct omap_dss_device *dssdev, return in->ops.hdmi->set_hdmi_mode(in, hdmi_mode); } -static int tpd_register_hpd_callback(struct omap_dss_device *dssdev, - dss_hdmi_hpd_cb func, - void *data) -{ - struct panel_drv_data *ddata = to_panel_data(dssdev); - struct omap_dss_device *in = ddata->in; - - if (in->ops.hdmi->register_hpd_callback) - return in->ops.hdmi->register_hpd_callback(dssdev, func, data); - - return 0; -} - static const struct omapdss_hdmi_ops tpd_hdmi_ops = { .connect = tpd_connect, .disconnect = tpd_disconnect, @@ -346,7 +332,6 @@ static const struct omapdss_hdmi_ops tpd_hdmi_ops = { .disable_hpd = tpd_disable_hpd, .set_infoframe = tpd_set_infoframe, .set_hdmi_mode = tpd_set_hdmi_mode, - .register_hpd_callback = tpd_register_hpd_callback }; static irqreturn_t tpd_hpd_isr(int irq, void *data) diff --git a/drivers/gpu/drm/omapdrm/dss/Kconfig b/drivers/gpu/drm/omapdrm/dss/Kconfig index 785c42374cc1..3965fc6a6149 100644 --- a/drivers/gpu/drm/omapdrm/dss/Kconfig +++ b/drivers/gpu/drm/omapdrm/dss/Kconfig @@ -73,7 +73,6 @@ config OMAP2_DSS_HDMI_COMMON config OMAP4_DSS_HDMI bool "HDMI support for OMAP4" - depends on EXTCON default y select OMAP2_DSS_HDMI_COMMON help @@ -81,7 +80,6 @@ config OMAP4_DSS_HDMI config OMAP5_DSS_HDMI bool "HDMI support for OMAP5" - depends on EXTCON default n select OMAP2_DSS_HDMI_COMMON help diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c index 97086704121a..085498a4357f 100644 --- a/drivers/gpu/drm/omapdrm/dss/dispc.c +++ b/drivers/gpu/drm/omapdrm/dss/dispc.c @@ -41,6 +41,7 @@ #include <linux/of.h> #include <linux/component.h> #include <video/omapdss.h> +#include <drm/drm_fourcc.h> #include "omapdss.h" #include "dss.h" @@ -78,7 +79,7 @@ struct dispc_features { int (*calc_scaling) (unsigned long pclk, unsigned long lclk, const struct omap_video_timings *mgr_timings, u16 width, u16 height, u16 out_width, u16 out_height, - enum omap_color_mode color_mode, bool *five_taps, + u32 color_mode, bool *five_taps, int *x_predecim, int *y_predecim, int *decim_x, int *decim_y, u16 pos_x, unsigned long *core_clk, bool mem_to_mem); unsigned long (*calc_core_clk) (unsigned long pclk, @@ -159,7 +160,7 @@ enum omap_color_component { */ DISPC_COLOR_COMPONENT_RGB_Y = 1 << 0, /* used for UV component for - * OMAP_DSS_COLOR_YUV2, OMAP_DSS_COLOR_UYVY, OMAP_DSS_COLOR_NV12 + * DRM_FORMAT_YUYV, DRM_FORMAT_UYVY, DRM_FORMAT_NV12 * color formats on OMAP4 */ DISPC_COLOR_COMPONENT_UV = 1 << 1, @@ -898,77 +899,69 @@ static void dispc_ovl_set_row_inc(enum omap_plane plane, s32 inc) } static void dispc_ovl_set_color_mode(enum omap_plane plane, - enum omap_color_mode color_mode) + u32 color_mode) { u32 m = 0; if (plane != OMAP_DSS_GFX) { switch (color_mode) { - case OMAP_DSS_COLOR_NV12: + case DRM_FORMAT_NV12: m = 0x0; break; - case OMAP_DSS_COLOR_RGBX16: + case DRM_FORMAT_XRGB4444: m = 0x1; break; - case OMAP_DSS_COLOR_RGBA16: + case DRM_FORMAT_RGBA4444: m = 0x2; break; - case OMAP_DSS_COLOR_RGB12U: + case DRM_FORMAT_RGBX4444: m = 0x4; break; - case OMAP_DSS_COLOR_ARGB16: + case DRM_FORMAT_ARGB4444: m = 0x5; break; - case OMAP_DSS_COLOR_RGB16: + case DRM_FORMAT_RGB565: m = 0x6; break; - case OMAP_DSS_COLOR_ARGB16_1555: + case DRM_FORMAT_ARGB1555: m = 0x7; break; - case OMAP_DSS_COLOR_RGB24U: + case DRM_FORMAT_XRGB8888: m = 0x8; break; - case OMAP_DSS_COLOR_RGB24P: + case DRM_FORMAT_RGB888: m = 0x9; break; - case OMAP_DSS_COLOR_YUV2: + case DRM_FORMAT_YUYV: m = 0xa; break; - case OMAP_DSS_COLOR_UYVY: + case DRM_FORMAT_UYVY: m = 0xb; break; - case OMAP_DSS_COLOR_ARGB32: + case DRM_FORMAT_ARGB8888: m = 0xc; break; - case OMAP_DSS_COLOR_RGBA32: + case DRM_FORMAT_RGBA8888: m = 0xd; break; - case OMAP_DSS_COLOR_RGBX32: + case DRM_FORMAT_RGBX8888: m = 0xe; break; - case OMAP_DSS_COLOR_XRGB16_1555: + case DRM_FORMAT_XRGB1555: m = 0xf; break; default: BUG(); return; } } else { switch (color_mode) { - case OMAP_DSS_COLOR_CLUT1: - m = 0x0; break; - case OMAP_DSS_COLOR_CLUT2: - m = 0x1; break; - case OMAP_DSS_COLOR_CLUT4: - m = 0x2; break; - case OMAP_DSS_COLOR_CLUT8: - m = 0x3; break; - case OMAP_DSS_COLOR_RGB12U: + case DRM_FORMAT_RGBX4444: m = 0x4; break; - case OMAP_DSS_COLOR_ARGB16: + case DRM_FORMAT_ARGB4444: m = 0x5; break; - case OMAP_DSS_COLOR_RGB16: + case DRM_FORMAT_RGB565: m = 0x6; break; - case OMAP_DSS_COLOR_ARGB16_1555: + case DRM_FORMAT_ARGB1555: m = 0x7; break; - case OMAP_DSS_COLOR_RGB24U: + case DRM_FORMAT_XRGB8888: m = 0x8; break; - case OMAP_DSS_COLOR_RGB24P: + case DRM_FORMAT_RGB888: m = 0x9; break; - case OMAP_DSS_COLOR_RGBX16: + case DRM_FORMAT_XRGB4444: m = 0xa; break; - case OMAP_DSS_COLOR_RGBA16: + case DRM_FORMAT_RGBA4444: m = 0xb; break; - case OMAP_DSS_COLOR_ARGB32: + case DRM_FORMAT_ARGB8888: m = 0xc; break; - case OMAP_DSS_COLOR_RGBA32: + case DRM_FORMAT_RGBA8888: m = 0xd; break; - case OMAP_DSS_COLOR_RGBX32: + case DRM_FORMAT_RGBX8888: m = 0xe; break; - case OMAP_DSS_COLOR_XRGB16_1555: + case DRM_FORMAT_XRGB1555: m = 0xf; break; default: BUG(); return; @@ -978,6 +971,18 @@ static void dispc_ovl_set_color_mode(enum omap_plane plane, REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), m, 4, 1); } +static bool format_is_yuv(u32 color_mode) +{ + switch (color_mode) { + case DRM_FORMAT_YUYV: + case DRM_FORMAT_UYVY: + case DRM_FORMAT_NV12: + return true; + default: + return false; + } +} + static void dispc_ovl_configure_burst_type(enum omap_plane plane, enum omap_dss_rotation_type rotation_type) { @@ -1120,7 +1125,7 @@ static u32 dispc_ovl_get_burst_size(enum omap_plane plane) return unit * 8; } -static enum omap_color_mode dispc_ovl_get_color_modes(enum omap_plane plane) +static const u32 *dispc_ovl_get_color_modes(enum omap_plane plane) { return dss_feat_get_supported_color_modes(plane); } @@ -1538,7 +1543,7 @@ static void dispc_ovl_set_scale_param(enum omap_plane plane, static void dispc_ovl_set_accu_uv(enum omap_plane plane, u16 orig_width, u16 orig_height, u16 out_width, u16 out_height, - bool ilace, enum omap_color_mode color_mode, u8 rotation) + bool ilace, u32 color_mode, u8 rotation) { int h_accu2_0, h_accu2_1; int v_accu2_0, v_accu2_1; @@ -1576,33 +1581,32 @@ static void dispc_ovl_set_accu_uv(enum omap_plane plane, { 0, 1, 0, 1, -1, 1, 0, 1 }, }; - switch (rotation) { - case OMAP_DSS_ROT_0: + /* Note: DSS HW rotates clockwise, DRM_ROTATE_* counter-clockwise */ + switch (rotation & DRM_ROTATE_MASK) { + default: + case BIT(DRM_ROTATE_0): idx = 0; break; - case OMAP_DSS_ROT_90: - idx = 1; + case BIT(DRM_ROTATE_90): + idx = 3; break; - case OMAP_DSS_ROT_180: + case BIT(DRM_ROTATE_180): idx = 2; break; - case OMAP_DSS_ROT_270: - idx = 3; + case BIT(DRM_ROTATE_270): + idx = 1; break; - default: - BUG(); - return; } switch (color_mode) { - case OMAP_DSS_COLOR_NV12: + case DRM_FORMAT_NV12: if (ilace) accu_table = accu_nv12_ilace; else accu_table = accu_nv12; break; - case OMAP_DSS_COLOR_YUV2: - case OMAP_DSS_COLOR_UYVY: + case DRM_FORMAT_YUYV: + case DRM_FORMAT_UYVY: accu_table = accu_yuv; break; default: @@ -1628,7 +1632,7 @@ static void dispc_ovl_set_scaling_common(enum omap_plane plane, u16 orig_width, u16 orig_height, u16 out_width, u16 out_height, bool ilace, bool five_taps, - bool fieldmode, enum omap_color_mode color_mode, + bool fieldmode, u32 color_mode, u8 rotation) { int accu0 = 0; @@ -1682,7 +1686,7 @@ static void dispc_ovl_set_scaling_uv(enum omap_plane plane, u16 orig_width, u16 orig_height, u16 out_width, u16 out_height, bool ilace, bool five_taps, - bool fieldmode, enum omap_color_mode color_mode, + bool fieldmode, u32 color_mode, u8 rotation) { int scale_x = out_width != orig_width; @@ -1691,9 +1695,8 @@ static void dispc_ovl_set_scaling_uv(enum omap_plane plane, if (!dss_has_feature(FEAT_HANDLE_UV_SEPARATE)) return; - if ((color_mode != OMAP_DSS_COLOR_YUV2 && - color_mode != OMAP_DSS_COLOR_UYVY && - color_mode != OMAP_DSS_COLOR_NV12)) { + + if (!format_is_yuv(color_mode)) { /* reset chroma resampling for RGB formats */ if (plane != OMAP_DSS_WB) REG_FLD_MOD(DISPC_OVL_ATTRIBUTES2(plane), 0, 8, 8); @@ -1704,7 +1707,7 @@ static void dispc_ovl_set_scaling_uv(enum omap_plane plane, out_height, ilace, color_mode, rotation); switch (color_mode) { - case OMAP_DSS_COLOR_NV12: + case DRM_FORMAT_NV12: if (chroma_upscale) { /* UV is subsampled by 2 horizontally and vertically */ orig_height >>= 1; @@ -1716,11 +1719,10 @@ static void dispc_ovl_set_scaling_uv(enum omap_plane plane, } break; - case OMAP_DSS_COLOR_YUV2: - case OMAP_DSS_COLOR_UYVY: + case DRM_FORMAT_YUYV: + case DRM_FORMAT_UYVY: /* For YUV422 with 90/270 rotation, we don't upsample chroma */ - if (rotation == OMAP_DSS_ROT_0 || - rotation == OMAP_DSS_ROT_180) { + if (!drm_rotation_90_or_270(rotation)) { if (chroma_upscale) /* UV is subsampled by 2 horizontally */ orig_width >>= 1; @@ -1730,7 +1732,7 @@ static void dispc_ovl_set_scaling_uv(enum omap_plane plane, } /* must use FIR for YUV422 if rotated */ - if (rotation != OMAP_DSS_ROT_0) + if ((rotation & DRM_ROTATE_MASK) != DRM_ROTATE_0) scale_x = scale_y = true; break; @@ -1762,7 +1764,7 @@ static void dispc_ovl_set_scaling(enum omap_plane plane, u16 orig_width, u16 orig_height, u16 out_width, u16 out_height, bool ilace, bool five_taps, - bool fieldmode, enum omap_color_mode color_mode, + bool fieldmode, u32 color_mode, u8 rotation) { BUG_ON(plane == OMAP_DSS_GFX); @@ -1783,48 +1785,48 @@ static void dispc_ovl_set_scaling(enum omap_plane plane, } static void dispc_ovl_set_rotation_attrs(enum omap_plane plane, u8 rotation, - enum omap_dss_rotation_type rotation_type, - bool mirroring, enum omap_color_mode color_mode) + enum omap_dss_rotation_type rotation_type, u32 color_mode) { bool row_repeat = false; int vidrot = 0; - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) { + /* Note: DSS HW rotates clockwise, DRM_ROTATE_* counter-clockwise */ + if (color_mode == DRM_FORMAT_YUYV || + color_mode == DRM_FORMAT_UYVY) { - if (mirroring) { - switch (rotation) { - case OMAP_DSS_ROT_0: + if (rotation & BIT(DRM_REFLECT_X)) { + switch (rotation & DRM_ROTATE_MASK) { + case BIT(DRM_ROTATE_0): vidrot = 2; break; - case OMAP_DSS_ROT_90: + case BIT(DRM_ROTATE_90): vidrot = 1; break; - case OMAP_DSS_ROT_180: + case BIT(DRM_ROTATE_180): vidrot = 0; break; - case OMAP_DSS_ROT_270: + case BIT(DRM_ROTATE_270): vidrot = 3; break; } } else { - switch (rotation) { - case OMAP_DSS_ROT_0: + switch (rotation & DRM_ROTATE_MASK) { + case BIT(DRM_ROTATE_0): vidrot = 0; break; - case OMAP_DSS_ROT_90: - vidrot = 1; + case BIT(DRM_ROTATE_90): + vidrot = 3; break; - case OMAP_DSS_ROT_180: + case BIT(DRM_ROTATE_180): vidrot = 2; break; - case OMAP_DSS_ROT_270: - vidrot = 3; + case BIT(DRM_ROTATE_270): + vidrot = 1; break; } } - if (rotation == OMAP_DSS_ROT_90 || rotation == OMAP_DSS_ROT_270) + if (drm_rotation_90_or_270(rotation)) row_repeat = true; else row_repeat = false; @@ -1835,7 +1837,7 @@ static void dispc_ovl_set_rotation_attrs(enum omap_plane plane, u8 rotation, * NV12 in 1D mode must use ROTATION=1. Otherwise DSS will fetch extra * rows beyond the framebuffer, which may cause OCP error. */ - if (color_mode == OMAP_DSS_COLOR_NV12 && + if (color_mode == DRM_FORMAT_NV12 && rotation_type != OMAP_DSS_ROT_TILER) vidrot = 1; @@ -1844,44 +1846,38 @@ static void dispc_ovl_set_rotation_attrs(enum omap_plane plane, u8 rotation, REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), row_repeat ? 1 : 0, 18, 18); - if (color_mode == OMAP_DSS_COLOR_NV12) { - bool doublestride = (rotation_type == OMAP_DSS_ROT_TILER) && - (rotation == OMAP_DSS_ROT_0 || - rotation == OMAP_DSS_ROT_180); + if (dss_feat_color_mode_supported(plane, DRM_FORMAT_NV12)) { + bool doublestride = + color_mode == DRM_FORMAT_NV12 && + rotation_type == OMAP_DSS_ROT_TILER && + !drm_rotation_90_or_270(rotation); + /* DOUBLESTRIDE */ REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), doublestride, 22, 22); } - } -static int color_mode_to_bpp(enum omap_color_mode color_mode) +static int color_mode_to_bpp(u32 color_mode) { switch (color_mode) { - case OMAP_DSS_COLOR_CLUT1: - return 1; - case OMAP_DSS_COLOR_CLUT2: - return 2; - case OMAP_DSS_COLOR_CLUT4: - return 4; - case OMAP_DSS_COLOR_CLUT8: - case OMAP_DSS_COLOR_NV12: + case DRM_FORMAT_NV12: return 8; - case OMAP_DSS_COLOR_RGB12U: - case OMAP_DSS_COLOR_RGB16: - case OMAP_DSS_COLOR_ARGB16: - case OMAP_DSS_COLOR_YUV2: - case OMAP_DSS_COLOR_UYVY: - case OMAP_DSS_COLOR_RGBA16: - case OMAP_DSS_COLOR_RGBX16: - case OMAP_DSS_COLOR_ARGB16_1555: - case OMAP_DSS_COLOR_XRGB16_1555: + case DRM_FORMAT_RGBX4444: + case DRM_FORMAT_RGB565: + case DRM_FORMAT_ARGB4444: + case DRM_FORMAT_YUYV: + case DRM_FORMAT_UYVY: + case DRM_FORMAT_RGBA4444: + case DRM_FORMAT_XRGB4444: + case DRM_FORMAT_ARGB1555: + case DRM_FORMAT_XRGB1555: return 16; - case OMAP_DSS_COLOR_RGB24P: + case DRM_FORMAT_RGB888: return 24; - case OMAP_DSS_COLOR_RGB24U: - case OMAP_DSS_COLOR_ARGB32: - case OMAP_DSS_COLOR_RGBA32: - case OMAP_DSS_COLOR_RGBX32: + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_ARGB8888: + case DRM_FORMAT_RGBA8888: + case DRM_FORMAT_RGBX8888: return 32; default: BUG(); @@ -1902,281 +1898,43 @@ static s32 pixinc(int pixels, u8 ps) return 0; } -static void calc_vrfb_rotation_offset(u8 rotation, bool mirror, - u16 screen_width, - u16 width, u16 height, - enum omap_color_mode color_mode, bool fieldmode, - unsigned int field_offset, - unsigned *offset0, unsigned *offset1, - s32 *row_inc, s32 *pix_inc, int x_predecim, int y_predecim) +static void calc_offset(u16 screen_width, u16 width, + u32 color_mode, bool fieldmode, + unsigned int field_offset, unsigned *offset0, unsigned *offset1, + s32 *row_inc, s32 *pix_inc, int x_predecim, int y_predecim, + enum omap_dss_rotation_type rotation_type, u8 rotation) { u8 ps; - /* FIXME CLUT formats */ - switch (color_mode) { - case OMAP_DSS_COLOR_CLUT1: - case OMAP_DSS_COLOR_CLUT2: - case OMAP_DSS_COLOR_CLUT4: - case OMAP_DSS_COLOR_CLUT8: - BUG(); - return; - case OMAP_DSS_COLOR_YUV2: - case OMAP_DSS_COLOR_UYVY: - ps = 4; - break; - default: - ps = color_mode_to_bpp(color_mode) / 8; - break; - } + ps = color_mode_to_bpp(color_mode) / 8; - DSSDBG("calc_rot(%d): scrw %d, %dx%d\n", rotation, screen_width, - width, height); + DSSDBG("scrw %d, width %d\n", screen_width, width); - /* - * field 0 = even field = bottom field - * field 1 = odd field = top field - */ - switch (rotation + mirror * 4) { - case OMAP_DSS_ROT_0: - case OMAP_DSS_ROT_180: + if (rotation_type == OMAP_DSS_ROT_TILER && + (color_mode == DRM_FORMAT_UYVY || color_mode == DRM_FORMAT_YUYV) && + drm_rotation_90_or_270(rotation)) { /* - * If the pixel format is YUV or UYVY divide the width - * of the image by 2 for 0 and 180 degree rotation. - */ - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) - width = width >> 1; - case OMAP_DSS_ROT_90: - case OMAP_DSS_ROT_270: - *offset1 = 0; - if (field_offset) - *offset0 = field_offset * screen_width * ps; - else - *offset0 = 0; - - *row_inc = pixinc(1 + - (y_predecim * screen_width - x_predecim * width) + - (fieldmode ? screen_width : 0), ps); - *pix_inc = pixinc(x_predecim, ps); - break; - - case OMAP_DSS_ROT_0 + 4: - case OMAP_DSS_ROT_180 + 4: - /* If the pixel format is YUV or UYVY divide the width - * of the image by 2 for 0 degree and 180 degree + * HACK: ROW_INC needs to be calculated with TILER units. + * We get such 'screen_width' that multiplying it with the + * YUV422 pixel size gives the correct TILER container width. + * However, 'width' is in pixels and multiplying it with YUV422 + * pixel size gives incorrect result. We thus multiply it here + * with 2 to match the 32 bit TILER unit size. */ - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) - width = width >> 1; - case OMAP_DSS_ROT_90 + 4: - case OMAP_DSS_ROT_270 + 4: - *offset1 = 0; - if (field_offset) - *offset0 = field_offset * screen_width * ps; - else - *offset0 = 0; - *row_inc = pixinc(1 - - (y_predecim * screen_width + x_predecim * width) - - (fieldmode ? screen_width : 0), ps); - *pix_inc = pixinc(x_predecim, ps); - break; - - default: - BUG(); - return; - } -} - -static void calc_dma_rotation_offset(u8 rotation, bool mirror, - u16 screen_width, - u16 width, u16 height, - enum omap_color_mode color_mode, bool fieldmode, - unsigned int field_offset, - unsigned *offset0, unsigned *offset1, - s32 *row_inc, s32 *pix_inc, int x_predecim, int y_predecim) -{ - u8 ps; - u16 fbw, fbh; - - /* FIXME CLUT formats */ - switch (color_mode) { - case OMAP_DSS_COLOR_CLUT1: - case OMAP_DSS_COLOR_CLUT2: - case OMAP_DSS_COLOR_CLUT4: - case OMAP_DSS_COLOR_CLUT8: - BUG(); - return; - default: - ps = color_mode_to_bpp(color_mode) / 8; - break; - } - - DSSDBG("calc_rot(%d): scrw %d, %dx%d\n", rotation, screen_width, - width, height); - - /* width & height are overlay sizes, convert to fb sizes */ - - if (rotation == OMAP_DSS_ROT_0 || rotation == OMAP_DSS_ROT_180) { - fbw = width; - fbh = height; - } else { - fbw = height; - fbh = width; - } - - /* - * field 0 = even field = bottom field - * field 1 = odd field = top field - */ - switch (rotation + mirror * 4) { - case OMAP_DSS_ROT_0: - *offset1 = 0; - if (field_offset) - *offset0 = *offset1 + field_offset * screen_width * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(1 + - (y_predecim * screen_width - fbw * x_predecim) + - (fieldmode ? screen_width : 0), ps); - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) - *pix_inc = pixinc(x_predecim, 2 * ps); - else - *pix_inc = pixinc(x_predecim, ps); - break; - case OMAP_DSS_ROT_90: - *offset1 = screen_width * (fbh - 1) * ps; - if (field_offset) - *offset0 = *offset1 + field_offset * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(screen_width * (fbh * x_predecim - 1) + - y_predecim + (fieldmode ? 1 : 0), ps); - *pix_inc = pixinc(-x_predecim * screen_width, ps); - break; - case OMAP_DSS_ROT_180: - *offset1 = (screen_width * (fbh - 1) + fbw - 1) * ps; - if (field_offset) - *offset0 = *offset1 - field_offset * screen_width * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(-1 - - (y_predecim * screen_width - fbw * x_predecim) - - (fieldmode ? screen_width : 0), ps); - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) - *pix_inc = pixinc(-x_predecim, 2 * ps); - else - *pix_inc = pixinc(-x_predecim, ps); - break; - case OMAP_DSS_ROT_270: - *offset1 = (fbw - 1) * ps; - if (field_offset) - *offset0 = *offset1 - field_offset * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(-screen_width * (fbh * x_predecim - 1) - - y_predecim - (fieldmode ? 1 : 0), ps); - *pix_inc = pixinc(x_predecim * screen_width, ps); - break; - - /* mirroring */ - case OMAP_DSS_ROT_0 + 4: - *offset1 = (fbw - 1) * ps; - if (field_offset) - *offset0 = *offset1 + field_offset * screen_width * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(y_predecim * screen_width * 2 - 1 + - (fieldmode ? screen_width : 0), - ps); - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) - *pix_inc = pixinc(-x_predecim, 2 * ps); - else - *pix_inc = pixinc(-x_predecim, ps); - break; - - case OMAP_DSS_ROT_90 + 4: - *offset1 = 0; - if (field_offset) - *offset0 = *offset1 + field_offset * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(-screen_width * (fbh * x_predecim - 1) + - y_predecim + (fieldmode ? 1 : 0), - ps); - *pix_inc = pixinc(x_predecim * screen_width, ps); - break; - - case OMAP_DSS_ROT_180 + 4: - *offset1 = screen_width * (fbh - 1) * ps; - if (field_offset) - *offset0 = *offset1 - field_offset * screen_width * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(1 - y_predecim * screen_width * 2 - - (fieldmode ? screen_width : 0), - ps); - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) - *pix_inc = pixinc(x_predecim, 2 * ps); - else - *pix_inc = pixinc(x_predecim, ps); - break; - - case OMAP_DSS_ROT_270 + 4: - *offset1 = (screen_width * (fbh - 1) + fbw - 1) * ps; - if (field_offset) - *offset0 = *offset1 - field_offset * ps; - else - *offset0 = *offset1; - *row_inc = pixinc(screen_width * (fbh * x_predecim - 1) - - y_predecim - (fieldmode ? 1 : 0), - ps); - *pix_inc = pixinc(-x_predecim * screen_width, ps); - break; - - default: - BUG(); - return; - } -} - -static void calc_tiler_rotation_offset(u16 screen_width, u16 width, - enum omap_color_mode color_mode, bool fieldmode, - unsigned int field_offset, unsigned *offset0, unsigned *offset1, - s32 *row_inc, s32 *pix_inc, int x_predecim, int y_predecim) -{ - u8 ps; - - switch (color_mode) { - case OMAP_DSS_COLOR_CLUT1: - case OMAP_DSS_COLOR_CLUT2: - case OMAP_DSS_COLOR_CLUT4: - case OMAP_DSS_COLOR_CLUT8: - BUG(); - return; - default: - ps = color_mode_to_bpp(color_mode) / 8; - break; + width *= 2; } - DSSDBG("scrw %d, width %d\n", screen_width, width); - /* * field 0 = even field = bottom field * field 1 = odd field = top field */ + *offset0 = field_offset * screen_width * ps; *offset1 = 0; - if (field_offset) - *offset0 = *offset1 + field_offset * screen_width * ps; - else - *offset0 = *offset1; + *row_inc = pixinc(1 + (y_predecim * screen_width - width * x_predecim) + (fieldmode ? screen_width : 0), ps); - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY) + if (color_mode == DRM_FORMAT_YUYV || + color_mode == DRM_FORMAT_UYVY) *pix_inc = pixinc(x_predecim, 2 * ps); else *pix_inc = pixinc(x_predecim, ps); @@ -2241,7 +1999,7 @@ static int check_horiz_timing_omap3(unsigned long pclk, unsigned long lclk, static unsigned long calc_core_clk_five_taps(unsigned long pclk, const struct omap_video_timings *mgr_timings, u16 width, u16 height, u16 out_width, u16 out_height, - enum omap_color_mode color_mode) + u32 color_mode) { u32 core_clk = 0; u64 tmp; @@ -2271,7 +2029,7 @@ static unsigned long calc_core_clk_five_taps(unsigned long pclk, do_div(tmp, out_width); core_clk = max_t(u32, core_clk, tmp); - if (color_mode == OMAP_DSS_COLOR_RGB24U) + if (color_mode == DRM_FORMAT_XRGB8888) core_clk <<= 1; } @@ -2334,7 +2092,7 @@ static unsigned long calc_core_clk_44xx(unsigned long pclk, u16 width, static int dispc_ovl_calc_scaling_24xx(unsigned long pclk, unsigned long lclk, const struct omap_video_timings *mgr_timings, u16 width, u16 height, u16 out_width, u16 out_height, - enum omap_color_mode color_mode, bool *five_taps, + u32 color_mode, bool *five_taps, int *x_predecim, int *y_predecim, int *decim_x, int *decim_y, u16 pos_x, unsigned long *core_clk, bool mem_to_mem) { @@ -2380,7 +2138,7 @@ static int dispc_ovl_calc_scaling_24xx(unsigned long pclk, unsigned long lclk, static int dispc_ovl_calc_scaling_34xx(unsigned long pclk, unsigned long lclk, const struct omap_video_timings *mgr_timings, u16 width, u16 height, u16 out_width, u16 out_height, - enum omap_color_mode color_mode, bool *five_taps, + u32 color_mode, bool *five_taps, int *x_predecim, int *y_predecim, int *decim_x, int *decim_y, u16 pos_x, unsigned long *core_clk, bool mem_to_mem) { @@ -2465,7 +2223,7 @@ again: static int dispc_ovl_calc_scaling_44xx(unsigned long pclk, unsigned long lclk, const struct omap_video_timings *mgr_timings, u16 width, u16 height, u16 out_width, u16 out_height, - enum omap_color_mode color_mode, bool *five_taps, + u32 color_mode, bool *five_taps, int *x_predecim, int *y_predecim, int *decim_x, int *decim_y, u16 pos_x, unsigned long *core_clk, bool mem_to_mem) { @@ -2499,6 +2257,25 @@ static int dispc_ovl_calc_scaling_44xx(unsigned long pclk, unsigned long lclk, return -EINVAL; } + if (*decim_x > 4 && color_mode != DRM_FORMAT_NV12) { + /* + * Let's disable all scaling that requires horizontal + * decimation with higher factor than 4, until we have + * better estimates of what we can and can not + * do. However, NV12 color format appears to work Ok + * with all decimation factors. + * + * When decimating horizontally by more that 4 the dss + * is not able to fetch the data in burst mode. When + * this happens it is hard to tell if there enough + * bandwidth. Despite what theory says this appears to + * be true also for 16-bit color formats. + */ + DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)", *decim_x); + + return -EINVAL; + } + *core_clk = dispc.feat->calc_core_clk(pclk, in_width, in_height, out_width, out_height, mem_to_mem); return 0; @@ -2512,7 +2289,7 @@ static int dispc_ovl_calc_scaling(enum omap_plane plane, enum omap_overlay_caps caps, const struct omap_video_timings *mgr_timings, u16 width, u16 height, u16 out_width, u16 out_height, - enum omap_color_mode color_mode, bool *five_taps, + u32 color_mode, bool *five_taps, int *x_predecim, int *y_predecim, u16 pos_x, enum omap_dss_rotation_type rotation_type, bool mem_to_mem) { @@ -2527,11 +2304,11 @@ static int dispc_ovl_calc_scaling(enum omap_plane plane, if (plane == OMAP_DSS_WB) { switch (color_mode) { - case OMAP_DSS_COLOR_NV12: + case DRM_FORMAT_NV12: maxhdownscale = maxvdownscale = 2; break; - case OMAP_DSS_COLOR_YUV2: - case OMAP_DSS_COLOR_UYVY: + case DRM_FORMAT_YUYV: + case DRM_FORMAT_UYVY: maxhdownscale = 2; maxvdownscale = 4; break; @@ -2557,16 +2334,6 @@ static int dispc_ovl_calc_scaling(enum omap_plane plane, 2 : max_decim_limit; } - if (color_mode == OMAP_DSS_COLOR_CLUT1 || - color_mode == OMAP_DSS_COLOR_CLUT2 || - color_mode == OMAP_DSS_COLOR_CLUT4 || - color_mode == OMAP_DSS_COLOR_CLUT8) { - *x_predecim = 1; - *y_predecim = 1; - *five_taps = false; - return 0; - } - decim_x = DIV_ROUND_UP(DIV_ROUND_UP(width, out_width), maxhdownscale); decim_y = DIV_ROUND_UP(DIV_ROUND_UP(height, out_height), maxvdownscale); @@ -2613,8 +2380,8 @@ static int dispc_ovl_calc_scaling(enum omap_plane plane, static int dispc_ovl_setup_common(enum omap_plane plane, enum omap_overlay_caps caps, u32 paddr, u32 p_uv_addr, u16 screen_width, int pos_x, int pos_y, u16 width, u16 height, - u16 out_width, u16 out_height, enum omap_color_mode color_mode, - u8 rotation, bool mirror, u8 zorder, u8 pre_mult_alpha, + u16 out_width, u16 out_height, u32 color_mode, + u8 rotation, u8 zorder, u8 pre_mult_alpha, u8 global_alpha, enum omap_dss_rotation_type rotation_type, bool replication, const struct omap_video_timings *mgr_timings, bool mem_to_mem) @@ -2641,19 +2408,9 @@ static int dispc_ovl_setup_common(enum omap_plane plane, if (paddr == 0 && rotation_type != OMAP_DSS_ROT_TILER) return -EINVAL; - switch (color_mode) { - case OMAP_DSS_COLOR_YUV2: - case OMAP_DSS_COLOR_UYVY: - case OMAP_DSS_COLOR_NV12: - if (in_width & 1) { - DSSERR("input width %d is not even for YUV format\n", - in_width); - return -EINVAL; - } - break; - - default: - break; + if (format_is_yuv(color_mode) && (in_width & 1)) { + DSSERR("input width %d is not even for YUV format\n", in_width); + return -EINVAL; } out_width = out_width == 0 ? width : out_width; @@ -2691,26 +2448,15 @@ static int dispc_ovl_setup_common(enum omap_plane plane, DSSDBG("predecimation %d x %x, new input size %d x %d\n", x_predecim, y_predecim, in_width, in_height); - switch (color_mode) { - case OMAP_DSS_COLOR_YUV2: - case OMAP_DSS_COLOR_UYVY: - case OMAP_DSS_COLOR_NV12: - if (in_width & 1) { - DSSDBG("predecimated input width is not even for YUV format\n"); - DSSDBG("adjusting input width %d -> %d\n", - in_width, in_width & ~1); - - in_width &= ~1; - } - break; + if (format_is_yuv(color_mode) && (in_width & 1)) { + DSSDBG("predecimated input width is not even for YUV format\n"); + DSSDBG("adjusting input width %d -> %d\n", + in_width, in_width & ~1); - default: - break; + in_width &= ~1; } - if (color_mode == OMAP_DSS_COLOR_YUV2 || - color_mode == OMAP_DSS_COLOR_UYVY || - color_mode == OMAP_DSS_COLOR_NV12) + if (format_is_yuv(color_mode)) cconv = 1; if (ilace && !fieldmode) { @@ -2744,23 +2490,11 @@ static int dispc_ovl_setup_common(enum omap_plane plane, frame_height = height; } - if (rotation_type == OMAP_DSS_ROT_TILER) - calc_tiler_rotation_offset(screen_width, frame_width, - color_mode, fieldmode, field_offset, - &offset0, &offset1, &row_inc, &pix_inc, - x_predecim, y_predecim); - else if (rotation_type == OMAP_DSS_ROT_DMA) - calc_dma_rotation_offset(rotation, mirror, screen_width, - frame_width, frame_height, - color_mode, fieldmode, field_offset, - &offset0, &offset1, &row_inc, &pix_inc, - x_predecim, y_predecim); - else - calc_vrfb_rotation_offset(rotation, mirror, - screen_width, frame_width, frame_height, - color_mode, fieldmode, field_offset, - &offset0, &offset1, &row_inc, &pix_inc, - x_predecim, y_predecim); + calc_offset(screen_width, frame_width, + color_mode, fieldmode, field_offset, + &offset0, &offset1, &row_inc, &pix_inc, + x_predecim, y_predecim, + rotation_type, rotation); DSSDBG("offset0 %u, offset1 %u, row_inc %d, pix_inc %d\n", offset0, offset1, row_inc, pix_inc); @@ -2775,7 +2509,7 @@ static int dispc_ovl_setup_common(enum omap_plane plane, dispc_ovl_set_ba0(plane, paddr + offset0); dispc_ovl_set_ba1(plane, paddr + offset1); - if (OMAP_DSS_COLOR_NV12 == color_mode) { + if (color_mode == DRM_FORMAT_NV12) { dispc_ovl_set_ba0_uv(plane, p_uv_addr + offset0); dispc_ovl_set_ba1_uv(plane, p_uv_addr + offset1); } @@ -2801,8 +2535,7 @@ static int dispc_ovl_setup_common(enum omap_plane plane, dispc_ovl_set_vid_color_conv(plane, cconv); } - dispc_ovl_set_rotation_attrs(plane, rotation, rotation_type, mirror, - color_mode); + dispc_ovl_set_rotation_attrs(plane, rotation, rotation_type, color_mode); dispc_ovl_set_zorder(plane, caps, zorder); dispc_ovl_set_pre_mult_alpha(plane, caps, pre_mult_alpha); @@ -2830,15 +2563,15 @@ static int dispc_ovl_setup(enum omap_plane plane, const struct omap_overlay_info channel = dispc_ovl_get_channel_out(plane); DSSDBG("dispc_ovl_setup %d, pa %pad, pa_uv %pad, sw %d, %d,%d, %dx%d ->" - " %dx%d, cmode %x, rot %d, mir %d, chan %d repl %d\n", + " %dx%d, cmode %x, rot %d, chan %d repl %d\n", plane, &oi->paddr, &oi->p_uv_addr, oi->screen_width, oi->pos_x, oi->pos_y, oi->width, oi->height, oi->out_width, oi->out_height, - oi->color_mode, oi->rotation, oi->mirror, channel, replication); + oi->color_mode, oi->rotation, channel, replication); r = dispc_ovl_setup_common(plane, caps, oi->paddr, oi->p_uv_addr, oi->screen_width, oi->pos_x, oi->pos_y, oi->width, oi->height, oi->out_width, oi->out_height, oi->color_mode, oi->rotation, - oi->mirror, oi->zorder, oi->pre_mult_alpha, oi->global_alpha, + oi->zorder, oi->pre_mult_alpha, oi->global_alpha, oi->rotation_type, replication, mgr_timings, mem_to_mem); return r; @@ -2861,27 +2594,26 @@ static int dispc_wb_setup(const struct omap_dss_writeback_info *wi, OMAP_DSS_OVL_CAP_SCALE | OMAP_DSS_OVL_CAP_PRE_MULT_ALPHA; DSSDBG("dispc_wb_setup, pa %x, pa_uv %x, %d,%d -> %dx%d, cmode %x, " - "rot %d, mir %d\n", wi->paddr, wi->p_uv_addr, in_width, - in_height, wi->width, wi->height, wi->color_mode, wi->rotation, - wi->mirror); + "rot %d\n", wi->paddr, wi->p_uv_addr, in_width, + in_height, wi->width, wi->height, wi->color_mode, wi->rotation); r = dispc_ovl_setup_common(plane, caps, wi->paddr, wi->p_uv_addr, wi->buf_width, pos_x, pos_y, in_width, in_height, wi->width, - wi->height, wi->color_mode, wi->rotation, wi->mirror, zorder, + wi->height, wi->color_mode, wi->rotation, zorder, wi->pre_mult_alpha, global_alpha, wi->rotation_type, replication, mgr_timings, mem_to_mem); if (r) return r; switch (wi->color_mode) { - case OMAP_DSS_COLOR_RGB16: - case OMAP_DSS_COLOR_RGB24P: - case OMAP_DSS_COLOR_ARGB16: - case OMAP_DSS_COLOR_RGBA16: - case OMAP_DSS_COLOR_RGB12U: - case OMAP_DSS_COLOR_ARGB16_1555: - case OMAP_DSS_COLOR_XRGB16_1555: - case OMAP_DSS_COLOR_RGBX16: + case DRM_FORMAT_RGB565: + case DRM_FORMAT_RGB888: + case DRM_FORMAT_ARGB4444: + case DRM_FORMAT_RGBA4444: + case DRM_FORMAT_RGBX4444: + case DRM_FORMAT_ARGB1555: + case DRM_FORMAT_XRGB1555: + case DRM_FORMAT_XRGB4444: truncation = true; break; default: @@ -4334,10 +4066,9 @@ static const struct dispc_errata_i734_data { .ovli = { .screen_width = 1, .width = 1, .height = 1, - .color_mode = OMAP_DSS_COLOR_RGB24U, - .rotation = OMAP_DSS_ROT_0, - .rotation_type = OMAP_DSS_ROT_DMA, - .mirror = 0, + .color_mode = DRM_FORMAT_XRGB8888, + .rotation = BIT(DRM_ROTATE_0), + .rotation_type = OMAP_DSS_ROT_NONE, .pos_x = 0, .pos_y = 0, .out_width = 0, .out_height = 0, .global_alpha = 0xff, diff --git a/drivers/gpu/drm/omapdrm/dss/dispc6.c b/drivers/gpu/drm/omapdrm/dss/dispc6.c index 0039853f2dc6..b4c2268b6790 100644 --- a/drivers/gpu/drm/omapdrm/dss/dispc6.c +++ b/drivers/gpu/drm/omapdrm/dss/dispc6.c @@ -914,22 +914,32 @@ static void dispc6_vid_set_scaling(enum omap_plane plane, /* OTHER */ +static const enum omap_color_mode dispc6_supported_formats[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGBX8888, + DRM_FORMAT_RGBA8888, + DRM_FORMAT_YUYV, + DRM_FORMAT_UYVY, + DRM_FORMAT_NV12, + 0 +}; + static const struct { u32 fourcc; - enum omap_color_mode color_mode; u8 dss_code; u8 bytespp; } dispc6_color_formats[] = { - { DRM_FORMAT_XRGB8888, OMAP_DSS_COLOR_RGB24U, 0x27, 4, }, - { DRM_FORMAT_ARGB8888, OMAP_DSS_COLOR_ARGB32, 0x7, 4, }, + { DRM_FORMAT_XRGB8888, 0x27, 4, }, + { DRM_FORMAT_ARGB8888, 0x7, 4, }, - { DRM_FORMAT_RGBX8888, OMAP_DSS_COLOR_RGBX32, 0x29, 4, }, - { DRM_FORMAT_RGBA8888, OMAP_DSS_COLOR_RGBA32, 0x9, 4, }, + { DRM_FORMAT_RGBX8888, 0x29, 4, }, + { DRM_FORMAT_RGBA8888, 0x9, 4, }, - { DRM_FORMAT_YUYV, OMAP_DSS_COLOR_YUV2, 0x3e, 2, }, - { DRM_FORMAT_UYVY, OMAP_DSS_COLOR_UYVY, 0x3f, 2, }, + { DRM_FORMAT_YUYV, 0x3e, 2, }, + { DRM_FORMAT_UYVY, 0x3f, 2, }, - { DRM_FORMAT_NV12, OMAP_DSS_COLOR_NV12, 0x3d, 2, }, + { DRM_FORMAT_NV12, 0x3d, 2, }, }; static bool dispc6_fourcc_is_yuv(u32 fourcc) @@ -944,19 +954,6 @@ static bool dispc6_fourcc_is_yuv(u32 fourcc) } } -static u32 dispc6_dss_colormode_to_fourcc(enum omap_color_mode dss_mode) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(dispc6_color_formats); ++i) { - if (dispc6_color_formats[i].color_mode == dss_mode) - return dispc6_color_formats[i].fourcc; - } - - __WARN(); - return DRM_FORMAT_XRGB8888; -} - static void dispc6_ovl_set_channel_out(enum omap_plane plane, enum omap_channel channel) { int val = 0; @@ -1009,7 +1006,7 @@ static int dispc6_ovl_setup(enum omap_plane plane, const struct omap_overlay_inf const struct omap_video_timings *mgr_timings, bool mem_to_mem) { - u32 fourcc = dispc6_dss_colormode_to_fourcc(oi->color_mode); + u32 fourcc = oi->color_mode; int bytespp = dispc6_fourcc_to_bytespp(fourcc); dispc6_ovl_set_pixel_format(plane, fourcc); @@ -1128,15 +1125,9 @@ static enum omap_dss_output_id dispc6_mgr_get_supported_outputs(enum omap_channe return OMAP_DSS_OUTPUT_DPI; } -static enum omap_color_mode dispc6_ovl_get_color_modes(enum omap_plane plane) +static const u32 *dispc6_ovl_get_color_modes(enum omap_plane plane) { - enum omap_color_mode formats = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(dispc6_color_formats); ++i) - formats |= dispc6_color_formats[i].color_mode; - - return formats; + return dispc6_supported_formats; } static bool dispc6_has_writeback(void) diff --git a/drivers/gpu/drm/omapdrm/dss/dss_features.c b/drivers/gpu/drm/omapdrm/dss/dss_features.c index 00f2ef962153..4c18c3ae7525 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss_features.c +++ b/drivers/gpu/drm/omapdrm/dss/dss_features.c @@ -22,6 +22,7 @@ #include <linux/types.h> #include <linux/err.h> #include <linux/slab.h> +#include <drm/drm_fourcc.h> #include "omapdss.h" #include "dss.h" @@ -52,12 +53,10 @@ struct omap_dss_features { const int num_ovls; const enum omap_display_type *supported_displays; const enum omap_dss_output_id *supported_outputs; - const enum omap_color_mode *supported_color_modes; + const u32 **supported_color_modes; const enum omap_overlay_caps *overlay_caps; const struct dss_param_range *dss_params; - const enum omap_dss_rotation_type supported_rotation_types; - const u32 buffer_size_unit; const u32 burst_size_unit; }; @@ -236,96 +235,104 @@ static const enum omap_dss_output_id omap5_dss_supported_outputs[] = { OMAP_DSS_OUTPUT_DSI2, }; -static const enum omap_color_mode omap2_dss_supported_color_modes[] = { +#define COLOR_ARRAY(arr...) (const u32[]) { arr, 0 } + +static const u32 *omap2_dss_supported_color_modes[] = { + /* OMAP_DSS_GFX */ - OMAP_DSS_COLOR_CLUT1 | OMAP_DSS_COLOR_CLUT2 | - OMAP_DSS_COLOR_CLUT4 | OMAP_DSS_COLOR_CLUT8 | - OMAP_DSS_COLOR_RGB12U | OMAP_DSS_COLOR_RGB16 | - OMAP_DSS_COLOR_RGB24U | OMAP_DSS_COLOR_RGB24P, + COLOR_ARRAY( + DRM_FORMAT_RGBX4444, DRM_FORMAT_RGB565, + DRM_FORMAT_XRGB8888, DRM_FORMAT_RGB888), /* OMAP_DSS_VIDEO1 */ - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_YUV2 | - OMAP_DSS_COLOR_UYVY, + COLOR_ARRAY( + DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_YUYV, + DRM_FORMAT_UYVY), /* OMAP_DSS_VIDEO2 */ - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_YUV2 | - OMAP_DSS_COLOR_UYVY, + COLOR_ARRAY( + DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_YUYV, + DRM_FORMAT_UYVY), }; -static const enum omap_color_mode omap3_dss_supported_color_modes[] = { +static const u32 *omap3_dss_supported_color_modes[] = { /* OMAP_DSS_GFX */ - OMAP_DSS_COLOR_CLUT1 | OMAP_DSS_COLOR_CLUT2 | - OMAP_DSS_COLOR_CLUT4 | OMAP_DSS_COLOR_CLUT8 | - OMAP_DSS_COLOR_RGB12U | OMAP_DSS_COLOR_ARGB16 | - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_ARGB32 | - OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_RGBX32, + COLOR_ARRAY( + DRM_FORMAT_RGBX4444, DRM_FORMAT_ARGB4444, + DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGBA8888, DRM_FORMAT_RGBX8888), /* OMAP_DSS_VIDEO1 */ - OMAP_DSS_COLOR_RGB24U | OMAP_DSS_COLOR_RGB24P | - OMAP_DSS_COLOR_RGB12U | OMAP_DSS_COLOR_RGB16 | - OMAP_DSS_COLOR_YUV2 | OMAP_DSS_COLOR_UYVY, + COLOR_ARRAY( + DRM_FORMAT_XRGB8888, DRM_FORMAT_RGB888, + DRM_FORMAT_RGBX4444, DRM_FORMAT_RGB565, + DRM_FORMAT_YUYV, DRM_FORMAT_UYVY), /* OMAP_DSS_VIDEO2 */ - OMAP_DSS_COLOR_RGB12U | OMAP_DSS_COLOR_ARGB16 | - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_YUV2 | - OMAP_DSS_COLOR_UYVY | OMAP_DSS_COLOR_ARGB32 | - OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_RGBX32, + COLOR_ARRAY( + DRM_FORMAT_RGBX4444, DRM_FORMAT_ARGB4444, + DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_YUYV, + DRM_FORMAT_UYVY, DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGBA8888, DRM_FORMAT_RGBX8888), }; -static const enum omap_color_mode omap4_dss_supported_color_modes[] = { +static const u32 *omap4_dss_supported_color_modes[] = { /* OMAP_DSS_GFX */ - OMAP_DSS_COLOR_CLUT1 | OMAP_DSS_COLOR_CLUT2 | - OMAP_DSS_COLOR_CLUT4 | OMAP_DSS_COLOR_CLUT8 | - OMAP_DSS_COLOR_RGB12U | OMAP_DSS_COLOR_ARGB16 | - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_ARGB32 | - OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_RGBX32 | - OMAP_DSS_COLOR_ARGB16_1555 | OMAP_DSS_COLOR_RGBX16 | - OMAP_DSS_COLOR_RGBA16 | OMAP_DSS_COLOR_XRGB16_1555, + COLOR_ARRAY( + DRM_FORMAT_RGBX4444, DRM_FORMAT_ARGB4444, + DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGBA8888, DRM_FORMAT_RGBX8888, + DRM_FORMAT_ARGB1555, DRM_FORMAT_XRGB4444, + DRM_FORMAT_RGBA4444, DRM_FORMAT_XRGB1555), /* OMAP_DSS_VIDEO1 */ - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB12U | - OMAP_DSS_COLOR_YUV2 | OMAP_DSS_COLOR_ARGB16_1555 | - OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_NV12 | - OMAP_DSS_COLOR_RGBA16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_UYVY | - OMAP_DSS_COLOR_ARGB16 | OMAP_DSS_COLOR_XRGB16_1555 | - OMAP_DSS_COLOR_ARGB32 | OMAP_DSS_COLOR_RGBX16 | - OMAP_DSS_COLOR_RGBX32, + COLOR_ARRAY( + DRM_FORMAT_RGB565, DRM_FORMAT_RGBX4444, + DRM_FORMAT_YUYV, DRM_FORMAT_ARGB1555, + DRM_FORMAT_RGBA8888, DRM_FORMAT_NV12, + DRM_FORMAT_RGBA4444, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_UYVY, + DRM_FORMAT_ARGB4444, DRM_FORMAT_XRGB1555, + DRM_FORMAT_ARGB8888, DRM_FORMAT_XRGB4444, + DRM_FORMAT_RGBX8888), /* OMAP_DSS_VIDEO2 */ - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB12U | - OMAP_DSS_COLOR_YUV2 | OMAP_DSS_COLOR_ARGB16_1555 | - OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_NV12 | - OMAP_DSS_COLOR_RGBA16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_UYVY | - OMAP_DSS_COLOR_ARGB16 | OMAP_DSS_COLOR_XRGB16_1555 | - OMAP_DSS_COLOR_ARGB32 | OMAP_DSS_COLOR_RGBX16 | - OMAP_DSS_COLOR_RGBX32, + COLOR_ARRAY( + DRM_FORMAT_RGB565, DRM_FORMAT_RGBX4444, + DRM_FORMAT_YUYV, DRM_FORMAT_ARGB1555, + DRM_FORMAT_RGBA8888, DRM_FORMAT_NV12, + DRM_FORMAT_RGBA4444, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_UYVY, + DRM_FORMAT_ARGB4444, DRM_FORMAT_XRGB1555, + DRM_FORMAT_ARGB8888, DRM_FORMAT_XRGB4444, + DRM_FORMAT_RGBX8888), /* OMAP_DSS_VIDEO3 */ - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB12U | - OMAP_DSS_COLOR_YUV2 | OMAP_DSS_COLOR_ARGB16_1555 | - OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_NV12 | - OMAP_DSS_COLOR_RGBA16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_UYVY | - OMAP_DSS_COLOR_ARGB16 | OMAP_DSS_COLOR_XRGB16_1555 | - OMAP_DSS_COLOR_ARGB32 | OMAP_DSS_COLOR_RGBX16 | - OMAP_DSS_COLOR_RGBX32, + COLOR_ARRAY( + DRM_FORMAT_RGB565, DRM_FORMAT_RGBX4444, + DRM_FORMAT_YUYV, DRM_FORMAT_ARGB1555, + DRM_FORMAT_RGBA8888, DRM_FORMAT_NV12, + DRM_FORMAT_RGBA4444, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_UYVY, + DRM_FORMAT_ARGB4444, DRM_FORMAT_XRGB1555, + DRM_FORMAT_ARGB8888, DRM_FORMAT_XRGB4444, + DRM_FORMAT_RGBX8888), /* OMAP_DSS_WB */ - OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB12U | - OMAP_DSS_COLOR_YUV2 | OMAP_DSS_COLOR_ARGB16_1555 | - OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_NV12 | - OMAP_DSS_COLOR_RGBA16 | OMAP_DSS_COLOR_RGB24U | - OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_UYVY | - OMAP_DSS_COLOR_ARGB16 | OMAP_DSS_COLOR_XRGB16_1555 | - OMAP_DSS_COLOR_ARGB32 | OMAP_DSS_COLOR_RGBX16 | - OMAP_DSS_COLOR_RGBX32, + COLOR_ARRAY( + DRM_FORMAT_RGB565, DRM_FORMAT_RGBX4444, + DRM_FORMAT_YUYV, DRM_FORMAT_ARGB1555, + DRM_FORMAT_RGBA8888, DRM_FORMAT_NV12, + DRM_FORMAT_RGBA4444, DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB888, DRM_FORMAT_UYVY, + DRM_FORMAT_ARGB4444, DRM_FORMAT_XRGB1555, + DRM_FORMAT_ARGB8888, DRM_FORMAT_XRGB4444, + DRM_FORMAT_RGBX8888), }; static const enum omap_overlay_caps omap2_dss_overlay_caps[] = { @@ -607,7 +614,6 @@ static const struct omap_dss_features omap2_dss_features = { .supported_color_modes = omap2_dss_supported_color_modes, .overlay_caps = omap2_dss_overlay_caps, .dss_params = omap2_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB, .buffer_size_unit = 1, .burst_size_unit = 8, }; @@ -627,7 +633,6 @@ static const struct omap_dss_features omap3430_dss_features = { .supported_color_modes = omap3_dss_supported_color_modes, .overlay_caps = omap3430_dss_overlay_caps, .dss_params = omap3_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB, .buffer_size_unit = 1, .burst_size_unit = 8, }; @@ -650,7 +655,6 @@ static const struct omap_dss_features am35xx_dss_features = { .supported_color_modes = omap3_dss_supported_color_modes, .overlay_caps = omap3430_dss_overlay_caps, .dss_params = omap3_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB, .buffer_size_unit = 1, .burst_size_unit = 8, }; @@ -669,7 +673,6 @@ static const struct omap_dss_features am43xx_dss_features = { .supported_color_modes = omap3_dss_supported_color_modes, .overlay_caps = omap3430_dss_overlay_caps, .dss_params = am43xx_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA, .buffer_size_unit = 1, .burst_size_unit = 8, }; @@ -688,7 +691,6 @@ static const struct omap_dss_features omap3630_dss_features = { .supported_color_modes = omap3_dss_supported_color_modes, .overlay_caps = omap3630_dss_overlay_caps, .dss_params = omap3_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB, .buffer_size_unit = 1, .burst_size_unit = 8, }; @@ -709,7 +711,6 @@ static const struct omap_dss_features omap4430_es1_0_dss_features = { .supported_color_modes = omap4_dss_supported_color_modes, .overlay_caps = omap4_dss_overlay_caps, .dss_params = omap4_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER, .buffer_size_unit = 16, .burst_size_unit = 16, }; @@ -729,7 +730,6 @@ static const struct omap_dss_features omap4430_es2_0_1_2_dss_features = { .supported_color_modes = omap4_dss_supported_color_modes, .overlay_caps = omap4_dss_overlay_caps, .dss_params = omap4_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER, .buffer_size_unit = 16, .burst_size_unit = 16, }; @@ -749,7 +749,6 @@ static const struct omap_dss_features omap4_dss_features = { .supported_color_modes = omap4_dss_supported_color_modes, .overlay_caps = omap4_dss_overlay_caps, .dss_params = omap4_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER, .buffer_size_unit = 16, .burst_size_unit = 16, }; @@ -769,7 +768,6 @@ static const struct omap_dss_features omap5_dss_features = { .supported_color_modes = omap4_dss_supported_color_modes, .overlay_caps = omap4_dss_overlay_caps, .dss_params = omap5_dss_param_range, - .supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER, .buffer_size_unit = 16, .burst_size_unit = 16, }; @@ -805,7 +803,7 @@ enum omap_dss_output_id dss_feat_get_supported_outputs(enum omap_channel channel return omap_current_dss_features->supported_outputs[channel]; } -enum omap_color_mode dss_feat_get_supported_color_modes(enum omap_plane plane) +const u32 *dss_feat_get_supported_color_modes(enum omap_plane plane) { return omap_current_dss_features->supported_color_modes[plane]; } @@ -816,10 +814,19 @@ enum omap_overlay_caps dss_feat_get_overlay_caps(enum omap_plane plane) } bool dss_feat_color_mode_supported(enum omap_plane plane, - enum omap_color_mode color_mode) + u32 color_mode) { - return omap_current_dss_features->supported_color_modes[plane] & - color_mode; + const u32 *modes; + unsigned int i; + + modes = omap_current_dss_features->supported_color_modes[plane]; + + for (i = 0; modes[i]; ++i) { + if (modes[i] == color_mode) + return true; + } + + return false; } u32 dss_feat_get_buffer_size_unit(void) @@ -856,11 +863,6 @@ void dss_feat_get_reg_field(enum dss_feat_reg_field id, u8 *start, u8 *end) *end = omap_current_dss_features->reg_fields[id].end; } -bool dss_feat_rotation_type_supported(enum omap_dss_rotation_type rot_type) -{ - return omap_current_dss_features->supported_rotation_types & rot_type; -} - void dss_features_init(enum omapdss_version version) { switch (version) { diff --git a/drivers/gpu/drm/omapdrm/dss/dss_features.h b/drivers/gpu/drm/omapdrm/dss/dss_features.h index bcec68ba8db9..0dd2183d7e6c 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss_features.h +++ b/drivers/gpu/drm/omapdrm/dss/dss_features.h @@ -90,13 +90,11 @@ unsigned long dss_feat_get_param_min(enum dss_range_param param); unsigned long dss_feat_get_param_max(enum dss_range_param param); enum omap_overlay_caps dss_feat_get_overlay_caps(enum omap_plane plane); bool dss_feat_color_mode_supported(enum omap_plane plane, - enum omap_color_mode color_mode); + u32 color_mode); u32 dss_feat_get_buffer_size_unit(void); /* in bytes */ u32 dss_feat_get_burst_size_unit(void); /* in bytes */ -bool dss_feat_rotation_type_supported(enum omap_dss_rotation_type rot_type); - bool dss_has_feature(enum dss_feat_id id); void dss_feat_get_reg_field(enum dss_feat_reg_field id, u8 *start, u8 *end); void dss_features_init(enum omapdss_version version); @@ -106,6 +104,6 @@ enum omap_dss_output_id dss_feat_get_supported_outputs(enum omap_channel channel int dss_feat_get_num_mgrs(void); int dss_feat_get_num_ovls(void); -enum omap_color_mode dss_feat_get_supported_color_modes(enum omap_plane plane); +const u32 *dss_feat_get_supported_color_modes(enum omap_plane plane); #endif diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi.h b/drivers/gpu/drm/omapdrm/dss/hdmi.h index c3d7067fad6e..63e711545865 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi.h +++ b/drivers/gpu/drm/omapdrm/dss/hdmi.h @@ -24,7 +24,6 @@ #include <linux/platform_device.h> #include <linux/hdmi.h> #include <sound/omap-hdmi-audio.h> -#include <linux/extcon.h> #include "omapdss.h" #include "dss.h" @@ -359,8 +358,6 @@ struct omap_hdmi { void (*audio_abort_cb)(struct device *dev); int wp_idlemode; - struct extcon_dev edev; - bool audio_configured; struct omap_dss_audio audio_config; @@ -368,9 +365,6 @@ struct omap_hdmi { spinlock_t audio_playing_lock; bool audio_playing; bool display_enabled; - - dss_hdmi_hpd_cb hpd_cb_func; - void *hpd_cb_data; }; #endif diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c index c7e68c75e1e8..ed3ca9707db3 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c @@ -42,11 +42,6 @@ #include "dss_features.h" #include "hdmi.h" -static const unsigned int hdmi4_extcon_cable[] = { - EXTCON_DISP_HDMI, - EXTCON_NONE, -}; - static struct omap_hdmi hdmi; static int hdmi_runtime_get(void) @@ -97,10 +92,8 @@ static irqreturn_t hdmi_irq_handler(int irq, void *data) hdmi_wp_set_phy_pwr(wp, HDMI_PHYPWRCMD_LDOON); } else if (irqstatus & HDMI_IRQ_LINK_CONNECT) { hdmi_wp_set_phy_pwr(wp, HDMI_PHYPWRCMD_TXON); - extcon_set_state(&hdmi.edev, 1); } else if (irqstatus & HDMI_IRQ_LINK_DISCONNECT) { hdmi_wp_set_phy_pwr(wp, HDMI_PHYPWRCMD_LDOON); - extcon_set_state(&hdmi.edev, 0); } return IRQ_HANDLED; @@ -748,18 +741,6 @@ static int hdmi4_bind(struct device *dev, struct device *master, void *data) goto err; } - hdmi.edev.name = "hdmi"; - hdmi.edev.supported_cable = hdmi4_extcon_cable; - hdmi.edev.dev.parent = &pdev->dev; - r = extcon_dev_register(&hdmi.edev); - if (r) { - DSSERR("Registering HDMI extcon failed %d\n", r); - return r; - } - - /* Init extcon state to zero */ - extcon_set_state(&hdmi.edev, 0); - pm_runtime_enable(&pdev->dev); hdmi_init_output(pdev); @@ -769,7 +750,6 @@ static int hdmi4_bind(struct device *dev, struct device *master, void *data) DSSERR("Registering HDMI audio failed\n"); hdmi_uninit_output(pdev); pm_runtime_disable(&pdev->dev); - extcon_dev_unregister(&hdmi.edev); return r; } @@ -793,8 +773,6 @@ static void hdmi4_unbind(struct device *dev, struct device *master, void *data) hdmi_pll_uninit(&hdmi.pll); pm_runtime_disable(&pdev->dev); - - extcon_dev_unregister(&hdmi.edev); } static const struct component_ops hdmi4_component_ops = { diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c index a31a38f4e452..549302267a8b 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c @@ -46,11 +46,6 @@ #include "dss.h" #include "dss_features.h" -static const unsigned int hdmi5_extcon_cable[] = { - EXTCON_DISP_HDMI, - EXTCON_NONE, -}; - static struct omap_hdmi hdmi; static int hdmi_runtime_get(void) @@ -116,18 +111,8 @@ static irqreturn_t hdmi_irq_handler(int irq, void *data) } else if (irqstatus & HDMI_IRQ_LINK_CONNECT) { hdmi_wp_set_phy_pwr(wp, HDMI_PHYPWRCMD_TXON); - - extcon_set_state(&hdmi.edev, 1); - - if (hdmi.hpd_cb_func) - hdmi.hpd_cb_func(irq, hdmi.hpd_cb_data); } else if (irqstatus & HDMI_IRQ_LINK_DISCONNECT) { hdmi_wp_set_phy_pwr(wp, HDMI_PHYPWRCMD_LDOON); - - extcon_set_state(&hdmi.edev, 0); - - if (hdmi.hpd_cb_func) - hdmi.hpd_cb_func(irq, hdmi.hpd_cb_data); } return IRQ_HANDLED; @@ -552,17 +537,6 @@ static int hdmi_set_hdmi_mode(struct omap_dss_device *dssdev, return 0; } -static int hdmi_register_hpd_callback(struct omap_dss_device *dssdev, - dss_hdmi_hpd_cb func, - void *data) - -{ - hdmi.hpd_cb_func = func; - hdmi.hpd_cb_data = data; - - return 0; -} - static const struct omapdss_hdmi_ops hdmi_ops = { .connect = hdmi_connect, .disconnect = hdmi_disconnect, @@ -577,7 +551,6 @@ static const struct omapdss_hdmi_ops hdmi_ops = { .read_edid = hdmi_read_edid, .set_infoframe = hdmi_set_infoframe, .set_hdmi_mode = hdmi_set_hdmi_mode, - .register_hpd_callback = hdmi_register_hpd_callback }; static void hdmi_init_output(struct platform_device *pdev) @@ -757,8 +730,6 @@ static int hdmi5_bind(struct device *dev, struct device *master, void *data) int r; int irq; - hdmi.hpd_cb_func = NULL; - hdmi.pdev = pdev; dev_set_drvdata(&pdev->dev, &hdmi); @@ -802,20 +773,6 @@ static int hdmi5_bind(struct device *dev, struct device *master, void *data) goto err; } - - hdmi.edev.name = "hdmi"; - hdmi.edev.supported_cable = hdmi5_extcon_cable; - hdmi.edev.dev.parent = &pdev->dev; - - r = extcon_dev_register(&hdmi.edev); - if (r) { - DSSERR("Registering HDMI extcon failed %d\n", r); - return r; - } - - /* Init extcon state to zero */ - extcon_set_state(&hdmi.edev, 0); - pm_runtime_enable(&pdev->dev); hdmi_init_output(pdev); @@ -825,7 +782,6 @@ static int hdmi5_bind(struct device *dev, struct device *master, void *data) DSSERR("Registering HDMI audio failed %d\n", r); hdmi_uninit_output(pdev); pm_runtime_disable(&pdev->dev); - extcon_dev_unregister(&hdmi.edev); return r; } @@ -848,7 +804,6 @@ static void hdmi5_unbind(struct device *dev, struct device *master, void *data) hdmi_pll_uninit(&hdmi.pll); - extcon_dev_unregister(&hdmi.edev); pm_runtime_disable(&pdev->dev); } diff --git a/drivers/gpu/drm/omapdrm/dss/omapdss.h b/drivers/gpu/drm/omapdrm/dss/omapdss.h index 06acc7ea9974..a79a73a48fe2 100644 --- a/drivers/gpu/drm/omapdrm/dss/omapdss.h +++ b/drivers/gpu/drm/omapdrm/dss/omapdss.h @@ -95,25 +95,7 @@ enum omap_channel { }; enum omap_color_mode { - OMAP_DSS_COLOR_CLUT1 = 1 << 0, /* BITMAP 1 */ - OMAP_DSS_COLOR_CLUT2 = 1 << 1, /* BITMAP 2 */ - OMAP_DSS_COLOR_CLUT4 = 1 << 2, /* BITMAP 4 */ - OMAP_DSS_COLOR_CLUT8 = 1 << 3, /* BITMAP 8 */ - OMAP_DSS_COLOR_RGB12U = 1 << 4, /* RGB12, 16-bit container */ - OMAP_DSS_COLOR_ARGB16 = 1 << 5, /* ARGB16 */ - OMAP_DSS_COLOR_RGB16 = 1 << 6, /* RGB16 */ - OMAP_DSS_COLOR_RGB24U = 1 << 7, /* RGB24, 32-bit container */ - OMAP_DSS_COLOR_RGB24P = 1 << 8, /* RGB24, 24-bit container */ - OMAP_DSS_COLOR_YUV2 = 1 << 9, /* YUV2 4:2:2 co-sited */ - OMAP_DSS_COLOR_UYVY = 1 << 10, /* UYVY 4:2:2 co-sited */ - OMAP_DSS_COLOR_ARGB32 = 1 << 11, /* ARGB32 */ - OMAP_DSS_COLOR_RGBA32 = 1 << 12, /* RGBA32 */ - OMAP_DSS_COLOR_RGBX32 = 1 << 13, /* RGBx32 */ - OMAP_DSS_COLOR_NV12 = 1 << 14, /* NV12 format: YUV 4:2:0 */ - OMAP_DSS_COLOR_RGBA16 = 1 << 15, /* RGBA16 - 4444 */ - OMAP_DSS_COLOR_RGBX16 = 1 << 16, /* RGBx16 - 4444 */ - OMAP_DSS_COLOR_ARGB16_1555 = 1 << 17, /* ARGB16 - 1555 */ - OMAP_DSS_COLOR_XRGB16_1555 = 1 << 18, /* xRGB16 - 1555 */ + _UNUSED_, }; enum omap_dss_load_mode { @@ -171,17 +153,8 @@ enum omap_dss_display_state { }; enum omap_dss_rotation_type { - OMAP_DSS_ROT_DMA = 1 << 0, - OMAP_DSS_ROT_VRFB = 1 << 1, - OMAP_DSS_ROT_TILER = 1 << 2, -}; - -/* clockwise rotation angle */ -enum omap_dss_rotation_angle { - OMAP_DSS_ROT_0 = 0, - OMAP_DSS_ROT_90 = 1, - OMAP_DSS_ROT_180 = 2, - OMAP_DSS_ROT_270 = 3, + OMAP_DSS_ROT_NONE = 0, + OMAP_DSS_ROT_TILER = 1 << 0, }; enum omap_overlay_caps { @@ -235,8 +208,6 @@ enum omap_dss_dsi_trans_mode { OMAP_DSS_DSI_BURST_MODE, }; -typedef irqreturn_t (*dss_hdmi_hpd_cb)(int irq, void *data); - struct omap_dss_dsi_videomode_timings { unsigned long hsclk; @@ -339,10 +310,9 @@ struct omap_overlay_info { u16 screen_width; u16 width; u16 height; - enum omap_color_mode color_mode; + u32 color_mode; u8 rotation; enum omap_dss_rotation_type rotation_type; - bool mirror; u16 pos_x; u16 pos_y; @@ -469,10 +439,9 @@ struct omap_dss_writeback_info { u16 buf_width; u16 width; u16 height; - enum omap_color_mode color_mode; + u32 color_mode; u8 rotation; enum omap_dss_rotation_type rotation_type; - bool mirror; u8 pre_mult_alpha; }; @@ -584,9 +553,6 @@ struct omapdss_hdmi_ops { int (*set_hdmi_mode)(struct omap_dss_device *dssdev, bool hdmi_mode); int (*set_infoframe)(struct omap_dss_device *dssdev, const struct hdmi_avi_infoframe *avi); - int (*register_hpd_callback)(struct omap_dss_device *dssdev, - dss_hdmi_hpd_cb func, - void *data); }; struct omapdss_dsi_ops { @@ -799,9 +765,6 @@ struct omap_dss_driver { int (*set_hdmi_mode)(struct omap_dss_device *dssdev, bool hdmi_mode); int (*set_hdmi_infoframe)(struct omap_dss_device *dssdev, const struct hdmi_avi_infoframe *avi); - int (*register_hpd_callback)(struct omap_dss_device *dssdev, - dss_hdmi_hpd_cb func, - void *data); }; enum omapdss_version omapdss_get_version(void); @@ -858,7 +821,6 @@ int omap_dispc_unregister_isr(omap_dispc_isr_t isr, void *arg, u32 mask); int omapdss_compat_init(void); void omapdss_compat_uninit(void); - static inline bool omapdss_device_is_connected(struct omap_dss_device *dssdev) { return dssdev->src; @@ -1022,7 +984,7 @@ struct dispc_ops { const struct omap_video_timings *mgr_timings, bool mem_to_mem); - enum omap_color_mode (*ovl_get_color_modes)(enum omap_plane plane); + const u32 *(*ovl_get_color_modes)(enum omap_plane plane); u32 (*wb_get_framedone_irq)(void); int (*wb_setup)(const struct omap_dss_writeback_info *wi, diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c index 32957e1c20a3..d717079a122f 100644 --- a/drivers/gpu/drm/omapdrm/omap_connector.c +++ b/drivers/gpu/drm/omapdrm/omap_connector.c @@ -162,9 +162,6 @@ static enum drm_connector_status omap_connector_detect( struct omap_dss_driver *dssdrv = dssdev->driver; enum drm_connector_status ret; - if (force) - ret = connector_status_connected; - if (dssdrv->detect) { if (dssdrv->detect(dssdev)) ret = connector_status_connected; @@ -350,28 +347,11 @@ struct drm_connector *omap_connector_init(struct drm_device *dev, omap_connector->encoder = encoder; connector = &omap_connector->base; - connector->force = DRM_FORCE_ON; drm_connector_init(dev, connector, &omap_connector_funcs, connector_type); drm_connector_helper_add(connector, &omap_connector_helper_funcs); - if (dssdev->driver->register_hpd_callback) { - dssdev->driver->register_hpd_callback(dssdev, - omap_hdmi_hpd_irq_handler, - dev); - - DBG("Registered ISR omap_drm_hdmi_hpd_irq"); - } - - if (dssdev->driver->register_hpd_callback) { - dssdev->driver->register_hpd_callback(dssdev, - omap_hdmi_hpd_irq_handler, - dev); - - DBG("Registered ISR omap_drm_hdmi_hpd_irq"); - } - #if 0 /* enable when dss2 supports hotplug */ if (dssdev->caps & OMAP_DSS_DISPLAY_CAP_HPD) connector->polled = 0; diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index 89e5cef7bea3..ae7fb6669f34 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -96,8 +96,22 @@ static void omap_atomic_complete(struct omap_atomic_state_commit *commit) priv->dispc_ops->runtime_get(); drm_atomic_helper_commit_modeset_disables(dev, old_state); - drm_atomic_helper_commit_planes(dev, old_state, false); + + /* With the current dss dispc implementation we have to enable + * the new modeset before we can commit planes. The dispc ovl + * configuration relies on the video mode configuration been + * written into the HW when the ovl configuration is + * calculated. + * + * This approach is not ideal because after a mode change the + * plane update is executed only after the first vblank + * interrupt. The dispc implementation should be fixed so that + * it is able use uncommitted drm state information. + */ drm_atomic_helper_commit_modeset_enables(dev, old_state); + omap_atomic_wait_for_completion(dev, old_state); + + drm_atomic_helper_commit_planes(dev, old_state, 0); omap_atomic_wait_for_completion(dev, old_state); diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h index 6ebe480e7038..57ceda1d139b 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.h +++ b/drivers/gpu/drm/omapdrm/omap_drv.h @@ -39,15 +39,6 @@ struct omap_drm_usergart; -/* parameters which describe (unrotated) coordinates of scanout within a fb: */ -struct omap_drm_window { - uint32_t rotation; - int32_t crtc_x, crtc_y; /* signed because can be offscreen */ - uint32_t crtc_w, crtc_h; - uint32_t src_x, src_y; - uint32_t src_w, src_h; -}; - /* For transiently registering for different DSS irqs that various parts * of the KMS code need during setup/configuration. We these are not * necessarily the same as what drm_vblank_get/put() are requesting, and @@ -150,7 +141,6 @@ void omap_irq_register(struct drm_device *dev, struct omap_drm_irq *irq); void omap_irq_unregister(struct drm_device *dev, struct omap_drm_irq *irq); void omap_drm_irq_uninstall(struct drm_device *dev); int omap_drm_irq_install(struct drm_device *dev); -irqreturn_t omap_hdmi_hpd_irq_handler(int irq, void *arg); #ifdef CONFIG_DRM_FBDEV_EMULATION struct drm_fb_helper *omap_fbdev_init(struct drm_device *dev); @@ -197,7 +187,7 @@ void copy_timings_drm_to_omap(struct omap_video_timings *timings, struct drm_display_mode *mode); uint32_t omap_framebuffer_get_formats(uint32_t *pixel_formats, - uint32_t max_formats, enum omap_color_mode supported_modes); + uint32_t max_formats, const u32 *supported_modes); struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev, struct drm_file *file, struct drm_mode_fb_cmd2 *mode_cmd); struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, @@ -206,7 +196,7 @@ struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p); int omap_framebuffer_pin(struct drm_framebuffer *fb); void omap_framebuffer_unpin(struct drm_framebuffer *fb); void omap_framebuffer_update_scanout(struct drm_framebuffer *fb, - struct omap_drm_window *win, struct omap_overlay_info *info); + struct drm_plane_state *state, struct omap_overlay_info *info); struct drm_connector *omap_framebuffer_get_next_connector( struct drm_framebuffer *fb, struct drm_connector *from); bool omap_framebuffer_supports_rotation(struct drm_framebuffer *fb); @@ -246,6 +236,7 @@ int omap_gem_get_pages(struct drm_gem_object *obj, struct page ***pages, bool remap); int omap_gem_put_pages(struct drm_gem_object *obj); struct sg_table *omap_gem_get_sgt(struct drm_gem_object *obj); +void omap_gem_put_sgt(struct drm_gem_object *obj, struct sg_table *sg); uint32_t omap_gem_flags(struct drm_gem_object *obj); int omap_gem_rotated_paddr(struct drm_gem_object *obj, uint32_t orient, int x, int y, dma_addr_t *paddr); diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c index 7a764260c48b..d302d83dcda3 100644 --- a/drivers/gpu/drm/omapdrm/omap_fb.c +++ b/drivers/gpu/drm/omapdrm/omap_fb.c @@ -29,7 +29,7 @@ /* per-format info: */ struct format { - enum omap_color_mode dss_format; + u32 dss_format; uint32_t pixel_format; struct { int stride_bpp; /* this times width is stride */ @@ -40,36 +40,44 @@ struct format { static const struct format formats[] = { /* 16bpp [A]RGB: */ - { OMAP_DSS_COLOR_RGB16, DRM_FORMAT_RGB565, {{2, 1}}, false }, /* RGB16-565 */ - { OMAP_DSS_COLOR_RGB12U, DRM_FORMAT_RGBX4444, {{2, 1}}, false }, /* RGB12x-4444 */ - { OMAP_DSS_COLOR_RGBX16, DRM_FORMAT_XRGB4444, {{2, 1}}, false }, /* xRGB12-4444 */ - { OMAP_DSS_COLOR_RGBA16, DRM_FORMAT_RGBA4444, {{2, 1}}, false }, /* RGBA12-4444 */ - { OMAP_DSS_COLOR_ARGB16, DRM_FORMAT_ARGB4444, {{2, 1}}, false }, /* ARGB16-4444 */ - { OMAP_DSS_COLOR_XRGB16_1555, DRM_FORMAT_XRGB1555, {{2, 1}}, false }, /* xRGB15-1555 */ - { OMAP_DSS_COLOR_ARGB16_1555, DRM_FORMAT_ARGB1555, {{2, 1}}, false }, /* ARGB16-1555 */ + { DRM_FORMAT_RGB565, DRM_FORMAT_RGB565, {{2, 1}}, false }, /* RGB16-565 */ + { DRM_FORMAT_RGBX4444, DRM_FORMAT_RGBX4444, {{2, 1}}, false }, /* RGB12x-4444 */ + { DRM_FORMAT_XRGB4444, DRM_FORMAT_XRGB4444, {{2, 1}}, false }, /* xRGB12-4444 */ + { DRM_FORMAT_RGBA4444, DRM_FORMAT_RGBA4444, {{2, 1}}, false }, /* RGBA12-4444 */ + { DRM_FORMAT_ARGB4444, DRM_FORMAT_ARGB4444, {{2, 1}}, false }, /* ARGB16-4444 */ + { DRM_FORMAT_XRGB1555, DRM_FORMAT_XRGB1555, {{2, 1}}, false }, /* xRGB15-1555 */ + { DRM_FORMAT_ARGB1555, DRM_FORMAT_ARGB1555, {{2, 1}}, false }, /* ARGB16-1555 */ /* 24bpp RGB: */ - { OMAP_DSS_COLOR_RGB24P, DRM_FORMAT_RGB888, {{3, 1}}, false }, /* RGB24-888 */ + { DRM_FORMAT_RGB888, DRM_FORMAT_RGB888, {{3, 1}}, false }, /* RGB24-888 */ /* 32bpp [A]RGB: */ - { OMAP_DSS_COLOR_RGBX32, DRM_FORMAT_RGBX8888, {{4, 1}}, false }, /* RGBx24-8888 */ - { OMAP_DSS_COLOR_RGB24U, DRM_FORMAT_XRGB8888, {{4, 1}}, false }, /* xRGB24-8888 */ - { OMAP_DSS_COLOR_RGBA32, DRM_FORMAT_RGBA8888, {{4, 1}}, false }, /* RGBA32-8888 */ - { OMAP_DSS_COLOR_ARGB32, DRM_FORMAT_ARGB8888, {{4, 1}}, false }, /* ARGB32-8888 */ + { DRM_FORMAT_RGBX8888, DRM_FORMAT_RGBX8888, {{4, 1}}, false }, /* RGBx24-8888 */ + { DRM_FORMAT_XRGB8888, DRM_FORMAT_XRGB8888, {{4, 1}}, false }, /* xRGB24-8888 */ + { DRM_FORMAT_RGBA8888, DRM_FORMAT_RGBA8888, {{4, 1}}, false }, /* RGBA32-8888 */ + { DRM_FORMAT_ARGB8888, DRM_FORMAT_ARGB8888, {{4, 1}}, false }, /* ARGB32-8888 */ /* YUV: */ - { OMAP_DSS_COLOR_NV12, DRM_FORMAT_NV12, {{1, 1}, {1, 2}}, true }, - { OMAP_DSS_COLOR_YUV2, DRM_FORMAT_YUYV, {{2, 1}}, true }, - { OMAP_DSS_COLOR_UYVY, DRM_FORMAT_UYVY, {{2, 1}}, true }, + { DRM_FORMAT_NV12, DRM_FORMAT_NV12, {{1, 1}, {1, 2}}, true }, + { DRM_FORMAT_YUYV, DRM_FORMAT_YUYV, {{2, 1}}, true }, + { DRM_FORMAT_UYVY, DRM_FORMAT_UYVY, {{2, 1}}, true }, }; /* convert from overlay's pixel formats bitmask to an array of fourcc's */ uint32_t omap_framebuffer_get_formats(uint32_t *pixel_formats, - uint32_t max_formats, enum omap_color_mode supported_modes) + uint32_t max_formats, const u32 *supported_modes) { uint32_t nformats = 0; int i = 0; - for (i = 0; i < ARRAY_SIZE(formats) && nformats < max_formats; i++) - if (formats[i].dss_format & supported_modes) + for (i = 0; i < ARRAY_SIZE(formats) && nformats < max_formats; i++) { + unsigned int t; + + for (t = 0; supported_modes[t]; ++t) { + if (supported_modes[t] != formats[i].dss_format) + continue; + pixel_formats[nformats++] = formats[i].pixel_format; + break; + } + } return nformats; } @@ -153,10 +161,40 @@ bool omap_framebuffer_supports_rotation(struct drm_framebuffer *fb) return omap_gem_flags(plane->bo) & OMAP_BO_TILED; } +/* Note: DRM rotates counter-clockwise, TILER & DSS rotates clockwise */ +static uint32_t drm_rotation_to_tiler(unsigned int drm_rot) +{ + uint32_t orient; + + switch (drm_rot & DRM_ROTATE_MASK) { + default: + case BIT(DRM_ROTATE_0): + orient = 0; + break; + case BIT(DRM_ROTATE_90): + orient = MASK_XY_FLIP | MASK_X_INVERT; + break; + case BIT(DRM_ROTATE_180): + orient = MASK_X_INVERT | MASK_Y_INVERT; + break; + case BIT(DRM_ROTATE_270): + orient = MASK_XY_FLIP | MASK_Y_INVERT; + break; + } + + if (drm_rot & BIT(DRM_REFLECT_X)) + orient ^= MASK_X_INVERT; + + if (drm_rot & BIT(DRM_REFLECT_Y)) + orient ^= MASK_Y_INVERT; + + return orient; +} + /* update ovl info for scanout, handles cases of multi-planar fb's, etc. */ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb, - struct omap_drm_window *win, struct omap_overlay_info *info) + struct drm_plane_state *state, struct omap_overlay_info *info) { struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb); const struct format *format = omap_fb->format; @@ -165,59 +203,53 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb, info->color_mode = format->dss_format; - info->pos_x = win->crtc_x; - info->pos_y = win->crtc_y; - info->out_width = win->crtc_w; - info->out_height = win->crtc_h; - info->width = win->src_w; - info->height = win->src_h; + info->pos_x = state->crtc_x; + info->pos_y = state->crtc_y; + info->out_width = state->crtc_w; + info->out_height = state->crtc_h; + info->width = state->src_w >> 16; + info->height = state->src_h >> 16; - x = win->src_x; - y = win->src_y; + /* DSS driver wants the w & h in rotated orientation */ + if (drm_rotation_90_or_270(state->rotation)) + swap(info->width, info->height); - if (omap_gem_flags(plane->bo) & OMAP_BO_TILED) { - uint32_t w = win->src_w; - uint32_t h = win->src_h; + x = state->src_x >> 16; + y = state->src_y >> 16; - switch (win->rotation & DRM_ROTATE_MASK) { - default: - dev_err(fb->dev->dev, "invalid rotation: %02x", - (uint32_t)win->rotation); - /* fallthru to default to no rotation */ - case 0: - case BIT(DRM_ROTATE_0): - orient = 0; - break; - case BIT(DRM_ROTATE_90): - orient = MASK_XY_FLIP | MASK_X_INVERT; - break; - case BIT(DRM_ROTATE_180): - orient = MASK_X_INVERT | MASK_Y_INVERT; - break; - case BIT(DRM_ROTATE_270): - orient = MASK_XY_FLIP | MASK_Y_INVERT; - break; + if (omap_gem_flags(plane->bo) & OMAP_BO_TILED) { + uint32_t w = state->src_w >> 16; + uint32_t h = state->src_h >> 16; + + orient = drm_rotation_to_tiler(state->rotation); + + /* + * omap_gem_rotated_paddr() wants the x & y in tiler units. + * Usually tiler unit size is the same as the pixel size, except + * for YUV422 formats, for which the tiler unit size is 32 bits + * and pixel size is 16 bits. + */ + if (fb->pixel_format == DRM_FORMAT_UYVY || + fb->pixel_format == DRM_FORMAT_YUYV) { + x /= 2; + w /= 2; } - if (win->rotation & BIT(DRM_REFLECT_X)) - orient ^= MASK_X_INVERT; - - if (win->rotation & BIT(DRM_REFLECT_Y)) - orient ^= MASK_Y_INVERT; - - /* adjust x,y offset for flip/invert: */ - if (orient & MASK_XY_FLIP) - swap(w, h); + /* adjust x,y offset for invert: */ if (orient & MASK_Y_INVERT) y += h - 1; if (orient & MASK_X_INVERT) x += w - 1; - omap_gem_rotated_paddr(plane->bo, orient, x, y, &info->paddr); + /* Note: x and y are in TILER units, not pixels */ + omap_gem_rotated_paddr(plane->bo, orient, x, y, + &info->paddr); info->rotation_type = OMAP_DSS_ROT_TILER; + info->rotation = state->rotation ?: DRM_ROTATE_0; + /* Note: stride in TILER units, not pixels */ info->screen_width = omap_gem_tiled_stride(plane->bo, orient); } else { - switch (win->rotation & DRM_ROTATE_MASK) { + switch (state->rotation & DRM_ROTATE_MASK) { case 0: case BIT(DRM_ROTATE_0): /* OK */ @@ -226,20 +258,20 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb, default: dev_warn(fb->dev->dev, "rotation '%d' ignored for non-tiled fb\n", - win->rotation); - win->rotation = 0; + state->rotation); break; } info->paddr = get_linear_addr(plane, format, 0, x, y); - info->rotation_type = OMAP_DSS_ROT_DMA; + info->rotation_type = OMAP_DSS_ROT_NONE; + info->rotation = DRM_ROTATE_0; info->screen_width = plane->pitch; } /* convert to pixels: */ info->screen_width /= format->planes[0].stride_bpp; - if (format->dss_format == OMAP_DSS_COLOR_NV12) { + if (format->dss_format == DRM_FORMAT_NV12) { plane = &omap_fb->planes[1]; if (info->rotation_type == OMAP_DSS_ROT_TILER) { diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 122f856bb041..6ec7916e3840 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -193,7 +193,7 @@ static void evict_entry(struct drm_gem_object *obj, size_t size = PAGE_SIZE * n; loff_t off = mmap_offset(obj) + (entry->obj_pgoff << PAGE_SHIFT); - const int m = 1 + ((omap_obj->width << fmt) / PAGE_SIZE); + const int m = DIV_ROUND_UP(omap_obj->width << fmt, PAGE_SIZE); if (m > 1) { int i; @@ -451,7 +451,7 @@ static int fault_2d(struct drm_gem_object *obj, * into account in some of the math, so figure out virtual stride * in pages */ - const int m = 1 + ((omap_obj->width << fmt) / PAGE_SIZE); + const int m = DIV_ROUND_UP(omap_obj->width << fmt, PAGE_SIZE); /* We don't use vmf->pgoff since that has the fake offset: */ pgoff = ((unsigned long)vmf->virtual_address - @@ -666,7 +666,8 @@ int omap_gem_dumb_create(struct drm_file *file, struct drm_device *dev, }; return omap_gem_new_handle(dev, file, gsize, - OMAP_BO_SCANOUT | OMAP_BO_WC, &args->handle); + OMAP_BO_SCANOUT | OMAP_BO_WC | args->flags, + &args->handle); } /** @@ -811,7 +812,14 @@ struct sg_table *omap_gem_get_sgt(struct drm_gem_object *obj) { struct omap_gem_object *omap_obj = to_omap_bo(obj); struct sg_table *sg; - int npages = obj->size >> PAGE_SHIFT; + dma_addr_t paddr; + int ret; + bool remap; + + remap = omap_obj->flags & OMAP_BO_SCANOUT; + ret = omap_gem_get_paddr(obj, &paddr, remap); + if (ret) + goto out; sg = kmalloc(sizeof(*sg), GFP_KERNEL); if (!sg) @@ -829,6 +837,7 @@ struct sg_table *omap_gem_get_sgt(struct drm_gem_object *obj) } else if (omap_obj->pages) { struct scatterlist *sgl; unsigned int i = 0; + int npages = obj->size >> PAGE_SHIFT; if (sg_alloc_table(sg, npages, GFP_KERNEL)) goto free; @@ -844,12 +853,23 @@ struct sg_table *omap_gem_get_sgt(struct drm_gem_object *obj) } return sg; +out: + return ERR_PTR(ret); free: sg_free_table(sg); kfree(sg); return NULL; } +void omap_gem_put_sgt(struct drm_gem_object *obj, struct sg_table *sg) +{ + struct omap_gem_object *omap_obj = to_omap_bo(obj); + bool remap = omap_obj->flags & OMAP_BO_SCANOUT; + + if (remap) + omap_gem_put_paddr(obj); +} + /* Get physical address for DMA.. if 'remap' is true, and the buffer is not * already contiguous, remap it to pin in physically contiguous memory.. (ie. * map in TILER) @@ -929,12 +949,12 @@ fail: /* Release physical address, when DMA is no longer being performed.. this * could potentially unpin and unmap buffers from TILER */ -void omap_gem_put_paddr(struct drm_gem_object *obj) + +static void omap_gem_put_paddr_locked(struct drm_gem_object *obj) { struct omap_gem_object *omap_obj = to_omap_bo(obj); int ret; - mutex_lock(&obj->dev->struct_mutex); if (omap_obj->paddr_cnt > 0) { omap_obj->paddr_cnt--; if (omap_obj->paddr_cnt == 0) { @@ -952,7 +972,12 @@ void omap_gem_put_paddr(struct drm_gem_object *obj) omap_obj->block = NULL; } } +} +void omap_gem_put_paddr(struct drm_gem_object *obj) +{ + mutex_lock(&obj->dev->struct_mutex); + omap_gem_put_paddr_locked(obj); mutex_unlock(&obj->dev->struct_mutex); } @@ -1344,6 +1369,9 @@ void omap_gem_free_object(struct drm_gem_object *obj) list_del(&omap_obj->mm_list); spin_unlock(&priv->list_lock); + if (omap_obj->flags & OMAP_BO_MEM_PIN) + omap_gem_put_paddr_locked(obj); + /* this means the object is still pinned.. which really should * not happen. I think.. */ @@ -1390,6 +1418,11 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev, return NULL; } + if (flags & OMAP_BO_MEM_CONTIG) { + dev_err(dev->dev, "Tiled buffers require TILER memory\n"); + return NULL; + } + /* * Tiled buffers are always shmem paged backed. When they are * scanned out, they are remapped into DMM/TILER. @@ -1403,7 +1436,8 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev, */ flags &= ~(OMAP_BO_CACHED|OMAP_BO_WC|OMAP_BO_UNCACHED); flags |= tiler_get_cpu_cache_flags(); - } else if ((flags & OMAP_BO_SCANOUT) && !priv->has_dmm) { + } else if ((flags & OMAP_BO_MEM_CONTIG) || + ((flags & OMAP_BO_SCANOUT) && !priv->has_dmm)) { /* * OMAP_BO_SCANOUT hints that the buffer doesn't need to be * tiled. However, to lower the pressure on memory allocation, @@ -1463,12 +1497,24 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev, goto err_release; } + if (flags & OMAP_BO_MEM_PIN) { + dma_addr_t dummy; + + ret = omap_gem_get_paddr(obj, &dummy, true); + if (ret) + goto err_free_dma; + } + spin_lock(&priv->list_lock); list_add(&omap_obj->mm_list, &priv->obj_list); spin_unlock(&priv->list_lock); return obj; +err_free_dma: + if (flags & OMAP_BO_MEM_DMA_API) + dma_free_writecombine(dev->dev, size, + omap_obj->vaddr, omap_obj->paddr); err_release: drm_gem_object_release(obj); err_free: diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index f53bbc50e382..f418a7d07205 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -30,29 +30,24 @@ static struct sg_table *omap_gem_map_dma_buf( enum dma_data_direction dir) { struct drm_gem_object *obj = attachment->dmabuf->priv; - dma_addr_t paddr; - int ret; + struct sg_table *sg; - /* camera, etc, need physically contiguous.. but we need a - * better way to know this.. - */ - ret = omap_gem_get_paddr(obj, &paddr, false); - if (ret) - goto out; + sg = omap_gem_get_sgt(obj); + if (IS_ERR(sg)) + return sg; /* this should be after _get_paddr() to ensure we have pages attached */ omap_gem_dma_sync(obj, dir); - return omap_gem_get_sgt(obj); -out: - return ERR_PTR(ret); + return sg; } static void omap_gem_unmap_dma_buf(struct dma_buf_attachment *attachment, struct sg_table *sg, enum dma_data_direction dir) { struct drm_gem_object *obj = attachment->dmabuf->priv; - omap_gem_put_paddr(obj); + + omap_gem_put_sgt(obj, sg); sg_free_table(sg); kfree(sg); } diff --git a/drivers/gpu/drm/omapdrm/omap_irq.c b/drivers/gpu/drm/omapdrm/omap_irq.c index c69ed81c4ccf..1fa68a206253 100644 --- a/drivers/gpu/drm/omapdrm/omap_irq.c +++ b/drivers/gpu/drm/omapdrm/omap_irq.c @@ -303,27 +303,3 @@ void omap_drm_irq_uninstall(struct drm_device *dev) priv->dispc_ops->free_irq(dev); } - -irqreturn_t omap_hdmi_hpd_irq_handler(int irq, void *arg) -{ - struct drm_device *dev = (struct drm_device *)arg; - struct drm_connector *connector; - struct omap_drm_private *priv = dev->dev_private; - unsigned long flags = 0; - - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { - if ((connector->connector_type == DRM_MODE_CONNECTOR_HDMIA) || - (connector->connector_type == DRM_MODE_CONNECTOR_HDMIB)) { - connector->status = connector_status_unknown; - - if (priv->fbdev) { - spin_lock_irqsave(&list_lock, flags); - drm_kms_helper_poll_enable(dev); - connector->force = 0; - spin_unlock_irqrestore(&list_lock, flags); - } - } - } - - return IRQ_HANDLED; -} diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c index 9a81878de3d0..1d8d17dbeb76 100644 --- a/drivers/gpu/drm/omapdrm/omap_plane.c +++ b/drivers/gpu/drm/omapdrm/omap_plane.c @@ -87,7 +87,6 @@ static void omap_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *state = plane->state; struct omap_plane_state *omap_state = to_omap_plane_state(state); struct omap_overlay_info info; - struct omap_drm_window win; int ret; DBG("%s, crtc=%p fb=%p", omap_plane->name, state->crtc, state->fb); @@ -98,41 +97,14 @@ static void omap_plane_atomic_update(struct drm_plane *plane, } memset(&info, 0, sizeof(info)); - info.rotation_type = OMAP_DSS_ROT_DMA; - info.rotation = OMAP_DSS_ROT_0; - info.mirror = 0; + info.rotation_type = OMAP_DSS_ROT_NONE; + info.rotation = BIT(DRM_ROTATE_0); info.zorder = omap_state->zorder; info.global_alpha = omap_state->global_alpha; info.pre_mult_alpha = omap_state->pre_mult_alpha; - memset(&win, 0, sizeof(win)); - win.rotation = state->rotation; - win.crtc_x = state->crtc_x; - win.crtc_y = state->crtc_y; - win.crtc_w = state->crtc_w; - win.crtc_h = state->crtc_h; - - /* - * src values are in Q16 fixed point, convert to integer. - * omap_framebuffer_update_scanout() takes adjusted src. - */ - win.src_x = state->src_x >> 16; - win.src_y = state->src_y >> 16; - - switch (state->rotation & DRM_ROTATE_MASK) { - case BIT(DRM_ROTATE_90): - case BIT(DRM_ROTATE_270): - win.src_w = state->src_h >> 16; - win.src_h = state->src_w >> 16; - break; - default: - win.src_w = state->src_w >> 16; - win.src_h = state->src_h >> 16; - break; - } - /* update scanout: */ - omap_framebuffer_update_scanout(state->fb, &win, &info); + omap_framebuffer_update_scanout(state->fb, state, &info); DBG("%dx%d -> %dx%d (%d)", info.width, info.height, info.out_width, info.out_height, diff --git a/drivers/gpu/drm/omapdrm/omap_wb.c b/drivers/gpu/drm/omapdrm/omap_wb.c index da988d9c7dbe..73b76fca2387 100644 --- a/drivers/gpu/drm/omapdrm/omap_wb.c +++ b/drivers/gpu/drm/omapdrm/omap_wb.c @@ -64,24 +64,6 @@ struct wb_fmt *find_format(struct v4l2_format *f) return NULL; } -enum omap_color_mode fourcc_to_dss(u32 fourcc) -{ - switch (fourcc) { - case DRM_FORMAT_XRGB8888: - return OMAP_DSS_COLOR_RGB24U; - - case DRM_FORMAT_NV12: - return OMAP_DSS_COLOR_NV12; - case DRM_FORMAT_YUYV: - return OMAP_DSS_COLOR_YUV2; - case DRM_FORMAT_UYVY: - return OMAP_DSS_COLOR_UYVY; - default: - WARN_ONCE(1, "WB: unsupported fourcc code: 0x%x\n", fourcc); - return OMAP_DSS_COLOR_UYVY; - } -} - static void wb_irq(struct omap_drm_irq *irq, uint32_t irqstatus) { struct wb_dev *dev = container_of(irq, struct wb_dev, wb_irq); diff --git a/drivers/gpu/drm/omapdrm/omap_wb.h b/drivers/gpu/drm/omapdrm/omap_wb.h index 6ab3f3078f2d..08f722572fc2 100644 --- a/drivers/gpu/drm/omapdrm/omap_wb.h +++ b/drivers/gpu/drm/omapdrm/omap_wb.h @@ -222,8 +222,6 @@ static inline dma_addr_t vb2_dma_addr_plus_data_offset(struct vb2_buffer *vb, vb->planes[plane_no].data_offset; } -enum omap_color_mode fourcc_to_dss(u32 fourcc); - void wbm2m_irq(struct wbm2m_dev *dev, uint32_t irqstatus); int wbm2m_init(struct wb_dev *dev); void wbm2m_cleanup(struct wb_dev *dev); diff --git a/drivers/gpu/drm/omapdrm/omap_wb_cap.c b/drivers/gpu/drm/omapdrm/omap_wb_cap.c index 7b7c1522069c..aa9217033e21 100644 --- a/drivers/gpu/drm/omapdrm/omap_wb_cap.c +++ b/drivers/gpu/drm/omapdrm/omap_wb_cap.c @@ -205,11 +205,11 @@ static int wbcap_schedule_next_buffer(struct wbcap_dev *dev) wb_info.width = pix->width; wb_info.height = pix->height; - wb_info.color_mode = fourcc_to_dss(pix->pixelformat); + wb_info.color_mode = pix->pixelformat; wb_info.pre_mult_alpha = 1; - wb_info.rotation = OMAP_DSS_ROT_0; - wb_info.rotation_type = OMAP_DSS_ROT_DMA; + wb_info.rotation = BIT(DRM_ROTATE_0); + wb_info.rotation_type = OMAP_DSS_ROT_NONE; ok = wb_cap_setup(dev, wb_inputs[dev->input].wb_channel, diff --git a/drivers/gpu/drm/omapdrm/omap_wb_m2m.c b/drivers/gpu/drm/omapdrm/omap_wb_m2m.c index 784c4247ade6..4a3291f699e6 100644 --- a/drivers/gpu/drm/omapdrm/omap_wb_m2m.c +++ b/drivers/gpu/drm/omapdrm/omap_wb_m2m.c @@ -202,11 +202,11 @@ static void device_run(void *priv) src_info.out_width = spix->width; src_info.out_height = spix->height; - src_info.color_mode = fourcc_to_dss(spix->pixelformat); + src_info.color_mode = spix->pixelformat; src_info.global_alpha = 0xff; - src_info.rotation = OMAP_DSS_ROT_0; - src_info.rotation_type = OMAP_DSS_ROT_DMA; + src_info.rotation = BIT(DRM_ROTATE_0); + src_info.rotation_type = OMAP_DSS_ROT_NONE; log_dbg(dev, "SRC: ctx %pa buf_index %d %dx%d, sw %d\n", &ctx, s_vb->index, @@ -221,11 +221,11 @@ static void device_run(void *priv) wb_info.width = dpix->width; wb_info.height = dpix->height; - wb_info.color_mode = fourcc_to_dss(dpix->pixelformat); + wb_info.color_mode = dpix->pixelformat; wb_info.pre_mult_alpha = 1; - wb_info.rotation = OMAP_DSS_ROT_0; - wb_info.rotation_type = OMAP_DSS_ROT_DMA; + wb_info.rotation = DRM_ROTATE_0; + wb_info.rotation_type = OMAP_DSS_ROT_NONE; log_dbg(dev, "DST: ctx %pa buf_index %d %dx%d, sw %d\n", &ctx, d_vb->index, diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index d4ac8c837314..8e86cf7da614 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -30,6 +30,7 @@ #include "radeon_audio.h" #include "atom.h" #include <linux/backlight.h> +#include <linux/dmi.h> extern int atom_debug; @@ -2183,9 +2184,17 @@ int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder, int fe_idx) goto assigned; } - /* on DCE32 and encoder can driver any block so just crtc id */ + /* + * On DCE32 any encoder can drive any block so usually just use crtc id, + * but Apple thinks different at least on iMac10,1, so there use linkb, + * otherwise the internal eDP panel will stay dark. + */ if (ASIC_IS_DCE32(rdev)) { - enc_idx = radeon_crtc->crtc_id; + if (dmi_match(DMI_PRODUCT_NAME, "iMac10,1")) + enc_idx = (dig->linkb) ? 1 : 0; + else + enc_idx = radeon_crtc->crtc_id; + goto assigned; } diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 4a09947be244..2ccf81168d1e 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -776,6 +776,18 @@ bool ci_dpm_vblank_too_short(struct radeon_device *rdev) u32 vblank_time = r600_dpm_get_vblank_time(rdev); u32 switch_limit = pi->mem_gddr5 ? 450 : 300; + /* disable mclk switching if the refresh is >120Hz, even if the + * blanking period would allow it + */ + if (r600_dpm_get_vrefresh(rdev) > 120) + return true; + + /* disable mclk switching if the refresh is >120Hz, even if the + * blanking period would allow it + */ + if (r600_dpm_get_vrefresh(rdev) > 120) + return true; + if (vblank_time < switch_limit) return true; else diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index f81fb2641097..134874cab4c7 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -7762,7 +7762,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, tmp); } if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT) { - tmp = RREG32(DC_HPD5_INT_CONTROL); + tmp = RREG32(DC_HPD6_INT_CONTROL); tmp |= DC_HPDx_INT_ACK; WREG32(DC_HPD6_INT_CONTROL, tmp); } @@ -7792,7 +7792,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, tmp); } if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) { - tmp = RREG32(DC_HPD5_INT_CONTROL); + tmp = RREG32(DC_HPD6_INT_CONTROL); tmp |= DC_HPDx_RX_INT_ACK; WREG32(DC_HPD6_INT_CONTROL, tmp); } diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 32491355a1d4..ba9e6ed4ae54 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -4924,7 +4924,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, tmp); } if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) { - tmp = RREG32(DC_HPD5_INT_CONTROL); + tmp = RREG32(DC_HPD6_INT_CONTROL); tmp |= DC_HPDx_INT_ACK; WREG32(DC_HPD6_INT_CONTROL, tmp); } @@ -4955,7 +4955,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, tmp); } if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) { - tmp = RREG32(DC_HPD5_INT_CONTROL); + tmp = RREG32(DC_HPD6_INT_CONTROL); tmp |= DC_HPDx_RX_INT_ACK; WREG32(DC_HPD6_INT_CONTROL, tmp); } diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index cc2fdf0be37a..0e20c08f8977 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3945,7 +3945,7 @@ static void r600_irq_ack(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, tmp); } if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT) { - tmp = RREG32(DC_HPD5_INT_CONTROL); + tmp = RREG32(DC_HPD6_INT_CONTROL); tmp |= DC_HPDx_INT_ACK; WREG32(DC_HPD6_INT_CONTROL, tmp); } diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index a9b01bcf7d0a..fcecaf5b5526 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -3394,6 +3394,13 @@ void radeon_combios_asic_init(struct drm_device *dev) rdev->pdev->subsystem_vendor == 0x103c && rdev->pdev->subsystem_device == 0x280a) return; + /* quirk for rs4xx Toshiba Sattellite L20-183 latop to make it resume + * - it hangs on resume inside the dynclk 1 table. + */ + if (rdev->family == CHIP_RS400 && + rdev->pdev->subsystem_vendor == 0x1179 && + rdev->pdev->subsystem_device == 0xff31) + return; /* DYN CLK 1 */ table = combios_get_table_offset(dev, COMBIOS_DYN_CLK_1_TABLE); diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c index 04cec0da5d1e..8901228b5d5d 100644 --- a/drivers/gpu/drm/radeon/radeon_cursor.c +++ b/drivers/gpu/drm/radeon/radeon_cursor.c @@ -205,8 +205,8 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y) } if (x <= (crtc->x - w) || y <= (crtc->y - radeon_crtc->cursor_height) || - x >= (crtc->x + crtc->mode.crtc_hdisplay) || - y >= (crtc->y + crtc->mode.crtc_vdisplay)) + x >= (crtc->x + crtc->mode.hdisplay) || + y >= (crtc->y + crtc->mode.vdisplay)) goto out_of_bounds; x += xorigin; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 4aa2cbe4c85f..a77521695c9a 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -127,6 +127,10 @@ static struct radeon_px_quirk radeon_px_quirk_list[] = { * https://bugzilla.kernel.org/show_bug.cgi?id=51381 */ { PCI_VENDOR_ID_ATI, 0x6840, 0x1043, 0x2122, RADEON_PX_QUIRK_DISABLE_PX }, + /* Asus K53TK laptop with AMD A6-3420M APU and Radeon 7670m GPU + * https://bugs.freedesktop.org/show_bug.cgi?id=101491 + */ + { PCI_VENDOR_ID_ATI, 0x6741, 0x1043, 0x2122, RADEON_PX_QUIRK_DISABLE_PX }, /* macbook pro 8.2 */ { PCI_VENDOR_ID_ATI, 0x6741, PCI_VENDOR_ID_APPLE, 0x00e2, RADEON_PX_QUIRK_LONG_WAKEUP }, { 0, 0, 0, 0, 0 }, diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 35310336dd0a..d684e2b79d2b 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -213,8 +213,8 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo, rbo->placement.num_busy_placement = 0; for (i = 0; i < rbo->placement.num_placement; i++) { if (rbo->placements[i].flags & TTM_PL_FLAG_VRAM) { - if (rbo->placements[0].fpfn < fpfn) - rbo->placements[0].fpfn = fpfn; + if (rbo->placements[i].fpfn < fpfn) + rbo->placements[i].fpfn = fpfn; } else { rbo->placement.busy_placement = &rbo->placements[i]; diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index f878d6962da5..5cf3a2cbc07e 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -6335,7 +6335,7 @@ static inline void si_irq_ack(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, tmp); } if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) { - tmp = RREG32(DC_HPD5_INT_CONTROL); + tmp = RREG32(DC_HPD6_INT_CONTROL); tmp |= DC_HPDx_INT_ACK; WREG32(DC_HPD6_INT_CONTROL, tmp); } @@ -6366,7 +6366,7 @@ static inline void si_irq_ack(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, tmp); } if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) { - tmp = RREG32(DC_HPD5_INT_CONTROL); + tmp = RREG32(DC_HPD6_INT_CONTROL); tmp |= DC_HPDx_RX_INT_ACK; WREG32(DC_HPD6_INT_CONTROL, tmp); } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c index 48cb19949ca3..9255b9c096b6 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -282,26 +282,6 @@ static void rcar_du_crtc_update_planes(struct rcar_du_crtc *rcrtc) * Page Flip */ -void rcar_du_crtc_cancel_page_flip(struct rcar_du_crtc *rcrtc, - struct drm_file *file) -{ - struct drm_pending_vblank_event *event; - struct drm_device *dev = rcrtc->crtc.dev; - unsigned long flags; - - /* Destroy the pending vertical blanking event associated with the - * pending page flip, if any, and disable vertical blanking interrupts. - */ - spin_lock_irqsave(&dev->event_lock, flags); - event = rcrtc->event; - if (event && event->base.file_priv == file) { - rcrtc->event = NULL; - event->base.destroy(&event->base); - drm_crtc_vblank_put(&rcrtc->crtc); - } - spin_unlock_irqrestore(&dev->event_lock, flags); -} - static void rcar_du_crtc_finish_page_flip(struct rcar_du_crtc *rcrtc) { struct drm_pending_vblank_event *event; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h index 4b95d9d08c49..2bbe3f5aab65 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h @@ -67,8 +67,6 @@ enum rcar_du_output { int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index); void rcar_du_crtc_enable_vblank(struct rcar_du_crtc *rcrtc, bool enable); -void rcar_du_crtc_cancel_page_flip(struct rcar_du_crtc *rcrtc, - struct drm_file *file); void rcar_du_crtc_suspend(struct rcar_du_crtc *rcrtc); void rcar_du_crtc_resume(struct rcar_du_crtc *rcrtc); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index 40422f6b645e..bb9cd35d7fdf 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -144,91 +144,6 @@ MODULE_DEVICE_TABLE(of, rcar_du_of_table); * DRM operations */ -static int rcar_du_unload(struct drm_device *dev) -{ - struct rcar_du_device *rcdu = dev->dev_private; - - if (rcdu->fbdev) - drm_fbdev_cma_fini(rcdu->fbdev); - - drm_kms_helper_poll_fini(dev); - drm_mode_config_cleanup(dev); - drm_vblank_cleanup(dev); - - dev->irq_enabled = 0; - dev->dev_private = NULL; - - return 0; -} - -static int rcar_du_load(struct drm_device *dev, unsigned long flags) -{ - struct platform_device *pdev = dev->platformdev; - struct device_node *np = pdev->dev.of_node; - struct rcar_du_device *rcdu; - struct resource *mem; - int ret; - - if (np == NULL) { - dev_err(dev->dev, "no platform data\n"); - return -ENODEV; - } - - rcdu = devm_kzalloc(&pdev->dev, sizeof(*rcdu), GFP_KERNEL); - if (rcdu == NULL) { - dev_err(dev->dev, "failed to allocate private data\n"); - return -ENOMEM; - } - - init_waitqueue_head(&rcdu->commit.wait); - - rcdu->dev = &pdev->dev; - rcdu->info = of_match_device(rcar_du_of_table, rcdu->dev)->data; - rcdu->ddev = dev; - dev->dev_private = rcdu; - - /* I/O resources */ - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - rcdu->mmio = devm_ioremap_resource(&pdev->dev, mem); - if (IS_ERR(rcdu->mmio)) - return PTR_ERR(rcdu->mmio); - - /* Initialize vertical blanking interrupts handling. Start with vblank - * disabled for all CRTCs. - */ - ret = drm_vblank_init(dev, (1 << rcdu->info->num_crtcs) - 1); - if (ret < 0) { - dev_err(&pdev->dev, "failed to initialize vblank\n"); - goto done; - } - - /* DRM/KMS objects */ - ret = rcar_du_modeset_init(rcdu); - if (ret < 0) { - dev_err(&pdev->dev, "failed to initialize DRM/KMS (%d)\n", ret); - goto done; - } - - dev->irq_enabled = 1; - - platform_set_drvdata(pdev, rcdu); - -done: - if (ret) - rcar_du_unload(dev); - - return ret; -} - -static void rcar_du_preclose(struct drm_device *dev, struct drm_file *file) -{ - struct rcar_du_device *rcdu = dev->dev_private; - unsigned int i; - - for (i = 0; i < rcdu->num_crtcs; ++i) - rcar_du_crtc_cancel_page_flip(&rcdu->crtcs[i], file); -} - static void rcar_du_lastclose(struct drm_device *dev) { struct rcar_du_device *rcdu = dev->dev_private; @@ -269,11 +184,7 @@ static const struct file_operations rcar_du_fops = { static struct drm_driver rcar_du_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC, - .load = rcar_du_load, - .unload = rcar_du_unload, - .preclose = rcar_du_preclose, .lastclose = rcar_du_lastclose, - .set_busid = drm_platform_set_busid, .get_vblank_counter = drm_vblank_no_hw_counter, .enable_vblank = rcar_du_enable_vblank, .disable_vblank = rcar_du_disable_vblank, @@ -333,18 +244,104 @@ static const struct dev_pm_ops rcar_du_pm_ops = { * Platform driver */ -static int rcar_du_probe(struct platform_device *pdev) +static int rcar_du_remove(struct platform_device *pdev) { - return drm_platform_init(&rcar_du_driver, pdev); + struct rcar_du_device *rcdu = platform_get_drvdata(pdev); + struct drm_device *ddev = rcdu->ddev; + + mutex_lock(&ddev->mode_config.mutex); + drm_connector_unplug_all(ddev); + mutex_unlock(&ddev->mode_config.mutex); + + drm_dev_unregister(ddev); + + if (rcdu->fbdev) + drm_fbdev_cma_fini(rcdu->fbdev); + + drm_kms_helper_poll_fini(ddev); + drm_mode_config_cleanup(ddev); + + drm_dev_unref(ddev); + + return 0; } -static int rcar_du_remove(struct platform_device *pdev) +static int rcar_du_probe(struct platform_device *pdev) { - struct rcar_du_device *rcdu = platform_get_drvdata(pdev); + struct device_node *np = pdev->dev.of_node; + struct rcar_du_device *rcdu; + struct drm_connector *connector; + struct drm_device *ddev; + struct resource *mem; + int ret; + + if (np == NULL) { + dev_err(&pdev->dev, "no device tree node\n"); + return -ENODEV; + } - drm_put_dev(rcdu->ddev); + /* Allocate and initialize the DRM and R-Car device structures. */ + rcdu = devm_kzalloc(&pdev->dev, sizeof(*rcdu), GFP_KERNEL); + if (rcdu == NULL) + return -ENOMEM; + + init_waitqueue_head(&rcdu->commit.wait); + + rcdu->dev = &pdev->dev; + rcdu->info = of_match_device(rcar_du_of_table, rcdu->dev)->data; + + platform_set_drvdata(pdev, rcdu); + + /* I/O resources */ + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + rcdu->mmio = devm_ioremap_resource(&pdev->dev, mem); + if (IS_ERR(rcdu->mmio)) + return PTR_ERR(rcdu->mmio); + + /* DRM/KMS objects */ + ddev = drm_dev_alloc(&rcar_du_driver, &pdev->dev); + if (!ddev) + return -ENOMEM; + + drm_dev_set_unique(ddev, dev_name(&pdev->dev)); + + rcdu->ddev = ddev; + ddev->dev_private = rcdu; + + ret = rcar_du_modeset_init(rcdu); + if (ret < 0) { + dev_err(&pdev->dev, "failed to initialize DRM/KMS (%d)\n", ret); + goto error; + } + + ddev->irq_enabled = 1; + + /* Register the DRM device with the core and the connectors with + * sysfs. + */ + ret = drm_dev_register(ddev, 0); + if (ret) + goto error; + + mutex_lock(&ddev->mode_config.mutex); + drm_for_each_connector(connector, ddev) { + ret = drm_connector_register(connector); + if (ret < 0) + break; + } + mutex_unlock(&ddev->mode_config.mutex); + + if (ret < 0) + goto error; + + DRM_INFO("Device %s probed\n", dev_name(&pdev->dev)); return 0; + +error: + rcar_du_remove(pdev); + + return ret; } static struct platform_driver rcar_du_platform_driver = { diff --git a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c b/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c index 96f2eb43713c..6038be93c58d 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c @@ -55,12 +55,6 @@ static const struct drm_connector_helper_funcs connector_helper_funcs = { .best_encoder = rcar_du_connector_best_encoder, }; -static void rcar_du_hdmi_connector_destroy(struct drm_connector *connector) -{ - drm_connector_unregister(connector); - drm_connector_cleanup(connector); -} - static enum drm_connector_status rcar_du_hdmi_connector_detect(struct drm_connector *connector, bool force) { @@ -79,7 +73,7 @@ static const struct drm_connector_funcs connector_funcs = { .reset = drm_atomic_helper_connector_reset, .detect = rcar_du_hdmi_connector_detect, .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = rcar_du_hdmi_connector_destroy, + .destroy = drm_connector_cleanup, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; @@ -108,9 +102,6 @@ int rcar_du_hdmi_connector_init(struct rcar_du_device *rcdu, return ret; drm_connector_helper_add(connector, &connector_helper_funcs); - ret = drm_connector_register(connector); - if (ret < 0) - return ret; connector->dpms = DRM_MODE_DPMS_OFF; drm_object_property_set_value(&connector->base, diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c index ca12e8ca5552..46429c4be8e5 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c @@ -761,6 +761,13 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu) if (ret < 0) return ret; + /* Initialize vertical blanking interrupts handling. Start with vblank + * disabled for all CRTCs. + */ + ret = drm_vblank_init(dev, (1 << rcdu->info->num_crtcs) - 1); + if (ret < 0) + return ret; + /* Initialize the groups. */ num_groups = DIV_ROUND_UP(rcdu->num_crtcs, 2); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c index 0c43032fc693..e905f5da7aaa 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c @@ -62,12 +62,6 @@ static const struct drm_connector_helper_funcs connector_helper_funcs = { .best_encoder = rcar_du_connector_best_encoder, }; -static void rcar_du_lvds_connector_destroy(struct drm_connector *connector) -{ - drm_connector_unregister(connector); - drm_connector_cleanup(connector); -} - static enum drm_connector_status rcar_du_lvds_connector_detect(struct drm_connector *connector, bool force) { @@ -79,7 +73,7 @@ static const struct drm_connector_funcs connector_funcs = { .reset = drm_atomic_helper_connector_reset, .detect = rcar_du_lvds_connector_detect, .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = rcar_du_lvds_connector_destroy, + .destroy = drm_connector_cleanup, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; @@ -117,9 +111,6 @@ int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu, return ret; drm_connector_helper_add(connector, &connector_helper_funcs); - ret = drm_connector_register(connector); - if (ret < 0) - return ret; connector->dpms = DRM_MODE_DPMS_OFF; drm_object_property_set_value(&connector->base, diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c index e0a5d8f93963..9d7e5c99caf6 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c @@ -31,12 +31,6 @@ static const struct drm_connector_helper_funcs connector_helper_funcs = { .best_encoder = rcar_du_connector_best_encoder, }; -static void rcar_du_vga_connector_destroy(struct drm_connector *connector) -{ - drm_connector_unregister(connector); - drm_connector_cleanup(connector); -} - static enum drm_connector_status rcar_du_vga_connector_detect(struct drm_connector *connector, bool force) { @@ -48,7 +42,7 @@ static const struct drm_connector_funcs connector_funcs = { .reset = drm_atomic_helper_connector_reset, .detect = rcar_du_vga_connector_detect, .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = rcar_du_vga_connector_destroy, + .destroy = drm_connector_cleanup, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; @@ -76,9 +70,6 @@ int rcar_du_vga_connector_init(struct rcar_du_device *rcdu, return ret; drm_connector_helper_add(connector, &connector_helper_funcs); - ret = drm_connector_register(connector); - if (ret < 0) - return ret; connector->dpms = DRM_MODE_DPMS_OFF; drm_object_property_set_value(&connector->base, diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 4ae8b56b1847..037c38bb5333 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1621,7 +1621,6 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink) struct ttm_buffer_object *bo; int ret = -EBUSY; int put_count; - uint32_t swap_placement = (TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM); spin_lock(&glob->lru_lock); list_for_each_entry(bo, &glob->swap_lru, swap) { @@ -1657,7 +1656,8 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink) if (unlikely(ret != 0)) goto out; - if ((bo->mem.placement & swap_placement) != swap_placement) { + if (bo->mem.mem_type != TTM_PL_SYSTEM || + bo->ttm->caching_state != tt_cached) { struct ttm_mem_reg evict_mem; evict_mem = bo->mem; diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 8fb7213277cc..b75391495778 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -66,8 +66,11 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo, if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out_unlock; + ttm_bo_reference(bo); up_read(&vma->vm_mm->mmap_sem); (void) ttm_bo_wait(bo, false, true, false); + ttm_bo_unreserve(bo); + ttm_bo_unref(&bo); goto out_unlock; } @@ -114,8 +117,10 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) { if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + ttm_bo_reference(bo); up_read(&vma->vm_mm->mmap_sem); (void) ttm_bo_wait_unreserved(bo); + ttm_bo_unref(&bo); } return VM_FAULT_RETRY; @@ -160,6 +165,13 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ret = ttm_bo_vm_fault_idle(bo, vma, vmf); if (unlikely(ret != 0)) { retval = ret; + + if (retval == VM_FAULT_RETRY && + !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + /* The BO has already been unreserved. */ + return retval; + } + goto out_unlock; } diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c index 4f5fa8d65fe9..144367c0c28f 100644 --- a/drivers/gpu/drm/ttm/ttm_object.c +++ b/drivers/gpu/drm/ttm/ttm_object.c @@ -179,7 +179,7 @@ int ttm_base_object_init(struct ttm_object_file *tfile, if (unlikely(ret != 0)) goto out_err0; - ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL); + ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false); if (unlikely(ret != 0)) goto out_err1; @@ -318,7 +318,8 @@ EXPORT_SYMBOL(ttm_ref_object_exists); int ttm_ref_object_add(struct ttm_object_file *tfile, struct ttm_base_object *base, - enum ttm_ref_type ref_type, bool *existed) + enum ttm_ref_type ref_type, bool *existed, + bool require_existed) { struct drm_open_hash *ht = &tfile->ref_hash[ref_type]; struct ttm_ref_object *ref; @@ -345,6 +346,9 @@ int ttm_ref_object_add(struct ttm_object_file *tfile, } rcu_read_unlock(); + if (require_existed) + return -EPERM; + ret = ttm_mem_global_alloc(mem_glob, sizeof(*ref), false, false); if (unlikely(ret != 0)) @@ -635,7 +639,7 @@ int ttm_prime_fd_to_handle(struct ttm_object_file *tfile, prime = (struct ttm_prime_object *) dma_buf->priv; base = &prime->base; *handle = base->hash.key; - ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL); + ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false); dma_buf_put(dma_buf); diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c index 6a81e084593b..2b59d80a09b8 100644 --- a/drivers/gpu/drm/virtio/virtgpu_fb.c +++ b/drivers/gpu/drm/virtio/virtgpu_fb.c @@ -338,7 +338,7 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper, info->fbops = &virtio_gpufb_ops; info->pixmap.flags = FB_PIXMAP_SYSTEM; - info->screen_base = obj->vmap; + info->screen_buffer = obj->vmap; info->screen_size = obj->gem_base.size; drm_fb_helper_fill_fix(info, fb->pitches[0], fb->depth); drm_fb_helper_fill_var(info, &vfbdev->helper, diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index f300eba95bb1..1244cdf52859 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -81,8 +81,10 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev, return -ENOMEM; size = roundup(size, PAGE_SIZE); ret = drm_gem_object_init(vgdev->ddev, &bo->gem_base, size); - if (ret != 0) + if (ret != 0) { + kfree(bo); return ret; + } bo->dumb = false; virtio_gpu_init_ttm_placement(bo, pinned); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c index 13db8a2851ed..1f013d45c9e9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c @@ -321,6 +321,7 @@ void vmw_cmdbuf_res_man_destroy(struct vmw_cmdbuf_res_manager *man) list_for_each_entry_safe(entry, next, &man->list, head) vmw_cmdbuf_res_free(man, entry); + drm_ht_remove(&man->resources); kfree(man); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index ecf15cf0c3fd..04fd0f2b6af0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -471,7 +471,7 @@ static int vmw_cmd_invalid(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGA3dCmdHeader *header) { - return capable(CAP_SYS_ADMIN) ? : -EINVAL; + return -EINVAL; } static int vmw_cmd_ok(struct vmw_private *dev_priv, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 8e689b439890..6c649f7b5929 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -539,7 +539,7 @@ int vmw_fence_create(struct vmw_fence_manager *fman, struct vmw_fence_obj **p_fence) { struct vmw_fence_obj *fence; - int ret; + int ret; fence = kzalloc(sizeof(*fence), GFP_KERNEL); if (unlikely(fence == NULL)) @@ -702,6 +702,41 @@ void vmw_fence_fifo_up(struct vmw_fence_manager *fman) } +/** + * vmw_fence_obj_lookup - Look up a user-space fence object + * + * @tfile: A struct ttm_object_file identifying the caller. + * @handle: A handle identifying the fence object. + * @return: A struct vmw_user_fence base ttm object on success or + * an error pointer on failure. + * + * The fence object is looked up and type-checked. The caller needs + * to have opened the fence object first, but since that happens on + * creation and fence objects aren't shareable, that's not an + * issue currently. + */ +static struct ttm_base_object * +vmw_fence_obj_lookup(struct ttm_object_file *tfile, u32 handle) +{ + struct ttm_base_object *base = ttm_base_object_lookup(tfile, handle); + + if (!base) { + pr_err("Invalid fence object handle 0x%08lx.\n", + (unsigned long)handle); + return ERR_PTR(-EINVAL); + } + + if (base->refcount_release != vmw_user_fence_base_release) { + pr_err("Invalid fence object handle 0x%08lx.\n", + (unsigned long)handle); + ttm_base_object_unref(&base); + return ERR_PTR(-EINVAL); + } + + return base; +} + + int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { @@ -727,13 +762,9 @@ int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data, arg->kernel_cookie = jiffies + wait_timeout; } - base = ttm_base_object_lookup(tfile, arg->handle); - if (unlikely(base == NULL)) { - printk(KERN_ERR "Wait invalid fence object handle " - "0x%08lx.\n", - (unsigned long)arg->handle); - return -EINVAL; - } + base = vmw_fence_obj_lookup(tfile, arg->handle); + if (IS_ERR(base)) + return PTR_ERR(base); fence = &(container_of(base, struct vmw_user_fence, base)->fence); @@ -772,13 +803,9 @@ int vmw_fence_obj_signaled_ioctl(struct drm_device *dev, void *data, struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; struct vmw_private *dev_priv = vmw_priv(dev); - base = ttm_base_object_lookup(tfile, arg->handle); - if (unlikely(base == NULL)) { - printk(KERN_ERR "Fence signaled invalid fence object handle " - "0x%08lx.\n", - (unsigned long)arg->handle); - return -EINVAL; - } + base = vmw_fence_obj_lookup(tfile, arg->handle); + if (IS_ERR(base)) + return PTR_ERR(base); fence = &(container_of(base, struct vmw_user_fence, base)->fence); fman = fman_from_fence(fence); @@ -1093,6 +1120,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data, (struct drm_vmw_fence_event_arg *) data; struct vmw_fence_obj *fence = NULL; struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv); + struct ttm_object_file *tfile = vmw_fp->tfile; struct drm_vmw_fence_rep __user *user_fence_rep = (struct drm_vmw_fence_rep __user *)(unsigned long) arg->fence_rep; @@ -1106,24 +1134,18 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data, */ if (arg->handle) { struct ttm_base_object *base = - ttm_base_object_lookup_for_ref(dev_priv->tdev, - arg->handle); - - if (unlikely(base == NULL)) { - DRM_ERROR("Fence event invalid fence object handle " - "0x%08lx.\n", - (unsigned long)arg->handle); - return -EINVAL; - } + vmw_fence_obj_lookup(tfile, arg->handle); + + if (IS_ERR(base)) + return PTR_ERR(base); + fence = &(container_of(base, struct vmw_user_fence, base)->fence); (void) vmw_fence_obj_reference(fence); if (user_fence_rep != NULL) { - bool existed; - ret = ttm_ref_object_add(vmw_fp->tfile, base, - TTM_REF_USAGE, &existed); + TTM_REF_USAGE, NULL, false); if (unlikely(ret != 0)) { DRM_ERROR("Failed to reference a fence " "object.\n"); @@ -1166,8 +1188,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data, return 0; out_no_create: if (user_fence_rep != NULL) - ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile, - handle, TTM_REF_USAGE); + ttm_ref_object_base_unref(tfile, handle, TTM_REF_USAGE); out_no_ref_obj: vmw_fence_obj_unreference(&fence); return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index b6a0806b06bf..a1c68e6a689e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -368,6 +368,8 @@ static void *vmw_local_fifo_reserve(struct vmw_private *dev_priv, return fifo_state->static_buffer; else { fifo_state->dynamic_buffer = vmalloc(bytes); + if (!fifo_state->dynamic_buffer) + goto out_err; return fifo_state->dynamic_buffer; } } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index b8c6a03c8c54..5ec24fd801cd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -114,8 +114,6 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, param->value = dev_priv->has_dx; break; default: - DRM_ERROR("Illegal vmwgfx get param request: %d\n", - param->param); return -EINVAL; } @@ -186,7 +184,7 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data, bool gb_objects = !!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS); struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv); - if (unlikely(arg->pad64 != 0)) { + if (unlikely(arg->pad64 != 0 || arg->max_size == 0)) { DRM_ERROR("Illegal GET_3D_CAP argument.\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index e57667ca7557..dbca128a9aa6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -591,7 +591,7 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo, return ret; ret = ttm_ref_object_add(tfile, &user_bo->prime.base, - TTM_REF_SYNCCPU_WRITE, &existed); + TTM_REF_SYNCCPU_WRITE, &existed, false); if (ret != 0 || existed) ttm_bo_synccpu_write_release(&user_bo->dma.base); @@ -775,7 +775,7 @@ int vmw_user_dmabuf_reference(struct ttm_object_file *tfile, *handle = user_bo->prime.base.hash.key; return ttm_ref_object_add(tfile, &user_bo->prime.base, - TTM_REF_USAGE, NULL); + TTM_REF_USAGE, NULL, false); } /* diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 7d620e82e000..027987023400 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -715,11 +715,14 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, 128; num_sizes = 0; - for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i) + for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i) { + if (req->mip_levels[i] > DRM_VMW_MAX_MIP_LEVELS) + return -EINVAL; num_sizes += req->mip_levels[i]; + } - if (num_sizes > DRM_VMW_MAX_SURFACE_FACES * - DRM_VMW_MAX_MIP_LEVELS) + if (num_sizes > DRM_VMW_MAX_SURFACE_FACES * DRM_VMW_MAX_MIP_LEVELS || + num_sizes == 0) return -EINVAL; size = vmw_user_surface_size + 128 + @@ -904,17 +907,16 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv, uint32_t handle; struct ttm_base_object *base; int ret; + bool require_exist = false; if (handle_type == DRM_VMW_HANDLE_PRIME) { ret = ttm_prime_fd_to_handle(tfile, u_handle, &handle); if (unlikely(ret != 0)) return ret; } else { - if (unlikely(drm_is_render_client(file_priv))) { - DRM_ERROR("Render client refused legacy " - "surface reference.\n"); - return -EACCES; - } + if (unlikely(drm_is_render_client(file_priv))) + require_exist = true; + if (ACCESS_ONCE(vmw_fpriv(file_priv)->locked_master)) { DRM_ERROR("Locked master refused legacy " "surface reference.\n"); @@ -942,17 +944,14 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv, /* * Make sure the surface creator has the same - * authenticating master. + * authenticating master, or is already registered with us. */ if (drm_is_primary_client(file_priv) && - user_srf->master != file_priv->master) { - DRM_ERROR("Trying to reference surface outside of" - " master domain.\n"); - ret = -EACCES; - goto out_bad_resource; - } + user_srf->master != file_priv->master) + require_exist = true; - ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL); + ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, + require_exist); if (unlikely(ret != 0)) { DRM_ERROR("Could not add a reference to a surface.\n"); goto out_bad_resource; @@ -1289,11 +1288,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data, struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; int ret; uint32_t size; - uint32_t backup_handle; + uint32_t backup_handle = 0; if (req->multisample_count != 0) return -EINVAL; + if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS) + return -EINVAL; + if (unlikely(vmw_user_surface_size == 0)) vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) + 128; @@ -1329,12 +1331,16 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data, ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle, &res->backup, &user_srf->backup_base); - if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE < - res->backup_size) { - DRM_ERROR("Surface backup buffer is too small.\n"); - vmw_dmabuf_unreference(&res->backup); - ret = -EINVAL; - goto out_unlock; + if (ret == 0) { + if (res->backup->base.num_pages * PAGE_SIZE < + res->backup_size) { + DRM_ERROR("Surface backup buffer is too small.\n"); + vmw_dmabuf_unreference(&res->backup); + ret = -EINVAL; + goto out_unlock; + } else { + backup_handle = req->buffer_handle; + } } } else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer) ret = vmw_user_dmabuf_alloc(dev_priv, tfile, diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 936960202cf4..11a051bd8a8b 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2427,6 +2427,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0002) }, { HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0003) }, { HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0004) }, + { HID_USB_DEVICE(USB_VENDOR_ID_PETZL, USB_DEVICE_ID_PETZL_HEADLAMP) }, { HID_USB_DEVICE(USB_VENDOR_ID_PHILIPS, USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE) }, { HID_USB_DEVICE(USB_VENDOR_ID_POWERCOM, USB_DEVICE_ID_POWERCOM_UPS) }, #if defined(CONFIG_MOUSE_SYNAPTICS_USB) || defined(CONFIG_MOUSE_SYNAPTICS_USB_MODULE) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index e37030624165..37cbc2ecfc5f 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -285,6 +285,9 @@ #define USB_VENDOR_ID_DEALEXTREAME 0x10c5 #define USB_DEVICE_ID_DEALEXTREAME_RADIO_SI4701 0x819a +#define USB_VENDOR_ID_DELL 0x413c +#define USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE 0x301a + #define USB_VENDOR_ID_DELORME 0x1163 #define USB_DEVICE_ID_DELORME_EARTHMATE 0x0100 #define USB_DEVICE_ID_DELORME_EM_LT20 0x0200 @@ -774,6 +777,9 @@ #define USB_VENDOR_ID_PETALYNX 0x18b1 #define USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE 0x0037 +#define USB_VENDOR_ID_PETZL 0x2122 +#define USB_DEVICE_ID_PETZL_HEADLAMP 0x1234 + #define USB_VENDOR_ID_PHILIPS 0x0471 #define USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE 0x0617 diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 0b80633bae91..d4d655a10df1 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -364,6 +364,15 @@ static int i2c_hid_hwreset(struct i2c_client *client) if (ret) return ret; + /* + * The HID over I2C specification states that if a DEVICE needs time + * after the PWR_ON request, it should utilise CLOCK stretching. + * However, it has been observered that the Windows driver provides a + * 1ms sleep between the PWR_ON and RESET requests and that some devices + * rely on this. + */ + usleep_range(1000, 5000); + i2c_hid_dbg(ihid, "resetting...\n"); ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0); diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 6ca6ab00fa93..ce1543d69acb 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -72,6 +72,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 5c02d7bbc7f2..b62c50d1b1e4 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -148,19 +148,21 @@ static int wacom_pl_irq(struct wacom_wac *wacom) wacom->id[0] = STYLUS_DEVICE_ID; } - pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1)); - if (features->pressure_max > 255) - pressure = (pressure << 1) | ((data[4] >> 6) & 1); - pressure += (features->pressure_max + 1) / 2; + if (prox) { + pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1)); + if (features->pressure_max > 255) + pressure = (pressure << 1) | ((data[4] >> 6) & 1); + pressure += (features->pressure_max + 1) / 2; - input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14)); - input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14)); - input_report_abs(input, ABS_PRESSURE, pressure); + input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14)); + input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14)); + input_report_abs(input, ABS_PRESSURE, pressure); - input_report_key(input, BTN_TOUCH, data[4] & 0x08); - input_report_key(input, BTN_STYLUS, data[4] & 0x10); - /* Only allow the stylus2 button to be reported for the pen tool. */ - input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20)); + input_report_key(input, BTN_TOUCH, data[4] & 0x08); + input_report_key(input, BTN_STYLUS, data[4] & 0x10); + /* Only allow the stylus2 button to be reported for the pen tool. */ + input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20)); + } if (!prox) wacom->id[0] = 0; @@ -1438,37 +1440,38 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len) { unsigned char *data = wacom->data; - if (wacom->pen_input) + if (wacom->pen_input) { dev_dbg(wacom->pen_input->dev.parent, "%s: received report #%d\n", __func__, data[0]); - else if (wacom->touch_input) + + if (len == WACOM_PKGLEN_PENABLED || + data[0] == WACOM_REPORT_PENABLED) + return wacom_tpc_pen(wacom); + } + else if (wacom->touch_input) { dev_dbg(wacom->touch_input->dev.parent, "%s: received report #%d\n", __func__, data[0]); - switch (len) { - case WACOM_PKGLEN_TPC1FG: - return wacom_tpc_single_touch(wacom, len); - - case WACOM_PKGLEN_TPC2FG: - return wacom_tpc_mt_touch(wacom); + switch (len) { + case WACOM_PKGLEN_TPC1FG: + return wacom_tpc_single_touch(wacom, len); - case WACOM_PKGLEN_PENABLED: - return wacom_tpc_pen(wacom); + case WACOM_PKGLEN_TPC2FG: + return wacom_tpc_mt_touch(wacom); - default: - switch (data[0]) { - case WACOM_REPORT_TPC1FG: - case WACOM_REPORT_TPCHID: - case WACOM_REPORT_TPCST: - case WACOM_REPORT_TPC1FGE: - return wacom_tpc_single_touch(wacom, len); + default: + switch (data[0]) { + case WACOM_REPORT_TPC1FG: + case WACOM_REPORT_TPCHID: + case WACOM_REPORT_TPCST: + case WACOM_REPORT_TPC1FGE: + return wacom_tpc_single_touch(wacom, len); - case WACOM_REPORT_TPCMT: - case WACOM_REPORT_TPCMT2: - return wacom_mt_touch(wacom); + case WACOM_REPORT_TPCMT: + case WACOM_REPORT_TPCMT2: + return wacom_mt_touch(wacom); - case WACOM_REPORT_PENABLED: - return wacom_tpc_pen(wacom); + } } } diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 1ef37c727572..d037454fe7b8 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -73,7 +73,6 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, void *in, *out; unsigned long flags; int ret, err = 0; - unsigned long t; struct page *page; spin_lock_irqsave(&newchannel->lock, flags); @@ -183,11 +182,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, goto error1; } - t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ); - if (t == 0) { - err = -ETIMEDOUT; - goto error1; - } + wait_for_completion(&open_info->waitevent); spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_del(&open_info->msglistentry); @@ -375,7 +370,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, struct vmbus_channel_gpadl_header *gpadlmsg; struct vmbus_channel_gpadl_body *gpadl_body; struct vmbus_channel_msginfo *msginfo = NULL; - struct vmbus_channel_msginfo *submsginfo; + struct vmbus_channel_msginfo *submsginfo, *tmp; u32 msgcount; struct list_head *curr; u32 next_gpadl_handle; @@ -437,6 +432,13 @@ cleanup: list_del(&msginfo->msglistentry); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); + if (msgcount > 1) { + list_for_each_entry_safe(submsginfo, tmp, &msginfo->submsglist, + msglistentry) { + kfree(submsginfo); + } + } + kfree(msginfo); return ret; } diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 4fc2e8836e60..2bbc53025549 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -429,7 +429,7 @@ int vmbus_post_msg(void *buffer, size_t buflen) union hv_connection_id conn_id; int ret = 0; int retries = 0; - u32 msec = 1; + u32 usec = 1; conn_id.asu32 = 0; conn_id.u.id = VMBUS_MESSAGE_CONNECTION_ID; @@ -462,9 +462,9 @@ int vmbus_post_msg(void *buffer, size_t buflen) } retries++; - msleep(msec); - if (msec < 2048) - msec *= 2; + udelay(usec); + if (usec < 2048) + usec *= 2; } return ret; } diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 63194a9a7189..8ce1f2e22912 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -219,7 +219,7 @@ int hv_init(void) /* See if the hypercall page is already set */ rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_EXEC); + virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX); if (!virtaddr) goto cleanup; @@ -274,7 +274,7 @@ cleanup: * * This routine is called normally during driver unloading or exiting. */ -void hv_cleanup(void) +void hv_cleanup(bool crash) { union hv_x64_msr_hypercall_contents hypercall_msr; @@ -284,7 +284,8 @@ void hv_cleanup(void) if (hv_context.hypercall_page) { hypercall_msr.as_uint64 = 0; wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - vfree(hv_context.hypercall_page); + if (!crash) + vfree(hv_context.hypercall_page); hv_context.hypercall_page = NULL; } @@ -304,8 +305,10 @@ void hv_cleanup(void) hypercall_msr.as_uint64 = 0; wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64); - vfree(hv_context.tsc_page); - hv_context.tsc_page = NULL; + if (!crash) { + vfree(hv_context.tsc_page); + hv_context.tsc_page = NULL; + } } #endif } @@ -422,7 +425,7 @@ int hv_synic_alloc(void) goto err; } - for_each_online_cpu(cpu) { + for_each_present_cpu(cpu) { hv_context.event_dpc[cpu] = kmalloc(size, GFP_ATOMIC); if (hv_context.event_dpc[cpu] == NULL) { pr_err("Unable to allocate event dpc\n"); @@ -461,6 +464,8 @@ int hv_synic_alloc(void) pr_err("Unable to allocate post msg page\n"); goto err; } + + INIT_LIST_HEAD(&hv_context.percpu_list[cpu]); } return 0; @@ -485,7 +490,7 @@ void hv_synic_free(void) int cpu; kfree(hv_context.hv_numa_map); - for_each_online_cpu(cpu) + for_each_present_cpu(cpu) hv_synic_free_cpu(cpu); } @@ -555,8 +560,6 @@ void hv_synic_init(void *arg) rdmsrl(HV_X64_MSR_VP_INDEX, vp_index); hv_context.vp_index[cpu] = (u32)vp_index; - INIT_LIST_HEAD(&hv_context.percpu_list[cpu]); - /* * Register the per-cpu clockevent source. */ diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index b853b4b083bd..354da7f207b7 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -430,16 +430,27 @@ struct dm_info_msg { * currently hot added. We hot add in multiples of 128M * chunks; it is possible that we may not be able to bring * online all the pages in the region. The range - * covered_end_pfn defines the pages that can + * covered_start_pfn:covered_end_pfn defines the pages that can * be brough online. */ struct hv_hotadd_state { struct list_head list; unsigned long start_pfn; + unsigned long covered_start_pfn; unsigned long covered_end_pfn; unsigned long ha_end_pfn; unsigned long end_pfn; + /* + * A list of gaps. + */ + struct list_head gap_list; +}; + +struct hv_hotadd_gap { + struct list_head list; + unsigned long start_pfn; + unsigned long end_pfn; }; struct balloon_state { @@ -595,18 +606,46 @@ static struct notifier_block hv_memory_nb = { .priority = 0 }; +/* Check if the particular page is backed and can be onlined and online it. */ +static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg) +{ + unsigned long cur_start_pgp; + unsigned long cur_end_pgp; + struct hv_hotadd_gap *gap; + + cur_start_pgp = (unsigned long)pfn_to_page(has->covered_start_pfn); + cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn); + + /* The page is not backed. */ + if (((unsigned long)pg < cur_start_pgp) || + ((unsigned long)pg >= cur_end_pgp)) + return; + + /* Check for gaps. */ + list_for_each_entry(gap, &has->gap_list, list) { + cur_start_pgp = (unsigned long) + pfn_to_page(gap->start_pfn); + cur_end_pgp = (unsigned long) + pfn_to_page(gap->end_pfn); + if (((unsigned long)pg >= cur_start_pgp) && + ((unsigned long)pg < cur_end_pgp)) { + return; + } + } -static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size) + /* This frame is currently backed; online the page. */ + __online_page_set_limits(pg); + __online_page_increment_counters(pg); + __online_page_free(pg); +} + +static void hv_bring_pgs_online(struct hv_hotadd_state *has, + unsigned long start_pfn, unsigned long size) { int i; - for (i = 0; i < size; i++) { - struct page *pg; - pg = pfn_to_page(start_pfn + i); - __online_page_set_limits(pg); - __online_page_increment_counters(pg); - __online_page_free(pg); - } + for (i = 0; i < size; i++) + hv_page_online_one(has, pfn_to_page(start_pfn + i)); } static void hv_mem_hot_add(unsigned long start, unsigned long size, @@ -682,26 +721,25 @@ static void hv_online_page(struct page *pg) list_for_each(cur, &dm_device.ha_region_list) { has = list_entry(cur, struct hv_hotadd_state, list); - cur_start_pgp = (unsigned long)pfn_to_page(has->start_pfn); - cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn); + cur_start_pgp = (unsigned long) + pfn_to_page(has->start_pfn); + cur_end_pgp = (unsigned long)pfn_to_page(has->end_pfn); - if (((unsigned long)pg >= cur_start_pgp) && - ((unsigned long)pg < cur_end_pgp)) { - /* - * This frame is currently backed; online the - * page. - */ - __online_page_set_limits(pg); - __online_page_increment_counters(pg); - __online_page_free(pg); - } + /* The page belongs to a different HAS. */ + if (((unsigned long)pg < cur_start_pgp) || + ((unsigned long)pg >= cur_end_pgp)) + continue; + + hv_page_online_one(has, pg); + break; } } -static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) +static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) { struct list_head *cur; struct hv_hotadd_state *has; + struct hv_hotadd_gap *gap; unsigned long residual, new_inc; if (list_empty(&dm_device.ha_region_list)) @@ -714,8 +752,26 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) * If the pfn range we are dealing with is not in the current * "hot add block", move on. */ - if ((start_pfn >= has->end_pfn)) + if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn) continue; + + /* + * If the current start pfn is not where the covered_end + * is, create a gap and update covered_end_pfn. + */ + if (has->covered_end_pfn != start_pfn) { + gap = kzalloc(sizeof(struct hv_hotadd_gap), GFP_ATOMIC); + if (!gap) + return -ENOMEM; + + INIT_LIST_HEAD(&gap->list); + gap->start_pfn = has->covered_end_pfn; + gap->end_pfn = start_pfn; + list_add_tail(&gap->list, &has->gap_list); + + has->covered_end_pfn = start_pfn; + } + /* * If the current hot add-request extends beyond * our current limit; extend it. @@ -732,19 +788,10 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) has->end_pfn += new_inc; } - /* - * If the current start pfn is not where the covered_end - * is, update it. - */ - - if (has->covered_end_pfn != start_pfn) - has->covered_end_pfn = start_pfn; - - return true; - + return 1; } - return false; + return 0; } static unsigned long handle_pg_range(unsigned long pg_start, @@ -768,7 +815,7 @@ static unsigned long handle_pg_range(unsigned long pg_start, * If the pfn range we are dealing with is not in the current * "hot add block", move on. */ - if ((start_pfn >= has->end_pfn)) + if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn) continue; old_covered_state = has->covered_end_pfn; @@ -783,6 +830,8 @@ static unsigned long handle_pg_range(unsigned long pg_start, if (pgs_ol > pfn_cnt) pgs_ol = pfn_cnt; + has->covered_end_pfn += pgs_ol; + pfn_cnt -= pgs_ol; /* * Check if the corresponding memory block is already * online by checking its last previously backed page. @@ -791,10 +840,8 @@ static unsigned long handle_pg_range(unsigned long pg_start, */ if (start_pfn > has->start_pfn && !PageReserved(pfn_to_page(start_pfn - 1))) - hv_bring_pgs_online(start_pfn, pgs_ol); + hv_bring_pgs_online(has, start_pfn, pgs_ol); - has->covered_end_pfn += pgs_ol; - pfn_cnt -= pgs_ol; } if ((has->ha_end_pfn < has->end_pfn) && (pfn_cnt > 0)) { @@ -832,13 +879,19 @@ static unsigned long process_hot_add(unsigned long pg_start, unsigned long rg_size) { struct hv_hotadd_state *ha_region = NULL; + int covered; if (pfn_cnt == 0) return 0; - if (!dm_device.host_specified_ha_region) - if (pfn_covered(pg_start, pfn_cnt)) + if (!dm_device.host_specified_ha_region) { + covered = pfn_covered(pg_start, pfn_cnt); + if (covered < 0) + return 0; + + if (covered) goto do_pg_range; + } /* * If the host has specified a hot-add range; deal with it first. @@ -850,10 +903,12 @@ static unsigned long process_hot_add(unsigned long pg_start, return 0; INIT_LIST_HEAD(&ha_region->list); + INIT_LIST_HEAD(&ha_region->gap_list); list_add_tail(&ha_region->list, &dm_device.ha_region_list); ha_region->start_pfn = rg_start; ha_region->ha_end_pfn = rg_start; + ha_region->covered_start_pfn = pg_start; ha_region->covered_end_pfn = pg_start; ha_region->end_pfn = rg_start + rg_size; } @@ -1581,6 +1636,7 @@ static int balloon_remove(struct hv_device *dev) struct hv_dynmem_device *dm = hv_get_drvdata(dev); struct list_head *cur, *tmp; struct hv_hotadd_state *has; + struct hv_hotadd_gap *gap, *tmp_gap; if (dm->num_pages_ballooned != 0) pr_warn("Ballooned pages: %d\n", dm->num_pages_ballooned); @@ -1597,6 +1653,10 @@ static int balloon_remove(struct hv_device *dev) #endif list_for_each_safe(cur, tmp, &dm->ha_region_list) { has = list_entry(cur, struct hv_hotadd_state, list); + list_for_each_entry_safe(gap, tmp_gap, &has->gap_list, list) { + list_del(&gap->list); + kfree(gap); + } list_del(&has->list); kfree(has); } diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index c37a71e13de0..1fb02dcbc500 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -61,6 +61,7 @@ static DECLARE_WORK(fcopy_send_work, fcopy_send_data); static const char fcopy_devname[] = "vmbus/hv_fcopy"; static u8 *recv_buffer; static struct hvutil_transport *hvt; +static struct completion release_event; /* * This state maintains the version number registered by the daemon. */ @@ -312,12 +313,14 @@ static void fcopy_on_reset(void) if (cancel_delayed_work_sync(&fcopy_timeout_work)) fcopy_respond_to_host(HV_E_FAIL); + complete(&release_event); } int hv_fcopy_init(struct hv_util_service *srv) { recv_buffer = srv->recv_buffer; + init_completion(&release_event); /* * When this driver loads, the user level daemon that * processes the host requests may not yet be running. @@ -339,4 +342,5 @@ void hv_fcopy_deinit(void) fcopy_transaction.state = HVUTIL_DEVICE_DYING; cancel_delayed_work_sync(&fcopy_timeout_work); hvutil_transport_destroy(hvt); + wait_for_completion(&release_event); } diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index 2a3420c4ca59..ce4d3a935491 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -86,6 +86,7 @@ static DECLARE_WORK(kvp_sendkey_work, kvp_send_key); static const char kvp_devname[] = "vmbus/hv_kvp"; static u8 *recv_buffer; static struct hvutil_transport *hvt; +static struct completion release_event; /* * Register the kernel component with the user-level daemon. * As part of this registration, pass the LIC version number. @@ -682,6 +683,7 @@ static void kvp_on_reset(void) if (cancel_delayed_work_sync(&kvp_timeout_work)) kvp_respond_to_host(NULL, HV_E_FAIL); kvp_transaction.state = HVUTIL_DEVICE_INIT; + complete(&release_event); } int @@ -689,6 +691,7 @@ hv_kvp_init(struct hv_util_service *srv) { recv_buffer = srv->recv_buffer; + init_completion(&release_event); /* * When this driver loads, the user level daemon that * processes the host requests may not yet be running. @@ -711,4 +714,5 @@ void hv_kvp_deinit(void) cancel_delayed_work_sync(&kvp_timeout_work); cancel_work_sync(&kvp_sendkey_work); hvutil_transport_destroy(hvt); + wait_for_completion(&release_event); } diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 81882d4848bd..faad79ae318a 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -66,6 +66,7 @@ static int dm_reg_value; static const char vss_devname[] = "vmbus/hv_vss"; static __u8 *recv_buffer; static struct hvutil_transport *hvt; +static struct completion release_event; static void vss_send_op(struct work_struct *dummy); static void vss_timeout_func(struct work_struct *dummy); @@ -326,11 +327,13 @@ static void vss_on_reset(void) if (cancel_delayed_work_sync(&vss_timeout_work)) vss_respond_to_host(HV_E_FAIL); vss_transaction.state = HVUTIL_DEVICE_INIT; + complete(&release_event); } int hv_vss_init(struct hv_util_service *srv) { + init_completion(&release_event); if (vmbus_proto_version < VERSION_WIN8_1) { pr_warn("Integration service 'Backup (volume snapshot)'" " not supported on this host version.\n"); @@ -360,4 +363,5 @@ void hv_vss_deinit(void) cancel_delayed_work_sync(&vss_timeout_work); cancel_work_sync(&vss_send_op_work); hvutil_transport_destroy(hvt); + wait_for_completion(&release_event); } diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 12156db2e88e..75e383e6d03d 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -581,7 +581,7 @@ struct hv_ring_buffer_debug_info { extern int hv_init(void); -extern void hv_cleanup(void); +extern void hv_cleanup(bool crash); extern int hv_post_message(union hv_connection_id connection_id, enum hv_message_type message_type, diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 509ed9731630..802dcb409030 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -889,7 +889,7 @@ err_alloc: bus_unregister(&hv_bus); err_cleanup: - hv_cleanup(); + hv_cleanup(false); return ret; } @@ -1254,7 +1254,7 @@ static void hv_kexec_handler(void) vmbus_initiate_unload(); for_each_online_cpu(cpu) smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1); - hv_cleanup(); + hv_cleanup(false); }; static void hv_crash_handler(struct pt_regs *regs) @@ -1266,7 +1266,7 @@ static void hv_crash_handler(struct pt_regs *regs) * for kdump. */ hv_synic_cleanup(NULL); - hv_cleanup(); + hv_cleanup(true); }; static int __init hv_acpi_init(void) @@ -1330,7 +1330,7 @@ static void __exit vmbus_exit(void) &hyperv_panic_block); } bus_unregister(&hv_bus); - hv_cleanup(); + hv_cleanup(false); for_each_online_cpu(cpu) { tasklet_kill(hv_context.event_dpc[cpu]); smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1); diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index 9e02ac963cd0..3978cbb6b038 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -388,9 +388,6 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) err_misc_register: coresight_unregister(drvdata->csdev); err_devm_kzalloc: - if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) - dma_free_coherent(dev, drvdata->size, - drvdata->vaddr, drvdata->paddr); return ret; } diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 630bce68bf38..b61db9db3ca5 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -54,7 +54,7 @@ #define SMBSLVDAT (0xC + piix4_smba) /* count for request_region */ -#define SMBIOSIZE 8 +#define SMBIOSIZE 9 /* PCI Address Constants */ #define SMBBA 0x090 diff --git a/drivers/i2c/busses/i2c-tiny-usb.c b/drivers/i2c/busses/i2c-tiny-usb.c index 0ed77eeff31e..a2e3dd715380 100644 --- a/drivers/i2c/busses/i2c-tiny-usb.c +++ b/drivers/i2c/busses/i2c-tiny-usb.c @@ -178,22 +178,39 @@ static int usb_read(struct i2c_adapter *adapter, int cmd, int value, int index, void *data, int len) { struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data; + void *dmadata = kmalloc(len, GFP_KERNEL); + int ret; + + if (!dmadata) + return -ENOMEM; /* do control transfer */ - return usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0), + ret = usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0), cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE | - USB_DIR_IN, value, index, data, len, 2000); + USB_DIR_IN, value, index, dmadata, len, 2000); + + memcpy(data, dmadata, len); + kfree(dmadata); + return ret; } static int usb_write(struct i2c_adapter *adapter, int cmd, int value, int index, void *data, int len) { struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data; + void *dmadata = kmemdup(data, len, GFP_KERNEL); + int ret; + + if (!dmadata) + return -ENOMEM; /* do control transfer */ - return usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0), + ret = usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0), cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - value, index, data, len, 2000); + value, index, dmadata, len, 2000); + + kfree(dmadata); + return ret; } static void i2c_tiny_usb_free(struct i2c_tiny_usb *dev) diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c index fa24d5196615..c7122919a8c0 100644 --- a/drivers/iio/accel/bmc150-accel-core.c +++ b/drivers/iio/accel/bmc150-accel-core.c @@ -194,7 +194,6 @@ struct bmc150_accel_data { struct device *dev; int irq; struct bmc150_accel_interrupt interrupts[BMC150_ACCEL_INTERRUPTS]; - atomic_t active_intr; struct bmc150_accel_trigger triggers[BMC150_ACCEL_TRIGGERS]; struct mutex mutex; u8 fifo_mode, watermark; @@ -489,11 +488,6 @@ static int bmc150_accel_set_interrupt(struct bmc150_accel_data *data, int i, goto out_fix_power_state; } - if (state) - atomic_inc(&data->active_intr); - else - atomic_dec(&data->active_intr); - return 0; out_fix_power_state: @@ -1704,8 +1698,7 @@ static int bmc150_accel_resume(struct device *dev) struct bmc150_accel_data *data = iio_priv(indio_dev); mutex_lock(&data->mutex); - if (atomic_read(&data->active_intr)) - bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0); + bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0); bmc150_accel_fifo_set_mode(data); mutex_unlock(&data->mutex); diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 0470fc843d4e..9b6854607d73 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -151,7 +151,9 @@ static irqreturn_t tiadc_irq_h(int irq, void *private) { struct iio_dev *indio_dev = private; struct tiadc_device *adc_dev = iio_priv(indio_dev); - unsigned int status, config; + unsigned int status, config, adc_fsm; + unsigned short count = 0; + status = tiadc_readl(adc_dev, REG_IRQSTATUS); /* @@ -165,6 +167,15 @@ static irqreturn_t tiadc_irq_h(int irq, void *private) tiadc_writel(adc_dev, REG_CTRL, config); tiadc_writel(adc_dev, REG_IRQSTATUS, IRQENB_FIFO1OVRRUN | IRQENB_FIFO1UNDRFLW | IRQENB_FIFO1THRES); + + /* wait for idle state. + * ADC needs to finish the current conversion + * before disabling the module + */ + do { + adc_fsm = tiadc_readl(adc_dev, REG_ADCFSM); + } while (adc_fsm != 0x10 && count++ < 100); + tiadc_writel(adc_dev, REG_CTRL, (config | CNTRLREG_TSCSSENB)); return IRQ_HANDLED; } else if (status & IRQENB_FIFO1THRES) { diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c index b10f629cc44b..1dbc2143cdfc 100644 --- a/drivers/iio/adc/vf610_adc.c +++ b/drivers/iio/adc/vf610_adc.c @@ -77,7 +77,7 @@ #define VF610_ADC_ADSTS_MASK 0x300 #define VF610_ADC_ADLPC_EN 0x80 #define VF610_ADC_ADHSC_EN 0x400 -#define VF610_ADC_REFSEL_VALT 0x100 +#define VF610_ADC_REFSEL_VALT 0x800 #define VF610_ADC_REFSEL_VBG 0x1000 #define VF610_ADC_ADTRG_HARD 0x2000 #define VF610_ADC_AVGS_8 0x4000 diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c index 595511022795..0a86ef43e781 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c @@ -51,8 +51,6 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state) st->report_state.report_id, st->report_state.index, HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM); - - poll_value = hid_sensor_read_poll_value(st); } else { int val; @@ -89,7 +87,9 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state) sensor_hub_get_feature(st->hsdev, st->power_state.report_id, st->power_state.index, sizeof(state_val), &state_val); - if (state && poll_value) + if (state) + poll_value = hid_sensor_read_poll_value(st); + if (poll_value > 0) msleep_interruptible(poll_value * 2); return 0; diff --git a/drivers/iio/dac/ad7303.c b/drivers/iio/dac/ad7303.c index e690dd11e99f..4b0f942b8914 100644 --- a/drivers/iio/dac/ad7303.c +++ b/drivers/iio/dac/ad7303.c @@ -184,9 +184,9 @@ static const struct iio_chan_spec_ext_info ad7303_ext_info[] = { .address = (chan), \ .scan_type = { \ .sign = 'u', \ - .realbits = '8', \ - .storagebits = '8', \ - .shift = '0', \ + .realbits = 8, \ + .storagebits = 8, \ + .shift = 0, \ }, \ .ext_info = ad7303_ext_info, \ } diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index acb3b303d800..90841abd3ce4 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -28,6 +28,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> #include <linux/regmap.h> +#include <linux/delay.h> #include "bmg160.h" #define BMG160_IRQ_NAME "bmg160_event" @@ -53,6 +54,9 @@ #define BMG160_NO_FILTER 0 #define BMG160_DEF_BW 100 +#define BMG160_GYRO_REG_RESET 0x14 +#define BMG160_GYRO_RESET_VAL 0xb6 + #define BMG160_REG_INT_MAP_0 0x17 #define BMG160_INT_MAP_0_BIT_ANY BIT(1) @@ -186,6 +190,14 @@ static int bmg160_chip_init(struct bmg160_data *data) int ret; unsigned int val; + /* + * Reset chip to get it in a known good state. A delay of 30ms after + * reset is required according to the datasheet. + */ + regmap_write(data->regmap, BMG160_GYRO_REG_RESET, + BMG160_GYRO_RESET_VAL); + usleep_range(30000, 30700); + ret = regmap_read(data->regmap, BMG160_REG_CHIP_ID, &val); if (ret < 0) { dev_err(data->dev, "Error reading reg_chip_id\n"); diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 6bf89d8f3741..b9d1e5c58ec5 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -74,9 +74,9 @@ static const int int_time_mapping[] = {100000, 50000, 200000, 400000}; static const struct reg_field reg_field_it = REG_FIELD(LTR501_ALS_MEAS_RATE, 3, 4); static const struct reg_field reg_field_als_intr = - REG_FIELD(LTR501_INTR, 0, 0); -static const struct reg_field reg_field_ps_intr = REG_FIELD(LTR501_INTR, 1, 1); +static const struct reg_field reg_field_ps_intr = + REG_FIELD(LTR501_INTR, 0, 0); static const struct reg_field reg_field_als_rate = REG_FIELD(LTR501_ALS_MEAS_RATE, 0, 2); static const struct reg_field reg_field_ps_rate = diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c index 12731d6b89ec..ec1b2e798cc1 100644 --- a/drivers/iio/light/tsl2563.c +++ b/drivers/iio/light/tsl2563.c @@ -626,7 +626,7 @@ static irqreturn_t tsl2563_event_handler(int irq, void *private) struct tsl2563_chip *chip = iio_priv(dev_info); iio_push_event(dev_info, - IIO_UNMOD_EVENT_CODE(IIO_LIGHT, + IIO_UNMOD_EVENT_CODE(IIO_INTENSITY, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), diff --git a/drivers/iio/pressure/mpl115.c b/drivers/iio/pressure/mpl115.c index a0d7deeac62f..3f90985d545e 100644 --- a/drivers/iio/pressure/mpl115.c +++ b/drivers/iio/pressure/mpl115.c @@ -136,6 +136,7 @@ static const struct iio_chan_spec mpl115_channels[] = { { .type = IIO_TEMP, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), + .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) | BIT(IIO_CHAN_INFO_SCALE), }, }; diff --git a/drivers/iio/pressure/mpl3115.c b/drivers/iio/pressure/mpl3115.c index 01b2e0b18878..0f5b8767ec2e 100644 --- a/drivers/iio/pressure/mpl3115.c +++ b/drivers/iio/pressure/mpl3115.c @@ -182,7 +182,7 @@ static const struct iio_chan_spec mpl3115_channels[] = { { .type = IIO_PRESSURE, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - BIT(IIO_CHAN_INFO_SCALE), + .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .scan_index = 0, .scan_type = { .sign = 'u', @@ -195,7 +195,7 @@ static const struct iio_chan_spec mpl3115_channels[] = { { .type = IIO_TEMP, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - BIT(IIO_CHAN_INFO_SCALE), + .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .scan_index = 1, .scan_type = { .sign = 's', diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c index a0aedda7dfd7..420478924a0c 100644 --- a/drivers/iio/proximity/as3935.c +++ b/drivers/iio/proximity/as3935.c @@ -40,9 +40,9 @@ #define AS3935_AFE_PWR_BIT BIT(0) #define AS3935_INT 0x03 -#define AS3935_INT_MASK 0x07 +#define AS3935_INT_MASK 0x0f #define AS3935_EVENT_INT BIT(3) -#define AS3935_NOISE_INT BIT(1) +#define AS3935_NOISE_INT BIT(0) #define AS3935_DATA 0x07 #define AS3935_DATA_MASK 0x3F @@ -50,7 +50,6 @@ #define AS3935_TUNE_CAP 0x08 #define AS3935_CALIBRATE 0x3D -#define AS3935_WRITE_DATA BIT(15) #define AS3935_READ_DATA BIT(14) #define AS3935_ADDRESS(x) ((x) << 8) @@ -105,7 +104,7 @@ static int as3935_write(struct as3935_state *st, { u8 *buf = st->buf; - buf[0] = (AS3935_WRITE_DATA | AS3935_ADDRESS(reg)) >> 8; + buf[0] = AS3935_ADDRESS(reg) >> 8; buf[1] = val; return spi_write(st->spi, buf, 2); @@ -264,8 +263,6 @@ static irqreturn_t as3935_interrupt_handler(int irq, void *private) static void calibrate_as3935(struct as3935_state *st) { - mutex_lock(&st->lock); - /* mask disturber interrupt bit */ as3935_write(st, AS3935_INT, BIT(5)); @@ -275,8 +272,6 @@ static void calibrate_as3935(struct as3935_state *st) mdelay(2); as3935_write(st, AS3935_TUNE_CAP, (st->tune_cap / TUNE_CAP_DIV)); - - mutex_unlock(&st->lock); } #ifdef CONFIG_PM_SLEEP @@ -313,6 +308,8 @@ static int as3935_resume(struct device *dev) val &= ~AS3935_AFE_PWR_BIT; ret = as3935_write(st, AS3935_AFE_GAIN, val); + calibrate_as3935(st); + err_resume: mutex_unlock(&st->lock); diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 34b1adad07aa..6a8024d9d742 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -277,8 +277,8 @@ static int addr6_resolve(struct sockaddr_in6 *src_in, fl6.saddr = src_in->sin6_addr; fl6.flowi6_oif = addr->bound_dev_if; - dst = ip6_route_output(addr->net, NULL, &fl6); - if ((ret = dst->error)) + ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6); + if (ret < 0) goto put; if (ipv6_addr_any(&fl6.saddr)) { diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 17a15c56028c..43d5166db4c6 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -857,6 +857,8 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, } else ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr, qp_attr_mask); + qp_attr->port_num = id_priv->id.port_num; + *qp_attr_mask |= IB_QP_PORT; } else ret = -ENOSYS; @@ -2578,7 +2580,8 @@ static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, if (!src_addr || !src_addr->sa_family) { src_addr = (struct sockaddr *) &id->route.addr.src_addr; src_addr->sa_family = dst_addr->sa_family; - if (dst_addr->sa_family == AF_INET6) { + if (IS_ENABLED(CONFIG_IPV6) && + dst_addr->sa_family == AF_INET6) { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *) src_addr; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *) dst_addr; src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; @@ -3348,6 +3351,9 @@ static int cma_accept_iw(struct rdma_id_private *id_priv, struct iw_cm_conn_param iw_param; int ret; + if (!conn_param) + return -EINVAL; + ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) return ret; diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index b1f37d4095fa..e76d52a203a7 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -863,7 +863,7 @@ err_put: free_port_list_attributes(device); err_unregister: - device_unregister(class_dev); + device_del(class_dev); err: return ret; diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 04f3c0db9126..0ae337bec4f2 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -134,6 +134,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND)); if (access & IB_ACCESS_ON_DEMAND) { + put_pid(umem->pid); ret = ib_umem_odp_get(context, umem); if (ret) { kfree(umem); @@ -149,6 +150,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, page_list = (struct page **) __get_free_page(GFP_KERNEL); if (!page_list) { + put_pid(umem->pid); kfree(umem); return ERR_PTR(-ENOMEM); } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 1c02deab068f..b7a73f1a8beb 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2287,6 +2287,11 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; + if ((cmd.attr_mask & IB_QP_PORT) && + (cmd.port_num < rdma_start_port(ib_dev) || + cmd.port_num > rdma_end_port(ib_dev))) + return -EINVAL; + INIT_UDATA(&udata, buf + sizeof cmd, NULL, in_len - sizeof cmd, out_len); @@ -2827,6 +2832,10 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; + if (cmd.attr.port_num < rdma_start_port(ib_dev) || + cmd.attr.port_num > rdma_end_port(ib_dev)) + return -EINVAL; + uobj = kmalloc(sizeof *uobj, GFP_KERNEL); if (!uobj) return -ENOMEM; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 77ddf2fa8625..8763fb832b01 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2491,6 +2491,7 @@ err_counter: mlx4_ib_delete_counters_table(ibdev, &ibdev->counters_table[i]); err_map: + mlx4_ib_free_eqs(dev, ibdev); iounmap(ibdev->uar_map); err_uar: diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c index 36ec8aa048aa..0b5bb0cee6f9 100644 --- a/drivers/infiniband/hw/mlx4/mcg.c +++ b/drivers/infiniband/hw/mlx4/mcg.c @@ -1105,7 +1105,8 @@ static void _mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy while ((p = rb_first(&ctx->mcg_table)) != NULL) { group = rb_entry(p, struct mcast_group, node); if (atomic_read(&group->refcount)) - mcg_warn_group(group, "group refcount %d!!! (pointer %p)\n", atomic_read(&group->refcount), group); + mcg_debug_group(group, "group refcount %d!!! (pointer %p)\n", + atomic_read(&group->refcount), group); force_clean_group(group); } diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 3eff35c2d453..2684605fe67f 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -41,13 +41,13 @@ #include "qib.h" -#define BITS_PER_PAGE (PAGE_SIZE*BITS_PER_BYTE) -#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) +#define RVT_BITS_PER_PAGE (PAGE_SIZE*BITS_PER_BYTE) +#define RVT_BITS_PER_PAGE_MASK (RVT_BITS_PER_PAGE-1) static inline unsigned mk_qpn(struct qib_qpn_table *qpt, struct qpn_map *map, unsigned off) { - return (map - qpt->map) * BITS_PER_PAGE + off; + return (map - qpt->map) * RVT_BITS_PER_PAGE + off; } static inline unsigned find_next_offset(struct qib_qpn_table *qpt, @@ -59,7 +59,7 @@ static inline unsigned find_next_offset(struct qib_qpn_table *qpt, if (((off & qpt->mask) >> 1) >= n) off = (off | qpt->mask) + 2; } else - off = find_next_zero_bit(map->page, BITS_PER_PAGE, off); + off = find_next_zero_bit(map->page, RVT_BITS_PER_PAGE, off); return off; } @@ -147,8 +147,8 @@ static int alloc_qpn(struct qib_devdata *dd, struct qib_qpn_table *qpt, qpn = 2; if (qpt->mask && ((qpn & qpt->mask) >> 1) >= dd->n_krcv_queues) qpn = (qpn | qpt->mask) + 2; - offset = qpn & BITS_PER_PAGE_MASK; - map = &qpt->map[qpn / BITS_PER_PAGE]; + offset = qpn & RVT_BITS_PER_PAGE_MASK; + map = &qpt->map[qpn / RVT_BITS_PER_PAGE]; max_scan = qpt->nmaps - !offset; for (i = 0;;) { if (unlikely(!map->page)) { @@ -173,7 +173,7 @@ static int alloc_qpn(struct qib_devdata *dd, struct qib_qpn_table *qpt, * We just need to be sure we don't loop * forever. */ - } while (offset < BITS_PER_PAGE && qpn < QPN_MAX); + } while (offset < RVT_BITS_PER_PAGE && qpn < QPN_MAX); /* * In order to keep the number of pages allocated to a * minimum, we scan the all existing pages before increasing @@ -204,9 +204,9 @@ static void free_qpn(struct qib_qpn_table *qpt, u32 qpn) { struct qpn_map *map; - map = qpt->map + qpn / BITS_PER_PAGE; + map = qpt->map + qpn / RVT_BITS_PER_PAGE; if (map->page) - clear_bit(qpn & BITS_PER_PAGE_MASK, map->page); + clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page); } static inline unsigned qpn_hash(struct qib_ibdev *dev, u32 qpn) diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c index e6b7556d5221..cbc4216091c9 100644 --- a/drivers/infiniband/hw/qib/qib_rc.c +++ b/drivers/infiniband/hw/qib/qib_rc.c @@ -2088,8 +2088,10 @@ send_last: ret = qib_get_rwqe(qp, 1); if (ret < 0) goto nack_op_err; - if (!ret) + if (!ret) { + qib_put_ss(&qp->r_sge); goto rnr_nak; + } wc.ex.imm_data = ohdr->u.rc.imm_data; hdrsize += 4; wc.wc_flags = IB_WC_WITH_IMM; diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 69a151ae8261..07cfcc326863 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -63,6 +63,8 @@ enum ipoib_flush_level { enum { IPOIB_ENCAP_LEN = 4, + IPOIB_PSEUDO_LEN = 20, + IPOIB_HARD_LEN = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN, IPOIB_UD_HEAD_SIZE = IB_GRH_BYTES + IPOIB_ENCAP_LEN, IPOIB_UD_RX_SG = 2, /* max buffer needed for 4K mtu */ @@ -131,15 +133,21 @@ struct ipoib_header { u16 reserved; }; -struct ipoib_cb { - struct qdisc_skb_cb qdisc_cb; - u8 hwaddr[INFINIBAND_ALEN]; +struct ipoib_pseudo_header { + u8 hwaddr[INFINIBAND_ALEN]; }; -static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb) +static inline void skb_add_pseudo_hdr(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb)); - return (struct ipoib_cb *)skb->cb; + char *data = skb_push(skb, IPOIB_PSEUDO_LEN); + + /* + * only the ipoib header is present now, make room for a dummy + * pseudo header and set skb field accordingly + */ + memset(data, 0, IPOIB_PSEUDO_LEN); + skb_reset_mac_header(skb); + skb_pull(skb, IPOIB_HARD_LEN); } /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */ diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index de5e2b01ab05..2018d24344de 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level, #define IPOIB_CM_RX_DELAY (3 * 256 * HZ) #define IPOIB_CM_RX_UPDATE_MASK (0x3) +#define IPOIB_CM_RX_RESERVE (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN) + static struct ib_qp_attr ipoib_cm_err_attr = { .qp_state = IB_QPS_ERR }; @@ -147,15 +149,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev, struct sk_buff *skb; int i; - skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12); + skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16)); if (unlikely(!skb)) return NULL; /* - * IPoIB adds a 4 byte header. So we need 12 more bytes to align the + * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the * IP header to a multiple of 16. */ - skb_reserve(skb, 12); + skb_reserve(skb, IPOIB_CM_RX_RESERVE); mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE, DMA_FROM_DEVICE); @@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) if (wc->byte_len < IPOIB_CM_COPYBREAK) { int dlen = wc->byte_len; - small_skb = dev_alloc_skb(dlen + 12); + small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE); if (small_skb) { - skb_reserve(small_skb, 12); + skb_reserve(small_skb, IPOIB_CM_RX_RESERVE); ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0], dlen, DMA_FROM_DEVICE); skb_copy_from_linear_data(skb, small_skb->data, dlen); @@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) copied: skb->protocol = ((struct ipoib_header *) skb->data)->proto; - skb_reset_mac_header(skb); - skb_pull(skb, IPOIB_ENCAP_LEN); + skb_add_pseudo_hdr(skb); ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; @@ -1487,12 +1488,14 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr, ret = ipoib_set_mode(dev, buf); - rtnl_unlock(); - - if (!ret) - return count; + /* The assumption is that the function ipoib_set_mode returned + * with the rtnl held by it, if not the value -EBUSY returned, + * then no need to rtnl_unlock + */ + if (ret != -EBUSY) + rtnl_unlock(); - return ret; + return (!ret || ret == -EBUSY) ? count : ret; } static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO, show_mode, set_mode); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_fs.c b/drivers/infiniband/ulp/ipoib/ipoib_fs.c index 6bd5740e2691..09396bd7b02d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_fs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_fs.c @@ -281,8 +281,11 @@ void ipoib_delete_debug_files(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); + WARN_ONCE(!priv->mcg_dentry, "null mcg debug file\n"); + WARN_ONCE(!priv->path_dentry, "null path debug file\n"); debugfs_remove(priv->mcg_dentry); debugfs_remove(priv->path_dentry); + priv->mcg_dentry = priv->path_dentry = NULL; } int ipoib_register_debugfs(void) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 85de078fb0ce..8f8c3af9f4e8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -130,16 +130,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); - skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN); + skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN); if (unlikely(!skb)) return NULL; /* - * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte - * header. So we need 4 more bytes to get to 48 and align the - * IP header to a multiple of 16. + * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is + * 64 bytes aligned */ - skb_reserve(skb, 4); + skb_reserve(skb, sizeof(struct ipoib_pseudo_header)); mapping = priv->rx_ring[id].mapping; mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size, @@ -242,8 +241,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) skb_pull(skb, IB_GRH_BYTES); skb->protocol = ((struct ipoib_header *) skb->data)->proto; - skb_reset_mac_header(skb); - skb_pull(skb, IPOIB_ENCAP_LEN); + skb_add_pseudo_hdr(skb); ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 5f7681b975d0..6699ecd855f0 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -106,6 +106,33 @@ static struct ib_client ipoib_client = { .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG +static int ipoib_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct netdev_notifier_info *ni = ptr; + struct net_device *dev = ni->dev; + + if (dev->netdev_ops->ndo_open != ipoib_open) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_REGISTER: + ipoib_create_debug_files(dev); + break; + case NETDEV_CHANGENAME: + ipoib_delete_debug_files(dev); + ipoib_create_debug_files(dev); + break; + case NETDEV_UNREGISTER: + ipoib_delete_debug_files(dev); + break; + } + + return NOTIFY_DONE; +} +#endif + int ipoib_open(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -464,8 +491,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf) priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); - rtnl_lock(); - return 0; + return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { @@ -474,8 +500,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf) dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); rtnl_unlock(); ipoib_flush_paths(dev); - rtnl_lock(); - return 0; + return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; @@ -628,6 +653,14 @@ void ipoib_mark_paths_invalid(struct net_device *dev) spin_unlock_irq(&priv->lock); } +static void push_pseudo_header(struct sk_buff *skb, const char *daddr) +{ + struct ipoib_pseudo_header *phdr; + + phdr = (struct ipoib_pseudo_header *)skb_push(skb, sizeof(*phdr)); + memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); +} + void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -850,9 +883,11 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, ipoib_neigh_free(neigh); goto err_drop; } - if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) + if (skb_queue_len(&neigh->queue) < + IPOIB_MAX_PATH_REC_QUEUE) { + push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); - else { + } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; @@ -868,10 +903,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, if (!path->query && path_rec_start(dev, path)) goto err_path; - if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) + if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); - else + } else { goto err_drop; + } } spin_unlock_irqrestore(&priv->lock, flags); @@ -889,7 +926,7 @@ err_drop: } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, - struct ipoib_cb *cb) + struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_path *path; @@ -897,16 +934,17 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, spin_lock_irqsave(&priv->lock, flags); - path = __path_find(dev, cb->hwaddr + 4); + path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->valid) { int new_path = 0; if (!path) { - path = path_rec_create(dev, cb->hwaddr + 4); + path = path_rec_create(dev, phdr->hwaddr + 4); new_path = 1; } if (path) { if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); } else { ++dev->stats.tx_dropped; @@ -934,10 +972,11 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, be16_to_cpu(path->pathrec.dlid)); spin_unlock_irqrestore(&priv->lock, flags); - ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr)); + ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr)); return; } else if ((path->query || !path_rec_start(dev, path)) && skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); } else { ++dev->stats.tx_dropped; @@ -951,13 +990,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_neigh *neigh; - struct ipoib_cb *cb = ipoib_skb_cb(skb); + struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; + phdr = (struct ipoib_pseudo_header *) skb->data; + skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; - if (unlikely(cb->hwaddr[4] == 0xff)) { + if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && @@ -970,13 +1011,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ - cb->hwaddr[8] = (priv->pkey >> 8) & 0xff; - cb->hwaddr[9] = priv->pkey & 0xff; + phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; + phdr->hwaddr[9] = priv->pkey & 0xff; - neigh = ipoib_neigh_get(dev, cb->hwaddr); + neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; - ipoib_mcast_send(dev, cb->hwaddr, skb); + ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } @@ -985,16 +1026,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): - neigh = ipoib_neigh_get(dev, cb->hwaddr); + neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { - neigh_add_path(skb, cb->hwaddr, dev); + neigh_add_path(skb, phdr->hwaddr, dev); return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ - unicast_arp_send(skb, dev, cb); + unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ @@ -1011,11 +1052,12 @@ send_using_neigh: goto unref; } } else if (neigh->ah) { - ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr)); + ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); @@ -1048,7 +1090,6 @@ static int ipoib_hard_header(struct sk_buff *skb, const void *daddr, const void *saddr, unsigned len) { struct ipoib_header *header; - struct ipoib_cb *cb = ipoib_skb_cb(skb); header = (struct ipoib_header *) skb_push(skb, sizeof *header); @@ -1057,12 +1098,12 @@ static int ipoib_hard_header(struct sk_buff *skb, /* * we don't rely on dst_entry structure, always stuff the - * destination address into skb->cb so we can figure out where + * destination address into skb hard header so we can figure out where * to send the packet later. */ - memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN); + push_pseudo_header(skb, daddr); - return sizeof *header; + return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) @@ -1581,8 +1622,6 @@ void ipoib_dev_cleanup(struct net_device *dev) ASSERT_RTNL(); - ipoib_delete_debug_files(dev); - /* Delete any child interfaces first */ list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) { /* Stop GC on child */ @@ -1638,7 +1677,7 @@ void ipoib_setup(struct net_device *dev) dev->flags |= IFF_BROADCAST | IFF_MULTICAST; - dev->hard_header_len = IPOIB_ENCAP_LEN; + dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = ipoib_sendq_size * 2; @@ -1894,8 +1933,6 @@ static struct net_device *ipoib_add_port(const char *format, goto register_failed; } - ipoib_create_debug_files(priv->dev); - if (ipoib_cm_add_mode_attr(priv->dev)) goto sysfs_failed; if (ipoib_add_pkey_attr(priv->dev)) @@ -1910,7 +1947,6 @@ static struct net_device *ipoib_add_port(const char *format, return priv->dev; sysfs_failed: - ipoib_delete_debug_files(priv->dev); unregister_netdev(priv->dev); register_failed: @@ -1992,6 +2028,12 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) kfree(dev_list); } +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG +static struct notifier_block ipoib_netdev_notifier = { + .notifier_call = ipoib_netdev_event, +}; +#endif + static int __init ipoib_init_module(void) { int ret; @@ -2043,6 +2085,9 @@ static int __init ipoib_init_module(void) if (ret) goto err_client; +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG + register_netdevice_notifier(&ipoib_netdev_notifier); +#endif return 0; err_client: @@ -2060,6 +2105,9 @@ err_fs: static void __exit ipoib_cleanup_module(void) { +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG + unregister_netdevice_notifier(&ipoib_netdev_notifier); +#endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 8ec99bdea76b..5580ab0b5781 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -756,9 +756,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) __ipoib_mcast_add(dev, mcast); list_add_tail(&mcast->list, &priv->multicast_list); } - if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) + if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) { + /* put pseudoheader back on for next time */ + skb_push(skb, sizeof(struct ipoib_pseudo_header)); skb_queue_tail(&mcast->pkt_queue, skb); - else { + } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index fca1a882de27..57a34f87dedf 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -85,8 +85,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, goto register_failed; } - ipoib_create_debug_files(priv->dev); - /* RTNL childs don't need proprietary sysfs entries */ if (type == IPOIB_LEGACY_CHILD) { if (ipoib_cm_add_mode_attr(priv->dev)) @@ -107,7 +105,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, sysfs_failed: result = -ENOMEM; - ipoib_delete_debug_files(priv->dev); unregister_netdevice(priv->dev); register_failed: diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index b0edb66a291b..0b7f5a701c60 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -1581,7 +1581,7 @@ isert_rcv_completion(struct iser_rx_desc *desc, struct isert_conn *isert_conn, u32 xfer_len) { - struct ib_device *ib_dev = isert_conn->cm_id->device; + struct ib_device *ib_dev = isert_conn->device->ib_device; struct iscsi_hdr *hdr; u64 rx_dma; int rx_buflen; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 5f0f4fc58f43..e397f1b0af09 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1787,17 +1787,24 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp) if (unlikely(rsp->tag & SRP_TAG_TSK_MGMT)) { spin_lock_irqsave(&ch->lock, flags); ch->req_lim += be32_to_cpu(rsp->req_lim_delta); + if (rsp->tag == ch->tsk_mgmt_tag) { + ch->tsk_mgmt_status = -1; + if (be32_to_cpu(rsp->resp_data_len) >= 4) + ch->tsk_mgmt_status = rsp->data[3]; + complete(&ch->tsk_mgmt_done); + } else { + shost_printk(KERN_ERR, target->scsi_host, + "Received tsk mgmt response too late for tag %#llx\n", + rsp->tag); + } spin_unlock_irqrestore(&ch->lock, flags); - - ch->tsk_mgmt_status = -1; - if (be32_to_cpu(rsp->resp_data_len) >= 4) - ch->tsk_mgmt_status = rsp->data[3]; - complete(&ch->tsk_mgmt_done); } else { scmnd = scsi_host_find_tag(target->scsi_host, rsp->tag); - if (scmnd) { + if (scmnd && scmnd->host_scribble) { req = (void *)scmnd->host_scribble; scmnd = srp_claim_req(ch, req, NULL, scmnd); + } else { + scmnd = NULL; } if (!scmnd) { shost_printk(KERN_ERR, target->scsi_host, @@ -2469,19 +2476,18 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth) } static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun, - u8 func) + u8 func, u8 *status) { struct srp_target_port *target = ch->target; struct srp_rport *rport = target->rport; struct ib_device *dev = target->srp_host->srp_dev->dev; struct srp_iu *iu; struct srp_tsk_mgmt *tsk_mgmt; + int res; if (!ch->connected || target->qp_in_error) return -1; - init_completion(&ch->tsk_mgmt_done); - /* * Lock the rport mutex to avoid that srp_create_ch_ib() is * invoked while a task management function is being sent. @@ -2504,10 +2510,16 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun, tsk_mgmt->opcode = SRP_TSK_MGMT; int_to_scsilun(lun, &tsk_mgmt->lun); - tsk_mgmt->tag = req_tag | SRP_TAG_TSK_MGMT; tsk_mgmt->tsk_mgmt_func = func; tsk_mgmt->task_tag = req_tag; + spin_lock_irq(&ch->lock); + ch->tsk_mgmt_tag = (ch->tsk_mgmt_tag + 1) | SRP_TAG_TSK_MGMT; + tsk_mgmt->tag = ch->tsk_mgmt_tag; + spin_unlock_irq(&ch->lock); + + init_completion(&ch->tsk_mgmt_done); + ib_dma_sync_single_for_device(dev, iu->dma, sizeof *tsk_mgmt, DMA_TO_DEVICE); if (srp_post_send(ch, iu, sizeof(*tsk_mgmt))) { @@ -2516,13 +2528,15 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun, return -1; } + res = wait_for_completion_timeout(&ch->tsk_mgmt_done, + msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS)); + if (res > 0 && status) + *status = ch->tsk_mgmt_status; mutex_unlock(&rport->mutex); - if (!wait_for_completion_timeout(&ch->tsk_mgmt_done, - msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS))) - return -1; + WARN_ON_ONCE(res < 0); - return 0; + return res > 0 ? 0 : -1; } static int srp_abort(struct scsi_cmnd *scmnd) @@ -2548,7 +2562,7 @@ static int srp_abort(struct scsi_cmnd *scmnd) shost_printk(KERN_ERR, target->scsi_host, "Sending SRP abort for tag %#x\n", tag); if (srp_send_tsk_mgmt(ch, tag, scmnd->device->lun, - SRP_TSK_ABORT_TASK) == 0) + SRP_TSK_ABORT_TASK, NULL) == 0) ret = SUCCESS; else if (target->rport->state == SRP_RPORT_LOST) ret = FAST_IO_FAIL; @@ -2566,14 +2580,15 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) struct srp_target_port *target = host_to_target(scmnd->device->host); struct srp_rdma_ch *ch; int i; + u8 status; shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n"); ch = &target->ch[0]; if (srp_send_tsk_mgmt(ch, SRP_TAG_NO_REQ, scmnd->device->lun, - SRP_TSK_LUN_RESET)) + SRP_TSK_LUN_RESET, &status)) return FAILED; - if (ch->tsk_mgmt_status) + if (status) return FAILED; for (i = 0; i < target->ch_count; i++) { diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index f6af531f9f32..109eea94d0f9 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -168,6 +168,7 @@ struct srp_rdma_ch { int max_ti_iu_len; int comp_vector; + u64 tsk_mgmt_tag; struct completion tsk_mgmt_done; u8 tsk_mgmt_status; bool connected; diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c index d96aa27dfcdc..db64adfbe1af 100644 --- a/drivers/input/joystick/iforce/iforce-usb.c +++ b/drivers/input/joystick/iforce/iforce-usb.c @@ -141,6 +141,9 @@ static int iforce_usb_probe(struct usb_interface *intf, interface = intf->cur_altsetting; + if (interface->desc.bNumEndpoints < 2) + return -ENODEV; + epirq = &interface->endpoint[0].desc; epout = &interface->endpoint[1].desc; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 16f000a76de5..3258baf3282e 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -189,6 +189,7 @@ static const struct xpad_device { { 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX }, { 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 }, { 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 }, + { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE }, { 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 }, @@ -310,6 +311,7 @@ static struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */ XPAD_XBOX360_VENDOR(0x24c6), /* PowerA Controllers */ XPAD_XBOX360_VENDOR(0x1532), /* Razer Sabertooth */ + XPAD_XBOXONE_VENDOR(0x1532), /* Razer Wildcat */ XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */ { } diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c index 9365535ba7f1..50a7faa504f7 100644 --- a/drivers/input/misc/cm109.c +++ b/drivers/input/misc/cm109.c @@ -675,6 +675,10 @@ static int cm109_usb_probe(struct usb_interface *intf, int error = -ENOMEM; interface = intf->cur_altsetting; + + if (interface->desc.bNumEndpoints < 1) + return -ENODEV; + endpoint = &interface->endpoint[0].desc; if (!usb_endpoint_is_int_in(endpoint)) diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index 9c0ea36913b4..f4e8fbec6a94 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -1667,6 +1667,10 @@ static int ims_pcu_parse_cdc_data(struct usb_interface *intf, struct ims_pcu *pc return -EINVAL; alt = pcu->ctrl_intf->cur_altsetting; + + if (alt->desc.bNumEndpoints < 1) + return -ENODEV; + pcu->ep_ctrl = &alt->endpoint[0].desc; pcu->max_ctrl_size = usb_endpoint_maxp(pcu->ep_ctrl); diff --git a/drivers/input/misc/yealink.c b/drivers/input/misc/yealink.c index 79c964c075f1..6e7ff9561d92 100644 --- a/drivers/input/misc/yealink.c +++ b/drivers/input/misc/yealink.c @@ -875,6 +875,10 @@ static int usb_probe(struct usb_interface *intf, const struct usb_device_id *id) int ret, pipe, i; interface = intf->cur_altsetting; + + if (interface->desc.bNumEndpoints < 1) + return -ENODEV; + endpoint = &interface->endpoint[0].desc; if (!usb_endpoint_is_int_in(endpoint)) return -ENODEV; diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index d15b33813021..98d4e515587a 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -218,17 +218,19 @@ static int elan_query_product(struct elan_tp_data *data) static int elan_check_ASUS_special_fw(struct elan_tp_data *data) { - if (data->ic_type != 0x0E) - return false; - - switch (data->product_id) { - case 0x05 ... 0x07: - case 0x09: - case 0x13: + if (data->ic_type == 0x0E) { + switch (data->product_id) { + case 0x05 ... 0x07: + case 0x09: + case 0x13: + return true; + } + } else if (data->ic_type == 0x08 && data->product_id == 0x26) { + /* ASUS EeeBook X205TA */ return true; - default: - return false; } + + return false; } static int __elan_initialize(struct elan_tp_data *data) @@ -1232,6 +1234,11 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0000", 0 }, { "ELAN0100", 0 }, { "ELAN0600", 0 }, + { "ELAN0605", 0 }, + { "ELAN0608", 0 }, + { "ELAN0605", 0 }, + { "ELAN0609", 0 }, + { "ELAN060B", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 43482ae1e049..6f4dc0fd2ca3 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1122,7 +1122,10 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons + * Fujitsu LIFEBOOK E546 0x470f00 50, 12, 09 2 hw buttons + * Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons + * Fujitsu LIFEBOOK E557 0x570f01 40, 14, 0c 2 hw buttons * Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons * Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**) * Gigabyte U2442 0x450f01 58, 17, 0c 2 hw buttons @@ -1528,6 +1531,20 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { }, }, { + /* Fujitsu LIFEBOOK E546 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E546"), + }, + }, + { + /* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E547"), + }, + }, + { /* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), @@ -1542,6 +1559,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { }, }, { + /* Fujitsu LIFEBOOK E557 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E557"), + }, + }, + { /* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 0cdd95801a25..5be14ad29d46 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -120,6 +120,13 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { }, }, { + /* Dell Embedded Box PC 3000 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"), + }, + }, + { /* OQO Model 01 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "OQO"), @@ -678,6 +685,13 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "20046"), }, }, + { + /* Clevo P650RS, 650RP6, Sager NP8152-S, and others */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"), + }, + }, { } }; @@ -774,6 +788,13 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), }, }, + { + /* Fujitsu UH554 laptop */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"), + }, + }, { } }; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 89abfdb539ac..c84c685056b9 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -434,8 +434,10 @@ static int i8042_start(struct serio *serio) { struct i8042_port *port = serio->port_data; + spin_lock_irq(&i8042_lock); port->exists = true; - mb(); + spin_unlock_irq(&i8042_lock); + return 0; } @@ -448,16 +450,20 @@ static void i8042_stop(struct serio *serio) { struct i8042_port *port = serio->port_data; + spin_lock_irq(&i8042_lock); port->exists = false; + port->serio = NULL; + spin_unlock_irq(&i8042_lock); /* + * We need to make sure that interrupt handler finishes using + * our serio port before we return from this function. * We synchronize with both AUX and KBD IRQs because there is * a (very unlikely) chance that AUX IRQ is raised for KBD port * and vice versa. */ synchronize_irq(I8042_AUX_IRQ); synchronize_irq(I8042_KBD_IRQ); - port->serio = NULL; } /* @@ -574,7 +580,7 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id) spin_unlock_irqrestore(&i8042_lock, flags); - if (likely(port->exists && !filtered)) + if (likely(serio && !filtered)) serio_interrupt(serio, data, dfl); out: diff --git a/drivers/input/tablet/hanwang.c b/drivers/input/tablet/hanwang.c index cd852059b99e..df4bea96d7ed 100644 --- a/drivers/input/tablet/hanwang.c +++ b/drivers/input/tablet/hanwang.c @@ -340,6 +340,9 @@ static int hanwang_probe(struct usb_interface *intf, const struct usb_device_id int error; int i; + if (intf->cur_altsetting->desc.bNumEndpoints < 1) + return -ENODEV; + hanwang = kzalloc(sizeof(struct hanwang), GFP_KERNEL); input_dev = input_allocate_device(); if (!hanwang || !input_dev) { diff --git a/drivers/input/tablet/kbtab.c b/drivers/input/tablet/kbtab.c index d2ac7c2b5b82..2812f9236b7d 100644 --- a/drivers/input/tablet/kbtab.c +++ b/drivers/input/tablet/kbtab.c @@ -122,6 +122,9 @@ static int kbtab_probe(struct usb_interface *intf, const struct usb_device_id *i struct input_dev *input_dev; int error = -ENOMEM; + if (intf->cur_altsetting->desc.bNumEndpoints < 1) + return -ENODEV; + kbtab = kzalloc(sizeof(struct kbtab), GFP_KERNEL); input_dev = input_allocate_device(); if (!kbtab || !input_dev) diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 8364d84fd696..97f1eacdda0e 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -325,6 +325,7 @@ config TOUCHSCREEN_GOODIX tristate "Goodix I2C touchscreen" depends on I2C depends on GPIOLIB + select INPUT_POLLDEV help Say Y here if you have the Goodix touchscreen (such as one installed in Onda v975w tablets) connected to your diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index a27f0d7107af..916c9877261f 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -22,6 +22,7 @@ #include <linux/i2c.h> #include <linux/input.h> #include <linux/input/mt.h> +#include <linux/input-polldev.h> #include <linux/module.h> #include <linux/delay.h> #include <linux/irq.h> @@ -34,6 +35,7 @@ struct goodix_ts_data { struct i2c_client *client; struct input_dev *input_dev; + struct input_polled_dev *poll_dev; int abs_x_max; int abs_y_max; bool swapped_x_y; @@ -77,6 +79,8 @@ struct goodix_ts_data { #define MAX_CONTACTS_LOC 5 #define TRIGGER_LOC 6 +#define TSC_DEFAULT_POLL_PERIOD 30 /* ms */ + static const unsigned long goodix_irq_flags[] = { IRQ_TYPE_EDGE_RISING, IRQ_TYPE_EDGE_FALLING, @@ -281,6 +285,20 @@ static void goodix_process_events(struct goodix_ts_data *ts) input_sync(ts->input_dev); } +static void _goodix_process_events(struct goodix_ts_data *ts) +{ + goodix_process_events(ts); + + if (goodix_i2c_write_u8(ts->client, GOODIX_READ_COOR_ADDR, 0) < 0) + dev_err(&ts->client->dev, "I2C write end_cmd error\n"); + +} +static void goodix_poll(struct input_polled_dev *poll_dev) +{ + struct goodix_ts_data *ts = poll_dev->private; + + _goodix_process_events(ts); +} /** * goodix_ts_irq_handler - The IRQ handler * @@ -291,10 +309,7 @@ static irqreturn_t goodix_ts_irq_handler(int irq, void *dev_id) { struct goodix_ts_data *ts = dev_id; - goodix_process_events(ts); - - if (goodix_i2c_write_u8(ts->client, GOODIX_READ_COOR_ADDR, 0) < 0) - dev_err(&ts->client->dev, "I2C write end_cmd error\n"); + _goodix_process_events(ts); return IRQ_HANDLED; } @@ -614,6 +629,58 @@ static int goodix_request_input_dev(struct goodix_ts_data *ts) return 0; } +static int goodix_request_input_polled_dev(struct goodix_ts_data *ts) +{ + int error; + struct input_polled_dev *poll_dev; + + dev_err(&ts->client->dev, "Setting up polling.\n"); + poll_dev = input_allocate_polled_device(); + if (!poll_dev) { + dev_err(&ts->client->dev, "Failed to allocate polled input device.\n"); + error = -ENOMEM; + return error; + } + + ts->poll_dev = poll_dev; + + poll_dev->private = ts; + poll_dev->poll = goodix_poll; + poll_dev->poll_interval = TSC_DEFAULT_POLL_PERIOD; + + ts->input_dev = poll_dev->input; + if (!ts->input_dev) { + dev_err(&ts->client->dev, "Failed to allocate input device."); + return -ENOMEM; + } + + input_set_abs_params(ts->input_dev, ABS_MT_POSITION_X, + 0, ts->abs_x_max, 0, 0); + input_set_abs_params(ts->input_dev, ABS_MT_POSITION_Y, + 0, ts->abs_y_max, 0, 0); + input_set_abs_params(ts->input_dev, ABS_MT_WIDTH_MAJOR, 0, 255, 0, 0); + input_set_abs_params(ts->input_dev, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); + + input_mt_init_slots(ts->input_dev, ts->max_touch_num, + INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED); + + ts->input_dev->name = "Goodix Capacitive TouchScreen"; + ts->input_dev->phys = "input/ts"; + ts->input_dev->id.bustype = BUS_I2C; + ts->input_dev->id.vendor = 0x0416; + ts->input_dev->id.product = ts->id; + ts->input_dev->id.version = ts->version; + + error = input_register_polled_device(poll_dev); + if (error) { + dev_err(&ts->client->dev, + "Failed to register input device: %d", error); + return error; + } + + return 0; +} + /** * goodix_configure_dev - Finish device initialization * @@ -637,15 +704,23 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) goodix_read_config(ts); - error = goodix_request_input_dev(ts); - if (error) - return error; + if (ts->client->irq) { + error = goodix_request_input_dev(ts); + if (error) + return error; + ts->irq_flags = goodix_irq_flags[ts->int_trigger_type] | + IRQF_ONESHOT; + error = goodix_request_irq(ts); + if (error) { + dev_err(&ts->client->dev, "request IRQ failed: %d\n", + error); + return error; + } + } else { + /* setup polling if IRQ is not defined */ + + error = goodix_request_input_polled_dev(ts); - ts->irq_flags = goodix_irq_flags[ts->int_trigger_type] | IRQF_ONESHOT; - error = goodix_request_irq(ts); - if (error) { - dev_err(&ts->client->dev, "request IRQ failed: %d\n", error); - return error; } return 0; diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c index 45b466e3bbe8..0146e2c74649 100644 --- a/drivers/input/touchscreen/sur40.c +++ b/drivers/input/touchscreen/sur40.c @@ -500,6 +500,9 @@ static int sur40_probe(struct usb_interface *interface, if (iface_desc->desc.bInterfaceClass != 0xFF) return -ENODEV; + if (iface_desc->desc.bNumEndpoints < 5) + return -ENODEV; + /* Use endpoint #4 (0x86). */ endpoint = &iface_desc->endpoint[4].desc; if (endpoint->bEndpointAddress != TOUCH_ENDPOINT) diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 4831eb910fc7..22160e481794 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -699,9 +699,9 @@ out_clear_state: out_unregister: mmu_notifier_unregister(&pasid_state->mn, mm); + mmput(mm); out_free: - mmput(mm); free_pasid_state(pasid_state); out: diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 9413b0726237..f9711aceef54 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -908,7 +908,7 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf * which we used for the IOMMU lookup. Strictly speaking * we could do this for all PCI devices; we only need to * get the BDF# from the scope table for ACPI matches. */ - if (pdev->is_virtfn) + if (pdev && pdev->is_virtfn) goto got_pdev; *bus = drhd->devices[i].bus; @@ -1137,7 +1137,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level, if (!dma_pte_present(pte) || dma_pte_superpage(pte)) goto next; - level_pfn = pfn & level_mask(level - 1); + level_pfn = pfn & level_mask(level); level_pte = phys_to_virt(dma_pte_addr(pte)); if (level > 2) @@ -2005,11 +2005,14 @@ static int domain_context_mapping_one(struct dmar_domain *domain, if (context_copied(context)) { u16 did_old = context_domain_id(context); - if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) + if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) { iommu->flush.flush_context(iommu, did_old, (((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL); + iommu->flush.flush_iotlb(iommu, did_old, 0, 0, + DMA_TLB_DSI_FLUSH); + } } pgd = domain->pgd; @@ -3238,13 +3241,14 @@ static int __init init_dmars(void) iommu_identity_mapping |= IDENTMAP_GFX; #endif + check_tylersburg_isoch(); + if (iommu_identity_mapping) { ret = si_domain_init(hw_pass_through); if (ret) goto free_iommu; } - check_tylersburg_isoch(); /* * If we copied translations from a previous kernel in the kdump diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 515bb8b80952..a070fa39521a 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -391,36 +391,30 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev) device->dev = dev; ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group"); - if (ret) { - kfree(device); - return ret; - } + if (ret) + goto err_free_device; device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj)); rename: if (!device->name) { - sysfs_remove_link(&dev->kobj, "iommu_group"); - kfree(device); - return -ENOMEM; + ret = -ENOMEM; + goto err_remove_link; } ret = sysfs_create_link_nowarn(group->devices_kobj, &dev->kobj, device->name); if (ret) { - kfree(device->name); if (ret == -EEXIST && i >= 0) { /* * Account for the slim chance of collision * and append an instance to the name. */ + kfree(device->name); device->name = kasprintf(GFP_KERNEL, "%s.%d", kobject_name(&dev->kobj), i++); goto rename; } - - sysfs_remove_link(&dev->kobj, "iommu_group"); - kfree(device); - return ret; + goto err_free_name; } kobject_get(group->devices_kobj); @@ -432,8 +426,10 @@ rename: mutex_lock(&group->mutex); list_add_tail(&device->list, &group->devices); if (group->domain) - __iommu_attach_device(group->domain, dev); + ret = __iommu_attach_device(group->domain, dev); mutex_unlock(&group->mutex); + if (ret) + goto err_put_group; /* Notify any listeners about change to group. */ blocking_notifier_call_chain(&group->notifier, @@ -444,6 +440,21 @@ rename: pr_info("Adding device %s to group %d\n", dev_name(dev), group->id); return 0; + +err_put_group: + mutex_lock(&group->mutex); + list_del(&device->list); + mutex_unlock(&group->mutex); + dev->iommu_group = NULL; + kobject_put(group->devices_kobj); +err_free_name: + kfree(device->name); +err_remove_link: + sysfs_remove_link(&dev->kobj, "iommu_group"); +err_free_device: + kfree(device); + pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret); + return ret; } EXPORT_SYMBOL_GPL(iommu_group_add_device); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 6ce7abb22732..f6ec55ab0233 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -908,7 +908,8 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd) err = iommu_enable(obj); if (err) goto err_enable; - flush_iotlb_all(obj); + if (!obj->late_attach) + flush_iotlb_all(obj); spin_unlock(&obj->iommu_lock); diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c index 37199b9b2cfa..831a195cb806 100644 --- a/drivers/irqchip/irq-atmel-aic-common.c +++ b/drivers/irqchip/irq-atmel-aic-common.c @@ -148,9 +148,9 @@ void __init aic_common_rtc_irq_fixup(struct device_node *root) struct device_node *np; void __iomem *regs; - np = of_find_compatible_node(root, NULL, "atmel,at91rm9200-rtc"); + np = of_find_compatible_node(NULL, NULL, "atmel,at91rm9200-rtc"); if (!np) - np = of_find_compatible_node(root, NULL, + np = of_find_compatible_node(NULL, NULL, "atmel,at91sam9x5-rtc"); if (!np) @@ -202,7 +202,6 @@ void __init aic_common_irq_fixup(const struct of_device_id *matches) return; match = of_match_node(matches, root); - of_node_put(root); if (match) { void (*fixup)(struct device_node *) = match->data; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index e33c729b9f48..5a1490b046ac 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -632,6 +632,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, int enabled; u64 val; + if (cpu >= nr_cpu_ids) + return -EINVAL; + if (gic_irq_in_rdist(d)) return -EINVAL; diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c index 15af9a9753e5..2d203b422129 100644 --- a/drivers/irqchip/irq-imx-gpcv2.c +++ b/drivers/irqchip/irq-imx-gpcv2.c @@ -230,6 +230,8 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node, return -ENOMEM; } + raw_spin_lock_init(&cd->rlock); + cd->gpc_base = of_iomap(node, 0); if (!cd->gpc_base) { pr_err("fsl-gpcv2: unable to map gpc registers\n"); diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index 17304705f2cf..05fa9f7af53c 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -131,12 +131,16 @@ static struct irq_chip mxs_icoll_chip = { .irq_ack = icoll_ack_irq, .irq_mask = icoll_mask_irq, .irq_unmask = icoll_unmask_irq, + .flags = IRQCHIP_MASK_ON_SUSPEND | + IRQCHIP_SKIP_SET_WAKE, }; static struct irq_chip asm9260_icoll_chip = { .irq_ack = icoll_ack_irq, .irq_mask = asm9260_mask_irq, .irq_unmask = asm9260_unmask_irq, + .flags = IRQCHIP_MASK_ON_SUSPEND | + IRQCHIP_SKIP_SET_WAKE, }; asmlinkage void __exception_irq_entry icoll_handle_irq(struct pt_regs *regs) diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c index bb3ac5fe5846..72a391e01011 100644 --- a/drivers/irqchip/irq-xtensa-mx.c +++ b/drivers/irqchip/irq-xtensa-mx.c @@ -142,7 +142,7 @@ static struct irq_chip xtensa_mx_irq_chip = { int __init xtensa_mx_init_legacy(struct device_node *interrupt_parent) { struct irq_domain *root_domain = - irq_domain_add_legacy(NULL, NR_IRQS, 0, 0, + irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0, &xtensa_mx_irq_domain_ops, &xtensa_mx_irq_chip); irq_set_default_host(root_domain); diff --git a/drivers/irqchip/irq-xtensa-pic.c b/drivers/irqchip/irq-xtensa-pic.c index 472ae1770964..f728755fa292 100644 --- a/drivers/irqchip/irq-xtensa-pic.c +++ b/drivers/irqchip/irq-xtensa-pic.c @@ -89,7 +89,7 @@ static struct irq_chip xtensa_irq_chip = { int __init xtensa_pic_init_legacy(struct device_node *interrupt_parent) { struct irq_domain *root_domain = - irq_domain_add_legacy(NULL, NR_IRQS, 0, 0, + irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0, &xtensa_irq_domain_ops, &xtensa_irq_chip); irq_set_default_host(root_domain); return 0; diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index aecec6d32463..7f1c625b08ec 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -2317,6 +2317,9 @@ static int gigaset_probe(struct usb_interface *interface, return -ENODEV; } + if (hostif->desc.bNumEndpoints < 1) + return -ENODEV; + dev_info(&udev->dev, "%s: Device matched (Vendor: 0x%x, Product: 0x%x)\n", __func__, le16_to_cpu(udev->descriptor.idVendor), diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c index d7c286656a25..7b4ddf0a39ec 100644 --- a/drivers/isdn/hardware/eicon/message.c +++ b/drivers/isdn/hardware/eicon/message.c @@ -11304,7 +11304,8 @@ static void mixer_notify_update(PLCI *plci, byte others) ((CAPI_MSG *) msg)->header.ncci = 0; ((CAPI_MSG *) msg)->info.facility_req.Selector = SELECTOR_LINE_INTERCONNECT; ((CAPI_MSG *) msg)->info.facility_req.structs[0] = 3; - PUT_WORD(&(((CAPI_MSG *) msg)->info.facility_req.structs[1]), LI_REQ_SILENT_UPDATE); + ((CAPI_MSG *) msg)->info.facility_req.structs[1] = LI_REQ_SILENT_UPDATE & 0xff; + ((CAPI_MSG *) msg)->info.facility_req.structs[2] = LI_REQ_SILENT_UPDATE >> 8; ((CAPI_MSG *) msg)->info.facility_req.structs[3] = 0; w = api_put(notify_plci->appl, (CAPI_MSG *) msg); if (w != _QUEUE_FULL) diff --git a/drivers/isdn/i4l/isdn_common.c b/drivers/isdn/i4l/isdn_common.c index 9b856e1890d1..e4c43a17b333 100644 --- a/drivers/isdn/i4l/isdn_common.c +++ b/drivers/isdn/i4l/isdn_common.c @@ -1379,6 +1379,7 @@ isdn_ioctl(struct file *file, uint cmd, ulong arg) if (arg) { if (copy_from_user(bname, argp, sizeof(bname) - 1)) return -EFAULT; + bname[sizeof(bname)-1] = 0; } else return -EINVAL; ret = mutex_lock_interruptible(&dev->mtx); diff --git a/drivers/isdn/i4l/isdn_net.c b/drivers/isdn/i4l/isdn_net.c index aa5dd5668528..dbad5c431bcb 100644 --- a/drivers/isdn/i4l/isdn_net.c +++ b/drivers/isdn/i4l/isdn_net.c @@ -2611,10 +2611,9 @@ isdn_net_newslave(char *parm) char newname[10]; if (p) { - /* Slave-Name MUST not be empty */ - if (!strlen(p + 1)) + /* Slave-Name MUST not be empty or overflow 'newname' */ + if (strscpy(newname, p + 1, sizeof(newname)) <= 0) return NULL; - strcpy(newname, p + 1); *p = 0; /* Master must already exist */ if (!(n = isdn_net_findif(parm))) diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c index 9c1e8adaf4fc..bf3fbd00a091 100644 --- a/drivers/isdn/i4l/isdn_ppp.c +++ b/drivers/isdn/i4l/isdn_ppp.c @@ -2364,7 +2364,7 @@ static struct ippp_ccp_reset_state *isdn_ppp_ccp_reset_alloc_state(struct ippp_s id); return NULL; } else { - rs = kzalloc(sizeof(struct ippp_ccp_reset_state), GFP_KERNEL); + rs = kzalloc(sizeof(struct ippp_ccp_reset_state), GFP_ATOMIC); if (!rs) return NULL; rs->state = CCPResetIdle; diff --git a/drivers/leds/leds-ktd2692.c b/drivers/leds/leds-ktd2692.c index feca07be85f5..1eb9fb33db38 100644 --- a/drivers/leds/leds-ktd2692.c +++ b/drivers/leds/leds-ktd2692.c @@ -296,15 +296,15 @@ static int ktd2692_parse_dt(struct ktd2692_context *led, struct device *dev, return -ENXIO; led->ctrl_gpio = devm_gpiod_get(dev, "ctrl", GPIOD_ASIS); - if (IS_ERR(led->ctrl_gpio)) { - ret = PTR_ERR(led->ctrl_gpio); + ret = PTR_ERR_OR_ZERO(led->ctrl_gpio); + if (ret) { dev_err(dev, "cannot get ctrl-gpios %d\n", ret); return ret; } led->aux_gpio = devm_gpiod_get(dev, "aux", GPIOD_ASIS); - if (IS_ERR(led->aux_gpio)) { - ret = PTR_ERR(led->aux_gpio); + ret = PTR_ERR_OR_ZERO(led->aux_gpio); + if (ret) { dev_err(dev, "cannot get aux-gpios %d\n", ret); return ret; } diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 6a4811f85705..9cf826df89b1 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -104,11 +104,14 @@ static void tx_tick(struct mbox_chan *chan, int r) /* Submit next message */ msg_submit(chan); + if (!mssg) + return; + /* Notify the client */ - if (mssg && chan->cl->tx_done) + if (chan->cl->tx_done) chan->cl->tx_done(chan->cl, mssg, r); - if (chan->cl->tx_block) + if (r != -ETIME && chan->cl->tx_block) complete(&chan->tx_complete); } @@ -261,7 +264,7 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg) msg_submit(chan); - if (chan->cl->tx_block && chan->active_req) { + if (chan->cl->tx_block) { unsigned long wait; int ret; @@ -272,8 +275,8 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg) ret = wait_for_completion_timeout(&chan->tx_complete, wait); if (ret == 0) { - t = -EIO; - tx_tick(chan, -EIO); + t = -ETIME; + tx_tick(chan, t); } } diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 3d237a03dab3..5649d1ab0083 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -357,6 +357,7 @@ config DM_LOG_USERSPACE config DM_RAID tristate "RAID 1/4/5/6/10 target" depends on BLK_DEV_DM + select MD_RAID0 select MD_RAID1 select MD_RAID10 select MD_RAID456 @@ -515,16 +516,27 @@ config DM_LOG_WRITES If unsure, say N. -config DM_ANDROID_VERITY - tristate "Android verity target support" +config DM_VERITY_AVB + tristate "Support AVB specific verity error behavior" depends on DM_VERITY + ---help--- + Enables Android Verified Boot platform-specific error + behavior. In particular, it will modify the vbmeta partition + specified on the kernel command-line when non-transient error + occurs (followed by a panic). + + If unsure, say N. + +config DM_ANDROID_VERITY + bool "Android verity target support" + depends on DM_VERITY=y depends on X509_CERTIFICATE_PARSER depends on SYSTEM_TRUSTED_KEYRING depends on PUBLIC_KEY_ALGO_RSA depends on KEYS depends on ASYMMETRIC_KEY_TYPE depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE - depends on MD_LINEAR + depends on MD_LINEAR=y select DM_VERITY_HASH_PREFETCH_MIN_SIZE_128 ---help--- This device-mapper target is virtually a VERITY target. This diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 32b5d0a90d60..c22cc74c9fa8 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -69,3 +69,7 @@ endif ifeq ($(CONFIG_DM_VERITY_FEC),y) dm-verity-objs += dm-verity-fec.o endif + +ifeq ($(CONFIG_DM_VERITY_AVB),y) +dm-verity-objs += dm-verity-avb.o +endif diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 6b420a55c745..c3ea03c9a1a8 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -425,7 +425,7 @@ struct cache { * until a gc finishes - otherwise we could pointlessly burn a ton of * cpu */ - unsigned invalidate_needs_gc:1; + unsigned invalidate_needs_gc; bool discard; /* Get rid of? */ @@ -593,8 +593,8 @@ struct cache_set { /* Counts how many sectors bio_insert has added to the cache */ atomic_t sectors_to_gc; + wait_queue_head_t gc_wait; - wait_queue_head_t moving_gc_wait; struct keybuf moving_gc_keys; /* Number of moving GC bios in flight */ struct semaphore moving_in_flight; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 22b9e34ceb75..5b815e64c1c9 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1762,33 +1762,34 @@ static void bch_btree_gc(struct cache_set *c) bch_moving_gc(c); } -static int bch_gc_thread(void *arg) +static bool gc_should_run(struct cache_set *c) { - struct cache_set *c = arg; struct cache *ca; unsigned i; - while (1) { -again: - bch_btree_gc(c); + for_each_cache(ca, c, i) + if (ca->invalidate_needs_gc) + return true; - set_current_state(TASK_INTERRUPTIBLE); - if (kthread_should_stop()) - break; + if (atomic_read(&c->sectors_to_gc) < 0) + return true; - mutex_lock(&c->bucket_lock); + return false; +} - for_each_cache(ca, c, i) - if (ca->invalidate_needs_gc) { - mutex_unlock(&c->bucket_lock); - set_current_state(TASK_RUNNING); - goto again; - } +static int bch_gc_thread(void *arg) +{ + struct cache_set *c = arg; - mutex_unlock(&c->bucket_lock); + while (1) { + wait_event_interruptible(c->gc_wait, + kthread_should_stop() || gc_should_run(c)); - try_to_freeze(); - schedule(); + if (kthread_should_stop()) + break; + + set_gc_sectors(c); + bch_btree_gc(c); } return 0; @@ -1796,11 +1797,10 @@ again: int bch_gc_thread_start(struct cache_set *c) { - c->gc_thread = kthread_create(bch_gc_thread, c, "bcache_gc"); + c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc"); if (IS_ERR(c->gc_thread)) return PTR_ERR(c->gc_thread); - set_task_state(c->gc_thread, TASK_INTERRUPTIBLE); return 0; } diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 5c391fa01bed..9b80417cd547 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -260,8 +260,7 @@ void bch_initial_mark_key(struct cache_set *, int, struct bkey *); static inline void wake_up_gc(struct cache_set *c) { - if (c->gc_thread) - wake_up_process(c->gc_thread); + wake_up(&c->gc_wait); } #define MAP_DONE 0 diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 25fa8445bb24..2410df1c2a05 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -196,10 +196,8 @@ static void bch_data_insert_start(struct closure *cl) struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); struct bio *bio = op->bio, *n; - if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) { - set_gc_sectors(op->c); + if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) wake_up_gc(op->c); - } if (op->bypass) return bch_data_invalidate(cl); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 3d5c0ba13181..7b5880b8874c 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1489,6 +1489,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); init_waitqueue_head(&c->bucket_wait); + init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1); spin_lock_init(&c->btree_gc_time.lock); @@ -1547,6 +1548,7 @@ static void run_cache_set(struct cache_set *c) for_each_cache(ca, c, i) c->nbuckets += ca->sb.nbuckets; + set_gc_sectors(c); if (CACHE_SYNC(&c->sb)) { LIST_HEAD(journal); diff --git a/drivers/md/dm-android-verity.c b/drivers/md/dm-android-verity.c index bb6c1285e499..c3c9502baf18 100644 --- a/drivers/md/dm-android-verity.c +++ b/drivers/md/dm-android-verity.c @@ -115,6 +115,12 @@ static inline bool is_userdebug(void) return !strncmp(buildvariant, typeuserdebug, sizeof(typeuserdebug)); } +static inline bool is_unlocked(void) +{ + static const char unlocked[] = "orange"; + + return !strncmp(verifiedbootstate, unlocked, sizeof(unlocked)); +} static int table_extract_mpi_array(struct public_key_signature *pks, const void *data, size_t len) @@ -585,6 +591,8 @@ static int verify_verity_signature(char *key_id, if (IS_ERR(pks)) { DMERR("hashing failed"); + retval = PTR_ERR(pks); + pks = NULL; goto error; } @@ -648,6 +656,28 @@ static int add_as_linear_device(struct dm_target *ti, char *dev) return err; } +static int create_linear_device(struct dm_target *ti, dev_t dev, + char *target_device) +{ + u64 device_size = 0; + int err = find_size(dev, &device_size); + + if (err) { + DMERR("error finding bdev size"); + handle_error(); + return err; + } + + ti->len = device_size; + err = add_as_linear_device(ti, target_device); + if (err) { + handle_error(); + return err; + } + verity_enabled = false; + return 0; +} + /* * Target parameters: * <key id> Key id of the public key in the system keyring. @@ -671,7 +701,6 @@ static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv) struct fec_ecc_metadata uninitialized_var(ecc); char buf[FEC_ARG_LENGTH], *buf_ptr; unsigned long long tmpll; - u64 uninitialized_var(device_size); if (argc == 1) { /* Use the default keyid */ @@ -699,23 +728,8 @@ static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv) return -EINVAL; } - if (is_eng()) { - err = find_size(dev, &device_size); - if (err) { - DMERR("error finding bdev size"); - handle_error(); - return err; - } - - ti->len = device_size; - err = add_as_linear_device(ti, target_device); - if (err) { - handle_error(); - return err; - } - verity_enabled = false; - return 0; - } + if (is_eng()) + return create_linear_device(ti, dev, target_device); strreplace(key_id, '#', ' '); @@ -730,6 +744,11 @@ static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv) err = extract_metadata(dev, &fec, &metadata, &verity_enabled); if (err) { + /* Allow invalid metadata when the device is unlocked */ + if (is_unlocked()) { + DMWARN("Allow invalid metadata when unlocked"); + return create_linear_device(ti, dev, target_device); + } DMERR("Error while extracting metadata"); handle_error(); goto free_metadata; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 2dd33085b331..cdceefd0e57d 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -222,7 +222,7 @@ static DEFINE_SPINLOCK(param_spinlock); * Buffers are freed after this timeout */ static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS; -static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; +static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; static unsigned long dm_bufio_peak_allocated; static unsigned long dm_bufio_allocated_kmem_cache; @@ -914,10 +914,11 @@ static void __get_memory_limit(struct dm_bufio_client *c, { unsigned long buffers; - if (ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch) { - mutex_lock(&dm_bufio_clients_lock); - __cache_size_refresh(); - mutex_unlock(&dm_bufio_clients_lock); + if (unlikely(ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) { + if (mutex_trylock(&dm_bufio_clients_lock)) { + __cache_size_refresh(); + mutex_unlock(&dm_bufio_clients_lock); + } } buffers = dm_bufio_cache_size_per_client >> @@ -1513,10 +1514,10 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) return true; } -static unsigned get_retain_buffers(struct dm_bufio_client *c) +static unsigned long get_retain_buffers(struct dm_bufio_client *c) { - unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); - return retain_bytes / c->block_size; + unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); + return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT); } static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, @@ -1526,7 +1527,7 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, struct dm_buffer *b, *tmp; unsigned long freed = 0; unsigned long count = nr_to_scan; - unsigned retain_target = get_retain_buffers(c); + unsigned long retain_target = get_retain_buffers(c); for (l = 0; l < LIST_SIZE; l++) { list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { @@ -1752,11 +1753,19 @@ static bool older_than(struct dm_buffer *b, unsigned long age_hz) static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz) { struct dm_buffer *b, *tmp; - unsigned retain_target = get_retain_buffers(c); - unsigned count; + unsigned long retain_target = get_retain_buffers(c); + unsigned long count; + LIST_HEAD(write_list); dm_bufio_lock(c); + __check_watermark(c, &write_list); + if (unlikely(!list_empty(&write_list))) { + dm_bufio_unlock(c); + __flush_write_list(&write_list); + dm_bufio_lock(c); + } + count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY]; list_for_each_entry_safe_reverse(b, tmp, &c->lru[LIST_CLEAN], lru_list) { if (count <= retain_target) @@ -1781,6 +1790,8 @@ static void cleanup_old_buffers(void) mutex_lock(&dm_bufio_clients_lock); + __cache_size_refresh(); + list_for_each_entry(c, &dm_bufio_all_clients, client_list) __evict_old_buffers(c, max_age_hz); @@ -1904,7 +1915,7 @@ MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache"); module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds"); -module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR); +module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory"); module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR); diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 3970cda10080..d3c55d7754af 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1326,17 +1326,19 @@ void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd, int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown) { - int r; + int r = -EINVAL; flags_mutator mutator = (clean_shutdown ? set_clean_shutdown : clear_clean_shutdown); WRITE_LOCK(cmd); + if (cmd->fail_io) + goto out; + r = __commit_transaction(cmd, mutator); if (r) goto out; r = __begin_transaction(cmd); - out: WRITE_UNLOCK(cmd); return r; @@ -1348,7 +1350,8 @@ int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd, int r = -EINVAL; READ_LOCK(cmd); - r = dm_sm_get_nr_free(cmd->metadata_sm, result); + if (!cmd->fail_io) + r = dm_sm_get_nr_free(cmd->metadata_sm, result); READ_UNLOCK(cmd); return r; @@ -1360,7 +1363,8 @@ int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd, int r = -EINVAL; READ_LOCK(cmd); - r = dm_sm_get_nr_blocks(cmd->metadata_sm, result); + if (!cmd->fail_io) + r = dm_sm_get_nr_blocks(cmd->metadata_sm, result); READ_UNLOCK(cmd); return r; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index bb9b92ebbf8e..0da5efaad85c 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -248,7 +248,7 @@ struct cache { /* * Fields for converting from sectors to blocks. */ - uint32_t sectors_per_block; + sector_t sectors_per_block; int sectors_per_block_shift; spinlock_t lock; @@ -3544,11 +3544,11 @@ static void cache_status(struct dm_target *ti, status_type_t type, residency = policy_residency(cache->policy); - DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ", + DMEMIT("%u %llu/%llu %llu %llu/%llu %u %u %u %u %u %u %lu ", (unsigned)DM_CACHE_METADATA_BLOCK_SIZE, (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata), (unsigned long long)nr_blocks_metadata, - cache->sectors_per_block, + (unsigned long long)cache->sectors_per_block, (unsigned long long) from_cblock(residency), (unsigned long long) from_cblock(cache->cache_size), (unsigned) atomic_read(&cache->stats.read_hit), diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 665bf3285618..32e76c5ee741 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -961,15 +961,15 @@ static int metadata_commit(struct era_metadata *md) } } - r = save_sm_root(md); + r = dm_tm_pre_commit(md->tm); if (r) { - DMERR("%s: save_sm_root failed", __func__); + DMERR("%s: pre commit failed", __func__); return r; } - r = dm_tm_pre_commit(md->tm); + r = save_sm_root(md); if (r) { - DMERR("%s: pre commit failed", __func__); + DMERR("%s: save_sm_root failed", __func__); return r; } diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index bc5e9a5b1f30..7baeeafa059d 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1843,7 +1843,7 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user) if (r) goto out; - param->data_size = sizeof(*param); + param->data_size = offsetof(struct dm_ioctl, data); r = fn(param, input_param_size); if (unlikely(param->flags & DM_BUFFER_FULL_FLAG) && diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 8289804ccd99..d5ea9f28ae70 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -175,6 +175,7 @@ static void dm_stat_free(struct rcu_head *head) int cpu; struct dm_stat *s = container_of(head, struct dm_stat, rcu_head); + kfree(s->histogram_boundaries); kfree(s->program_id); kfree(s->aux_data); for_each_possible_cpu(cpu) { diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 911ada643364..3b67afda430b 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -485,11 +485,11 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) if (r < 0) return r; - r = save_sm_roots(pmd); + r = dm_tm_pre_commit(pmd->tm); if (r < 0) return r; - r = dm_tm_pre_commit(pmd->tm); + r = save_sm_roots(pmd); if (r < 0) return r; diff --git a/drivers/md/dm-verity-avb.c b/drivers/md/dm-verity-avb.c new file mode 100644 index 000000000000..88487346c4c6 --- /dev/null +++ b/drivers/md/dm-verity-avb.c @@ -0,0 +1,217 @@ +/* + * Copyright (C) 2017 Google. + * + * This file is released under the GPLv2. + * + * Based on drivers/md/dm-verity-chromeos.c + */ + +#include <linux/device-mapper.h> +#include <linux/module.h> +#include <linux/mount.h> + +#define DM_MSG_PREFIX "verity-avb" + +/* Set via module parameter. */ +static char avb_vbmeta_device[64]; + +static void invalidate_vbmeta_endio(struct bio *bio) +{ + complete(bio->bi_private); +} + +static int invalidate_vbmeta_submit(struct bio *bio, + struct block_device *bdev, + int rw, int access_last_sector, + struct page *page) +{ + DECLARE_COMPLETION_ONSTACK(wait); + + bio->bi_private = &wait; + bio->bi_end_io = invalidate_vbmeta_endio; + bio->bi_bdev = bdev; + + bio->bi_iter.bi_sector = 0; + if (access_last_sector) { + sector_t last_sector = (i_size_read(bdev->bd_inode)>>SECTOR_SHIFT) - 1; + bio->bi_iter.bi_sector = last_sector; + } + bio->bi_vcnt = 1; + bio->bi_iter.bi_idx = 0; + bio->bi_iter.bi_size = 512; + bio->bi_iter.bi_bvec_done = 0; + bio->bi_rw = rw; + bio->bi_io_vec[0].bv_page = page; + bio->bi_io_vec[0].bv_len = 512; + bio->bi_io_vec[0].bv_offset = 0; + + submit_bio(rw, bio); + /* Wait up to 2 seconds for completion or fail. */ + if (!wait_for_completion_timeout(&wait, msecs_to_jiffies(2000))) + return -EIO; + return 0; +} + +static int invalidate_vbmeta(dev_t vbmeta_devt) +{ + int ret = 0; + struct block_device *bdev; + struct bio *bio; + struct page *page; + fmode_t dev_mode; + /* Ensure we do synchronous unblocked I/O. We may also need + * sync_bdev() on completion, but it really shouldn't. + */ + int rw = REQ_SYNC | REQ_SOFTBARRIER | REQ_NOIDLE; + int access_last_sector = 0; + + /* First we open the device for reading. */ + dev_mode = FMODE_READ | FMODE_EXCL; + bdev = blkdev_get_by_dev(vbmeta_devt, dev_mode, + invalidate_vbmeta); + if (IS_ERR(bdev)) { + DMERR("invalidate_kernel: could not open device for reading"); + dev_mode = 0; + ret = -ENOENT; + goto failed_to_read; + } + + bio = bio_alloc(GFP_NOIO, 1); + if (!bio) { + ret = -ENOMEM; + goto failed_bio_alloc; + } + + page = alloc_page(GFP_NOIO); + if (!page) { + ret = -ENOMEM; + goto failed_to_alloc_page; + } + + access_last_sector = 0; + ret = invalidate_vbmeta_submit(bio, bdev, rw, access_last_sector, page); + if (ret) { + DMERR("invalidate_vbmeta: error reading"); + goto failed_to_submit_read; + } + + /* We have a page. Let's make sure it looks right. */ + if (memcmp("AVB0", page_address(page), 4) == 0) { + /* Stamp it. */ + memcpy(page_address(page), "AVE0", 4); + DMINFO("invalidate_vbmeta: found vbmeta partition"); + } else { + /* Could be this is on a AVB footer, check. Also, since the + * AVB footer is in the last 64 bytes, adjust for the fact that + * we're dealing with 512-byte sectors. + */ + size_t offset = (1<<SECTOR_SHIFT) - 64; + + access_last_sector = 1; + ret = invalidate_vbmeta_submit(bio, bdev, rw, + access_last_sector, page); + if (ret) { + DMERR("invalidate_vbmeta: error reading"); + goto failed_to_submit_read; + } + if (memcmp("AVBf", page_address(page) + offset, 4) != 0) { + DMERR("invalidate_vbmeta called on non-vbmeta partition"); + ret = -EINVAL; + goto invalid_header; + } + /* Stamp it. */ + memcpy(page_address(page) + offset, "AVE0", 4); + DMINFO("invalidate_vbmeta: found vbmeta footer partition"); + } + + /* Now rewrite the changed page - the block dev was being + * changed on read. Let's reopen here. + */ + blkdev_put(bdev, dev_mode); + dev_mode = FMODE_WRITE | FMODE_EXCL; + bdev = blkdev_get_by_dev(vbmeta_devt, dev_mode, + invalidate_vbmeta); + if (IS_ERR(bdev)) { + DMERR("invalidate_vbmeta: could not open device for writing"); + dev_mode = 0; + ret = -ENOENT; + goto failed_to_write; + } + + /* We re-use the same bio to do the write after the read. Need to reset + * it to initialize bio->bi_remaining. + */ + bio_reset(bio); + + rw |= REQ_WRITE; + ret = invalidate_vbmeta_submit(bio, bdev, rw, access_last_sector, page); + if (ret) { + DMERR("invalidate_vbmeta: error writing"); + goto failed_to_submit_write; + } + + DMERR("invalidate_vbmeta: completed."); + ret = 0; +failed_to_submit_write: +failed_to_write: +invalid_header: + __free_page(page); +failed_to_submit_read: + /* Technically, we'll leak a page with the pending bio, but + * we're about to reboot anyway. + */ +failed_to_alloc_page: + bio_put(bio); +failed_bio_alloc: + if (dev_mode) + blkdev_put(bdev, dev_mode); +failed_to_read: + return ret; +} + +void dm_verity_avb_error_handler(void) +{ + dev_t dev; + + DMINFO("AVB error handler called for %s", avb_vbmeta_device); + + if (avb_vbmeta_device[0] == '\0') { + DMERR("avb_vbmeta_device parameter not set"); + goto fail_no_dev; + } + + dev = name_to_dev_t(avb_vbmeta_device); + if (!dev) { + DMERR("No matching partition for device: %s", + avb_vbmeta_device); + goto fail_no_dev; + } + + invalidate_vbmeta(dev); + +fail_no_dev: + ; +} + +static int __init dm_verity_avb_init(void) +{ + DMINFO("AVB error handler initialized with vbmeta device: %s", + avb_vbmeta_device); + return 0; +} + +static void __exit dm_verity_avb_exit(void) +{ +} + +module_init(dm_verity_avb_init); +module_exit(dm_verity_avb_exit); + +MODULE_AUTHOR("David Zeuthen <zeuthen@google.com>"); +MODULE_DESCRIPTION("AVB-specific error handler for dm-verity"); +MODULE_LICENSE("GPL"); + +/* Declare parameter with no module prefix */ +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "androidboot.vbmeta." +module_param_string(device, avb_vbmeta_device, sizeof(avb_vbmeta_device), 0); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index c7e97cf6e7fb..e34cf53bd068 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -233,8 +233,12 @@ out: if (v->mode == DM_VERITY_MODE_LOGGING) return 0; - if (v->mode == DM_VERITY_MODE_RESTART) + if (v->mode == DM_VERITY_MODE_RESTART) { +#ifdef CONFIG_DM_VERITY_AVB + dm_verity_avb_error_handler(); +#endif kernel_restart("dm-verity device corrupted"); + } return 1; } diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 75effca400a3..a90d1d416107 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -136,4 +136,5 @@ extern void verity_io_hints(struct dm_target *ti, struct queue_limits *limits); extern void verity_dtr(struct dm_target *ti); extern int verity_ctr(struct dm_target *ti, unsigned argc, char **argv); extern int verity_map(struct dm_target *ti, struct bio *bio); +extern void dm_verity_avb_error_handler(void); #endif /* DM_VERITY_H */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3384a3eef917..320eb3c4bb6b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1467,11 +1467,65 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) } EXPORT_SYMBOL_GPL(dm_accept_partial_bio); +/* + * Flush current->bio_list when the target map method blocks. + * This fixes deadlocks in snapshot and possibly in other targets. + */ +struct dm_offload { + struct blk_plug plug; + struct blk_plug_cb cb; +}; + +static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule) +{ + struct dm_offload *o = container_of(cb, struct dm_offload, cb); + struct bio_list list; + struct bio *bio; + int i; + + INIT_LIST_HEAD(&o->cb.list); + + if (unlikely(!current->bio_list)) + return; + + for (i = 0; i < 2; i++) { + list = current->bio_list[i]; + bio_list_init(¤t->bio_list[i]); + + while ((bio = bio_list_pop(&list))) { + struct bio_set *bs = bio->bi_pool; + if (unlikely(!bs) || bs == fs_bio_set) { + bio_list_add(¤t->bio_list[i], bio); + continue; + } + + spin_lock(&bs->rescue_lock); + bio_list_add(&bs->rescue_list, bio); + queue_work(bs->rescue_workqueue, &bs->rescue_work); + spin_unlock(&bs->rescue_lock); + } + } +} + +static void dm_offload_start(struct dm_offload *o) +{ + blk_start_plug(&o->plug); + o->cb.callback = flush_current_bio_list; + list_add(&o->cb.list, ¤t->plug->cb_list); +} + +static void dm_offload_end(struct dm_offload *o) +{ + list_del(&o->cb.list); + blk_finish_plug(&o->plug); +} + static void __map_bio(struct dm_target_io *tio) { int r; sector_t sector; struct mapped_device *md; + struct dm_offload o; struct bio *clone = &tio->clone; struct dm_target *ti = tio->ti; @@ -1484,7 +1538,11 @@ static void __map_bio(struct dm_target_io *tio) */ atomic_inc(&tio->io->io_count); sector = clone->bi_iter.bi_sector; + + dm_offload_start(&o); r = ti->type->map(ti, clone); + dm_offload_end(&o); + if (r == DM_MAPIO_REMAPPED) { /* the bio has been remapped so dispatch it */ diff --git a/drivers/md/linear.c b/drivers/md/linear.c index b7fe7e9fc777..6ba3227e29b2 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -52,18 +52,26 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) return conf->disks + lo; } +/* + * In linear_congested() conf->raid_disks is used as a copy of + * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks + * and conf->disks[] are created in linear_conf(), they are always + * consitent with each other, but mddev->raid_disks does not. + */ static int linear_congested(struct mddev *mddev, int bits) { struct linear_conf *conf; int i, ret = 0; - conf = mddev->private; + rcu_read_lock(); + conf = rcu_dereference(mddev->private); - for (i = 0; i < mddev->raid_disks && !ret ; i++) { + for (i = 0; i < conf->raid_disks && !ret ; i++) { struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev); ret |= bdi_congested(&q->backing_dev_info, bits); } + rcu_read_unlock(); return ret; } @@ -143,6 +151,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) conf->disks[i-1].end_sector + conf->disks[i].rdev->sectors; + /* + * conf->raid_disks is copy of mddev->raid_disks. The reason to + * keep a copy of mddev->raid_disks in struct linear_conf is, + * mddev->raid_disks may not be consistent with pointers number of + * conf->disks[] when it is updated in linear_add() and used to + * iterate old conf->disks[] earray in linear_congested(). + * Here conf->raid_disks is always consitent with number of + * pointers in conf->disks[] array, and mddev->private is updated + * with rcu_assign_pointer() in linear_addr(), such race can be + * avoided. + */ + conf->raid_disks = raid_disks; + return conf; out: @@ -195,15 +216,23 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev) if (!newconf) return -ENOMEM; + /* newconf->raid_disks already keeps a copy of * the increased + * value of mddev->raid_disks, WARN_ONCE() is just used to make + * sure of this. It is possible that oldconf is still referenced + * in linear_congested(), therefore kfree_rcu() is used to free + * oldconf until no one uses it anymore. + */ mddev_suspend(mddev); - oldconf = mddev->private; + oldconf = rcu_dereference(mddev->private); mddev->raid_disks++; - mddev->private = newconf; + WARN_ONCE(mddev->raid_disks != newconf->raid_disks, + "copied raid_disks doesn't match mddev->raid_disks"); + rcu_assign_pointer(mddev->private, newconf); md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); set_capacity(mddev->gendisk, mddev->array_sectors); mddev_resume(mddev); revalidate_disk(mddev->gendisk); - kfree(oldconf); + kfree_rcu(oldconf, rcu); return 0; } diff --git a/drivers/md/linear.h b/drivers/md/linear.h index b685ddd7d7f7..8d392e6098b3 100644 --- a/drivers/md/linear.h +++ b/drivers/md/linear.h @@ -10,6 +10,7 @@ struct linear_conf { struct rcu_head rcu; sector_t array_sectors; + int raid_disks; /* a copy of mddev->raid_disks */ struct dev_info disks[0]; }; #endif diff --git a/drivers/md/md.c b/drivers/md/md.c index eff554a12fb4..0a856cb181e9 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1866,7 +1866,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) } sb = page_address(rdev->sb_page); sb->data_size = cpu_to_le64(num_sectors); - sb->super_offset = rdev->sb_start; + sb->super_offset = cpu_to_le64(rdev->sb_start); sb->sb_csum = calc_sb_1_csum(sb); md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, rdev->sb_page); @@ -2273,7 +2273,7 @@ static bool does_sb_need_changing(struct mddev *mddev) /* Check if any mddev parameters have changed */ if ((mddev->dev_sectors != le64_to_cpu(sb->size)) || (mddev->reshape_position != le64_to_cpu(sb->reshape_position)) || - (mddev->layout != le64_to_cpu(sb->layout)) || + (mddev->layout != le32_to_cpu(sb->layout)) || (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) || (mddev->chunk_sectors != le32_to_cpu(sb->chunksize))) return true; diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index b1ced58eb5e1..a1a68209bd36 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -887,8 +887,12 @@ static int find_key(struct ro_spine *s, dm_block_t block, bool find_highest, else *result_key = le64_to_cpu(ro_node(s)->keys[0]); - if (next_block || flags & INTERNAL_NODE) - block = value64(ro_node(s), i); + if (next_block || flags & INTERNAL_NODE) { + if (find_highest) + block = value64(ro_node(s), i); + else + block = value64(ro_node(s), 0); + } } while (flags & INTERNAL_NODE); diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index ebb280a14325..32adf6b4a9c7 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -142,10 +142,23 @@ static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b) static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b) { + int r; + uint32_t old_count; enum allocation_event ev; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); - return sm_ll_dec(&smd->ll, b, &ev); + r = sm_ll_dec(&smd->ll, b, &ev); + if (!r && (ev == SM_FREE)) { + /* + * It's only free if it's also free in the last + * transaction. + */ + r = sm_ll_lookup(&smd->old_ll, b, &old_count); + if (!r && !old_count) + smd->nr_allocated_this_transaction--; + } + + return r; } static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 515554c7365b..f24a9e14021d 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -570,7 +570,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect if (best_dist_disk < 0) { if (is_badblock(rdev, this_sector, sectors, &first_bad, &bad_sectors)) { - if (first_bad < this_sector) + if (first_bad <= this_sector) /* Cannot use this */ continue; best_good_sectors = first_bad - this_sector; @@ -877,7 +877,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio) ((conf->start_next_window < conf->next_resync + RESYNC_SECTORS) && current->bio_list && - !bio_list_empty(current->bio_list))), + (!bio_list_empty(¤t->bio_list[0]) || + !bio_list_empty(¤t->bio_list[1])))), conf->resync_lock); conf->nr_waiting--; } @@ -1087,7 +1088,7 @@ static void make_request(struct mddev *mddev, struct bio * bio) */ DEFINE_WAIT(w); for (;;) { - flush_signals(current); + sigset_t full, old; prepare_to_wait(&conf->wait_barrier, &w, TASK_INTERRUPTIBLE); if (bio_end_sector(bio) <= mddev->suspend_lo || @@ -1096,7 +1097,10 @@ static void make_request(struct mddev *mddev, struct bio * bio) !md_cluster_ops->area_resyncing(mddev, WRITE, bio->bi_iter.bi_sector, bio_end_sector(bio)))) break; + sigfillset(&full); + sigprocmask(SIG_BLOCK, &full, &old); schedule(); + sigprocmask(SIG_SETMASK, &old, NULL); } finish_wait(&conf->wait_barrier, &w); } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ebb0dd612ebd..e5ee4e9e0ea5 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -946,7 +946,8 @@ static void wait_barrier(struct r10conf *conf) !conf->barrier || (conf->nr_pending && current->bio_list && - !bio_list_empty(current->bio_list)), + (!bio_list_empty(¤t->bio_list[0]) || + !bio_list_empty(¤t->bio_list[1]))), conf->resync_lock); conf->nr_waiting--; } @@ -1072,6 +1073,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio) int max_sectors; int sectors; + md_write_start(mddev, bio); + /* * Register the new request and wait if the reconstruction * thread has put up a bar for new requests. @@ -1455,8 +1458,6 @@ static void make_request(struct mddev *mddev, struct bio *bio) return; } - md_write_start(mddev, bio); - do { /* @@ -1477,7 +1478,25 @@ static void make_request(struct mddev *mddev, struct bio *bio) split = bio; } + /* + * If a bio is splitted, the first part of bio will pass + * barrier but the bio is queued in current->bio_list (see + * generic_make_request). If there is a raise_barrier() called + * here, the second part of bio can't pass barrier. But since + * the first part bio isn't dispatched to underlaying disks + * yet, the barrier is never released, hence raise_barrier will + * alays wait. We have a deadlock. + * Note, this only happens in read path. For write path, the + * first part of bio is dispatched in a schedule() call + * (because of blk plug) or offloaded to raid10d. + * Quitting from the function immediately can change the bio + * order queued in bio_list and avoid the deadlock. + */ __make_request(mddev, split); + if (split != bio && bio_data_dir(bio) == READ) { + generic_make_request(bio); + break; + } } while (split != bio); /* In case raid10d snuck in to freeze_array */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7af976934441..8f60520c8392 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2232,6 +2232,10 @@ static int resize_stripes(struct r5conf *conf, int newsize) err = -ENOMEM; mutex_unlock(&conf->cache_size_mutex); + + conf->slab_cache = sc; + conf->active_name = 1-conf->active_name; + /* Step 4, return new stripes to service */ while(!list_empty(&newstripes)) { nsh = list_entry(newstripes.next, struct stripe_head, lru); @@ -2249,8 +2253,6 @@ static int resize_stripes(struct r5conf *conf, int newsize) } /* critical section pass, GFP_NOIO no longer needed */ - conf->slab_cache = sc; - conf->active_name = 1-conf->active_name; if (!err) conf->pool_size = newsize; return err; @@ -5277,12 +5279,15 @@ static void make_request(struct mddev *mddev, struct bio * bi) * userspace, we want an interruptible * wait. */ - flush_signals(current); prepare_to_wait(&conf->wait_for_overlap, &w, TASK_INTERRUPTIBLE); if (logical_sector >= mddev->suspend_lo && logical_sector < mddev->suspend_hi) { + sigset_t full, old; + sigfillset(&full); + sigprocmask(SIG_BLOCK, &full, &old); schedule(); + sigprocmask(SIG_SETMASK, &old, NULL); do_prepare = true; } goto retry; @@ -5816,6 +5821,8 @@ static void raid5_do_work(struct work_struct *work) pr_debug("%d stripes handled\n", handled); spin_unlock_irq(&conf->device_lock); + + async_tx_issue_pending_all(); blk_finish_plug(&plug); pr_debug("--- raid5worker inactive\n"); @@ -7526,12 +7533,10 @@ static void end_reshape(struct r5conf *conf) { if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { - struct md_rdev *rdev; spin_lock_irq(&conf->device_lock); conf->previous_raid_disks = conf->raid_disks; - rdev_for_each(rdev, conf->mddev) - rdev->data_offset = rdev->new_data_offset; + md_finish_reshape(conf->mddev); smp_wmb(); conf->reshape_progress = MaxSector; conf->mddev->reshape_position = MaxSector; diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c index fdffb2f0ded8..107853b0fddd 100644 --- a/drivers/media/dvb-frontends/cxd2841er.c +++ b/drivers/media/dvb-frontends/cxd2841er.c @@ -2678,7 +2678,9 @@ static struct dvb_frontend_ops cxd2841er_dvbt_t2_ops = { FE_CAN_MUTE_TS | FE_CAN_2G_MODULATION, .frequency_min = 42000000, - .frequency_max = 1002000000 + .frequency_max = 1002000000, + .symbol_rate_min = 870000, + .symbol_rate_max = 11700000 }, .init = cxd2841er_init_tc, .sleep = cxd2841er_sleep_tc, diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index fa0b375d1083..1cb286a0afb0 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -650,6 +650,7 @@ config VIDEO_S5K6A3 config VIDEO_S5K4ECGX tristate "Samsung S5K4ECGX sensor support" depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API + select CRC32 ---help--- This is a V4L2 sensor-level driver for Samsung S5K4ECGX 5M camera sensor with an embedded SoC image signal processor. diff --git a/drivers/media/i2c/ov490.c b/drivers/media/i2c/ov490.c index 80dc23a6314b..18fbb68fd439 100644 --- a/drivers/media/i2c/ov490.c +++ b/drivers/media/i2c/ov490.c @@ -47,7 +47,12 @@ #define OV490_MAX_HEIGHT 800 #define MAX_NUM_GPIOS 10 -#define OV490_PIXEL_RATE 192000000 + +/* + * = fvco / pixel_width * num_lanes + * = 804,000,000 / 16 bits * 4 lanes + */ +#define OV490_PIXEL_RATE 201000000 struct ov490_regval { u32 addr; diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c b/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c index 8001cde1db1e..503135a4f47a 100644 --- a/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c +++ b/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c @@ -211,7 +211,7 @@ static int s5c73m3_3a_lock(struct s5c73m3 *state, struct v4l2_ctrl *ctrl) } if ((ctrl->val ^ ctrl->cur.val) & V4L2_LOCK_FOCUS) - ret = s5c73m3_af_run(state, ~af_lock); + ret = s5c73m3_af_run(state, !af_lock); return ret; } diff --git a/drivers/media/pci/cx88/cx88-cards.c b/drivers/media/pci/cx88/cx88-cards.c index 8f2556ec3971..61611d1682d1 100644 --- a/drivers/media/pci/cx88/cx88-cards.c +++ b/drivers/media/pci/cx88/cx88-cards.c @@ -3691,7 +3691,14 @@ struct cx88_core *cx88_core_create(struct pci_dev *pci, int nr) core->nr = nr; sprintf(core->name, "cx88[%d]", core->nr); - core->tvnorm = V4L2_STD_NTSC_M; + /* + * Note: Setting initial standard here would cause first call to + * cx88_set_tvnorm() to return without programming any registers. Leave + * it blank for at this point and it will get set later in + * cx8800_initdev() + */ + core->tvnorm = 0; + core->width = 320; core->height = 240; core->field = V4L2_FIELD_INTERLACED; diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c index aef9acf351f6..abbf5b05b6f5 100644 --- a/drivers/media/pci/cx88/cx88-video.c +++ b/drivers/media/pci/cx88/cx88-video.c @@ -1429,7 +1429,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev, /* initial device configuration */ mutex_lock(&core->lock); - cx88_set_tvnorm(core, core->tvnorm); + cx88_set_tvnorm(core, V4L2_STD_NTSC_M); v4l2_ctrl_handler_setup(&core->video_hdl); v4l2_ctrl_handler_setup(&core->audio_hdl); cx88_video_mux(core, 0); diff --git a/drivers/media/pci/dm1105/Kconfig b/drivers/media/pci/dm1105/Kconfig index 173daf0c0847..14fa7e40f2a6 100644 --- a/drivers/media/pci/dm1105/Kconfig +++ b/drivers/media/pci/dm1105/Kconfig @@ -1,6 +1,6 @@ config DVB_DM1105 tristate "SDMC DM1105 based PCI cards" - depends on DVB_CORE && PCI && I2C + depends on DVB_CORE && PCI && I2C && I2C_ALGOBIT select DVB_PLL if MEDIA_SUBDRV_AUTOSELECT select DVB_STV0299 if MEDIA_SUBDRV_AUTOSELECT select DVB_STV0288 if MEDIA_SUBDRV_AUTOSELECT diff --git a/drivers/media/pci/saa7134/saa7134-i2c.c b/drivers/media/pci/saa7134/saa7134-i2c.c index 8ef6399d794f..bc957528f69f 100644 --- a/drivers/media/pci/saa7134/saa7134-i2c.c +++ b/drivers/media/pci/saa7134/saa7134-i2c.c @@ -355,12 +355,43 @@ static struct i2c_client saa7134_client_template = { /* ----------------------------------------------------------- */ +/* On Medion 7134 reading EEPROM needs DVB-T demod i2c gate open */ +static void saa7134_i2c_eeprom_md7134_gate(struct saa7134_dev *dev) +{ + u8 subaddr = 0x7, dmdregval; + u8 data[2]; + int ret; + struct i2c_msg i2cgatemsg_r[] = { {.addr = 0x08, .flags = 0, + .buf = &subaddr, .len = 1}, + {.addr = 0x08, + .flags = I2C_M_RD, + .buf = &dmdregval, .len = 1} + }; + struct i2c_msg i2cgatemsg_w[] = { {.addr = 0x08, .flags = 0, + .buf = data, .len = 2} }; + + ret = i2c_transfer(&dev->i2c_adap, i2cgatemsg_r, 2); + if ((ret == 2) && (dmdregval & 0x2)) { + pr_debug("%s: DVB-T demod i2c gate was left closed\n", + dev->name); + + data[0] = subaddr; + data[1] = (dmdregval & ~0x2); + if (i2c_transfer(&dev->i2c_adap, i2cgatemsg_w, 1) != 1) + pr_err("%s: EEPROM i2c gate open failure\n", + dev->name); + } +} + static int saa7134_i2c_eeprom(struct saa7134_dev *dev, unsigned char *eedata, int len) { unsigned char buf; int i,err; + if (dev->board == SAA7134_BOARD_MD7134) + saa7134_i2c_eeprom_md7134_gate(dev); + dev->i2c_client.addr = 0xa0 >> 1; buf = 0; if (1 != (err = i2c_master_send(&dev->i2c_client,&buf,1))) { diff --git a/drivers/media/pci/saa7164/saa7164-bus.c b/drivers/media/pci/saa7164/saa7164-bus.c index a18fe5d47238..b4857cd7069e 100644 --- a/drivers/media/pci/saa7164/saa7164-bus.c +++ b/drivers/media/pci/saa7164/saa7164-bus.c @@ -393,11 +393,11 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg, msg_tmp.size = le16_to_cpu((__force __le16)msg_tmp.size); msg_tmp.command = le32_to_cpu((__force __le32)msg_tmp.command); msg_tmp.controlselector = le16_to_cpu((__force __le16)msg_tmp.controlselector); + memcpy(msg, &msg_tmp, sizeof(*msg)); /* No need to update the read positions, because this was a peek */ /* If the caller specifically want to peek, return */ if (peekonly) { - memcpy(msg, &msg_tmp, sizeof(*msg)); goto peekout; } @@ -442,21 +442,15 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg, space_rem = bus->m_dwSizeGetRing - curr_grp; if (space_rem < sizeof(*msg)) { - /* msg wraps around the ring */ - memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, space_rem); - memcpy_fromio((u8 *)msg + space_rem, bus->m_pdwGetRing, - sizeof(*msg) - space_rem); if (buf) memcpy_fromio(buf, bus->m_pdwGetRing + sizeof(*msg) - space_rem, buf_size); } else if (space_rem == sizeof(*msg)) { - memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg)); if (buf) memcpy_fromio(buf, bus->m_pdwGetRing, buf_size); } else { /* Additional data wraps around the ring */ - memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg)); if (buf) { memcpy_fromio(buf, bus->m_pdwGetRing + curr_grp + sizeof(*msg), space_rem - sizeof(*msg)); @@ -469,15 +463,10 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg, } else { /* No wrapping */ - memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg)); if (buf) memcpy_fromio(buf, bus->m_pdwGetRing + curr_grp + sizeof(*msg), buf_size); } - /* Convert from little endian to CPU */ - msg->size = le16_to_cpu((__force __le16)msg->size); - msg->command = le32_to_cpu((__force __le32)msg->command); - msg->controlselector = le16_to_cpu((__force __le16)msg->controlselector); /* Update the read positions, adjusting the ring */ saa7164_writel(bus->m_dwGetReadPos, new_grp); diff --git a/drivers/media/platform/davinci/vpfe_capture.c b/drivers/media/platform/davinci/vpfe_capture.c index 7767e072d623..1f656a3a84b9 100644 --- a/drivers/media/platform/davinci/vpfe_capture.c +++ b/drivers/media/platform/davinci/vpfe_capture.c @@ -1709,27 +1709,9 @@ static long vpfe_param_handler(struct file *file, void *priv, switch (cmd) { case VPFE_CMD_S_CCDC_RAW_PARAMS: + ret = -EINVAL; v4l2_warn(&vpfe_dev->v4l2_dev, - "VPFE_CMD_S_CCDC_RAW_PARAMS: experimental ioctl\n"); - if (ccdc_dev->hw_ops.set_params) { - ret = ccdc_dev->hw_ops.set_params(param); - if (ret) { - v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, - "Error setting parameters in CCDC\n"); - goto unlock_out; - } - ret = vpfe_get_ccdc_image_format(vpfe_dev, - &vpfe_dev->fmt); - if (ret < 0) { - v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, - "Invalid image format at CCDC\n"); - goto unlock_out; - } - } else { - ret = -EINVAL; - v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, - "VPFE_CMD_S_CCDC_RAW_PARAMS not supported\n"); - } + "VPFE_CMD_S_CCDC_RAW_PARAMS not supported\n"); break; default: ret = -ENOTTY; diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c index 4a608cbe0fdb..9c6fc09b88e0 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c @@ -1098,10 +1098,10 @@ static bool s5p_jpeg_parse_hdr(struct s5p_jpeg_q_data *result, struct s5p_jpeg_ctx *ctx) { int c, components = 0, notfound, n_dht = 0, n_dqt = 0; - unsigned int height, width, word, subsampling = 0, sos = 0, sof = 0, - sof_len = 0; - unsigned int dht[S5P_JPEG_MAX_MARKER], dht_len[S5P_JPEG_MAX_MARKER], - dqt[S5P_JPEG_MAX_MARKER], dqt_len[S5P_JPEG_MAX_MARKER]; + unsigned int height = 0, width = 0, word, subsampling = 0; + unsigned int sos = 0, sof = 0, sof_len = 0; + unsigned int dht[S5P_JPEG_MAX_MARKER], dht_len[S5P_JPEG_MAX_MARKER]; + unsigned int dqt[S5P_JPEG_MAX_MARKER], dqt_len[S5P_JPEG_MAX_MARKER]; long length; struct s5p_jpeg_buffer jpeg_buffer; diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c index c8946f98ced4..7727789dbda1 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c @@ -173,6 +173,7 @@ static void s5p_mfc_watchdog_worker(struct work_struct *work) } s5p_mfc_clock_on(); ret = s5p_mfc_init_hw(dev); + s5p_mfc_clock_off(); if (ret) mfc_err("Failed to reinit FW\n"); } diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c index 4bf3e350cd5e..7f8b91019218 100644 --- a/drivers/media/platform/ti-vpe/cal.c +++ b/drivers/media/platform/ti-vpe/cal.c @@ -77,8 +77,6 @@ static const struct v4l2_fract #define CAL_NUM_INPUT 1 #define CAL_NUM_CONTEXT 2 -#define bytes_per_line(pixel, bpp) (ALIGN(pixel * bpp, 16)) - #define reg_read(dev, offset) ioread32(dev->base + offset) #define reg_write(dev, offset, val) iowrite32(val, dev->base + offset) @@ -97,102 +95,103 @@ static const struct v4l2_fract struct cal_fmt { u32 fourcc; u32 code; - u8 depth; + /* Bits per pixel */ + u8 bpp; }; static struct cal_fmt cal_formats[] = { { .fourcc = V4L2_PIX_FMT_YUYV, .code = MEDIA_BUS_FMT_YUYV8_2X8, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_UYVY, .code = MEDIA_BUS_FMT_UYVY8_2X8, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_YVYU, .code = MEDIA_BUS_FMT_YVYU8_2X8, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_VYUY, .code = MEDIA_BUS_FMT_VYUY8_2X8, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_RGB565, /* gggbbbbb rrrrrggg */ .code = MEDIA_BUS_FMT_RGB565_2X8_LE, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_RGB565X, /* rrrrrggg gggbbbbb */ .code = MEDIA_BUS_FMT_RGB565_2X8_BE, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_RGB555, /* gggbbbbb arrrrrgg */ .code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_RGB555X, /* arrrrrgg gggbbbbb */ .code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE, - .depth = 16, + .bpp = 16, }, { .fourcc = V4L2_PIX_FMT_RGB24, /* rgb */ .code = MEDIA_BUS_FMT_RGB888_2X12_LE, - .depth = 24, + .bpp = 24, }, { .fourcc = V4L2_PIX_FMT_BGR24, /* bgr */ .code = MEDIA_BUS_FMT_RGB888_2X12_BE, - .depth = 24, + .bpp = 24, }, { .fourcc = V4L2_PIX_FMT_RGB32, /* argb */ .code = MEDIA_BUS_FMT_ARGB8888_1X32, - .depth = 32, + .bpp = 32, }, { .fourcc = V4L2_PIX_FMT_SBGGR8, .code = MEDIA_BUS_FMT_SBGGR8_1X8, - .depth = 8, + .bpp = 8, }, { .fourcc = V4L2_PIX_FMT_SGBRG8, .code = MEDIA_BUS_FMT_SGBRG8_1X8, - .depth = 8, + .bpp = 8, }, { .fourcc = V4L2_PIX_FMT_SGRBG8, .code = MEDIA_BUS_FMT_SGRBG8_1X8, - .depth = 8, + .bpp = 8, }, { .fourcc = V4L2_PIX_FMT_SRGGB8, .code = MEDIA_BUS_FMT_SRGGB8_1X8, - .depth = 8, + .bpp = 8, }, { .fourcc = V4L2_PIX_FMT_SBGGR10, .code = MEDIA_BUS_FMT_SBGGR10_1X10, - .depth = 16, + .bpp = 10, }, { .fourcc = V4L2_PIX_FMT_SGBRG10, .code = MEDIA_BUS_FMT_SGBRG10_1X10, - .depth = 16, + .bpp = 10, }, { .fourcc = V4L2_PIX_FMT_SGRBG10, .code = MEDIA_BUS_FMT_SGRBG10_1X10, - .depth = 16, + .bpp = 10, }, { .fourcc = V4L2_PIX_FMT_SRGGB10, .code = MEDIA_BUS_FMT_SRGGB10_1X10, - .depth = 16, + .bpp = 10, }, { .fourcc = V4L2_PIX_FMT_SBGGR12, .code = MEDIA_BUS_FMT_SBGGR12_1X12, - .depth = 16, + .bpp = 12, }, { .fourcc = V4L2_PIX_FMT_SGBRG12, .code = MEDIA_BUS_FMT_SGBRG12_1X12, - .depth = 16, + .bpp = 12, }, { .fourcc = V4L2_PIX_FMT_SGRBG12, .code = MEDIA_BUS_FMT_SGRBG12_1X12, - .depth = 16, + .bpp = 12, }, { .fourcc = V4L2_PIX_FMT_SRGGB12, .code = MEDIA_BUS_FMT_SRGGB12_1X12, - .depth = 16, + .bpp = 12, }, }; @@ -609,29 +608,76 @@ static void disable_irqs(struct cal_ctx *ctx) reg_write(ctx->dev, CAL_CSI2_VC_IRQENABLE(1), 0); } -static void csi2_init(struct cal_ctx *ctx) +static void csi2_phy_config(struct cal_ctx *ctx); + +static void csi2_phy_init(struct cal_ctx *ctx) { int i; u32 val; + /* Steps + * 1. Configure D-PHY mode and enable required lanes + * 2. Reset complex IO - Wait for completion of reset + * Note if the external sensor is not sending byte clock, + * the reset will timeout + * 3 Program Stop States + * A. Program THS_TERM, THS_SETTLE, etc... Timings parameters + * in terms of DDR clock periods + * B. Enable stop state transition timeouts + * 4.Force FORCERXMODE + * D. Enable pull down using pad control + * E. Power up PHY + * F. Wait for power up completion + * G. Wait for all enabled lane to reach stop state + * H. Disable pull down using pad control + */ + + /* 1. Configure D-PHY mode and enable required lanes */ + camerarx_phy_enable(ctx); + + /* 2. Reset complex IO - Do not wait for reset completion */ + val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)); + set_field(&val, CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_OPERATIONAL, + CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK); + reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val); + ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x De-assert Complex IO Reset\n", + ctx->csi2_port, + reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port))); + + /* Dummy read to allow SCP to complete */ + val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)); + + /* 3.A. Program Phy Timing Parameters */ + csi2_phy_config(ctx); + + /* 3.B. Program Stop States */ val = reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port)); set_field(&val, CAL_GEN_ENABLE, - CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK); - set_field(&val, CAL_GEN_ENABLE, CAL_CSI2_TIMING_STOP_STATE_X16_IO1_MASK); set_field(&val, CAL_GEN_DISABLE, CAL_CSI2_TIMING_STOP_STATE_X4_IO1_MASK); set_field(&val, 407, CAL_CSI2_TIMING_STOP_STATE_COUNTER_IO1_MASK); reg_write(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port), val); - ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x\n", ctx->csi2_port, + ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x Stop States\n", + ctx->csi2_port, + reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port))); + + /* 4. Force FORCERXMODE */ + val = reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port)); + set_field(&val, CAL_GEN_ENABLE, + CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK); + reg_write(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port), val); + ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x Force RXMODE\n", + ctx->csi2_port, reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port))); + /* E. Power up the PHY using the complex IO */ val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)); - set_field(&val, CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_OPERATIONAL, - CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK); set_field(&val, CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_ON, CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_MASK); reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val); + + /* F. Wait for power up completion */ for (i = 0; i < 10; i++) { if (reg_read_field(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), @@ -640,18 +686,104 @@ static void csi2_init(struct cal_ctx *ctx) break; usleep_range(1000, 1100); } - ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x\n", ctx->csi2_port, - reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port))); + ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Powered UP %s\n", + ctx->csi2_port, + reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)), + (i >= 10) ? "(timeout)" : ""); +} - val = reg_read(ctx->dev, CAL_CTRL); - set_field(&val, CAL_CTRL_BURSTSIZE_BURST128, CAL_CTRL_BURSTSIZE_MASK); - set_field(&val, 0xF, CAL_CTRL_TAGCNT_MASK); - set_field(&val, CAL_CTRL_POSTED_WRITES_NONPOSTED, - CAL_CTRL_POSTED_WRITES_MASK); - set_field(&val, 0xFF, CAL_CTRL_MFLAGL_MASK); - set_field(&val, 0xFF, CAL_CTRL_MFLAGH_MASK); - reg_write(ctx->dev, CAL_CTRL, val); - ctx_dbg(3, ctx, "CAL_CTRL = 0x%08x\n", reg_read(ctx->dev, CAL_CTRL)); +static void csi2_wait_for_phy(struct cal_ctx *ctx) +{ + int i; + + /* Steps + * 2. Wait for completion of reset + * Note if the external sensor is not sending byte clock, + * the reset will timeout + * 4.Force FORCERXMODE + * G. Wait for all enabled lane to reach stop state + * H. Disable pull down using pad control + */ + + /* 2. Wait for reset completion */ + for (i = 0; i < 250; i++) { + if (reg_read_field(ctx->dev, + CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), + CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_MASK) == + CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETCOMPLETED) + break; + usleep_range(1000, 1100); + } + ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Complex IO Reset Done (%d) %s\n", + ctx->csi2_port, + reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)), i, + (i >= 250) ? "(timeout)" : ""); + + /* 4. G. Wait for all enabled lane to reach stop state */ + for (i = 0; i < 10; i++) { + if (reg_read_field(ctx->dev, + CAL_CSI2_TIMING(ctx->csi2_port), + CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK) == + CAL_GEN_DISABLE) + break; + usleep_range(1000, 1100); + } + ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x Stop State Reached %s\n", + ctx->csi2_port, + reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port)), + (i >= 10) ? "(timeout)" : ""); + + ctx_dbg(1, ctx, "CSI2_%d_REG1 = 0x%08x (Bit(31,28) should be set!)\n", + (ctx->csi2_port - 1), reg_read(ctx->cc, CAL_CSI2_PHY_REG1)); +} + +static void csi2_phy_deinit(struct cal_ctx *ctx) +{ + int i; + u32 val; + + /* Power down the PHY using the complex IO */ + val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)); + set_field(&val, CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_OFF, + CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_MASK); + reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val); + + /* Wait for power down completion */ + for (i = 0; i < 10; i++) { + if (reg_read_field(ctx->dev, + CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), + CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_MASK) == + CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_OFF) + break; + usleep_range(1000, 1100); + } + ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Powered Down %s\n", + ctx->csi2_port, + reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)), + (i >= 10) ? "(timeout)" : ""); + + /* Assert Comple IO Reset */ + val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)); + set_field(&val, CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL, + CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK); + reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val); + + /* Wait for power down completion */ + for (i = 0; i < 10; i++) { + if (reg_read_field(ctx->dev, + CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), + CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_MASK) == + CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETONGOING) + break; + usleep_range(1000, 1100); + } + ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Complex IO in Reset (%d) %s\n", + ctx->csi2_port, + reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)), i, + (i >= 10) ? "(timeout)" : ""); + + /* Disable the phy */ + camerarx_phy_disable(ctx); } static void csi2_lane_config(struct cal_ctx *ctx) @@ -722,13 +854,45 @@ static void csi2_ctx_config(struct cal_ctx *ctx) static void pix_proc_config(struct cal_ctx *ctx) { - u32 val; + u32 val, extract, pack; + + switch (ctx->fmt->bpp) { + default: + /* + * If you see this warning then it means that you added + * some new entry in the cal_formats[] array with a different + * bit per pixel values then the one supported below. + * Either add support for the new bpp value below or adjust + * the new entry to use one of the value below. + * + * Instead of failing here just use 8 bpp as a default. + */ + dev_warn_once(&ctx->dev->pdev->dev, + "%s:%d:%s: bpp:%d unsupported! Overwritten with 8.\n", + __FILE__, __LINE__, __func__, ctx->fmt->bpp); + case 8: + extract = CAL_PIX_PROC_EXTRACT_B8; + pack = CAL_PIX_PROC_PACK_B8; + break; + case 10: + extract = CAL_PIX_PROC_EXTRACT_B10_MIPI; + pack = CAL_PIX_PROC_PACK_B16; + break; + case 12: + extract = CAL_PIX_PROC_EXTRACT_B12_MIPI; + pack = CAL_PIX_PROC_PACK_B16; + break; + case 16: + extract = CAL_PIX_PROC_EXTRACT_B16_LE; + pack = CAL_PIX_PROC_PACK_B16; + break; + } val = reg_read(ctx->dev, CAL_PIX_PROC(ctx->csi2_port)); - set_field(&val, CAL_PIX_PROC_EXTRACT_B8, CAL_PIX_PROC_EXTRACT_MASK); + set_field(&val, extract, CAL_PIX_PROC_EXTRACT_MASK); set_field(&val, CAL_PIX_PROC_DPCMD_BYPASS, CAL_PIX_PROC_DPCMD_MASK); set_field(&val, CAL_PIX_PROC_DPCME_BYPASS, CAL_PIX_PROC_DPCME_MASK); - set_field(&val, CAL_PIX_PROC_PACK_B8, CAL_PIX_PROC_PACK_MASK); + set_field(&val, pack, CAL_PIX_PROC_PACK_MASK); set_field(&val, ctx->csi2_port, CAL_PIX_PROC_CPORT_MASK); set_field(&val, CAL_GEN_ENABLE, CAL_PIX_PROC_EN_MASK); reg_write(ctx->dev, CAL_PIX_PROC(ctx->csi2_port), val); @@ -778,6 +942,16 @@ static void cal_wr_dma_config(struct cal_ctx *ctx, reg_write(ctx->dev, CAL_WR_DMA_XSIZE(ctx->csi2_port), val); ctx_dbg(3, ctx, "CAL_WR_DMA_XSIZE(%d) = 0x%08x\n", ctx->csi2_port, reg_read(ctx->dev, CAL_WR_DMA_XSIZE(ctx->csi2_port))); + + val = reg_read(ctx->dev, CAL_CTRL); + set_field(&val, CAL_CTRL_BURSTSIZE_BURST128, CAL_CTRL_BURSTSIZE_MASK); + set_field(&val, 0xF, CAL_CTRL_TAGCNT_MASK); + set_field(&val, CAL_CTRL_POSTED_WRITES_NONPOSTED, + CAL_CTRL_POSTED_WRITES_MASK); + set_field(&val, 0xFF, CAL_CTRL_MFLAGL_MASK); + set_field(&val, 0xFF, CAL_CTRL_MFLAGH_MASK); + reg_write(ctx->dev, CAL_CTRL, val); + ctx_dbg(3, ctx, "CAL_CTRL = 0x%08x\n", reg_read(ctx->dev, CAL_CTRL)); } static void cal_wr_dma_addr(struct cal_ctx *ctx, unsigned int dmaaddr) @@ -791,41 +965,27 @@ static void cal_wr_dma_addr(struct cal_ctx *ctx, unsigned int dmaaddr) #define TCLK_TERM 0 #define TCLK_MISS 1 #define TCLK_SETTLE 14 -#define THS_SETTLE 15 static void csi2_phy_config(struct cal_ctx *ctx) { unsigned int reg0, reg1; unsigned int ths_term, ths_settle; - unsigned int ddrclkperiod_us; + unsigned int csi2_ddrclk_khz; + struct v4l2_of_bus_mipi_csi2 *mipi_csi2 = &ctx->endpoint.bus.mipi_csi2; + u32 num_lanes = mipi_csi2->num_data_lanes; - /* - * THS_TERM: Programmed value = floor(20 ns/DDRClk period) - 2. - */ - ddrclkperiod_us = ctx->external_rate / 2000000; - ddrclkperiod_us = 1000000 / ddrclkperiod_us; - ctx_dbg(1, ctx, "ddrclkperiod_us: %d\n", ddrclkperiod_us); + /* DPHY timing configuration */ + /* CSI-2 is DDR and we only count used lanes. */ + csi2_ddrclk_khz = ctx->external_rate / 1000 + / (2 * num_lanes) * ctx->fmt->bpp; + ctx_dbg(1, ctx, "csi2_ddrclk_khz: %d\n", csi2_ddrclk_khz); - ths_term = 20000 / ddrclkperiod_us; - ths_term = (ths_term >= 2) ? ths_term - 2 : ths_term; + /* THS_TERM: Programmed value = floor(20 ns/DDRClk period) */ + ths_term = 20 * csi2_ddrclk_khz / 1000000; ctx_dbg(1, ctx, "ths_term: %d (0x%02x)\n", ths_term, ths_term); - /* - * THS_SETTLE: Programmed value = floor(176.3 ns/CtrlClk period) - 1. - * Since CtrlClk is fixed at 96Mhz then we get - * ths_settle = floor(176.3 / 10.416) - 1 = 15 - * If we ever switch to a dynamic clock then this code might be useful - * - * unsigned int ctrlclkperiod_us; - * ctrlclkperiod_us = 96000000 / 1000000; - * ctrlclkperiod_us = 1000000 / ctrlclkperiod_us; - * ctx_dbg(1, ctx, "ctrlclkperiod_us: %d\n", ctrlclkperiod_us); - - * ths_settle = 176300 / ctrlclkperiod_us; - * ths_settle = (ths_settle > 1) ? ths_settle - 1 : ths_settle; - */ - - ths_settle = THS_SETTLE; + /* THS_SETTLE: Programmed value = floor(105 ns/DDRClk period) + 4 */ + ths_settle = (105 * csi2_ddrclk_khz / 1000000) + 4; ctx_dbg(1, ctx, "ths_settle: %d (0x%02x)\n", ths_settle, ths_settle); reg0 = reg_read(ctx->cc, CAL_CSI2_PHY_REG0); @@ -1040,6 +1200,8 @@ static int cal_calc_format_size(struct cal_ctx *ctx, const struct cal_fmt *fmt, struct v4l2_format *f) { + u32 bpl; + if (!fmt) { ctx_dbg(3, ctx, "No cal_fmt provided!\n"); return -EINVAL; @@ -1047,8 +1209,10 @@ static int cal_calc_format_size(struct cal_ctx *ctx, v4l_bound_align_image(&f->fmt.pix.width, 48, MAX_WIDTH, 2, &f->fmt.pix.height, 32, MAX_HEIGHT, 0, 0); - f->fmt.pix.bytesperline = bytes_per_line(f->fmt.pix.width, - fmt->depth >> 3); + + bpl = (f->fmt.pix.width * ALIGN(fmt->bpp, 8)) >> 3; + f->fmt.pix.bytesperline = ALIGN(bpl, 16); + f->fmt.pix.sizeimage = f->fmt.pix.height * f->fmt.pix.bytesperline; @@ -1360,17 +1524,14 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count) cal_runtime_get(ctx->dev); - enable_irqs(ctx); - camerarx_phy_enable(ctx); - csi2_init(ctx); - csi2_phy_config(ctx); - csi2_lane_config(ctx); csi2_ctx_config(ctx); pix_proc_config(ctx); cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline, - ctx->v_fmt.fmt.pix.height); - cal_wr_dma_addr(ctx, addr); - csi2_ppi_enable(ctx); + ctx->v_fmt.fmt.pix.height); + csi2_lane_config(ctx); + + enable_irqs(ctx); + csi2_phy_init(ctx); ret = v4l2_subdev_call(ctx->sensor, video, s_stream, 1); if (ret) { @@ -1379,6 +1540,10 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count) goto err; } + csi2_wait_for_phy(ctx); + cal_wr_dma_addr(ctx, addr); + csi2_ppi_enable(ctx); + if (debug >= 4) cal_quickdump_regs(ctx->dev); @@ -1399,11 +1564,12 @@ static void cal_stop_streaming(struct vb2_queue *vq) struct cal_buffer *buf, *tmp; unsigned long flags; - if (v4l2_subdev_call(ctx->sensor, video, s_stream, 0)) - ctx_err(ctx, "stream off failed in subdev\n"); - csi2_ppi_disable(ctx); disable_irqs(ctx); + csi2_phy_deinit(ctx); + + if (v4l2_subdev_call(ctx->sensor, video, s_stream, 0)) + ctx_err(ctx, "stream off failed in subdev\n"); /* Release all active buffers */ spin_lock_irqsave(&ctx->slock, flags); diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index 65f80b8b9f7a..eb9e7feb9b13 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -1629,7 +1629,7 @@ static void imon_incoming_packet(struct imon_context *ictx, if (kc == KEY_KEYBOARD && !ictx->release_code) { ictx->last_keycode = kc; if (!nomouse) { - ictx->pad_mouse = ~(ictx->pad_mouse) & 0x1; + ictx->pad_mouse = !ictx->pad_mouse; dev_dbg(dev, "toggling to %s mode\n", ictx->pad_mouse ? "mouse" : "keyboard"); spin_unlock_irqrestore(&ictx->kc_lock, flags); diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c index a32659fcd266..efc21b1da211 100644 --- a/drivers/media/rc/ir-lirc-codec.c +++ b/drivers/media/rc/ir-lirc-codec.c @@ -254,7 +254,7 @@ static long ir_lirc_ioctl(struct file *filep, unsigned int cmd, return 0; case LIRC_GET_REC_RESOLUTION: - val = dev->rx_resolution; + val = dev->rx_resolution / 1000; break; case LIRC_SET_WIDEBAND_RECEIVER: diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index 2cdb740cde48..f838d9c7ed12 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -1321,8 +1321,8 @@ static int mceusb_dev_probe(struct usb_interface *intf, } } } - if (ep_in == NULL) { - dev_dbg(&intf->dev, "inbound and/or endpoint not found"); + if (!ep_in || !ep_out) { + dev_dbg(&intf->dev, "required endpoints not found\n"); return -ENODEV; } diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c index 317ef63ee789..8d96a22647b3 100644 --- a/drivers/media/tuners/tuner-xc2028.c +++ b/drivers/media/tuners/tuner-xc2028.c @@ -281,6 +281,14 @@ static void free_firmware(struct xc2028_data *priv) int i; tuner_dbg("%s called\n", __func__); + /* free allocated f/w string */ + if (priv->fname != firmware_name) + kfree(priv->fname); + priv->fname = NULL; + + priv->state = XC2028_NO_FIRMWARE; + memset(&priv->cur_fw, 0, sizeof(priv->cur_fw)); + if (!priv->firm) return; @@ -291,9 +299,6 @@ static void free_firmware(struct xc2028_data *priv) priv->firm = NULL; priv->firm_size = 0; - priv->state = XC2028_NO_FIRMWARE; - - memset(&priv->cur_fw, 0, sizeof(priv->cur_fw)); } static int load_all_firmwares(struct dvb_frontend *fe, @@ -884,9 +889,8 @@ read_not_reliable: return 0; fail: - priv->state = XC2028_NO_FIRMWARE; + free_firmware(priv); - memset(&priv->cur_fw, 0, sizeof(priv->cur_fw)); if (retry_count < 8) { msleep(50); retry_count++; @@ -1332,11 +1336,8 @@ static int xc2028_dvb_release(struct dvb_frontend *fe) mutex_lock(&xc2028_list_mutex); /* only perform final cleanup if this is the last instance */ - if (hybrid_tuner_report_instance_count(priv) == 1) { + if (hybrid_tuner_report_instance_count(priv) == 1) free_firmware(priv); - kfree(priv->ctrl.fname); - priv->ctrl.fname = NULL; - } if (priv) hybrid_tuner_release_state(priv); @@ -1399,19 +1400,8 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg) /* * Copy the config data. - * For the firmware name, keep a local copy of the string, - * in order to avoid troubles during device release. */ - kfree(priv->ctrl.fname); - priv->ctrl.fname = NULL; memcpy(&priv->ctrl, p, sizeof(priv->ctrl)); - if (p->fname) { - priv->ctrl.fname = kstrdup(p->fname, GFP_KERNEL); - if (priv->ctrl.fname == NULL) { - rc = -ENOMEM; - goto unlock; - } - } /* * If firmware name changed, frees firmware. As free_firmware will @@ -1426,10 +1416,15 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg) if (priv->state == XC2028_NO_FIRMWARE) { if (!firmware_name[0]) - priv->fname = priv->ctrl.fname; + priv->fname = kstrdup(p->fname, GFP_KERNEL); else priv->fname = firmware_name; + if (!priv->fname) { + rc = -ENOMEM; + goto unlock; + } + rc = request_firmware_nowait(THIS_MODULE, 1, priv->fname, priv->i2c_props.adap->dev.parent, diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c index de4ae5eb4830..10d8a08e36e6 100644 --- a/drivers/media/usb/cx231xx/cx231xx-audio.c +++ b/drivers/media/usb/cx231xx/cx231xx-audio.c @@ -671,10 +671,8 @@ static int cx231xx_audio_init(struct cx231xx *dev) spin_lock_init(&adev->slock); err = snd_pcm_new(card, "Cx231xx Audio", 0, 0, 1, &pcm); - if (err < 0) { - snd_card_free(card); - return err; - } + if (err < 0) + goto err_free_card; snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_cx231xx_pcm_capture); @@ -688,10 +686,9 @@ static int cx231xx_audio_init(struct cx231xx *dev) INIT_WORK(&dev->wq_trigger, audio_trigger); err = snd_card_register(card); - if (err < 0) { - snd_card_free(card); - return err; - } + if (err < 0) + goto err_free_card; + adev->sndcard = card; adev->udev = dev->udev; @@ -701,6 +698,11 @@ static int cx231xx_audio_init(struct cx231xx *dev) hs_config_info[0].interface_info. audio_index + 1]; + if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1) { + err = -ENODEV; + goto err_free_card; + } + adev->end_point_addr = uif->altsetting[0].endpoint[isoc_pipe].desc. bEndpointAddress; @@ -710,13 +712,20 @@ static int cx231xx_audio_init(struct cx231xx *dev) "audio EndPoint Addr 0x%x, Alternate settings: %i\n", adev->end_point_addr, adev->num_alt); adev->alt_max_pkt_size = kmalloc(32 * adev->num_alt, GFP_KERNEL); - - if (adev->alt_max_pkt_size == NULL) - return -ENOMEM; + if (!adev->alt_max_pkt_size) { + err = -ENOMEM; + goto err_free_card; + } for (i = 0; i < adev->num_alt; i++) { - u16 tmp = - le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc. + u16 tmp; + + if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1) { + err = -ENODEV; + goto err_free_pkt_size; + } + + tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc. wMaxPacketSize); adev->alt_max_pkt_size[i] = (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1); @@ -726,6 +735,13 @@ static int cx231xx_audio_init(struct cx231xx *dev) } return 0; + +err_free_pkt_size: + kfree(adev->alt_max_pkt_size); +err_free_card: + snd_card_free(card); + + return err; } static int cx231xx_audio_fini(struct cx231xx *dev) diff --git a/drivers/media/usb/cx231xx/cx231xx-cards.c b/drivers/media/usb/cx231xx/cx231xx-cards.c index 8389c162bc89..2c5f76d588ac 100644 --- a/drivers/media/usb/cx231xx/cx231xx-cards.c +++ b/drivers/media/usb/cx231xx/cx231xx-cards.c @@ -1447,6 +1447,9 @@ static int cx231xx_init_v4l2(struct cx231xx *dev, uif = udev->actconfig->interface[idx]; + if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1) + return -ENODEV; + dev->video_mode.end_point_addr = uif->altsetting[0].endpoint[isoc_pipe].desc.bEndpointAddress; dev->video_mode.num_alt = uif->num_altsetting; @@ -1460,7 +1463,12 @@ static int cx231xx_init_v4l2(struct cx231xx *dev, return -ENOMEM; for (i = 0; i < dev->video_mode.num_alt; i++) { - u16 tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc.wMaxPacketSize); + u16 tmp; + + if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1) + return -ENODEV; + + tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc.wMaxPacketSize); dev->video_mode.alt_max_pkt_size[i] = (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1); dev_dbg(dev->dev, "Alternate setting %i, max size= %i\n", i, @@ -1477,6 +1485,9 @@ static int cx231xx_init_v4l2(struct cx231xx *dev, } uif = udev->actconfig->interface[idx]; + if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1) + return -ENODEV; + dev->vbi_mode.end_point_addr = uif->altsetting[0].endpoint[isoc_pipe].desc. bEndpointAddress; @@ -1493,8 +1504,12 @@ static int cx231xx_init_v4l2(struct cx231xx *dev, return -ENOMEM; for (i = 0; i < dev->vbi_mode.num_alt; i++) { - u16 tmp = - le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe]. + u16 tmp; + + if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1) + return -ENODEV; + + tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe]. desc.wMaxPacketSize); dev->vbi_mode.alt_max_pkt_size[i] = (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1); @@ -1514,6 +1529,9 @@ static int cx231xx_init_v4l2(struct cx231xx *dev, } uif = udev->actconfig->interface[idx]; + if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1) + return -ENODEV; + dev->sliced_cc_mode.end_point_addr = uif->altsetting[0].endpoint[isoc_pipe].desc. bEndpointAddress; @@ -1528,7 +1546,12 @@ static int cx231xx_init_v4l2(struct cx231xx *dev, return -ENOMEM; for (i = 0; i < dev->sliced_cc_mode.num_alt; i++) { - u16 tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe]. + u16 tmp; + + if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1) + return -ENODEV; + + tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe]. desc.wMaxPacketSize); dev->sliced_cc_mode.alt_max_pkt_size[i] = (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1); @@ -1693,6 +1716,11 @@ static int cx231xx_usb_probe(struct usb_interface *interface, } uif = udev->actconfig->interface[idx]; + if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1) { + retval = -ENODEV; + goto err_video_alt; + } + dev->ts1_mode.end_point_addr = uif->altsetting[0].endpoint[isoc_pipe]. desc.bEndpointAddress; @@ -1710,7 +1738,14 @@ static int cx231xx_usb_probe(struct usb_interface *interface, } for (i = 0; i < dev->ts1_mode.num_alt; i++) { - u16 tmp = le16_to_cpu(uif->altsetting[i]. + u16 tmp; + + if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1) { + retval = -ENODEV; + goto err_video_alt; + } + + tmp = le16_to_cpu(uif->altsetting[i]. endpoint[isoc_pipe].desc. wMaxPacketSize); dev->ts1_mode.alt_max_pkt_size[i] = diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c index f5df9eaba04f..9757f35cd5f5 100644 --- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c +++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c @@ -1010,8 +1010,8 @@ EXPORT_SYMBOL(dvb_usbv2_probe); void dvb_usbv2_disconnect(struct usb_interface *intf) { struct dvb_usb_device *d = usb_get_intfdata(intf); - const char *name = d->name; - struct device dev = d->udev->dev; + const char *devname = kstrdup(dev_name(&d->udev->dev), GFP_KERNEL); + const char *drvname = d->name; dev_dbg(&d->udev->dev, "%s: bInterfaceNumber=%d\n", __func__, intf->cur_altsetting->desc.bInterfaceNumber); @@ -1021,8 +1021,9 @@ void dvb_usbv2_disconnect(struct usb_interface *intf) dvb_usbv2_exit(d); - dev_info(&dev, "%s: '%s' successfully deinitialized and disconnected\n", - KBUILD_MODNAME, name); + pr_info("%s: '%s:%s' successfully deinitialized and disconnected\n", + KBUILD_MODNAME, drvname, devname); + kfree(devname); } EXPORT_SYMBOL(dvb_usbv2_disconnect); diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c index ab58f0b9da5c..d1b4b729e814 100644 --- a/drivers/media/usb/dvb-usb/dib0700_core.c +++ b/drivers/media/usb/dvb-usb/dib0700_core.c @@ -783,6 +783,9 @@ int dib0700_rc_setup(struct dvb_usb_device *d, struct usb_interface *intf) /* Starting in firmware 1.20, the RC info is provided on a bulk pipe */ + if (intf->altsetting[0].desc.bNumEndpoints < rc_ep + 1) + return -ENODEV; + purb = usb_alloc_urb(0, GFP_KERNEL); if (purb == NULL) { err("rc usb alloc urb failed"); diff --git a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c index 733a7ff7b207..caad3b5c01ad 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c @@ -35,42 +35,51 @@ static int usb_cypress_writemem(struct usb_device *udev,u16 addr,u8 *data, u8 le int usb_cypress_load_firmware(struct usb_device *udev, const struct firmware *fw, int type) { - struct hexline hx; - u8 reset; - int ret,pos=0; + struct hexline *hx; + u8 *buf; + int ret, pos = 0; + u16 cpu_cs_register = cypress[type].cpu_cs_register; + + buf = kmalloc(sizeof(*hx), GFP_KERNEL); + if (!buf) + return -ENOMEM; + hx = (struct hexline *)buf; /* stop the CPU */ - reset = 1; - if ((ret = usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1)) != 1) + buf[0] = 1; + if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1) err("could not stop the USB controller CPU."); - while ((ret = dvb_usb_get_hexline(fw,&hx,&pos)) > 0) { - deb_fw("writing to address 0x%04x (buffer: 0x%02x %02x)\n",hx.addr,hx.len,hx.chk); - ret = usb_cypress_writemem(udev,hx.addr,hx.data,hx.len); + while ((ret = dvb_usb_get_hexline(fw, hx, &pos)) > 0) { + deb_fw("writing to address 0x%04x (buffer: 0x%02x %02x)\n", hx->addr, hx->len, hx->chk); + ret = usb_cypress_writemem(udev, hx->addr, hx->data, hx->len); - if (ret != hx.len) { + if (ret != hx->len) { err("error while transferring firmware " "(transferred size: %d, block size: %d)", - ret,hx.len); + ret, hx->len); ret = -EINVAL; break; } } if (ret < 0) { err("firmware download failed at %d with %d",pos,ret); + kfree(buf); return ret; } if (ret == 0) { /* restart the CPU */ - reset = 0; - if (ret || usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1) != 1) { + buf[0] = 0; + if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1) { err("could not restart the USB controller CPU."); ret = -EINVAL; } } else ret = -EIO; + kfree(buf); + return ret; } EXPORT_SYMBOL(usb_cypress_load_firmware); diff --git a/drivers/media/usb/dvb-usb/ttusb2.c b/drivers/media/usb/dvb-usb/ttusb2.c index f10717311e05..dd93c2c8fea9 100644 --- a/drivers/media/usb/dvb-usb/ttusb2.c +++ b/drivers/media/usb/dvb-usb/ttusb2.c @@ -78,6 +78,9 @@ static int ttusb2_msg(struct dvb_usb_device *d, u8 cmd, u8 *s, *r = NULL; int ret = 0; + if (4 + rlen > 64) + return -EIO; + s = kzalloc(wlen+4, GFP_KERNEL); if (!s) return -ENOMEM; @@ -381,6 +384,22 @@ static int ttusb2_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num write_read = i+1 < num && (msg[i+1].flags & I2C_M_RD); read = msg[i].flags & I2C_M_RD; + if (3 + msg[i].len > sizeof(obuf)) { + err("i2c wr len=%d too high", msg[i].len); + break; + } + if (write_read) { + if (3 + msg[i+1].len > sizeof(ibuf)) { + err("i2c rd len=%d too high", msg[i+1].len); + break; + } + } else if (read) { + if (3 + msg[i].len > sizeof(ibuf)) { + err("i2c rd len=%d too high", msg[i].len); + break; + } + } + obuf[0] = (msg[i].addr << 1) | (write_read | read); if (read) obuf[1] = 0; diff --git a/drivers/media/usb/gspca/konica.c b/drivers/media/usb/gspca/konica.c index 0712b1bc90b4..0f6d57fbf91b 100644 --- a/drivers/media/usb/gspca/konica.c +++ b/drivers/media/usb/gspca/konica.c @@ -188,6 +188,9 @@ static int sd_start(struct gspca_dev *gspca_dev) return -EIO; } + if (alt->desc.bNumEndpoints < 2) + return -ENODEV; + packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize); n = gspca_dev->cam.cam_mode[gspca_dev->curr_mode].priv; diff --git a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c index e1907cd0c3b7..7613d1fee104 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c @@ -123,15 +123,10 @@ int pvr2_eeprom_analyze(struct pvr2_hdw *hdw) memset(&tvdata,0,sizeof(tvdata)); eeprom = pvr2_eeprom_fetch(hdw); - if (!eeprom) return -EINVAL; - - { - struct i2c_client fake_client; - /* Newer version expects a useless client interface */ - fake_client.addr = hdw->eeprom_addr; - fake_client.adapter = &hdw->i2c_adap; - tveeprom_hauppauge_analog(&fake_client,&tvdata,eeprom); - } + if (!eeprom) + return -EINVAL; + + tveeprom_hauppauge_analog(NULL, &tvdata, eeprom); trace_eeprom("eeprom assumed v4l tveeprom module"); trace_eeprom("eeprom direct call results:"); diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c index c945e4c2fbd4..ec30a004f319 100644 --- a/drivers/media/usb/siano/smsusb.c +++ b/drivers/media/usb/siano/smsusb.c @@ -200,22 +200,30 @@ static int smsusb_start_streaming(struct smsusb_device_t *dev) static int smsusb_sendrequest(void *context, void *buffer, size_t size) { struct smsusb_device_t *dev = (struct smsusb_device_t *) context; - struct sms_msg_hdr *phdr = (struct sms_msg_hdr *) buffer; - int dummy; + struct sms_msg_hdr *phdr; + int dummy, ret; if (dev->state != SMSUSB_ACTIVE) { pr_debug("Device not active yet\n"); return -ENOENT; } + phdr = kmalloc(size, GFP_KERNEL); + if (!phdr) + return -ENOMEM; + memcpy(phdr, buffer, size); + pr_debug("sending %s(%d) size: %d\n", smscore_translate_msg(phdr->msg_type), phdr->msg_type, phdr->msg_length); smsendian_handle_tx_message((struct sms_msg_data *) phdr); - smsendian_handle_message_header((struct sms_msg_hdr *)buffer); - return usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2), - buffer, size, &dummy, 1000); + smsendian_handle_message_header((struct sms_msg_hdr *)phdr); + ret = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2), + phdr, size, &dummy, 1000); + + kfree(phdr); + return ret; } static char *smsusb1_fw_lkup[] = { diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c index d1dc1a198e3e..91d709efef7a 100644 --- a/drivers/media/usb/usbvision/usbvision-video.c +++ b/drivers/media/usb/usbvision/usbvision-video.c @@ -1523,7 +1523,14 @@ static int usbvision_probe(struct usb_interface *intf, } for (i = 0; i < usbvision->num_alt; i++) { - u16 tmp = le16_to_cpu(uif->altsetting[i].endpoint[1].desc. + u16 tmp; + + if (uif->altsetting[i].desc.bNumEndpoints < 2) { + ret = -ENODEV; + goto err_pkt; + } + + tmp = le16_to_cpu(uif->altsetting[i].endpoint[1].desc. wMaxPacketSize); usbvision->alt_max_pkt_size[i] = (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1); diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 5cefca95734e..885f689ac870 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -1595,6 +1595,114 @@ static const char *uvc_print_chain(struct uvc_video_chain *chain) return buffer; } +static struct uvc_video_chain *uvc_alloc_chain(struct uvc_device *dev) +{ + struct uvc_video_chain *chain; + + chain = kzalloc(sizeof(*chain), GFP_KERNEL); + if (chain == NULL) + return NULL; + + INIT_LIST_HEAD(&chain->entities); + mutex_init(&chain->ctrl_mutex); + chain->dev = dev; + v4l2_prio_init(&chain->prio); + + return chain; +} + +/* + * Fallback heuristic for devices that don't connect units and terminals in a + * valid chain. + * + * Some devices have invalid baSourceID references, causing uvc_scan_chain() + * to fail, but if we just take the entities we can find and put them together + * in the most sensible chain we can think of, turns out they do work anyway. + * Note: This heuristic assumes there is a single chain. + * + * At the time of writing, devices known to have such a broken chain are + * - Acer Integrated Camera (5986:055a) + * - Realtek rtl157a7 (0bda:57a7) + */ +static int uvc_scan_fallback(struct uvc_device *dev) +{ + struct uvc_video_chain *chain; + struct uvc_entity *iterm = NULL; + struct uvc_entity *oterm = NULL; + struct uvc_entity *entity; + struct uvc_entity *prev; + + /* + * Start by locating the input and output terminals. We only support + * devices with exactly one of each for now. + */ + list_for_each_entry(entity, &dev->entities, list) { + if (UVC_ENTITY_IS_ITERM(entity)) { + if (iterm) + return -EINVAL; + iterm = entity; + } + + if (UVC_ENTITY_IS_OTERM(entity)) { + if (oterm) + return -EINVAL; + oterm = entity; + } + } + + if (iterm == NULL || oterm == NULL) + return -EINVAL; + + /* Allocate the chain and fill it. */ + chain = uvc_alloc_chain(dev); + if (chain == NULL) + return -ENOMEM; + + if (uvc_scan_chain_entity(chain, oterm) < 0) + goto error; + + prev = oterm; + + /* + * Add all Processing and Extension Units with two pads. The order + * doesn't matter much, use reverse list traversal to connect units in + * UVC descriptor order as we build the chain from output to input. This + * leads to units appearing in the order meant by the manufacturer for + * the cameras known to require this heuristic. + */ + list_for_each_entry_reverse(entity, &dev->entities, list) { + if (entity->type != UVC_VC_PROCESSING_UNIT && + entity->type != UVC_VC_EXTENSION_UNIT) + continue; + + if (entity->num_pads != 2) + continue; + + if (uvc_scan_chain_entity(chain, entity) < 0) + goto error; + + prev->baSourceID[0] = entity->id; + prev = entity; + } + + if (uvc_scan_chain_entity(chain, iterm) < 0) + goto error; + + prev->baSourceID[0] = iterm->id; + + list_add_tail(&chain->list, &dev->chains); + + uvc_trace(UVC_TRACE_PROBE, + "Found a video chain by fallback heuristic (%s).\n", + uvc_print_chain(chain)); + + return 0; + +error: + kfree(chain); + return -EINVAL; +} + /* * Scan the device for video chains and register video devices. * @@ -1617,15 +1725,10 @@ static int uvc_scan_device(struct uvc_device *dev) if (term->chain.next || term->chain.prev) continue; - chain = kzalloc(sizeof(*chain), GFP_KERNEL); + chain = uvc_alloc_chain(dev); if (chain == NULL) return -ENOMEM; - INIT_LIST_HEAD(&chain->entities); - mutex_init(&chain->ctrl_mutex); - chain->dev = dev; - v4l2_prio_init(&chain->prio); - term->flags |= UVC_ENTITY_FLAG_DEFAULT; if (uvc_scan_chain(chain, term) < 0) { @@ -1639,6 +1742,9 @@ static int uvc_scan_device(struct uvc_device *dev) list_add_tail(&chain->list, &dev->chains); } + if (list_empty(&dev->chains)) + uvc_scan_fallback(dev); + if (list_empty(&dev->chains)) { uvc_printk(KERN_INFO, "No valid video chain found.\n"); return -1; diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c index cfb868a48b5f..ff6feff21e94 100644 --- a/drivers/media/usb/uvc/uvc_queue.c +++ b/drivers/media/usb/uvc/uvc_queue.c @@ -416,7 +416,7 @@ struct uvc_buffer *uvc_queue_next_buffer(struct uvc_video_queue *queue, nextbuf = NULL; spin_unlock_irqrestore(&queue->irqlock, flags); - buf->state = buf->error ? VB2_BUF_STATE_ERROR : UVC_BUF_STATE_DONE; + buf->state = buf->error ? UVC_BUF_STATE_ERROR : UVC_BUF_STATE_DONE; vb2_set_plane_payload(&buf->buf.vb2_buf, 0, buf->bytesused); vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE); diff --git a/drivers/media/usb/zr364xx/zr364xx.c b/drivers/media/usb/zr364xx/zr364xx.c index 7433ba5c4bad..fd6a3b36208e 100644 --- a/drivers/media/usb/zr364xx/zr364xx.c +++ b/drivers/media/usb/zr364xx/zr364xx.c @@ -604,6 +604,14 @@ static int zr364xx_read_video_callback(struct zr364xx_camera *cam, ptr = pdest = frm->lpvbits; if (frm->ulState == ZR364XX_READ_IDLE) { + if (purb->actual_length < 128) { + /* header incomplete */ + dev_info(&cam->udev->dev, + "%s: buffer (%d bytes) too small to hold jpeg header. Discarding.\n", + __func__, purb->actual_length); + return -EINVAL; + } + frm->ulState = ZR364XX_READ_FRAME; frm->cur_size = 0; diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index 47f37683893a..3dc9ed2e0774 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -793,7 +793,7 @@ EXPORT_SYMBOL_GPL(vb2_core_create_bufs); */ void *vb2_plane_vaddr(struct vb2_buffer *vb, unsigned int plane_no) { - if (plane_no > vb->num_planes || !vb->planes[plane_no].mem_priv) + if (plane_no >= vb->num_planes || !vb->planes[plane_no].mem_priv) return NULL; return call_ptr_memop(vb, vaddr, vb->planes[plane_no].mem_priv); diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 9b9301b5efaa..8b05b4f86e1b 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1164,6 +1164,20 @@ config MFD_TI_LP873X This driver can also be built as a module. If so, the module will be called lp873x. +config MFD_TI_LP87565 + tristate "TI LP87565 Power Management IC" + depends on I2C && OF + select MFD_CORE + select REGMAP_I2C + help + If you say yes here then you get support for the LP87565 series of + Power Management Integrated Circuits (PMIC). + These include voltage regulators, thermal protection, configurable + General Purpose Outputs (GPO) that are used in portable devices. + + This driver can also be built as a module. If so, the module + will be called lp87565. + config MFD_TPS65218 tristate "TI TPS65218 Power Management chips" depends on I2C diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index ccec2de3e9d2..03bb5c5dc87d 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_HTC_PASIC3) += htc-pasic3.o obj-$(CONFIG_HTC_I2CPLD) += htc-i2cpld.o obj-$(CONFIG_MFD_TI_LP873X) += lp873x.o +obj-$(CONFIG_MFD_TI_LP87565) += lp87565.o obj-$(CONFIG_MFD_DAVINCI_VOICECODEC) += davinci_voicecodec.o obj-$(CONFIG_MFD_DM355EVM_MSP) += dm355evm_msp.o diff --git a/drivers/mfd/lp87565.c b/drivers/mfd/lp87565.c new file mode 100644 index 000000000000..340ad0c63744 --- /dev/null +++ b/drivers/mfd/lp87565.c @@ -0,0 +1,100 @@ +/* + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * Author: Keerthy <j-keerthy@ti.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + */ + +#include <linux/interrupt.h> +#include <linux/mfd/core.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regmap.h> + +#include <linux/mfd/lp87565.h> + +static const struct regmap_config lp87565_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = LP87565_REG_MAX, +}; + +static const struct mfd_cell lp87565_cells[] = { + { .name = "lp87565-q1-regulator", }, + { .name = "lp87565-q1-gpio", }, +}; + +static const struct of_device_id of_lp87565_match_table[] = { + { .compatible = "ti,lp87565", }, + { + .compatible = "ti,lp87565-q1", + .data = (void *)LP87565_DEVICE_TYPE_LP87565_Q1, + }, + {} +}; +MODULE_DEVICE_TABLE(of, of_lp87565_match_table); + +static int lp87565_probe(struct i2c_client *client, + const struct i2c_device_id *ids) +{ + struct lp87565 *lp87565; + const struct of_device_id *of_id; + int ret; + unsigned int otpid; + + lp87565 = devm_kzalloc(&client->dev, sizeof(*lp87565), GFP_KERNEL); + if (!lp87565) + return -ENOMEM; + + lp87565->dev = &client->dev; + + lp87565->regmap = devm_regmap_init_i2c(client, &lp87565_regmap_config); + if (IS_ERR(lp87565->regmap)) { + ret = PTR_ERR(lp87565->regmap); + dev_err(lp87565->dev, + "Failed to initialize register map: %d\n", ret); + return ret; + } + + ret = regmap_read(lp87565->regmap, LP87565_REG_OTP_REV, &otpid); + if (ret) { + dev_err(lp87565->dev, "Failed to read OTP ID\n"); + return ret; + } + + lp87565->rev = otpid & LP87565_OTP_REV_OTP_ID; + + of_id = of_match_device(of_lp87565_match_table, &client->dev); + if (of_id) + lp87565->dev_type = (enum lp87565_device_type)of_id->data; + + i2c_set_clientdata(client, lp87565); + + ret = mfd_add_devices(lp87565->dev, PLATFORM_DEVID_AUTO, lp87565_cells, + ARRAY_SIZE(lp87565_cells), NULL, 0, NULL); + + return ret; +} + +static const struct i2c_device_id lp87565_id_table[] = { + { "lp87565-q1", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(i2c, lp87565_id_table); + +static struct i2c_driver lp87565_driver = { + .driver = { + .name = "lp87565", + .of_match_table = of_lp87565_match_table, + }, + .probe = lp87565_probe, + .id_table = lp87565_id_table, +}; +module_i2c_driver(lp87565_driver); + +MODULE_AUTHOR("J Keerthy <j-keerthy@ti.com>"); +MODULE_DESCRIPTION("lp87565 chip family Multi-Function Device driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c index c30290f33430..fe51e9709210 100644 --- a/drivers/mfd/omap-usb-tll.c +++ b/drivers/mfd/omap-usb-tll.c @@ -375,8 +375,8 @@ int omap_tll_init(struct usbhs_omap_platform_data *pdata) * and use SDR Mode */ reg &= ~(OMAP_TLL_CHANNEL_CONF_UTMIAUTOIDLE - | OMAP_TLL_CHANNEL_CONF_ULPINOBITSTUFF | OMAP_TLL_CHANNEL_CONF_ULPIDDRMODE); + reg |= OMAP_TLL_CHANNEL_CONF_ULPINOBITSTUFF; } else if (pdata->port_mode[i] == OMAP_EHCI_PORT_MODE_HSIC) { /* diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index e5e0be9b01dd..63e564cf3bf5 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -525,11 +525,13 @@ config VEXPRESS_SYSCFG bus. System Configuration interface is one of the possible means of generating transactions on this bus. -config UID_CPUTIME - bool "Per-UID cpu time statistics" +config UID_SYS_STATS + bool "Per-UID statistics" depends on PROFILING help Per UID based cpu time statistics exported to /proc/uid_cputime + Per UID based io statistics exported to /proc/uid_io + Per UID based procstat control in /proc/uid_procstat config MEMORY_STATE_TIME tristate "Memory freq/bandwidth time statistics" diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 3b7567f940ec..7eb91c62b9fc 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -56,6 +56,6 @@ obj-$(CONFIG_GENWQE) += genwqe/ obj-$(CONFIG_ECHO) += echo/ obj-$(CONFIG_VEXPRESS_SYSCFG) += vexpress-syscfg.o obj-$(CONFIG_CXL_BASE) += cxl/ -obj-$(CONFIG_UID_CPUTIME) += uid_cputime.o +obj-$(CONFIG_UID_SYS_STATS) += uid_sys_stats.o obj-$(CONFIG_MEMORY_STATE_TIME) += memory_state_time.o obj-$(CONFIG_PCI_ENDPOINT_TEST) += pci_endpoint_test.o diff --git a/drivers/misc/c2port/c2port-duramar2150.c b/drivers/misc/c2port/c2port-duramar2150.c index 5484301d57d9..3dc61ea7dc64 100644 --- a/drivers/misc/c2port/c2port-duramar2150.c +++ b/drivers/misc/c2port/c2port-duramar2150.c @@ -129,8 +129,8 @@ static int __init duramar2150_c2port_init(void) duramar2150_c2port_dev = c2port_device_register("uc", &duramar2150_c2port_ops, NULL); - if (!duramar2150_c2port_dev) { - ret = -ENODEV; + if (IS_ERR(duramar2150_c2port_dev)) { + ret = PTR_ERR(duramar2150_c2port_dev); goto free_region; } diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c index 783337d22f36..10a02934bfc0 100644 --- a/drivers/misc/cxl/file.c +++ b/drivers/misc/cxl/file.c @@ -158,11 +158,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx, /* Do this outside the status_mutex to avoid a circular dependency with * the locking in cxl_mmap_fault() */ - if (copy_from_user(&work, uwork, - sizeof(struct cxl_ioctl_start_work))) { - rc = -EFAULT; - goto out; - } + if (copy_from_user(&work, uwork, sizeof(work))) + return -EFAULT; mutex_lock(&ctx->status_mutex); if (ctx->status != OPENED) { diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index 65fed7146e9b..cc91f7b3d90c 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -375,6 +375,7 @@ int enclosure_add_device(struct enclosure_device *edev, int component, struct device *dev) { struct enclosure_component *cdev; + int err; if (!edev || component >= edev->components) return -EINVAL; @@ -384,12 +385,17 @@ int enclosure_add_device(struct enclosure_device *edev, int component, if (cdev->dev == dev) return -EEXIST; - if (cdev->dev) + if (cdev->dev) { enclosure_remove_links(cdev); - - put_device(cdev->dev); + put_device(cdev->dev); + } cdev->dev = get_device(dev); - return enclosure_add_links(cdev); + err = enclosure_add_links(cdev); + if (err) { + put_device(cdev->dev); + cdev->dev = NULL; + } + return err; } EXPORT_SYMBOL_GPL(enclosure_add_device); diff --git a/drivers/misc/uid_cputime.c b/drivers/misc/uid_cputime.c deleted file mode 100644 index c1ad5246f564..000000000000 --- a/drivers/misc/uid_cputime.c +++ /dev/null @@ -1,240 +0,0 @@ -/* drivers/misc/uid_cputime.c - * - * Copyright (C) 2014 - 2015 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#include <linux/atomic.h> -#include <linux/err.h> -#include <linux/hashtable.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/proc_fs.h> -#include <linux/profile.h> -#include <linux/sched.h> -#include <linux/seq_file.h> -#include <linux/slab.h> -#include <linux/uaccess.h> - -#define UID_HASH_BITS 10 -DECLARE_HASHTABLE(hash_table, UID_HASH_BITS); - -static DEFINE_MUTEX(uid_lock); -static struct proc_dir_entry *parent; - -struct uid_entry { - uid_t uid; - cputime_t utime; - cputime_t stime; - cputime_t active_utime; - cputime_t active_stime; - struct hlist_node hash; -}; - -static struct uid_entry *find_uid_entry(uid_t uid) -{ - struct uid_entry *uid_entry; - hash_for_each_possible(hash_table, uid_entry, hash, uid) { - if (uid_entry->uid == uid) - return uid_entry; - } - return NULL; -} - -static struct uid_entry *find_or_register_uid(uid_t uid) -{ - struct uid_entry *uid_entry; - - uid_entry = find_uid_entry(uid); - if (uid_entry) - return uid_entry; - - uid_entry = kzalloc(sizeof(struct uid_entry), GFP_ATOMIC); - if (!uid_entry) - return NULL; - - uid_entry->uid = uid; - - hash_add(hash_table, &uid_entry->hash, uid); - - return uid_entry; -} - -static int uid_stat_show(struct seq_file *m, void *v) -{ - struct uid_entry *uid_entry; - struct task_struct *task, *temp; - cputime_t utime; - cputime_t stime; - unsigned long bkt; - - mutex_lock(&uid_lock); - - hash_for_each(hash_table, bkt, uid_entry, hash) { - uid_entry->active_stime = 0; - uid_entry->active_utime = 0; - } - - read_lock(&tasklist_lock); - do_each_thread(temp, task) { - uid_entry = find_or_register_uid(from_kuid_munged( - current_user_ns(), task_uid(task))); - if (!uid_entry) { - read_unlock(&tasklist_lock); - mutex_unlock(&uid_lock); - pr_err("%s: failed to find the uid_entry for uid %d\n", - __func__, from_kuid_munged(current_user_ns(), - task_uid(task))); - return -ENOMEM; - } - task_cputime_adjusted(task, &utime, &stime); - uid_entry->active_utime += utime; - uid_entry->active_stime += stime; - } while_each_thread(temp, task); - read_unlock(&tasklist_lock); - - hash_for_each(hash_table, bkt, uid_entry, hash) { - cputime_t total_utime = uid_entry->utime + - uid_entry->active_utime; - cputime_t total_stime = uid_entry->stime + - uid_entry->active_stime; - seq_printf(m, "%d: %llu %llu\n", uid_entry->uid, - (unsigned long long)jiffies_to_msecs( - cputime_to_jiffies(total_utime)) * USEC_PER_MSEC, - (unsigned long long)jiffies_to_msecs( - cputime_to_jiffies(total_stime)) * USEC_PER_MSEC); - } - - mutex_unlock(&uid_lock); - return 0; -} - -static int uid_stat_open(struct inode *inode, struct file *file) -{ - return single_open(file, uid_stat_show, PDE_DATA(inode)); -} - -static const struct file_operations uid_stat_fops = { - .open = uid_stat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int uid_remove_open(struct inode *inode, struct file *file) -{ - return single_open(file, NULL, NULL); -} - -static ssize_t uid_remove_write(struct file *file, - const char __user *buffer, size_t count, loff_t *ppos) -{ - struct uid_entry *uid_entry; - struct hlist_node *tmp; - char uids[128]; - char *start_uid, *end_uid = NULL; - long int uid_start = 0, uid_end = 0; - - if (count >= sizeof(uids)) - count = sizeof(uids) - 1; - - if (copy_from_user(uids, buffer, count)) - return -EFAULT; - - uids[count] = '\0'; - end_uid = uids; - start_uid = strsep(&end_uid, "-"); - - if (!start_uid || !end_uid) - return -EINVAL; - - if (kstrtol(start_uid, 10, &uid_start) != 0 || - kstrtol(end_uid, 10, &uid_end) != 0) { - return -EINVAL; - } - mutex_lock(&uid_lock); - - for (; uid_start <= uid_end; uid_start++) { - hash_for_each_possible_safe(hash_table, uid_entry, tmp, - hash, (uid_t)uid_start) { - if (uid_start == uid_entry->uid) { - hash_del(&uid_entry->hash); - kfree(uid_entry); - } - } - } - - mutex_unlock(&uid_lock); - return count; -} - -static const struct file_operations uid_remove_fops = { - .open = uid_remove_open, - .release = single_release, - .write = uid_remove_write, -}; - -static int process_notifier(struct notifier_block *self, - unsigned long cmd, void *v) -{ - struct task_struct *task = v; - struct uid_entry *uid_entry; - cputime_t utime, stime; - uid_t uid; - - if (!task) - return NOTIFY_OK; - - mutex_lock(&uid_lock); - uid = from_kuid_munged(current_user_ns(), task_uid(task)); - uid_entry = find_or_register_uid(uid); - if (!uid_entry) { - pr_err("%s: failed to find uid %d\n", __func__, uid); - goto exit; - } - - task_cputime_adjusted(task, &utime, &stime); - uid_entry->utime += utime; - uid_entry->stime += stime; - -exit: - mutex_unlock(&uid_lock); - return NOTIFY_OK; -} - -static struct notifier_block process_notifier_block = { - .notifier_call = process_notifier, -}; - -static int __init proc_uid_cputime_init(void) -{ - hash_init(hash_table); - - parent = proc_mkdir("uid_cputime", NULL); - if (!parent) { - pr_err("%s: failed to create proc entry\n", __func__); - return -ENOMEM; - } - - proc_create_data("remove_uid_range", S_IWUGO, parent, &uid_remove_fops, - NULL); - - proc_create_data("show_uid_stat", S_IRUGO, parent, &uid_stat_fops, - NULL); - - profile_event_register(PROFILE_TASK_EXIT, &process_notifier_block); - - return 0; -} - -early_initcall(proc_uid_cputime_init); diff --git a/drivers/misc/uid_sys_stats.c b/drivers/misc/uid_sys_stats.c new file mode 100644 index 000000000000..ad21276c8d9e --- /dev/null +++ b/drivers/misc/uid_sys_stats.c @@ -0,0 +1,505 @@ +/* drivers/misc/uid_cputime.c + * + * Copyright (C) 2014 - 2015 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/atomic.h> +#include <linux/err.h> +#include <linux/hashtable.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/proc_fs.h> +#include <linux/profile.h> +#include <linux/rtmutex.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + +#define UID_HASH_BITS 10 +DECLARE_HASHTABLE(hash_table, UID_HASH_BITS); + +static DEFINE_RT_MUTEX(uid_lock); +static struct proc_dir_entry *cpu_parent; +static struct proc_dir_entry *io_parent; +static struct proc_dir_entry *proc_parent; + +struct io_stats { + u64 read_bytes; + u64 write_bytes; + u64 rchar; + u64 wchar; + u64 fsync; +}; + +#define UID_STATE_FOREGROUND 0 +#define UID_STATE_BACKGROUND 1 +#define UID_STATE_BUCKET_SIZE 2 + +#define UID_STATE_TOTAL_CURR 2 +#define UID_STATE_TOTAL_LAST 3 +#define UID_STATE_SIZE 4 + +struct uid_entry { + uid_t uid; + cputime_t utime; + cputime_t stime; + cputime_t active_utime; + cputime_t active_stime; + int state; + struct io_stats io[UID_STATE_SIZE]; + struct hlist_node hash; +}; + +static struct uid_entry *find_uid_entry(uid_t uid) +{ + struct uid_entry *uid_entry; + hash_for_each_possible(hash_table, uid_entry, hash, uid) { + if (uid_entry->uid == uid) + return uid_entry; + } + return NULL; +} + +static struct uid_entry *find_or_register_uid(uid_t uid) +{ + struct uid_entry *uid_entry; + + uid_entry = find_uid_entry(uid); + if (uid_entry) + return uid_entry; + + uid_entry = kzalloc(sizeof(struct uid_entry), GFP_ATOMIC); + if (!uid_entry) + return NULL; + + uid_entry->uid = uid; + + hash_add(hash_table, &uid_entry->hash, uid); + + return uid_entry; +} + +static int uid_cputime_show(struct seq_file *m, void *v) +{ + struct uid_entry *uid_entry; + struct task_struct *task, *temp; + struct user_namespace *user_ns = current_user_ns(); + cputime_t utime; + cputime_t stime; + unsigned long bkt; + uid_t uid; + + rt_mutex_lock(&uid_lock); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + uid_entry->active_stime = 0; + uid_entry->active_utime = 0; + } + + read_lock(&tasklist_lock); + do_each_thread(temp, task) { + uid = from_kuid_munged(user_ns, task_uid(task)); + uid_entry = find_or_register_uid(uid); + if (!uid_entry) { + read_unlock(&tasklist_lock); + rt_mutex_unlock(&uid_lock); + pr_err("%s: failed to find the uid_entry for uid %d\n", + __func__, uid); + return -ENOMEM; + } + task_cputime_adjusted(task, &utime, &stime); + uid_entry->active_utime += utime; + uid_entry->active_stime += stime; + } while_each_thread(temp, task); + read_unlock(&tasklist_lock); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + cputime_t total_utime = uid_entry->utime + + uid_entry->active_utime; + cputime_t total_stime = uid_entry->stime + + uid_entry->active_stime; + seq_printf(m, "%d: %llu %llu\n", uid_entry->uid, + (unsigned long long)jiffies_to_msecs( + cputime_to_jiffies(total_utime)) * USEC_PER_MSEC, + (unsigned long long)jiffies_to_msecs( + cputime_to_jiffies(total_stime)) * USEC_PER_MSEC); + } + + rt_mutex_unlock(&uid_lock); + return 0; +} + +static int uid_cputime_open(struct inode *inode, struct file *file) +{ + return single_open(file, uid_cputime_show, PDE_DATA(inode)); +} + +static const struct file_operations uid_cputime_fops = { + .open = uid_cputime_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int uid_remove_open(struct inode *inode, struct file *file) +{ + return single_open(file, NULL, NULL); +} + +static ssize_t uid_remove_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos) +{ + struct uid_entry *uid_entry; + struct hlist_node *tmp; + char uids[128]; + char *start_uid, *end_uid = NULL; + long int uid_start = 0, uid_end = 0; + + if (count >= sizeof(uids)) + count = sizeof(uids) - 1; + + if (copy_from_user(uids, buffer, count)) + return -EFAULT; + + uids[count] = '\0'; + end_uid = uids; + start_uid = strsep(&end_uid, "-"); + + if (!start_uid || !end_uid) + return -EINVAL; + + if (kstrtol(start_uid, 10, &uid_start) != 0 || + kstrtol(end_uid, 10, &uid_end) != 0) { + return -EINVAL; + } + rt_mutex_lock(&uid_lock); + + for (; uid_start <= uid_end; uid_start++) { + hash_for_each_possible_safe(hash_table, uid_entry, tmp, + hash, (uid_t)uid_start) { + if (uid_start == uid_entry->uid) { + hash_del(&uid_entry->hash); + kfree(uid_entry); + } + } + } + + rt_mutex_unlock(&uid_lock); + return count; +} + +static const struct file_operations uid_remove_fops = { + .open = uid_remove_open, + .release = single_release, + .write = uid_remove_write, +}; + +static u64 compute_write_bytes(struct task_struct *task) +{ + if (task->ioac.write_bytes <= task->ioac.cancelled_write_bytes) + return 0; + + return task->ioac.write_bytes - task->ioac.cancelled_write_bytes; +} + +static void add_uid_io_curr_stats(struct uid_entry *uid_entry, + struct task_struct *task) +{ + struct io_stats *io_curr = &uid_entry->io[UID_STATE_TOTAL_CURR]; + + io_curr->read_bytes += task->ioac.read_bytes; + io_curr->write_bytes += compute_write_bytes(task); + io_curr->rchar += task->ioac.rchar; + io_curr->wchar += task->ioac.wchar; + io_curr->fsync += task->ioac.syscfs; +} + +static void clean_uid_io_last_stats(struct uid_entry *uid_entry, + struct task_struct *task) +{ + struct io_stats *io_last = &uid_entry->io[UID_STATE_TOTAL_LAST]; + + io_last->read_bytes -= task->ioac.read_bytes; + io_last->write_bytes -= compute_write_bytes(task); + io_last->rchar -= task->ioac.rchar; + io_last->wchar -= task->ioac.wchar; + io_last->fsync -= task->ioac.syscfs; +} + +static void update_io_stats_all_locked(void) +{ + struct uid_entry *uid_entry; + struct task_struct *task, *temp; + struct io_stats *io_bucket, *io_curr, *io_last; + struct user_namespace *user_ns = current_user_ns(); + unsigned long bkt; + uid_t uid; + + hash_for_each(hash_table, bkt, uid_entry, hash) + memset(&uid_entry->io[UID_STATE_TOTAL_CURR], 0, + sizeof(struct io_stats)); + + rcu_read_lock(); + do_each_thread(temp, task) { + uid = from_kuid_munged(user_ns, task_uid(task)); + uid_entry = find_or_register_uid(uid); + if (!uid_entry) + continue; + add_uid_io_curr_stats(uid_entry, task); + } while_each_thread(temp, task); + rcu_read_unlock(); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + io_bucket = &uid_entry->io[uid_entry->state]; + io_curr = &uid_entry->io[UID_STATE_TOTAL_CURR]; + io_last = &uid_entry->io[UID_STATE_TOTAL_LAST]; + + io_bucket->read_bytes += + io_curr->read_bytes - io_last->read_bytes; + io_bucket->write_bytes += + io_curr->write_bytes - io_last->write_bytes; + io_bucket->rchar += io_curr->rchar - io_last->rchar; + io_bucket->wchar += io_curr->wchar - io_last->wchar; + io_bucket->fsync += io_curr->fsync - io_last->fsync; + + io_last->read_bytes = io_curr->read_bytes; + io_last->write_bytes = io_curr->write_bytes; + io_last->rchar = io_curr->rchar; + io_last->wchar = io_curr->wchar; + io_last->fsync = io_curr->fsync; + } +} + +static void update_io_stats_uid_locked(uid_t target_uid) +{ + struct uid_entry *uid_entry; + struct task_struct *task, *temp; + struct io_stats *io_bucket, *io_curr, *io_last; + struct user_namespace *user_ns = current_user_ns(); + + uid_entry = find_or_register_uid(target_uid); + if (!uid_entry) + return; + + memset(&uid_entry->io[UID_STATE_TOTAL_CURR], 0, + sizeof(struct io_stats)); + + rcu_read_lock(); + do_each_thread(temp, task) { + if (from_kuid_munged(user_ns, task_uid(task)) != target_uid) + continue; + add_uid_io_curr_stats(uid_entry, task); + } while_each_thread(temp, task); + rcu_read_unlock(); + + io_bucket = &uid_entry->io[uid_entry->state]; + io_curr = &uid_entry->io[UID_STATE_TOTAL_CURR]; + io_last = &uid_entry->io[UID_STATE_TOTAL_LAST]; + + io_bucket->read_bytes += + io_curr->read_bytes - io_last->read_bytes; + io_bucket->write_bytes += + io_curr->write_bytes - io_last->write_bytes; + io_bucket->rchar += io_curr->rchar - io_last->rchar; + io_bucket->wchar += io_curr->wchar - io_last->wchar; + io_bucket->fsync += io_curr->fsync - io_last->fsync; + + io_last->read_bytes = io_curr->read_bytes; + io_last->write_bytes = io_curr->write_bytes; + io_last->rchar = io_curr->rchar; + io_last->wchar = io_curr->wchar; + io_last->fsync = io_curr->fsync; +} + +static int uid_io_show(struct seq_file *m, void *v) +{ + struct uid_entry *uid_entry; + unsigned long bkt; + + rt_mutex_lock(&uid_lock); + + update_io_stats_all_locked(); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + seq_printf(m, "%d %llu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + uid_entry->uid, + uid_entry->io[UID_STATE_FOREGROUND].rchar, + uid_entry->io[UID_STATE_FOREGROUND].wchar, + uid_entry->io[UID_STATE_FOREGROUND].read_bytes, + uid_entry->io[UID_STATE_FOREGROUND].write_bytes, + uid_entry->io[UID_STATE_BACKGROUND].rchar, + uid_entry->io[UID_STATE_BACKGROUND].wchar, + uid_entry->io[UID_STATE_BACKGROUND].read_bytes, + uid_entry->io[UID_STATE_BACKGROUND].write_bytes, + uid_entry->io[UID_STATE_FOREGROUND].fsync, + uid_entry->io[UID_STATE_BACKGROUND].fsync); + } + + rt_mutex_unlock(&uid_lock); + + return 0; +} + +static int uid_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, uid_io_show, PDE_DATA(inode)); +} + +static const struct file_operations uid_io_fops = { + .open = uid_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int uid_procstat_open(struct inode *inode, struct file *file) +{ + return single_open(file, NULL, NULL); +} + +static ssize_t uid_procstat_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos) +{ + struct uid_entry *uid_entry; + uid_t uid; + int argc, state; + char input[128]; + + if (count >= sizeof(input)) + return -EINVAL; + + if (copy_from_user(input, buffer, count)) + return -EFAULT; + + input[count] = '\0'; + + argc = sscanf(input, "%u %d", &uid, &state); + if (argc != 2) + return -EINVAL; + + if (state != UID_STATE_BACKGROUND && state != UID_STATE_FOREGROUND) + return -EINVAL; + + rt_mutex_lock(&uid_lock); + + uid_entry = find_or_register_uid(uid); + if (!uid_entry) { + rt_mutex_unlock(&uid_lock); + return -EINVAL; + } + + if (uid_entry->state == state) { + rt_mutex_unlock(&uid_lock); + return count; + } + + update_io_stats_uid_locked(uid); + + uid_entry->state = state; + + rt_mutex_unlock(&uid_lock); + + return count; +} + +static const struct file_operations uid_procstat_fops = { + .open = uid_procstat_open, + .release = single_release, + .write = uid_procstat_write, +}; + +static int process_notifier(struct notifier_block *self, + unsigned long cmd, void *v) +{ + struct task_struct *task = v; + struct uid_entry *uid_entry; + cputime_t utime, stime; + uid_t uid; + + if (!task) + return NOTIFY_OK; + + rt_mutex_lock(&uid_lock); + uid = from_kuid_munged(current_user_ns(), task_uid(task)); + uid_entry = find_or_register_uid(uid); + if (!uid_entry) { + pr_err("%s: failed to find uid %d\n", __func__, uid); + goto exit; + } + + task_cputime_adjusted(task, &utime, &stime); + uid_entry->utime += utime; + uid_entry->stime += stime; + + update_io_stats_uid_locked(uid); + clean_uid_io_last_stats(uid_entry, task); + +exit: + rt_mutex_unlock(&uid_lock); + return NOTIFY_OK; +} + +static struct notifier_block process_notifier_block = { + .notifier_call = process_notifier, +}; + +static int __init proc_uid_sys_stats_init(void) +{ + hash_init(hash_table); + + cpu_parent = proc_mkdir("uid_cputime", NULL); + if (!cpu_parent) { + pr_err("%s: failed to create uid_cputime proc entry\n", + __func__); + goto err; + } + + proc_create_data("remove_uid_range", 0222, cpu_parent, + &uid_remove_fops, NULL); + proc_create_data("show_uid_stat", 0444, cpu_parent, + &uid_cputime_fops, NULL); + + io_parent = proc_mkdir("uid_io", NULL); + if (!io_parent) { + pr_err("%s: failed to create uid_io proc entry\n", + __func__); + goto err; + } + + proc_create_data("stats", 0444, io_parent, + &uid_io_fops, NULL); + + proc_parent = proc_mkdir("uid_procstat", NULL); + if (!proc_parent) { + pr_err("%s: failed to create uid_procstat proc entry\n", + __func__); + goto err; + } + + proc_create_data("set", 0222, proc_parent, + &uid_procstat_fops, NULL); + + profile_event_register(PROFILE_TASK_EXIT, &process_notifier_block); + + return 0; + +err: + remove_proc_subtree("uid_cputime", NULL); + remove_proc_subtree("uid_io", NULL); + remove_proc_subtree("uid_procstat", NULL); + return -ENOMEM; +} + +early_initcall(proc_uid_sys_stats_init); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 78187699467a..83b9bf880834 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -592,6 +592,12 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) card->ext_csd.ffu_capable = (ext_csd[EXT_CSD_SUPPORTED_MODE] & 0x1) && !(ext_csd[EXT_CSD_FW_CONFIG] & 0x1); + + card->ext_csd.pre_eol_info = ext_csd[EXT_CSD_PRE_EOL_INFO]; + card->ext_csd.device_life_time_est_typ_a = + ext_csd[EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A]; + card->ext_csd.device_life_time_est_typ_b = + ext_csd[EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B]; } out: return err; @@ -721,6 +727,11 @@ MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid); MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name); MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid); MMC_DEV_ATTR(prv, "0x%x\n", card->cid.prv); +MMC_DEV_ATTR(rev, "0x%x\n", card->ext_csd.rev); +MMC_DEV_ATTR(pre_eol_info, "%02x\n", card->ext_csd.pre_eol_info); +MMC_DEV_ATTR(life_time, "0x%02x 0x%02x\n", + card->ext_csd.device_life_time_est_typ_a, + card->ext_csd.device_life_time_est_typ_b); MMC_DEV_ATTR(serial, "0x%08x\n", card->cid.serial); MMC_DEV_ATTR(enhanced_area_offset, "%llu\n", card->ext_csd.enhanced_area_offset); @@ -757,6 +768,9 @@ static struct attribute *mmc_std_attrs[] = { &dev_attr_name.attr, &dev_attr_oemid.attr, &dev_attr_prv.attr, + &dev_attr_rev.attr, + &dev_attr_pre_eol_info.attr, + &dev_attr_life_time.attr, &dev_attr_serial.attr, &dev_attr_enhanced_area_offset.attr, &dev_attr_enhanced_area_size.attr, @@ -1581,10 +1595,10 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, err = mmc_select_hs400(card); if (err) goto free_card; - } else if (mmc_card_hs(card)) { + } else { /* Select the desired bus width optionally */ err = mmc_select_bus_width(card); - if (!IS_ERR_VALUE(err)) { + if (!IS_ERR_VALUE(err) && mmc_card_hs(card)) { err = mmc_select_hs_ddr(card); if (err) goto free_card; diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 1f1582f6cccb..8d838779fd1b 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -804,6 +804,7 @@ static int esdhc_change_pinstate(struct sdhci_host *host, switch (uhs) { case MMC_TIMING_UHS_SDR50: + case MMC_TIMING_UHS_DDR50: pinctrl = imx_data->pins_100mhz; break; case MMC_TIMING_UHS_SDR104: diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c index 3b423b0ad8e7..f280744578e4 100644 --- a/drivers/mmc/host/sdhci-iproc.c +++ b/drivers/mmc/host/sdhci-iproc.c @@ -156,7 +156,8 @@ static const struct sdhci_ops sdhci_iproc_ops = { }; static const struct sdhci_pltfm_data sdhci_iproc_pltfm_data = { - .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK, + .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | + SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN, .ops = &sdhci_iproc_ops, }; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 7277dfd7338f..62d37d2ac557 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1274,7 +1274,9 @@ clock_set: return; } timeout--; - mdelay(1); + spin_unlock_irq(&host->lock); + usleep_range(900, 1100); + spin_lock_irq(&host->lock); } clk |= SDHCI_CLOCK_CARD_EN; @@ -2629,7 +2631,8 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) pr_err("%s: Card is consuming too much power!\n", mmc_hostname(host->mmc)); - if (intmask & SDHCI_INT_CARD_INT) { + if ((intmask & SDHCI_INT_CARD_INT) && + (host->ier & SDHCI_INT_CARD_INT)) { sdhci_enable_sdio_irq_nolock(host, false); host->thread_isr |= SDHCI_INT_CARD_INT; result = IRQ_WAKE_THREAD; diff --git a/drivers/mmc/host/ushc.c b/drivers/mmc/host/ushc.c index d2c386f09d69..1d843357422e 100644 --- a/drivers/mmc/host/ushc.c +++ b/drivers/mmc/host/ushc.c @@ -426,6 +426,9 @@ static int ushc_probe(struct usb_interface *intf, const struct usb_device_id *id struct ushc_data *ushc; int ret; + if (intf->cur_altsetting->desc.bNumEndpoints < 1) + return -ENODEV; + mmc = mmc_alloc_host(sizeof(struct ushc_data), &intf->dev); if (mmc == NULL) return -ENOMEM; diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c index c0720c1ee4c9..9190057535e6 100644 --- a/drivers/mtd/bcm47xxpart.c +++ b/drivers/mtd/bcm47xxpart.c @@ -66,11 +66,13 @@ static const char *bcm47xxpart_trx_data_part_name(struct mtd_info *master, { uint32_t buf; size_t bytes_read; + int err; - if (mtd_read(master, offset, sizeof(buf), &bytes_read, - (uint8_t *)&buf) < 0) { - pr_err("mtd_read error while parsing (offset: 0x%X)!\n", - offset); + err = mtd_read(master, offset, sizeof(buf), &bytes_read, + (uint8_t *)&buf); + if (err && !mtd_is_bitflip(err)) { + pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", + offset, err); goto out_default; } @@ -95,6 +97,7 @@ static int bcm47xxpart_parse(struct mtd_info *master, int trx_part = -1; int last_trx_part = -1; int possible_nvram_sizes[] = { 0x8000, 0xF000, 0x10000, }; + int err; /* * Some really old flashes (like AT45DB*) had smaller erasesize-s, but @@ -118,8 +121,8 @@ static int bcm47xxpart_parse(struct mtd_info *master, /* Parse block by block looking for magics */ for (offset = 0; offset <= master->size - blocksize; offset += blocksize) { - /* Nothing more in higher memory */ - if (offset >= 0x2000000) + /* Nothing more in higher memory on BCM47XX (MIPS) */ + if (config_enabled(CONFIG_BCM47XX) && offset >= 0x2000000) break; if (curr_part >= BCM47XXPART_MAX_PARTS) { @@ -128,10 +131,11 @@ static int bcm47xxpart_parse(struct mtd_info *master, } /* Read beginning of the block */ - if (mtd_read(master, offset, BCM47XXPART_BYTES_TO_READ, - &bytes_read, (uint8_t *)buf) < 0) { - pr_err("mtd_read error while parsing (offset: 0x%X)!\n", - offset); + err = mtd_read(master, offset, BCM47XXPART_BYTES_TO_READ, + &bytes_read, (uint8_t *)buf); + if (err && !mtd_is_bitflip(err)) { + pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", + offset, err); continue; } @@ -225,12 +229,10 @@ static int bcm47xxpart_parse(struct mtd_info *master, last_trx_part = curr_part - 1; - /* - * We have whole TRX scanned, skip to the next part. Use - * roundown (not roundup), as the loop will increase - * offset in next step. - */ - offset = rounddown(offset + trx->length, blocksize); + /* Jump to the end of TRX */ + offset = roundup(offset + trx->length, blocksize); + /* Next loop iteration will increase the offset */ + offset -= blocksize; continue; } @@ -254,10 +256,11 @@ static int bcm47xxpart_parse(struct mtd_info *master, } /* Read middle of the block */ - if (mtd_read(master, offset + 0x8000, 0x4, - &bytes_read, (uint8_t *)buf) < 0) { - pr_err("mtd_read error while parsing (offset: 0x%X)!\n", - offset); + err = mtd_read(master, offset + 0x8000, 0x4, &bytes_read, + (uint8_t *)buf); + if (err && !mtd_is_bitflip(err)) { + pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", + offset, err); continue; } @@ -277,10 +280,11 @@ static int bcm47xxpart_parse(struct mtd_info *master, } offset = master->size - possible_nvram_sizes[i]; - if (mtd_read(master, offset, 0x4, &bytes_read, - (uint8_t *)buf) < 0) { - pr_err("mtd_read error while reading at offset 0x%X!\n", - offset); + err = mtd_read(master, offset, 0x4, &bytes_read, + (uint8_t *)buf); + if (err && !mtd_is_bitflip(err)) { + pr_err("mtd_read error while reading (offset 0x%X): %d\n", + offset, err); continue; } diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig index 54479c481a7a..8a25adced79f 100644 --- a/drivers/mtd/chips/Kconfig +++ b/drivers/mtd/chips/Kconfig @@ -111,6 +111,7 @@ config MTD_MAP_BANK_WIDTH_16 config MTD_MAP_BANK_WIDTH_32 bool "Support 256-bit buswidth" if MTD_CFI_GEOMETRY + select MTD_COMPLEX_MAPPINGS if HAS_IOMEM default n help If you wish to support CFI devices on a physical bus which is diff --git a/drivers/mtd/maps/pmcmsp-flash.c b/drivers/mtd/maps/pmcmsp-flash.c index f9fa3fad728e..2051f28ddac6 100644 --- a/drivers/mtd/maps/pmcmsp-flash.c +++ b/drivers/mtd/maps/pmcmsp-flash.c @@ -139,15 +139,13 @@ static int __init init_msp_flash(void) } msp_maps[i].bankwidth = 1; - msp_maps[i].name = kmalloc(7, GFP_KERNEL); + msp_maps[i].name = kstrndup(flash_name, 7, GFP_KERNEL); if (!msp_maps[i].name) { iounmap(msp_maps[i].virt); kfree(msp_parts[i]); goto cleanup_loop; } - msp_maps[i].name = strncpy(msp_maps[i].name, flash_name, 7); - for (j = 0; j < pcnt; j++) { part_name[5] = '0' + i; part_name[7] = '0' + j; diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 37e4135ab213..64d6f053c2a5 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1057,6 +1057,13 @@ static int spansion_quad_enable(struct spi_nor *nor) return -EINVAL; } + ret = spi_nor_wait_till_ready(nor); + if (ret) { + dev_err(nor->dev, + "timeout while writing configuration register\n"); + return ret; + } + /* read back and check it */ ret = read_cr(nor); if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) { diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 0134ba32a057..39712560b4c1 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -148,11 +148,11 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, return err; } - if (bytes == 0) { - err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); - if (err) - return err; + err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); + if (err) + return err; + if (bytes == 0) { err = clear_update_marker(ubi, vol, 0); if (err) return err; diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c index 7be393c96b1a..cf7c18947189 100644 --- a/drivers/net/can/c_can/c_can_pci.c +++ b/drivers/net/can/c_can/c_can_pci.c @@ -161,6 +161,7 @@ static int c_can_pci_probe(struct pci_dev *pdev, dev->irq = pdev->irq; priv->base = addr; + priv->device = &pdev->dev; if (!c_can_pci_data->freq) { dev_err(&pdev->dev, "no clock frequency defined\n"); diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 680d1ff07a55..6749b1829469 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -948,7 +948,12 @@ static int ti_hecc_probe(struct platform_device *pdev) netif_napi_add(ndev, &priv->napi, ti_hecc_rx_poll, HECC_DEF_NAPI_WEIGHT); - clk_enable(priv->clk); + err = clk_prepare_enable(priv->clk); + if (err) { + dev_err(&pdev->dev, "clk_prepare_enable() failed\n"); + goto probe_exit_clk; + } + err = register_candev(ndev); if (err) { dev_err(&pdev->dev, "register_candev() failed\n"); @@ -981,7 +986,7 @@ static int ti_hecc_remove(struct platform_device *pdev) struct ti_hecc_priv *priv = netdev_priv(ndev); unregister_candev(ndev); - clk_disable(priv->clk); + clk_disable_unprepare(priv->clk); clk_put(priv->clk); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); iounmap(priv->base); @@ -1006,7 +1011,7 @@ static int ti_hecc_suspend(struct platform_device *pdev, pm_message_t state) hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_PDR); priv->can.state = CAN_STATE_SLEEPING; - clk_disable(priv->clk); + clk_disable_unprepare(priv->clk); return 0; } @@ -1015,8 +1020,11 @@ static int ti_hecc_resume(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct ti_hecc_priv *priv = netdev_priv(dev); + int err; - clk_enable(priv->clk); + err = clk_prepare_enable(priv->clk); + if (err) + return err; hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_PDR); priv->can.state = CAN_STATE_ERROR_ACTIVE; diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index cbc99d5649af..ae5709354546 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -246,6 +246,8 @@ static int gs_cmd_reset(struct gs_usb *gsusb, struct gs_can *gsdev) sizeof(*dm), 1000); + kfree(dm); + return rc; } diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index a731720f1d13..449b2a47f9a8 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -954,8 +954,8 @@ static int usb_8dev_probe(struct usb_interface *intf, for (i = 0; i < MAX_TX_URBS; i++) priv->tx_contexts[i].echo_index = MAX_TX_URBS; - priv->cmd_msg_buffer = kzalloc(sizeof(struct usb_8dev_cmd_msg), - GFP_KERNEL); + priv->cmd_msg_buffer = devm_kzalloc(&intf->dev, sizeof(struct usb_8dev_cmd_msg), + GFP_KERNEL); if (!priv->cmd_msg_buffer) goto cleanup_candev; @@ -969,7 +969,7 @@ static int usb_8dev_probe(struct usb_interface *intf, if (err) { netdev_err(netdev, "couldn't register CAN device: %d\n", err); - goto cleanup_cmd_msg_buffer; + goto cleanup_candev; } err = usb_8dev_cmd_version(priv, &version); @@ -990,9 +990,6 @@ static int usb_8dev_probe(struct usb_interface *intf, cleanup_unregister_candev: unregister_netdev(priv->netdev); -cleanup_cmd_msg_buffer: - kfree(priv->cmd_msg_buffer); - cleanup_candev: free_candev(netdev); diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index ac7288240d55..f089fa954f42 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -1153,6 +1153,12 @@ static void init_ring(struct net_device *dev) if (skb == NULL) break; np->rx_info[i].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE); + if (pci_dma_mapping_error(np->pci_dev, + np->rx_info[i].mapping)) { + dev_kfree_skb(skb); + np->rx_info[i].skb = NULL; + break; + } /* Grrr, we cannot offset to correctly align the IP header. */ np->rx_ring[i].rxaddr = cpu_to_dma(np->rx_info[i].mapping | RxDescValid); } @@ -1183,8 +1189,9 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) { struct netdev_private *np = netdev_priv(dev); unsigned int entry; + unsigned int prev_tx; u32 status; - int i; + int i, j; /* * be cautious here, wrapping the queue has weird semantics @@ -1202,6 +1209,7 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) } #endif /* ZEROCOPY && HAS_BROKEN_FIRMWARE */ + prev_tx = np->cur_tx; entry = np->cur_tx % TX_RING_SIZE; for (i = 0; i < skb_num_frags(skb); i++) { int wrap_ring = 0; @@ -1235,6 +1243,11 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) skb_frag_size(this_frag), PCI_DMA_TODEVICE); } + if (pci_dma_mapping_error(np->pci_dev, + np->tx_info[entry].mapping)) { + dev->stats.tx_dropped++; + goto err_out; + } np->tx_ring[entry].addr = cpu_to_dma(np->tx_info[entry].mapping); np->tx_ring[entry].status = cpu_to_le32(status); @@ -1269,8 +1282,30 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) netif_stop_queue(dev); return NETDEV_TX_OK; -} +err_out: + entry = prev_tx % TX_RING_SIZE; + np->tx_info[entry].skb = NULL; + if (i > 0) { + pci_unmap_single(np->pci_dev, + np->tx_info[entry].mapping, + skb_first_frag_len(skb), + PCI_DMA_TODEVICE); + np->tx_info[entry].mapping = 0; + entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE; + for (j = 1; j < i; j++) { + pci_unmap_single(np->pci_dev, + np->tx_info[entry].mapping, + skb_frag_size( + &skb_shinfo(skb)->frags[j-1]), + PCI_DMA_TODEVICE); + entry++; + } + } + dev_kfree_skb_any(skb); + np->cur_tx = prev_tx; + return NETDEV_TX_OK; +} /* The interrupt handler does all of the Rx thread work and cleans up after the Tx thread. */ @@ -1570,6 +1605,12 @@ static void refill_rx_ring(struct net_device *dev) break; /* Better luck next round. */ np->rx_info[entry].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE); + if (pci_dma_mapping_error(np->pci_dev, + np->rx_info[entry].mapping)) { + dev_kfree_skb(skb); + np->rx_info[entry].skb = NULL; + break; + } np->rx_ring[entry].rxaddr = cpu_to_dma(np->rx_info[entry].mapping | RxDescValid); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index b6fa89102526..66ba1e0ff37e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -913,8 +913,8 @@ #define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH 1 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX 1 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH 1 -#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX 2 -#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH 1 +#define RX_PACKET_ATTRIBUTES_LAST_INDEX 2 +#define RX_PACKET_ATTRIBUTES_LAST_WIDTH 1 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_INDEX 3 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_WIDTH 1 #define RX_PACKET_ATTRIBUTES_CONTEXT_INDEX 4 @@ -923,6 +923,8 @@ #define RX_PACKET_ATTRIBUTES_RX_TSTAMP_WIDTH 1 #define RX_PACKET_ATTRIBUTES_RSS_HASH_INDEX 6 #define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH 1 +#define RX_PACKET_ATTRIBUTES_FIRST_INDEX 7 +#define RX_PACKET_ATTRIBUTES_FIRST_WIDTH 1 #define RX_NORMAL_DESC0_OVT_INDEX 0 #define RX_NORMAL_DESC0_OVT_WIDTH 16 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index f6a7161e3b85..75e6e7e6baed 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1658,10 +1658,15 @@ static int xgbe_dev_read(struct xgbe_channel *channel) /* Get the header length */ if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) { + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + FIRST, 1); rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2, RX_NORMAL_DESC2, HL); if (rdata->rx.hdr_len) pdata->ext_stats.rx_split_header_packets++; + } else { + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + FIRST, 0); } /* Get the RSS hash */ @@ -1684,19 +1689,16 @@ static int xgbe_dev_read(struct xgbe_channel *channel) } } - /* Get the packet length */ - rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL); - - if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) { - /* Not all the data has been transferred for this packet */ - XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, - INCOMPLETE, 1); + /* Not all the data has been transferred for this packet */ + if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) return 0; - } /* This is the last of the data for this packet */ XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, - INCOMPLETE, 0); + LAST, 1); + + /* Get the packet length */ + rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL); /* Set checksum done indicator as appropriate */ if (netdev->features & NETIF_F_RXCSUM) @@ -2730,8 +2732,10 @@ static int xgbe_init(struct xgbe_prv_data *pdata) /* Flush Tx queues */ ret = xgbe_flush_tx_queues(pdata); - if (ret) + if (ret) { + netdev_err(pdata->netdev, "error flushing TX queues\n"); return ret; + } /* * Initialize DMA related features diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 53ce1222b11d..64034ff081a0 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -877,7 +877,9 @@ static int xgbe_start(struct xgbe_prv_data *pdata) DBGPR("-->xgbe_start\n"); - hw_if->init(pdata); + ret = hw_if->init(pdata); + if (ret) + return ret; ret = phy_if->phy_start(pdata); if (ret) @@ -1760,13 +1762,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata, { struct sk_buff *skb; u8 *packet; - unsigned int copy_len; skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len); if (!skb) return NULL; - /* Start with the header buffer which may contain just the header + /* Pull in the header buffer which may contain just the header * or the header plus data */ dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base, @@ -1775,30 +1776,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata, packet = page_address(rdata->rx.hdr.pa.pages) + rdata->rx.hdr.pa.pages_offset; - copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len; - copy_len = min(rdata->rx.hdr.dma_len, copy_len); - skb_copy_to_linear_data(skb, packet, copy_len); - skb_put(skb, copy_len); - - len -= copy_len; - if (len) { - /* Add the remaining data as a frag */ - dma_sync_single_range_for_cpu(pdata->dev, - rdata->rx.buf.dma_base, - rdata->rx.buf.dma_off, - rdata->rx.buf.dma_len, - DMA_FROM_DEVICE); - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - rdata->rx.buf.pa.pages, - rdata->rx.buf.pa.pages_offset, - len, rdata->rx.buf.dma_len); - rdata->rx.buf.pa.pages = NULL; - } + skb_copy_to_linear_data(skb, packet, len); + skb_put(skb, len); return skb; } +static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata, + struct xgbe_packet_data *packet) +{ + /* Always zero if not the first descriptor */ + if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST)) + return 0; + + /* First descriptor with split header, return header length */ + if (rdata->rx.hdr_len) + return rdata->rx.hdr_len; + + /* First descriptor but not the last descriptor and no split header, + * so the full buffer was used + */ + if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST)) + return rdata->rx.hdr.dma_len; + + /* First descriptor and last descriptor and no split header, so + * calculate how much of the buffer was used + */ + return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len); +} + +static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata, + struct xgbe_packet_data *packet, + unsigned int len) +{ + /* Always the full buffer if not the last descriptor */ + if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST)) + return rdata->rx.buf.dma_len; + + /* Last descriptor so calculate how much of the buffer was used + * for the last bit of data + */ + return rdata->rx.len - len; +} + static int xgbe_tx_poll(struct xgbe_channel *channel) { struct xgbe_prv_data *pdata = channel->pdata; @@ -1881,8 +1901,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget) struct napi_struct *napi; struct sk_buff *skb; struct skb_shared_hwtstamps *hwtstamps; - unsigned int incomplete, error, context_next, context; - unsigned int len, rdesc_len, max_len; + unsigned int last, error, context_next, context; + unsigned int len, buf1_len, buf2_len, max_len; unsigned int received = 0; int packet_count = 0; @@ -1892,7 +1912,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget) if (!ring) return 0; - incomplete = 0; + last = 0; context_next = 0; napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi; @@ -1926,9 +1946,8 @@ read_again: received++; ring->cur++; - incomplete = XGMAC_GET_BITS(packet->attributes, - RX_PACKET_ATTRIBUTES, - INCOMPLETE); + last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + LAST); context_next = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, CONTEXT_NEXT); @@ -1937,7 +1956,7 @@ read_again: CONTEXT); /* Earlier error, just drain the remaining data */ - if ((incomplete || context_next) && error) + if ((!last || context_next) && error) goto read_again; if (error || packet->errors) { @@ -1949,16 +1968,22 @@ read_again: } if (!context) { - /* Length is cumulative, get this descriptor's length */ - rdesc_len = rdata->rx.len - len; - len += rdesc_len; + /* Get the data length in the descriptor buffers */ + buf1_len = xgbe_rx_buf1_len(rdata, packet); + len += buf1_len; + buf2_len = xgbe_rx_buf2_len(rdata, packet, len); + len += buf2_len; - if (rdesc_len && !skb) { + if (!skb) { skb = xgbe_create_skb(pdata, napi, rdata, - rdesc_len); - if (!skb) + buf1_len); + if (!skb) { error = 1; - } else if (rdesc_len) { + goto skip_data; + } + } + + if (buf2_len) { dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.buf.dma_base, rdata->rx.buf.dma_off, @@ -1968,13 +1993,14 @@ read_again: skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rdata->rx.buf.pa.pages, rdata->rx.buf.pa.pages_offset, - rdesc_len, + buf2_len, rdata->rx.buf.dma_len); rdata->rx.buf.pa.pages = NULL; } } - if (incomplete || context_next) +skip_data: + if (!last || context_next) goto read_again; if (!skb) @@ -2033,7 +2059,7 @@ next_packet: } /* Check if we need to save state before leaving */ - if (received && (incomplete || context_next)) { + if (received && (!last || context_next)) { rdata = XGBE_GET_DESC_DATA(ring, ring->cur); rdata->state_saved = 1; rdata->state.skb = skb; diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index ecc4a334c507..0a54e7dac0ab 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -608,7 +608,7 @@ static void nb8800_mac_config(struct net_device *dev) mac_mode |= HALF_DUPLEX; if (gigabit) { - if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII) + if (phy_interface_is_rgmii(dev->phydev)) mac_mode |= RGMII_MODE; mac_mode |= GMAC_MODE; @@ -1295,11 +1295,10 @@ static int nb8800_tangox_init(struct net_device *dev) break; case PHY_INTERFACE_MODE_RGMII: - pad_mode = PAD_MODE_RGMII; - break; - + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: - pad_mode = PAD_MODE_RGMII | PAD_MODE_GTX_CLK_DELAY; + pad_mode = PAD_MODE_RGMII; break; default: diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 858106352ce9..8860e74aa28f 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -732,11 +732,8 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs; unsigned int pkts_compl = 0, bytes_compl = 0; struct bcm_sysport_cb *cb; - struct netdev_queue *txq; u32 hw_ind; - txq = netdev_get_tx_queue(ndev, ring->index); - /* Compute how many descriptors have been processed since last call */ hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index)); c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK; @@ -767,9 +764,6 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, ring->c_index = c_index; - if (netif_tx_queue_stopped(txq) && pkts_compl) - netif_tx_wake_queue(txq); - netif_dbg(priv, tx_done, ndev, "ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n", ring->index, ring->c_index, pkts_compl, bytes_compl); @@ -781,16 +775,33 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, struct bcm_sysport_tx_ring *ring) { + struct netdev_queue *txq; unsigned int released; unsigned long flags; + txq = netdev_get_tx_queue(priv->netdev, ring->index); + spin_lock_irqsave(&ring->lock, flags); released = __bcm_sysport_tx_reclaim(priv, ring); + if (released) + netif_tx_wake_queue(txq); + spin_unlock_irqrestore(&ring->lock, flags); return released; } +/* Locked version of the per-ring TX reclaim, but does not wake the queue */ +static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv, + struct bcm_sysport_tx_ring *ring) +{ + unsigned long flags; + + spin_lock_irqsave(&ring->lock, flags); + __bcm_sysport_tx_reclaim(priv, ring); + spin_unlock_irqrestore(&ring->lock, flags); +} + static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget) { struct bcm_sysport_tx_ring *ring = @@ -1275,7 +1286,7 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv, napi_disable(&ring->napi); netif_napi_del(&ring->napi); - bcm_sysport_tx_reclaim(priv, ring); + bcm_sysport_tx_clean(priv, ring); kfree(ring->cbs); ring->cbs = NULL; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index b56c9c581359..a5e4b4b93d1b 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -255,15 +255,16 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring) while (ring->start != ring->end) { int slot_idx = ring->start % BGMAC_TX_RING_SLOTS; struct bgmac_slot_info *slot = &ring->slots[slot_idx]; - u32 ctl1; + u32 ctl0, ctl1; int len; if (slot_idx == empty_slot) break; + ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0); ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1); len = ctl1 & BGMAC_DESC_CTL1_LEN; - if (ctl1 & BGMAC_DESC_CTL0_SOF) + if (ctl0 & BGMAC_DESC_CTL0_SOF) /* Unmap no longer used buffer */ dma_unmap_single(dma_dev, slot->dma_addr, len, DMA_TO_DEVICE); @@ -469,6 +470,11 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring, len -= ETH_FCS_LEN; skb = build_skb(buf, BGMAC_RX_ALLOC_SIZE); + if (unlikely(!skb)) { + bgmac_err(bgmac, "build_skb failed\n"); + put_page(virt_to_head_page(buf)); + break; + } skb_put(skb, BGMAC_RX_FRAME_OFFSET + BGMAC_RX_BUF_OFFSET + len); skb_pull(skb, BGMAC_RX_FRAME_OFFSET + @@ -1302,7 +1308,8 @@ static int bgmac_open(struct net_device *net_dev) phy_start(bgmac->phy_dev); - netif_carrier_on(net_dev); + netif_start_queue(net_dev); + return 0; } @@ -1576,6 +1583,11 @@ static int bgmac_probe(struct bcma_device *core) dev_warn(&core->dev, "Using random MAC: %pM\n", mac); } + /* This (reset &) enable is not preset in specs or reference driver but + * Broadcom does it in arch PCI code when enabling fake PCI device. + */ + bcma_core_enable(core, 0); + /* Allocation and references */ net_dev = alloc_etherdev(sizeof(*bgmac)); if (!net_dev) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index c82ab87fcbe8..e5911ccb2148 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1949,7 +1949,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); + return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); } void bnx2x_set_num_queues(struct bnx2x *bp) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 07f5f239cb65..4744919440e0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2473,7 +2473,8 @@ static int bnxt_alloc_ntp_fltrs(struct bnxt *bp) INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]); bp->ntp_fltr_count = 0; - bp->ntp_fltr_bmap = kzalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR), + bp->ntp_fltr_bmap = kcalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR), + sizeof(long), GFP_KERNEL); if (!bp->ntp_fltr_bmap) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 91627561c58d..f971d92f7b41 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3495,7 +3495,8 @@ static int bcmgenet_suspend(struct device *d) bcmgenet_netif_stop(dev); - phy_suspend(priv->phydev); + if (!device_may_wakeup(d)) + phy_suspend(priv->phydev); netif_device_detach(dev); @@ -3592,7 +3593,8 @@ static int bcmgenet_resume(struct device *d) netif_device_attach(dev); - phy_resume(priv->phydev); + if (!device_may_wakeup(d)) + phy_resume(priv->phydev); if (priv->eee.eee_enabled) bcmgenet_eee_enable_set(dev, true); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 8bdfe53754ba..e96d1f95bb47 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -220,20 +220,6 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable) udelay(60); } -static void bcmgenet_internal_phy_setup(struct net_device *dev) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - u32 reg; - - /* Power up PHY */ - bcmgenet_phy_power_set(dev, true); - /* enable APD */ - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= EXT_PWR_DN_EN_LD; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - bcmgenet_mii_reset(dev); -} - static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) { u32 reg; @@ -281,7 +267,6 @@ int bcmgenet_mii_config(struct net_device *dev) if (priv->internal_phy) { phy_name = "internal PHY"; - bcmgenet_internal_phy_setup(dev); } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { phy_name = "MoCA"; bcmgenet_moca_phy_setup(priv); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 49056c33be74..3613469dc5c6 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -8722,11 +8722,14 @@ static void tg3_free_consistent(struct tg3 *tp) tg3_mem_rx_release(tp); tg3_mem_tx_release(tp); + /* Protect tg3_get_stats64() from reading freed tp->hw_stats. */ + tg3_full_lock(tp, 0); if (tp->hw_stats) { dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats), tp->hw_stats, tp->stats_mapping); tp->hw_stats = NULL; } + tg3_full_unlock(tp); } /* @@ -12031,7 +12034,7 @@ static int tg3_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, int ret; u32 offset, len, b_offset, odd_len; u8 *buf; - __be32 start, end; + __be32 start = 0, end; if (tg3_flag(tp, NO_NVRAM) || eeprom->magic != TG3_EEPROM_MAGIC) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 7445da218bd9..cc1725616f9d 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2823,7 +2823,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) if (!g) { netif_info(lio, tx_err, lio->netdev, "Transmit scatter gather: glist null!\n"); - goto lio_xmit_failed; + goto lio_xmit_dma_failed; } cmdsetup.s.gather = 1; @@ -2894,7 +2894,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) else status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more); if (status == IQ_SEND_FAILED) - goto lio_xmit_failed; + goto lio_xmit_dma_failed; netif_info(lio, tx_queued, lio->netdev, "Transmit queued successfully\n"); @@ -2908,12 +2908,13 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; +lio_xmit_dma_failed: + dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr, + ndata.datasize, DMA_TO_DEVICE); lio_xmit_failed: stats->tx_dropped++; netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n", iq_no, stats->tx_dropped); - dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr, - ndata.datasize, DMA_TO_DEVICE); recv_buffer_free(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 0d147610a06f..090e00650601 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2714,10 +2714,14 @@ static int cxgb_up(struct adapter *adap) if (err) goto irq_err; } + + mutex_lock(&uld_mutex); enable_rx(adap); t4_sge_start(adap); t4_intr_enable(adap); adap->flags |= FULL_INIT_DONE; + mutex_unlock(&uld_mutex); + notify_ulds(adap, CXGB4_STATE_UP); #if IS_ENABLED(CONFIG_IPV6) update_clip(adap); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 1795c935ff02..7b8638ddb673 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1052,7 +1052,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, err: spin_unlock_bh(&adapter->mcc_lock); - if (status == MCC_STATUS_UNAUTHORIZED_REQUEST) + if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST) status = -EPERM; return status; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 8a1d9fffd7d6..26255862d1cf 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5260,9 +5260,11 @@ static netdev_features_t be_features_check(struct sk_buff *skb, struct be_adapter *adapter = netdev_priv(dev); u8 l4_hdr = 0; - /* The code below restricts offload features for some tunneled packets. + /* The code below restricts offload features for some tunneled and + * Q-in-Q packets. * Offload features for normal (non tunnel) packets are unchanged. */ + features = vlan_features_check(skb, features); if (!skb->encapsulation || !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS)) return features; diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index ff665493ca97..52f2230062e7 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -713,6 +713,8 @@ static int ethoc_open(struct net_device *dev) if (ret) return ret; + napi_enable(&priv->napi); + ethoc_init_ring(priv, dev->mem_start); ethoc_reset(priv); @@ -725,7 +727,6 @@ static int ethoc_open(struct net_device *dev) } phy_start(priv->phy); - napi_enable(&priv->napi); if (netif_msg_ifup(priv)) { dev_info(&dev->dev, "I/O: %08lx Memory: %08lx-%08lx\n", diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 3e233d924cce..4cd2a7d0124f 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1999,8 +1999,8 @@ static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue) if (!rxb->page) continue; - dma_unmap_single(rx_queue->dev, rxb->dma, - PAGE_SIZE, DMA_FROM_DEVICE); + dma_unmap_page(rx_queue->dev, rxb->dma, + PAGE_SIZE, DMA_FROM_DEVICE); __free_page(rxb->page); rxb->page = NULL; @@ -2939,7 +2939,7 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus, size, GFAR_RXB_TRUESIZE); /* try reuse page */ - if (unlikely(page_count(page) != 1)) + if (unlikely(page_count(page) != 1 || page_is_pfmemalloc(page))) return false; /* change offset to the other half */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index bdbd80423b17..9ff2881f933d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -900,9 +900,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(base); - - writel(value, reg_addr + reg); + writel(value, base + reg); } #define dsaf_write_dev(a, reg, value) \ @@ -910,9 +908,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value) static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg) { - u8 __iomem *reg_addr = ACCESS_ONCE(base); - - return readl(reg_addr + reg); + return readl(base + reg); } #define dsaf_read_dev(a, reg) \ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 08cef0dfb5db..2fa54b0b0679 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -105,8 +105,8 @@ int hns_nic_net_xmit_hw(struct net_device *ndev, struct hns_nic_ring_data *ring_data) { struct hns_nic_priv *priv = netdev_priv(ndev); - struct device *dev = priv->dev; struct hnae_ring *ring = ring_data->ring; + struct device *dev = ring_to_dev(ring); struct netdev_queue *dev_queue; struct skb_frag_struct *frag; int buf_num; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 7af870a3c549..2f9b12cf9ee5 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -58,7 +58,7 @@ static struct kobj_type ktype_veth_pool; static const char ibmveth_driver_name[] = "ibmveth"; static const char ibmveth_driver_string[] = "IBM Power Virtual Ethernet Driver"; -#define ibmveth_driver_version "1.05" +#define ibmveth_driver_version "1.06" MODULE_AUTHOR("Santiago Leon <santil@linux.vnet.ibm.com>"); MODULE_DESCRIPTION("IBM Power Virtual Ethernet Driver"); @@ -137,6 +137,11 @@ static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter) return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK; } +static inline int ibmveth_rxq_large_packet(struct ibmveth_adapter *adapter) +{ + return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_LRG_PKT; +} + static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter) { return be32_to_cpu(adapter->rx_queue.queue_addr[adapter->rx_queue.index].length); @@ -1172,6 +1177,53 @@ map_failed: goto retry_bounce; } +static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt) +{ + struct tcphdr *tcph; + int offset = 0; + int hdr_len; + + /* only TCP packets will be aggregated */ + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)skb->data; + + if (iph->protocol == IPPROTO_TCP) { + offset = iph->ihl * 4; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + } else { + return; + } + } else if (skb->protocol == htons(ETH_P_IPV6)) { + struct ipv6hdr *iph6 = (struct ipv6hdr *)skb->data; + + if (iph6->nexthdr == IPPROTO_TCP) { + offset = sizeof(struct ipv6hdr); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + } else { + return; + } + } else { + return; + } + /* if mss is not set through Large Packet bit/mss in rx buffer, + * expect that the mss will be written to the tcp header checksum. + */ + tcph = (struct tcphdr *)(skb->data + offset); + if (lrg_pkt) { + skb_shinfo(skb)->gso_size = mss; + } else if (offset) { + skb_shinfo(skb)->gso_size = ntohs(tcph->check); + tcph->check = 0; + } + + if (skb_shinfo(skb)->gso_size) { + hdr_len = offset + tcph->doff * 4; + skb_shinfo(skb)->gso_segs = + DIV_ROUND_UP(skb->len - hdr_len, + skb_shinfo(skb)->gso_size); + } +} + static int ibmveth_poll(struct napi_struct *napi, int budget) { struct ibmveth_adapter *adapter = @@ -1180,6 +1232,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) int frames_processed = 0; unsigned long lpar_rc; struct iphdr *iph; + u16 mss = 0; restart_poll: while (frames_processed < budget) { @@ -1197,9 +1250,21 @@ restart_poll: int length = ibmveth_rxq_frame_length(adapter); int offset = ibmveth_rxq_frame_offset(adapter); int csum_good = ibmveth_rxq_csum_good(adapter); + int lrg_pkt = ibmveth_rxq_large_packet(adapter); skb = ibmveth_rxq_get_buffer(adapter); + /* if the large packet bit is set in the rx queue + * descriptor, the mss will be written by PHYP eight + * bytes from the start of the rx buffer, which is + * skb->data at this stage + */ + if (lrg_pkt) { + __be64 *rxmss = (__be64 *)(skb->data + 8); + + mss = (u16)be64_to_cpu(*rxmss); + } + new_skb = NULL; if (length < rx_copybreak) new_skb = netdev_alloc_skb(netdev, length); @@ -1233,11 +1298,15 @@ restart_poll: if (iph->check == 0xffff) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - adapter->rx_large_packets++; } } } + if (length > netdev->mtu + ETH_HLEN) { + ibmveth_rx_mss_helper(skb, mss, lrg_pkt); + adapter->rx_large_packets++; + } + napi_gro_receive(napi, skb); /* send it up */ netdev->stats.rx_packets++; @@ -1533,8 +1602,11 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) netdev->netdev_ops = &ibmveth_netdev_ops; netdev->ethtool_ops = &netdev_ethtool_ops; SET_NETDEV_DEV(netdev, &dev->dev); - netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | - NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + netdev->hw_features = NETIF_F_SG; + if (vio_get_attribute(dev, "ibm,illan-options", NULL) != NULL) { + netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM; + } netdev->features |= netdev->hw_features; diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 4eade67fe30c..7acda04d034e 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -209,6 +209,7 @@ struct ibmveth_rx_q_entry { #define IBMVETH_RXQ_TOGGLE 0x80000000 #define IBMVETH_RXQ_TOGGLE_SHIFT 31 #define IBMVETH_RXQ_VALID 0x40000000 +#define IBMVETH_RXQ_LRG_PKT 0x04000000 #define IBMVETH_RXQ_NO_CSUM 0x02000000 #define IBMVETH_RXQ_CSUM_GOOD 0x01000000 #define IBMVETH_RXQ_OFF_MASK 0x0000FFFF diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index 23ec28f43f6d..afaa98d1d4e4 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -77,6 +77,10 @@ s32 igb_get_phy_id(struct e1000_hw *hw) s32 ret_val = 0; u16 phy_id; + /* ensure PHY page selection to fix misconfigured i210 */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) + phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0); + ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id); if (ret_val) goto out; diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index d74f5f4e5782..07eabf72c480 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -900,10 +900,10 @@ static void korina_restart_task(struct work_struct *work) DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR, &lp->rx_dma_regs->dmasm); - korina_free_ring(dev); - napi_disable(&lp->napi); + korina_free_ring(dev); + if (korina_init(dev) < 0) { printk(KERN_ERR "%s: cannot restart device\n", dev->name); return; @@ -1064,12 +1064,12 @@ static int korina_close(struct net_device *dev) tmp = tmp | DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR; writel(tmp, &lp->rx_dma_regs->dmasm); - korina_free_ring(dev); - napi_disable(&lp->napi); cancel_work_sync(&lp->restart_task); + korina_free_ring(dev); + free_irq(lp->rx_irq, dev); free_irq(lp->tx_irq, dev); free_irq(lp->ovr_irq, dev); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 71ec9cb08e06..15056f06754a 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2446,7 +2446,7 @@ static void mvneta_start_dev(struct mvneta_port *pp) mvneta_port_enable(pp); /* Enable polling on the port */ - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); napi_enable(&port->napi); @@ -2472,7 +2472,7 @@ static void mvneta_stop_dev(struct mvneta_port *pp) phy_stop(pp->phy_dev); - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); napi_disable(&port->napi); @@ -2902,13 +2902,11 @@ err_cleanup_rxqs: static int mvneta_stop(struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); - int cpu; mvneta_stop_dev(pp); mvneta_mdio_remove(pp); unregister_cpu_notifier(&pp->cpu_notifier); - for_each_present_cpu(cpu) - smp_call_function_single(cpu, mvneta_percpu_disable, pp, true); + on_each_cpu(mvneta_percpu_disable, pp, true); free_percpu_irq(dev->irq, pp->ports); mvneta_cleanup_rxqs(pp); mvneta_cleanup_txqs(pp); diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 25aba9886990..0e67145bc418 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -993,7 +993,7 @@ static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu, txq_pcpu->buffs + txq_pcpu->txq_put_index; tx_buf->skb = skb; tx_buf->size = tx_desc->data_size; - tx_buf->phys = tx_desc->buf_phys_addr; + tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset; txq_pcpu->txq_put_index++; if (txq_pcpu->txq_put_index == txq_pcpu->size) txq_pcpu->txq_put_index = 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 715de8affcc9..e203d0c4e5a3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -158,7 +158,7 @@ static int mlx4_reset_slave(struct mlx4_dev *dev) return -ETIMEDOUT; } -static int mlx4_comm_internal_err(u32 slave_read) +int mlx4_comm_internal_err(u32 slave_read) { return (u32)COMM_CHAN_EVENT_INTERNAL_ERR == (slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index 3348e646db70..6eba58044456 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -101,13 +101,19 @@ void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn) { struct mlx4_cq *cq; + rcu_read_lock(); cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree, cqn & (dev->caps.num_cqs - 1)); + rcu_read_unlock(); + if (!cq) { mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ ++cq->arm_sn; cq->comp(cq); @@ -118,23 +124,19 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type) struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table; struct mlx4_cq *cq; - spin_lock(&cq_table->lock); - + rcu_read_lock(); cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1)); - if (cq) - atomic_inc(&cq->refcount); - - spin_unlock(&cq_table->lock); + rcu_read_unlock(); if (!cq) { - mlx4_warn(dev, "Async event for bogus CQ %08x\n", cqn); + mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ cq->event(cq, event_type); - - if (atomic_dec_and_test(&cq->refcount)) - complete(&cq->free); } static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox, @@ -301,9 +303,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, if (err) return err; - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); err = radix_tree_insert(&cq_table->tree, cq->cqn, cq); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); if (err) goto err_icm; @@ -347,9 +349,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, return 0; err_radix: - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); err_icm: mlx4_cq_free_icm(dev, cq->cqn); @@ -368,15 +370,15 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq) if (err) mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn); + spin_lock(&cq_table->lock); + radix_tree_delete(&cq_table->tree, cq->cqn); + spin_unlock(&cq_table->lock); + synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq); if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq != priv->eq_table.eq[MLX4_EQ_ASYNC].irq) synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq); - spin_lock_irq(&cq_table->lock); - radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); - if (atomic_dec_and_test(&cq->refcount)) complete(&cq->free); wait_for_completion(&cq->free); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index bbff8ec6713e..82bf1b539d87 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -439,8 +439,14 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv) ring->cqn = priv->rx_cq[ring_ind]->mcq.cqn; ring->stride = stride; - if (ring->stride <= TXBB_SIZE) + if (ring->stride <= TXBB_SIZE) { + /* Stamp first unused send wqe */ + __be32 *ptr = (__be32 *)ring->buf; + __be32 stamp = cpu_to_be32(1 << STAMP_SHIFT); + *ptr = stamp; + /* Move pointer to start of rx section */ ring->buf += TXBB_SIZE; + } ring->log_stride = ffs(ring->stride) - 1; ring->buf_size = ring->size * ring->stride; @@ -502,8 +508,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) return; for (ring = 0; ring < priv->rx_ring_num; ring++) { - if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) + if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) { + local_bh_disable(); napi_reschedule(&priv->rx_cq[ring]->napi); + local_bh_enable(); + } } } diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 603d1c3d3b2e..ff77b8b608bd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -542,8 +542,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) break; case MLX4_EVENT_TYPE_SRQ_LIMIT: - mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n", - __func__); + mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n", + __func__, be32_to_cpu(eqe->event.srq.srqn), + eq->eqn); case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR: if (mlx4_is_master(dev)) { /* forward only to slave owning the SRQ */ @@ -558,15 +559,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) eq->eqn, eq->cons_index, ret); break; } - mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", - __func__, slave, - be32_to_cpu(eqe->event.srq.srqn), - eqe->type, eqe->subtype); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", + __func__, slave, + be32_to_cpu(eqe->event.srq.srqn), + eqe->type, eqe->subtype); if (!ret && slave != dev->caps.function) { - mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", - __func__, eqe->type, - eqe->subtype, slave); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", + __func__, eqe->type, + eqe->subtype, slave); mlx4_slave_event(dev, slave, eqe); break; } diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index 2a9dd460a95f..e1f9e7cebf8f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -118,8 +118,13 @@ static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem, if (!buf) return -ENOMEM; + if (offset_in_page(buf)) { + dma_free_coherent(dev, PAGE_SIZE << order, + buf, sg_dma_address(mem)); + return -ENOMEM; + } + sg_set_buf(mem, buf, PAGE_SIZE << order); - BUG_ON(mem->offset); sg_dma_len(mem) = PAGE_SIZE << order; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 0472941af820..1a134e08f010 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -218,6 +218,18 @@ void mlx4_unregister_device(struct mlx4_dev *dev) struct mlx4_interface *intf; mlx4_stop_catas_poll(dev); + if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION && + mlx4_is_slave(dev)) { + /* In mlx4_remove_one on a VF */ + u32 slave_read = + swab32(readl(&mlx4_priv(dev)->mfunc.comm->slave_read)); + + if (mlx4_comm_internal_err(slave_read)) { + mlx4_dbg(dev, "%s: comm channel is down, entering error state.\n", + __func__); + mlx4_enter_error_state(dev->persist); + } + } mutex_lock(&intf_mutex); list_for_each_entry(intf, &intf_list, list) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index e1cf9036af22..f5fdbd53d052 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1205,6 +1205,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type); void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type); void mlx4_enter_error_state(struct mlx4_dev_persistent *persist); +int mlx4_comm_internal_err(u32 slave_read); int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port, enum mlx4_port_type *type); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index d314d96dcb1c..d1fc7fa87b05 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2955,6 +2955,9 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, put_res(dev, slave, srqn, RES_SRQ); qp->srq = srq; } + + /* Save param3 for dynamic changes from VST back to VGT */ + qp->param3 = qpc->param3; put_res(dev, slave, rcqn, RES_CQ); put_res(dev, slave, mtt_base, RES_MTT); res_end_move(dev, slave, RES_QP, qpn); @@ -3747,7 +3750,6 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, int qpn = vhcr->in_modifier & 0x7fffff; struct res_qp *qp; u8 orig_sched_queue; - __be32 orig_param3 = qpc->param3; u8 orig_vlan_control = qpc->pri_path.vlan_control; u8 orig_fvl_rx = qpc->pri_path.fvl_rx; u8 orig_pri_path_fl = qpc->pri_path.fl; @@ -3789,7 +3791,6 @@ out: */ if (!err) { qp->sched_queue = orig_sched_queue; - qp->param3 = orig_param3; qp->vlan_control = orig_vlan_control; qp->fvl_rx = orig_fvl_rx; qp->pri_path_fl = orig_pri_path_fl; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index cc199063612a..6c66d2979795 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -630,6 +630,10 @@ static void dump_command(struct mlx5_core_dev *dev, pr_debug("\n"); } +static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg); +static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev, + struct mlx5_cmd_msg *msg); + static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); @@ -638,16 +642,27 @@ static void cmd_work_handler(struct work_struct *work) struct mlx5_cmd_layout *lay; struct semaphore *sem; unsigned long flags; + int alloc_ret; sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { - ent->idx = alloc_ent(cmd); - if (ent->idx < 0) { + alloc_ret = alloc_ent(cmd); + if (alloc_ret < 0) { + if (ent->callback) { + ent->callback(-EAGAIN, ent->context); + mlx5_free_cmd_msg(dev, ent->out); + free_msg(dev, ent->in); + free_cmd(ent); + } else { + ent->ret = -EAGAIN; + complete(&ent->done); + } mlx5_core_err(dev, "failed to allocate command entry\n"); up(sem); return; } + ent->idx = alloc_ret; } else { ent->idx = cmd->max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index cf0098596e85..e9408f5e2a1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -197,6 +197,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, if (lro_num_seg > 1) { mlx5e_lro_update_hdr(skb, cqe); skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg); + /* Subtract one since we already counted this as one + * "regular" packet in mlx5e_complete_rx_cqe() + */ + rq->stats.packets += lro_num_seg - 1; rq->stats.lro_packets++; rq->stats.lro_bytes += cqe_bcnt; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index ba115ec7aa92..f5c1f4acc57b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -85,7 +85,7 @@ static struct mlx5_profile profile[] = { [2] = { .mask = MLX5_PROF_MASK_QP_SIZE | MLX5_PROF_MASK_MR_CACHE, - .log_max_qp = 17, + .log_max_qp = 18, .mr_cache[0] = { .size = 500, .limit = 250 @@ -153,8 +153,9 @@ static struct mlx5_profile profile[] = { }, }; -#define FW_INIT_TIMEOUT_MILI 2000 -#define FW_INIT_WAIT_MS 2 +#define FW_INIT_TIMEOUT_MILI 2000 +#define FW_INIT_WAIT_MS 2 +#define FW_PRE_INIT_TIMEOUT_MILI 10000 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili) { @@ -934,6 +935,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) */ dev->state = MLX5_DEVICE_STATE_UP; + /* wait for firmware to accept initialization segments configurations + */ + err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI); + if (err) { + dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n", + FW_PRE_INIT_TIMEOUT_MILI); + goto out; + } + err = mlx5_cmd_init(dev); if (err) { dev_err(&pdev->dev, "Failed initializing command interface, aborting\n"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index 142f33d978c5..a0fbe00dd690 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -206,21 +206,21 @@ MLXSW_ITEM32(pci, eqe, owner, 0x0C, 0, 1); /* pci_eqe_cmd_token * Command completion event - token */ -MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16); +MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16); /* pci_eqe_cmd_status * Command completion event - status */ -MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8); +MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8); /* pci_eqe_cmd_out_param_h * Command completion event - output parameter - higher part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32); /* pci_eqe_cmd_out_param_l * Command completion event - output parameter - lower part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3be4a2355ead..cb165c2d4803 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -390,6 +390,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } if (eth_skb_pad(skb)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index d85960cfb694..fb2d9a82ce3d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -313,6 +313,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } mlxsw_sx_txhdr_construct(skb, &tx_info); len = skb->len; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 79ef799f88ab..c5ea1018cb47 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -326,6 +326,7 @@ enum cfg_version { static const struct pci_device_id rtl8169_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8129), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8136), 0, 0, RTL_CFG_2 }, + { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8161), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8167), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8168), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8169), 0, 0, RTL_CFG_0 }, diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 467d41698fd5..585e90f8341d 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -171,34 +171,67 @@ static struct mdiobb_ops bb_ops = { .get_mdio_data = ravb_get_mdio_data, }; -/* Free skb's and DMA buffers for Ethernet AVB */ -static void ravb_ring_free(struct net_device *ndev, int q) +/* Free TX skb function for AVB-IP */ +static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) { struct ravb_private *priv = netdev_priv(ndev); - int ring_size; - int i; + struct net_device_stats *stats = &priv->stats[q]; + struct ravb_tx_desc *desc; + int free_num = 0; + int entry; + u32 size; - /* Free RX skb ringbuffer */ - if (priv->rx_skb[q]) { - for (i = 0; i < priv->num_rx_ring[q]; i++) - dev_kfree_skb(priv->rx_skb[q][i]); - } - kfree(priv->rx_skb[q]); - priv->rx_skb[q] = NULL; + for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) { + bool txed; - /* Free TX skb ringbuffer */ - if (priv->tx_skb[q]) { - for (i = 0; i < priv->num_tx_ring[q]; i++) - dev_kfree_skb(priv->tx_skb[q][i]); + entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] * + NUM_TX_DESC); + desc = &priv->tx_ring[q][entry]; + txed = desc->die_dt == DT_FEMPTY; + if (free_txed_only && !txed) + break; + /* Descriptor type must be checked before all other reads */ + dma_rmb(); + size = le16_to_cpu(desc->ds_tagl) & TX_DS; + /* Free the original skb. */ + if (priv->tx_skb[q][entry / NUM_TX_DESC]) { + dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), + size, DMA_TO_DEVICE); + /* Last packet descriptor? */ + if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) { + entry /= NUM_TX_DESC; + dev_kfree_skb_any(priv->tx_skb[q][entry]); + priv->tx_skb[q][entry] = NULL; + if (txed) + stats->tx_packets++; + } + free_num++; + } + if (txed) + stats->tx_bytes += size; + desc->die_dt = DT_EEMPTY; } - kfree(priv->tx_skb[q]); - priv->tx_skb[q] = NULL; + return free_num; +} - /* Free aligned TX buffers */ - kfree(priv->tx_align[q]); - priv->tx_align[q] = NULL; +/* Free skb's and DMA buffers for Ethernet AVB */ +static void ravb_ring_free(struct net_device *ndev, int q) +{ + struct ravb_private *priv = netdev_priv(ndev); + int ring_size; + int i; if (priv->rx_ring[q]) { + for (i = 0; i < priv->num_rx_ring[q]; i++) { + struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i]; + + if (!dma_mapping_error(ndev->dev.parent, + le32_to_cpu(desc->dptr))) + dma_unmap_single(ndev->dev.parent, + le32_to_cpu(desc->dptr), + PKT_BUF_SZ, + DMA_FROM_DEVICE); + } ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q], @@ -207,12 +240,32 @@ static void ravb_ring_free(struct net_device *ndev, int q) } if (priv->tx_ring[q]) { + ravb_tx_free(ndev, q, false); + ring_size = sizeof(struct ravb_tx_desc) * (priv->num_tx_ring[q] * NUM_TX_DESC + 1); dma_free_coherent(ndev->dev.parent, ring_size, priv->tx_ring[q], priv->tx_desc_dma[q]); priv->tx_ring[q] = NULL; } + + /* Free RX skb ringbuffer */ + if (priv->rx_skb[q]) { + for (i = 0; i < priv->num_rx_ring[q]; i++) + dev_kfree_skb(priv->rx_skb[q][i]); + } + kfree(priv->rx_skb[q]); + priv->rx_skb[q] = NULL; + + /* Free aligned TX buffers */ + kfree(priv->tx_align[q]); + priv->tx_align[q] = NULL; + + /* Free TX skb ringbuffer. + * SKBs are freed by ravb_tx_free() call above. + */ + kfree(priv->tx_skb[q]); + priv->tx_skb[q] = NULL; } /* Format skb and descriptor buffer for Ethernet AVB */ @@ -420,44 +473,6 @@ static int ravb_dmac_init(struct net_device *ndev) return 0; } -/* Free TX skb function for AVB-IP */ -static int ravb_tx_free(struct net_device *ndev, int q) -{ - struct ravb_private *priv = netdev_priv(ndev); - struct net_device_stats *stats = &priv->stats[q]; - struct ravb_tx_desc *desc; - int free_num = 0; - int entry; - u32 size; - - for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) { - entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] * - NUM_TX_DESC); - desc = &priv->tx_ring[q][entry]; - if (desc->die_dt != DT_FEMPTY) - break; - /* Descriptor type must be checked before all other reads */ - dma_rmb(); - size = le16_to_cpu(desc->ds_tagl) & TX_DS; - /* Free the original skb. */ - if (priv->tx_skb[q][entry / NUM_TX_DESC]) { - dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - size, DMA_TO_DEVICE); - /* Last packet descriptor? */ - if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) { - entry /= NUM_TX_DESC; - dev_kfree_skb_any(priv->tx_skb[q][entry]); - priv->tx_skb[q][entry] = NULL; - stats->tx_packets++; - } - free_num++; - } - stats->tx_bytes += size; - desc->die_dt = DT_EEMPTY; - } - return free_num; -} - static void ravb_get_tx_tstamp(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); @@ -797,7 +812,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) spin_lock_irqsave(&priv->lock, flags); /* Clear TX interrupt */ ravb_write(ndev, ~mask, TIS); - ravb_tx_free(ndev, q); + ravb_tx_free(ndev, q, true); netif_wake_subqueue(ndev, q); mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); @@ -1330,6 +1345,19 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) + entry / NUM_TX_DESC * DPTR_ALIGN; len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data; + /* Zero length DMA descriptors are problematic as they seem to + * terminate DMA transfers. Avoid them by simply using a length of + * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN. + * + * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of + * data by the call to skb_put_padto() above this is safe with + * respect to both the length of the first DMA descriptor (len) + * overflowing the available data and the length of the second DMA + * descriptor (skb->len - len) being negative. + */ + if (len == 0) + len = DPTR_ALIGN; + memcpy(buffer, skb->data, len); dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE); if (dma_mapping_error(ndev->dev.parent, dma_addr)) @@ -1380,7 +1408,8 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) priv->cur_tx[q] += NUM_TX_DESC; if (priv->cur_tx[q] - priv->dirty_tx[q] > - (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && !ravb_tx_free(ndev, q)) + (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && + !ravb_tx_free(ndev, q, true)) netif_stop_subqueue(ndev, q); exit: diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 480f3dae0780..479af106aaeb 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -750,6 +750,7 @@ static struct sh_eth_cpu_data sh7734_data = { .tsu = 1, .hw_crc = 1, .select_mii = 1, + .shift_rd0 = 1, }; /* SH7763 */ @@ -818,6 +819,7 @@ static struct sh_eth_cpu_data r8a7740_data = { .rpadir_value = 2 << 16, .no_trimd = 1, .no_ade = 1, + .hw_crc = 1, .tsu = 1, .select_mii = 1, .shift_rd0 = 1, diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c index d790cb8d9db3..8e832ba8ab24 100644 --- a/drivers/net/ethernet/sfc/falcon.c +++ b/drivers/net/ethernet/sfc/falcon.c @@ -2796,6 +2796,11 @@ const struct efx_nic_type falcon_a1_nic_type = { .timer_period_max = 1 << FRF_AB_TC_TIMER_VAL_WIDTH, .offload_features = NETIF_F_IP_CSUM, .mcdi_max_ver = -1, +#ifdef CONFIG_SFC_SRIOV + .vswitching_probe = efx_port_dummy_op_int, + .vswitching_restore = efx_port_dummy_op_int, + .vswitching_remove = efx_port_dummy_op_void, +#endif }; const struct efx_nic_type falcon_b0_nic_type = { @@ -2897,4 +2902,9 @@ const struct efx_nic_type falcon_b0_nic_type = { .offload_features = NETIF_F_IP_CSUM | NETIF_F_RXHASH | NETIF_F_NTUPLE, .mcdi_max_ver = -1, .max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS, +#ifdef CONFIG_SFC_SRIOV + .vswitching_probe = efx_port_dummy_op_int, + .vswitching_restore = efx_port_dummy_op_int, + .vswitching_remove = efx_port_dummy_op_void, +#endif }; diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index d52ea3008946..7e8bce46e6b4 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1237,7 +1237,7 @@ int cpmac_init(void) goto fail_alloc; } -#warning FIXME: unhardcode gpio&reset bits + /* FIXME: unhardcode gpio&reset bits */ ar7_gpio_disable(26); ar7_gpio_disable(27); ar7_device_reset(AR7_RESET_BIT_CPMAC_LO); diff --git a/drivers/net/ethernet/ti/prueth.c b/drivers/net/ethernet/ti/prueth.c index 809b7f44f77b..5d19d3d41c5f 100644 --- a/drivers/net/ethernet/ti/prueth.c +++ b/drivers/net/ethernet/ti/prueth.c @@ -1531,9 +1531,9 @@ static int prueth_netdev_init(struct prueth *prueth, emac->phydev = of_phy_connect(ndev, emac->phy_node, &emac_adjust_link, 0, emac->phy_if); if (!emac->phydev) { - dev_err(prueth->dev, "couldn't connect to phy %s\n", + dev_dbg(prueth->dev, "couldn't connect to phy %s\n", emac->phy_node->full_name); - ret = -ENODEV; + ret = -EPROBE_DEFER; goto free; } @@ -1600,23 +1600,29 @@ static int prueth_probe(struct platform_device *pdev) prueth->dev = dev; pruss = pruss_get(dev); - if (!pruss) { - dev_err(dev, "unable to get pruss handle\n"); - return -ENODEV; + if (IS_ERR(pruss)) { + ret = PTR_ERR(pruss); + if (ret == -EPROBE_DEFER) + dev_dbg(dev, "pruss not yet available, deferring probe.\n"); + else + dev_err(dev, "unable to get pruss handle\n"); + return ret; } prueth->pruss = pruss; prueth->pru0 = pruss_rproc_get(pruss, PRUSS_PRU0); if (IS_ERR(prueth->pru0)) { ret = PTR_ERR(prueth->pru0); - dev_err(dev, "unable to get PRU0\n"); + if (ret != -EPROBE_DEFER) + dev_err(dev, "unable to get PRU0: %d\n", ret); goto pruss_put; } prueth->pru1 = pruss_rproc_get(pruss, PRUSS_PRU1); if (IS_ERR(prueth->pru1)) { ret = PTR_ERR(prueth->pru1); - dev_err(dev, "unable to get PRU1\n"); + if (ret != -EPROBE_DEFER) + dev_err(dev, "unable to get PRU1: %d\n", ret); goto put_pru0; } @@ -1671,13 +1677,11 @@ static int prueth_probe(struct platform_device *pdev) } ret = prueth_netdev_init(prueth, eth_node); if (ret) { - if (ret == -EPROBE_DEFER) { - prueth->eth_node[PRUETH_PORT_MII0] = eth_node; - goto netdev_exit; + if (ret != -EPROBE_DEFER) { + dev_err(dev, "netdev init %s failed: %d\n", + eth_node->name, ret); } - dev_err(dev, "netdev init %s failed: %d\n", - eth_node->name, ret); - of_node_put(eth_node); + goto netdev_exit; } else { prueth->eth_node[PRUETH_PORT_MII0] = eth_node; } @@ -1690,13 +1694,11 @@ static int prueth_probe(struct platform_device *pdev) } ret = prueth_netdev_init(prueth, eth_node); if (ret) { - if (ret == -EPROBE_DEFER) { - prueth->eth_node[PRUETH_PORT_MII1] = eth_node; - goto netdev_exit; + if (ret != -EPROBE_DEFER) { + dev_err(dev, "netdev init %s failed: %d\n", + eth_node->name, ret); } - dev_err(dev, "netdev init %s failed: %d\n", - eth_node->name, ret); - of_node_put(eth_node); + goto netdev_exit; } else { prueth->eth_node[PRUETH_PORT_MII1] = eth_node; } diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index cf468c87ce57..4cb8b85cbf2c 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -100,6 +100,14 @@ /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */ #define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT) +#ifdef __BIG_ENDIAN +#define xemaclite_readl ioread32be +#define xemaclite_writel iowrite32be +#else +#define xemaclite_readl ioread32 +#define xemaclite_writel iowrite32 +#endif + /** * struct net_local - Our private per device data * @ndev: instance of the network device @@ -158,15 +166,15 @@ static void xemaclite_enable_interrupts(struct net_local *drvdata) u32 reg_data; /* Enable the Tx interrupts for the first Buffer */ - reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET); - __raw_writel(reg_data | XEL_TSR_XMIT_IE_MASK, - drvdata->base_addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data | XEL_TSR_XMIT_IE_MASK, + drvdata->base_addr + XEL_TSR_OFFSET); /* Enable the Rx interrupts for the first buffer */ - __raw_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET); + xemaclite_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET); /* Enable the Global Interrupt Enable */ - __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); + xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); } /** @@ -181,17 +189,17 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata) u32 reg_data; /* Disable the Global Interrupt Enable */ - __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); + xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET); /* Disable the Tx interrupts for the first buffer */ - reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET); - __raw_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK), - drvdata->base_addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK), + drvdata->base_addr + XEL_TSR_OFFSET); /* Disable the Rx interrupts for the first buffer */ - reg_data = __raw_readl(drvdata->base_addr + XEL_RSR_OFFSET); - __raw_writel(reg_data & (~XEL_RSR_RECV_IE_MASK), - drvdata->base_addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(drvdata->base_addr + XEL_RSR_OFFSET); + xemaclite_writel(reg_data & (~XEL_RSR_RECV_IE_MASK), + drvdata->base_addr + XEL_RSR_OFFSET); } /** @@ -323,7 +331,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, byte_count = ETH_FRAME_LEN; /* Check if the expected buffer is available */ - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK)) == 0) { @@ -336,7 +344,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, addr = (void __iomem __force *)((u32 __force)addr ^ XEL_BUFFER_OFFSET); - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK)) != 0) @@ -347,16 +355,16 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, /* Write the frame to the buffer */ xemaclite_aligned_write(data, (u32 __force *) addr, byte_count); - __raw_writel((byte_count & XEL_TPLR_LENGTH_MASK), - addr + XEL_TPLR_OFFSET); + xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK), + addr + XEL_TPLR_OFFSET); /* Update the Tx Status Register to indicate that there is a * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which * is used by the interrupt handler to check whether a frame * has been transmitted */ - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK); - __raw_writel(reg_data, addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET); return 0; } @@ -371,7 +379,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, * * Return: Total number of bytes received */ -static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) +static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) { void __iomem *addr; u16 length, proto_type; @@ -381,7 +389,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) addr = (drvdata->base_addr + drvdata->next_rx_buf_to_use); /* Verify which buffer has valid data */ - reg_data = __raw_readl(addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET); if ((reg_data & XEL_RSR_RECV_DONE_MASK) == XEL_RSR_RECV_DONE_MASK) { if (drvdata->rx_ping_pong != 0) @@ -398,27 +406,28 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) return 0; /* No data was available */ /* Verify that buffer has valid data */ - reg_data = __raw_readl(addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET); if ((reg_data & XEL_RSR_RECV_DONE_MASK) != XEL_RSR_RECV_DONE_MASK) return 0; /* No data was available */ } /* Get the protocol type of the ethernet frame that arrived */ - proto_type = ((ntohl(__raw_readl(addr + XEL_HEADER_OFFSET + + proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET + XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) & XEL_RPLR_LENGTH_MASK); /* Check if received ethernet frame is a raw ethernet frame * or an IP packet or an ARP packet */ - if (proto_type > (ETH_FRAME_LEN + ETH_FCS_LEN)) { + if (proto_type > ETH_DATA_LEN) { if (proto_type == ETH_P_IP) { - length = ((ntohl(__raw_readl(addr + + length = ((ntohl(xemaclite_readl(addr + XEL_HEADER_IP_LENGTH_OFFSET + XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) & XEL_RPLR_LENGTH_MASK); + length = min_t(u16, length, ETH_DATA_LEN); length += ETH_HLEN + ETH_FCS_LEN; } else if (proto_type == ETH_P_ARP) @@ -431,14 +440,17 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data) /* Use the length in the frame, plus the header and trailer */ length = proto_type + ETH_HLEN + ETH_FCS_LEN; + if (WARN_ON(length > maxlen)) + length = maxlen; + /* Read from the EmacLite device */ xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET), data, length); /* Acknowledge the frame */ - reg_data = __raw_readl(addr + XEL_RSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET); reg_data &= ~XEL_RSR_RECV_DONE_MASK; - __raw_writel(reg_data, addr + XEL_RSR_OFFSET); + xemaclite_writel(reg_data, addr + XEL_RSR_OFFSET); return length; } @@ -465,14 +477,14 @@ static void xemaclite_update_address(struct net_local *drvdata, xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN); - __raw_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET); + xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET); /* Update the MAC address in the EmacLite */ - reg_data = __raw_readl(addr + XEL_TSR_OFFSET); - __raw_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET); + reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); + xemaclite_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET); /* Wait for EmacLite to finish with the MAC address update */ - while ((__raw_readl(addr + XEL_TSR_OFFSET) & + while ((xemaclite_readl(addr + XEL_TSR_OFFSET) & XEL_TSR_PROG_MAC_ADDR) != 0) ; } @@ -605,7 +617,7 @@ static void xemaclite_rx_handler(struct net_device *dev) skb_reserve(skb, 2); - len = xemaclite_recv_data(lp, (u8 *) skb->data); + len = xemaclite_recv_data(lp, (u8 *) skb->data, len); if (!len) { dev->stats.rx_errors++; @@ -642,32 +654,32 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id) u32 tx_status; /* Check if there is Rx Data available */ - if ((__raw_readl(base_addr + XEL_RSR_OFFSET) & + if ((xemaclite_readl(base_addr + XEL_RSR_OFFSET) & XEL_RSR_RECV_DONE_MASK) || - (__raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET) + (xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET) & XEL_RSR_RECV_DONE_MASK)) xemaclite_rx_handler(dev); /* Check if the Transmission for the first buffer is completed */ - tx_status = __raw_readl(base_addr + XEL_TSR_OFFSET); + tx_status = xemaclite_readl(base_addr + XEL_TSR_OFFSET); if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) && (tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) { tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK; - __raw_writel(tx_status, base_addr + XEL_TSR_OFFSET); + xemaclite_writel(tx_status, base_addr + XEL_TSR_OFFSET); tx_complete = true; } /* Check if the Transmission for the second buffer is completed */ - tx_status = __raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); + tx_status = xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) && (tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) { tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK; - __raw_writel(tx_status, base_addr + XEL_BUFFER_OFFSET + - XEL_TSR_OFFSET); + xemaclite_writel(tx_status, base_addr + XEL_BUFFER_OFFSET + + XEL_TSR_OFFSET); tx_complete = true; } @@ -700,7 +712,7 @@ static int xemaclite_mdio_wait(struct net_local *lp) /* wait for the MDIO interface to not be busy or timeout after some time. */ - while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) & + while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) & XEL_MDIOCTRL_MDIOSTS_MASK) { if (time_before_eq(end, jiffies)) { WARN_ON(1); @@ -736,17 +748,17 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg) * MDIO Address register. Set the Status bit in the MDIO Control * register to start a MDIO read transaction. */ - ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); - __raw_writel(XEL_MDIOADDR_OP_MASK | - ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), - lp->base_addr + XEL_MDIOADDR_OFFSET); - __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, - lp->base_addr + XEL_MDIOCTRL_OFFSET); + ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); + xemaclite_writel(XEL_MDIOADDR_OP_MASK | + ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), + lp->base_addr + XEL_MDIOADDR_OFFSET); + xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, + lp->base_addr + XEL_MDIOCTRL_OFFSET); if (xemaclite_mdio_wait(lp)) return -ETIMEDOUT; - rc = __raw_readl(lp->base_addr + XEL_MDIORD_OFFSET); + rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET); dev_dbg(&lp->ndev->dev, "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n", @@ -783,13 +795,13 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, * Data register. Finally, set the Status bit in the MDIO Control * register to start a MDIO write transaction. */ - ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); - __raw_writel(~XEL_MDIOADDR_OP_MASK & - ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), - lp->base_addr + XEL_MDIOADDR_OFFSET); - __raw_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET); - __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, - lp->base_addr + XEL_MDIOCTRL_OFFSET); + ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET); + xemaclite_writel(~XEL_MDIOADDR_OP_MASK & + ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg), + lp->base_addr + XEL_MDIOADDR_OFFSET); + xemaclite_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET); + xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK, + lp->base_addr + XEL_MDIOCTRL_OFFSET); return 0; } @@ -836,8 +848,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) /* Enable the MDIO bus by asserting the enable bit in MDIO Control * register. */ - __raw_writel(XEL_MDIOCTRL_MDIOEN_MASK, - lp->base_addr + XEL_MDIOCTRL_OFFSET); + xemaclite_writel(XEL_MDIOCTRL_MDIOEN_MASK, + lp->base_addr + XEL_MDIOCTRL_OFFSET); bus = mdiobus_alloc(); if (!bus) { @@ -1141,8 +1153,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev) dev_warn(dev, "No MAC address found\n"); /* Clear the Tx CSR's in case this is a restart */ - __raw_writel(0, lp->base_addr + XEL_TSR_OFFSET); - __raw_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); + xemaclite_writel(0, lp->base_addr + XEL_TSR_OFFSET); + xemaclite_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET); /* Set the MAC address in the EmacLite device */ xemaclite_update_address(lp, ndev->dev_addr); diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 85828f153445..0758d0816840 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -648,8 +648,8 @@ static void ax_setup(struct net_device *dev) { /* Finish setting up the DEVICE info. */ dev->mtu = AX_MTU; - dev->hard_header_len = 0; - dev->addr_len = 0; + dev->hard_header_len = AX25_MAX_HEADER_LEN; + dev->addr_len = AX25_ADDR_LEN; dev->type = ARPHRD_AX25; dev->tx_queue_len = 10; dev->header_ops = &ax25_header_ops; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 7a601d8c615e..c8a7802d2953 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -197,65 +197,6 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size, return ppi; } -union sub_key { - u64 k; - struct { - u8 pad[3]; - u8 kb; - u32 ka; - }; -}; - -/* Toeplitz hash function - * data: network byte order - * return: host byte order - */ -static u32 comp_hash(u8 *key, int klen, void *data, int dlen) -{ - union sub_key subk; - int k_next = 4; - u8 dt; - int i, j; - u32 ret = 0; - - subk.k = 0; - subk.ka = ntohl(*(u32 *)key); - - for (i = 0; i < dlen; i++) { - subk.kb = key[k_next]; - k_next = (k_next + 1) % klen; - dt = ((u8 *)data)[i]; - for (j = 0; j < 8; j++) { - if (dt & 0x80) - ret ^= subk.ka; - dt <<= 1; - subk.k <<= 1; - } - } - - return ret; -} - -static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb) -{ - struct flow_keys flow; - int data_len; - - if (!skb_flow_dissect_flow_keys(skb, &flow, 0) || - !(flow.basic.n_proto == htons(ETH_P_IP) || - flow.basic.n_proto == htons(ETH_P_IPV6))) - return false; - - if (flow.basic.ip_proto == IPPROTO_TCP) - data_len = 12; - else - data_len = 8; - - *hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len); - - return true; -} - static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback) { @@ -268,11 +209,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1) return 0; - if (netvsc_set_hash(&hash, skb)) { - q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] % - ndev->real_num_tx_queues; - skb_set_hash(skb, hash, PKT_HASH_TYPE_L3); - } + hash = skb_get_hash(skb); + q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] % + ndev->real_num_tx_queues; return q_idx; } @@ -854,7 +793,6 @@ static int netvsc_set_channels(struct net_device *net, } goto recover; } - netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE); out: netvsc_open(net); @@ -1142,6 +1080,7 @@ static int netvsc_probe(struct hv_device *dev, nvdev = hv_get_drvdata(dev); netif_set_real_num_tx_queues(net, nvdev->num_chn); netif_set_real_num_rx_queues(net, nvdev->num_chn); + netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE); ret = register_netdev(net); if (ret != 0) { diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c index 860d4aed8274..43617ded3773 100644 --- a/drivers/net/ieee802154/fakelb.c +++ b/drivers/net/ieee802154/fakelb.c @@ -30,7 +30,7 @@ static int numlbs = 2; static LIST_HEAD(fakelb_phys); -static DEFINE_SPINLOCK(fakelb_phys_lock); +static DEFINE_MUTEX(fakelb_phys_lock); static LIST_HEAD(fakelb_ifup_phys); static DEFINE_RWLOCK(fakelb_ifup_phys_lock); @@ -180,9 +180,9 @@ static int fakelb_add_one(struct device *dev) if (err) goto err_reg; - spin_lock(&fakelb_phys_lock); + mutex_lock(&fakelb_phys_lock); list_add_tail(&phy->list, &fakelb_phys); - spin_unlock(&fakelb_phys_lock); + mutex_unlock(&fakelb_phys_lock); return 0; @@ -214,10 +214,10 @@ static int fakelb_probe(struct platform_device *pdev) return 0; err_slave: - spin_lock(&fakelb_phys_lock); + mutex_lock(&fakelb_phys_lock); list_for_each_entry_safe(phy, tmp, &fakelb_phys, list) fakelb_del(phy); - spin_unlock(&fakelb_phys_lock); + mutex_unlock(&fakelb_phys_lock); return err; } @@ -225,10 +225,10 @@ static int fakelb_remove(struct platform_device *pdev) { struct fakelb_phy *phy, *tmp; - spin_lock(&fakelb_phys_lock); + mutex_lock(&fakelb_phys_lock); list_for_each_entry_safe(phy, tmp, &fakelb_phys, list) fakelb_del(phy); - spin_unlock(&fakelb_phys_lock); + mutex_unlock(&fakelb_phys_lock); return 0; } diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index 25f21968fa5c..de2ea9f2f966 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -1077,7 +1077,7 @@ static int stir421x_patch_device(struct irda_usb_cb *self) * are "42101001.sb" or "42101002.sb" */ sprintf(stir421x_fw_name, "4210%4X.sb", - self->usbdev->descriptor.bcdDevice); + le16_to_cpu(self->usbdev->descriptor.bcdDevice)); ret = request_firmware(&fw, stir421x_fw_name, &self->usbdev->dev); if (ret < 0) return ret; diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c index bca6a1e72d1d..e1bb802d4a4d 100644 --- a/drivers/net/irda/mcs7780.c +++ b/drivers/net/irda/mcs7780.c @@ -141,9 +141,19 @@ static int mcs_set_reg(struct mcs_cb *mcs, __u16 reg, __u16 val) static int mcs_get_reg(struct mcs_cb *mcs, __u16 reg, __u16 * val) { struct usb_device *dev = mcs->usbdev; - int ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ, - MCS_RD_RTYPE, 0, reg, val, 2, - msecs_to_jiffies(MCS_CTRL_TIMEOUT)); + void *dmabuf; + int ret; + + dmabuf = kmalloc(sizeof(__u16), GFP_KERNEL); + if (!dmabuf) + return -ENOMEM; + + ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ, + MCS_RD_RTYPE, 0, reg, dmabuf, 2, + msecs_to_jiffies(MCS_CTRL_TIMEOUT)); + + memcpy(val, dmabuf, sizeof(__u16)); + kfree(dmabuf); return ret; } diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index dc7d970bd1c0..effcdbfb06e9 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -164,6 +164,7 @@ static void loopback_setup(struct net_device *dev) { dev->mtu = 64 * 1024; dev->hard_header_len = ETH_HLEN; /* 14 */ + dev->min_header_len = ETH_HLEN; /* 14 */ dev->addr_len = ETH_ALEN; /* 6 */ dev->type = ARPHRD_LOOPBACK; /* 0x0001*/ dev->flags = IFF_LOOPBACK; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 06c8bfeaccd6..40cd86614677 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1110,6 +1110,7 @@ static int macvlan_port_create(struct net_device *dev) static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = macvlan_port_get_rtnl(dev); + struct sk_buff *skb; dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); @@ -1118,7 +1119,15 @@ static void macvlan_port_destroy(struct net_device *dev) * but we need to cancel it and purge left skbs if any. */ cancel_work_sync(&port->bc_work); - __skb_queue_purge(&port->bc_queue); + + while ((skb = __skb_dequeue(&port->bc_queue))) { + const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; + + if (src) + dev_put(src->dev); + + kfree_skb(skb); + } kfree_rcu(port, rcu); } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 159a68782bec..79de9608ac48 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -725,7 +725,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, ssize_t n; if (q->flags & IFF_VNET_HDR) { - vnet_hdr_len = q->vnet_hdr_sz; + vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz); err = -EINVAL; if (len < vnet_hdr_len) @@ -865,7 +865,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, if (q->flags & IFF_VNET_HDR) { struct virtio_net_hdr vnet_hdr; - vnet_hdr_len = q->vnet_hdr_sz; + vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz); if (iov_iter_count(iter) < vnet_hdr_len) return -EINVAL; diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index 86b28052bf06..9b709f78bb03 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -21,6 +21,23 @@ MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver"); MODULE_AUTHOR("Maxime Bizon <mbizon@freebox.fr>"); MODULE_LICENSE("GPL"); +static int bcm63xx_config_intr(struct phy_device *phydev) +{ + int reg, err; + + reg = phy_read(phydev, MII_BCM63XX_IR); + if (reg < 0) + return reg; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + reg &= ~MII_BCM63XX_IR_GMASK; + else + reg |= MII_BCM63XX_IR_GMASK; + + err = phy_write(phydev, MII_BCM63XX_IR, reg); + return err; +} + static int bcm63xx_config_init(struct phy_device *phydev) { int reg, err; @@ -55,7 +72,7 @@ static struct phy_driver bcm63xx_driver[] = { .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = bcm_phy_ack_intr, - .config_intr = bcm_phy_config_intr, + .config_intr = bcm63xx_config_intr, .driver = { .owner = THIS_MODULE }, }, { /* same phy as above, with just a different OUI */ @@ -68,7 +85,7 @@ static struct phy_driver bcm63xx_driver[] = { .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = bcm_phy_ack_intr, - .config_intr = bcm_phy_config_intr, + .config_intr = bcm63xx_config_intr, .driver = { .owner = THIS_MODULE }, } }; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index e6cefd0e3262..e83acc608678 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -907,7 +907,7 @@ static void decode_txts(struct dp83640_private *dp83640, if (overflow) { pr_debug("tx timestamp queue overflow, count %d\n", overflow); while (skb) { - skb_complete_tx_timestamp(skb, NULL); + kfree_skb(skb); skb = skb_dequeue(&dp83640->tx_queue); } return; @@ -1436,8 +1436,6 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; skb_queue_tail(&dp83640->rx_queue, skb); schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT); - } else { - netif_rx_ni(skb); } return true; diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index fd27f7144d4a..85112cc4787f 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -29,6 +29,7 @@ #define MII_DP83867_MICR 0x12 #define MII_DP83867_ISR 0x13 #define DP83867_CTRL 0x1f +#define DP83867_CFG3 0x1e /* Extended Registers */ #define DP83867_RGMIICTL 0x0032 @@ -98,6 +99,8 @@ static int dp83867_config_intr(struct phy_device *phydev) micr_status |= (MII_DP83867_MICR_AN_ERR_INT_EN | MII_DP83867_MICR_SPEED_CHNG_INT_EN | + MII_DP83867_MICR_AUTONEG_COMP_INT_EN | + MII_DP83867_MICR_LINK_STS_CHNG_INT_EN | MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN | MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN); @@ -222,6 +225,13 @@ static int dp83867_config_init(struct phy_device *phydev) } } + /* Enable Interrupt output INT_OE in CFG3 register */ + if (phy_interrupt_is_valid(phydev)) { + val = phy_read(phydev, DP83867_CFG3); + val |= BIT(7); + phy_write(phydev, DP83867_CFG3, val); + } + return 0; } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 0240552b50f3..ebec2dceff45 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -203,34 +203,6 @@ static int marvell_config_aneg(struct phy_device *phydev) { int err; - /* The Marvell PHY has an errata which requires - * that certain registers get written in order - * to restart autonegotiation */ - err = phy_write(phydev, MII_BMCR, BMCR_RESET); - - if (err < 0) - return err; - - err = phy_write(phydev, 0x1d, 0x1f); - if (err < 0) - return err; - - err = phy_write(phydev, 0x1e, 0x200c); - if (err < 0) - return err; - - err = phy_write(phydev, 0x1d, 0x5); - if (err < 0) - return err; - - err = phy_write(phydev, 0x1e, 0); - if (err < 0) - return err; - - err = phy_write(phydev, 0x1e, 0x100); - if (err < 0) - return err; - err = marvell_set_polarity(phydev, phydev->mdix); if (err < 0) return err; @@ -264,6 +236,42 @@ static int marvell_config_aneg(struct phy_device *phydev) return 0; } +static int m88e1101_config_aneg(struct phy_device *phydev) +{ + int err; + + /* This Marvell PHY has an errata which requires + * that certain registers get written in order + * to restart autonegotiation + */ + err = phy_write(phydev, MII_BMCR, BMCR_RESET); + + if (err < 0) + return err; + + err = phy_write(phydev, 0x1d, 0x1f); + if (err < 0) + return err; + + err = phy_write(phydev, 0x1e, 0x200c); + if (err < 0) + return err; + + err = phy_write(phydev, 0x1d, 0x5); + if (err < 0) + return err; + + err = phy_write(phydev, 0x1e, 0); + if (err < 0) + return err; + + err = phy_write(phydev, 0x1e, 0x100); + if (err < 0) + return err; + + return marvell_config_aneg(phydev); +} + #ifdef CONFIG_OF_MDIO /* * Set and/or override some configuration registers based on the @@ -814,8 +822,6 @@ static int marvell_read_status(struct phy_device *phydev) phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb) | mii_lpa_to_ethtool_lpa_t(lpa); - lpa &= adv; - if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) phydev->duplex = DUPLEX_FULL; else @@ -993,7 +999,7 @@ static struct phy_driver marvell_drivers[] = { .name = "Marvell 88E1101", .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, - .config_aneg = &marvell_config_aneg, + .config_aneg = &m88e1101_config_aneg, .read_status = &genphy_read_status, .ack_interrupt = &marvell_ack_interrupt, .config_intr = &marvell_config_intr, diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c index c0b4e65267af..46fe1ae919a3 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/phy/mdio-bcm-iproc.c @@ -81,8 +81,6 @@ static int iproc_mdio_read(struct mii_bus *bus, int phy_id, int reg) if (rc) return rc; - iproc_mdio_config_clk(priv->base); - /* Prepare the read operation */ cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) | (reg << MII_DATA_RA_SHIFT) | @@ -112,8 +110,6 @@ static int iproc_mdio_write(struct mii_bus *bus, int phy_id, if (rc) return rc; - iproc_mdio_config_clk(priv->base); - /* Prepare the write operation */ cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) | (reg << MII_DATA_RA_SHIFT) | @@ -163,6 +159,8 @@ static int iproc_mdio_probe(struct platform_device *pdev) bus->read = iproc_mdio_read; bus->write = iproc_mdio_write; + iproc_mdio_config_clk(priv->base); + rc = of_mdiobus_register(bus, pdev->dev.of_node); if (rc) { dev_err(&pdev->dev, "MDIO bus registration failed\n"); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index e13ad6cdcc22..c8b85f1069ff 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -539,6 +539,8 @@ static int ksz9031_read_status(struct phy_device *phydev) if ((regval & 0xFF) == 0xFF) { phy_init_hw(phydev); phydev->link = 0; + if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) + phydev->drv->config_intr(phydev); } return 0; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index bba0ca786aaa..49d9f0a789fe 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -538,9 +538,12 @@ void phy_stop_machine(struct phy_device *phydev) cancel_delayed_work_sync(&phydev->state_queue); mutex_lock(&phydev->lock); - if (phydev->state > PHY_UP) + if (phydev->state > PHY_UP && phydev->state != PHY_HALTED) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); + + /* Now we can run the state machine synchronously */ + phy_state_machine(&phydev->state_queue.work); } /** @@ -918,6 +921,15 @@ void phy_state_machine(struct work_struct *work) if (old_link != phydev->link) phydev->state = PHY_CHANGELINK; } + /* + * Failsafe: check that nobody set phydev->link=0 between two + * poll cycles, otherwise we won't leave RUNNING state as long + * as link remains down. + */ + if (!phydev->link && phydev->state == PHY_RUNNING) { + phydev->state = PHY_CHANGELINK; + dev_err(&phydev->dev, "no link in PHY_RUNNING\n"); + } break; case PHY_CHANGELINK: err = phy_read_status(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 0bfbabad4431..8179727d3423 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1368,6 +1368,8 @@ static int phy_remove(struct device *dev) { struct phy_device *phydev = to_phy_device(dev); + cancel_delayed_work_sync(&phydev->state_queue); + mutex_lock(&phydev->lock); phydev->state = PHY_DOWN; mutex_unlock(&phydev->lock); @@ -1442,7 +1444,7 @@ static struct phy_driver genphy_driver[] = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic PHY", - .soft_reset = genphy_soft_reset, + .soft_reset = genphy_no_soft_reset, .config_init = genphy_config_init, .features = PHY_GBIT_FEATURES | SUPPORTED_MII | SUPPORTED_AUI | SUPPORTED_FIBRE | diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 6941f0888b00..63778be9e768 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1105,9 +1105,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } if (tun->flags & IFF_VNET_HDR) { - if (len < tun->vnet_hdr_sz) + int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); + + if (len < vnet_hdr_sz) return -EINVAL; - len -= tun->vnet_hdr_sz; + len -= vnet_hdr_sz; n = copy_from_iter(&gso, sizeof(gso), from); if (n != sizeof(gso)) @@ -1119,7 +1121,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (tun16_to_cpu(tun, gso.hdr_len) > len) return -EINVAL; - iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso)); + iov_iter_advance(from, vnet_hdr_sz - sizeof(gso)); } if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) { @@ -1298,7 +1300,7 @@ static ssize_t tun_put_user(struct tun_struct *tun, vlan_hlen = VLAN_HLEN; if (tun->flags & IFF_VNET_HDR) - vnet_hdr_sz = tun->vnet_hdr_sz; + vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); total = skb->len + vlan_hlen + vnet_hdr_sz; diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 4e2b26a88b15..2aa1a1d29cb4 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -777,7 +777,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id struct net_device *netdev; struct catc *catc; u8 broadcast[ETH_ALEN]; - int i, pktsz; + int pktsz, ret; if (usb_set_interface(usbdev, intf->altsetting->desc.bInterfaceNumber, 1)) { @@ -812,12 +812,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id if ((!catc->ctrl_urb) || (!catc->tx_urb) || (!catc->rx_urb) || (!catc->irq_urb)) { dev_err(&intf->dev, "No free urbs available.\n"); - usb_free_urb(catc->ctrl_urb); - usb_free_urb(catc->tx_urb); - usb_free_urb(catc->rx_urb); - usb_free_urb(catc->irq_urb); - free_netdev(netdev); - return -ENOMEM; + ret = -ENOMEM; + goto fail_free; } /* The F5U011 has the same vendor/product as the netmate but a device version of 0x130 */ @@ -845,15 +841,24 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id catc->irq_buf, 2, catc_irq_done, catc, 1); if (!catc->is_f5u011) { + u32 *buf; + int i; + dev_dbg(dev, "Checking memory size\n"); - i = 0x12345678; - catc_write_mem(catc, 0x7a80, &i, 4); - i = 0x87654321; - catc_write_mem(catc, 0xfa80, &i, 4); - catc_read_mem(catc, 0x7a80, &i, 4); + buf = kmalloc(4, GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto fail_free; + } + + *buf = 0x12345678; + catc_write_mem(catc, 0x7a80, buf, 4); + *buf = 0x87654321; + catc_write_mem(catc, 0xfa80, buf, 4); + catc_read_mem(catc, 0x7a80, buf, 4); - switch (i) { + switch (*buf) { case 0x12345678: catc_set_reg(catc, TxBufCount, 8); catc_set_reg(catc, RxBufCount, 32); @@ -868,6 +873,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id dev_dbg(dev, "32k Memory\n"); break; } + + kfree(buf); dev_dbg(dev, "Getting MAC from SEEROM.\n"); @@ -914,16 +921,21 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id usb_set_intfdata(intf, catc); SET_NETDEV_DEV(netdev, &intf->dev); - if (register_netdev(netdev) != 0) { - usb_set_intfdata(intf, NULL); - usb_free_urb(catc->ctrl_urb); - usb_free_urb(catc->tx_urb); - usb_free_urb(catc->rx_urb); - usb_free_urb(catc->irq_urb); - free_netdev(netdev); - return -EIO; - } + ret = register_netdev(netdev); + if (ret) + goto fail_clear_intfdata; + return 0; + +fail_clear_intfdata: + usb_set_intfdata(intf, NULL); +fail_free: + usb_free_urb(catc->ctrl_urb); + usb_free_urb(catc->tx_urb); + usb_free_urb(catc->rx_urb); + usb_free_urb(catc->irq_urb); + free_netdev(netdev); + return ret; } static void catc_disconnect(struct usb_interface *intf) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 7cba2c3759df..8c408aa2f208 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -462,6 +462,7 @@ static const struct driver_info wwan_info = { #define SAMSUNG_VENDOR_ID 0x04e8 #define LENOVO_VENDOR_ID 0x17ef #define NVIDIA_VENDOR_ID 0x0955 +#define HP_VENDOR_ID 0x03f0 static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -608,6 +609,13 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* HP lt2523 (Novatel E371) - handled by qmi_wwan */ +{ + USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* AnyDATA ADU960S - handled by qmi_wwan */ { USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM, diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index f64b25c221e8..cd93220c9b45 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -1009,6 +1009,7 @@ static int kaweth_probe( struct net_device *netdev; const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; int result = 0; + int rv = -EIO; dev_dbg(dev, "Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n", @@ -1029,6 +1030,7 @@ static int kaweth_probe( kaweth = netdev_priv(netdev); kaweth->dev = udev; kaweth->net = netdev; + kaweth->intf = intf; spin_lock_init(&kaweth->device_lock); init_waitqueue_head(&kaweth->term_wait); @@ -1048,6 +1050,10 @@ static int kaweth_probe( /* Download the firmware */ dev_info(dev, "Downloading firmware...\n"); kaweth->firmware_buf = (__u8 *)__get_free_page(GFP_KERNEL); + if (!kaweth->firmware_buf) { + rv = -ENOMEM; + goto err_free_netdev; + } if ((result = kaweth_download_firmware(kaweth, "kaweth/new_code.bin", 100, @@ -1139,8 +1145,6 @@ err_fw: dev_dbg(dev, "Initializing net device.\n"); - kaweth->intf = intf; - kaweth->tx_urb = usb_alloc_urb(0, GFP_KERNEL); if (!kaweth->tx_urb) goto err_free_netdev; @@ -1204,7 +1208,7 @@ err_only_tx: err_free_netdev: free_netdev(netdev); - return -EIO; + return rv; } /**************************************************************** diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index f84080215915..17fac0121e56 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -126,40 +126,61 @@ static void async_ctrl_callback(struct urb *urb) static int get_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data) { + u8 *buf; int ret; + buf = kmalloc(size, GFP_NOIO); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(pegasus->usb, usb_rcvctrlpipe(pegasus->usb, 0), PEGASUS_REQ_GET_REGS, PEGASUS_REQT_READ, 0, - indx, data, size, 1000); + indx, buf, size, 1000); if (ret < 0) netif_dbg(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + else if (ret <= size) + memcpy(data, buf, ret); + kfree(buf); return ret; } -static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data) +static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, + const void *data) { + u8 *buf; int ret; + buf = kmemdup(data, size, GFP_NOIO); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0), PEGASUS_REQ_SET_REGS, PEGASUS_REQT_WRITE, 0, - indx, data, size, 100); + indx, buf, size, 100); if (ret < 0) netif_dbg(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + kfree(buf); return ret; } static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data) { + u8 *buf; int ret; + buf = kmemdup(&data, 1, GFP_NOIO); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0), PEGASUS_REQ_SET_REG, PEGASUS_REQT_WRITE, data, - indx, &data, 1, 1000); + indx, buf, 1, 1000); if (ret < 0) netif_dbg(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + kfree(buf); return ret; } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index a34f491224c1..958af3b1af7f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -485,6 +485,13 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* HP lt2523 (Novatel E371) */ + USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&qmi_wwan_info, + }, { /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */ USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, @@ -700,6 +707,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */ {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ + {QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ @@ -723,6 +731,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ @@ -747,6 +757,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ + {QMI_FIXED_INTF(0x1e0e, 0x9001, 5)}, /* SIMCom 7230E */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 32b7ec976dcc..1c27e6fb99f9 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1645,7 +1645,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc) u8 checksum = CHECKSUM_NONE; u32 opts2, opts3; - if (tp->version == RTL_VER_01) + if (!(tp->netdev->features & NETIF_F_RXCSUM)) goto return_result; opts2 = le32_to_cpu(rx_desc->opts2); @@ -1851,6 +1851,9 @@ static int r8152_poll(struct napi_struct *napi, int budget) napi_complete(napi); if (!list_empty(&tp->rx_done)) napi_schedule(napi); + else if (!skb_queue_empty(&tp->tx_queue) && + !list_empty(&tp->tx_free)) + napi_schedule(napi); } return work_done; @@ -2990,10 +2993,13 @@ static void set_carrier(struct r8152 *tp) if (!netif_carrier_ok(netdev)) { tp->rtl_ops.enable(tp); set_bit(RTL8152_SET_RX_MODE, &tp->flags); + netif_stop_queue(netdev); napi_disable(&tp->napi); netif_carrier_on(netdev); rtl_start_rx(tp); napi_enable(&tp->napi); + netif_wake_queue(netdev); + netif_info(tp, link, netdev, "carrier on\n"); } } else { if (netif_carrier_ok(netdev)) { @@ -3001,6 +3007,7 @@ static void set_carrier(struct r8152 *tp) napi_disable(&tp->napi); tp->rtl_ops.disable(tp); napi_enable(&tp->napi); + netif_info(tp, link, netdev, "carrier off\n"); } } } @@ -3385,12 +3392,12 @@ static int rtl8152_pre_reset(struct usb_interface *intf) if (!netif_running(netdev)) return 0; + netif_stop_queue(netdev); napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); if (netif_carrier_ok(netdev)) { - netif_stop_queue(netdev); mutex_lock(&tp->control); tp->rtl_ops.disable(tp); mutex_unlock(&tp->control); @@ -3415,12 +3422,14 @@ static int rtl8152_post_reset(struct usb_interface *intf) if (netif_carrier_ok(netdev)) { mutex_lock(&tp->control); tp->rtl_ops.enable(tp); + rtl_start_rx(tp); rtl8152_set_rx_mode(netdev); mutex_unlock(&tp->control); - netif_wake_queue(netdev); } napi_enable(&tp->napi); + netif_wake_queue(netdev); + usb_submit_urb(tp->intr_urb, GFP_KERNEL); return 0; } @@ -3442,6 +3451,8 @@ static bool delay_autosuspend(struct r8152 *tp) */ if (!sw_linking && tp->rtl_ops.in_nway(tp)) return true; + else if (!skb_queue_empty(&tp->tx_queue)) + return true; else return false; } @@ -4221,6 +4232,11 @@ static int rtl8152_probe(struct usb_interface *intf, NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + if (tp->version == RTL_VER_01) { + netdev->features &= ~NETIF_F_RXCSUM; + netdev->hw_features &= ~NETIF_F_RXCSUM; + } + netdev->ethtool_ops = &ops; netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE); diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index d37b7dce2d40..39672984dde1 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -155,16 +155,36 @@ static const char driver_name [] = "rtl8150"; */ static int get_registers(rtl8150_t * dev, u16 indx, u16 size, void *data) { - return usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), - RTL8150_REQ_GET_REGS, RTL8150_REQT_READ, - indx, 0, data, size, 500); + void *buf; + int ret; + + buf = kmalloc(size, GFP_NOIO); + if (!buf) + return -ENOMEM; + + ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), + RTL8150_REQ_GET_REGS, RTL8150_REQT_READ, + indx, 0, buf, size, 500); + if (ret > 0 && ret <= size) + memcpy(data, buf, ret); + kfree(buf); + return ret; } -static int set_registers(rtl8150_t * dev, u16 indx, u16 size, void *data) +static int set_registers(rtl8150_t * dev, u16 indx, u16 size, const void *data) { - return usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), - RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE, - indx, 0, data, size, 500); + void *buf; + int ret; + + buf = kmemdup(data, size, GFP_NOIO); + if (!buf) + return -ENOMEM; + + ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), + RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE, + indx, 0, buf, size, 500); + kfree(buf); + return ret; } static void async_set_reg_cb(struct urb *urb) diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index a251588762ec..0b5a84c9022c 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -73,8 +73,6 @@ static atomic_t iface_counter = ATOMIC_INIT(0); /* Private data structure */ struct sierra_net_data { - u8 ethr_hdr_tmpl[ETH_HLEN]; /* ethernet header template for rx'd pkts */ - u16 link_up; /* air link up or down */ u8 tx_hdr_template[4]; /* part of HIP hdr for tx'd packets */ @@ -122,6 +120,7 @@ struct param { /* LSI Protocol types */ #define SIERRA_NET_PROTOCOL_UMTS 0x01 +#define SIERRA_NET_PROTOCOL_UMTS_DS 0x04 /* LSI Coverage */ #define SIERRA_NET_COVERAGE_NONE 0x00 #define SIERRA_NET_COVERAGE_NOPACKET 0x01 @@ -129,7 +128,8 @@ struct param { /* LSI Session */ #define SIERRA_NET_SESSION_IDLE 0x00 /* LSI Link types */ -#define SIERRA_NET_AS_LINK_TYPE_IPv4 0x00 +#define SIERRA_NET_AS_LINK_TYPE_IPV4 0x00 +#define SIERRA_NET_AS_LINK_TYPE_IPV6 0x02 struct lsi_umts { u8 protocol; @@ -137,9 +137,14 @@ struct lsi_umts { __be16 length; /* eventually use a union for the rest - assume umts for now */ u8 coverage; - u8 unused2[41]; + u8 network_len; /* network name len */ + u8 network[40]; /* network name (UCS2, bigendian) */ u8 session_state; u8 unused3[33]; +} __packed; + +struct lsi_umts_single { + struct lsi_umts lsi; u8 link_type; u8 pdp_addr_len; /* NW-supplied PDP address len */ u8 pdp_addr[16]; /* NW-supplied PDP address (bigendian)) */ @@ -158,10 +163,31 @@ struct lsi_umts { u8 reserved[8]; } __packed; +struct lsi_umts_dual { + struct lsi_umts lsi; + u8 pdp_addr4_len; /* NW-supplied PDP IPv4 address len */ + u8 pdp_addr4[4]; /* NW-supplied PDP IPv4 address (bigendian)) */ + u8 pdp_addr6_len; /* NW-supplied PDP IPv6 address len */ + u8 pdp_addr6[16]; /* NW-supplied PDP IPv6 address (bigendian)) */ + u8 unused4[23]; + u8 dns1_addr4_len; /* NW-supplied 1st DNS v4 address len (bigendian) */ + u8 dns1_addr4[4]; /* NW-supplied 1st DNS v4 address */ + u8 dns1_addr6_len; /* NW-supplied 1st DNS v6 address len */ + u8 dns1_addr6[16]; /* NW-supplied 1st DNS v6 address (bigendian)*/ + u8 dns2_addr4_len; /* NW-supplied 2nd DNS v4 address len (bigendian) */ + u8 dns2_addr4[4]; /* NW-supplied 2nd DNS v4 address */ + u8 dns2_addr6_len; /* NW-supplied 2nd DNS v6 address len */ + u8 dns2_addr6[16]; /* NW-supplied 2nd DNS v6 address (bigendian)*/ + u8 unused5[68]; +} __packed; + #define SIERRA_NET_LSI_COMMON_LEN 4 -#define SIERRA_NET_LSI_UMTS_LEN (sizeof(struct lsi_umts)) +#define SIERRA_NET_LSI_UMTS_LEN (sizeof(struct lsi_umts_single)) #define SIERRA_NET_LSI_UMTS_STATUS_LEN \ (SIERRA_NET_LSI_UMTS_LEN - SIERRA_NET_LSI_COMMON_LEN) +#define SIERRA_NET_LSI_UMTS_DS_LEN (sizeof(struct lsi_umts_dual)) +#define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \ + (SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN) /* Forward definitions */ static void sierra_sync_timer(unsigned long syncdata); @@ -191,10 +217,11 @@ static inline void sierra_net_set_private(struct usbnet *dev, dev->data[0] = (unsigned long)priv; } -/* is packet IPv4 */ +/* is packet IPv4/IPv6 */ static inline int is_ip(struct sk_buff *skb) { - return skb->protocol == cpu_to_be16(ETH_P_IP); + return skb->protocol == cpu_to_be16(ETH_P_IP) || + skb->protocol == cpu_to_be16(ETH_P_IPV6); } /* @@ -350,49 +377,54 @@ static inline int sierra_net_is_valid_addrlen(u8 len) static int sierra_net_parse_lsi(struct usbnet *dev, char *data, int datalen) { struct lsi_umts *lsi = (struct lsi_umts *)data; + u32 expected_length; - if (datalen < sizeof(struct lsi_umts)) { - netdev_err(dev->net, "%s: Data length %d, exp %Zu\n", - __func__, datalen, - sizeof(struct lsi_umts)); + if (datalen < sizeof(struct lsi_umts_single)) { + netdev_err(dev->net, "%s: Data length %d, exp >= %Zu\n", + __func__, datalen, sizeof(struct lsi_umts_single)); return -1; } - if (lsi->length != cpu_to_be16(SIERRA_NET_LSI_UMTS_STATUS_LEN)) { - netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n", - __func__, be16_to_cpu(lsi->length), - (u32)SIERRA_NET_LSI_UMTS_STATUS_LEN); - return -1; + /* Validate the session state */ + if (lsi->session_state == SIERRA_NET_SESSION_IDLE) { + netdev_err(dev->net, "Session idle, 0x%02x\n", + lsi->session_state); + return 0; } /* Validate the protocol - only support UMTS for now */ - if (lsi->protocol != SIERRA_NET_PROTOCOL_UMTS) { + if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS) { + struct lsi_umts_single *single = (struct lsi_umts_single *)lsi; + + /* Validate the link type */ + if (single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV4 && + single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV6) { + netdev_err(dev->net, "Link type unsupported: 0x%02x\n", + single->link_type); + return -1; + } + expected_length = SIERRA_NET_LSI_UMTS_STATUS_LEN; + } else if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS_DS) { + expected_length = SIERRA_NET_LSI_UMTS_DS_STATUS_LEN; + } else { netdev_err(dev->net, "Protocol unsupported, 0x%02x\n", - lsi->protocol); + lsi->protocol); return -1; } - /* Validate the link type */ - if (lsi->link_type != SIERRA_NET_AS_LINK_TYPE_IPv4) { - netdev_err(dev->net, "Link type unsupported: 0x%02x\n", - lsi->link_type); + if (be16_to_cpu(lsi->length) != expected_length) { + netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n", + __func__, be16_to_cpu(lsi->length), expected_length); return -1; } /* Validate the coverage */ - if (lsi->coverage == SIERRA_NET_COVERAGE_NONE - || lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) { + if (lsi->coverage == SIERRA_NET_COVERAGE_NONE || + lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) { netdev_err(dev->net, "No coverage, 0x%02x\n", lsi->coverage); return 0; } - /* Validate the session state */ - if (lsi->session_state == SIERRA_NET_SESSION_IDLE) { - netdev_err(dev->net, "Session idle, 0x%02x\n", - lsi->session_state); - return 0; - } - /* Set link_sense true */ return 1; } @@ -662,7 +694,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf) u8 numendpoints; u16 fwattr = 0; int status; - struct ethhdr *eth; struct sierra_net_data *priv; static const u8 sync_tmplate[sizeof(priv->sync_msg)] = { 0x00, 0x00, SIERRA_NET_HIP_MSYNC_ID, 0x00}; @@ -700,11 +731,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->dev_addr[ETH_ALEN-2] = atomic_inc_return(&iface_counter); dev->net->dev_addr[ETH_ALEN-1] = ifacenum; - /* we will have to manufacture ethernet headers, prepare template */ - eth = (struct ethhdr *)priv->ethr_hdr_tmpl; - memcpy(ð->h_dest, dev->net->dev_addr, ETH_ALEN); - eth->h_proto = cpu_to_be16(ETH_P_IP); - /* prepare shutdown message template */ memcpy(priv->shdwn_msg, shdwn_tmplate, sizeof(priv->shdwn_msg)); /* set context index initially to 0 - prepares tx hdr template */ @@ -833,9 +859,14 @@ static int sierra_net_rx_fixup(struct usbnet *dev, struct sk_buff *skb) skb_pull(skb, hh.hdrlen); - /* We are going to accept this packet, prepare it */ - memcpy(skb->data, sierra_net_get_private(dev)->ethr_hdr_tmpl, - ETH_HLEN); + /* We are going to accept this packet, prepare it. + * In case protocol is IPv6, keep it, otherwise force IPv4. + */ + skb_reset_mac_header(skb); + if (eth_hdr(skb)->h_proto != cpu_to_be16(ETH_P_IPV6)) + eth_hdr(skb)->h_proto = cpu_to_be16(ETH_P_IP); + eth_zero_addr(eth_hdr(skb)->h_source); + memcpy(eth_hdr(skb)->h_dest, dev->net->dev_addr, ETH_ALEN); /* Last packet in batch handled by usbnet */ if (hh.payload_len.word == skb->len) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0e2a19e58923..8dfc75250583 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -47,8 +47,16 @@ module_param(gso, bool, 0444); */ DECLARE_EWMA(pkt_len, 1, 64) +/* With mergeable buffers we align buffer address and use the low bits to + * encode its true size. Buffer size is up to 1 page so we need to align to + * square root of page size to ensure we reserve enough bits to encode the true + * size. + */ +#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2) + /* Minimum alignment for mergeable packet buffers. */ -#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256) +#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \ + 1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT) #define VIRTNET_DRIVER_VERSION "1.0.0" @@ -1415,6 +1423,7 @@ static const struct net_device_ops virtnet_netdev = { #ifdef CONFIG_NET_RX_BUSY_POLL .ndo_busy_poll = virtnet_busy_poll, #endif + .ndo_features_check = passthru_features_check, }; static void virtnet_config_changed_work(struct work_struct *work) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index d6b619667f1a..ac945f8781ac 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -345,6 +345,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { + int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { @@ -352,7 +353,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) u64_stats_update_begin(&dstats->syncp); dstats->tx_pkts++; - dstats->tx_bytes += skb->len; + dstats->tx_bytes += len; u64_stats_update_end(&dstats->syncp); } else { this_cpu_inc(dev->dstats->tx_drps); @@ -732,15 +733,15 @@ static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) static void vrf_dev_uninit(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); - struct slave_queue *queue = &vrf->queue; - struct list_head *head = &queue->all_slaves; - struct slave *slave, *next; +// struct slave_queue *queue = &vrf->queue; +// struct list_head *head = &queue->all_slaves; +// struct slave *slave, *next; vrf_rtable_destroy(vrf); vrf_rt6_destroy(vrf); - list_for_each_entry_safe(slave, next, head, list) - vrf_del_slave(dev, slave->dev); +// list_for_each_entry_safe(slave, next, head, list) +// vrf_del_slave(dev, slave->dev); free_percpu(dev->dstats); dev->dstats = NULL; @@ -913,6 +914,14 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[]) static void vrf_dellink(struct net_device *dev, struct list_head *head) { + struct net_vrf *vrf = netdev_priv(dev); + struct slave_queue *queue = &vrf->queue; + struct list_head *all_slaves = &queue->all_slaves; + struct slave *slave, *next; + + list_for_each_entry_safe(slave, next, all_slaves, list) + vrf_del_slave(dev, slave->dev); + unregister_netdevice_queue(dev, head); } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 6fa8e165878e..dab3bf6649e6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -77,6 +77,8 @@ static const u8 all_zeros_mac[ETH_ALEN]; static int vxlan_sock_add(struct vxlan_dev *vxlan); +static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); + /* per-network namespace private data for this module */ struct vxlan_net { struct list_head vxlan_list; @@ -1052,6 +1054,8 @@ static void __vxlan_sock_release(struct vxlan_sock *vs) static void vxlan_sock_release(struct vxlan_dev *vxlan) { + vxlan_vs_del_dev(vxlan); + __vxlan_sock_release(vxlan->vn4_sock); #if IS_ENABLED(CONFIG_IPV6) __vxlan_sock_release(vxlan->vn6_sock); @@ -2236,7 +2240,7 @@ static void vxlan_cleanup(unsigned long arg) = container_of(p, struct vxlan_fdb, hlist); unsigned long timeout; - if (f->state & NUD_PERMANENT) + if (f->state & (NUD_PERMANENT | NUD_NOARP)) continue; timeout = f->used + vxlan->cfg.age_interval * HZ; @@ -2255,6 +2259,15 @@ static void vxlan_cleanup(unsigned long arg) mod_timer(&vxlan->age_timer, next_timer); } +static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + + spin_lock(&vn->sock_lock); + hlist_del_init_rcu(&vxlan->hlist); + spin_unlock(&vn->sock_lock); +} + static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); @@ -2600,7 +2613,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VXLAN_ID]) { __u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); - if (id >= VXLAN_VID_MASK) + if (id >= VXLAN_N_VID) return -ERANGE; } @@ -3028,12 +3041,6 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); - - spin_lock(&vn->sock_lock); - if (!hlist_unhashed(&vxlan->hlist)) - hlist_del_rcu(&vxlan->hlist); - spin_unlock(&vn->sock_lock); gro_cells_destroy(&vxlan->gro_cells); list_del(&vxlan->next); diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 1e1bef349487..6decf4a95ce1 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -6351,12 +6351,13 @@ static u64 ath10k_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) static int ath10k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct ath10k *ar = hw->priv; struct ath10k_vif *arvif = ath10k_vif_to_arvif(vif); + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; ath10k_dbg(ar, ATH10K_DBG_MAC, "mac ampdu vdev_id %i sta %pM tid %hu action %d\n", arvif->vdev_id, sta->addr, tid, action); diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index 930785a724e1..907fd60c4241 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -3050,7 +3050,7 @@ static int ath10k_pci_probe(struct pci_dev *pdev, goto err_core_destroy; } - if (QCA_REV_6174(ar)) + if (QCA_REV_6174(ar) || QCA_REV_9377(ar)) ath10k_pci_override_ce_config(ar); ret = ath10k_pci_alloc_pipes(ar); diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h index 8f4f6a892581..cfed5808bc4e 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-ops.h +++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h @@ -639,6 +639,9 @@ ath10k_wmi_vdev_spectral_conf(struct ath10k *ar, struct sk_buff *skb; u32 cmd_id; + if (!ar->wmi.ops->gen_vdev_spectral_conf) + return -EOPNOTSUPP; + skb = ar->wmi.ops->gen_vdev_spectral_conf(ar, arg); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -654,6 +657,9 @@ ath10k_wmi_vdev_spectral_enable(struct ath10k *ar, u32 vdev_id, u32 trigger, struct sk_buff *skb; u32 cmd_id; + if (!ar->wmi.ops->gen_vdev_spectral_enable) + return -EOPNOTSUPP; + skb = ar->wmi.ops->gen_vdev_spectral_enable(ar, vdev_id, trigger, enable); if (IS_ERR(skb)) diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c index dc44cfef7517..16e052d02c94 100644 --- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c +++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c @@ -502,8 +502,7 @@ ath5k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, break; return -EOPNOTSUPP; default: - WARN_ON(1); - return -EINVAL; + return -EOPNOTSUPP; } mutex_lock(&ah->lock); diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h index 694ca2e680e5..74670e08e6da 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h @@ -73,13 +73,13 @@ #define AR9300_OTP_BASE \ ((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x30000 : 0x14000) #define AR9300_OTP_STATUS \ - ((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x30018 : 0x15f18) + ((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x31018 : 0x15f18) #define AR9300_OTP_STATUS_TYPE 0x7 #define AR9300_OTP_STATUS_VALID 0x4 #define AR9300_OTP_STATUS_ACCESS_BUSY 0x2 #define AR9300_OTP_STATUS_SM_BUSY 0x1 #define AR9300_OTP_READ_DATA \ - ((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x3001c : 0x15f1c) + ((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x3101c : 0x15f1c) enum targetPowerHTRates { HT_TARGET_RATE_0_8_16, diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c index 201425e7f9cb..fbc8c9a9014b 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c @@ -1815,8 +1815,6 @@ static void ar9003_hw_spectral_scan_wait(struct ath_hw *ah) static void ar9003_hw_tx99_start(struct ath_hw *ah, u32 qnum) { REG_SET_BIT(ah, AR_PHY_TEST, PHY_AGC_CLR); - REG_SET_BIT(ah, 0x9864, 0x7f000); - REG_SET_BIT(ah, 0x9924, 0x7f00fe); REG_CLR_BIT(ah, AR_DIAG_SW, AR_DIAG_RX_DIS); REG_WRITE(ah, AR_CR, AR_CR_RXD); REG_WRITE(ah, AR_DLCL_IFS(qnum), 0); diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h index b42f4a963ef4..a660e40f2df1 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -959,6 +959,7 @@ struct ath_softc { struct survey_info *cur_survey; struct survey_info survey[ATH9K_NUM_CHANNELS]; + spinlock_t intr_lock; struct tasklet_struct intr_tq; struct tasklet_struct bcon_tasklet; struct ath_hw *sc_ah; diff --git a/drivers/net/wireless/ath/ath9k/common-spectral.c b/drivers/net/wireless/ath/ath9k/common-spectral.c index a8762711ad74..03945731eb65 100644 --- a/drivers/net/wireless/ath/ath9k/common-spectral.c +++ b/drivers/net/wireless/ath/ath9k/common-spectral.c @@ -528,6 +528,9 @@ int ath_cmn_process_fft(struct ath_spec_scan_priv *spec_priv, struct ieee80211_h if (!(radar_info->pulse_bw_info & SPECTRAL_SCAN_BITMASK)) return 0; + if (!spec_priv->rfs_chan_spec_scan) + return 1; + /* Output buffers are full, no need to process anything * since there is no space to put the result anyway */ @@ -1072,7 +1075,7 @@ static struct rchan_callbacks rfs_spec_scan_cb = { void ath9k_cmn_spectral_deinit_debug(struct ath_spec_scan_priv *spec_priv) { - if (config_enabled(CONFIG_ATH9K_DEBUGFS)) { + if (config_enabled(CONFIG_ATH9K_DEBUGFS) && spec_priv->rfs_chan_spec_scan) { relay_close(spec_priv->rfs_chan_spec_scan); spec_priv->rfs_chan_spec_scan = NULL; } @@ -1086,6 +1089,9 @@ void ath9k_cmn_spectral_init_debug(struct ath_spec_scan_priv *spec_priv, debugfs_phy, 1024, 256, &rfs_spec_scan_cb, NULL); + if (!spec_priv->rfs_chan_spec_scan) + return; + debugfs_create_file("spectral_scan_ctl", S_IRUSR | S_IWUSR, debugfs_phy, spec_priv, diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 165dd202c365..c92564b3ec85 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -37,6 +37,7 @@ static struct usb_device_id ath9k_hif_usb_ids[] = { { USB_DEVICE(0x0cf3, 0xb002) }, /* Ubiquiti WifiStation */ { USB_DEVICE(0x057c, 0x8403) }, /* AVM FRITZ!WLAN 11N v2 USB */ { USB_DEVICE(0x0471, 0x209e) }, /* Philips (or NXP) PTA01 */ + { USB_DEVICE(0x1eda, 0x2315) }, /* AirTies */ { USB_DEVICE(0x0cf3, 0x7015), .driver_info = AR9287_USB }, /* Atheros */ @@ -1216,6 +1217,9 @@ static int send_eject_command(struct usb_interface *interface) u8 bulk_out_ep; int r; + if (iface_desc->desc.bNumEndpoints < 2) + return -ENODEV; + /* Find bulk out endpoint */ for (r = 1; r >= 0; r--) { endpoint = &iface_desc->endpoint[r].desc; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index a680a970b7f7..e4281438c04f 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -1657,13 +1657,14 @@ static void ath9k_htc_reset_tsf(struct ieee80211_hw *hw, static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct ath9k_htc_priv *priv = hw->priv; struct ath9k_htc_sta *ista; int ret = 0; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; mutex_lock(&priv->mutex); ath9k_htc_ps_wakeup(priv); diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index bc70ce62bc03..0f5672f5c9ba 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -619,6 +619,7 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, common->bt_ant_diversity = 1; spin_lock_init(&common->cc_lock); + spin_lock_init(&sc->intr_lock); spin_lock_init(&sc->sc_serial_rw); spin_lock_init(&sc->sc_pm_lock); spin_lock_init(&sc->chan_lock); diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c index bba85d1a6cd1..d937c39b3a0b 100644 --- a/drivers/net/wireless/ath/ath9k/mac.c +++ b/drivers/net/wireless/ath/ath9k/mac.c @@ -805,21 +805,12 @@ void ath9k_hw_disable_interrupts(struct ath_hw *ah) } EXPORT_SYMBOL(ath9k_hw_disable_interrupts); -void ath9k_hw_enable_interrupts(struct ath_hw *ah) +static void __ath9k_hw_enable_interrupts(struct ath_hw *ah) { struct ath_common *common = ath9k_hw_common(ah); u32 sync_default = AR_INTR_SYNC_DEFAULT; u32 async_mask; - if (!(ah->imask & ATH9K_INT_GLOBAL)) - return; - - if (!atomic_inc_and_test(&ah->intr_ref_cnt)) { - ath_dbg(common, INTERRUPT, "Do not enable IER ref count %d\n", - atomic_read(&ah->intr_ref_cnt)); - return; - } - if (AR_SREV_9340(ah) || AR_SREV_9550(ah) || AR_SREV_9531(ah) || AR_SREV_9561(ah)) sync_default &= ~AR_INTR_SYNC_HOST1_FATAL; @@ -841,6 +832,39 @@ void ath9k_hw_enable_interrupts(struct ath_hw *ah) ath_dbg(common, INTERRUPT, "AR_IMR 0x%x IER 0x%x\n", REG_READ(ah, AR_IMR), REG_READ(ah, AR_IER)); } + +void ath9k_hw_resume_interrupts(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!(ah->imask & ATH9K_INT_GLOBAL)) + return; + + if (atomic_read(&ah->intr_ref_cnt) != 0) { + ath_dbg(common, INTERRUPT, "Do not enable IER ref count %d\n", + atomic_read(&ah->intr_ref_cnt)); + return; + } + + __ath9k_hw_enable_interrupts(ah); +} +EXPORT_SYMBOL(ath9k_hw_resume_interrupts); + +void ath9k_hw_enable_interrupts(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!(ah->imask & ATH9K_INT_GLOBAL)) + return; + + if (!atomic_inc_and_test(&ah->intr_ref_cnt)) { + ath_dbg(common, INTERRUPT, "Do not enable IER ref count %d\n", + atomic_read(&ah->intr_ref_cnt)); + return; + } + + __ath9k_hw_enable_interrupts(ah); +} EXPORT_SYMBOL(ath9k_hw_enable_interrupts); void ath9k_hw_set_interrupts(struct ath_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h index 7fbf7f965f61..1b63d26f30ce 100644 --- a/drivers/net/wireless/ath/ath9k/mac.h +++ b/drivers/net/wireless/ath/ath9k/mac.h @@ -748,6 +748,7 @@ void ath9k_hw_set_interrupts(struct ath_hw *ah); void ath9k_hw_enable_interrupts(struct ath_hw *ah); void ath9k_hw_disable_interrupts(struct ath_hw *ah); void ath9k_hw_kill_interrupts(struct ath_hw *ah); +void ath9k_hw_resume_interrupts(struct ath_hw *ah); void ar9002_hw_attach_mac_ops(struct ath_hw *ah); diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 8c5d2cf9c979..3abc64574116 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -373,21 +373,20 @@ void ath9k_tasklet(unsigned long data) struct ath_common *common = ath9k_hw_common(ah); enum ath_reset_type type; unsigned long flags; - u32 status = sc->intrstatus; + u32 status; u32 rxmask; + spin_lock_irqsave(&sc->intr_lock, flags); + status = sc->intrstatus; + sc->intrstatus = 0; + spin_unlock_irqrestore(&sc->intr_lock, flags); + ath9k_ps_wakeup(sc); spin_lock(&sc->sc_pcu_lock); if (status & ATH9K_INT_FATAL) { type = RESET_TYPE_FATAL_INT; ath9k_queue_reset(sc, type); - - /* - * Increment the ref. counter here so that - * interrupts are enabled in the reset routine. - */ - atomic_inc(&ah->intr_ref_cnt); ath_dbg(common, RESET, "FATAL: Skipping interrupts\n"); goto out; } @@ -403,11 +402,6 @@ void ath9k_tasklet(unsigned long data) type = RESET_TYPE_BB_WATCHDOG; ath9k_queue_reset(sc, type); - /* - * Increment the ref. counter here so that - * interrupts are enabled in the reset routine. - */ - atomic_inc(&ah->intr_ref_cnt); ath_dbg(common, RESET, "BB_WATCHDOG: Skipping interrupts\n"); goto out; @@ -420,7 +414,6 @@ void ath9k_tasklet(unsigned long data) if ((sc->gtt_cnt >= MAX_GTT_CNT) && !ath9k_hw_check_alive(ah)) { type = RESET_TYPE_TX_GTT; ath9k_queue_reset(sc, type); - atomic_inc(&ah->intr_ref_cnt); ath_dbg(common, RESET, "GTT: Skipping interrupts\n"); goto out; @@ -477,7 +470,7 @@ void ath9k_tasklet(unsigned long data) ath9k_btcoex_handle_interrupt(sc, status); /* re-enable hardware interrupt */ - ath9k_hw_enable_interrupts(ah); + ath9k_hw_resume_interrupts(ah); out: spin_unlock(&sc->sc_pcu_lock); ath9k_ps_restore(sc); @@ -541,7 +534,9 @@ irqreturn_t ath_isr(int irq, void *dev) return IRQ_NONE; /* Cache the status */ - sc->intrstatus = status; + spin_lock(&sc->intr_lock); + sc->intrstatus |= status; + spin_unlock(&sc->intr_lock); if (status & SCHED_INTR) sched = true; @@ -587,7 +582,7 @@ chip_reset: if (sched) { /* turn off every interrupt */ - ath9k_hw_disable_interrupts(ah); + ath9k_hw_kill_interrupts(ah); tasklet_schedule(&sc->intr_tq); } @@ -1860,14 +1855,16 @@ static void ath9k_reset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) static int ath9k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); bool flush = false; int ret = 0; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; mutex_lock(&sc->mutex); diff --git a/drivers/net/wireless/ath/ath9k/tx99.c b/drivers/net/wireless/ath/ath9k/tx99.c index ac4781f37e78..b4e6304afd40 100644 --- a/drivers/net/wireless/ath/ath9k/tx99.c +++ b/drivers/net/wireless/ath/ath9k/tx99.c @@ -190,22 +190,27 @@ static ssize_t write_file_tx99(struct file *file, const char __user *user_buf, if (strtobool(buf, &start)) return -EINVAL; + mutex_lock(&sc->mutex); + if (start == sc->tx99_state) { if (!start) - return count; + goto out; ath_dbg(common, XMIT, "Resetting TX99\n"); ath9k_tx99_deinit(sc); } if (!start) { ath9k_tx99_deinit(sc); - return count; + goto out; } r = ath9k_tx99_init(sc); - if (r) + if (r) { + mutex_unlock(&sc->mutex); return r; - + } +out: + mutex_unlock(&sc->mutex); return count; } diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c index 19d3d64416bf..4d1527a2e292 100644 --- a/drivers/net/wireless/ath/carl9170/main.c +++ b/drivers/net/wireless/ath/carl9170/main.c @@ -1413,10 +1413,12 @@ static void carl9170_ampdu_work(struct work_struct *work) static int carl9170_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; struct ar9170 *ar = hw->priv; struct carl9170_sta_info *sta_info = (void *) sta->drv_priv; struct carl9170_sta_tid *tid_info; diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index 7c169abdbafe..a27279c2c695 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -857,12 +857,14 @@ static int wcn36xx_resume(struct ieee80211_hw *hw) static int wcn36xx_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct wcn36xx *wcn = hw->priv; struct wcn36xx_sta *sta_priv = NULL; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; wcn36xx_dbg(WCN36XX_DBG_MAC, "mac ampdu action action %d tid %d\n", action, tid); diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c index bb69a5949aea..85bca557a339 100644 --- a/drivers/net/wireless/ath/wil6210/main.c +++ b/drivers/net/wireless/ath/wil6210/main.c @@ -330,18 +330,19 @@ static void wil_fw_error_worker(struct work_struct *work) wil->last_fw_recovery = jiffies; + wil_info(wil, "fw error recovery requested (try %d)...\n", + wil->recovery_count); + if (!no_fw_recovery) + wil->recovery_state = fw_recovery_running; + if (wil_wait_for_recovery(wil) != 0) + return; + mutex_lock(&wil->mutex); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_MONITOR: - wil_info(wil, "fw error recovery requested (try %d)...\n", - wil->recovery_count); - if (!no_fw_recovery) - wil->recovery_state = fw_recovery_running; - if (0 != wil_wait_for_recovery(wil)) - break; - + /* silent recovery, upper layers will see disconnect */ __wil_down(wil); __wil_up(wil); break; diff --git a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c index 70a6985334d5..da5826d788d6 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c @@ -4472,6 +4472,11 @@ brcmf_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, cfg80211_mgmt_tx_status(wdev, *cookie, buf, len, true, GFP_KERNEL); } else if (ieee80211_is_action(mgmt->frame_control)) { + if (len > BRCMF_FIL_ACTION_FRAME_SIZE + DOT11_MGMT_HDR_LEN) { + brcmf_err("invalid action frame length\n"); + err = -EINVAL; + goto exit; + } af_params = kzalloc(sizeof(*af_params), GFP_KERNEL); if (af_params == NULL) { brcmf_err("unable to allocate frame\n"); diff --git a/drivers/net/wireless/brcm80211/brcmfmac/core.c b/drivers/net/wireless/brcm80211/brcmfmac/core.c index b5ab98ee1445..82753e7c7e7c 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/core.c @@ -211,7 +211,7 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb, int ret; struct brcmf_if *ifp = netdev_priv(ndev); struct brcmf_pub *drvr = ifp->drvr; - struct ethhdr *eh = (struct ethhdr *)(skb->data); + struct ethhdr *eh; brcmf_dbg(DATA, "Enter, idx=%d\n", ifp->bssidx); @@ -232,22 +232,13 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb, goto done; } - /* Make sure there's enough room for any header */ - if (skb_headroom(skb) < drvr->hdrlen) { - struct sk_buff *skb2; - - brcmf_dbg(INFO, "%s: insufficient headroom\n", + /* Make sure there's enough writable headroom*/ + ret = skb_cow_head(skb, drvr->hdrlen); + if (ret < 0) { + brcmf_err("%s: skb_cow_head failed\n", brcmf_ifname(drvr, ifp->bssidx)); - drvr->bus_if->tx_realloc++; - skb2 = skb_realloc_headroom(skb, drvr->hdrlen); dev_kfree_skb(skb); - skb = skb2; - if (skb == NULL) { - brcmf_err("%s: skb_realloc_headroom failed\n", - brcmf_ifname(drvr, ifp->bssidx)); - ret = -ENOMEM; - goto done; - } + goto done; } /* validate length for ether packet */ @@ -257,6 +248,8 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb, goto done; } + eh = (struct ethhdr *)(skb->data); + if (eh->h_proto == htons(ETH_P_PAE)) atomic_inc(&ifp->pend_8021x_cnt); diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c index bec2dc1ca2e4..61ae2768132a 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c @@ -818,13 +818,15 @@ brcms_ops_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, static int brcms_ops_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct brcms_info *wl = hw->priv; struct scb *scb = &wl->wlc->pri_scb; int status; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u8 buf_size = params->buf_size; if (WARN_ON(scb->magic != SCB_MAGIC)) return -EIDRM; diff --git a/drivers/net/wireless/cw1200/sta.c b/drivers/net/wireless/cw1200/sta.c index 95a7fdb3cc1c..c602a1e674ca 100644 --- a/drivers/net/wireless/cw1200/sta.c +++ b/drivers/net/wireless/cw1200/sta.c @@ -2135,9 +2135,7 @@ void cw1200_mcast_timeout(unsigned long arg) int cw1200_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { /* Aggregation is implemented fully in firmware, * including block ack negotiation. Do not allow diff --git a/drivers/net/wireless/cw1200/sta.h b/drivers/net/wireless/cw1200/sta.h index bebb3379017f..a0bacaa39b31 100644 --- a/drivers/net/wireless/cw1200/sta.h +++ b/drivers/net/wireless/cw1200/sta.h @@ -109,9 +109,7 @@ void cw1200_bss_info_changed(struct ieee80211_hw *dev, u32 changed); int cw1200_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); void cw1200_suspend_resume(struct cw1200_common *priv, struct wsm_suspend_resume *arg); diff --git a/drivers/net/wireless/hostap/hostap_hw.c b/drivers/net/wireless/hostap/hostap_hw.c index 6df3ee561d52..515aa3f993f3 100644 --- a/drivers/net/wireless/hostap/hostap_hw.c +++ b/drivers/net/wireless/hostap/hostap_hw.c @@ -836,25 +836,30 @@ static int hfa384x_get_rid(struct net_device *dev, u16 rid, void *buf, int len, spin_lock_bh(&local->baplock); res = hfa384x_setup_bap(dev, BAP0, rid, 0); - if (!res) - res = hfa384x_from_bap(dev, BAP0, &rec, sizeof(rec)); + if (res) + goto unlock; + + res = hfa384x_from_bap(dev, BAP0, &rec, sizeof(rec)); + if (res) + goto unlock; if (le16_to_cpu(rec.len) == 0) { /* RID not available */ res = -ENODATA; + goto unlock; } rlen = (le16_to_cpu(rec.len) - 1) * 2; - if (!res && exact_len && rlen != len) { + if (exact_len && rlen != len) { printk(KERN_DEBUG "%s: hfa384x_get_rid - RID len mismatch: " "rid=0x%04x, len=%d (expected %d)\n", dev->name, rid, rlen, len); res = -ENODATA; } - if (!res) - res = hfa384x_from_bap(dev, BAP0, buf, len); + res = hfa384x_from_bap(dev, BAP0, buf, len); +unlock: spin_unlock_bh(&local->baplock); mutex_unlock(&local->rid_bap_mtx); diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c index 6656215a13a9..04b0349a6ad9 100644 --- a/drivers/net/wireless/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/iwlegacy/4965-mac.c @@ -5982,12 +5982,14 @@ il4965_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 * ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct il_priv *il = hw->priv; int ret = -EINVAL; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; D_HT("A-MPDU action on addr %pM tid %d\n", sta->addr, tid); diff --git a/drivers/net/wireless/iwlegacy/4965.h b/drivers/net/wireless/iwlegacy/4965.h index 8ab8706f9422..e432715e02d8 100644 --- a/drivers/net/wireless/iwlegacy/4965.h +++ b/drivers/net/wireless/iwlegacy/4965.h @@ -182,9 +182,7 @@ void il4965_mac_update_tkip_key(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u32 iv32, u16 *phase1key); int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 * ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); int il4965_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c index b3ad34e8bf5a..1eb1a823a111 100644 --- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c @@ -729,12 +729,15 @@ static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg) static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw); int ret = -EINVAL; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; struct iwl_station_priv *sta_priv = (void *) sta->drv_priv; IWL_DEBUG_HT(priv, "A-MPDU action on addr %pM tid %d\n", diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index ce12717e656a..1a8ea775de08 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -826,13 +826,16 @@ iwl_mvm_ampdu_check_trigger(struct iwl_mvm *mvm, struct ieee80211_vif *vif, static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); int ret; bool tx_agg_ref = false; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; IWL_DEBUG_HT(mvm, "A-MPDU action on addr %pM tid %d: action %d\n", sta->addr, tid, action); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 0cd95120bc78..019d7165a045 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1817,10 +1817,12 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw, static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + switch (action) { case IEEE80211_AMPDU_TX_START: ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid); @@ -2537,7 +2539,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, tasklet_hrtimer_init(&data->beacon_timer, mac80211_hwsim_beacon, - CLOCK_MONOTONIC_RAW, HRTIMER_MODE_ABS); + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); spin_lock_bh(&hwsim_radio_lock); list_add_tail(&data->list, &hwsim_radios); diff --git a/drivers/net/wireless/mediatek/mt7601u/main.c b/drivers/net/wireless/mediatek/mt7601u/main.c index f715eee39851..e70dd9523911 100644 --- a/drivers/net/wireless/mediatek/mt7601u/main.c +++ b/drivers/net/wireless/mediatek/mt7601u/main.c @@ -334,11 +334,13 @@ static int mt7601u_set_rts_threshold(struct ieee80211_hw *hw, u32 value) static int mt76_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size, - bool amsdu) + struct ieee80211_ampdu_params *params) { struct mt7601u_dev *dev = hw->priv; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv; WARN_ON(msta->wcid.idx > GROUP_WCID(0)); diff --git a/drivers/net/wireless/mwifiex/11n_aggr.c b/drivers/net/wireless/mwifiex/11n_aggr.c index aa498e0d2204..49f3e17c28ea 100644 --- a/drivers/net/wireless/mwifiex/11n_aggr.c +++ b/drivers/net/wireless/mwifiex/11n_aggr.c @@ -101,13 +101,6 @@ mwifiex_11n_form_amsdu_txpd(struct mwifiex_private *priv, { struct txpd *local_tx_pd; struct mwifiex_txinfo *tx_info = MWIFIEX_SKB_TXCB(skb); - unsigned int pad; - int headroom = (priv->adapter->iface_type == - MWIFIEX_USB) ? 0 : INTF_HEADER_LEN; - - pad = ((void *)skb->data - sizeof(*local_tx_pd) - - headroom - NULL) & (MWIFIEX_DMA_ALIGN_SZ - 1); - skb_push(skb, pad); skb_push(skb, sizeof(*local_tx_pd)); @@ -121,12 +114,10 @@ mwifiex_11n_form_amsdu_txpd(struct mwifiex_private *priv, local_tx_pd->bss_num = priv->bss_num; local_tx_pd->bss_type = priv->bss_type; /* Always zero as the data is followed by struct txpd */ - local_tx_pd->tx_pkt_offset = cpu_to_le16(sizeof(struct txpd) + - pad); + local_tx_pd->tx_pkt_offset = cpu_to_le16(sizeof(struct txpd)); local_tx_pd->tx_pkt_type = cpu_to_le16(PKT_TYPE_AMSDU); local_tx_pd->tx_pkt_length = cpu_to_le16(skb->len - - sizeof(*local_tx_pd) - - pad); + sizeof(*local_tx_pd)); if (tx_info->flags & MWIFIEX_BUF_FLAG_TDLS_PKT) local_tx_pd->flags |= MWIFIEX_TXPD_FLAGS_TDLS_PACKET; @@ -190,7 +181,11 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv, ra_list_flags); return -1; } - skb_reserve(skb_aggr, MWIFIEX_MIN_DATA_HEADER_LEN); + + /* skb_aggr->data already 64 byte align, just reserve bus interface + * header and txpd. + */ + skb_reserve(skb_aggr, headroom + sizeof(struct txpd)); tx_info_aggr = MWIFIEX_SKB_TXCB(skb_aggr); memset(tx_info_aggr, 0, sizeof(*tx_info_aggr)); diff --git a/drivers/net/wireless/mwifiex/debugfs.c b/drivers/net/wireless/mwifiex/debugfs.c index 9824d8dd2b44..45d97b64ef84 100644 --- a/drivers/net/wireless/mwifiex/debugfs.c +++ b/drivers/net/wireless/mwifiex/debugfs.c @@ -115,7 +115,8 @@ mwifiex_info_read(struct file *file, char __user *ubuf, if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA) { p += sprintf(p, "multicast_count=\"%d\"\n", netdev_mc_count(netdev)); - p += sprintf(p, "essid=\"%s\"\n", info.ssid.ssid); + p += sprintf(p, "essid=\"%.*s\"\n", info.ssid.ssid_len, + info.ssid.ssid); p += sprintf(p, "bssid=\"%pM\"\n", info.bssid); p += sprintf(p, "channel=\"%d\"\n", (int) info.bss_chan); p += sprintf(p, "country_code = \"%s\"\n", info.country_code); diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c index 21192b6f9c64..268e50ba88a5 100644 --- a/drivers/net/wireless/mwifiex/pcie.c +++ b/drivers/net/wireless/mwifiex/pcie.c @@ -947,6 +947,7 @@ static int mwifiex_pcie_delete_cmdrsp_buf(struct mwifiex_adapter *adapter) if (card && card->cmd_buf) { mwifiex_unmap_pci_memory(adapter, card->cmd_buf, PCI_DMA_TODEVICE); + dev_kfree_skb_any(card->cmd_buf); } return 0; } @@ -1513,6 +1514,11 @@ mwifiex_pcie_send_cmd(struct mwifiex_adapter *adapter, struct sk_buff *skb) return -1; card->cmd_buf = skb; + /* + * Need to keep a reference, since core driver might free up this + * buffer before we've unmapped it. + */ + skb_get(skb); /* To send a command, the driver will: 1. Write the 64bit physical address of the data buffer to @@ -1610,6 +1616,7 @@ static int mwifiex_pcie_process_cmd_complete(struct mwifiex_adapter *adapter) if (card->cmd_buf) { mwifiex_unmap_pci_memory(adapter, card->cmd_buf, PCI_DMA_TODEVICE); + dev_kfree_skb_any(card->cmd_buf); card->cmd_buf = NULL; } diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c index d6c4f0f60839..6cfa2969b123 100644 --- a/drivers/net/wireless/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/mwifiex/sta_ioctl.c @@ -1098,8 +1098,6 @@ int mwifiex_set_encode(struct mwifiex_private *priv, struct key_params *kp, encrypt_key.is_rx_seq_valid = true; } } else { - if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) - return 0; encrypt_key.key_disable = true; if (mac_addr) memcpy(encrypt_key.mac_addr, mac_addr, ETH_ALEN); diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 30e3aaae32e2..088429d0a634 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -5421,11 +5421,13 @@ static int mwl8k_get_survey(struct ieee80211_hw *hw, int idx, static int mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { - + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; int i, rc = 0; struct mwl8k_priv *priv = hw->priv; struct mwl8k_ampdu_stream *stream; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c index 6aed923a709a..7d820c395375 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c @@ -5375,13 +5375,13 @@ static int rtl8xxxu_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, static int rtl8xxxu_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size, - bool amsdu) + struct ieee80211_ampdu_params *params) { struct rtl8xxxu_priv *priv = hw->priv; struct device *dev = &priv->udev->dev; u8 ampdu_factor, ampdu_density; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; switch (action) { case IEEE80211_AMPDU_TX_START: diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index e36d8c456275..8b537a5a4b01 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -1369,11 +1369,13 @@ static void rtl_op_sta_notify(struct ieee80211_hw *hw, static int rtl_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct rtl_priv *rtlpriv = rtl_priv(hw); + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; switch (action) { case IEEE80211_AMPDU_TX_START: diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.h b/drivers/net/wireless/realtek/rtlwifi/pci.h index 5da6703942d9..672f81ea02d0 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.h +++ b/drivers/net/wireless/realtek/rtlwifi/pci.h @@ -275,10 +275,10 @@ struct mp_adapter { }; struct rtl_pci_priv { + struct bt_coexist_info bt_coexist; + struct rtl_led_ctl ledctl; struct rtl_pci dev; struct mp_adapter ndis_adapter; - struct rtl_led_ctl ledctl; - struct bt_coexist_info bt_coexist; }; #define rtl_pcipriv(hw) (((struct rtl_pci_priv *)(rtl_priv(hw))->priv)) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c index 5f14308e8eb3..b1601441991d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c @@ -1003,7 +1003,7 @@ static void _rtl92ee_hw_configure(struct ieee80211_hw *hw) rtl_write_word(rtlpriv, REG_SIFS_TRX, 0x100a); /* Note Data sheet don't define */ - rtl_write_word(rtlpriv, 0x4C7, 0x80); + rtl_write_byte(rtlpriv, 0x4C7, 0x80); rtl_write_byte(rtlpriv, REG_RX_PKT_LIMIT, 0x20); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c index bbb789f8990b..c2103e7a8132 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c @@ -1127,7 +1127,7 @@ static u8 _rtl8821ae_dbi_read(struct rtl_priv *rtlpriv, u16 addr) } if (0 == tmp) { read_addr = REG_DBI_RDATA + addr % 4; - ret = rtl_read_word(rtlpriv, read_addr); + ret = rtl_read_byte(rtlpriv, read_addr); } return ret; } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c index 9b4d8a637915..4b354918e183 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c @@ -359,6 +359,107 @@ bool rtl8821ae_phy_rf_config(struct ieee80211_hw *hw) return rtl8821ae_phy_rf6052_config(hw); } +static void _rtl8812ae_phy_set_rfe_reg_24g(struct ieee80211_hw *hw) +{ + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); + u8 tmp; + + switch (rtlhal->rfe_type) { + case 3: + rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x54337770); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x54337770); + rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010); + rtl_set_bbreg(hw, 0x900, 0x00000303, 0x1); + break; + case 4: + rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77777777); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777); + rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x001); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x001); + break; + case 5: + rtl_write_byte(rtlpriv, RA_RFE_PINMUX + 2, 0x77); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777); + tmp = rtl_read_byte(rtlpriv, RA_RFE_INV + 3); + rtl_write_byte(rtlpriv, RA_RFE_INV + 3, tmp & ~0x1); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000); + break; + case 1: + if (rtlpriv->btcoexist.bt_coexistence) { + rtl_set_bbreg(hw, RA_RFE_PINMUX, 0xffffff, 0x777777); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, + 0x77777777); + rtl_set_bbreg(hw, RA_RFE_INV, 0x33f00000, 0x000); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000); + break; + } + case 0: + case 2: + default: + rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77777777); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777); + rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x000); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000); + break; + } +} + +static void _rtl8812ae_phy_set_rfe_reg_5g(struct ieee80211_hw *hw) +{ + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); + u8 tmp; + + switch (rtlhal->rfe_type) { + case 0: + rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77337717); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337717); + rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010); + break; + case 1: + if (rtlpriv->btcoexist.bt_coexistence) { + rtl_set_bbreg(hw, RA_RFE_PINMUX, 0xffffff, 0x337717); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, + 0x77337717); + rtl_set_bbreg(hw, RA_RFE_INV, 0x33f00000, 0x000); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000); + } else { + rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, + 0x77337717); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, + 0x77337717); + rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x000); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000); + } + break; + case 3: + rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x54337717); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x54337717); + rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010); + rtl_set_bbreg(hw, 0x900, 0x00000303, 0x1); + break; + case 5: + rtl_write_byte(rtlpriv, RA_RFE_PINMUX + 2, 0x33); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337777); + tmp = rtl_read_byte(rtlpriv, RA_RFE_INV + 3); + rtl_write_byte(rtlpriv, RA_RFE_INV + 3, tmp | 0x1); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010); + break; + case 2: + case 4: + default: + rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77337777); + rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337777); + rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010); + rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010); + break; + } +} + u32 phy_get_tx_swing_8812A(struct ieee80211_hw *hw, u8 band, u8 rf_path) { @@ -553,14 +654,9 @@ void rtl8821ae_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band) /* 0x82C[1:0] = 2b'00 */ rtl_set_bbreg(hw, 0x82c, 0x3, 0); } - if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) { - rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, - 0x77777777); - rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, - 0x77777777); - rtl_set_bbreg(hw, RA_RFE_INV, 0x3ff00000, 0x000); - rtl_set_bbreg(hw, RB_RFE_INV, 0x3ff00000, 0x000); - } + + if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) + _rtl8812ae_phy_set_rfe_reg_24g(hw); rtl_set_bbreg(hw, RTXPATH, 0xf0, 0x1); rtl_set_bbreg(hw, RCCK_RX, 0x0f000000, 0x1); @@ -615,14 +711,8 @@ void rtl8821ae_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band) /* 0x82C[1:0] = 2'b00 */ rtl_set_bbreg(hw, 0x82c, 0x3, 1); - if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) { - rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, - 0x77337777); - rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, - 0x77337777); - rtl_set_bbreg(hw, RA_RFE_INV, 0x3ff00000, 0x010); - rtl_set_bbreg(hw, RB_RFE_INV, 0x3ff00000, 0x010); - } + if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) + _rtl8812ae_phy_set_rfe_reg_5g(hw); rtl_set_bbreg(hw, RTXPATH, 0xf0, 0); rtl_set_bbreg(hw, RCCK_RX, 0x0f000000, 0xf); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h index 1d6110f9c1fb..ed69dbe178ff 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h @@ -2424,6 +2424,7 @@ #define BMASKH4BITS 0xf0000000 #define BMASKOFDM_D 0xffc00000 #define BMASKCCK 0x3f3f3f3f +#define BMASKRFEINV 0x3ff00000 #define BRFREGOFFSETMASK 0xfffff diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index aac1ed3f7bb4..ad8390d2997b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -834,12 +834,30 @@ static void rtl_usb_stop(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw)); + struct urb *urb; /* should after adapter start and interrupt enable. */ set_hal_stop(rtlhal); cancel_work_sync(&rtlpriv->works.fill_h2c_cmd); /* Enable software */ SET_USB_STOP(rtlusb); + + /* free pre-allocated URBs from rtl_usb_start() */ + usb_kill_anchored_urbs(&rtlusb->rx_submitted); + + tasklet_kill(&rtlusb->rx_work_tasklet); + cancel_work_sync(&rtlpriv->works.lps_change_work); + + flush_workqueue(rtlpriv->works.rtl_wq); + + skb_queue_purge(&rtlusb->rx_queue); + + while ((urb = usb_get_from_anchor(&rtlusb->rx_cleanup_urbs))) { + usb_free_coherent(urb->dev, urb->transfer_buffer_length, + urb->transfer_buffer, urb->transfer_dma); + usb_free_urb(urb); + } + rtlpriv->cfg->ops->hw_disable(hw); } @@ -1073,6 +1091,7 @@ int rtl_usb_probe(struct usb_interface *intf, return -ENOMEM; } rtlpriv = hw->priv; + rtlpriv->hw = hw; rtlpriv->usb_data = kzalloc(RTL_USB_MAX_RX_COUNT * sizeof(u32), GFP_KERNEL); if (!rtlpriv->usb_data) diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.h b/drivers/net/wireless/realtek/rtlwifi/usb.h index 685273ca9561..441c4412130c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.h +++ b/drivers/net/wireless/realtek/rtlwifi/usb.h @@ -150,8 +150,9 @@ struct rtl_usb { }; struct rtl_usb_priv { - struct rtl_usb dev; + struct bt_coexist_info bt_coexist; struct rtl_led_ctl ledctl; + struct rtl_usb dev; }; #define rtl_usbpriv(hw) (((struct rtl_usb_priv *)(rtl_priv(hw))->priv)) diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index b5bcc933a2a6..4df992de7d07 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -659,29 +659,24 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw, * informs the f/w regarding this. * @hw: Pointer to the ieee80211_hw structure. * @vif: Pointer to the ieee80211_vif structure. - * @action: ieee80211_ampdu_mlme_action enum. - * @sta: Pointer to the ieee80211_sta structure. - * @tid: Traffic identifier. - * @ssn: Pointer to ssn value. - * @buf_size: Buffer size (for kernel version > 2.6.38). - * @amsdu: is AMSDU in AMPDU allowed + * @params: Pointer to A-MPDU action parameters * * Return: status: 0 on success, negative error code on failure. */ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - unsigned short tid, - unsigned short *ssn, - unsigned char buf_size, - bool amsdu) + struct ieee80211_ampdu_params *params) { int status = -EOPNOTSUPP; struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; u16 seq_no = 0; u8 ii = 0; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; for (ii = 0; ii < RSI_MAX_VIFS; ii++) { if (vif == adapter->vifs[ii]) diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 9733b31a780d..69c1c09687a3 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -7935,10 +7935,11 @@ u64 rt2800_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) EXPORT_SYMBOL_GPL(rt2800_get_tsf); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; struct rt2x00_sta *sta_priv = (struct rt2x00_sta *)sta->drv_priv; int ret = 0; diff --git a/drivers/net/wireless/rt2x00/rt2800lib.h b/drivers/net/wireless/rt2x00/rt2800lib.h index 440790b92b19..83f1a44fb9b4 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.h +++ b/drivers/net/wireless/rt2x00/rt2800lib.h @@ -218,9 +218,7 @@ int rt2800_conf_tx(struct ieee80211_hw *hw, const struct ieee80211_tx_queue_params *params); u64 rt2800_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); int rt2800_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void rt2800_disable_wpdma(struct rt2x00_dev *rt2x00dev); diff --git a/drivers/net/wireless/ti/wl18xx/event.c b/drivers/net/wireless/ti/wl18xx/event.c index 5d44eb7bbd5e..aa1466cdbc4e 100644 --- a/drivers/net/wireless/ti/wl18xx/event.c +++ b/drivers/net/wireless/ti/wl18xx/event.c @@ -274,6 +274,5 @@ int wl18xx_process_mailbox_events(struct wl1271 *wl) } out_event: - return 0; } diff --git a/drivers/net/wireless/ti/wl18xx/main.c b/drivers/net/wireless/ti/wl18xx/main.c index 462b9312ebb4..71d456f644f6 100644 --- a/drivers/net/wireless/ti/wl18xx/main.c +++ b/drivers/net/wireless/ti/wl18xx/main.c @@ -1040,8 +1040,8 @@ static int wl18xx_boot(struct wl1271 *wl) DFS_CHANNELS_CONFIG_COMPLETE_EVENT | SMART_CONFIG_SYNC_EVENT_ID | SMART_CONFIG_DECODE_EVENT_ID | - RX_BA_WIN_SIZE_CHANGE_EVENT_ID | - TIME_SYNC_EVENT_ID; + TIME_SYNC_EVENT_ID | + RX_BA_WIN_SIZE_CHANGE_EVENT_ID; wl->ap_event_mask = MAX_TX_FAILURE_EVENT_ID; diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 3241e9eba738..2561815c0df8 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -5326,15 +5326,17 @@ EXPORT_SYMBOL_GPL(wlcore_rx_ba_max_subframes); static int wl1271_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct wl1271 *wl = hw->priv; struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vif); int ret; u8 hlid, *ba_bitmap; int win_size; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; wl1271_debug(DEBUG_MAC80211, "mac80211 ampdu action %d tid %d", action, tid); diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c index 44f059f7f34e..9ebe00ea8f81 100644 --- a/drivers/net/wireless/ti/wlcore/spi.c +++ b/drivers/net/wireless/ti/wlcore/spi.c @@ -71,7 +71,7 @@ * only support SPI for 12xx - this code should be reworked when 18xx * support is introduced */ -#define SPI_AGGR_BUFFER_SIZE (4 * PAGE_SIZE) +#define SPI_AGGR_BUFFER_SIZE (4 * SZ_4K) /* Maximum number of SPI write chunks */ #define WSPI_MAX_NUM_OF_CHUNKS \ diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 0333ab0fd926..34173b5e886f 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -201,6 +201,7 @@ struct xenvif_queue { /* Per-queue data for xenvif */ unsigned long remaining_credit; struct timer_list credit_timeout; u64 credit_window_start; + bool rate_limited; /* Statistics */ struct xenvif_stats stats; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index e7bd63eb2876..60b26f32d31d 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -105,7 +105,11 @@ static int xenvif_poll(struct napi_struct *napi, int budget) if (work_done < budget) { napi_complete(napi); - xenvif_napi_schedule_or_enable_events(queue); + /* If the queue is rate-limited, it shall be + * rescheduled in the timer callback. + */ + if (likely(!queue->rate_limited)) + xenvif_napi_schedule_or_enable_events(queue); } return work_done; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 1049c34e7d43..72ee1c305cc4 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -687,6 +687,7 @@ static void tx_add_credit(struct xenvif_queue *queue) max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */ queue->remaining_credit = min(max_credit, max_burst); + queue->rate_limited = false; } void xenvif_tx_credit_callback(unsigned long data) @@ -1184,8 +1185,10 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) msecs_to_jiffies(queue->credit_usec / 1000); /* Timer could already be pending in rare cases. */ - if (timer_pending(&queue->credit_timeout)) + if (timer_pending(&queue->credit_timeout)) { + queue->rate_limited = true; return true; + } /* Passed the point where we can replenish credit? */ if (time_after_eq64(now, next_credit)) { @@ -1200,6 +1203,7 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) mod_timer(&queue->credit_timeout, next_credit); queue->credit_window_start = next_credit; + queue->rate_limited = true; return true; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index d6abf191122a..34a062ccb11d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -304,7 +304,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue) queue->rx_skbs[id] = skb; ref = gnttab_claim_grant_reference(&queue->gref_rx_head); - BUG_ON((signed short)ref < 0); + WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); queue->grant_rx_ref[id] = ref; page = skb_frag_page(&skb_shinfo(skb)->frags[0]); @@ -321,7 +321,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue) queue->rx.req_prod_pvt = req_prod; /* Not enough requests? Try again later. */ - if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) { + if (req_prod - queue->rx.sring->req_prod < NET_RX_SLOTS_MIN) { mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10)); return; } @@ -437,7 +437,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs); tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++); ref = gnttab_claim_grant_reference(&queue->gref_tx_head); - BUG_ON((signed short)ref < 0); + WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id, gfn, GNTMAP_readonly); @@ -1391,6 +1391,8 @@ static void xennet_disconnect_backend(struct netfront_info *info) for (i = 0; i < num_queues && info->queues; ++i) { struct netfront_queue *queue = &info->queues[i]; + del_timer_sync(&queue->rx_refill_timer); + if (queue->tx_irq && (queue->tx_irq == queue->rx_irq)) unbind_from_irqhandler(queue->tx_irq, queue); if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) { @@ -1745,7 +1747,6 @@ static void xennet_destroy_queues(struct netfront_info *info) if (netif_running(info->netdev)) napi_disable(&queue->napi); - del_timer_sync(&queue->rx_refill_timer); netif_napi_del(&queue->napi); } diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 532db28145c7..a5d7332dfce5 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -210,14 +210,14 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id) struct sk_buff *skb; int r; - client = phy->i2c_dev; - dev_dbg(&client->dev, "%s\n", __func__); - if (!phy || irq != phy->i2c_dev->irq) { WARN_ON_ONCE(1); return IRQ_NONE; } + client = phy->i2c_dev; + dev_dbg(&client->dev, "%s\n", __func__); + r = fdp_nci_i2c_read(phy, &skb); if (r == -EREMOTEIO) diff --git a/drivers/nfc/nfcmrvl/fw_dnld.c b/drivers/nfc/nfcmrvl/fw_dnld.c index f8dcdf4b24f6..af62c4c854f3 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.c +++ b/drivers/nfc/nfcmrvl/fw_dnld.c @@ -459,7 +459,7 @@ int nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv) INIT_WORK(&priv->fw_dnld.rx_work, fw_dnld_rx_work); snprintf(name, sizeof(name), "%s_nfcmrvl_fw_dnld_rx_wq", - dev_name(priv->dev)); + dev_name(&priv->ndev->nfc_dev->dev)); priv->fw_dnld.rx_wq = create_singlethread_workqueue(name); if (!priv->fw_dnld.rx_wq) return -ENOMEM; @@ -496,6 +496,7 @@ int nfcmrvl_fw_dnld_start(struct nci_dev *ndev, const char *firmware_name) { struct nfcmrvl_private *priv = nci_get_drvdata(ndev); struct nfcmrvl_fw_dnld *fw_dnld = &priv->fw_dnld; + int res; if (!priv->support_fw_dnld) return -ENOTSUPP; @@ -511,7 +512,9 @@ int nfcmrvl_fw_dnld_start(struct nci_dev *ndev, const char *firmware_name) */ /* Retrieve FW binary */ - if (request_firmware(&fw_dnld->fw, firmware_name, priv->dev) < 0) { + res = request_firmware(&fw_dnld->fw, firmware_name, + &ndev->nfc_dev->dev); + if (res < 0) { nfc_err(priv->dev, "failed to retrieve FW %s", firmware_name); return -ENOENT; } diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index 51c8240a1672..a446590a71ca 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -124,12 +124,13 @@ struct nfcmrvl_private *nfcmrvl_nci_register_dev(enum nfcmrvl_phy phy, memcpy(&priv->config, pdata, sizeof(*pdata)); if (priv->config.reset_n_io) { - rc = devm_gpio_request_one(dev, - priv->config.reset_n_io, - GPIOF_OUT_INIT_LOW, - "nfcmrvl_reset_n"); - if (rc < 0) + rc = gpio_request_one(priv->config.reset_n_io, + GPIOF_OUT_INIT_LOW, + "nfcmrvl_reset_n"); + if (rc < 0) { + priv->config.reset_n_io = 0; nfc_err(dev, "failed to request reset_n io\n"); + } } if (phy == NFCMRVL_PHY_SPI) { @@ -154,7 +155,13 @@ struct nfcmrvl_private *nfcmrvl_nci_register_dev(enum nfcmrvl_phy phy, if (!priv->ndev) { nfc_err(dev, "nci_allocate_device failed\n"); rc = -ENOMEM; - goto error; + goto error_free_gpio; + } + + rc = nfcmrvl_fw_dnld_init(priv); + if (rc) { + nfc_err(dev, "failed to initialize FW download %d\n", rc); + goto error_free_dev; } nci_set_drvdata(priv->ndev, priv); @@ -162,24 +169,22 @@ struct nfcmrvl_private *nfcmrvl_nci_register_dev(enum nfcmrvl_phy phy, rc = nci_register_device(priv->ndev); if (rc) { nfc_err(dev, "nci_register_device failed %d\n", rc); - goto error_free_dev; + goto error_fw_dnld_deinit; } /* Ensure that controller is powered off */ nfcmrvl_chip_halt(priv); - rc = nfcmrvl_fw_dnld_init(priv); - if (rc) { - nfc_err(dev, "failed to initialize FW download %d\n", rc); - goto error_free_dev; - } - nfc_info(dev, "registered with nci successfully\n"); return priv; +error_fw_dnld_deinit: + nfcmrvl_fw_dnld_deinit(priv); error_free_dev: nci_free_device(priv->ndev); -error: +error_free_gpio: + if (priv->config.reset_n_io) + gpio_free(priv->config.reset_n_io); kfree(priv); return ERR_PTR(rc); } @@ -195,7 +200,7 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv) nfcmrvl_fw_dnld_deinit(priv); if (priv->config.reset_n_io) - devm_gpio_free(priv->dev, priv->config.reset_n_io); + gpio_free(priv->config.reset_n_io); nci_unregister_device(ndev); nci_free_device(ndev); diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 83a99e38e7bd..6c0c301611c4 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -109,6 +109,7 @@ static int nfcmrvl_nci_uart_open(struct nci_uart *nu) struct nfcmrvl_private *priv; struct nfcmrvl_platform_data *pdata = NULL; struct nfcmrvl_platform_data config; + struct device *dev = nu->tty->dev; /* * Platform data cannot be used here since usually it is already used @@ -116,9 +117,8 @@ static int nfcmrvl_nci_uart_open(struct nci_uart *nu) * and check if DT entries were added. */ - if (nu->tty->dev->parent && nu->tty->dev->parent->of_node) - if (nfcmrvl_uart_parse_dt(nu->tty->dev->parent->of_node, - &config) == 0) + if (dev && dev->parent && dev->parent->of_node) + if (nfcmrvl_uart_parse_dt(dev->parent->of_node, &config) == 0) pdata = &config; if (!pdata) { @@ -131,7 +131,7 @@ static int nfcmrvl_nci_uart_open(struct nci_uart *nu) } priv = nfcmrvl_nci_register_dev(NFCMRVL_PHY_UART, nu, &uart_ops, - nu->tty->dev, pdata); + dev, pdata); if (IS_ERR(priv)) return PTR_ERR(priv); diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 60654d524858..ecc6fb9ca92f 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -1623,7 +1623,7 @@ ntb_transport_create_queue(void *data, struct device *client_dev, node = dev_to_node(&ndev->dev); - free_queue = ffs(nt->qp_bitmap); + free_queue = ffs(nt->qp_bitmap_free); if (!free_queue) goto err; @@ -2082,9 +2082,8 @@ module_init(ntb_transport_init); static void __exit ntb_transport_exit(void) { - debugfs_remove_recursive(nt_debugfs_dir); - ntb_unregister_client(&ntb_transport_client); bus_unregister(&ntb_transport_bus); + debugfs_remove_recursive(nt_debugfs_dir); } module_exit(ntb_transport_exit); diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index efb2c1ceef98..957234272ef7 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1205,10 +1205,13 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector, struct page *page, int rw) { struct btt *btt = bdev->bd_disk->private_data; + int rc; - btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector); - page_endio(page, rw & WRITE, 0); - return 0; + rc = btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector); + if (rc == 0) + page_endio(page, rw & WRITE, 0); + + return rc; } diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 5f47356d6942..254b0ee37039 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -590,8 +590,14 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len); if (rc < 0) goto out_unlock; + nvdimm_bus_unlock(&nvdimm_bus->dev); + if (copy_to_user(p, buf, buf_len)) rc = -EFAULT; + + vfree(buf); + return rc; + out_unlock: nvdimm_bus_unlock(&nvdimm_bus->dev); out: diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 62120c38d56b..aae7379af4e4 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1534,6 +1534,7 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) static int find_pmem_label_set(struct nd_region *nd_region, struct nd_namespace_pmem *nspm) { + u64 altcookie = nd_region_interleave_set_altcookie(nd_region); u64 cookie = nd_region_interleave_set_cookie(nd_region); struct nd_namespace_label *nd_label; u8 select_id[NSLABEL_UUID_LEN]; @@ -1542,8 +1543,10 @@ static int find_pmem_label_set(struct nd_region *nd_region, int rc = -ENODEV, l; u16 i; - if (cookie == 0) + if (cookie == 0) { + dev_dbg(&nd_region->dev, "invalid interleave-set-cookie\n"); return -ENXIO; + } /* * Find a complete set of labels by uuid. By definition we can start @@ -1552,13 +1555,24 @@ static int find_pmem_label_set(struct nd_region *nd_region, for_each_label(l, nd_label, nd_region->mapping[0].labels) { u64 isetcookie = __le64_to_cpu(nd_label->isetcookie); - if (isetcookie != cookie) - continue; + if (isetcookie != cookie) { + dev_dbg(&nd_region->dev, "invalid cookie in label: %pUb\n", + nd_label->uuid); + if (isetcookie != altcookie) + continue; + + dev_dbg(&nd_region->dev, "valid altcookie in label: %pUb\n", + nd_label->uuid); + } + + for (i = 0; nd_region->ndr_mappings; i++) { + if (has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i)) + continue; + if (has_uuid_at_pos(nd_region, nd_label->uuid, altcookie, i)) + continue; + break; + } - for (i = 0; nd_region->ndr_mappings; i++) - if (!has_uuid_at_pos(nd_region, nd_label->uuid, - cookie, i)) - break; if (i < nd_region->ndr_mappings) { /* * Give up if we don't find an instance of a diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 417e521d299c..fc870e55bb66 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -245,6 +245,7 @@ struct nd_region *to_nd_region(struct device *dev); int nd_region_to_nstype(struct nd_region *nd_region); int nd_region_register_namespaces(struct nd_region *nd_region, int *err); u64 nd_region_interleave_set_cookie(struct nd_region *nd_region); +u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region); void nvdimm_bus_lock(struct device *dev); void nvdimm_bus_unlock(struct device *dev); bool is_nvdimm_bus_locked(struct device *dev); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 9521696c9385..dc2e919daa39 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -379,6 +379,15 @@ u64 nd_region_interleave_set_cookie(struct nd_region *nd_region) return 0; } +u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region) +{ + struct nd_interleave_set *nd_set = nd_region->nd_set; + + if (nd_set) + return nd_set->altcookie; + return 0; +} + /* * Upon successful probe/remove, take/release a reference on the * associated interleave set (if present), and plant new btt + namespace diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 044253dca30a..b8a5a8e8f57d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -27,6 +27,13 @@ enum { NVME_NS_LIGHTNVM = 1, }; +/* The below value is the specific amount of delay needed before checking + * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the + * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was + * found empirically. + */ +#define NVME_QUIRK_DELAY_AMOUNT 2000 + /* * Represents an NVM Express device. Each nvme_dev is a PCI function. */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c851bc53831c..4c673d45f1bd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1633,10 +1633,15 @@ static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled) */ static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap) { + struct pci_dev *pdev = to_pci_dev(dev->dev); + dev->ctrl_config &= ~NVME_CC_SHN_MASK; dev->ctrl_config &= ~NVME_CC_ENABLE; writel(dev->ctrl_config, &dev->bar->cc); + if (pdev->vendor == 0x1c58 && pdev->device == 0x0003) + msleep(NVME_QUIRK_DELAY_AMOUNT); + return nvme_wait_ready(dev, cap, false); } diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index b7971d410b60..74e5360c53f0 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -88,7 +88,7 @@ static struct nvmem_config imx_ocotp_nvmem_config = { static const struct of_device_id imx_ocotp_dt_ids[] = { { .compatible = "fsl,imx6q-ocotp", (void *)128 }, - { .compatible = "fsl,imx6sl-ocotp", (void *)32 }, + { .compatible = "fsl,imx6sl-ocotp", (void *)64 }, { .compatible = "fsl,imx6sx-ocotp", (void *)128 }, { }, }; diff --git a/drivers/of/address.c b/drivers/of/address.c index 9582c5703b3c..4fe5fe21cd49 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -260,7 +260,7 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, if (!parser->range || parser->range + parser->np > parser->end) return NULL; - range->pci_space = parser->range[0]; + range->pci_space = be32_to_cpup(parser->range); range->flags = of_bus_pci_get_flags(parser->range); range->pci_addr = of_read_number(parser->range + 1, ns); range->cpu_addr = of_translate_address(parser->node, diff --git a/drivers/of/device.c b/drivers/of/device.c index e5f47cec75f3..97a280d50d6d 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -225,6 +225,7 @@ ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len) return tsize; } +EXPORT_SYMBOL_GPL(of_device_get_modalias); /** * of_device_uevent - Display OF related uevent information @@ -287,3 +288,4 @@ int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) return 0; } +EXPORT_SYMBOL_GPL(of_device_uevent_modalias); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index c6d196188bc9..901dd1ca2781 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -632,9 +632,12 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node, const char *pathp; int offset, rc = 0, depth = -1; - for (offset = fdt_next_node(blob, -1, &depth); - offset >= 0 && depth >= 0 && !rc; - offset = fdt_next_node(blob, offset, &depth)) { + if (!blob) + return 0; + + for (offset = fdt_next_node(blob, -1, &depth); + offset >= 0 && depth >= 0 && !rc; + offset = fdt_next_node(blob, offset, &depth)) { pathp = fdt_get_name(blob, offset, NULL); if (*pathp == '/') diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index 8e11fb2831cd..34f1d6b41fb9 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -741,6 +741,8 @@ ccio_map_single(struct device *dev, void *addr, size_t size, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) + return DMA_ERROR_CODE; BUG_ON(size <= 0); @@ -805,6 +807,10 @@ ccio_unmap_single(struct device *dev, dma_addr_t iova, size_t size, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } DBG_RUN("%s() iovp 0x%lx/%x\n", __func__, (long)iova, size); @@ -908,6 +914,8 @@ ccio_map_sg(struct device *dev, struct scatterlist *sglist, int nents, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) + return 0; DBG_RUN_SG("%s() START %d entries\n", __func__, nents); @@ -980,6 +988,10 @@ ccio_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } DBG_RUN_SG("%s() START %d entries, %p,%x\n", __func__, nents, sg_virt(sglist), sglist->length); diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c index a0580afe1713..005ea632ba53 100644 --- a/drivers/parisc/dino.c +++ b/drivers/parisc/dino.c @@ -154,7 +154,10 @@ struct dino_device }; /* Looks nice and keeps the compiler happy */ -#define DINO_DEV(d) ((struct dino_device *) d) +#define DINO_DEV(d) ({ \ + void *__pdata = d; \ + BUG_ON(!__pdata); \ + (struct dino_device *)__pdata; }) /* @@ -951,7 +954,7 @@ static int __init dino_probe(struct parisc_device *dev) dino_dev->hba.dev = dev; dino_dev->hba.base_addr = ioremap_nocache(hpa, 4096); - dino_dev->hba.lmmio_space_offset = 0; /* CPU addrs == bus addrs */ + dino_dev->hba.lmmio_space_offset = PCI_F_EXTEND; spin_lock_init(&dino_dev->dinosaur_pen); dino_dev->hba.iommu = ccio_get_iommu(dev); diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index 42844c2bc065..d0c2759076a2 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -111,8 +111,10 @@ static u32 lba_t32; /* Looks nice and keeps the compiler happy */ -#define LBA_DEV(d) ((struct lba_device *) (d)) - +#define LBA_DEV(d) ({ \ + void *__pdata = d; \ + BUG_ON(!__pdata); \ + (struct lba_device *)__pdata; }) /* ** Only allow 8 subsidiary busses per LBA diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index 225049b492e5..d6326144ce01 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -691,6 +691,8 @@ static int sba_dma_supported( struct device *dev, u64 mask) return 0; ioc = GET_IOC(dev); + if (!ioc) + return 0; /* * check if mask is >= than the current max IO Virt Address @@ -722,6 +724,8 @@ sba_map_single(struct device *dev, void *addr, size_t size, int pide; ioc = GET_IOC(dev); + if (!ioc) + return DMA_ERROR_CODE; /* save offset bits */ offset = ((dma_addr_t) (long) addr) & ~IOVP_MASK; @@ -803,6 +807,10 @@ sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size, DBG_RUN("%s() iovp 0x%lx/%x\n", __func__, (long) iova, size); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } offset = iova & ~IOVP_MASK; iova ^= offset; /* clear offset bits */ size += offset; @@ -942,6 +950,8 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, DBG_RUN_SG("%s() START %d entries\n", __func__, nents); ioc = GET_IOC(dev); + if (!ioc) + return 0; /* Fast path single entry scatterlists. */ if (nents == 1) { @@ -1027,6 +1037,10 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, __func__, nents, sg_virt(sglist), sglist->length); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } #ifdef SBA_COLLECT_STATS ioc->usg_calls++; diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c index 6e3a60c78873..50f3bb0dd1f1 100644 --- a/drivers/parport/parport_gsc.c +++ b/drivers/parport/parport_gsc.c @@ -293,7 +293,7 @@ struct parport *parport_gsc_probe_port(unsigned long base, p->irq = PARPORT_IRQ_NONE; } if (p->irq != PARPORT_IRQ_NONE) { - printk(", irq %d", p->irq); + pr_cont(", irq %d", p->irq); if (p->dma == PARPORT_DMA_AUTO) { p->dma = PARPORT_DMA_NONE; @@ -303,8 +303,8 @@ struct parport *parport_gsc_probe_port(unsigned long base, is mandatory (see above) */ p->dma = PARPORT_DMA_NONE; - printk(" ["); -#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}} + pr_cont(" ["); +#define printmode(x) {if(p->modes&PARPORT_MODE_##x){pr_cont("%s%s",f?",":"",#x);f++;}} { int f = 0; printmode(PCSPP); @@ -315,7 +315,7 @@ struct parport *parport_gsc_probe_port(unsigned long base, // printmode(DMA); } #undef printmode - printk("]\n"); + pr_cont("]\n"); if (p->irq != PARPORT_IRQ_NONE) { if (request_irq (p->irq, parport_irq_handler, diff --git a/drivers/parport/share.c b/drivers/parport/share.c index 5ce5ef211bdb..754f21fd9768 100644 --- a/drivers/parport/share.c +++ b/drivers/parport/share.c @@ -936,8 +936,10 @@ parport_register_dev_model(struct parport *port, const char *name, * pardevice fields. -arca */ port->ops->init_state(par_dev, par_dev->state); - port->proc_device = par_dev; - parport_device_proc_register(par_dev); + if (!test_and_set_bit(PARPORT_DEVPROC_REGISTERED, &port->devflags)) { + port->proc_device = par_dev; + parport_device_proc_register(par_dev); + } return par_dev; diff --git a/drivers/pci/controller/pci-dra7xx.c b/drivers/pci/controller/pci-dra7xx.c index d60d4cf20516..330866f9b924 100644 --- a/drivers/pci/controller/pci-dra7xx.c +++ b/drivers/pci/controller/pci-dra7xx.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/of_gpio.h> #include <linux/of_device.h> +#include <linux/of_platform.h> #include <linux/pci.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> @@ -81,6 +82,9 @@ #define MSI_REQ_GRANT BIT(0) #define MSI_VECTOR_SHIFT 7 +#define PCIE_1LANE_2LANE_SELECTION BIT(13) +#define PCIE_B1C0_MODE_SEL BIT(2) + struct dra7xx_pcie { void __iomem *base; struct phy **phy; @@ -94,6 +98,10 @@ struct dra7xx_pcie { struct dra7xx_pcie_of_data { enum dw_pcie_device_mode mode; + u32 b1co_mode_sel_mask; +}; + +struct dra7xx_pcie_data { }; #define to_dra7xx_pcie(x) dev_get_drvdata((x)->dev) @@ -506,6 +514,16 @@ static const struct dra7xx_pcie_of_data dra7xx_pcie_ep_of_data = { .mode = DW_PCIE_EP_TYPE, }; +static const struct dra7xx_pcie_of_data dra746_pcie_rc_of_data = { + .b1co_mode_sel_mask = BIT(2), + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra746_pcie_ep_of_data = { + .b1co_mode_sel_mask = BIT(2), + .mode = DW_PCIE_EP_TYPE, +}; + static const struct of_device_id of_dra7xx_pcie_match[] = { { .compatible = "ti,dra7-pcie", @@ -515,6 +533,22 @@ static const struct of_device_id of_dra7xx_pcie_match[] = { .compatible = "ti,dra7-pcie-ep", .data = &dra7xx_pcie_ep_of_data, }, + { + .compatible = "ti,dra746-pcie-rc", + .data = &dra746_pcie_rc_of_data, + }, + { + .compatible = "ti,dra746-pcie-ep", + .data = &dra746_pcie_ep_of_data, + }, + { + .compatible = "ti,dra726-pcie-rc", + .data = &dra7xx_pcie_rc_of_data, + }, + { + .compatible = "ti,dra726-pcie-ep", + .data = &dra7xx_pcie_ep_of_data, + }, {}, }; MODULE_DEVICE_TABLE(of, of_dra7xx_pcie_match); @@ -562,6 +596,44 @@ static int dra7xx_pcie_ep_legacy_mode(struct dra7xx_pcie *dra7xx) return ret; } +static int dra7xx_pcie_configure_two_lane(struct device *dev, + u32 b1co_mode_sel_mask) +{ + struct device_node *np = dev->of_node; + struct regmap *pcie_syscon; + unsigned int pcie_reg; + + pcie_syscon = syscon_regmap_lookup_by_phandle(np, "syscon-lane-conf"); + if (IS_ERR(pcie_syscon)) { + dev_err(dev, "unable to get syscon-lane-conf\n"); + return -EINVAL; + } + + if (of_property_read_u32_index(np, "syscon-lane-conf", 1, &pcie_reg)) { + dev_err(dev, "couldn't get lane configuration reg offset\n"); + return -EINVAL; + } + + regmap_update_bits(pcie_syscon, pcie_reg, PCIE_1LANE_2LANE_SELECTION, + PCIE_1LANE_2LANE_SELECTION); + + pcie_syscon = syscon_regmap_lookup_by_phandle(np, "syscon-lane-sel"); + if (IS_ERR(pcie_syscon)) { + dev_err(dev, "unable to get syscon-lane-sel\n"); + return -EINVAL; + } + + if (of_property_read_u32_index(np, "syscon-lane-sel", 1, &pcie_reg)) { + dev_err(dev, "couldn't get lane selection reg offset\n"); + return -EINVAL; + } + + regmap_update_bits(pcie_syscon, pcie_reg, b1co_mode_sel_mask, + PCIE_B1C0_MODE_SEL); + + return 0; +} + static int __init dra7xx_pcie_probe(struct platform_device *pdev) { u32 reg; @@ -581,6 +653,7 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) const struct of_device_id *match; const struct dra7xx_pcie_of_data *data; enum dw_pcie_device_mode mode; + u32 b1co_mode_sel_mask; match = of_match_device(of_match_ptr(of_dra7xx_pcie_match), dev); if (!match) @@ -588,6 +661,7 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) data = (struct dra7xx_pcie_of_data *)match->data; mode = (enum dw_pcie_device_mode)data->mode; + b1co_mode_sel_mask = data->b1co_mode_sel_mask; dra7xx = devm_kzalloc(dev, sizeof(*dra7xx), GFP_KERNEL); if (!dra7xx) @@ -651,6 +725,12 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) dra7xx->dev = dev; dra7xx->phy_count = phy_count; + if (phy_count == 2) { + ret = dra7xx_pcie_configure_two_lane(dev, b1co_mode_sel_mask); + if (ret < 0) + goto err_phy; + } + pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); if (ret < 0) { diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 31f31d460fc9..357527712539 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -303,13 +303,6 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) return rc; } - pci_iov_set_numvfs(dev, nr_virtfn); - iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE; - pci_cfg_access_lock(dev); - pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl); - msleep(100); - pci_cfg_access_unlock(dev); - iov->initial_VFs = initial; if (nr_virtfn < initial) initial = nr_virtfn; @@ -320,6 +313,13 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) goto err_pcibios; } + pci_iov_set_numvfs(dev, nr_virtfn); + iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE; + pci_cfg_access_lock(dev); + pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl); + msleep(100); + pci_cfg_access_unlock(dev); + for (i = 0; i < initial; i++) { rc = virtfn_add(dev, i, 0); if (rc) @@ -555,21 +555,61 @@ void pci_iov_release(struct pci_dev *dev) } /** - * pci_iov_resource_bar - get position of the SR-IOV BAR + * pci_iov_update_resource - update a VF BAR * @dev: the PCI device * @resno: the resource number * - * Returns position of the BAR encapsulated in the SR-IOV capability. + * Update a VF BAR in the SR-IOV capability of a PF. */ -int pci_iov_resource_bar(struct pci_dev *dev, int resno) +void pci_iov_update_resource(struct pci_dev *dev, int resno) { - if (resno < PCI_IOV_RESOURCES || resno > PCI_IOV_RESOURCE_END) - return 0; + struct pci_sriov *iov = dev->is_physfn ? dev->sriov : NULL; + struct resource *res = dev->resource + resno; + int vf_bar = resno - PCI_IOV_RESOURCES; + struct pci_bus_region region; + u16 cmd; + u32 new; + int reg; + + /* + * The generic pci_restore_bars() path calls this for all devices, + * including VFs and non-SR-IOV devices. If this is not a PF, we + * have nothing to do. + */ + if (!iov) + return; + + pci_read_config_word(dev, iov->pos + PCI_SRIOV_CTRL, &cmd); + if ((cmd & PCI_SRIOV_CTRL_VFE) && (cmd & PCI_SRIOV_CTRL_MSE)) { + dev_WARN(&dev->dev, "can't update enabled VF BAR%d %pR\n", + vf_bar, res); + return; + } + + /* + * Ignore unimplemented BARs, unused resource slots for 64-bit + * BARs, and non-movable resources, e.g., those described via + * Enhanced Allocation. + */ + if (!res->flags) + return; + + if (res->flags & IORESOURCE_UNSET) + return; + + if (res->flags & IORESOURCE_PCI_FIXED) + return; - BUG_ON(!dev->is_physfn); + pcibios_resource_to_bus(dev->bus, ®ion, res); + new = region.start; + new |= res->flags & ~PCI_BASE_ADDRESS_MEM_MASK; - return dev->sriov->pos + PCI_SRIOV_BAR + - 4 * (resno - PCI_IOV_RESOURCES); + reg = iov->pos + PCI_SRIOV_BAR + 4 * vf_bar; + pci_write_config_dword(dev, reg, new); + if (res->flags & IORESOURCE_MEM_64) { + new = region.start >> 16 >> 16; + pci_write_config_dword(dev, reg + 4, new); + } } resource_size_t __weak pcibios_iov_resource_alignment(struct pci_dev *dev, diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index d7ffd66814bb..fca925543fae 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -945,6 +945,7 @@ static int pci_pm_thaw_noirq(struct device *dev) return pci_legacy_resume_early(dev); pci_update_current_state(pci_dev, PCI_D0); + pci_restore_state(pci_dev); if (drv && drv->pm && drv->pm->thaw_noirq) error = drv->pm->thaw_noirq(dev); diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index d7508704c992..f8b2b5987ea9 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -973,15 +973,19 @@ void pci_remove_legacy_files(struct pci_bus *b) int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma, enum pci_mmap_api mmap_api) { - unsigned long nr, start, size, pci_start; + unsigned long nr, start, size; + resource_size_t pci_start = 0, pci_end; if (pci_resource_len(pdev, resno) == 0) return 0; nr = vma_pages(vma); start = vma->vm_pgoff; size = ((pci_resource_len(pdev, resno) - 1) >> PAGE_SHIFT) + 1; - pci_start = (mmap_api == PCI_MMAP_PROCFS) ? - pci_resource_start(pdev, resno) >> PAGE_SHIFT : 0; + if (mmap_api == PCI_MMAP_PROCFS) { + pci_resource_to_user(pdev, resno, &pdev->resource[resno], + &pci_start, &pci_end); + pci_start >>= PAGE_SHIFT; + } if (start >= pci_start && start < pci_start + size && start + nr <= pci_start + size) return 1; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e311a9bf2c90..1a14ca8965e6 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -519,10 +519,6 @@ static void pci_restore_bars(struct pci_dev *dev) { int i; - /* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */ - if (dev->is_virtfn) - return; - for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) pci_update_resource(dev, i); } @@ -1736,8 +1732,8 @@ static void pci_pme_list_scan(struct work_struct *work) } } if (!list_empty(&pci_pme_list)) - schedule_delayed_work(&pci_pme_work, - msecs_to_jiffies(PME_TIMEOUT)); + queue_delayed_work(system_freezable_wq, &pci_pme_work, + msecs_to_jiffies(PME_TIMEOUT)); mutex_unlock(&pci_pme_list_mutex); } @@ -1802,8 +1798,9 @@ void pci_pme_active(struct pci_dev *dev, bool enable) mutex_lock(&pci_pme_list_mutex); list_add(&pme_dev->list, &pci_pme_list); if (list_is_singular(&pci_pme_list)) - schedule_delayed_work(&pci_pme_work, - msecs_to_jiffies(PME_TIMEOUT)); + queue_delayed_work(system_freezable_wq, + &pci_pme_work, + msecs_to_jiffies(PME_TIMEOUT)); mutex_unlock(&pci_pme_list_mutex); } else { mutex_lock(&pci_pme_list_mutex); @@ -4472,36 +4469,6 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags) } EXPORT_SYMBOL(pci_select_bars); -/** - * pci_resource_bar - get position of the BAR associated with a resource - * @dev: the PCI device - * @resno: the resource number - * @type: the BAR type to be filled in - * - * Returns BAR position in config space, or 0 if the BAR is invalid. - */ -int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type) -{ - int reg; - - if (resno < PCI_ROM_RESOURCE) { - *type = pci_bar_unknown; - return PCI_BASE_ADDRESS_0 + 4 * resno; - } else if (resno == PCI_ROM_RESOURCE) { - *type = pci_bar_mem32; - return dev->rom_base_reg; - } else if (resno < PCI_BRIDGE_RESOURCES) { - /* device specific resource */ - *type = pci_bar_unknown; - reg = pci_iov_resource_bar(dev, resno); - if (reg) - return reg; - } - - dev_err(&dev->dev, "BAR %d: invalid resource\n", resno); - return 0; -} - /* Some architectures require additional programming to enable VGA */ static arch_set_vga_state_t arch_set_vga_state; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index d390fc1475ec..c43e448873ca 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -232,7 +232,6 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, int pci_setup_device(struct pci_dev *dev); int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, struct resource *res, unsigned int reg); -int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type); void pci_configure_ari(struct pci_dev *dev); void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head); @@ -276,7 +275,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev) #ifdef CONFIG_PCI_IOV int pci_iov_init(struct pci_dev *dev); void pci_iov_release(struct pci_dev *dev); -int pci_iov_resource_bar(struct pci_dev *dev, int resno); +void pci_iov_update_resource(struct pci_dev *dev, int resno); resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno); void pci_restore_iov_state(struct pci_dev *dev); int pci_iov_bus_range(struct pci_bus *bus); @@ -290,10 +289,6 @@ static inline void pci_iov_release(struct pci_dev *dev) { } -static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno) -{ - return 0; -} static inline void pci_restore_iov_state(struct pci_dev *dev) { } diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 317e3558a35e..c6a012b5ba39 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -518,25 +518,32 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) return NULL; + INIT_LIST_HEAD(&link->sibling); INIT_LIST_HEAD(&link->children); INIT_LIST_HEAD(&link->link); link->pdev = pdev; - if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) { + + /* + * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe + * hierarchies. + */ + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT || + pci_pcie_type(pdev) == PCI_EXP_TYPE_PCIE_BRIDGE) { + link->root = link; + } else { struct pcie_link_state *parent; + parent = pdev->bus->parent->self->link_state; if (!parent) { kfree(link); return NULL; } + link->parent = parent; + link->root = link->parent->root; list_add(&link->link, &parent->children); } - /* Setup a pointer to the root port link */ - if (!link->parent) - link->root = link; - else - link->root = link->parent->root; list_add(&link->sibling, &link_list); pdev->link_state = link; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 71d9a6d1bd56..b83df942794f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -226,7 +226,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, mask64 = (u32)PCI_BASE_ADDRESS_MEM_MASK; } } else { - res->flags |= (l & IORESOURCE_ROM_ENABLE); + if (l & PCI_ROM_ADDRESS_ENABLE) + res->flags |= IORESOURCE_ROM_ENABLE; l64 = l & PCI_ROM_ADDRESS_MASK; sz64 = sz & PCI_ROM_ADDRESS_MASK; mask64 = (u32)PCI_ROM_ADDRESS_MASK; diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index eb0ad530dc43..3eea7fc5e1a2 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -31,6 +31,11 @@ int pci_enable_rom(struct pci_dev *pdev) if (!res->flags) return -1; + /* + * Ideally pci_update_resource() would update the ROM BAR address, + * and we would only set the enable bit here. But apparently some + * devices have buggy ROM BARs that read as zero when disabled. + */ pcibios_resource_to_bus(pdev->bus, ®ion, res); pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr); rom_addr &= ~PCI_ROM_ADDRESS_MASK; diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 604011e047d6..25062966cbfa 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -25,21 +25,18 @@ #include <linux/slab.h> #include "pci.h" - -void pci_update_resource(struct pci_dev *dev, int resno) +static void pci_std_update_resource(struct pci_dev *dev, int resno) { struct pci_bus_region region; bool disable; u16 cmd; u32 new, check, mask; int reg; - enum pci_bar_type type; struct resource *res = dev->resource + resno; - if (dev->is_virtfn) { - dev_warn(&dev->dev, "can't update VF BAR%d\n", resno); + /* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */ + if (dev->is_virtfn) return; - } /* * Ignore resources for unimplemented BARs and unused resource slots @@ -60,21 +57,34 @@ void pci_update_resource(struct pci_dev *dev, int resno) return; pcibios_resource_to_bus(dev->bus, ®ion, res); + new = region.start; - new = region.start | (res->flags & PCI_REGION_FLAG_MASK); - if (res->flags & IORESOURCE_IO) + if (res->flags & IORESOURCE_IO) { mask = (u32)PCI_BASE_ADDRESS_IO_MASK; - else + new |= res->flags & ~PCI_BASE_ADDRESS_IO_MASK; + } else if (resno == PCI_ROM_RESOURCE) { + mask = (u32)PCI_ROM_ADDRESS_MASK; + } else { mask = (u32)PCI_BASE_ADDRESS_MEM_MASK; + new |= res->flags & ~PCI_BASE_ADDRESS_MEM_MASK; + } - reg = pci_resource_bar(dev, resno, &type); - if (!reg) - return; - if (type != pci_bar_unknown) { + if (resno < PCI_ROM_RESOURCE) { + reg = PCI_BASE_ADDRESS_0 + 4 * resno; + } else if (resno == PCI_ROM_RESOURCE) { + + /* + * Apparently some Matrox devices have ROM BARs that read + * as zero when disabled, so don't update ROM BARs unless + * they're enabled. See https://lkml.org/lkml/2005/8/30/138. + */ if (!(res->flags & IORESOURCE_ROM_ENABLE)) return; + + reg = dev->rom_base_reg; new |= PCI_ROM_ADDRESS_ENABLE; - } + } else + return; /* * We can't update a 64-bit BAR atomically, so when possible, @@ -110,6 +120,16 @@ void pci_update_resource(struct pci_dev *dev, int resno) pci_write_config_word(dev, PCI_COMMAND, cmd); } +void pci_update_resource(struct pci_dev *dev, int resno) +{ + if (resno <= PCI_ROM_RESOURCE) + pci_std_update_resource(dev, resno); +#ifdef CONFIG_PCI_IOV + else if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END) + pci_iov_update_resource(dev, resno); +#endif +} + int pci_claim_resource(struct pci_dev *dev, int resource) { struct resource *res = &dev->resource[resource]; diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index c793ef320015..f638e05fc9db 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -376,6 +376,7 @@ config PHY_QCOM_UFS config PHY_TUSB1210 tristate "TI TUSB1210 ULPI PHY module" depends on USB_ULPI_BUS + depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in select GENERIC_PHY help Support for TI TUSB1210 USB ULPI PHY. diff --git a/drivers/pinctrl/berlin/berlin-bg4ct.c b/drivers/pinctrl/berlin/berlin-bg4ct.c index 09172043d589..c617ec49e9ed 100644 --- a/drivers/pinctrl/berlin/berlin-bg4ct.c +++ b/drivers/pinctrl/berlin/berlin-bg4ct.c @@ -217,7 +217,7 @@ static const struct berlin_desc_group berlin4ct_soc_pinctrl_groups[] = { BERLIN_PINCTRL_GROUP("SCRD0_CRD_PRES", 0xc, 0x3, 0x15, BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO20 */ BERLIN_PINCTRL_FUNCTION(0x1, "scrd0"), /* crd pres */ - BERLIN_PINCTRL_FUNCTION(0x1, "sd1a")), /* DAT3 */ + BERLIN_PINCTRL_FUNCTION(0x3, "sd1a")), /* DAT3 */ BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x18, BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */ BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */ diff --git a/drivers/pinctrl/freescale/pinctrl-mxs.c b/drivers/pinctrl/freescale/pinctrl-mxs.c index 6bbda6b4ab50..5da9c95dccb7 100644 --- a/drivers/pinctrl/freescale/pinctrl-mxs.c +++ b/drivers/pinctrl/freescale/pinctrl-mxs.c @@ -195,6 +195,16 @@ static int mxs_pinctrl_get_func_groups(struct pinctrl_dev *pctldev, return 0; } +static void mxs_pinctrl_rmwl(u32 value, u32 mask, u8 shift, void __iomem *reg) +{ + u32 tmp; + + tmp = readl(reg); + tmp &= ~(mask << shift); + tmp |= value << shift; + writel(tmp, reg); +} + static int mxs_pinctrl_set_mux(struct pinctrl_dev *pctldev, unsigned selector, unsigned group) { @@ -212,8 +222,7 @@ static int mxs_pinctrl_set_mux(struct pinctrl_dev *pctldev, unsigned selector, reg += bank * 0x20 + pin / 16 * 0x10; shift = pin % 16 * 2; - writel(0x3 << shift, reg + CLR); - writel(g->muxsel[i] << shift, reg + SET); + mxs_pinctrl_rmwl(g->muxsel[i], 0x3, shift, reg); } return 0; @@ -280,8 +289,7 @@ static int mxs_pinconf_group_set(struct pinctrl_dev *pctldev, /* mA */ if (config & MA_PRESENT) { shift = pin % 8 * 4; - writel(0x3 << shift, reg + CLR); - writel(ma << shift, reg + SET); + mxs_pinctrl_rmwl(ma, 0x3, shift, reg); } /* vol */ diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c index 5979d38c46b2..7329500943a3 100644 --- a/drivers/pinctrl/intel/pinctrl-broxton.c +++ b/drivers/pinctrl/intel/pinctrl-broxton.c @@ -19,7 +19,7 @@ #define BXT_PAD_OWN 0x020 #define BXT_HOSTSW_OWN 0x080 -#define BXT_PADCFGLOCK 0x090 +#define BXT_PADCFGLOCK 0x060 #define BXT_GPI_IE 0x110 #define BXT_COMMUNITY(s, e) \ diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index a009ae34c5ef..930f0f25c1ce 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1466,12 +1466,11 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) offset += range->npins; } - /* Mask and clear all interrupts */ - chv_writel(0, pctrl->regs + CHV_INTMASK); + /* Clear all interrupts */ chv_writel(0xffff, pctrl->regs + CHV_INTSTAT); ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0, - handle_simple_irq, IRQ_TYPE_NONE); + handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add IRQ chip\n"); goto fail; diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c index 9677807db364..b505b87661f8 100644 --- a/drivers/pinctrl/meson/pinctrl-meson8b.c +++ b/drivers/pinctrl/meson/pinctrl-meson8b.c @@ -732,8 +732,8 @@ static const char * const sdxc_c_groups[] = { static const char * const nand_groups[] = { "nand_io", "nand_io_ce0", "nand_io_ce1", "nand_io_rb0", "nand_ale", "nand_cle", - "nand_wen_clk", "nand_ren_clk", "nand_dqs0", - "nand_dqs1" + "nand_wen_clk", "nand_ren_clk", "nand_dqs_0", + "nand_dqs_1" }; static const char * const nor_groups[] = { diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 146264a41ec8..9736f9be5447 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -597,10 +597,6 @@ static void msm_gpio_irq_unmask(struct irq_data *d) spin_lock_irqsave(&pctrl->lock, flags); - val = readl(pctrl->regs + g->intr_status_reg); - val &= ~BIT(g->intr_status_bit); - writel(val, pctrl->regs + g->intr_status_reg); - val = readl(pctrl->regs + g->intr_cfg_reg); val |= BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index 71ccf6a90b22..2551e4adb33f 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -194,8 +194,6 @@ static int exynos_irq_request_resources(struct irq_data *irqd) spin_unlock_irqrestore(&bank->slock, flags); - exynos_irq_unmask(irqd); - return 0; } @@ -216,8 +214,6 @@ static void exynos_irq_release_resources(struct irq_data *irqd) shift = irqd->hwirq * bank_type->fld_width[PINCFG_TYPE_FUNC]; mask = (1 << bank_type->fld_width[PINCFG_TYPE_FUNC]) - 1; - exynos_irq_mask(irqd); - spin_lock_irqsave(&bank->slock, flags); con = readl(d->virt_base + reg_con); diff --git a/drivers/pinctrl/sh-pfc/core.c b/drivers/pinctrl/sh-pfc/core.c index 2b0d70217bbd..699efb1a8c45 100644 --- a/drivers/pinctrl/sh-pfc/core.c +++ b/drivers/pinctrl/sh-pfc/core.c @@ -543,6 +543,9 @@ static int sh_pfc_probe(struct platform_device *pdev) ret = info->ops->init(pfc); if (ret < 0) return ret; + + /* .init() may have overridden pfc->info */ + info = pfc->info; } /* Enable dummy states for those platforms without pinctrl support */ diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c index 87a4f44147c1..42ffa8708abc 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c @@ -1102,7 +1102,7 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_MSEL(IP6_5_3, FMIN_E, SEL_FM_4), PINMUX_IPSR_DATA(IP6_7_6, AUDIO_CLKOUT), PINMUX_IPSR_MSEL(IP6_7_6, MSIOF1_SS1_B, SEL_SOF1_1), - PINMUX_IPSR_MSEL(IP6_5_3, TX2, SEL_SCIF2_0), + PINMUX_IPSR_MSEL(IP6_7_6, TX2, SEL_SCIF2_0), PINMUX_IPSR_MSEL(IP6_7_6, SCIFA2_TXD, SEL_SCIFA2_0), PINMUX_IPSR_DATA(IP6_9_8, IRQ0), PINMUX_IPSR_MSEL(IP6_9_8, SCIFB1_RXD_D, SEL_SCIFB1_3), diff --git a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c index 862a096c5dba..be5c71df148d 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c @@ -811,6 +811,7 @@ static const struct sunxi_desc_pin sun4i_a10_pins[] = { SUNXI_FUNCTION(0x2, "lcd1"), /* D16 */ SUNXI_FUNCTION(0x3, "pata"), /* ATAD12 */ SUNXI_FUNCTION(0x4, "keypad"), /* IN6 */ + SUNXI_FUNCTION(0x5, "sim"), /* DET */ SUNXI_FUNCTION_IRQ(0x6, 16), /* EINT16 */ SUNXI_FUNCTION(0x7, "csi1")), /* D16 */ SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 17), diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c index 90b973e15982..a7c81e988656 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c @@ -394,7 +394,7 @@ static const struct sunxi_desc_pin sun8i_a83t_pins[] = { SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 18), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), - SUNXI_FUNCTION(0x3, "owa")), /* DOUT */ + SUNXI_FUNCTION(0x3, "spdif")), /* DOUT */ SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 19), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out")), diff --git a/drivers/platform/goldfish/pdev_bus.c b/drivers/platform/goldfish/pdev_bus.c index 1f52462f4cdd..dd9ea463c2a4 100644 --- a/drivers/platform/goldfish/pdev_bus.c +++ b/drivers/platform/goldfish/pdev_bus.c @@ -157,23 +157,26 @@ static int goldfish_new_pdev(void) static irqreturn_t goldfish_pdev_bus_interrupt(int irq, void *dev_id) { irqreturn_t ret = IRQ_NONE; + while (1) { u32 op = readl(pdev_bus_base + PDEV_BUS_OP); - switch (op) { - case PDEV_BUS_OP_DONE: - return IRQ_NONE; + switch (op) { case PDEV_BUS_OP_REMOVE_DEV: goldfish_pdev_remove(); + ret = IRQ_HANDLED; break; case PDEV_BUS_OP_ADD_DEV: goldfish_new_pdev(); + ret = IRQ_HANDLED; break; + + case PDEV_BUS_OP_DONE: + default: + return ret; } - ret = IRQ_HANDLED; } - return ret; } static int goldfish_pdev_bus_probe(struct platform_device *pdev) diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 1062fa42ff26..b2cdc1a1ad4f 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -1816,11 +1816,24 @@ static int __init acer_wmi_enable_lm(void) return status; } +#define ACER_WMID_ACCEL_HID "BST0001" + static acpi_status __init acer_wmi_get_handle_cb(acpi_handle ah, u32 level, void *ctx, void **retval) { + struct acpi_device *dev; + + if (!strcmp(ctx, "SENR")) { + if (acpi_bus_get_device(ah, &dev)) + return AE_OK; + if (!strcmp(ACER_WMID_ACCEL_HID, acpi_device_hid(dev))) + return AE_OK; + } else + return AE_OK; + *(acpi_handle *)retval = ah; - return AE_OK; + + return AE_CTRL_TERMINATE; } static int __init acer_wmi_get_handle(const char *name, const char *prop, @@ -1847,7 +1860,7 @@ static int __init acer_wmi_accel_setup(void) { int err; - err = acer_wmi_get_handle("SENR", "BST0001", &gsensor_handle); + err = acer_wmi_get_handle("SENR", ACER_WMID_ACCEL_HID, &gsensor_handle); if (err) return err; @@ -2185,10 +2198,11 @@ static int __init acer_wmi_init(void) err = acer_wmi_input_setup(); if (err) return err; + err = acer_wmi_accel_setup(); + if (err) + return err; } - acer_wmi_accel_setup(); - err = platform_driver_register(&acer_platform_driver); if (err) { pr_err("Unable to register platform driver\n"); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index be3bc2f4edd4..09cc64b3b695 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -807,6 +807,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) case 11: case 7: case 6: + case 1: ideapad_input_report(priv, vpc_bit); break; case 5: diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c index 1fc0de870ff8..361770568ad0 100644 --- a/drivers/platform/x86/intel_mid_powerbtn.c +++ b/drivers/platform/x86/intel_mid_powerbtn.c @@ -77,7 +77,7 @@ static int mfld_pb_probe(struct platform_device *pdev) input_set_capability(input, EV_KEY, KEY_POWER); - error = request_threaded_irq(irq, NULL, mfld_pb_isr, 0, + error = request_threaded_irq(irq, NULL, mfld_pb_isr, IRQF_ONESHOT, DRIVER_NAME, input); if (error) { dev_err(&pdev->dev, "Unable to request irq %d for mfld power" diff --git a/drivers/power/bq24190_charger.c b/drivers/power/bq24190_charger.c index f5746b9f4e83..f05d2773fe00 100644 --- a/drivers/power/bq24190_charger.c +++ b/drivers/power/bq24190_charger.c @@ -144,10 +144,7 @@ * so the first read after a fault returns the latched value and subsequent * reads return the current value. In order to return the fault status * to the user, have the interrupt handler save the reg's value and retrieve - * it in the appropriate health/status routine. Each routine has its own - * flag indicating whether it should use the value stored by the last run - * of the interrupt handler or do an actual reg read. That way each routine - * can report back whatever fault may have occured. + * it in the appropriate health/status routine. */ struct bq24190_dev_info { struct i2c_client *client; @@ -159,10 +156,6 @@ struct bq24190_dev_info { unsigned int gpio_int; unsigned int irq; struct mutex f_reg_lock; - bool first_time; - bool charger_health_valid; - bool battery_health_valid; - bool battery_status_valid; u8 f_reg; u8 ss_reg; u8 watchdog; @@ -636,21 +629,11 @@ static int bq24190_charger_get_health(struct bq24190_dev_info *bdi, union power_supply_propval *val) { u8 v; - int health, ret; + int health; mutex_lock(&bdi->f_reg_lock); - - if (bdi->charger_health_valid) { - v = bdi->f_reg; - bdi->charger_health_valid = false; - mutex_unlock(&bdi->f_reg_lock); - } else { - mutex_unlock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &v); - if (ret < 0) - return ret; - } + v = bdi->f_reg; + mutex_unlock(&bdi->f_reg_lock); if (v & BQ24190_REG_F_BOOST_FAULT_MASK) { /* @@ -937,18 +920,8 @@ static int bq24190_battery_get_status(struct bq24190_dev_info *bdi, int status, ret; mutex_lock(&bdi->f_reg_lock); - - if (bdi->battery_status_valid) { - chrg_fault = bdi->f_reg; - bdi->battery_status_valid = false; - mutex_unlock(&bdi->f_reg_lock); - } else { - mutex_unlock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &chrg_fault); - if (ret < 0) - return ret; - } + chrg_fault = bdi->f_reg; + mutex_unlock(&bdi->f_reg_lock); chrg_fault &= BQ24190_REG_F_CHRG_FAULT_MASK; chrg_fault >>= BQ24190_REG_F_CHRG_FAULT_SHIFT; @@ -996,21 +969,11 @@ static int bq24190_battery_get_health(struct bq24190_dev_info *bdi, union power_supply_propval *val) { u8 v; - int health, ret; + int health; mutex_lock(&bdi->f_reg_lock); - - if (bdi->battery_health_valid) { - v = bdi->f_reg; - bdi->battery_health_valid = false; - mutex_unlock(&bdi->f_reg_lock); - } else { - mutex_unlock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &v); - if (ret < 0) - return ret; - } + v = bdi->f_reg; + mutex_unlock(&bdi->f_reg_lock); if (v & BQ24190_REG_F_BAT_FAULT_MASK) { health = POWER_SUPPLY_HEALTH_OVERVOLTAGE; @@ -1197,9 +1160,12 @@ static const struct power_supply_desc bq24190_battery_desc = { static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) { struct bq24190_dev_info *bdi = data; - bool alert_userspace = false; + const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK; + const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK + | BQ24190_REG_F_NTC_FAULT_MASK; + bool alert_charger = false, alert_battery = false; u8 ss_reg = 0, f_reg = 0; - int ret; + int i, ret; pm_runtime_get_sync(bdi->dev); @@ -1209,6 +1175,32 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) goto out; } + i = 0; + do { + ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg); + if (ret < 0) { + dev_err(bdi->dev, "Can't read F reg: %d\n", ret); + goto out; + } + } while (f_reg && ++i < 2); + + if (f_reg != bdi->f_reg) { + dev_info(bdi->dev, + "Fault: boost %d, charge %d, battery %d, ntc %d\n", + !!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK), + !!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK), + !!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK), + !!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK)); + + mutex_lock(&bdi->f_reg_lock); + if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f)) + alert_battery = true; + if ((bdi->f_reg & ~battery_mask_f) != (f_reg & ~battery_mask_f)) + alert_charger = true; + bdi->f_reg = f_reg; + mutex_unlock(&bdi->f_reg_lock); + } + if (ss_reg != bdi->ss_reg) { /* * The device is in host mode so when PG_STAT goes from 1->0 @@ -1225,47 +1217,17 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) ret); } + if ((bdi->ss_reg & battery_mask_ss) != (ss_reg & battery_mask_ss)) + alert_battery = true; + if ((bdi->ss_reg & ~battery_mask_ss) != (ss_reg & ~battery_mask_ss)) + alert_charger = true; bdi->ss_reg = ss_reg; - alert_userspace = true; - } - - mutex_lock(&bdi->f_reg_lock); - - ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg); - if (ret < 0) { - mutex_unlock(&bdi->f_reg_lock); - dev_err(bdi->dev, "Can't read F reg: %d\n", ret); - goto out; } - if (f_reg != bdi->f_reg) { - bdi->f_reg = f_reg; - bdi->charger_health_valid = true; - bdi->battery_health_valid = true; - bdi->battery_status_valid = true; - - alert_userspace = true; - } - - mutex_unlock(&bdi->f_reg_lock); - - /* - * Sometimes bq24190 gives a steady trickle of interrupts even - * though the watchdog timer is turned off and neither the STATUS - * nor FAULT registers have changed. Weed out these sprurious - * interrupts so userspace isn't alerted for no reason. - * In addition, the chip always generates an interrupt after - * register reset so we should ignore that one (the very first - * interrupt received). - */ - if (alert_userspace) { - if (!bdi->first_time) { - power_supply_changed(bdi->charger); - power_supply_changed(bdi->battery); - } else { - bdi->first_time = false; - } - } + if (alert_charger) + power_supply_changed(bdi->charger); + if (alert_battery) + power_supply_changed(bdi->battery); out: pm_runtime_put_sync(bdi->dev); @@ -1300,6 +1262,10 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi) goto out; ret = bq24190_set_mode_host(bdi); + if (ret < 0) + goto out; + + ret = bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg); out: pm_runtime_put_sync(bdi->dev); return ret; @@ -1375,10 +1341,8 @@ static int bq24190_probe(struct i2c_client *client, bdi->model = id->driver_data; strncpy(bdi->model_name, id->name, I2C_NAME_SIZE); mutex_init(&bdi->f_reg_lock); - bdi->first_time = true; - bdi->charger_health_valid = false; - bdi->battery_health_valid = false; - bdi->battery_status_valid = false; + bdi->f_reg = 0; + bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */ i2c_set_clientdata(client, bdi); @@ -1392,22 +1356,13 @@ static int bq24190_probe(struct i2c_client *client, return -EINVAL; } - ret = devm_request_threaded_irq(dev, bdi->irq, NULL, - bq24190_irq_handler_thread, - IRQF_TRIGGER_RISING | IRQF_ONESHOT, - "bq24190-charger", bdi); - if (ret < 0) { - dev_err(dev, "Can't set up irq handler\n"); - goto out1; - } - pm_runtime_enable(dev); pm_runtime_resume(dev); ret = bq24190_hw_init(bdi); if (ret < 0) { dev_err(dev, "Hardware init failed\n"); - goto out2; + goto out1; } charger_cfg.drv_data = bdi; @@ -1418,7 +1373,7 @@ static int bq24190_probe(struct i2c_client *client, if (IS_ERR(bdi->charger)) { dev_err(dev, "Can't register charger\n"); ret = PTR_ERR(bdi->charger); - goto out2; + goto out1; } battery_cfg.drv_data = bdi; @@ -1427,24 +1382,34 @@ static int bq24190_probe(struct i2c_client *client, if (IS_ERR(bdi->battery)) { dev_err(dev, "Can't register battery\n"); ret = PTR_ERR(bdi->battery); - goto out3; + goto out2; } ret = bq24190_sysfs_create_group(bdi); if (ret) { dev_err(dev, "Can't create sysfs entries\n"); + goto out3; + } + + ret = devm_request_threaded_irq(dev, bdi->irq, NULL, + bq24190_irq_handler_thread, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + "bq24190-charger", bdi); + if (ret < 0) { + dev_err(dev, "Can't set up irq handler\n"); goto out4; } return 0; out4: - power_supply_unregister(bdi->battery); + bq24190_sysfs_remove_group(bdi); out3: - power_supply_unregister(bdi->charger); + power_supply_unregister(bdi->battery); out2: - pm_runtime_disable(dev); + power_supply_unregister(bdi->charger); out1: + pm_runtime_disable(dev); if (bdi->gpio_int) gpio_free(bdi->gpio_int); @@ -1488,12 +1453,13 @@ static int bq24190_pm_resume(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct bq24190_dev_info *bdi = i2c_get_clientdata(client); - bdi->charger_health_valid = false; - bdi->battery_health_valid = false; - bdi->battery_status_valid = false; + bdi->f_reg = 0; + bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */ pm_runtime_get_sync(bdi->dev); bq24190_register_reset(bdi); + bq24190_set_mode_host(bdi); + bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg); pm_runtime_put_sync(bdi->dev); /* Things may have changed while suspended so alert upper layer */ diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c index e9e24df35f26..2579f025b90b 100644 --- a/drivers/power/reset/at91-poweroff.c +++ b/drivers/power/reset/at91-poweroff.c @@ -14,9 +14,12 @@ #include <linux/io.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/platform_device.h> #include <linux/printk.h> +#include <soc/at91/at91sam9_ddrsdr.h> + #define AT91_SHDW_CR 0x00 /* Shut Down Control Register */ #define AT91_SHDW_SHDW BIT(0) /* Shut Down command */ #define AT91_SHDW_KEY (0xa5 << 24) /* KEY Password */ @@ -50,6 +53,7 @@ static const char *shdwc_wakeup_modes[] = { static void __iomem *at91_shdwc_base; static struct clk *sclk; +static void __iomem *mpddrc_base; static void __init at91_wakeup_status(void) { @@ -73,6 +77,29 @@ static void at91_poweroff(void) writel(AT91_SHDW_KEY | AT91_SHDW_SHDW, at91_shdwc_base + AT91_SHDW_CR); } +static void at91_lpddr_poweroff(void) +{ + asm volatile( + /* Align to cache lines */ + ".balign 32\n\t" + + /* Ensure AT91_SHDW_CR is in the TLB by reading it */ + " ldr r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t" + + /* Power down SDRAM0 */ + " str %1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t" + /* Shutdown CPU */ + " str %3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t" + + " b .\n\t" + : + : "r" (mpddrc_base), + "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF), + "r" (at91_shdwc_base), + "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW) + : "r0"); +} + static int at91_poweroff_get_wakeup_mode(struct device_node *np) { const char *pm; @@ -124,6 +151,8 @@ static void at91_poweroff_dt_set_wakeup_mode(struct platform_device *pdev) static int __init at91_poweroff_probe(struct platform_device *pdev) { struct resource *res; + struct device_node *np; + u32 ddr_type; int ret; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -150,12 +179,30 @@ static int __init at91_poweroff_probe(struct platform_device *pdev) pm_power_off = at91_poweroff; + np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc"); + if (!np) + return 0; + + mpddrc_base = of_iomap(np, 0); + of_node_put(np); + + if (!mpddrc_base) + return 0; + + ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD; + if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) || + (ddr_type == AT91_DDRSDRC_MD_LPDDR3)) + pm_power_off = at91_lpddr_poweroff; + else + iounmap(mpddrc_base); + return 0; } static int __exit at91_poweroff_remove(struct platform_device *pdev) { - if (pm_power_off == at91_poweroff) + if (pm_power_off == at91_poweroff || + pm_power_off == at91_lpddr_poweroff) pm_power_off = NULL; clk_disable_unprepare(sclk); @@ -163,6 +210,11 @@ static int __exit at91_poweroff_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id at91_ramc_of_match[] = { + { .compatible = "atmel,sama5d3-ddramc", }, + { /* sentinel */ } +}; + static const struct of_device_id at91_poweroff_of_match[] = { { .compatible = "atmel,at91sam9260-shdwc", }, { .compatible = "atmel,at91sam9rl-shdwc", }, diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c index 117fccf7934a..01a6a83f625d 100644 --- a/drivers/pwm/pwm-pca9685.c +++ b/drivers/pwm/pwm-pca9685.c @@ -65,7 +65,6 @@ #define PCA9685_MAXCHAN 0x10 #define LED_FULL (1 << 4) -#define MODE1_RESTART (1 << 7) #define MODE1_SLEEP (1 << 4) #define MODE2_INVRT (1 << 4) #define MODE2_OUTDRV (1 << 2) @@ -117,16 +116,6 @@ static int pca9685_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, udelay(500); pca->period_ns = period_ns; - - /* - * If the duty cycle did not change, restart PWM with - * the same duty cycle to period ratio and return. - */ - if (duty_ns == pca->duty_ns) { - regmap_update_bits(pca->regmap, PCA9685_MODE1, - MODE1_RESTART, 0x1); - return 0; - } } else { dev_err(chip->dev, "prescaler not set: period out of bounds!\n"); diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index f289fe06194f..e367bf078048 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -313,6 +313,14 @@ config REGULATOR_LP8755 chip contains six step-down DC/DC converters which can support 9 mode multiphase configuration. +config REGULATOR_LP87565 + tristate "TI LP87565 Power regulators" + depends on MFD_TI_LP87565 && OF + help + This driver supports LP87565 voltage regulator chips. LP87565 + provides four step-down converters. It supports software based + voltage control for different voltage domains + config REGULATOR_LP8788 tristate "TI LP8788 Power Regulators" depends on MFD_LP8788 diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index 874b242b227f..eb439bcbf4af 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -40,6 +40,7 @@ obj-$(CONFIG_REGULATOR_LP3971) += lp3971.o obj-$(CONFIG_REGULATOR_LP3972) += lp3972.o obj-$(CONFIG_REGULATOR_LP872X) += lp872x.o obj-$(CONFIG_REGULATOR_LP873X) += lp873x-regulator.o +obj-$(CONFIG_REGULATOR_LP87565) += lp87565-regulator.o obj-$(CONFIG_REGULATOR_LP8788) += lp8788-buck.o obj-$(CONFIG_REGULATOR_LP8788) += lp8788-ldo.o obj-$(CONFIG_REGULATOR_LP8755) += lp8755.o diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 195f13742201..39561f461208 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1517,6 +1517,7 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) ret = regulator_enable(rdev->supply); if (ret < 0) { _regulator_put(rdev->supply); + rdev->supply = NULL; return ret; } } @@ -4271,12 +4272,13 @@ static void regulator_summary_show_subtree(struct seq_file *s, seq_puts(s, "\n"); list_for_each_entry(consumer, &rdev->consumer_list, list) { - if (consumer->dev->class == ®ulator_class) + if (consumer->dev && consumer->dev->class == ®ulator_class) continue; seq_printf(s, "%*s%-*s ", (level + 1) * 3 + 1, "", - 30 - (level + 1) * 3, dev_name(consumer->dev)); + 30 - (level + 1) * 3, + consumer->dev ? dev_name(consumer->dev) : "deviceless"); switch (rdev->desc->type) { case REGULATOR_VOLTAGE: diff --git a/drivers/regulator/lp87565-regulator.c b/drivers/regulator/lp87565-regulator.c new file mode 100644 index 000000000000..04a76ec9bad8 --- /dev/null +++ b/drivers/regulator/lp87565-regulator.c @@ -0,0 +1,236 @@ +/* + * Regulator driver for LP87565 PMIC + * + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation version 2. + */ + +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> + +#include <linux/mfd/lp87565.h> + +#define LP87565_REGULATOR(_name, _id, _of, _ops, _n, _vr, _vm, _er, _em, \ + _delay, _lr, _cr) \ + [_id] = { \ + .desc = { \ + .name = _name, \ + .supply_name = _of "-in", \ + .id = _id, \ + .of_match = of_match_ptr(_of), \ + .regulators_node = of_match_ptr("regulators"),\ + .ops = &_ops, \ + .n_voltages = _n, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .vsel_reg = _vr, \ + .vsel_mask = _vm, \ + .enable_reg = _er, \ + .enable_mask = _em, \ + .ramp_delay = _delay, \ + .linear_ranges = _lr, \ + .n_linear_ranges = ARRAY_SIZE(_lr), \ + }, \ + .ctrl2_reg = _cr, \ + } + +struct lp87565_regulator { + struct regulator_desc desc; + unsigned int ctrl2_reg; +}; + +static const struct lp87565_regulator regulators[]; + +static const struct regulator_linear_range buck0_1_2_3_ranges[] = { + REGULATOR_LINEAR_RANGE(600000, 0xA, 0x17, 10000), + REGULATOR_LINEAR_RANGE(735000, 0x18, 0x9d, 5000), + REGULATOR_LINEAR_RANGE(1420000, 0x9e, 0xff, 20000), +}; + +static unsigned int lp87565_buck_ramp_delay[] = { + 30000, 15000, 10000, 7500, 3800, 1900, 940, 470 +}; + +/* LP87565 BUCK current limit */ +static const unsigned int lp87565_buck_uA[] = { + 1500000, 2000000, 2500000, 3000000, 3500000, 4000000, 4500000, 5000000, +}; + +static int lp87565_buck_set_ramp_delay(struct regulator_dev *rdev, + int ramp_delay) +{ + int id = rdev_get_id(rdev); + struct lp87565 *lp87565 = rdev_get_drvdata(rdev); + unsigned int reg; + int ret; + + if (ramp_delay <= 470) + reg = 7; + else if (ramp_delay <= 940) + reg = 6; + else if (ramp_delay <= 1900) + reg = 5; + else if (ramp_delay <= 3800) + reg = 4; + else if (ramp_delay <= 7500) + reg = 3; + else if (ramp_delay <= 10000) + reg = 2; + else if (ramp_delay <= 15000) + reg = 1; + else + reg = 0; + + ret = regmap_update_bits(lp87565->regmap, regulators[id].ctrl2_reg, + LP87565_BUCK_CTRL_2_SLEW_RATE, + reg << __ffs(LP87565_BUCK_CTRL_2_SLEW_RATE)); + if (ret) { + dev_err(lp87565->dev, "SLEW RATE write failed: %d\n", ret); + return ret; + } + + rdev->constraints->ramp_delay = lp87565_buck_ramp_delay[reg]; + + return 0; +} + +static int lp87565_buck_set_current_limit(struct regulator_dev *rdev, + int min_uA, int max_uA) +{ + int id = rdev_get_id(rdev); + struct lp87565 *lp87565 = rdev_get_drvdata(rdev); + int i; + + for (i = ARRAY_SIZE(lp87565_buck_uA) - 1; i >= 0; i--) { + if (lp87565_buck_uA[i] >= min_uA && + lp87565_buck_uA[i] <= max_uA) + return regmap_update_bits(lp87565->regmap, + regulators[id].ctrl2_reg, + LP87565_BUCK_CTRL_2_ILIM, + i << __ffs(LP87565_BUCK_CTRL_2_ILIM)); + } + + return -EINVAL; +} + +static int lp87565_buck_get_current_limit(struct regulator_dev *rdev) +{ + int id = rdev_get_id(rdev); + struct lp87565 *lp87565 = rdev_get_drvdata(rdev); + int ret; + unsigned int val; + + ret = regmap_read(lp87565->regmap, regulators[id].ctrl2_reg, &val); + if (ret) + return ret; + + val = (val & LP87565_BUCK_CTRL_2_ILIM) >> + __ffs(LP87565_BUCK_CTRL_2_ILIM); + + return (val < ARRAY_SIZE(lp87565_buck_uA)) ? + lp87565_buck_uA[val] : -EINVAL; +} + +/* Operations permitted on BUCK0, BUCK1 */ +static struct regulator_ops lp87565_buck_ops = { + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear_range, + .map_voltage = regulator_map_voltage_linear_range, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .set_ramp_delay = lp87565_buck_set_ramp_delay, + .set_current_limit = lp87565_buck_set_current_limit, + .get_current_limit = lp87565_buck_get_current_limit, +}; + +static const struct lp87565_regulator regulators[] = { + LP87565_REGULATOR("BUCK0", LP87565_BUCK_0, "buck0", lp87565_buck_ops, + 256, LP87565_REG_BUCK0_VOUT, LP87565_BUCK_VSET, + LP87565_REG_BUCK0_CTRL_1, + LP87565_BUCK_CTRL_1_EN, 3800, + buck0_1_2_3_ranges, LP87565_REG_BUCK0_CTRL_2), + LP87565_REGULATOR("BUCK1", LP87565_BUCK_1, "buck1", lp87565_buck_ops, + 256, LP87565_REG_BUCK1_VOUT, LP87565_BUCK_VSET, + LP87565_REG_BUCK1_CTRL_1, + LP87565_BUCK_CTRL_1_EN, 3800, + buck0_1_2_3_ranges, LP87565_REG_BUCK1_CTRL_2), + LP87565_REGULATOR("BUCK2", LP87565_BUCK_2, "buck2", lp87565_buck_ops, + 256, LP87565_REG_BUCK2_VOUT, LP87565_BUCK_VSET, + LP87565_REG_BUCK2_CTRL_1, + LP87565_BUCK_CTRL_1_EN, 3800, + buck0_1_2_3_ranges, LP87565_REG_BUCK2_CTRL_2), + LP87565_REGULATOR("BUCK3", LP87565_BUCK_3, "buck3", lp87565_buck_ops, + 256, LP87565_REG_BUCK3_VOUT, LP87565_BUCK_VSET, + LP87565_REG_BUCK3_CTRL_1, + LP87565_BUCK_CTRL_1_EN, 3800, + buck0_1_2_3_ranges, LP87565_REG_BUCK3_CTRL_2), + LP87565_REGULATOR("BUCK10", LP87565_BUCK_10, "buck10", lp87565_buck_ops, + 256, LP87565_REG_BUCK0_VOUT, LP87565_BUCK_VSET, + LP87565_REG_BUCK0_CTRL_1, + LP87565_BUCK_CTRL_1_EN, 3800, + buck0_1_2_3_ranges, LP87565_REG_BUCK0_CTRL_2), + LP87565_REGULATOR("BUCK23", LP87565_BUCK_23, "buck23", lp87565_buck_ops, + 256, LP87565_REG_BUCK2_VOUT, LP87565_BUCK_VSET, + LP87565_REG_BUCK2_CTRL_1, + LP87565_BUCK_CTRL_1_EN, 3800, + buck0_1_2_3_ranges, LP87565_REG_BUCK2_CTRL_2), +}; + +static int lp87565_regulator_probe(struct platform_device *pdev) +{ + struct lp87565 *lp87565 = dev_get_drvdata(pdev->dev.parent); + struct regulator_config config = { }; + struct regulator_dev *rdev; + int i, min_idx = LP87565_BUCK_1, max_idx = LP87565_BUCK_3; + + platform_set_drvdata(pdev, lp87565); + + config.dev = &pdev->dev; + config.dev->of_node = lp87565->dev->of_node; + config.driver_data = lp87565; + config.regmap = lp87565->regmap; + + if (lp87565->dev_type == LP87565_DEVICE_TYPE_LP87565_Q1) { + min_idx = LP87565_BUCK_10; + max_idx = LP87565_BUCK_23; + } + + for (i = min_idx; i <= max_idx; i++) { + rdev = devm_regulator_register(&pdev->dev, ®ulators[i].desc, + &config); + if (IS_ERR(rdev)) { + dev_err(lp87565->dev, "failed to register %s regulator\n", + pdev->name); + return PTR_ERR(rdev); + } + } + + return 0; +} + +static const struct platform_device_id lp87565_regulator_id_table[] = { + { "lp87565-regulator", }, + { "lp87565-q1-regulator", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, lp87565_regulator_id_table); + +static struct platform_driver lp87565_regulator_driver = { + .driver = { + .name = "lp87565-pmic", + }, + .probe = lp87565_regulator_probe, + .id_table = lp87565_regulator_id_table, +}; +module_platform_driver(lp87565_regulator_driver); + +MODULE_AUTHOR("J Keerthy <j-keerthy@ti.com>"); +MODULE_DESCRIPTION("LP87565 voltage regulator driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index 854e1e2b1c4f..4c91bb54a21f 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -264,6 +264,13 @@ static struct palmas_regs_info tps65917_regs_info[] = { .sleep_id = TPS65917_EXTERNAL_REQSTR_ID_SMPS5, }, { + .name = "SMPS12", + .sname = "smps1-in", + .vsel_addr = TPS65917_SMPS1_VOLTAGE, + .ctrl_addr = TPS65917_SMPS1_CTRL, + .sleep_id = TPS65917_EXTERNAL_REQSTR_ID_SMPS12, + }, + { .name = "LDO1", .sname = "ldo1-in", .vsel_addr = TPS65917_LDO1_VOLTAGE, @@ -367,6 +374,7 @@ static struct palmas_sleep_requestor_info tps65917_sleep_req_info[] = { EXTERNAL_REQUESTOR_TPS65917(SMPS3, 1, 2), EXTERNAL_REQUESTOR_TPS65917(SMPS4, 1, 3), EXTERNAL_REQUESTOR_TPS65917(SMPS5, 1, 4), + EXTERNAL_REQUESTOR_TPS65917(SMPS12, 1, 5), EXTERNAL_REQUESTOR_TPS65917(LDO1, 2, 0), EXTERNAL_REQUESTOR_TPS65917(LDO2, 2, 1), EXTERNAL_REQUESTOR_TPS65917(LDO3, 2, 2), @@ -1324,7 +1332,8 @@ static int tps65917_smps_registration(struct palmas_pmic *pmic, */ desc = &pmic->desc[id]; desc->n_linear_ranges = 3; - if ((id == TPS65917_REG_SMPS2) && pmic->smps12) + if ((id == TPS65917_REG_SMPS2 || id == TPS65917_REG_SMPS1) && + pmic->smps12) continue; /* Initialise sleep/init values from platform data */ @@ -1446,6 +1455,7 @@ static struct of_regulator_match tps65917_matches[] = { { .name = "smps3", }, { .name = "smps4", }, { .name = "smps5", }, + { .name = "smps12",}, { .name = "ldo1", }, { .name = "ldo2", }, { .name = "ldo3", }, @@ -1474,7 +1484,7 @@ static struct palmas_pmic_driver_data palmas_ddata = { static struct palmas_pmic_driver_data tps65917_ddata = { .smps_start = TPS65917_REG_SMPS1, - .smps_end = TPS65917_REG_SMPS5, + .smps_end = TPS65917_REG_SMPS12, .ldo_begin = TPS65917_REG_LDO1, .ldo_end = TPS65917_REG_LDO5, .max_reg = TPS65917_NUM_REGS, @@ -1662,8 +1672,10 @@ static int palmas_regulators_probe(struct platform_device *pdev) if (ret) return ret; - if (reg & PALMAS_SMPS_CTRL_SMPS12_SMPS123_EN) + if (reg & PALMAS_SMPS_CTRL_SMPS12_SMPS123_EN) { pmic->smps123 = 1; + pmic->smps12 = 1; + } if (reg & PALMAS_SMPS_CTRL_SMPS45_SMPS457_EN) pmic->smps457 = 1; diff --git a/drivers/regulator/tps65023-regulator.c b/drivers/regulator/tps65023-regulator.c index d2c3d7cc35f5..5ca6d2130593 100644 --- a/drivers/regulator/tps65023-regulator.c +++ b/drivers/regulator/tps65023-regulator.c @@ -311,8 +311,7 @@ static int tps_65023_probe(struct i2c_client *client, /* Enable setting output voltage by I2C */ regmap_update_bits(tps->regmap, TPS65023_REG_CON_CTRL2, - TPS65023_REG_CTRL2_CORE_ADJ, - TPS65023_REG_CTRL2_CORE_ADJ); + TPS65023_REG_CTRL2_CORE_ADJ, 0); return 0; } diff --git a/drivers/remoteproc/omap_remoteproc.c b/drivers/remoteproc/omap_remoteproc.c index 51db2441b506..5d6f17bdfb2f 100644 --- a/drivers/remoteproc/omap_remoteproc.c +++ b/drivers/remoteproc/omap_remoteproc.c @@ -397,18 +397,27 @@ static void omap_rproc_kick(struct rproc *rproc, int vqid) * * Set boot address for a supported DSP remote processor. */ -static void omap_rproc_write_dsp_boot_addr(struct rproc *rproc) +static int omap_rproc_write_dsp_boot_addr(struct rproc *rproc) { + struct device *dev = rproc->dev.parent; struct omap_rproc *oproc = rproc->priv; struct omap_rproc_boot_data *bdata = oproc->boot_data; u32 offset = bdata->boot_reg; unsigned int value = rproc->bootaddr; unsigned int mask = ~(SZ_1K - 1); + if (value & (SZ_1K - 1)) { + dev_err(dev, "invalid boot address 0x%x, must be aligned on a 1KB boundary\n", + value); + return -EINVAL; + } + value >>= bdata->boot_reg_shift; mask >>= bdata->boot_reg_shift; regmap_update_bits(bdata->syscon, offset, mask, value); + + return 0; } /* @@ -431,8 +440,11 @@ static int omap_rproc_start(struct rproc *rproc) * We set boot address irrespective of the value of the late attach flag * as boot address takes effect only on a deassert of remoteproc reset. */ - if (oproc->boot_data) - omap_rproc_write_dsp_boot_addr(rproc); + if (oproc->boot_data) { + ret = omap_rproc_write_dsp_boot_addr(rproc); + if (ret) + return ret; + } client->dev = dev; client->tx_done = NULL; @@ -715,8 +727,13 @@ static int _omap_rproc_resume(struct rproc *rproc, bool auto_suspend) } /* boot address could be lost after suspend, so restore it */ - if (oproc->boot_data) - omap_rproc_write_dsp_boot_addr(rproc); + if (oproc->boot_data) { + ret = omap_rproc_write_dsp_boot_addr(rproc); + if (ret) { + dev_err(dev, "boot address restore failed %d\n", ret); + goto suspend_iommu; + } + } ret = omap_rproc_enable_timers(pdev, false); if (ret) { @@ -836,6 +853,11 @@ static int omap_rproc_runtime_suspend(struct device *dev) struct omap_rproc *oproc = rproc->priv; int ret; + if (rproc->state == RPROC_CRASHED) { + dev_dbg(dev, "rproc cannot be runtime suspended when crashed!\n"); + return -EBUSY; + } + if (WARN_ON(rproc->state != RPROC_RUNNING)) { dev_err(dev, "rproc cannot be runtime suspended when not running!\n"); return -EBUSY; @@ -967,8 +989,8 @@ static int omap_rproc_get_autosuspend_delay(struct platform_device *pdev) data = match->data; - if (!of_device_is_compatible(np, "ti,dra7-rproc-dsp") && - !of_device_is_compatible(np, "ti,dra7-rproc-ipu")) { + if (!of_device_is_compatible(np, "ti,dra7-dsp") && + !of_device_is_compatible(np, "ti,dra7-ipu")) { delay = data->autosuspend_delay; goto out; } @@ -1052,12 +1074,15 @@ static int omap_rproc_get_boot_data(struct platform_device *pdev, static int omap_rproc_of_get_internal_memories(struct platform_device *pdev, struct rproc *rproc) { - static const char * const mem_names[] = {"l2ram"}; + static const char * const ipu_mem_names[] = {"l2ram"}; + static const char * const dra7_dsp_mem_names[] = {"l2ram", "l1pram", + "l1dram"}; struct device_node *np = pdev->dev.of_node; struct omap_rproc *oproc = rproc->priv; struct device *dev = &pdev->dev; + const char * const *mem_names; struct resource *res; - int num_mems = 0; + int num_mems; const __be32 *addrp; u32 l4_offset = 0; u64 size; @@ -1068,8 +1093,15 @@ static int omap_rproc_of_get_internal_memories(struct platform_device *pdev, of_device_is_compatible(np, "ti,omap5-dsp")) return 0; - /* XXX: add support for DRA7 DSP L1 RAMs if needed */ - num_mems = ARRAY_SIZE(mem_names); + /* DRA7 DSPs have two additional SRAMs at L1 level */ + if (of_device_is_compatible(np, "ti,dra7-dsp")) { + mem_names = dra7_dsp_mem_names; + num_mems = ARRAY_SIZE(dra7_dsp_mem_names); + } else { + mem_names = ipu_mem_names; + num_mems = ARRAY_SIZE(ipu_mem_names); + } + oproc->mem = devm_kcalloc(dev, num_mems, sizeof(*oproc->mem), GFP_KERNEL); if (!oproc->mem) @@ -1218,7 +1250,9 @@ static int omap_rproc_probe(struct platform_device *pdev) oproc->num_wd_timers); oproc->num_wd_timers = 0; } else { - if (!timer_ops || !timer_ops->get_timer_irq || + if (!timer_ops || !timer_ops->request_timer || + !timer_ops->release_timer || !timer_ops->start_timer || + !timer_ops->stop_timer || !timer_ops->get_timer_irq || !timer_ops->ack_timer_irq) { dev_err(&pdev->dev, "device does not have required watchdog timer ops\n"); ret = -ENODEV; @@ -1242,19 +1276,26 @@ static int omap_rproc_probe(struct platform_device *pdev) init_completion(&oproc->pm_comp); oproc->autosuspend_delay = omap_rproc_get_autosuspend_delay(pdev); - if (oproc->autosuspend_delay < 0) + if (oproc->autosuspend_delay < 0) { + ret = oproc->autosuspend_delay; goto free_rproc; + } ret = of_property_read_u32(np, "ti,rproc-standby-info", &standby_addr); - if (ret || !standby_addr) + if (ret || !standby_addr) { + ret = !standby_addr ? -EINVAL : ret; goto free_rproc; + } oproc->standby_addr = devm_ioremap(&pdev->dev, standby_addr, sizeof(u32)); - if (!oproc->standby_addr) + if (!oproc->standby_addr) { + ret = -ENOMEM; goto free_rproc; + } - if (of_reserved_mem_device_init(&pdev->dev)) { + ret = of_reserved_mem_device_init(&pdev->dev); + if (ret) { dev_err(&pdev->dev, "device does not have specific CMA pool\n"); goto free_rproc; } diff --git a/drivers/remoteproc/pruss.c b/drivers/remoteproc/pruss.c index 7d9b3ebb627e..83b1127901d4 100644 --- a/drivers/remoteproc/pruss.c +++ b/drivers/remoteproc/pruss.c @@ -71,7 +71,10 @@ static LIST_HEAD(pruss_list); * This function increments the pruss device's refcount, so always * use pruss_put() to decrement it back once pruss isn't needed anymore. * - * Returns the pruss handle on success, and NULL on failure. + * Returns the pruss handle on success. ERR_PTR on failure e.g. + * -ENOENT if missing "pruss" property or if pruss device is not enabled in dt + * -EINVAL if invalid parameter + * -EPROBE_DEFER if the pruss device is not yet available */ struct pruss *pruss_get(struct device *dev) { @@ -79,11 +82,12 @@ struct pruss *pruss_get(struct device *dev) struct device_node *np; if (!dev) - return NULL; + return ERR_PTR(-EINVAL); np = of_parse_phandle(dev->of_node, "pruss", 0); - if (!np) - return NULL; + if (!np || !of_device_is_available(np)) + /* pruss is never going to show up */ + return ERR_PTR(-ENOENT); mutex_lock(&pruss_list_mutex); list_for_each_entry(p, &pruss_list, node) { @@ -97,7 +101,7 @@ struct pruss *pruss_get(struct device *dev) mutex_unlock(&pruss_list_mutex); of_node_put(np); - return pruss; + return pruss ? pruss : ERR_PTR(-EPROBE_DEFER); } EXPORT_SYMBOL_GPL(pruss_get); diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 98af87ac31bc..361a6d8aa297 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -409,8 +409,11 @@ static int rpmsg_dev_probe(struct device *dev) nsm.flags = RPMSG_NS_CREATE; err = rpmsg_sendto(rpdev, &nsm, sizeof(nsm), RPMSG_NS_ADDR); - if (err) + if (err) { dev_err(dev, "failed to announce service %d\n", err); + rpdrv->remove(rpdev); + rpmsg_destroy_ept(ept); + } } out: @@ -571,6 +574,13 @@ struct rpmsg_channel *__rpmsg_create_channel(struct virtproc_info *vrp, return NULL; } + if (!rpdev->ept) { + dev_err(dev, "failed to create ept\n"); + device_unregister(&rpdev->dev); + put_device(&rpdev->dev); + return NULL; + } + return rpdev; } diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index c07ffa5a0501..8d85cf385e09 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -748,9 +748,23 @@ EXPORT_SYMBOL_GPL(rtc_irq_set_freq); */ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer) { + struct timerqueue_node *next = timerqueue_getnext(&rtc->timerqueue); + struct rtc_time tm; + ktime_t now; + timer->enabled = 1; + __rtc_read_time(rtc, &tm); + now = rtc_tm_to_ktime(tm); + + /* Skip over expired timers */ + while (next) { + if (next->expires.tv64 >= now.tv64) + break; + next = timerqueue_iterate_next(next); + } + timerqueue_add(&rtc->timerqueue, &timer->node); - if (&timer->node == timerqueue_getnext(&rtc->timerqueue)) { + if (!next) { struct rtc_wkalrm alarm; int err; alarm.time = rtc_ktime_to_tm(timer->node.expires); diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c index f40afdd0e5f5..00662dd28d66 100644 --- a/drivers/rtc/rtc-s35390a.c +++ b/drivers/rtc/rtc-s35390a.c @@ -15,6 +15,7 @@ #include <linux/bitrev.h> #include <linux/bcd.h> #include <linux/slab.h> +#include <linux/delay.h> #define S35390A_CMD_STATUS1 0 #define S35390A_CMD_STATUS2 1 @@ -34,10 +35,14 @@ #define S35390A_ALRM_BYTE_HOURS 1 #define S35390A_ALRM_BYTE_MINS 2 +/* flags for STATUS1 */ #define S35390A_FLAG_POC 0x01 #define S35390A_FLAG_BLD 0x02 +#define S35390A_FLAG_INT2 0x04 #define S35390A_FLAG_24H 0x40 #define S35390A_FLAG_RESET 0x80 + +/* flag for STATUS2 */ #define S35390A_FLAG_TEST 0x01 #define S35390A_INT2_MODE_MASK 0xF0 @@ -94,19 +99,63 @@ static int s35390a_get_reg(struct s35390a *s35390a, int reg, char *buf, int len) return 0; } -static int s35390a_reset(struct s35390a *s35390a) +/* + * Returns <0 on error, 0 if rtc is setup fine and 1 if the chip was reset. + * To keep the information if an irq is pending, pass the value read from + * STATUS1 to the caller. + */ +static int s35390a_reset(struct s35390a *s35390a, char *status1) { - char buf[1]; - - if (s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, buf, sizeof(buf)) < 0) - return -EIO; - - if (!(buf[0] & (S35390A_FLAG_POC | S35390A_FLAG_BLD))) + char buf; + int ret; + unsigned initcount = 0; + + ret = s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, status1, 1); + if (ret < 0) + return ret; + + if (*status1 & S35390A_FLAG_POC) + /* + * Do not communicate for 0.5 seconds since the power-on + * detection circuit is in operation. + */ + msleep(500); + else if (!(*status1 & S35390A_FLAG_BLD)) + /* + * If both POC and BLD are unset everything is fine. + */ return 0; - buf[0] |= (S35390A_FLAG_RESET | S35390A_FLAG_24H); - buf[0] &= 0xf0; - return s35390a_set_reg(s35390a, S35390A_CMD_STATUS1, buf, sizeof(buf)); + /* + * At least one of POC and BLD are set, so reinitialise chip. Keeping + * this information in the hardware to know later that the time isn't + * valid is unfortunately not possible because POC and BLD are cleared + * on read. So the reset is best done now. + * + * The 24H bit is kept over reset, so set it already here. + */ +initialize: + *status1 = S35390A_FLAG_24H; + buf = S35390A_FLAG_RESET | S35390A_FLAG_24H; + ret = s35390a_set_reg(s35390a, S35390A_CMD_STATUS1, &buf, 1); + + if (ret < 0) + return ret; + + ret = s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, &buf, 1); + if (ret < 0) + return ret; + + if (buf & (S35390A_FLAG_POC | S35390A_FLAG_BLD)) { + /* Try up to five times to reset the chip */ + if (initcount < 5) { + ++initcount; + goto initialize; + } else + return -EIO; + } + + return 1; } static int s35390a_disable_test_mode(struct s35390a *s35390a) @@ -242,6 +291,8 @@ static int s35390a_set_alarm(struct i2c_client *client, struct rtc_wkalrm *alm) if (alm->time.tm_wday != -1) buf[S35390A_ALRM_BYTE_WDAY] = bin2bcd(alm->time.tm_wday) | 0x80; + else + buf[S35390A_ALRM_BYTE_WDAY] = 0; buf[S35390A_ALRM_BYTE_HOURS] = s35390a_hr2reg(s35390a, alm->time.tm_hour) | 0x80; @@ -265,27 +316,61 @@ static int s35390a_read_alarm(struct i2c_client *client, struct rtc_wkalrm *alm) char buf[3], sts; int i, err; + /* + * initialize all members to -1 to signal the core that they are not + * defined by the hardware. + */ + alm->time.tm_sec = -1; + alm->time.tm_min = -1; + alm->time.tm_hour = -1; + alm->time.tm_mday = -1; + alm->time.tm_mon = -1; + alm->time.tm_year = -1; + alm->time.tm_wday = -1; + alm->time.tm_yday = -1; + alm->time.tm_isdst = -1; + err = s35390a_get_reg(s35390a, S35390A_CMD_STATUS2, &sts, sizeof(sts)); if (err < 0) return err; - if (bitrev8(sts) != S35390A_INT2_MODE_ALARM) - return -EINVAL; + if ((bitrev8(sts) & S35390A_INT2_MODE_MASK) != S35390A_INT2_MODE_ALARM) { + /* + * When the alarm isn't enabled, the register to configure + * the alarm time isn't accessible. + */ + alm->enabled = 0; + return 0; + } else { + alm->enabled = 1; + } err = s35390a_get_reg(s35390a, S35390A_CMD_INT2_REG1, buf, sizeof(buf)); if (err < 0) return err; /* This chip returns the bits of each byte in reverse order */ - for (i = 0; i < 3; ++i) { + for (i = 0; i < 3; ++i) buf[i] = bitrev8(buf[i]); - buf[i] &= ~0x80; - } - alm->time.tm_wday = bcd2bin(buf[S35390A_ALRM_BYTE_WDAY]); - alm->time.tm_hour = s35390a_reg2hr(s35390a, - buf[S35390A_ALRM_BYTE_HOURS]); - alm->time.tm_min = bcd2bin(buf[S35390A_ALRM_BYTE_MINS]); + /* + * B0 of the three matching registers is an enable flag. Iff it is set + * the configured value is used for matching. + */ + if (buf[S35390A_ALRM_BYTE_WDAY] & 0x80) + alm->time.tm_wday = + bcd2bin(buf[S35390A_ALRM_BYTE_WDAY] & ~0x80); + + if (buf[S35390A_ALRM_BYTE_HOURS] & 0x80) + alm->time.tm_hour = + s35390a_reg2hr(s35390a, + buf[S35390A_ALRM_BYTE_HOURS] & ~0x80); + + if (buf[S35390A_ALRM_BYTE_MINS] & 0x80) + alm->time.tm_min = bcd2bin(buf[S35390A_ALRM_BYTE_MINS] & ~0x80); + + /* alarm triggers always at s=0 */ + alm->time.tm_sec = 0; dev_dbg(&client->dev, "%s: alm is mins=%d, hours=%d, wday=%d\n", __func__, alm->time.tm_min, alm->time.tm_hour, @@ -327,11 +412,11 @@ static struct i2c_driver s35390a_driver; static int s35390a_probe(struct i2c_client *client, const struct i2c_device_id *id) { - int err; + int err, err_reset; unsigned int i; struct s35390a *s35390a; struct rtc_time tm; - char buf[1]; + char buf, status1; if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { err = -ENODEV; @@ -360,29 +445,35 @@ static int s35390a_probe(struct i2c_client *client, } } - err = s35390a_reset(s35390a); - if (err < 0) { + err_reset = s35390a_reset(s35390a, &status1); + if (err_reset < 0) { + err = err_reset; dev_err(&client->dev, "error resetting chip\n"); goto exit_dummy; } - err = s35390a_disable_test_mode(s35390a); - if (err < 0) { - dev_err(&client->dev, "error disabling test mode\n"); - goto exit_dummy; - } - - err = s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, buf, sizeof(buf)); - if (err < 0) { - dev_err(&client->dev, "error checking 12/24 hour mode\n"); - goto exit_dummy; - } - if (buf[0] & S35390A_FLAG_24H) + if (status1 & S35390A_FLAG_24H) s35390a->twentyfourhour = 1; else s35390a->twentyfourhour = 0; - if (s35390a_get_datetime(client, &tm) < 0) + if (status1 & S35390A_FLAG_INT2) { + /* disable alarm (and maybe test mode) */ + buf = 0; + err = s35390a_set_reg(s35390a, S35390A_CMD_STATUS2, &buf, 1); + if (err < 0) { + dev_err(&client->dev, "error disabling alarm"); + goto exit_dummy; + } + } else { + err = s35390a_disable_test_mode(s35390a); + if (err < 0) { + dev_err(&client->dev, "error disabling test mode\n"); + goto exit_dummy; + } + } + + if (err_reset > 0 || s35390a_get_datetime(client, &tm) < 0) dev_warn(&client->dev, "clock needs to be set\n"); device_set_wakeup_capable(&client->dev, 1); @@ -395,6 +486,10 @@ static int s35390a_probe(struct i2c_client *client, err = PTR_ERR(s35390a->rtc); goto exit_dummy; } + + if (status1 & S35390A_FLAG_INT2) + rtc_update_irq(s35390a->rtc, 1, RTC_AF); + return 0; exit_dummy: diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index c169a2cd4727..e29cc9fca0bf 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -37,9 +37,11 @@ /* Control register */ #define SUN6I_LOSC_CTRL 0x0000 +#define SUN6I_LOSC_CTRL_KEY (0x16aa << 16) #define SUN6I_LOSC_CTRL_ALM_DHMS_ACC BIT(9) #define SUN6I_LOSC_CTRL_RTC_HMS_ACC BIT(8) #define SUN6I_LOSC_CTRL_RTC_YMD_ACC BIT(7) +#define SUN6I_LOSC_CTRL_EXT_OSC BIT(0) #define SUN6I_LOSC_CTRL_ACC_MASK GENMASK(9, 7) /* RTC */ @@ -114,13 +116,17 @@ struct sun6i_rtc_dev { void __iomem *base; int irq; unsigned long alarm; + + spinlock_t lock; }; static irqreturn_t sun6i_rtc_alarmirq(int irq, void *id) { struct sun6i_rtc_dev *chip = (struct sun6i_rtc_dev *) id; + irqreturn_t ret = IRQ_NONE; u32 val; + spin_lock(&chip->lock); val = readl(chip->base + SUN6I_ALRM_IRQ_STA); if (val & SUN6I_ALRM_IRQ_STA_CNT_IRQ_PEND) { @@ -129,10 +135,11 @@ static irqreturn_t sun6i_rtc_alarmirq(int irq, void *id) rtc_update_irq(chip->rtc, 1, RTC_AF | RTC_IRQF); - return IRQ_HANDLED; + ret = IRQ_HANDLED; } + spin_unlock(&chip->lock); - return IRQ_NONE; + return ret; } static void sun6i_rtc_setaie(int to, struct sun6i_rtc_dev *chip) @@ -140,6 +147,7 @@ static void sun6i_rtc_setaie(int to, struct sun6i_rtc_dev *chip) u32 alrm_val = 0; u32 alrm_irq_val = 0; u32 alrm_wake_val = 0; + unsigned long flags; if (to) { alrm_val = SUN6I_ALRM_EN_CNT_EN; @@ -150,9 +158,11 @@ static void sun6i_rtc_setaie(int to, struct sun6i_rtc_dev *chip) chip->base + SUN6I_ALRM_IRQ_STA); } + spin_lock_irqsave(&chip->lock, flags); writel(alrm_val, chip->base + SUN6I_ALRM_EN); writel(alrm_irq_val, chip->base + SUN6I_ALRM_IRQ_EN); writel(alrm_wake_val, chip->base + SUN6I_ALARM_CONFIG); + spin_unlock_irqrestore(&chip->lock, flags); } static int sun6i_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) @@ -191,11 +201,15 @@ static int sun6i_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) static int sun6i_rtc_getalarm(struct device *dev, struct rtc_wkalrm *wkalrm) { struct sun6i_rtc_dev *chip = dev_get_drvdata(dev); + unsigned long flags; u32 alrm_st; u32 alrm_en; + spin_lock_irqsave(&chip->lock, flags); alrm_en = readl(chip->base + SUN6I_ALRM_IRQ_EN); alrm_st = readl(chip->base + SUN6I_ALRM_IRQ_STA); + spin_unlock_irqrestore(&chip->lock, flags); + wkalrm->enabled = !!(alrm_en & SUN6I_ALRM_EN_CNT_EN); wkalrm->pending = !!(alrm_st & SUN6I_ALRM_EN_CNT_EN); rtc_time_to_tm(chip->alarm, &wkalrm->time); @@ -356,6 +370,7 @@ static int sun6i_rtc_probe(struct platform_device *pdev) chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL); if (!chip) return -ENOMEM; + spin_lock_init(&chip->lock); platform_set_drvdata(pdev, chip); chip->dev = &pdev->dev; @@ -404,6 +419,10 @@ static int sun6i_rtc_probe(struct platform_device *pdev) /* disable alarm wakeup */ writel(0, chip->base + SUN6I_ALARM_CONFIG); + /* switch to the external, more precise, oscillator */ + writel(SUN6I_LOSC_CTRL_KEY | SUN6I_LOSC_CTRL_EXT_OSC, + chip->base + SUN6I_LOSC_CTRL); + chip->rtc = rtc_device_register("rtc-sun6i", &pdev->dev, &sun6i_rtc_ops, THIS_MODULE); if (IS_ERR(chip->rtc)) { diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c index 60232bd366ef..71216aa68905 100644 --- a/drivers/rtc/rtc-tegra.c +++ b/drivers/rtc/rtc-tegra.c @@ -18,6 +18,7 @@ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ #include <linux/kernel.h> +#include <linux/clk.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> @@ -59,6 +60,7 @@ struct tegra_rtc_info { struct platform_device *pdev; struct rtc_device *rtc_dev; void __iomem *rtc_base; /* NULL if not initialized. */ + struct clk *clk; int tegra_rtc_irq; /* alarm and periodic irq */ spinlock_t tegra_rtc_lock; }; @@ -332,6 +334,14 @@ static int __init tegra_rtc_probe(struct platform_device *pdev) if (info->tegra_rtc_irq <= 0) return -EBUSY; + info->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(info->clk)) + return PTR_ERR(info->clk); + + ret = clk_prepare_enable(info->clk); + if (ret < 0) + return ret; + /* set context info. */ info->pdev = pdev; spin_lock_init(&info->tegra_rtc_lock); @@ -352,7 +362,7 @@ static int __init tegra_rtc_probe(struct platform_device *pdev) ret = PTR_ERR(info->rtc_dev); dev_err(&pdev->dev, "Unable to register device (err=%d).\n", ret); - return ret; + goto disable_clk; } ret = devm_request_irq(&pdev->dev, info->tegra_rtc_irq, @@ -362,12 +372,25 @@ static int __init tegra_rtc_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Unable to request interrupt for device (err=%d).\n", ret); - return ret; + goto disable_clk; } dev_notice(&pdev->dev, "Tegra internal Real Time Clock\n"); return 0; + +disable_clk: + clk_disable_unprepare(info->clk); + return ret; +} + +static int tegra_rtc_remove(struct platform_device *pdev) +{ + struct tegra_rtc_info *info = platform_get_drvdata(pdev); + + clk_disable_unprepare(info->clk); + + return 0; } #ifdef CONFIG_PM_SLEEP @@ -419,6 +442,7 @@ static void tegra_rtc_shutdown(struct platform_device *pdev) MODULE_ALIAS("platform:tegra_rtc"); static struct platform_driver tegra_rtc_driver = { + .remove = tegra_rtc_remove, .shutdown = tegra_rtc_shutdown, .driver = { .name = "tegra_rtc", diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 94a8f4ab57bc..ae1dc37e4068 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -892,7 +892,7 @@ dcssblk_direct_access (struct block_device *bdev, sector_t secnum, dev_info = bdev->bd_disk->private_data; if (!dev_info) return -ENODEV; - dev_sz = dev_info->end - dev_info->start; + dev_sz = dev_info->end - dev_info->start + 1; offset = secnum * 512; addr = (void *) (dev_info->start + offset); *pfn = virt_to_phys(addr) >> PAGE_SHIFT; diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c index 5d06253c2a7a..30e9fbbff051 100644 --- a/drivers/s390/cio/qdio_thinint.c +++ b/drivers/s390/cio/qdio_thinint.c @@ -147,11 +147,11 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq) struct qdio_q *q; int i; - for_each_input_queue(irq, q, i) { - if (!references_shared_dsci(irq) && - has_multiple_inq_on_dsci(irq)) - xchg(q->irq_ptr->dsci, 0); + if (!references_shared_dsci(irq) && + has_multiple_inq_on_dsci(irq)) + xchg(irq->dsci, 0); + for_each_input_queue(irq, q, i) { if (q->u.in.queue_start_poll) { /* skip if polling is enabled or already in work */ if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED, diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 24ec282e15d8..7c3b8d3516e3 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1651,6 +1651,9 @@ static void ap_scan_bus(struct work_struct *unused) ap_dev->queue_depth = queue_depth; ap_dev->raw_hwtype = device_type; ap_dev->device_type = device_type; + /* CEX6 toleration: map to CEX5 */ + if (device_type == AP_DEVICE_TYPE_CEX6) + ap_dev->device_type = AP_DEVICE_TYPE_CEX5; ap_dev->functions = device_functions; spin_lock_init(&ap_dev->lock); INIT_LIST_HEAD(&ap_dev->pendingq); diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 6adcbdf225d1..cc741e948170 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -105,6 +105,7 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr) #define AP_DEVICE_TYPE_CEX3C 9 #define AP_DEVICE_TYPE_CEX4 10 #define AP_DEVICE_TYPE_CEX5 11 +#define AP_DEVICE_TYPE_CEX6 12 /* * Known function facilities diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 1766a20ebcb1..741f3ee81cfe 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -717,6 +717,7 @@ enum qeth_discipline_id { }; struct qeth_discipline { + const struct device_type *devtype; void (*start_poll)(struct ccw_device *, int, unsigned long); qdio_handler_t *input_handler; qdio_handler_t *output_handler; @@ -881,6 +882,9 @@ extern struct qeth_discipline qeth_l2_discipline; extern struct qeth_discipline qeth_l3_discipline; extern const struct attribute_group *qeth_generic_attr_groups[]; extern const struct attribute_group *qeth_osn_attr_groups[]; +extern const struct attribute_group qeth_device_attr_group; +extern const struct attribute_group qeth_device_blkt_group; +extern const struct device_type qeth_generic_devtype; extern struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 31ac53fa5cee..d10bf3da8e5f 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5449,10 +5449,12 @@ void qeth_core_free_discipline(struct qeth_card *card) card->discipline = NULL; } -static const struct device_type qeth_generic_devtype = { +const struct device_type qeth_generic_devtype = { .name = "qeth_generic", .groups = qeth_generic_attr_groups, }; +EXPORT_SYMBOL_GPL(qeth_generic_devtype); + static const struct device_type qeth_osn_devtype = { .name = "qeth_osn", .groups = qeth_osn_attr_groups, @@ -5578,23 +5580,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) goto err_card; } - if (card->info.type == QETH_CARD_TYPE_OSN) - gdev->dev.type = &qeth_osn_devtype; - else - gdev->dev.type = &qeth_generic_devtype; - switch (card->info.type) { case QETH_CARD_TYPE_OSN: case QETH_CARD_TYPE_OSM: rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2); if (rc) goto err_card; + + gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN) + ? card->discipline->devtype + : &qeth_osn_devtype; rc = card->discipline->setup(card->gdev); if (rc) goto err_disc; - case QETH_CARD_TYPE_OSD: - case QETH_CARD_TYPE_OSX: + break; default: + gdev->dev.type = &qeth_generic_devtype; break; } @@ -5650,8 +5651,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev) if (rc) goto err; rc = card->discipline->setup(card->gdev); - if (rc) + if (rc) { + qeth_core_free_discipline(card); goto err; + } } rc = card->discipline->set_online(gdev); err: diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index e6e5b9671bf2..fa844b0ff847 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -409,12 +409,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev, if (card->options.layer2 == newdis) goto out; - else { - card->info.mac_bits = 0; - if (card->discipline) { - card->discipline->remove(card->gdev); - qeth_core_free_discipline(card); - } + if (card->info.type == QETH_CARD_TYPE_OSM) { + /* fixed layer, can't switch */ + rc = -EOPNOTSUPP; + goto out; + } + + card->info.mac_bits = 0; + if (card->discipline) { + card->discipline->remove(card->gdev); + qeth_core_free_discipline(card); } rc = qeth_core_load_discipline(card, newdis); @@ -422,6 +426,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev, goto out; rc = card->discipline->setup(card->gdev); + if (rc) + qeth_core_free_discipline(card); out: mutex_unlock(&card->discipline_mutex); return rc ? rc : count; @@ -699,10 +705,11 @@ static struct attribute *qeth_blkt_device_attrs[] = { &dev_attr_inter_jumbo.attr, NULL, }; -static struct attribute_group qeth_device_blkt_group = { +const struct attribute_group qeth_device_blkt_group = { .name = "blkt", .attrs = qeth_blkt_device_attrs, }; +EXPORT_SYMBOL_GPL(qeth_device_blkt_group); static struct attribute *qeth_device_attrs[] = { &dev_attr_state.attr, @@ -722,9 +729,10 @@ static struct attribute *qeth_device_attrs[] = { &dev_attr_switch_attrs.attr, NULL, }; -static struct attribute_group qeth_device_attr_group = { +const struct attribute_group qeth_device_attr_group = { .attrs = qeth_device_attrs, }; +EXPORT_SYMBOL_GPL(qeth_device_attr_group); const struct attribute_group *qeth_generic_attr_groups[] = { &qeth_device_attr_group, diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h index 0767556404bd..eb87bf97d38a 100644 --- a/drivers/s390/net/qeth_l2.h +++ b/drivers/s390/net/qeth_l2.h @@ -8,6 +8,8 @@ #include "qeth_core.h" +extern const struct attribute_group *qeth_l2_attr_groups[]; + int qeth_l2_create_device_attributes(struct device *); void qeth_l2_remove_device_attributes(struct device *); void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index df036b872b05..bf1e0e39334d 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1027,11 +1027,21 @@ static int qeth_l2_stop(struct net_device *dev) return 0; } +static const struct device_type qeth_l2_devtype = { + .name = "qeth_layer2", + .groups = qeth_l2_attr_groups, +}; + static int qeth_l2_probe_device(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); + int rc; - qeth_l2_create_device_attributes(&gdev->dev); + if (gdev->dev.type == &qeth_generic_devtype) { + rc = qeth_l2_create_device_attributes(&gdev->dev); + if (rc) + return rc; + } INIT_LIST_HEAD(&card->vid_list); hash_init(card->mac_htable); card->options.layer2 = 1; @@ -1043,7 +1053,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) { struct qeth_card *card = dev_get_drvdata(&cgdev->dev); - qeth_l2_remove_device_attributes(&cgdev->dev); + if (cgdev->dev.type == &qeth_generic_devtype) + qeth_l2_remove_device_attributes(&cgdev->dev); qeth_set_allowed_threads(card, 0, 1); wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0); @@ -1101,7 +1112,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) case QETH_CARD_TYPE_OSN: card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup); - card->dev->flags |= IFF_NOARP; break; default: card->dev = alloc_etherdev(0); @@ -1114,9 +1124,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) card->dev->watchdog_timeo = QETH_TX_TIMEOUT; card->dev->mtu = card->info.initial_mtu; card->dev->netdev_ops = &qeth_l2_netdev_ops; - card->dev->ethtool_ops = - (card->info.type != QETH_CARD_TYPE_OSN) ? - &qeth_l2_ethtool_ops : &qeth_l2_osn_ops; + if (card->info.type == QETH_CARD_TYPE_OSN) { + card->dev->ethtool_ops = &qeth_l2_osn_ops; + card->dev->flags |= IFF_NOARP; + } else { + card->dev->ethtool_ops = &qeth_l2_ethtool_ops; + } card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { card->dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM; @@ -1429,6 +1442,7 @@ static int qeth_l2_control_event(struct qeth_card *card, } struct qeth_discipline qeth_l2_discipline = { + .devtype = &qeth_l2_devtype, .start_poll = qeth_qdio_start_poll, .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 692db49e3d2a..a48ed9e7e168 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -272,3 +272,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) } else qeth_bridgeport_an_set(card, 0); } + +const struct attribute_group *qeth_l2_attr_groups[] = { + &qeth_device_attr_group, + &qeth_device_blkt_group, + /* l2 specific, see l2_{create,remove}_device_attributes(): */ + &qeth_l2_bridgeport_attr_group, + NULL, +}; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index cc4d3c3d8cc5..285fe0b2c753 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3227,8 +3227,11 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) static int qeth_l3_probe_device(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); + int rc; - qeth_l3_create_device_attributes(&gdev->dev); + rc = qeth_l3_create_device_attributes(&gdev->dev); + if (rc) + return rc; card->options.layer2 = 0; card->info.hwtrap = 0; return 0; @@ -3519,6 +3522,7 @@ static int qeth_l3_control_event(struct qeth_card *card, } struct qeth_discipline qeth_l3_discipline = { + .devtype = &qeth_generic_devtype, .start_poll = qeth_qdio_start_poll, .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 75f820ca17b7..27ff38f839fc 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -1583,7 +1583,7 @@ out: int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port) { struct zfcp_qdio *qdio = wka_port->adapter->qdio; - struct zfcp_fsf_req *req = NULL; + struct zfcp_fsf_req *req; int retval = -EIO; spin_lock_irq(&qdio->req_q_lock); @@ -1612,7 +1612,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port) zfcp_fsf_req_free(req); out: spin_unlock_irq(&qdio->req_q_lock); - if (req && !IS_ERR(req)) + if (!retval) zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req->req_id); return retval; } @@ -1638,7 +1638,7 @@ static void zfcp_fsf_close_wka_port_handler(struct zfcp_fsf_req *req) int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port) { struct zfcp_qdio *qdio = wka_port->adapter->qdio; - struct zfcp_fsf_req *req = NULL; + struct zfcp_fsf_req *req; int retval = -EIO; spin_lock_irq(&qdio->req_q_lock); @@ -1667,7 +1667,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port) zfcp_fsf_req_free(req); out: spin_unlock_irq(&qdio->req_q_lock); - if (req && !IS_ERR(req)) + if (!retval) zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req->req_id); return retval; } diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 64eed87d34a8..433c5e3d5733 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1637,7 +1637,7 @@ config ATARI_SCSI_RESET_BOOT config MAC_SCSI tristate "Macintosh NCR5380 SCSI" - depends on MAC && SCSI=y + depends on MAC && SCSI select SCSI_SPI_ATTRS help This is the NCR 5380 SCSI controller included on most of the 68030 diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c index 0d351cd3191b..26d38b1a45ab 100644 --- a/drivers/scsi/aacraid/comminit.c +++ b/drivers/scsi/aacraid/comminit.c @@ -50,9 +50,13 @@ struct aac_common aac_config = { static inline int aac_is_msix_mode(struct aac_dev *dev) { - u32 status; + u32 status = 0; - status = src_readl(dev, MUnit.OMR); + if (dev->pdev->device == PMC_DEVICE_S6 || + dev->pdev->device == PMC_DEVICE_S7 || + dev->pdev->device == PMC_DEVICE_S8) { + status = src_readl(dev, MUnit.OMR); + } return (status & AAC_INT_MODE_MSIX); } diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index bc0203f3d243..e415e1c58eb5 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -413,16 +413,23 @@ static int aac_src_check_health(struct aac_dev *dev) u32 status = src_readl(dev, MUnit.OMR); /* + * Check to see if the board panic'd. + */ + if (unlikely(status & KERNEL_PANIC)) + goto err_blink; + + /* * Check to see if the board failed any self tests. */ if (unlikely(status & SELF_TEST_FAILED)) - return -1; + goto err_out; /* - * Check to see if the board panic'd. + * Check to see if the board failed any self tests. */ - if (unlikely(status & KERNEL_PANIC)) - return (status >> 16) & 0xFF; + if (unlikely(status & MONITOR_PANIC)) + goto err_out; + /* * Wait for the adapter to be up and running. */ @@ -432,6 +439,12 @@ static int aac_src_check_health(struct aac_dev *dev) * Everything is OK */ return 0; + +err_out: + return -1; + +err_blink: + return (status > 16) & 0xFF; } /** diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h index 5ada9268a450..a8ac4c0a1493 100644 --- a/drivers/scsi/cxlflash/common.h +++ b/drivers/scsi/cxlflash/common.h @@ -34,7 +34,6 @@ extern const struct file_operations cxlflash_cxl_fops; sectors */ -#define NUM_RRQ_ENTRY 16 /* for master issued cmds */ #define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry)) /* AFU command retry limit */ @@ -48,9 +47,12 @@ extern const struct file_operations cxlflash_cxl_fops; index derivation */ -#define CXLFLASH_MAX_CMDS 16 +#define CXLFLASH_MAX_CMDS 256 #define CXLFLASH_MAX_CMDS_PER_LUN CXLFLASH_MAX_CMDS +/* RRQ for master issued cmds */ +#define NUM_RRQ_ENTRY CXLFLASH_MAX_CMDS + static inline void check_sizes(void) { @@ -149,7 +151,7 @@ struct afu_cmd { struct afu { /* Stuff requiring alignment go first. */ - u64 rrq_entry[NUM_RRQ_ENTRY]; /* 128B RRQ */ + u64 rrq_entry[NUM_RRQ_ENTRY]; /* 2K RRQ */ /* * Command & data for AFU commands. */ diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index c86847c68448..0b096730c72a 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -996,6 +996,8 @@ static int wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry) do { msleep(delay_us / 1000); status = readq_be(&fc_regs[FC_MTIP_STATUS / 8]); + if (status == U64_MAX) + nretry /= 2; } while ((status & FC_MTIP_STATUS_MASK) != FC_MTIP_STATUS_ONLINE && nretry--); @@ -1027,6 +1029,8 @@ static int wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry) do { msleep(delay_us / 1000); status = readq_be(&fc_regs[FC_MTIP_STATUS / 8]); + if (status == U64_MAX) + nretry /= 2; } while ((status & FC_MTIP_STATUS_MASK) != FC_MTIP_STATUS_OFFLINE && nretry--); @@ -1137,7 +1141,7 @@ static const struct asyc_intr_info ainfo[] = { {SISL_ASTATUS_FC0_LOGI_F, "login failed", 0, CLR_FC_ERROR}, {SISL_ASTATUS_FC0_LOGI_S, "login succeeded", 0, SCAN_HOST}, {SISL_ASTATUS_FC0_LINK_DN, "link down", 0, 0}, - {SISL_ASTATUS_FC0_LINK_UP, "link up", 0, SCAN_HOST}, + {SISL_ASTATUS_FC0_LINK_UP, "link up", 0, 0}, {SISL_ASTATUS_FC1_OTHER, "other error", 1, CLR_FC_ERROR | LINK_RESET}, {SISL_ASTATUS_FC1_LOGO, "target initiated LOGO", 1, 0}, {SISL_ASTATUS_FC1_CRC_T, "CRC threshold exceeded", 1, LINK_RESET}, @@ -1145,7 +1149,7 @@ static const struct asyc_intr_info ainfo[] = { {SISL_ASTATUS_FC1_LOGI_F, "login failed", 1, CLR_FC_ERROR}, {SISL_ASTATUS_FC1_LOGI_S, "login succeeded", 1, SCAN_HOST}, {SISL_ASTATUS_FC1_LINK_DN, "link down", 1, 0}, - {SISL_ASTATUS_FC1_LINK_UP, "link up", 1, SCAN_HOST}, + {SISL_ASTATUS_FC1_LINK_UP, "link up", 1, 0}, {0x0, "", 0, 0} /* terminator */ }; @@ -1962,6 +1966,11 @@ retry: * cxlflash_eh_host_reset_handler() - reset the host adapter * @scp: SCSI command from stack identifying host. * + * Following a reset, the state is evaluated again in case an EEH occurred + * during the reset. In such a scenario, the host reset will either yield + * until the EEH recovery is complete or return success or failure based + * upon the current device state. + * * Return: * SUCCESS as defined in scsi/scsi.h * FAILED as defined in scsi/scsi.h @@ -1993,7 +2002,8 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp) } else cfg->state = STATE_NORMAL; wake_up_all(&cfg->reset_waitq); - break; + ssleep(1); + /* fall through */ case STATE_RESET: wait_event(cfg->reset_waitq, cfg->state != STATE_RESET); if (cfg->state == STATE_NORMAL) @@ -2305,7 +2315,7 @@ static struct scsi_host_template driver_template = { .eh_device_reset_handler = cxlflash_eh_device_reset_handler, .eh_host_reset_handler = cxlflash_eh_host_reset_handler, .change_queue_depth = cxlflash_change_queue_depth, - .cmd_per_lun = 16, + .cmd_per_lun = CXLFLASH_MAX_CMDS_PER_LUN, .can_queue = CXLFLASH_MAX_CMDS, .this_id = -1, .sg_tablesize = SG_NONE, /* No scatter gather support */ @@ -2534,6 +2544,9 @@ static void drain_ioctls(struct cxlflash_cfg *cfg) * @pdev: PCI device struct. * @state: PCI channel state. * + * When an EEH occurs during an active reset, wait until the reset is + * complete and then take action based upon the device state. + * * Return: PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT */ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev, @@ -2547,6 +2560,10 @@ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev, switch (state) { case pci_channel_io_frozen: + wait_event(cfg->reset_waitq, cfg->state != STATE_RESET); + if (cfg->state == STATE_FAILTERM) + return PCI_ERS_RESULT_DISCONNECT; + cfg->state = STATE_RESET; scsi_block_requests(cfg->host); drain_ioctls(cfg); diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index ce129e595b55..5c935847599c 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -248,6 +248,7 @@ struct fnic { struct completion *remove_wait; /* device remove thread blocks */ atomic_t in_flight; /* io counter */ + bool internal_reset_inprogress; u32 _reserved; /* fill hole */ unsigned long state_flags; /* protected by host lock */ enum fnic_state state; diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 266b909fe854..82e4bc8c11c5 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -2533,6 +2533,19 @@ int fnic_host_reset(struct scsi_cmnd *sc) unsigned long wait_host_tmo; struct Scsi_Host *shost = sc->device->host; struct fc_lport *lp = shost_priv(shost); + struct fnic *fnic = lport_priv(lp); + unsigned long flags; + + spin_lock_irqsave(&fnic->fnic_lock, flags); + if (fnic->internal_reset_inprogress == 0) { + fnic->internal_reset_inprogress = 1; + } else { + spin_unlock_irqrestore(&fnic->fnic_lock, flags); + FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, + "host reset in progress skipping another host reset\n"); + return SUCCESS; + } + spin_unlock_irqrestore(&fnic->fnic_lock, flags); /* * If fnic_reset is successful, wait for fabric login to complete @@ -2553,6 +2566,9 @@ int fnic_host_reset(struct scsi_cmnd *sc) } } + spin_lock_irqsave(&fnic->fnic_lock, flags); + fnic->internal_reset_inprogress = 0; + spin_unlock_irqrestore(&fnic->fnic_lock, flags); return ret; } diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 6bffd91b973a..c1ccf1ee99ea 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -560,8 +560,12 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) WARN_ON_ONCE(task->state == ISCSI_TASK_FREE); task->state = state; - if (!list_empty(&task->running)) + spin_lock_bh(&conn->taskqueuelock); + if (!list_empty(&task->running)) { + pr_debug_once("%s while task on list", __func__); list_del_init(&task->running); + } + spin_unlock_bh(&conn->taskqueuelock); if (conn->task == task) conn->task = NULL; @@ -783,7 +787,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (session->tt->xmit_task(task)) goto free_task; } else { + spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->mgmtqueue); + spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -1474,8 +1480,10 @@ void iscsi_requeue_task(struct iscsi_task *task) * this may be on the requeue list already if the xmit_task callout * is handling the r2ts while we are adding new ones */ + spin_lock_bh(&conn->taskqueuelock); if (list_empty(&task->running)) list_add_tail(&task->running, &conn->requeue); + spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } EXPORT_SYMBOL_GPL(iscsi_requeue_task); @@ -1512,22 +1520,26 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) * only have one nop-out as a ping from us and targets should not * overflow us with nop-ins */ + spin_lock_bh(&conn->taskqueuelock); check_mgmt: while (!list_empty(&conn->mgmtqueue)) { conn->task = list_entry(conn->mgmtqueue.next, struct iscsi_task, running); list_del_init(&conn->task->running); + spin_unlock_bh(&conn->taskqueuelock); if (iscsi_prep_mgmt_task(conn, conn->task)) { /* regular RX path uses back_lock */ spin_lock_bh(&conn->session->back_lock); __iscsi_put_task(conn->task); spin_unlock_bh(&conn->session->back_lock); conn->task = NULL; + spin_lock_bh(&conn->taskqueuelock); continue; } rc = iscsi_xmit_task(conn); if (rc) goto done; + spin_lock_bh(&conn->taskqueuelock); } /* process pending command queue */ @@ -1535,19 +1547,24 @@ check_mgmt: conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task, running); list_del_init(&conn->task->running); + spin_unlock_bh(&conn->taskqueuelock); if (conn->session->state == ISCSI_STATE_LOGGING_OUT) { fail_scsi_task(conn->task, DID_IMM_RETRY); + spin_lock_bh(&conn->taskqueuelock); continue; } rc = iscsi_prep_scsi_cmd_pdu(conn->task); if (rc) { if (rc == -ENOMEM || rc == -EACCES) { + spin_lock_bh(&conn->taskqueuelock); list_add_tail(&conn->task->running, &conn->cmdqueue); conn->task = NULL; + spin_unlock_bh(&conn->taskqueuelock); goto done; } else fail_scsi_task(conn->task, DID_ABORT); + spin_lock_bh(&conn->taskqueuelock); continue; } rc = iscsi_xmit_task(conn); @@ -1558,6 +1575,7 @@ check_mgmt: * we need to check the mgmt queue for nops that need to * be sent to aviod starvation */ + spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } @@ -1577,12 +1595,15 @@ check_mgmt: conn->task = task; list_del_init(&conn->task->running); conn->task->state = ISCSI_TASK_RUNNING; + spin_unlock_bh(&conn->taskqueuelock); rc = iscsi_xmit_task(conn); if (rc) goto done; + spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } + spin_unlock_bh(&conn->taskqueuelock); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1738,7 +1759,9 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto prepd_reject; } } else { + spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->cmdqueue); + spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -2900,6 +2923,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, INIT_LIST_HEAD(&conn->mgmtqueue); INIT_LIST_HEAD(&conn->cmdqueue); INIT_LIST_HEAD(&conn->requeue); + spin_lock_init(&conn->taskqueuelock); INIT_WORK(&conn->xmitwork, iscsi_xmitworker); /* allocate login_task used for the login/text sequences */ diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 9c706d8c1441..6f5e2720ffad 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -218,7 +218,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) task->num_scatter = qc->n_elem; } else { for_each_sg(qc->sg, sg, qc->n_elem, si) - xfer += sg->length; + xfer += sg_dma_len(sg); task->total_xfer_len = xfer; task->num_scatter = si; diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 59ced8864b2f..0e6aaef9a038 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -3563,12 +3563,14 @@ lpfc_els_free_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *elsiocb) } else { buf_ptr1 = (struct lpfc_dmabuf *) elsiocb->context2; lpfc_els_free_data(phba, buf_ptr1); + elsiocb->context2 = NULL; } } if (elsiocb->context3) { buf_ptr = (struct lpfc_dmabuf *) elsiocb->context3; lpfc_els_free_bpl(phba, buf_ptr); + elsiocb->context3 = NULL; } lpfc_sli_release_iocbq(phba, elsiocb); return 0; diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index 33ec4fa39ccb..f224cdb2fce4 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -1182,6 +1182,7 @@ struct lpfc_mbx_wq_create { #define lpfc_mbx_wq_create_page_size_SHIFT 0 #define lpfc_mbx_wq_create_page_size_MASK 0x000000FF #define lpfc_mbx_wq_create_page_size_WORD word1 +#define LPFC_WQ_PAGE_SIZE_4096 0x1 #define lpfc_mbx_wq_create_wqe_size_SHIFT 8 #define lpfc_mbx_wq_create_wqe_size_MASK 0x0000000F #define lpfc_mbx_wq_create_wqe_size_WORD word1 @@ -1253,6 +1254,7 @@ struct rq_context { #define lpfc_rq_context_page_size_SHIFT 0 /* Version 1 Only */ #define lpfc_rq_context_page_size_MASK 0x000000FF #define lpfc_rq_context_page_size_WORD word0 +#define LPFC_RQ_PAGE_SIZE_4096 0x1 uint32_t reserved1; uint32_t word2; #define lpfc_rq_context_cq_id_SHIFT 16 diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index c14ab6c3ae40..60c21093f865 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -11387,6 +11387,7 @@ static struct pci_driver lpfc_driver = { .id_table = lpfc_id_table, .probe = lpfc_pci_probe_one, .remove = lpfc_pci_remove_one, + .shutdown = lpfc_pci_remove_one, .suspend = lpfc_pci_suspend_one, .resume = lpfc_pci_resume_one, .err_handler = &lpfc_err_handler, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 92dfd6a5178c..38e90d9c2ced 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -5887,18 +5887,25 @@ lpfc_sli4_alloc_resource_identifiers(struct lpfc_hba *phba) free_vfi_bmask: kfree(phba->sli4_hba.vfi_bmask); + phba->sli4_hba.vfi_bmask = NULL; free_xri_ids: kfree(phba->sli4_hba.xri_ids); + phba->sli4_hba.xri_ids = NULL; free_xri_bmask: kfree(phba->sli4_hba.xri_bmask); + phba->sli4_hba.xri_bmask = NULL; free_vpi_ids: kfree(phba->vpi_ids); + phba->vpi_ids = NULL; free_vpi_bmask: kfree(phba->vpi_bmask); + phba->vpi_bmask = NULL; free_rpi_ids: kfree(phba->sli4_hba.rpi_ids); + phba->sli4_hba.rpi_ids = NULL; free_rpi_bmask: kfree(phba->sli4_hba.rpi_bmask); + phba->sli4_hba.rpi_bmask = NULL; err_exit: return rc; } @@ -13475,7 +13482,7 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq, LPFC_WQ_WQE_SIZE_128); bf_set(lpfc_mbx_wq_create_page_size, &wq_create->u.request_1, - (PAGE_SIZE/SLI4_PAGE_SIZE)); + LPFC_WQ_PAGE_SIZE_4096); page = wq_create->u.request_1.page; break; } @@ -13501,8 +13508,9 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq, LPFC_WQ_WQE_SIZE_128); break; } - bf_set(lpfc_mbx_wq_create_page_size, &wq_create->u.request_1, - (PAGE_SIZE/SLI4_PAGE_SIZE)); + bf_set(lpfc_mbx_wq_create_page_size, + &wq_create->u.request_1, + LPFC_WQ_PAGE_SIZE_4096); page = wq_create->u.request_1.page; break; default: @@ -13688,7 +13696,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq, LPFC_RQE_SIZE_8); bf_set(lpfc_rq_context_page_size, &rq_create->u.request.context, - (PAGE_SIZE/SLI4_PAGE_SIZE)); + LPFC_RQ_PAGE_SIZE_4096); } else { switch (hrq->entry_count) { default: diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 5b2c37f1e908..9b5367294116 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -4981,15 +4981,14 @@ _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, int sleep_flag, static int _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc, int sleep_flag) { - int r, i; + int r, i, index; unsigned long flags; u32 reply_address; u16 smid; struct _tr_list *delayed_tr, *delayed_tr_next; u8 hide_flag; struct adapter_reply_queue *reply_q; - long reply_post_free; - u32 reply_post_free_sz, index = 0; + Mpi2ReplyDescriptorsUnion_t *reply_post_free_contig; dinitprintk(ioc, pr_info(MPT3SAS_FMT "%s\n", ioc->name, __func__)); @@ -5061,27 +5060,27 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc, int sleep_flag) _base_assign_reply_queues(ioc); /* initialize Reply Post Free Queue */ - reply_post_free_sz = ioc->reply_post_queue_depth * - sizeof(Mpi2DefaultReplyDescriptor_t); - reply_post_free = (long)ioc->reply_post[index].reply_post_free; + index = 0; + reply_post_free_contig = ioc->reply_post[0].reply_post_free; list_for_each_entry(reply_q, &ioc->reply_queue_list, list) { + /* + * If RDPQ is enabled, switch to the next allocation. + * Otherwise advance within the contiguous region. + */ + if (ioc->rdpq_array_enable) { + reply_q->reply_post_free = + ioc->reply_post[index++].reply_post_free; + } else { + reply_q->reply_post_free = reply_post_free_contig; + reply_post_free_contig += ioc->reply_post_queue_depth; + } + reply_q->reply_post_host_index = 0; - reply_q->reply_post_free = (Mpi2ReplyDescriptorsUnion_t *) - reply_post_free; for (i = 0; i < ioc->reply_post_queue_depth; i++) reply_q->reply_post_free[i].Words = cpu_to_le64(ULLONG_MAX); if (!_base_is_controller_msix_enabled(ioc)) goto skip_init_reply_post_free_queue; - /* - * If RDPQ is enabled, switch to the next allocation. - * Otherwise advance within the contiguous region. - */ - if (ioc->rdpq_array_enable) - reply_post_free = (long) - ioc->reply_post[++index].reply_post_free; - else - reply_post_free += reply_post_free_sz; } skip_init_reply_post_free_queue: diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 92648a5ea2d2..63f5965acc89 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -390,6 +390,7 @@ struct MPT3SAS_TARGET { * @eedp_enable: eedp support enable bit * @eedp_type: 0(type_1), 1(type_2), 2(type_3) * @eedp_block_length: block size + * @ata_command_pending: SATL passthrough outstanding for device */ struct MPT3SAS_DEVICE { struct MPT3SAS_TARGET *sas_target; @@ -398,6 +399,17 @@ struct MPT3SAS_DEVICE { u8 configured_lun; u8 block; u8 tlr_snoop_check; + /* + * Bug workaround for SATL handling: the mpt2/3sas firmware + * doesn't return BUSY or TASK_SET_FULL for subsequent + * commands while a SATL pass through is in operation as the + * spec requires, it simply does nothing with them until the + * pass through completes, causing them possibly to timeout if + * the passthrough is a long executing command (like format or + * secure erase). This variable allows us to do the right + * thing while a SATL command is pending. + */ + unsigned long ata_command_pending; }; #define MPT3_CMD_NOT_USED 0x8000 /* free */ diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 8cead04f26d6..e333029e4b6c 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -51,6 +51,7 @@ #include <linux/workqueue.h> #include <linux/delay.h> #include <linux/pci.h> +#include <linux/pci-aspm.h> #include <linux/interrupt.h> #include <linux/aer.h> #include <linux/raid_class.h> @@ -3706,9 +3707,18 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc, } } -static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd) +static int _scsih_set_satl_pending(struct scsi_cmnd *scmd, bool pending) { - return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16); + struct MPT3SAS_DEVICE *priv = scmd->device->hostdata; + + if (scmd->cmnd[0] != ATA_12 && scmd->cmnd[0] != ATA_16) + return 0; + + if (pending) + return test_and_set_bit(0, &priv->ata_command_pending); + + clear_bit(0, &priv->ata_command_pending); + return 0; } /** @@ -3732,9 +3742,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc) if (!scmd) continue; count++; - if (ata_12_16_cmd(scmd)) - scsi_internal_device_unblock(scmd->device, - SDEV_RUNNING); + _scsih_set_satl_pending(scmd, false); mpt3sas_base_free_smid(ioc, smid); scsi_dma_unmap(scmd); if (ioc->pci_error_recovery) @@ -3865,13 +3873,6 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd) if (ioc->logging_level & MPT_DEBUG_SCSI) scsi_print_command(scmd); - /* - * Lock the device for any subsequent command until command is - * done. - */ - if (ata_12_16_cmd(scmd)) - scsi_internal_device_block(scmd->device); - sas_device_priv_data = scmd->device->hostdata; if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { scmd->result = DID_NO_CONNECT << 16; @@ -3885,6 +3886,19 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd) return 0; } + /* + * Bug work around for firmware SATL handling. The loop + * is based on atomic operations and ensures consistency + * since we're lockless at this point + */ + do { + if (test_bit(0, &sas_device_priv_data->ata_command_pending)) { + scmd->result = SAM_STAT_BUSY; + scmd->scsi_done(scmd); + return 0; + } + } while (_scsih_set_satl_pending(scmd, true)); + sas_target_priv_data = sas_device_priv_data->sas_target; /* invalid device handle */ @@ -4438,14 +4452,14 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) struct MPT3SAS_DEVICE *sas_device_priv_data; u32 response_code = 0; unsigned long flags; + unsigned int sector_sz; mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply); scmd = _scsih_scsi_lookup_get_clear(ioc, smid); if (scmd == NULL) return 1; - if (ata_12_16_cmd(scmd)) - scsi_internal_device_unblock(scmd->device, SDEV_RUNNING); + _scsih_set_satl_pending(scmd, false); mpi_request = mpt3sas_base_get_msg_frame(ioc, smid); @@ -4497,6 +4511,20 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) } xfer_cnt = le32_to_cpu(mpi_reply->TransferCount); + + /* In case of bogus fw or device, we could end up having + * unaligned partial completion. We can force alignment here, + * then scsi-ml does not need to handle this misbehavior. + */ + sector_sz = scmd->device->sector_size; + if (unlikely(scmd->request->cmd_type == REQ_TYPE_FS && sector_sz && + xfer_cnt % sector_sz)) { + sdev_printk(KERN_INFO, scmd->device, + "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n", + xfer_cnt, sector_sz); + xfer_cnt = round_down(xfer_cnt, sector_sz); + } + scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt); if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE) log_info = le32_to_cpu(mpi_reply->IOCLogInfo); @@ -8483,6 +8511,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id) switch (hba_mpi_version) { case MPI2_VERSION: + pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | + PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM); /* Use mpt2sas driver host template for SAS 2.0 HBA's */ shost = scsi_host_alloc(&mpt2sas_driver_template, sizeof(struct MPT3SAS_ADAPTER)); diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index 9c780740fb82..e712fe745955 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -737,8 +737,8 @@ static int mvs_task_prep(struct sas_task *task, struct mvs_info *mvi, int is_tmf mv_dprintk("device %016llx not ready.\n", SAS_ADDR(dev->sas_addr)); - rc = SAS_PHY_DOWN; - return rc; + rc = SAS_PHY_DOWN; + return rc; } tei.port = dev->port->lldd_port; if (tei.port && !tei.port->port_attached && !tmf) { diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 6b942d9e5b74..1ed85dfc008d 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -329,12 +329,15 @@ qla2x00_sysfs_read_optrom(struct file *filp, struct kobject *kobj, struct qla_hw_data *ha = vha->hw; ssize_t rval = 0; + mutex_lock(&ha->optrom_mutex); + if (ha->optrom_state != QLA_SREADING) - return 0; + goto out; - mutex_lock(&ha->optrom_mutex); rval = memory_read_from_buffer(buf, count, &off, ha->optrom_buffer, ha->optrom_region_size); + +out: mutex_unlock(&ha->optrom_mutex); return rval; @@ -349,14 +352,19 @@ qla2x00_sysfs_write_optrom(struct file *filp, struct kobject *kobj, struct device, kobj))); struct qla_hw_data *ha = vha->hw; - if (ha->optrom_state != QLA_SWRITING) + mutex_lock(&ha->optrom_mutex); + + if (ha->optrom_state != QLA_SWRITING) { + mutex_unlock(&ha->optrom_mutex); return -EINVAL; - if (off > ha->optrom_region_size) + } + if (off > ha->optrom_region_size) { + mutex_unlock(&ha->optrom_mutex); return -ERANGE; + } if (off + count > ha->optrom_region_size) count = ha->optrom_region_size - off; - mutex_lock(&ha->optrom_mutex); memcpy(&ha->optrom_buffer[off], buf, count); mutex_unlock(&ha->optrom_mutex); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 0e59731f95ad..1f6a3b86965f 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2466,6 +2466,10 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt) if (pkt->entry_status & RF_BUSY) res = DID_BUS_BUSY << 16; + if (pkt->entry_type == NOTIFY_ACK_TYPE && + pkt->handle == QLA_TGT_SKIP_HANDLE) + return; + sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); if (sp) { sp->done(ha, sp, res); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 3588a56aabb4..5cbf20ab94aa 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2311,10 +2311,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) if (mem_only) { if (pci_enable_device_mem(pdev)) - goto probe_out; + return ret; } else { if (pci_enable_device(pdev)) - goto probe_out; + return ret; } /* This may fail but that's ok */ @@ -2324,7 +2324,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) if (!ha) { ql_log_pci(ql_log_fatal, pdev, 0x0009, "Unable to allocate memory for ha.\n"); - goto probe_out; + goto disable_device; } ql_dbg_pci(ql_dbg_init, pdev, 0x000a, "Memory allocated for ha=%p.\n", ha); @@ -2923,7 +2923,7 @@ iospace_config_failed: kfree(ha); ha = NULL; -probe_out: +disable_device: pci_disable_device(pdev); return ret; } diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index f57d96984ae4..e6faa0b050d1 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -2865,7 +2865,7 @@ static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha, pkt->entry_type = NOTIFY_ACK_TYPE; pkt->entry_count = 1; - pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK; + pkt->handle = QLA_TGT_SKIP_HANDLE; nack = (struct nack_to_isp *)pkt; nack->ox_id = ntfy->ox_id; diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index e7649ed3f667..4d655b568269 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -289,20 +289,6 @@ int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh) } EXPORT_SYMBOL_GPL(scsi_unregister_device_handler); -static struct scsi_device *get_sdev_from_queue(struct request_queue *q) -{ - struct scsi_device *sdev; - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - sdev = q->queuedata; - if (!sdev || !get_device(&sdev->sdev_gendev)) - sdev = NULL; - spin_unlock_irqrestore(q->queue_lock, flags); - - return sdev; -} - /* * scsi_dh_activate - activate the path associated with the scsi_device * corresponding to the given request queue. @@ -321,7 +307,7 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data) struct scsi_device *sdev; int err = SCSI_DH_NOSYS; - sdev = get_sdev_from_queue(q); + sdev = scsi_device_from_queue(q); if (!sdev) { if (fn) fn(data, err); @@ -368,7 +354,7 @@ int scsi_dh_set_params(struct request_queue *q, const char *params) struct scsi_device *sdev; int err = -SCSI_DH_NOSYS; - sdev = get_sdev_from_queue(q); + sdev = scsi_device_from_queue(q); if (!sdev) return err; @@ -391,7 +377,7 @@ int scsi_dh_attach(struct request_queue *q, const char *name) struct scsi_device_handler *scsi_dh; int err = 0; - sdev = get_sdev_from_queue(q); + sdev = scsi_device_from_queue(q); if (!sdev) return -ENODEV; @@ -429,7 +415,7 @@ const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp) struct scsi_device *sdev; const char *handler_name = NULL; - sdev = get_sdev_from_queue(q); + sdev = scsi_device_from_queue(q); if (!sdev) return NULL; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index cf5b99e1f12b..887045ae5d10 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1120,7 +1120,8 @@ int scsi_init_io(struct scsi_cmnd *cmd) bool is_mq = (rq->mq_ctx != NULL); int error; - BUG_ON(!rq->nr_phys_segments); + if (WARN_ON_ONCE(!rq->nr_phys_segments)) + return -EINVAL; error = scsi_init_sgtable(rq, &cmd->sdb); if (error) @@ -2214,6 +2215,29 @@ void scsi_mq_destroy_tags(struct Scsi_Host *shost) blk_mq_free_tag_set(&shost->tag_set); } +/** + * scsi_device_from_queue - return sdev associated with a request_queue + * @q: The request queue to return the sdev from + * + * Return the sdev associated with a request queue or NULL if the + * request_queue does not reference a SCSI device. + */ +struct scsi_device *scsi_device_from_queue(struct request_queue *q) +{ + struct scsi_device *sdev = NULL; + + if (q->mq_ops) { + if (q->mq_ops == &scsi_mq_ops) + sdev = q->queuedata; + } else if (q->request_fn == scsi_request_fn) + sdev = q->queuedata; + if (!sdev || !get_device(&sdev->sdev_gendev)) + sdev = NULL; + + return sdev; +} +EXPORT_SYMBOL_GPL(scsi_device_from_queue); + /* * Function: scsi_block_requests() * diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 6ee50742f6a5..8750c86f95f9 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1398,11 +1398,15 @@ static int media_not_present(struct scsi_disk *sdkp, **/ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) { - struct scsi_disk *sdkp = scsi_disk(disk); - struct scsi_device *sdp = sdkp->device; + struct scsi_disk *sdkp = scsi_disk_get(disk); + struct scsi_device *sdp; struct scsi_sense_hdr *sshdr = NULL; int retval; + if (!sdkp) + return 0; + + sdp = sdkp->device; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n")); /* @@ -1459,6 +1463,7 @@ out: kfree(sshdr); retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0; sdp->changed = 0; + scsi_disk_put(sdkp); return retval; } @@ -2046,6 +2051,22 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, #define READ_CAPACITY_RETRIES_ON_RESET 10 +/* + * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set + * and the reported logical block size is bigger than 512 bytes. Note + * that last_sector is a u64 and therefore logical_to_sectors() is not + * applicable. + */ +static bool sd_addressable_capacity(u64 lba, unsigned int sector_size) +{ + u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9); + + if (sizeof(sector_t) == 4 && last_sector > U32_MAX) + return false; + + return true; +} + static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, unsigned char *buffer) { @@ -2111,7 +2132,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, return -ENODEV; } - if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) { + if (!sd_addressable_capacity(lba, sector_size)) { sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " "kernel compiled with support for large block " "devices.\n"); @@ -2197,7 +2218,7 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, return sector_size; } - if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) { + if (!sd_addressable_capacity(lba, sector_size)) { sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " "kernel compiled with support for large block " "devices.\n"); @@ -2545,7 +2566,8 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) if (sdp->broken_fua) { sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n"); sdkp->DPOFUA = 0; - } else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) { + } else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw && + !sdkp->device->use_16_for_rw) { sd_first_printk(KERN_NOTICE, sdkp, "Uses READ/WRITE(6), disabling FUA\n"); sdkp->DPOFUA = 0; @@ -2883,7 +2905,8 @@ static int sd_revalidate_disk(struct gendisk *disk) q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); } else - rw_max = BLK_DEF_MAX_SECTORS; + rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), + (sector_t)BLK_DEF_MAX_SECTORS); /* Combine with controller limits */ q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index a1c29b0afb22..6514636431ab 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1008,6 +1008,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) result = get_user(val, ip); if (result) return result; + if (val > SG_MAX_CDB_SIZE) + return -ENOMEM; sfp->next_cmd_len = (val > 0) ? val : 0; return 0; case SG_GET_VERSION_NUM: @@ -1763,6 +1765,10 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) return res; iov_iter_truncate(&i, hp->dxfer_len); + if (!iov_iter_count(&i)) { + kfree(iov); + return -EINVAL; + } res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC); kfree(iov); diff --git a/drivers/scsi/snic/snic_main.c b/drivers/scsi/snic/snic_main.c index 2b3c25371d76..8175f997e82c 100644 --- a/drivers/scsi/snic/snic_main.c +++ b/drivers/scsi/snic/snic_main.c @@ -584,6 +584,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!pool) { SNIC_HOST_ERR(shost, "dflt sgl pool creation failed\n"); + ret = -ENOMEM; goto err_free_res; } @@ -594,6 +595,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!pool) { SNIC_HOST_ERR(shost, "max sgl pool creation failed\n"); + ret = -ENOMEM; goto err_free_dflt_sgl_pool; } @@ -604,6 +606,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!pool) { SNIC_HOST_ERR(shost, "snic tmreq info pool creation failed.\n"); + ret = -ENOMEM; goto err_free_max_sgl_pool; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 64c867405ad4..804586aeaffe 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -834,6 +834,7 @@ static void get_capabilities(struct scsi_cd *cd) unsigned char *buffer; struct scsi_mode_data data; struct scsi_sense_hdr sshdr; + unsigned int ms_len = 128; int rc, n; static const char *loadmech[] = @@ -860,10 +861,11 @@ static void get_capabilities(struct scsi_cd *cd) scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr); /* ask for mode page 0x2a */ - rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, 128, + rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, ms_len, SR_TIMEOUT, 3, &data, NULL); - if (!scsi_status_is_good(rc)) { + if (!scsi_status_is_good(rc) || data.length > ms_len || + data.header_length + data.block_descriptor_length > data.length) { /* failed, drive doesn't have capabilities mode page */ cd->cdi.speed = 1; cd->cdi.mask |= (CDC_CD_R | CDC_CD_RW | CDC_DVD_R | diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 0f636cc4c809..cd5c1c060481 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -135,6 +135,8 @@ struct hv_fc_wwn_packet { #define SRB_FLAGS_PORT_DRIVER_RESERVED 0x0F000000 #define SRB_FLAGS_CLASS_DRIVER_RESERVED 0xF0000000 +#define SP_UNTAGGED ((unsigned char) ~0) +#define SRB_SIMPLE_TAG_REQUEST 0x20 /* * Platform neutral description of a scsi request - @@ -354,6 +356,7 @@ enum storvsc_request_type { #define SRB_STATUS_SUCCESS 0x01 #define SRB_STATUS_ABORTED 0x02 #define SRB_STATUS_ERROR 0x04 +#define SRB_STATUS_DATA_OVERRUN 0x12 #define SRB_STATUS(status) \ (status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN)) @@ -864,6 +867,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, switch (SRB_STATUS(vm_srb->srb_status)) { case SRB_STATUS_ERROR: /* + * Let upper layer deal with error when + * sense message is present. + */ + + if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) + break; + /* * If there is an error; offline the device since all * error recovery strategies would have already been * deployed on the host side. However, if the command @@ -927,6 +937,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request) struct hv_host_device *host_dev = shost_priv(scmnd->device->host); struct scsi_sense_hdr sense_hdr; struct vmscsi_request *vm_srb; + u32 data_transfer_length; struct Scsi_Host *host; struct storvsc_device *stor_dev; struct hv_device *dev = host_dev->dev; @@ -937,6 +948,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request) host = stor_dev->host; vm_srb = &cmd_request->vstor_packet.vm_srb; + data_transfer_length = vm_srb->data_transfer_length; scmnd->result = vm_srb->scsi_status; @@ -947,13 +959,20 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request) &sense_hdr); } - if (vm_srb->srb_status != SRB_STATUS_SUCCESS) + if (vm_srb->srb_status != SRB_STATUS_SUCCESS) { storvsc_handle_error(vm_srb, scmnd, host, sense_hdr.asc, sense_hdr.ascq); + /* + * The Windows driver set data_transfer_length on + * SRB_STATUS_DATA_OVERRUN. On other errors, this value + * is untouched. In these cases we set it to 0. + */ + if (vm_srb->srb_status != SRB_STATUS_DATA_OVERRUN) + data_transfer_length = 0; + } scsi_set_resid(scmnd, - cmd_request->payload->range.len - - vm_srb->data_transfer_length); + cmd_request->payload->range.len - data_transfer_length); scmnd->scsi_done(scmnd); @@ -1409,6 +1428,13 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DISABLE_SYNCH_TRANSFER; + if (scmnd->device->tagged_supported) { + vm_srb->win8_extension.srb_flags |= + (SRB_FLAGS_QUEUE_ACTION_ENABLE | SRB_FLAGS_NO_QUEUE_FREEZE); + vm_srb->win8_extension.queue_tag = SP_UNTAGGED; + vm_srb->win8_extension.queue_action = SRB_SIMPLE_TAG_REQUEST; + } + /* Build the SRB */ switch (scmnd->sc_data_direction) { case DMA_TO_DEVICE: diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 7dbbb29d24c6..03a2aadf0d3c 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -533,7 +533,9 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi, { struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev); struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc); + unsigned long flags; int req_size; + int ret; BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize); @@ -561,8 +563,15 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi, req_size = sizeof(cmd->req.cmd); } - if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0) + ret = virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)); + if (ret == -EIO) { + cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET; + spin_lock_irqsave(&req_vq->vq_lock, flags); + virtscsi_complete_cmd(vscsi, cmd); + spin_unlock_irqrestore(&req_vq->vq_lock, flags); + } else if (ret != 0) { return SCSI_MLQUEUE_HOST_BUSY; + } return 0; } diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c index d36c11b73a35..02fb96797ac8 100644 --- a/drivers/spi/spi-davinci.c +++ b/drivers/spi/spi-davinci.c @@ -646,7 +646,7 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t) buf = t->rx_buf; t->rx_dma = dma_map_single(&spi->dev, buf, t->len, DMA_FROM_DEVICE); - if (!t->rx_dma) { + if (dma_mapping_error(&spi->dev, !t->rx_dma)) { ret = -EFAULT; goto err_rx_map; } @@ -660,7 +660,7 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t) buf = (void *)t->tx_buf; t->tx_dma = dma_map_single(&spi->dev, buf, t->len, DMA_TO_DEVICE); - if (!t->tx_dma) { + if (dma_mapping_error(&spi->dev, t->tx_dma)) { ret = -EFAULT; goto err_tx_map; } diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index 882cd6618cd5..87a0e47eeae6 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -107,7 +107,10 @@ static const struct file_operations dw_spi_regs_ops = { static int dw_spi_debugfs_init(struct dw_spi *dws) { - dws->debugfs = debugfs_create_dir("dw_spi", NULL); + char name[128]; + + snprintf(name, 128, "dw_spi-%s", dev_name(&dws->master->dev)); + dws->debugfs = debugfs_create_dir(name, NULL); if (!dws->debugfs) return -ENOMEM; diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index 6b3da1bb0d63..2db681722d2c 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -364,11 +364,23 @@ static int spmi_drv_remove(struct device *dev) return 0; } +static int spmi_drv_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + int ret; + + ret = of_device_uevent_modalias(dev, env); + if (ret != -ENODEV) + return ret; + + return 0; +} + static struct bus_type spmi_bus_type = { .name = "spmi", .match = spmi_device_match, .probe = spmi_drv_probe, .remove = spmi_drv_remove, + .uevent = spmi_drv_uevent, }; /** diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 3f1133230a1a..e4530ac6d5d4 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -392,6 +392,7 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) ret = PTR_ERR(vmfile); goto out; } + vmfile->f_mode |= FMODE_LSEEK; asma->file = vmfile; } get_file(asma->file); diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c index 7b4af519e17e..b831f08e2769 100644 --- a/drivers/staging/comedi/comedi_fops.c +++ b/drivers/staging/comedi/comedi_fops.c @@ -2901,9 +2901,6 @@ static int __init comedi_init(void) comedi_class->dev_groups = comedi_dev_groups; - /* XXX requires /proc interface */ - comedi_proc_init(); - /* create devices files for legacy/manual use */ for (i = 0; i < comedi_num_legacy_minors; i++) { struct comedi_device *dev; @@ -2911,6 +2908,7 @@ static int __init comedi_init(void) dev = comedi_alloc_board_minor(NULL); if (IS_ERR(dev)) { comedi_cleanup_board_minors(); + class_destroy(comedi_class); cdev_del(&comedi_cdev); unregister_chrdev_region(MKDEV(COMEDI_MAJOR, 0), COMEDI_NUM_MINORS); @@ -2920,6 +2918,9 @@ static int __init comedi_init(void) mutex_unlock(&dev->mutex); } + /* XXX requires /proc interface */ + comedi_proc_init(); + return 0; } module_init(comedi_init); diff --git a/drivers/staging/comedi/drivers/jr3_pci.c b/drivers/staging/comedi/drivers/jr3_pci.c index b87192e0f9aa..109becdabc24 100644 --- a/drivers/staging/comedi/drivers/jr3_pci.c +++ b/drivers/staging/comedi/drivers/jr3_pci.c @@ -610,7 +610,7 @@ static void jr3_pci_poll_dev(unsigned long data) s = &dev->subdevices[i]; spriv = s->private; - if (now > spriv->next_time_min) { + if (time_after_eq(now, spriv->next_time_min)) { struct jr3_pci_poll_delay sub_delay; sub_delay = jr3_pci_poll_subdevice(s); @@ -726,11 +726,12 @@ static int jr3_pci_auto_attach(struct comedi_device *dev, s->insn_read = jr3_pci_ai_insn_read; spriv = jr3_pci_alloc_spriv(dev, s); - if (spriv) { - /* Channel specific range and maxdata */ - s->range_table_list = spriv->range_table_list; - s->maxdata_list = spriv->maxdata_list; - } + if (!spriv) + return -ENOMEM; + + /* Channel specific range and maxdata */ + s->range_table_list = spriv->range_table_list; + s->maxdata_list = spriv->maxdata_list; } /* Reset DSP card */ diff --git a/drivers/staging/emxx_udc/emxx_udc.c b/drivers/staging/emxx_udc/emxx_udc.c index 4e6c16af40fc..91ff8fb0cc3a 100644 --- a/drivers/staging/emxx_udc/emxx_udc.c +++ b/drivers/staging/emxx_udc/emxx_udc.c @@ -3181,7 +3181,7 @@ static const struct { }; /*-------------------------------------------------------------------------*/ -static void __init nbu2ss_drv_ep_init(struct nbu2ss_udc *udc) +static void nbu2ss_drv_ep_init(struct nbu2ss_udc *udc) { int i; @@ -3211,7 +3211,7 @@ static void __init nbu2ss_drv_ep_init(struct nbu2ss_udc *udc) /*-------------------------------------------------------------------------*/ /* platform_driver */ -static int __init nbu2ss_drv_contest_init( +static int nbu2ss_drv_contest_init( struct platform_device *pdev, struct nbu2ss_udc *udc) { diff --git a/drivers/staging/gdm724x/gdm_mux.c b/drivers/staging/gdm724x/gdm_mux.c index 445f83615575..fb4f3fea6c66 100644 --- a/drivers/staging/gdm724x/gdm_mux.c +++ b/drivers/staging/gdm724x/gdm_mux.c @@ -670,14 +670,14 @@ static int __init gdm_usb_mux_init(void) static void __exit gdm_usb_mux_exit(void) { - unregister_lte_tty_driver(); - if (mux_rx_wq) { flush_workqueue(mux_rx_wq); destroy_workqueue(mux_rx_wq); } usb_deregister(&gdm_mux_driver); + unregister_lte_tty_driver(); + } module_init(gdm_usb_mux_init); diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c index d97aa2827412..8eb7179da342 100644 --- a/drivers/staging/iio/resolver/ad2s1210.c +++ b/drivers/staging/iio/resolver/ad2s1210.c @@ -468,7 +468,7 @@ static int ad2s1210_read_raw(struct iio_dev *indio_dev, long m) { struct ad2s1210_state *st = iio_priv(indio_dev); - bool negative; + u16 negative; int ret = 0; u16 pos; s16 vel; diff --git a/drivers/staging/lustre/lustre/lov/lov_pack.c b/drivers/staging/lustre/lustre/lov/lov_pack.c index 2fb1e974cc70..e11b1001d1f6 100644 --- a/drivers/staging/lustre/lustre/lov/lov_pack.c +++ b/drivers/staging/lustre/lustre/lov/lov_pack.c @@ -399,18 +399,10 @@ int lov_getstripe(struct obd_export *exp, struct lov_stripe_md *lsm, struct lov_mds_md *lmmk = NULL; int rc, lmm_size; int lum_size; - mm_segment_t seg; if (!lsm) return -ENODATA; - /* - * "Switch to kernel segment" to allow copying from kernel space by - * copy_{to,from}_user(). - */ - seg = get_fs(); - set_fs(KERNEL_DS); - /* we only need the header part from user space to get lmm_magic and * lmm_stripe_count, (the header part is common to v1 and v3) */ lum_size = sizeof(struct lov_user_md_v1); @@ -485,6 +477,5 @@ int lov_getstripe(struct obd_export *exp, struct lov_stripe_md *lsm, obd_free_diskmd(exp, &lmmk); out_set: - set_fs(seg); return rc; } diff --git a/drivers/staging/rdma/ehca/ehca_mrmw.c b/drivers/staging/rdma/ehca/ehca_mrmw.c index f914b30999f8..4d52ca42644a 100644 --- a/drivers/staging/rdma/ehca/ehca_mrmw.c +++ b/drivers/staging/rdma/ehca/ehca_mrmw.c @@ -1921,7 +1921,7 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo, u64 *kpage) { int ret = 0; - u64 pgaddr, prev_pgaddr; + u64 pgaddr, prev_pgaddr = 0; u32 j = 0; int kpages_per_hwpage = pginfo->hwpage_size / PAGE_SIZE; int nr_kpages = kpages_per_hwpage; @@ -2417,6 +2417,7 @@ static int ehca_reg_bmap_mr_rpages(struct ehca_shca *shca, ehca_err(&shca->ib_device, "kpage alloc failed"); return -ENOMEM; } + hret = H_SUCCESS; for (top = 0; top < EHCA_MAP_ENTRIES; top++) { if (!ehca_bmap_valid(ehca_bmap->top[top])) continue; diff --git a/drivers/staging/rtl8188eu/core/rtw_ap.c b/drivers/staging/rtl8188eu/core/rtw_ap.c index 3cdb40fea5ee..f5cedbbc552a 100644 --- a/drivers/staging/rtl8188eu/core/rtw_ap.c +++ b/drivers/staging/rtl8188eu/core/rtw_ap.c @@ -894,7 +894,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf, int len) return _FAIL; - if (len > MAX_IE_SZ) + if (len < 0 || len > MAX_IE_SZ) return _FAIL; pbss_network->IELength = len; diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index 110b8c0b6cd7..0f2fe34e14c2 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -1405,6 +1405,9 @@ static int wlanhdr_to_ethhdr(struct recv_frame *precvframe) ptr = recvframe_pull(precvframe, (rmv_len-sizeof(struct ethhdr) + (bsnaphdr ? 2 : 0))); } + if (!ptr) + return _FAIL; + memcpy(ptr, pattrib->dst, ETH_ALEN); memcpy(ptr+ETH_ALEN, pattrib->src, ETH_ALEN); diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index 82a7c27c517f..02c3feef4e36 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -47,6 +47,7 @@ static struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */ {USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */ {USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */ + {USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */ {USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ {} /* Terminating entry */ }; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index e9c4f973bba9..7a8ceb961bb6 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -97,8 +97,9 @@ void rtl92e_set_reg(struct net_device *dev, u8 variable, u8 *val) switch (variable) { case HW_VAR_BSSID: - rtl92e_writel(dev, BSSIDR, ((u32 *)(val))[0]); - rtl92e_writew(dev, BSSIDR+2, ((u16 *)(val+2))[0]); + /* BSSIDR 2 byte alignment */ + rtl92e_writew(dev, BSSIDR, *(u16 *)val); + rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(val + 2)); break; case HW_VAR_MEDIA_STATUS: @@ -626,7 +627,7 @@ void rtl92e_get_eeprom_size(struct net_device *dev) struct r8192_priv *priv = rtllib_priv(dev); RT_TRACE(COMP_INIT, "===========>%s()\n", __func__); - curCR = rtl92e_readl(dev, EPROM_CMD); + curCR = rtl92e_readw(dev, EPROM_CMD); RT_TRACE(COMP_INIT, "read from Reg Cmd9346CR(%x):%x\n", EPROM_CMD, curCR); priv->epromtype = (curCR & EPROM_CMD_9356SEL) ? EEPROM_93C56 : @@ -963,8 +964,8 @@ static void _rtl92e_net_update(struct net_device *dev) rtl92e_config_rate(dev, &rate_config); priv->dot11CurrentPreambleMode = PREAMBLE_AUTO; priv->basic_rate = rate_config &= 0x15f; - rtl92e_writel(dev, BSSIDR, ((u32 *)net->bssid)[0]); - rtl92e_writew(dev, BSSIDR+4, ((u16 *)net->bssid)[2]); + rtl92e_writew(dev, BSSIDR, *(u16 *)net->bssid); + rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(net->bssid + 2)); if (priv->rtllib->iw_mode == IW_MODE_ADHOC) { rtl92e_writew(dev, ATIMWND, 2); @@ -1184,8 +1185,7 @@ void rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc, struct cb_desc *cb_desc, struct sk_buff *skb) { struct r8192_priv *priv = rtllib_priv(dev); - dma_addr_t mapping = pci_map_single(priv->pdev, skb->data, skb->len, - PCI_DMA_TODEVICE); + dma_addr_t mapping; struct tx_fwinfo_8190pci *pTxFwInfo = NULL; pTxFwInfo = (struct tx_fwinfo_8190pci *)skb->data; @@ -1196,8 +1196,6 @@ void rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc, pTxFwInfo->Short = _rtl92e_query_is_short(pTxFwInfo->TxHT, pTxFwInfo->TxRate, cb_desc); - if (pci_dma_mapping_error(priv->pdev, mapping)) - netdev_err(dev, "%s(): DMA Mapping error\n", __func__); if (cb_desc->bAMPDUEnable) { pTxFwInfo->AllowAggregation = 1; pTxFwInfo->RxMF = cb_desc->ampdu_factor; @@ -1232,6 +1230,14 @@ void rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc, } memset((u8 *)pdesc, 0, 12); + + mapping = pci_map_single(priv->pdev, skb->data, skb->len, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(priv->pdev, mapping)) { + netdev_err(dev, "%s(): DMA Mapping error\n", __func__); + return; + } + pdesc->LINIP = 0; pdesc->CmdInit = 1; pdesc->Offset = sizeof(struct tx_fwinfo_8190pci) + 8; diff --git a/drivers/staging/rtl8712/rtl871x_recv.c b/drivers/staging/rtl8712/rtl871x_recv.c index 4ff530155187..04ac23cc47a8 100644 --- a/drivers/staging/rtl8712/rtl871x_recv.c +++ b/drivers/staging/rtl8712/rtl871x_recv.c @@ -641,11 +641,16 @@ sint r8712_wlanhdr_to_ethhdr(union recv_frame *precvframe) /* append rx status for mp test packets */ ptr = recvframe_pull(precvframe, (rmv_len - sizeof(struct ethhdr) + 2) - 24); + if (!ptr) + return _FAIL; memcpy(ptr, get_rxmem(precvframe), 24); ptr += 24; - } else + } else { ptr = recvframe_pull(precvframe, (rmv_len - sizeof(struct ethhdr) + (bsnaphdr ? 2 : 0))); + if (!ptr) + return _FAIL; + } memcpy(ptr, pattrib->dst, ETH_ALEN); memcpy(ptr + ETH_ALEN, pattrib->src, ETH_ALEN); diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c index 01e642db311e..f35ee85f61b5 100644 --- a/drivers/staging/vt6656/main_usb.c +++ b/drivers/staging/vt6656/main_usb.c @@ -529,6 +529,9 @@ static int vnt_start(struct ieee80211_hw *hw) goto free_all; } + if (vnt_key_init_table(priv)) + goto free_all; + priv->int_interval = 1; /* bInterval is set to 1 */ vnt_int_start_interrupt(priv); diff --git a/drivers/staging/vt6656/usbpipe.c b/drivers/staging/vt6656/usbpipe.c index c975c3b87093..cfc3017fd64a 100644 --- a/drivers/staging/vt6656/usbpipe.c +++ b/drivers/staging/vt6656/usbpipe.c @@ -50,15 +50,25 @@ int vnt_control_out(struct vnt_private *priv, u8 request, u16 value, u16 index, u16 length, u8 *buffer) { int status = 0; + u8 *usb_buffer; if (test_bit(DEVICE_FLAGS_DISCONNECTED, &priv->flags)) return STATUS_FAILURE; mutex_lock(&priv->usb_lock); + usb_buffer = kmemdup(buffer, length, GFP_KERNEL); + if (!usb_buffer) { + mutex_unlock(&priv->usb_lock); + return -ENOMEM; + } + status = usb_control_msg(priv->usb, - usb_sndctrlpipe(priv->usb, 0), request, 0x40, value, - index, buffer, length, USB_CTL_WAIT); + usb_sndctrlpipe(priv->usb, 0), + request, 0x40, value, + index, usb_buffer, length, USB_CTL_WAIT); + + kfree(usb_buffer); mutex_unlock(&priv->usb_lock); @@ -78,15 +88,28 @@ int vnt_control_in(struct vnt_private *priv, u8 request, u16 value, u16 index, u16 length, u8 *buffer) { int status; + u8 *usb_buffer; if (test_bit(DEVICE_FLAGS_DISCONNECTED, &priv->flags)) return STATUS_FAILURE; mutex_lock(&priv->usb_lock); + usb_buffer = kmalloc(length, GFP_KERNEL); + if (!usb_buffer) { + mutex_unlock(&priv->usb_lock); + return -ENOMEM; + } + status = usb_control_msg(priv->usb, - usb_rcvctrlpipe(priv->usb, 0), request, 0xc0, value, - index, buffer, length, USB_CTL_WAIT); + usb_rcvctrlpipe(priv->usb, 0), + request, 0xc0, value, + index, usb_buffer, length, USB_CTL_WAIT); + + if (status == length) + memcpy(buffer, usb_buffer, length); + + kfree(usb_buffer); mutex_unlock(&priv->usb_lock); diff --git a/drivers/staging/wlan-ng/p80211netdev.c b/drivers/staging/wlan-ng/p80211netdev.c index a9c1e0bafa62..e35fbece3d2f 100644 --- a/drivers/staging/wlan-ng/p80211netdev.c +++ b/drivers/staging/wlan-ng/p80211netdev.c @@ -232,7 +232,7 @@ static int p80211_convert_to_ether(wlandevice_t *wlandev, struct sk_buff *skb) struct p80211_hdr_a3 *hdr; hdr = (struct p80211_hdr_a3 *) skb->data; - if (p80211_rx_typedrop(wlandev, hdr->fc)) + if (p80211_rx_typedrop(wlandev, le16_to_cpu(hdr->fc))) return CONV_TO_ETHER_SKIPPED; /* perform mcast filtering: allow my local address through but reject diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index bd810c109277..1ff1c83e2df5 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -418,6 +418,7 @@ int iscsit_reset_np_thread( return 0; } np->np_thread_state = ISCSI_NP_THREAD_RESET; + atomic_inc(&np->np_reset_count); if (np->np_thread) { spin_unlock_bh(&np->np_thread_lock); @@ -1112,6 +1113,18 @@ iscsit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr, */ if (dump_payload) goto after_immediate_data; + /* + * Check for underflow case where both EDTL and immediate data payload + * exceeds what is presented by CDB's TRANSFER LENGTH, and what has + * already been set in target_cmd_size_check() as se_cmd->data_length. + * + * For this special case, fail the command and dump the immediate data + * payload. + */ + if (cmd->first_burst_len > cmd->se_cmd.data_length) { + cmd->sense_reason = TCM_INVALID_CDB_FIELD; + goto after_immediate_data; + } immed_ret = iscsit_handle_immediate_data(cmd, hdr, cmd->first_burst_len); @@ -1984,6 +1997,7 @@ iscsit_setup_text_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, cmd->cmd_sn = be32_to_cpu(hdr->cmdsn); cmd->exp_stat_sn = be32_to_cpu(hdr->exp_statsn); cmd->data_direction = DMA_NONE; + kfree(cmd->text_in_ptr); cmd->text_in_ptr = NULL; return 0; @@ -3436,7 +3450,7 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, if ((tpg->tpg_attrib.generate_node_acls == 0) && (tpg->tpg_attrib.demo_mode_discovery == 0) && - (!core_tpg_get_initiator_node_acl(&tpg->tpg_se_tpg, + (!target_tpg_has_node_acl(&tpg->tpg_se_tpg, cmd->conn->sess->sess_ops->InitiatorName))) { continue; } @@ -3953,6 +3967,8 @@ int iscsi_target_tx_thread(void *arg) { int ret = 0; struct iscsi_conn *conn = arg; + bool conn_freed = false; + /* * Allow ourselves to be interrupted by SIGINT so that a * connection recovery / failure event can be triggered externally. @@ -3978,12 +3994,14 @@ get_immediate: goto transport_err; ret = iscsit_handle_response_queue(conn); - if (ret == 1) + if (ret == 1) { goto get_immediate; - else if (ret == -ECONNRESET) + } else if (ret == -ECONNRESET) { + conn_freed = true; goto out; - else if (ret < 0) + } else if (ret < 0) { goto transport_err; + } } transport_err: @@ -3993,8 +4011,13 @@ transport_err: * responsible for cleaning up the early connection failure. */ if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN) - iscsit_take_action_for_connection_exit(conn); + iscsit_take_action_for_connection_exit(conn, &conn_freed); out: + if (!conn_freed) { + while (!kthread_should_stop()) { + msleep(100); + } + } return 0; } @@ -4093,6 +4116,7 @@ int iscsi_target_rx_thread(void *arg) u32 checksum = 0, digest = 0; struct iscsi_conn *conn = arg; struct kvec iov; + bool conn_freed = false; /* * Allow ourselves to be interrupted by SIGINT so that a * connection recovery / failure event can be triggered externally. @@ -4104,7 +4128,7 @@ int iscsi_target_rx_thread(void *arg) */ rc = wait_for_completion_interruptible(&conn->rx_login_comp); if (rc < 0 || iscsi_target_check_conn_state(conn)) - return 0; + goto out; if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) { struct completion comp; @@ -4189,7 +4213,13 @@ int iscsi_target_rx_thread(void *arg) transport_err: if (!signal_pending(current)) atomic_set(&conn->transport_failed, 1); - iscsit_take_action_for_connection_exit(conn); + iscsit_take_action_for_connection_exit(conn, &conn_freed); +out: + if (!conn_freed) { + while (!kthread_should_stop()) { + msleep(100); + } + } return 0; } @@ -4563,8 +4593,11 @@ static void iscsit_logout_post_handler_closesession( * always sleep waiting for RX/TX thread shutdown to complete * within iscsit_close_connection(). */ - if (conn->conn_transport->transport_type == ISCSI_TCP) + if (conn->conn_transport->transport_type == ISCSI_TCP) { sleep = cmpxchg(&conn->tx_thread_active, true, false); + if (!sleep) + return; + } atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); @@ -4580,8 +4613,11 @@ static void iscsit_logout_post_handler_samecid( { int sleep = 1; - if (conn->conn_transport->transport_type == ISCSI_TCP) + if (conn->conn_transport->transport_type == ISCSI_TCP) { sleep = cmpxchg(&conn->tx_thread_active, true, false); + if (!sleep) + return; + } atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); @@ -4821,6 +4857,7 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force) continue; } atomic_set(&sess->session_reinstatement, 1); + atomic_set(&sess->session_fall_back_to_erl0, 1); spin_unlock(&sess->conn_lock); list_move_tail(&se_sess->sess_list, &free_list); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index b4bfd706ac94..634ad3662ed6 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -725,11 +725,8 @@ static ssize_t lio_target_nacl_cmdsn_depth_store(struct config_item *item, if (iscsit_get_tpg(tpg) < 0) return -EINVAL; - /* - * iscsit_tpg_set_initiator_node_queue_depth() assumes force=1 - */ - ret = iscsit_tpg_set_initiator_node_queue_depth(tpg, - config_item_name(acl_ci), cmdsn_depth, 1); + + ret = core_tpg_set_initiator_node_queue_depth(se_nacl, cmdsn_depth); pr_debug("LIO_Target_ConfigFS: %s/%s Set CmdSN Window: %u for" "InitiatorName: %s\n", config_item_name(wwn_ci), @@ -871,6 +868,7 @@ DEF_TPG_ATTRIB(default_erl); DEF_TPG_ATTRIB(t10_pi); DEF_TPG_ATTRIB(fabric_prot_type); DEF_TPG_ATTRIB(tpg_enabled_sendtargets); +DEF_TPG_ATTRIB(login_keys_workaround); static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_attr_authentication, @@ -886,6 +884,7 @@ static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_attr_t10_pi, &iscsi_tpg_attrib_attr_fabric_prot_type, &iscsi_tpg_attrib_attr_tpg_enabled_sendtargets, + &iscsi_tpg_attrib_attr_login_keys_workaround, NULL, }; @@ -1593,42 +1592,31 @@ static int lio_tpg_check_prot_fabric_only( } /* - * Called with spin_lock_irq(struct se_portal_group->session_lock) held - * or not held. - * - * Also, this function calls iscsit_inc_session_usage_count() on the + * This function calls iscsit_inc_session_usage_count() on the * struct iscsi_session in question. */ static int lio_tpg_shutdown_session(struct se_session *se_sess) { struct iscsi_session *sess = se_sess->fabric_sess_ptr; - struct se_portal_group *se_tpg = se_sess->se_tpg; - bool local_lock = false; - - if (!spin_is_locked(&se_tpg->session_lock)) { - spin_lock_irq(&se_tpg->session_lock); - local_lock = true; - } + struct se_portal_group *se_tpg = &sess->tpg->tpg_se_tpg; + spin_lock_bh(&se_tpg->session_lock); spin_lock(&sess->conn_lock); if (atomic_read(&sess->session_fall_back_to_erl0) || atomic_read(&sess->session_logout) || (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) { spin_unlock(&sess->conn_lock); - if (local_lock) - spin_unlock_irq(&sess->conn_lock); + spin_unlock_bh(&se_tpg->session_lock); return 0; } atomic_set(&sess->session_reinstatement, 1); + atomic_set(&sess->session_fall_back_to_erl0, 1); spin_unlock(&sess->conn_lock); iscsit_stop_time2retain_timer(sess); - spin_unlock_irq(&se_tpg->session_lock); + spin_unlock_bh(&se_tpg->session_lock); iscsit_stop_session(sess, 1, 1); - if (!local_lock) - spin_lock_irq(&se_tpg->session_lock); - return 1; } diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c index 210f6e4830e3..6c88fb021444 100644 --- a/drivers/target/iscsi/iscsi_target_erl0.c +++ b/drivers/target/iscsi/iscsi_target_erl0.c @@ -930,8 +930,10 @@ static void iscsit_handle_connection_cleanup(struct iscsi_conn *conn) } } -void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn) +void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn, bool *conn_freed) { + *conn_freed = false; + spin_lock_bh(&conn->state_lock); if (atomic_read(&conn->connection_exit)) { spin_unlock_bh(&conn->state_lock); @@ -942,6 +944,7 @@ void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn) if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) { spin_unlock_bh(&conn->state_lock); iscsit_close_connection(conn); + *conn_freed = true; return; } @@ -955,4 +958,5 @@ void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn) spin_unlock_bh(&conn->state_lock); iscsit_handle_connection_cleanup(conn); + *conn_freed = true; } diff --git a/drivers/target/iscsi/iscsi_target_erl0.h b/drivers/target/iscsi/iscsi_target_erl0.h index a9e2f9497fb2..fbc1d84a63c3 100644 --- a/drivers/target/iscsi/iscsi_target_erl0.h +++ b/drivers/target/iscsi/iscsi_target_erl0.h @@ -9,6 +9,6 @@ extern int iscsit_stop_time2retain_timer(struct iscsi_session *); extern void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *); extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int); extern void iscsit_fall_back_to_erl0(struct iscsi_session *); -extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *); +extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *, bool *); #endif /*** ISCSI_TARGET_ERL0_H ***/ diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 316f66172335..bc2cbffec27e 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -195,6 +195,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn) initiatorname_param->value) && (sess_p->sess_ops->SessionType == sessiontype))) { atomic_set(&sess_p->session_reinstatement, 1); + atomic_set(&sess_p->session_fall_back_to_erl0, 1); spin_unlock(&sess_p->conn_lock); iscsit_inc_session_usage_count(sess_p); iscsit_stop_time2retain_timer(sess_p); @@ -1218,9 +1219,11 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) flush_signals(current); spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (atomic_dec_if_positive(&np->np_reset_count) >= 0) { np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; + spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); + return 1; } else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) { spin_unlock_bh(&np->np_thread_lock); goto exit; @@ -1253,7 +1256,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) goto exit; } else if (rc < 0) { spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (atomic_dec_if_positive(&np->np_reset_count) >= 0) { + np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); iscsit_put_transport(conn->conn_transport); @@ -1435,5 +1439,9 @@ int iscsi_target_login_thread(void *arg) break; } + while (!kthread_should_stop()) { + msleep(100); + } + return 0; } diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 9fc9117d0f22..58c629aec73c 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -489,14 +489,60 @@ static void iscsi_target_restore_sock_callbacks(struct iscsi_conn *conn) static int iscsi_target_do_login(struct iscsi_conn *, struct iscsi_login *); -static bool iscsi_target_sk_state_check(struct sock *sk) +static bool __iscsi_target_sk_check_close(struct sock *sk) { if (sk->sk_state == TCP_CLOSE_WAIT || sk->sk_state == TCP_CLOSE) { - pr_debug("iscsi_target_sk_state_check: TCP_CLOSE_WAIT|TCP_CLOSE," + pr_debug("__iscsi_target_sk_check_close: TCP_CLOSE_WAIT|TCP_CLOSE," "returning FALSE\n"); - return false; + return true; } - return true; + return false; +} + +static bool iscsi_target_sk_check_close(struct iscsi_conn *conn) +{ + bool state = false; + + if (conn->sock) { + struct sock *sk = conn->sock->sk; + + read_lock_bh(&sk->sk_callback_lock); + state = (__iscsi_target_sk_check_close(sk) || + test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)); + read_unlock_bh(&sk->sk_callback_lock); + } + return state; +} + +static bool iscsi_target_sk_check_flag(struct iscsi_conn *conn, unsigned int flag) +{ + bool state = false; + + if (conn->sock) { + struct sock *sk = conn->sock->sk; + + read_lock_bh(&sk->sk_callback_lock); + state = test_bit(flag, &conn->login_flags); + read_unlock_bh(&sk->sk_callback_lock); + } + return state; +} + +static bool iscsi_target_sk_check_and_clear(struct iscsi_conn *conn, unsigned int flag) +{ + bool state = false; + + if (conn->sock) { + struct sock *sk = conn->sock->sk; + + write_lock_bh(&sk->sk_callback_lock); + state = (__iscsi_target_sk_check_close(sk) || + test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)); + if (!state) + clear_bit(flag, &conn->login_flags); + write_unlock_bh(&sk->sk_callback_lock); + } + return state; } static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login) @@ -536,6 +582,20 @@ static void iscsi_target_do_login_rx(struct work_struct *work) pr_debug("entering iscsi_target_do_login_rx, conn: %p, %s:%d\n", conn, current->comm, current->pid); + /* + * If iscsi_target_do_login_rx() has been invoked by ->sk_data_ready() + * before initial PDU processing in iscsi_target_start_negotiation() + * has completed, go ahead and retry until it's cleared. + * + * Otherwise if the TCP connection drops while this is occuring, + * iscsi_target_start_negotiation() will detect the failure, call + * cancel_delayed_work_sync(&conn->login_work), and cleanup the + * remaining iscsi connection resources from iscsi_np process context. + */ + if (iscsi_target_sk_check_flag(conn, LOGIN_FLAGS_INITIAL_PDU)) { + schedule_delayed_work(&conn->login_work, msecs_to_jiffies(10)); + return; + } spin_lock(&tpg->tpg_state_lock); state = (tpg->tpg_state == TPG_STATE_ACTIVE); @@ -543,26 +603,12 @@ static void iscsi_target_do_login_rx(struct work_struct *work) if (!state) { pr_debug("iscsi_target_do_login_rx: tpg_state != TPG_STATE_ACTIVE\n"); - iscsi_target_restore_sock_callbacks(conn); - iscsi_target_login_drop(conn, login); - iscsit_deaccess_np(np, tpg, tpg_np); - return; + goto err; } - if (conn->sock) { - struct sock *sk = conn->sock->sk; - - read_lock_bh(&sk->sk_callback_lock); - state = iscsi_target_sk_state_check(sk); - read_unlock_bh(&sk->sk_callback_lock); - - if (!state) { - pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n"); - iscsi_target_restore_sock_callbacks(conn); - iscsi_target_login_drop(conn, login); - iscsit_deaccess_np(np, tpg, tpg_np); - return; - } + if (iscsi_target_sk_check_close(conn)) { + pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n"); + goto err; } conn->login_kworker = current; @@ -580,34 +626,29 @@ static void iscsi_target_do_login_rx(struct work_struct *work) flush_signals(current); conn->login_kworker = NULL; - if (rc < 0) { - iscsi_target_restore_sock_callbacks(conn); - iscsi_target_login_drop(conn, login); - iscsit_deaccess_np(np, tpg, tpg_np); - return; - } + if (rc < 0) + goto err; pr_debug("iscsi_target_do_login_rx after rx_login_io, %p, %s:%d\n", conn, current->comm, current->pid); rc = iscsi_target_do_login(conn, login); if (rc < 0) { - iscsi_target_restore_sock_callbacks(conn); - iscsi_target_login_drop(conn, login); - iscsit_deaccess_np(np, tpg, tpg_np); + goto err; } else if (!rc) { - if (conn->sock) { - struct sock *sk = conn->sock->sk; - - write_lock_bh(&sk->sk_callback_lock); - clear_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags); - write_unlock_bh(&sk->sk_callback_lock); - } + if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_READ_ACTIVE)) + goto err; } else if (rc == 1) { iscsi_target_nego_release(conn); iscsi_post_login_handler(np, conn, zero_tsih); iscsit_deaccess_np(np, tpg, tpg_np); } + return; + +err: + iscsi_target_restore_sock_callbacks(conn); + iscsi_target_login_drop(conn, login); + iscsit_deaccess_np(np, tpg, tpg_np); } static void iscsi_target_do_cleanup(struct work_struct *work) @@ -655,31 +696,54 @@ static void iscsi_target_sk_state_change(struct sock *sk) orig_state_change(sk); return; } + state = __iscsi_target_sk_check_close(sk); + pr_debug("__iscsi_target_sk_close_change: state: %d\n", state); + if (test_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags)) { pr_debug("Got LOGIN_FLAGS_READ_ACTIVE=1 sk_state_change" " conn: %p\n", conn); + if (state) + set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags); write_unlock_bh(&sk->sk_callback_lock); orig_state_change(sk); return; } - if (test_and_set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) { + if (test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) { pr_debug("Got LOGIN_FLAGS_CLOSED=1 sk_state_change conn: %p\n", conn); write_unlock_bh(&sk->sk_callback_lock); orig_state_change(sk); return; } + /* + * If the TCP connection has dropped, go ahead and set LOGIN_FLAGS_CLOSED, + * but only queue conn->login_work -> iscsi_target_do_login_rx() + * processing if LOGIN_FLAGS_INITIAL_PDU has already been cleared. + * + * When iscsi_target_do_login_rx() runs, iscsi_target_sk_check_close() + * will detect the dropped TCP connection from delayed workqueue context. + * + * If LOGIN_FLAGS_INITIAL_PDU is still set, which means the initial + * iscsi_target_start_negotiation() is running, iscsi_target_do_login() + * via iscsi_target_sk_check_close() or iscsi_target_start_negotiation() + * via iscsi_target_sk_check_and_clear() is responsible for detecting the + * dropped TCP connection in iscsi_np process context, and cleaning up + * the remaining iscsi connection resources. + */ + if (state) { + pr_debug("iscsi_target_sk_state_change got failed state\n"); + set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags); + state = test_bit(LOGIN_FLAGS_INITIAL_PDU, &conn->login_flags); + write_unlock_bh(&sk->sk_callback_lock); - state = iscsi_target_sk_state_check(sk); - write_unlock_bh(&sk->sk_callback_lock); - - pr_debug("iscsi_target_sk_state_change: state: %d\n", state); + orig_state_change(sk); - if (!state) { - pr_debug("iscsi_target_sk_state_change got failed state\n"); - schedule_delayed_work(&conn->login_cleanup_work, 0); + if (!state) + schedule_delayed_work(&conn->login_work, 0); return; } + write_unlock_bh(&sk->sk_callback_lock); + orig_state_change(sk); } @@ -818,7 +882,8 @@ static int iscsi_target_handle_csg_zero( SENDER_TARGET, login->rsp_buf, &login->rsp_length, - conn->param_list); + conn->param_list, + conn->tpg->tpg_attrib.login_keys_workaround); if (ret < 0) return -1; @@ -888,7 +953,8 @@ static int iscsi_target_handle_csg_one(struct iscsi_conn *conn, struct iscsi_log SENDER_TARGET, login->rsp_buf, &login->rsp_length, - conn->param_list); + conn->param_list, + conn->tpg->tpg_attrib.login_keys_workaround); if (ret < 0) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_INITIATOR_ERR, ISCSI_LOGIN_STATUS_INIT_ERR); @@ -942,6 +1008,15 @@ static int iscsi_target_do_login(struct iscsi_conn *conn, struct iscsi_login *lo if (iscsi_target_handle_csg_one(conn, login) < 0) return -1; if (login_rsp->flags & ISCSI_FLAG_LOGIN_TRANSIT) { + /* + * Check to make sure the TCP connection has not + * dropped asynchronously while session reinstatement + * was occuring in this kthread context, before + * transitioning to full feature phase operation. + */ + if (iscsi_target_sk_check_close(conn)) + return -1; + login->tsih = conn->sess->tsih; login->login_complete = 1; iscsi_target_restore_sock_callbacks(conn); @@ -968,21 +1043,6 @@ static int iscsi_target_do_login(struct iscsi_conn *conn, struct iscsi_login *lo break; } - if (conn->sock) { - struct sock *sk = conn->sock->sk; - bool state; - - read_lock_bh(&sk->sk_callback_lock); - state = iscsi_target_sk_state_check(sk); - read_unlock_bh(&sk->sk_callback_lock); - - if (!state) { - pr_debug("iscsi_target_do_login() failed state for" - " conn: %p\n", conn); - return -1; - } - } - return 0; } @@ -1246,16 +1306,28 @@ int iscsi_target_start_negotiation( { int ret; + if (conn->sock) { + struct sock *sk = conn->sock->sk; + + write_lock_bh(&sk->sk_callback_lock); + set_bit(LOGIN_FLAGS_READY, &conn->login_flags); + set_bit(LOGIN_FLAGS_INITIAL_PDU, &conn->login_flags); + write_unlock_bh(&sk->sk_callback_lock); + } + /* + * If iscsi_target_do_login returns zero to signal more PDU + * exchanges are required to complete the login, go ahead and + * clear LOGIN_FLAGS_INITIAL_PDU but only if the TCP connection + * is still active. + * + * Otherwise if TCP connection dropped asynchronously, go ahead + * and perform connection cleanup now. + */ ret = iscsi_target_do_login(conn, login); - if (!ret) { - if (conn->sock) { - struct sock *sk = conn->sock->sk; + if (!ret && iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU)) + ret = -1; - write_lock_bh(&sk->sk_callback_lock); - set_bit(LOGIN_FLAGS_READY, &conn->login_flags); - write_unlock_bh(&sk->sk_callback_lock); - } - } else if (ret < 0) { + if (ret < 0) { cancel_delayed_work_sync(&conn->login_work); cancel_delayed_work_sync(&conn->login_cleanup_work); iscsi_target_restore_sock_callbacks(conn); diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index 2cbea2af7cd0..76bde76edad1 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -764,7 +764,8 @@ static int iscsi_check_for_auth_key(char *key) return 0; } -static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param) +static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param, + bool keys_workaround) { if (IS_TYPE_BOOL_AND(param)) { if (!strcmp(param->value, NO)) @@ -772,35 +773,31 @@ static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param) } else if (IS_TYPE_BOOL_OR(param)) { if (!strcmp(param->value, YES)) SET_PSTATE_REPLY_OPTIONAL(param); - /* - * Required for gPXE iSCSI boot client - */ - if (!strcmp(param->name, IMMEDIATEDATA)) - SET_PSTATE_REPLY_OPTIONAL(param); + + if (keys_workaround) { + /* + * Required for gPXE iSCSI boot client + */ + if (!strcmp(param->name, IMMEDIATEDATA)) + SET_PSTATE_REPLY_OPTIONAL(param); + } } else if (IS_TYPE_NUMBER(param)) { if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH)) SET_PSTATE_REPLY_OPTIONAL(param); - /* - * The GlobalSAN iSCSI Initiator for MacOSX does - * not respond to MaxBurstLength, FirstBurstLength, - * DefaultTime2Wait or DefaultTime2Retain parameter keys. - * So, we set them to 'reply optional' here, and assume the - * the defaults from iscsi_parameters.h if the initiator - * is not RFC compliant and the keys are not negotiated. - */ - if (!strcmp(param->name, MAXBURSTLENGTH)) - SET_PSTATE_REPLY_OPTIONAL(param); - if (!strcmp(param->name, FIRSTBURSTLENGTH)) - SET_PSTATE_REPLY_OPTIONAL(param); - if (!strcmp(param->name, DEFAULTTIME2WAIT)) - SET_PSTATE_REPLY_OPTIONAL(param); - if (!strcmp(param->name, DEFAULTTIME2RETAIN)) - SET_PSTATE_REPLY_OPTIONAL(param); - /* - * Required for gPXE iSCSI boot client - */ - if (!strcmp(param->name, MAXCONNECTIONS)) - SET_PSTATE_REPLY_OPTIONAL(param); + + if (keys_workaround) { + /* + * Required for Mellanox Flexboot PXE boot ROM + */ + if (!strcmp(param->name, FIRSTBURSTLENGTH)) + SET_PSTATE_REPLY_OPTIONAL(param); + + /* + * Required for gPXE iSCSI boot client + */ + if (!strcmp(param->name, MAXCONNECTIONS)) + SET_PSTATE_REPLY_OPTIONAL(param); + } } else if (IS_PHASE_DECLARATIVE(param)) SET_PSTATE_REPLY_OPTIONAL(param); } @@ -1437,7 +1434,8 @@ int iscsi_encode_text_output( u8 sender, char *textbuf, u32 *length, - struct iscsi_param_list *param_list) + struct iscsi_param_list *param_list, + bool keys_workaround) { char *output_buf = NULL; struct iscsi_extra_response *er; @@ -1473,7 +1471,8 @@ int iscsi_encode_text_output( *length += 1; output_buf = textbuf + *length; SET_PSTATE_PROPOSER(param); - iscsi_check_proposer_for_optional_reply(param); + iscsi_check_proposer_for_optional_reply(param, + keys_workaround); pr_debug("Sending key: %s=%s\n", param->name, param->value); } diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h index a0751e3f0813..17a58c2913f2 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.h +++ b/drivers/target/iscsi/iscsi_target_parameters.h @@ -40,7 +40,7 @@ extern int iscsi_extract_key_value(char *, char **, char **); extern int iscsi_update_param_value(struct iscsi_param *, char *); extern int iscsi_decode_text_input(u8, u8, char *, u32, struct iscsi_conn *); extern int iscsi_encode_text_output(u8, u8, char *, u32 *, - struct iscsi_param_list *); + struct iscsi_param_list *, bool); extern int iscsi_check_negotiated_keys(struct iscsi_param_list *); extern void iscsi_set_connection_parameters(struct iscsi_conn_ops *, struct iscsi_param_list *); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 68261b7dcefe..63e1dcc5914d 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -227,6 +227,7 @@ static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg) a->t10_pi = TA_DEFAULT_T10_PI; a->fabric_prot_type = TA_DEFAULT_FABRIC_PROT_TYPE; a->tpg_enabled_sendtargets = TA_DEFAULT_TPG_ENABLED_SENDTARGETS; + a->login_keys_workaround = TA_DEFAULT_LOGIN_KEYS_WORKAROUND; } int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_group *tpg) @@ -589,16 +590,6 @@ int iscsit_tpg_del_network_portal( return iscsit_tpg_release_np(tpg_np, tpg, np); } -int iscsit_tpg_set_initiator_node_queue_depth( - struct iscsi_portal_group *tpg, - unsigned char *initiatorname, - u32 queue_depth, - int force) -{ - return core_tpg_set_initiator_node_queue_depth(&tpg->tpg_se_tpg, - initiatorname, queue_depth, force); -} - int iscsit_ta_authentication(struct iscsi_portal_group *tpg, u32 authentication) { unsigned char buf1[256], buf2[256], *none = NULL; @@ -909,3 +900,21 @@ int iscsit_ta_tpg_enabled_sendtargets( return 0; } + +int iscsit_ta_login_keys_workaround( + struct iscsi_portal_group *tpg, + u32 flag) +{ + struct iscsi_tpg_attrib *a = &tpg->tpg_attrib; + + if ((flag != 0) && (flag != 1)) { + pr_err("Illegal value %d\n", flag); + return -EINVAL; + } + + a->login_keys_workaround = flag; + pr_debug("iSCSI_TPG[%hu] - TPG enabled bit for login keys workaround: %s ", + tpg->tpgt, (a->login_keys_workaround) ? "ON" : "OFF"); + + return 0; +} diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index 9db32bd24cd4..901a712180f0 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -26,8 +26,6 @@ extern struct iscsi_tpg_np *iscsit_tpg_add_network_portal(struct iscsi_portal_gr int); extern int iscsit_tpg_del_network_portal(struct iscsi_portal_group *, struct iscsi_tpg_np *); -extern int iscsit_tpg_set_initiator_node_queue_depth(struct iscsi_portal_group *, - unsigned char *, u32, int); extern int iscsit_ta_authentication(struct iscsi_portal_group *, u32); extern int iscsit_ta_login_timeout(struct iscsi_portal_group *, u32); extern int iscsit_ta_netif_timeout(struct iscsi_portal_group *, u32); @@ -41,5 +39,6 @@ extern int iscsit_ta_default_erl(struct iscsi_portal_group *, u32); extern int iscsit_ta_t10_pi(struct iscsi_portal_group *, u32); extern int iscsit_ta_fabric_prot_type(struct iscsi_portal_group *, u32); extern int iscsit_ta_tpg_enabled_sendtargets(struct iscsi_portal_group *, u32); +extern int iscsit_ta_login_keys_workaround(struct iscsi_portal_group *, u32); #endif /* ISCSI_TARGET_TPG_H */ diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 428b0d9e3dba..93590521ae33 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -731,21 +731,23 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) { struct se_cmd *se_cmd = NULL; int rc; + bool op_scsi = false; /* * Determine if a struct se_cmd is associated with * this struct iscsi_cmd. */ switch (cmd->iscsi_opcode) { case ISCSI_OP_SCSI_CMD: - se_cmd = &cmd->se_cmd; - __iscsit_free_cmd(cmd, true, shutdown); + op_scsi = true; /* * Fallthrough */ case ISCSI_OP_SCSI_TMFUNC: - rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown); - if (!rc && shutdown && se_cmd && se_cmd->se_sess) { - __iscsit_free_cmd(cmd, true, shutdown); + se_cmd = &cmd->se_cmd; + __iscsit_free_cmd(cmd, op_scsi, shutdown); + rc = transport_generic_free_cmd(se_cmd, shutdown); + if (!rc && shutdown && se_cmd->se_sess) { + __iscsit_free_cmd(cmd, op_scsi, shutdown); target_put_sess_cmd(se_cmd); } break; diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index dcd5ed26eb18..bb6a6c35324a 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -77,12 +77,16 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun) &deve->read_bytes); se_lun = rcu_dereference(deve->se_lun); + + if (!percpu_ref_tryget_live(&se_lun->lun_ref)) { + se_lun = NULL; + goto out_unlock; + } + se_cmd->se_lun = rcu_dereference(deve->se_lun); se_cmd->pr_res_key = deve->pr_res_key; se_cmd->orig_fe_lun = unpacked_lun; se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD; - - percpu_ref_get(&se_lun->lun_ref); se_cmd->lun_ref_active = true; if ((se_cmd->data_direction == DMA_TO_DEVICE) && @@ -96,6 +100,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun) goto ref_dev; } } +out_unlock: rcu_read_unlock(); if (!se_lun) { @@ -362,7 +367,15 @@ int core_enable_device_list_for_node( kfree(new); return -EINVAL; } - BUG_ON(orig->se_lun_acl != NULL); + if (orig->se_lun_acl != NULL) { + pr_warn_ratelimited("Detected existing explicit" + " se_lun_acl->se_lun_group reference for %s" + " mapped_lun: %llu, failing\n", + nacl->initiatorname, mapped_lun); + mutex_unlock(&nacl->lun_entry_mutex); + kfree(new); + return -EINVAL; + } rcu_assign_pointer(new->se_lun, lun); rcu_assign_pointer(new->se_lun_acl, lun_acl); @@ -818,6 +831,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) xcopy_lun = &dev->xcopy_lun; rcu_assign_pointer(xcopy_lun->lun_se_dev, dev); init_completion(&xcopy_lun->lun_ref_comp); + init_completion(&xcopy_lun->lun_shutdown_comp); INIT_LIST_HEAD(&xcopy_lun->lun_deve_list); INIT_LIST_HEAD(&xcopy_lun->lun_dev_link); mutex_init(&xcopy_lun->lun_tg_pt_md_mutex); diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index f916d18ccb48..b070ddf1dc37 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -92,6 +92,11 @@ static int target_fabric_mappedlun_link( pr_err("Source se_lun->lun_se_dev does not exist\n"); return -EINVAL; } + if (lun->lun_shutdown) { + pr_err("Unable to create mappedlun symlink because" + " lun->lun_shutdown=true\n"); + return -EINVAL; + } se_tpg = lun->lun_tpg; nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item; diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 79291869bce6..041a56987845 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -594,8 +594,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (ret < 0) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - if (ret) - target_complete_cmd(cmd, SAM_STAT_GOOD); + target_complete_cmd(cmd, SAM_STAT_GOOD); return 0; } diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 253a91bff943..272e6f755322 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -132,7 +132,7 @@ int init_se_kmem_caches(void); void release_se_kmem_caches(void); u32 scsi_get_new_index(scsi_index_t); void transport_subsystem_check_init(void); -void transport_cmd_finish_abort(struct se_cmd *, int); +int transport_cmd_finish_abort(struct se_cmd *, int); unsigned char *transport_dump_cmd_direction(struct se_cmd *); void transport_dump_dev_state(struct se_device *, char *, int *); void transport_dump_dev_info(struct se_device *, struct se_lun *, diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index de18790eb21c..d72a4058fd08 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -154,7 +154,7 @@ static void pscsi_tape_read_blocksize(struct se_device *dev, buf = kzalloc(12, GFP_KERNEL); if (!buf) - return; + goto out_free; memset(cdb, 0, MAX_COMMAND_SIZE); cdb[0] = MODE_SENSE; @@ -169,9 +169,10 @@ static void pscsi_tape_read_blocksize(struct se_device *dev, * If MODE_SENSE still returns zero, set the default value to 1024. */ sdev->sector_size = (buf[9] << 16) | (buf[10] << 8) | (buf[11]); +out_free: if (!sdev->sector_size) sdev->sector_size = 1024; -out_free: + kfree(buf); } @@ -314,9 +315,10 @@ static int pscsi_add_device_to_list(struct se_device *dev, sd->lun, sd->queue_depth); } - dev->dev_attrib.hw_block_size = sd->sector_size; + dev->dev_attrib.hw_block_size = + min_not_zero((int)sd->sector_size, 512); dev->dev_attrib.hw_max_sectors = - min_t(int, sd->host->max_sectors, queue_max_hw_sectors(q)); + min_not_zero(sd->host->max_sectors, queue_max_hw_sectors(q)); dev->dev_attrib.hw_queue_depth = sd->queue_depth; /* @@ -339,8 +341,10 @@ static int pscsi_add_device_to_list(struct se_device *dev, /* * For TYPE_TAPE, attempt to determine blocksize with MODE_SENSE. */ - if (sd->type == TYPE_TAPE) + if (sd->type == TYPE_TAPE) { pscsi_tape_read_blocksize(dev, sd); + dev->dev_attrib.hw_block_size = sd->sector_size; + } return 0; } @@ -406,7 +410,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) /* * Called with struct Scsi_Host->host_lock called. */ -static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd) +static int pscsi_create_type_nondisk(struct se_device *dev, struct scsi_device *sd) __releases(sh->host_lock) { struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr; @@ -433,28 +437,6 @@ static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd) return 0; } -/* - * Called with struct Scsi_Host->host_lock called. - */ -static int pscsi_create_type_other(struct se_device *dev, - struct scsi_device *sd) - __releases(sh->host_lock) -{ - struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr; - struct Scsi_Host *sh = sd->host; - int ret; - - spin_unlock_irq(sh->host_lock); - ret = pscsi_add_device_to_list(dev, sd); - if (ret) - return ret; - - pr_debug("CORE_PSCSI[%d] - Added Type: %s for %d:%d:%d:%llu\n", - phv->phv_host_id, scsi_device_type(sd->type), sh->host_no, - sd->channel, sd->id, sd->lun); - return 0; -} - static int pscsi_configure_device(struct se_device *dev) { struct se_hba *hba = dev->se_hba; @@ -542,11 +524,8 @@ static int pscsi_configure_device(struct se_device *dev) case TYPE_DISK: ret = pscsi_create_type_disk(dev, sd); break; - case TYPE_ROM: - ret = pscsi_create_type_rom(dev, sd); - break; default: - ret = pscsi_create_type_other(dev, sd); + ret = pscsi_create_type_nondisk(dev, sd); break; } @@ -611,8 +590,7 @@ static void pscsi_free_device(struct se_device *dev) else if (pdv->pdv_lld_host) scsi_host_put(pdv->pdv_lld_host); - if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM)) - scsi_device_put(sd); + scsi_device_put(sd); pdv->pdv_sd = NULL; } @@ -1088,7 +1066,6 @@ static sector_t pscsi_get_blocks(struct se_device *dev) if (pdv->pdv_bd && pdv->pdv_bd->bd_part) return pdv->pdv_bd->bd_part->nr_sects; - dump_stack(); return 0; } diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index c220bb8dfa9d..608117819366 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -442,6 +442,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success, int *post_ret) { struct se_device *dev = cmd->se_dev; + sense_reason_t ret = TCM_NO_SENSE; /* * Only set SCF_COMPARE_AND_WRITE_POST to force a response fall-through @@ -449,9 +450,12 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success, * sent to the backend driver. */ spin_lock_irq(&cmd->t_state_lock); - if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status) { + if (cmd->transport_state & CMD_T_SENT) { cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST; *post_ret = 1; + + if (cmd->scsi_status == SAM_STAT_CHECK_CONDITION) + ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } spin_unlock_irq(&cmd->t_state_lock); @@ -461,7 +465,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success, */ up(&dev->caw_sem); - return TCM_NO_SENSE; + return ret; } static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success, @@ -494,8 +498,11 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool succes * been failed with a non-zero SCSI status. */ if (cmd->scsi_status) { - pr_err("compare_and_write_callback: non zero scsi_status:" + pr_debug("compare_and_write_callback: non zero scsi_status:" " 0x%02x\n", cmd->scsi_status); + *post_ret = 1; + if (cmd->scsi_status == SAM_STAT_CHECK_CONDITION) + ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; goto out; } @@ -1092,9 +1099,15 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) return ret; break; case VERIFY: + case VERIFY_16: size = 0; - sectors = transport_get_sectors_10(cdb); - cmd->t_task_lba = transport_lba_32(cdb); + if (cdb[0] == VERIFY) { + sectors = transport_get_sectors_10(cdb); + cmd->t_task_lba = transport_lba_32(cdb); + } else { + sectors = transport_get_sectors_16(cdb); + cmd->t_task_lba = transport_lba_64(cdb); + } cmd->execute_cmd = sbc_emulate_noop; goto check_lba; case REZERO_UNIT: diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 46b1991fbb50..c9be953496ec 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -75,7 +75,7 @@ void core_tmr_release_req(struct se_tmr_req *tmr) kfree(tmr); } -static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas) +static int core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas) { unsigned long flags; bool remove = true, send_tas; @@ -91,7 +91,7 @@ static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas) transport_send_task_abort(cmd); } - transport_cmd_finish_abort(cmd, remove); + return transport_cmd_finish_abort(cmd, remove); } static int target_check_cdb_and_preempt(struct list_head *list, @@ -185,8 +185,8 @@ void core_tmr_abort_task( cancel_work_sync(&se_cmd->work); transport_wait_for_tasks(se_cmd); - transport_cmd_finish_abort(se_cmd, true); - target_put_sess_cmd(se_cmd); + if (!transport_cmd_finish_abort(se_cmd, true)) + target_put_sess_cmd(se_cmd); printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for" " ref_tag: %llu\n", ref_tag); @@ -286,8 +286,8 @@ static void core_tmr_drain_tmr_list( cancel_work_sync(&cmd->work); transport_wait_for_tasks(cmd); - transport_cmd_finish_abort(cmd, 1); - target_put_sess_cmd(cmd); + if (!transport_cmd_finish_abort(cmd, 1)) + target_put_sess_cmd(cmd); } } @@ -385,8 +385,8 @@ static void core_tmr_drain_state_list( cancel_work_sync(&cmd->work); transport_wait_for_tasks(cmd); - core_tmr_handle_tas_abort(cmd, tas); - target_put_sess_cmd(cmd); + if (!core_tmr_handle_tas_abort(cmd, tas)) + target_put_sess_cmd(cmd); } } diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 5fb9dd7f08bb..f69f4902dc07 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -75,9 +75,21 @@ struct se_node_acl *core_tpg_get_initiator_node_acl( unsigned char *initiatorname) { struct se_node_acl *acl; - + /* + * Obtain se_node_acl->acl_kref using fabric driver provided + * initiatorname[] during node acl endpoint lookup driven by + * new se_session login. + * + * The reference is held until se_session shutdown -> release + * occurs via fabric driver invoked transport_deregister_session() + * or transport_free_session() code. + */ mutex_lock(&tpg->acl_node_mutex); acl = __core_tpg_get_initiator_node_acl(tpg, initiatorname); + if (acl) { + if (!kref_get_unless_zero(&acl->acl_kref)) + acl = NULL; + } mutex_unlock(&tpg->acl_node_mutex); return acl; @@ -157,28 +169,25 @@ void core_tpg_add_node_to_devs( mutex_unlock(&tpg->tpg_lun_mutex); } -/* core_set_queue_depth_for_node(): - * - * - */ -static int core_set_queue_depth_for_node( - struct se_portal_group *tpg, - struct se_node_acl *acl) +static void +target_set_nacl_queue_depth(struct se_portal_group *tpg, + struct se_node_acl *acl, u32 queue_depth) { + acl->queue_depth = queue_depth; + if (!acl->queue_depth) { - pr_err("Queue depth for %s Initiator Node: %s is 0," + pr_warn("Queue depth for %s Initiator Node: %s is 0," "defaulting to 1.\n", tpg->se_tpg_tfo->get_fabric_name(), acl->initiatorname); acl->queue_depth = 1; } - - return 0; } static struct se_node_acl *target_alloc_node_acl(struct se_portal_group *tpg, const unsigned char *initiatorname) { struct se_node_acl *acl; + u32 queue_depth; acl = kzalloc(max(sizeof(*acl), tpg->se_tpg_tfo->node_acl_size), GFP_KERNEL); @@ -193,24 +202,20 @@ static struct se_node_acl *target_alloc_node_acl(struct se_portal_group *tpg, spin_lock_init(&acl->nacl_sess_lock); mutex_init(&acl->lun_entry_mutex); atomic_set(&acl->acl_pr_ref_count, 0); + if (tpg->se_tpg_tfo->tpg_get_default_depth) - acl->queue_depth = tpg->se_tpg_tfo->tpg_get_default_depth(tpg); + queue_depth = tpg->se_tpg_tfo->tpg_get_default_depth(tpg); else - acl->queue_depth = 1; + queue_depth = 1; + target_set_nacl_queue_depth(tpg, acl, queue_depth); + snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname); acl->se_tpg = tpg; acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX); tpg->se_tpg_tfo->set_default_node_attributes(acl); - if (core_set_queue_depth_for_node(tpg, acl) < 0) - goto out_free_acl; - return acl; - -out_free_acl: - kfree(acl); - return NULL; } static void target_add_node_acl(struct se_node_acl *acl) @@ -232,6 +237,25 @@ static void target_add_node_acl(struct se_node_acl *acl) acl->initiatorname); } +bool target_tpg_has_node_acl(struct se_portal_group *tpg, + const char *initiatorname) +{ + struct se_node_acl *acl; + bool found = false; + + mutex_lock(&tpg->acl_node_mutex); + list_for_each_entry(acl, &tpg->acl_node_list, acl_list) { + if (!strcmp(acl->initiatorname, initiatorname)) { + found = true; + break; + } + } + mutex_unlock(&tpg->acl_node_mutex); + + return found; +} +EXPORT_SYMBOL(target_tpg_has_node_acl); + struct se_node_acl *core_tpg_check_initiator_node_acl( struct se_portal_group *tpg, unsigned char *initiatorname) @@ -248,6 +272,15 @@ struct se_node_acl *core_tpg_check_initiator_node_acl( acl = target_alloc_node_acl(tpg, initiatorname); if (!acl) return NULL; + /* + * When allocating a dynamically generated node_acl, go ahead + * and take the extra kref now before returning to the fabric + * driver caller. + * + * Note this reference will be released at session shutdown + * time within transport_free_session() code. + */ + kref_get(&acl->acl_kref); acl->dynamic_node_acl = 1; /* @@ -329,7 +362,8 @@ void core_tpg_del_initiator_node_acl(struct se_node_acl *acl) if (sess->sess_tearing_down != 0) continue; - target_get_session(sess); + if (!target_get_session(sess)) + continue; list_move(&sess->sess_acl_list, &sess_list); } spin_unlock_irqrestore(&acl->nacl_sess_lock, flags); @@ -366,108 +400,52 @@ void core_tpg_del_initiator_node_acl(struct se_node_acl *acl) * */ int core_tpg_set_initiator_node_queue_depth( - struct se_portal_group *tpg, - unsigned char *initiatorname, - u32 queue_depth, - int force) + struct se_node_acl *acl, + u32 queue_depth) { - struct se_session *sess, *init_sess = NULL; - struct se_node_acl *acl; + LIST_HEAD(sess_list); + struct se_portal_group *tpg = acl->se_tpg; + struct se_session *sess, *sess_tmp; unsigned long flags; - int dynamic_acl = 0; - - mutex_lock(&tpg->acl_node_mutex); - acl = __core_tpg_get_initiator_node_acl(tpg, initiatorname); - if (!acl) { - pr_err("Access Control List entry for %s Initiator" - " Node %s does not exists for TPG %hu, ignoring" - " request.\n", tpg->se_tpg_tfo->get_fabric_name(), - initiatorname, tpg->se_tpg_tfo->tpg_get_tag(tpg)); - mutex_unlock(&tpg->acl_node_mutex); - return -ENODEV; - } - if (acl->dynamic_node_acl) { - acl->dynamic_node_acl = 0; - dynamic_acl = 1; - } - mutex_unlock(&tpg->acl_node_mutex); - - spin_lock_irqsave(&tpg->session_lock, flags); - list_for_each_entry(sess, &tpg->tpg_sess_list, sess_list) { - if (sess->se_node_acl != acl) - continue; - - if (!force) { - pr_err("Unable to change queue depth for %s" - " Initiator Node: %s while session is" - " operational. To forcefully change the queue" - " depth and force session reinstatement" - " use the \"force=1\" parameter.\n", - tpg->se_tpg_tfo->get_fabric_name(), initiatorname); - spin_unlock_irqrestore(&tpg->session_lock, flags); - - mutex_lock(&tpg->acl_node_mutex); - if (dynamic_acl) - acl->dynamic_node_acl = 1; - mutex_unlock(&tpg->acl_node_mutex); - return -EEXIST; - } - /* - * Determine if the session needs to be closed by our context. - */ - if (!tpg->se_tpg_tfo->shutdown_session(sess)) - continue; - - init_sess = sess; - break; - } + int rc; /* * User has requested to change the queue depth for a Initiator Node. * Change the value in the Node's struct se_node_acl, and call - * core_set_queue_depth_for_node() to add the requested queue depth. - * - * Finally call tpg->se_tpg_tfo->close_session() to force session - * reinstatement to occur if there is an active session for the - * $FABRIC_MOD Initiator Node in question. + * target_set_nacl_queue_depth() to set the new queue depth. */ - acl->queue_depth = queue_depth; + target_set_nacl_queue_depth(tpg, acl, queue_depth); + + spin_lock_irqsave(&acl->nacl_sess_lock, flags); + list_for_each_entry_safe(sess, sess_tmp, &acl->acl_sess_list, + sess_acl_list) { + if (sess->sess_tearing_down != 0) + continue; + if (!target_get_session(sess)) + continue; + spin_unlock_irqrestore(&acl->nacl_sess_lock, flags); - if (core_set_queue_depth_for_node(tpg, acl) < 0) { - spin_unlock_irqrestore(&tpg->session_lock, flags); /* - * Force session reinstatement if - * core_set_queue_depth_for_node() failed, because we assume - * the $FABRIC_MOD has already the set session reinstatement - * bit from tpg->se_tpg_tfo->shutdown_session() called above. + * Finally call tpg->se_tpg_tfo->close_session() to force session + * reinstatement to occur if there is an active session for the + * $FABRIC_MOD Initiator Node in question. */ - if (init_sess) - tpg->se_tpg_tfo->close_session(init_sess); - - mutex_lock(&tpg->acl_node_mutex); - if (dynamic_acl) - acl->dynamic_node_acl = 1; - mutex_unlock(&tpg->acl_node_mutex); - return -EINVAL; + rc = tpg->se_tpg_tfo->shutdown_session(sess); + target_put_session(sess); + if (!rc) { + spin_lock_irqsave(&acl->nacl_sess_lock, flags); + continue; + } + target_put_session(sess); + spin_lock_irqsave(&acl->nacl_sess_lock, flags); } - spin_unlock_irqrestore(&tpg->session_lock, flags); - /* - * If the $FABRIC_MOD session for the Initiator Node ACL exists, - * forcefully shutdown the $FABRIC_MOD session/nexus. - */ - if (init_sess) - tpg->se_tpg_tfo->close_session(init_sess); + spin_unlock_irqrestore(&acl->nacl_sess_lock, flags); pr_debug("Successfully changed queue depth to: %d for Initiator" - " Node: %s on %s Target Portal Group: %u\n", queue_depth, - initiatorname, tpg->se_tpg_tfo->get_fabric_name(), + " Node: %s on %s Target Portal Group: %u\n", acl->queue_depth, + acl->initiatorname, tpg->se_tpg_tfo->get_fabric_name(), tpg->se_tpg_tfo->tpg_get_tag(tpg)); - mutex_lock(&tpg->acl_node_mutex); - if (dynamic_acl) - acl->dynamic_node_acl = 1; - mutex_unlock(&tpg->acl_node_mutex); - return 0; } EXPORT_SYMBOL(core_tpg_set_initiator_node_queue_depth); @@ -499,7 +477,7 @@ static void core_tpg_lun_ref_release(struct percpu_ref *ref) { struct se_lun *lun = container_of(ref, struct se_lun, lun_ref); - complete(&lun->lun_ref_comp); + complete(&lun->lun_shutdown_comp); } int core_tpg_register( @@ -626,6 +604,7 @@ struct se_lun *core_tpg_alloc_lun( lun->lun_link_magic = SE_LUN_LINK_MAGIC; atomic_set(&lun->lun_acl_count, 0); init_completion(&lun->lun_ref_comp); + init_completion(&lun->lun_shutdown_comp); INIT_LIST_HEAD(&lun->lun_deve_list); INIT_LIST_HEAD(&lun->lun_dev_link); atomic_set(&lun->lun_tg_pt_secondary_offline, 0); @@ -694,6 +673,8 @@ void core_tpg_remove_lun( */ struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev); + lun->lun_shutdown = true; + core_clear_lun_from_tpg(lun, tpg); /* * Wait for any active I/O references to percpu se_lun->lun_ref to @@ -715,6 +696,8 @@ void core_tpg_remove_lun( } if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) hlist_del_rcu(&lun->link); + + lun->lun_shutdown = false; mutex_unlock(&tpg->tpg_lun_mutex); percpu_ref_exit(&lun->lun_ref); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 2a67af4e2e13..f71bedea973a 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -341,7 +341,6 @@ void __transport_register_session( &buf[0], PR_REG_ISID_LEN); se_sess->sess_bin_isid = get_unaligned_be64(&buf[0]); } - kref_get(&se_nacl->acl_kref); spin_lock_irq(&se_nacl->nacl_sess_lock); /* @@ -384,9 +383,9 @@ static void target_release_session(struct kref *kref) se_tpg->se_tpg_tfo->close_session(se_sess); } -void target_get_session(struct se_session *se_sess) +int target_get_session(struct se_session *se_sess) { - kref_get(&se_sess->sess_kref); + return kref_get_unless_zero(&se_sess->sess_kref); } EXPORT_SYMBOL(target_get_session); @@ -424,14 +423,27 @@ static void target_complete_nacl(struct kref *kref) { struct se_node_acl *nacl = container_of(kref, struct se_node_acl, acl_kref); + struct se_portal_group *se_tpg = nacl->se_tpg; - complete(&nacl->acl_free_comp); + if (!nacl->dynamic_stop) { + complete(&nacl->acl_free_comp); + return; + } + + mutex_lock(&se_tpg->acl_node_mutex); + list_del(&nacl->acl_list); + mutex_unlock(&se_tpg->acl_node_mutex); + + core_tpg_wait_for_nacl_pr_ref(nacl); + core_free_device_list_for_node(nacl, se_tpg); + kfree(nacl); } void target_put_nacl(struct se_node_acl *nacl) { kref_put(&nacl->acl_kref, target_complete_nacl); } +EXPORT_SYMBOL(target_put_nacl); void transport_deregister_session_configfs(struct se_session *se_sess) { @@ -464,6 +476,42 @@ EXPORT_SYMBOL(transport_deregister_session_configfs); void transport_free_session(struct se_session *se_sess) { + struct se_node_acl *se_nacl = se_sess->se_node_acl; + + /* + * Drop the se_node_acl->nacl_kref obtained from within + * core_tpg_get_initiator_node_acl(). + */ + if (se_nacl) { + struct se_portal_group *se_tpg = se_nacl->se_tpg; + const struct target_core_fabric_ops *se_tfo = se_tpg->se_tpg_tfo; + unsigned long flags; + + se_sess->se_node_acl = NULL; + + /* + * Also determine if we need to drop the extra ->cmd_kref if + * it had been previously dynamically generated, and + * the endpoint is not caching dynamic ACLs. + */ + mutex_lock(&se_tpg->acl_node_mutex); + if (se_nacl->dynamic_node_acl && + !se_tfo->tpg_check_demo_mode_cache(se_tpg)) { + spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags); + if (list_empty(&se_nacl->acl_sess_list)) + se_nacl->dynamic_stop = true; + spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags); + + if (se_nacl->dynamic_stop) + list_del(&se_nacl->acl_list); + } + mutex_unlock(&se_tpg->acl_node_mutex); + + if (se_nacl->dynamic_stop) + target_put_nacl(se_nacl); + + target_put_nacl(se_nacl); + } if (se_sess->sess_cmd_map) { percpu_ida_destroy(&se_sess->sess_tag_pool); kvfree(se_sess->sess_cmd_map); @@ -475,16 +523,12 @@ EXPORT_SYMBOL(transport_free_session); void transport_deregister_session(struct se_session *se_sess) { struct se_portal_group *se_tpg = se_sess->se_tpg; - const struct target_core_fabric_ops *se_tfo; - struct se_node_acl *se_nacl; unsigned long flags; - bool comp_nacl = true, drop_nacl = false; if (!se_tpg) { transport_free_session(se_sess); return; } - se_tfo = se_tpg->se_tpg_tfo; spin_lock_irqsave(&se_tpg->session_lock, flags); list_del(&se_sess->sess_list); @@ -492,37 +536,16 @@ void transport_deregister_session(struct se_session *se_sess) se_sess->fabric_sess_ptr = NULL; spin_unlock_irqrestore(&se_tpg->session_lock, flags); - /* - * Determine if we need to do extra work for this initiator node's - * struct se_node_acl if it had been previously dynamically generated. - */ - se_nacl = se_sess->se_node_acl; - - mutex_lock(&se_tpg->acl_node_mutex); - if (se_nacl && se_nacl->dynamic_node_acl) { - if (!se_tfo->tpg_check_demo_mode_cache(se_tpg)) { - list_del(&se_nacl->acl_list); - se_tpg->num_node_acls--; - drop_nacl = true; - } - } - mutex_unlock(&se_tpg->acl_node_mutex); - - if (drop_nacl) { - core_tpg_wait_for_nacl_pr_ref(se_nacl); - core_free_device_list_for_node(se_nacl, se_tpg); - kfree(se_nacl); - comp_nacl = false; - } pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n", se_tpg->se_tpg_tfo->get_fabric_name()); /* * If last kref is dropping now for an explicit NodeACL, awake sleeping * ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group - * removal context. + * removal context from within transport_free_session() code. + * + * For dynamic ACL, target_put_nacl() uses target_complete_nacl() + * to release all remaining generate_node_acl=1 created ACL resources. */ - if (se_nacl && comp_nacl) - target_put_nacl(se_nacl); transport_free_session(se_sess); } @@ -616,9 +639,10 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd) percpu_ref_put(&lun->lun_ref); } -void transport_cmd_finish_abort(struct se_cmd *cmd, int remove) +int transport_cmd_finish_abort(struct se_cmd *cmd, int remove) { bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF); + int ret = 0; if (cmd->se_cmd_flags & SCF_SE_LUN_CMD) transport_lun_remove_cmd(cmd); @@ -630,9 +654,11 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove) cmd->se_tfo->aborted_task(cmd); if (transport_cmd_check_stop_to_fabric(cmd)) - return; + return 1; if (remove && ack_kref) - transport_put_cmd(cmd); + ret = transport_put_cmd(cmd); + + return ret; } static void target_complete_failure_work(struct work_struct *work) @@ -702,6 +728,15 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) if (cmd->transport_state & CMD_T_ABORTED || cmd->transport_state & CMD_T_STOP) { spin_unlock_irqrestore(&cmd->t_state_lock, flags); + /* + * If COMPARE_AND_WRITE was stopped by __transport_wait_for_tasks(), + * release se_device->caw_sem obtained by sbc_compare_and_write() + * since target_complete_ok_work() or target_complete_failure_work() + * won't be called to invoke the normal CAW completion callbacks. + */ + if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) { + up(&dev->caw_sem); + } complete_all(&cmd->t_transport_stop_comp); return; } else if (!success) { @@ -1131,15 +1166,28 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size) if (cmd->unknown_data_length) { cmd->data_length = size; } else if (size != cmd->data_length) { - pr_warn("TARGET_CORE[%s]: Expected Transfer Length:" + pr_warn_ratelimited("TARGET_CORE[%s]: Expected Transfer Length:" " %u does not match SCSI CDB Length: %u for SAM Opcode:" " 0x%02x\n", cmd->se_tfo->get_fabric_name(), cmd->data_length, size, cmd->t_task_cdb[0]); - if (cmd->data_direction == DMA_TO_DEVICE && - cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { - pr_err("Rejecting underflow/overflow WRITE data\n"); - return TCM_INVALID_CDB_FIELD; + if (cmd->data_direction == DMA_TO_DEVICE) { + if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { + pr_err_ratelimited("Rejecting underflow/overflow" + " for WRITE data CDB\n"); + return TCM_INVALID_CDB_FIELD; + } + /* + * Some fabric drivers like iscsi-target still expect to + * always reject overflow writes. Reject this case until + * full fabric driver level support for overflow writes + * is introduced tree-wide. + */ + if (size > cmd->data_length) { + pr_err_ratelimited("Rejecting overflow for" + " WRITE control CDB\n"); + return TCM_INVALID_CDB_FIELD; + } } /* * Reject READ_* or WRITE_* with overflow/underflow for @@ -2657,10 +2705,39 @@ void target_wait_for_sess_cmds(struct se_session *se_sess) } EXPORT_SYMBOL(target_wait_for_sess_cmds); +static void target_lun_confirm(struct percpu_ref *ref) +{ + struct se_lun *lun = container_of(ref, struct se_lun, lun_ref); + + complete(&lun->lun_ref_comp); +} + void transport_clear_lun_ref(struct se_lun *lun) { - percpu_ref_kill(&lun->lun_ref); + /* + * Mark the percpu-ref as DEAD, switch to atomic_t mode, drop + * the initial reference and schedule confirm kill to be + * executed after one full RCU grace period has completed. + */ + percpu_ref_kill_and_confirm(&lun->lun_ref, target_lun_confirm); + /* + * The first completion waits for percpu_ref_switch_to_atomic_rcu() + * to call target_lun_confirm after lun->lun_ref has been marked + * as __PERCPU_REF_DEAD on all CPUs, and switches to atomic_t + * mode so that percpu_ref_tryget_live() lookup of lun->lun_ref + * fails for all new incoming I/O. + */ wait_for_completion(&lun->lun_ref_comp); + /* + * The second completion waits for percpu_ref_put_many() to + * invoke ->release() after lun->lun_ref has switched to + * atomic_t mode, and lun->lun_ref.count has reached zero. + * + * At this point all target-core lun->lun_ref references have + * been dropped via transport_lun_remove_cmd(), and it's safe + * to proceed with the remaining LUN shutdown. + */ + wait_for_completion(&lun->lun_shutdown_comp); } static bool @@ -3058,7 +3135,6 @@ static void target_tmr_work(struct work_struct *work) spin_unlock_irqrestore(&cmd->t_state_lock, flags); goto check_stop; } - cmd->t_state = TRANSPORT_ISTATE_PROCESSING; spin_unlock_irqrestore(&cmd->t_state_lock, flags); cmd->se_tfo->queue_tm_rsp(cmd); @@ -3071,11 +3147,25 @@ int transport_generic_handle_tmr( struct se_cmd *cmd) { unsigned long flags; + bool aborted = false; spin_lock_irqsave(&cmd->t_state_lock, flags); - cmd->transport_state |= CMD_T_ACTIVE; + if (cmd->transport_state & CMD_T_ABORTED) { + aborted = true; + } else { + cmd->t_state = TRANSPORT_ISTATE_PROCESSING; + cmd->transport_state |= CMD_T_ACTIVE; + } spin_unlock_irqrestore(&cmd->t_state_lock, flags); + if (aborted) { + pr_warn_ratelimited("handle_tmr caught CMD_T_ABORTED TMR %d" + "ref_tag: %llu tag: %llu\n", cmd->se_tmr_req->function, + cmd->se_tmr_req->ref_task_tag, cmd->tag); + transport_cmd_check_stop_to_fabric(cmd); + return 0; + } + INIT_WORK(&cmd->work, target_tmr_work); queue_work(cmd->se_dev->tmr_wq, &cmd->work); return 0; diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 153a6f255b6d..6415e9b09a52 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -836,7 +836,7 @@ out: " CHECK_CONDITION -> sending response\n", rc); ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION; } - target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION); + target_complete_cmd(ec_cmd, ec_cmd->scsi_status); } sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 97fad0e2f90a..f7b7b404c990 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -25,12 +25,19 @@ struct optee_call_waiter { struct list_head list_node; struct completion c; - bool completed; }; static void optee_cq_wait_init(struct optee_call_queue *cq, struct optee_call_waiter *w) { + /* + * We're preparing to make a call to secure world. In case we can't + * allocate a thread in secure world we'll end up waiting in + * optee_cq_wait_for_completion(). + * + * Normally if there's no contention in secure world the call will + * complete and we can cleanup directly with optee_cq_wait_final(). + */ mutex_lock(&cq->mutex); /* @@ -39,7 +46,6 @@ static void optee_cq_wait_init(struct optee_call_queue *cq, * returns busy and another thread just exited and try to complete * someone. */ - w->completed = false; init_completion(&w->c); list_add_tail(&w->list_node, &cq->waiters); @@ -55,7 +61,6 @@ static void optee_cq_wait_for_completion(struct optee_call_queue *cq, /* Move to end of list to get out of the way for other waiters */ list_del(&w->list_node); - w->completed = false; reinit_completion(&w->c); list_add_tail(&w->list_node, &cq->waiters); @@ -67,9 +72,8 @@ static void optee_cq_complete_one(struct optee_call_queue *cq) struct optee_call_waiter *w; list_for_each_entry(w, &cq->waiters, list_node) { - if (!w->completed) { + if (!completion_done(&w->c)) { complete(&w->c); - w->completed = true; break; } } @@ -78,17 +82,26 @@ static void optee_cq_complete_one(struct optee_call_queue *cq) static void optee_cq_wait_final(struct optee_call_queue *cq, struct optee_call_waiter *w) { + /* + * We're done with the call to secure world. The thread in secure + * world that was used for this call is now available for some + * other task to use. + */ mutex_lock(&cq->mutex); /* Get out of the list */ list_del(&w->list_node); + /* Wake up one eventual waiting task */ optee_cq_complete_one(cq); + /* - * If we're completed we've got a completion that some other task - * could have used instead. + * If we're completed we've got a completion from another task that + * was just done with its call to secure world. Since yet another + * thread now is available in secure world wake up another eventual + * waiting task. */ - if (w->completed) + if (completion_done(&w->c)) optee_cq_complete_one(cq); mutex_unlock(&cq->mutex); @@ -206,7 +219,6 @@ int optee_open_session(struct tee_context *ctx, struct tee_shm *shm; struct optee_msg_arg *msg_arg; phys_addr_t msg_parg; - struct optee_msg_param *msg_param; struct optee_session *sess = NULL; /* +2 for the meta parameters added below */ @@ -216,21 +228,20 @@ int optee_open_session(struct tee_context *ctx, msg_arg->cmd = OPTEE_MSG_CMD_OPEN_SESSION; msg_arg->cancel_id = arg->cancel_id; - msg_param = OPTEE_MSG_GET_PARAMS(msg_arg); /* * Initialize and add the meta parameters needed when opening a * session. */ - msg_param[0].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT | - OPTEE_MSG_ATTR_META; - msg_param[1].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT | - OPTEE_MSG_ATTR_META; - memcpy(&msg_param[0].u.value, arg->uuid, sizeof(arg->uuid)); - memcpy(&msg_param[1].u.value, arg->uuid, sizeof(arg->clnt_uuid)); - msg_param[1].u.value.c = arg->clnt_login; - - rc = optee_to_msg_param(msg_param + 2, arg->num_params, param); + msg_arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT | + OPTEE_MSG_ATTR_META; + msg_arg->params[1].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT | + OPTEE_MSG_ATTR_META; + memcpy(&msg_arg->params[0].u.value, arg->uuid, sizeof(arg->uuid)); + memcpy(&msg_arg->params[1].u.value, arg->uuid, sizeof(arg->clnt_uuid)); + msg_arg->params[1].u.value.c = arg->clnt_login; + + rc = optee_to_msg_param(msg_arg->params + 2, arg->num_params, param); if (rc) goto out; @@ -255,7 +266,7 @@ int optee_open_session(struct tee_context *ctx, kfree(sess); } - if (optee_from_msg_param(param, arg->num_params, msg_param + 2)) { + if (optee_from_msg_param(param, arg->num_params, msg_arg->params + 2)) { arg->ret = TEEC_ERROR_COMMUNICATION; arg->ret_origin = TEEC_ORIGIN_COMMS; /* Close session again to avoid leakage */ @@ -308,7 +319,6 @@ int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg, struct tee_shm *shm; struct optee_msg_arg *msg_arg; phys_addr_t msg_parg; - struct optee_msg_param *msg_param; struct optee_session *sess; int rc; @@ -326,9 +336,8 @@ int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg, msg_arg->func = arg->func; msg_arg->session = arg->session; msg_arg->cancel_id = arg->cancel_id; - msg_param = OPTEE_MSG_GET_PARAMS(msg_arg); - rc = optee_to_msg_param(msg_param, arg->num_params, param); + rc = optee_to_msg_param(msg_arg->params, arg->num_params, param); if (rc) goto out; @@ -337,7 +346,7 @@ int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg, msg_arg->ret_origin = TEEC_ORIGIN_COMMS; } - if (optee_from_msg_param(param, arg->num_params, msg_param)) { + if (optee_from_msg_param(param, arg->num_params, msg_arg->params)) { msg_arg->ret = TEEC_ERROR_COMMUNICATION; msg_arg->ret_origin = TEEC_ORIGIN_COMMS; } @@ -401,7 +410,7 @@ void optee_enable_shm_cache(struct optee *optee) } /** - * optee_enable_shm_cache() - Disables caching of some shared memory allocation + * optee_disable_shm_cache() - Disables caching of some shared memory allocation * in OP-TEE * @optee: main service struct */ diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index b4fe7713b2fb..58169e519422 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -11,6 +11,10 @@ * GNU General Public License for more details. * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/arm-smccc.h> #include <linux/errno.h> #include <linux/io.h> #include <linux/module.h> @@ -326,9 +330,8 @@ static bool optee_msg_exchange_capabilities(optee_invoke_fn *invoke_fn, * point of view) or not, is_smp() returns the the information * needed, but can't be called directly from here. */ -#ifndef CONFIG_SMP - a1 |= OPTEE_SMC_NSEC_CAP_UNIPROCESSOR; -#endif + if (!IS_ENABLED(CONFIG_SMP) || nr_cpu_ids == 1) + a1 |= OPTEE_SMC_NSEC_CAP_UNIPROCESSOR; invoke_fn(OPTEE_SMC_EXCHANGE_CAPABILITIES, a1, 0, 0, 0, 0, 0, 0, &res.smccc); @@ -341,8 +344,7 @@ static bool optee_msg_exchange_capabilities(optee_invoke_fn *invoke_fn, } static struct tee_shm_pool * -optee_config_shm_ioremap(struct device *dev, optee_invoke_fn *invoke_fn, - void __iomem **ioremaped_shm) +optee_config_shm_memremap(optee_invoke_fn *invoke_fn, void **memremaped_shm) { union { struct arm_smccc_res smccc; @@ -354,18 +356,18 @@ optee_config_shm_ioremap(struct device *dev, optee_invoke_fn *invoke_fn, size_t size; phys_addr_t begin; phys_addr_t end; - void __iomem *va; + void *va; struct tee_shm_pool_mem_info priv_info; struct tee_shm_pool_mem_info dmabuf_info; invoke_fn(OPTEE_SMC_GET_SHM_CONFIG, 0, 0, 0, 0, 0, 0, 0, &res.smccc); if (res.result.status != OPTEE_SMC_RETURN_OK) { - dev_info(dev, "shm service not available\n"); + pr_info("shm service not available\n"); return ERR_PTR(-ENOENT); } if (res.result.settings != OPTEE_SMC_SHM_CACHED) { - dev_err(dev, "only normal cached shared memory supported\n"); + pr_err("only normal cached shared memory supported\n"); return ERR_PTR(-EINVAL); } @@ -375,13 +377,13 @@ optee_config_shm_ioremap(struct device *dev, optee_invoke_fn *invoke_fn, size = end - begin; if (size < 2 * OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE) { - dev_err(dev, "too small shared memory area\n"); + pr_err("too small shared memory area\n"); return ERR_PTR(-EINVAL); } - va = ioremap_cache(paddr, size); + va = memremap(paddr, size, MEMREMAP_WB); if (!va) { - dev_err(dev, "shared memory ioremap failed\n"); + pr_err("shared memory ioremap failed\n"); return ERR_PTR(-EINVAL); } vaddr = (unsigned long)va; @@ -393,97 +395,112 @@ optee_config_shm_ioremap(struct device *dev, optee_invoke_fn *invoke_fn, dmabuf_info.paddr = paddr + OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE; dmabuf_info.size = size - OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE; - pool = tee_shm_pool_alloc_res_mem(dev, &priv_info, &dmabuf_info); + pool = tee_shm_pool_alloc_res_mem(&priv_info, &dmabuf_info); if (IS_ERR(pool)) { - iounmap(va); + memunmap(va); goto out; } - *ioremaped_shm = va; + *memremaped_shm = va; out: return pool; } -static int get_invoke_func(struct device *dev, optee_invoke_fn **invoke_fn) +/* Simple wrapper functions to be able to use a function pointer */ +static void optee_smccc_smc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + unsigned long a4, unsigned long a5, + unsigned long a6, unsigned long a7, + struct arm_smccc_res *res) +{ + arm_smccc_smc(a0, a1, a2, a3, a4, a5, a6, a7, res); +} + +static void optee_smccc_hvc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + unsigned long a4, unsigned long a5, + unsigned long a6, unsigned long a7, + struct arm_smccc_res *res) +{ + arm_smccc_hvc(a0, a1, a2, a3, a4, a5, a6, a7, res); +} + +static optee_invoke_fn *get_invoke_func(struct device_node *np) { - struct device_node *np = dev->of_node; const char *method; - dev_info(dev, "probing for conduit method from DT.\n"); + pr_info("probing for conduit method from DT.\n"); if (of_property_read_string(np, "method", &method)) { - dev_warn(dev, "missing \"method\" property\n"); - return -ENXIO; + pr_warn("missing \"method\" property\n"); + return ERR_PTR(-ENXIO); } - if (!strcmp("hvc", method)) { - *invoke_fn = arm_smccc_hvc; - } else if (!strcmp("smc", method)) { - *invoke_fn = arm_smccc_smc; - } else { - dev_warn(dev, "invalid \"method\" property: %s\n", method); - return -EINVAL; - } - return 0; + if (!strcmp("hvc", method)) + return optee_smccc_hvc; + else if (!strcmp("smc", method)) + return optee_smccc_smc; + + pr_warn("invalid \"method\" property: %s\n", method); + return ERR_PTR(-EINVAL); } -static int optee_probe(struct platform_device *pdev) +static struct optee *optee_probe(struct device_node *np) { optee_invoke_fn *invoke_fn; struct tee_shm_pool *pool; struct optee *optee = NULL; - void __iomem *ioremaped_shm = NULL; + void *memremaped_shm = NULL; struct tee_device *teedev; u32 sec_caps; int rc; - rc = get_invoke_func(&pdev->dev, &invoke_fn); - if (rc) - return rc; + invoke_fn = get_invoke_func(np); + if (IS_ERR(invoke_fn)) + return (void *)invoke_fn; if (!optee_msg_api_uid_is_optee_api(invoke_fn)) { - dev_warn(&pdev->dev, "api uid mismatch\n"); - return -EINVAL; + pr_warn("api uid mismatch\n"); + return ERR_PTR(-EINVAL); } if (!optee_msg_api_revision_is_compatible(invoke_fn)) { - dev_warn(&pdev->dev, "api revision mismatch\n"); - return -EINVAL; + pr_warn("api revision mismatch\n"); + return ERR_PTR(-EINVAL); } if (!optee_msg_exchange_capabilities(invoke_fn, &sec_caps)) { - dev_warn(&pdev->dev, "capabilities mismatch\n"); - return -EINVAL; + pr_warn("capabilities mismatch\n"); + return ERR_PTR(-EINVAL); } /* * We have no other option for shared memory, if secure world * doesn't have any reserved memory we can use we can't continue. */ - if (!(sec_caps & OPTEE_SMC_SEC_CAP_HAVE_RESERVERED_SHM)) - return -EINVAL; + if (!(sec_caps & OPTEE_SMC_SEC_CAP_HAVE_RESERVED_SHM)) + return ERR_PTR(-EINVAL); - pool = optee_config_shm_ioremap(&pdev->dev, invoke_fn, &ioremaped_shm); + pool = optee_config_shm_memremap(invoke_fn, &memremaped_shm); if (IS_ERR(pool)) - return PTR_ERR(pool); + return (void *)pool; - optee = devm_kzalloc(&pdev->dev, sizeof(*optee), GFP_KERNEL); + optee = kzalloc(sizeof(*optee), GFP_KERNEL); if (!optee) { rc = -ENOMEM; goto err; } - optee->dev = &pdev->dev; optee->invoke_fn = invoke_fn; - teedev = tee_device_alloc(&optee_desc, &pdev->dev, pool, optee); + teedev = tee_device_alloc(&optee_desc, NULL, pool, optee); if (IS_ERR(teedev)) { rc = PTR_ERR(teedev); goto err; } optee->teedev = teedev; - teedev = tee_device_alloc(&optee_supp_desc, &pdev->dev, pool, optee); + teedev = tee_device_alloc(&optee_supp_desc, NULL, pool, optee); if (IS_ERR(teedev)) { rc = PTR_ERR(teedev); goto err; @@ -502,15 +519,13 @@ static int optee_probe(struct platform_device *pdev) INIT_LIST_HEAD(&optee->call_queue.waiters); optee_wait_queue_init(&optee->wait_queue); optee_supp_init(&optee->supp); - optee->ioremaped_shm = ioremaped_shm; + optee->memremaped_shm = memremaped_shm; optee->pool = pool; - platform_set_drvdata(pdev, optee); - optee_enable_shm_cache(optee); - dev_info(&pdev->dev, "initialized driver\n"); - return 0; + pr_info("initialized driver\n"); + return optee; err: if (optee) { /* @@ -520,18 +535,17 @@ err: */ tee_device_unregister(optee->supp_teedev); tee_device_unregister(optee->teedev); + kfree(optee); } if (pool) tee_shm_pool_free(pool); - if (ioremaped_shm) - iounmap(ioremaped_shm); - return rc; + if (memremaped_shm) + memunmap(memremaped_shm); + return ERR_PTR(rc); } -static int optee_remove(struct platform_device *pdev) +static void optee_remove(struct optee *optee) { - struct optee *optee = platform_get_drvdata(pdev); - /* * Ask OP-TEE to free all cached shared memory objects to decrease * reference counters and also avoid wild pointers in secure world @@ -547,13 +561,13 @@ static int optee_remove(struct platform_device *pdev) tee_device_unregister(optee->teedev); tee_shm_pool_free(optee->pool); - if (optee->ioremaped_shm) - iounmap(optee->ioremaped_shm); + if (optee->memremaped_shm) + memunmap(optee->memremaped_shm); optee_wait_queue_exit(&optee->wait_queue); optee_supp_uninit(&optee->supp); mutex_destroy(&optee->call_queue.mutex); - return 0; + kfree(optee); } static const struct of_device_id optee_match[] = { @@ -561,33 +575,43 @@ static const struct of_device_id optee_match[] = { {}, }; -static struct platform_driver optee_driver = { - .driver = { - .name = DRIVER_NAME, - .of_match_table = optee_match, - }, - .probe = optee_probe, - .remove = optee_remove, -}; +static struct optee *optee_svc; static int __init optee_driver_init(void) { - struct device_node *node; + struct device_node *fw_np; + struct device_node *np; + struct optee *optee; - /* - * Preferred path is /firmware/optee, but it's the matching that - * matters. - */ - for_each_matching_node(node, optee_match) - of_platform_device_create(node, NULL, NULL); + /* Node is supposed to be below /firmware */ + fw_np = of_find_node_by_name(NULL, "firmware"); + if (!fw_np) + return -ENODEV; + + np = of_find_matching_node(fw_np, optee_match); + of_node_put(fw_np); + if (!np) + return -ENODEV; + + optee = optee_probe(np); + of_node_put(np); + + if (IS_ERR(optee)) + return PTR_ERR(optee); - return platform_driver_register(&optee_driver); + optee_svc = optee; + + return 0; } module_init(optee_driver_init); static void __exit optee_driver_exit(void) { - platform_driver_unregister(&optee_driver); + struct optee *optee = optee_svc; + + optee_svc = NULL; + if (optee) + optee_remove(optee); } module_exit(optee_driver_exit); diff --git a/drivers/tee/optee/optee_msg.h b/drivers/tee/optee/optee_msg.h index 3c0a91213610..dd7a06ee0462 100644 --- a/drivers/tee/optee/optee_msg.h +++ b/drivers/tee/optee/optee_msg.h @@ -194,29 +194,9 @@ struct optee_msg_arg { u32 ret_origin; u32 num_params; - /* - * this struct is 8 byte aligned since the 'struct optee_msg_param' - * which follows requires 8 byte alignment. - * - * Commented out element used to visualize the layout dynamic part - * of the struct. This field is not available at all if - * num_params == 0. - * - * params is accessed through the macro OPTEE_MSG_GET_PARAMS - * - * struct optee_msg_param params[num_params]; - */ -} __aligned(8); - -/** - * OPTEE_MSG_GET_PARAMS - return pointer to struct optee_msg_param * - * - * @x: Pointer to a struct optee_msg_arg - * - * Returns a pointer to the params[] inside a struct optee_msg_arg. - */ -#define OPTEE_MSG_GET_PARAMS(x) \ - (struct optee_msg_param *)(((struct optee_msg_arg *)(x)) + 1) + /* num_params tells the actual number of element in params */ + struct optee_msg_param params[0]; +}; /** * OPTEE_MSG_GET_ARG_SIZE - return size of struct optee_msg_arg @@ -281,8 +261,6 @@ struct optee_msg_arg { * Returns revision in 2 32-bit words in the same way as * OPTEE_MSG_CALLS_REVISION described above. */ -#define OPTEE_MSG_OS_OPTEE_REVISION_MAJOR 1 -#define OPTEE_MSG_OS_OPTEE_REVISION_MINOR 0 #define OPTEE_MSG_FUNCID_GET_OS_REVISION 0x0001 /* @@ -371,7 +349,12 @@ struct optee_msg_arg { #define OPTEE_MSG_RPC_CMD_GET_TIME 3 /* - * Wait queue primitive, helper for secure world to implement a wait queue + * Wait queue primitive, helper for secure world to implement a wait queue. + * + * If secure world need to wait for a secure world mutex it issues a sleep + * request instead of spinning in secure world. Conversely is a wakeup + * request issued when a secure world mutex with a thread waiting thread is + * unlocked. * * Waiting on a key * [in] param[0].u.value.a OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h index 807f74c41319..c374cd594314 100644 --- a/drivers/tee/optee/optee_private.h +++ b/drivers/tee/optee/optee_private.h @@ -89,25 +89,23 @@ struct optee_supp { * struct optee - main service struct * @supp_teedev: supplicant device * @teedev: client device - * @dev: probed device * @invoke_fn: function to issue smc or hvc * @call_queue: queue of threads waiting to call @invoke_fn * @wait_queue: queue of threads from secure world waiting for a * secure world sync object * @supp: supplicant synchronization struct for RPC to supplicant * @pool: shared memory pool - * @ioremaped_shm virtual address of memory in shared memory pool + * @memremaped_shm virtual address of memory in shared memory pool */ struct optee { struct tee_device *supp_teedev; struct tee_device *teedev; - struct device *dev; optee_invoke_fn *invoke_fn; struct optee_call_queue call_queue; struct optee_wait_queue wait_queue; struct optee_supp supp; struct tee_shm_pool *pool; - void __iomem *ioremaped_shm; + void *memremaped_shm; }; struct optee_session { diff --git a/drivers/tee/optee/optee_smc.h b/drivers/tee/optee/optee_smc.h index d470d450b182..13b7c98cdf25 100644 --- a/drivers/tee/optee/optee_smc.h +++ b/drivers/tee/optee/optee_smc.h @@ -219,7 +219,7 @@ struct optee_smc_get_shm_config_result { /* Normal world works as a uniprocessor system */ #define OPTEE_SMC_NSEC_CAP_UNIPROCESSOR BIT(0) /* Secure world has reserved shared memory for normal world to use */ -#define OPTEE_SMC_SEC_CAP_HAVE_RESERVERED_SHM BIT(0) +#define OPTEE_SMC_SEC_CAP_HAVE_RESERVED_SHM BIT(0) /* Secure world can communicate via previously unregistered shared memory */ #define OPTEE_SMC_SEC_CAP_UNREGISTERED_SHM BIT(1) #define OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES 9 diff --git a/drivers/tee/optee/rpc.c b/drivers/tee/optee/rpc.c index 0b9c1a2accd0..8c1ab49c83c3 100644 --- a/drivers/tee/optee/rpc.c +++ b/drivers/tee/optee/rpc.c @@ -11,6 +11,10 @@ * GNU General Public License for more details. * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/delay.h> #include <linux/device.h> #include <linux/sched.h> #include <linux/slab.h> @@ -37,19 +41,17 @@ void optee_wait_queue_exit(struct optee_wait_queue *priv) static void handle_rpc_func_cmd_get_time(struct optee_msg_arg *arg) { - struct optee_msg_param *params; struct timespec64 ts; if (arg->num_params != 1) goto bad; - params = OPTEE_MSG_GET_PARAMS(arg); - if ((params->attr & OPTEE_MSG_ATTR_TYPE_MASK) != + if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) != OPTEE_MSG_ATTR_TYPE_VALUE_OUTPUT) goto bad; getnstimeofday64(&ts); - params->u.value.a = ts.tv_sec; - params->u.value.b = ts.tv_nsec; + arg->params[0].u.value.a = ts.tv_sec; + arg->params[0].u.value.b = ts.tv_nsec; arg->ret = TEEC_SUCCESS; return; @@ -102,22 +104,19 @@ static void wq_wakeup(struct optee_wait_queue *wq, u32 key) static void handle_rpc_func_cmd_wq(struct optee *optee, struct optee_msg_arg *arg) { - struct optee_msg_param *params; - if (arg->num_params != 1) goto bad; - params = OPTEE_MSG_GET_PARAMS(arg); - if ((params->attr & OPTEE_MSG_ATTR_TYPE_MASK) != + if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) goto bad; - switch (params->u.value.a) { + switch (arg->params[0].u.value.a) { case OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP: - wq_sleep(&optee->wait_queue, params->u.value.b); + wq_sleep(&optee->wait_queue, arg->params[0].u.value.b); break; case OPTEE_MSG_RPC_WAIT_QUEUE_WAKEUP: - wq_wakeup(&optee->wait_queue, params->u.value.b); + wq_wakeup(&optee->wait_queue, arg->params[0].u.value.b); break; default: goto bad; @@ -131,24 +130,22 @@ bad: static void handle_rpc_func_cmd_wait(struct optee_msg_arg *arg) { - struct optee_msg_param *params; u32 msec_to_wait; if (arg->num_params != 1) goto bad; - params = OPTEE_MSG_GET_PARAMS(arg); - if ((params->attr & OPTEE_MSG_ATTR_TYPE_MASK) != + if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) goto bad; - msec_to_wait = params->u.value.a; + msec_to_wait = arg->params[0].u.value.a; /* set task's state to interruptible sleep */ set_current_state(TASK_INTERRUPTIBLE); /* take a nap */ - schedule_timeout(msecs_to_jiffies(msec_to_wait)); + msleep(msec_to_wait); arg->ret = TEEC_SUCCESS; return; @@ -160,7 +157,6 @@ static void handle_rpc_supp_cmd(struct tee_context *ctx, struct optee_msg_arg *arg) { struct tee_param *params; - struct optee_msg_param *msg_params = OPTEE_MSG_GET_PARAMS(arg); arg->ret_origin = TEEC_ORIGIN_COMMS; @@ -171,14 +167,14 @@ static void handle_rpc_supp_cmd(struct tee_context *ctx, return; } - if (optee_from_msg_param(params, arg->num_params, msg_params)) { + if (optee_from_msg_param(params, arg->num_params, arg->params)) { arg->ret = TEEC_ERROR_BAD_PARAMETERS; goto out; } arg->ret = optee_supp_thrd_req(ctx, arg->cmd, arg->num_params, params); - if (optee_to_msg_param(msg_params, arg->num_params, params)) + if (optee_to_msg_param(arg->params, arg->num_params, params)) arg->ret = TEEC_ERROR_BAD_PARAMETERS; out: kfree(params); @@ -210,7 +206,6 @@ static struct tee_shm *cmd_alloc_suppl(struct tee_context *ctx, size_t sz) static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx, struct optee_msg_arg *arg) { - struct optee_msg_param *params = OPTEE_MSG_GET_PARAMS(arg); phys_addr_t pa; struct tee_shm *shm; size_t sz; @@ -219,20 +214,20 @@ static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx, arg->ret_origin = TEEC_ORIGIN_COMMS; if (!arg->num_params || - params->attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) { + arg->params[0].attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) { arg->ret = TEEC_ERROR_BAD_PARAMETERS; return; } for (n = 1; n < arg->num_params; n++) { - if (params[n].attr != OPTEE_MSG_ATTR_TYPE_NONE) { + if (arg->params[n].attr != OPTEE_MSG_ATTR_TYPE_NONE) { arg->ret = TEEC_ERROR_BAD_PARAMETERS; return; } } - sz = params->u.value.b; - switch (params->u.value.a) { + sz = arg->params[0].u.value.b; + switch (arg->params[0].u.value.a) { case OPTEE_MSG_RPC_SHM_TYPE_APPL: shm = cmd_alloc_suppl(ctx, sz); break; @@ -254,10 +249,10 @@ static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx, goto bad; } - params[0].attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT; - params[0].u.tmem.buf_ptr = pa; - params[0].u.tmem.size = sz; - params[0].u.tmem.shm_ref = (unsigned long)shm; + arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT; + arg->params[0].u.tmem.buf_ptr = pa; + arg->params[0].u.tmem.size = sz; + arg->params[0].u.tmem.shm_ref = (unsigned long)shm; arg->ret = TEEC_SUCCESS; return; bad: @@ -292,19 +287,18 @@ static void cmd_free_suppl(struct tee_context *ctx, struct tee_shm *shm) static void handle_rpc_func_cmd_shm_free(struct tee_context *ctx, struct optee_msg_arg *arg) { - struct optee_msg_param *params = OPTEE_MSG_GET_PARAMS(arg); struct tee_shm *shm; arg->ret_origin = TEEC_ORIGIN_COMMS; if (arg->num_params != 1 || - params->attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) { + arg->params[0].attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) { arg->ret = TEEC_ERROR_BAD_PARAMETERS; return; } - shm = (struct tee_shm *)(unsigned long)params->u.value.b; - switch (params->u.value.a) { + shm = (struct tee_shm *)(unsigned long)arg->params[0].u.value.b; + switch (arg->params[0].u.value.a) { case OPTEE_MSG_RPC_SHM_TYPE_APPL: cmd_free_suppl(ctx, shm); break; @@ -324,8 +318,7 @@ static void handle_rpc_func_cmd(struct tee_context *ctx, struct optee *optee, arg = tee_shm_get_va(shm, 0); if (IS_ERR(arg)) { - dev_err(optee->dev, "%s: tee_shm_get_va %p failed\n", - __func__, shm); + pr_err("%s: tee_shm_get_va %p failed\n", __func__, shm); return; } @@ -395,8 +388,8 @@ void optee_handle_rpc(struct tee_context *ctx, struct optee_rpc_param *param) handle_rpc_func_cmd(ctx, optee, shm); break; default: - dev_warn(optee->dev, "Unknown RPC func 0x%x\n", - (u32)OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)); + pr_warn("Unknown RPC func 0x%x\n", + (u32)OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)); break; } diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 204521003350..5c60bf4423e6 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -157,9 +157,9 @@ static int params_from_user(struct tee_context *ctx, struct tee_param *params, break; case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT: - params[n].u.value.a = ip.u.value.a; - params[n].u.value.b = ip.u.value.b; - params[n].u.value.c = ip.u.value.c; + params[n].u.value.a = ip.a; + params[n].u.value.b = ip.b; + params[n].u.value.c = ip.c; break; case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: @@ -172,12 +172,12 @@ static int params_from_user(struct tee_context *ctx, struct tee_param *params, * count. It's the callers responibility to do * tee_shm_put() on all resolved pointers. */ - shm = tee_shm_get_from_id(ctx, ip.u.memref.shm_id); + shm = tee_shm_get_from_id(ctx, ip.c); if (IS_ERR(shm)) return PTR_ERR(shm); - params[n].u.memref.shm_offs = ip.u.memref.shm_offs; - params[n].u.memref.size = ip.u.memref.size; + params[n].u.memref.shm_offs = ip.a; + params[n].u.memref.size = ip.b; params[n].u.memref.shm = shm; break; default: @@ -200,14 +200,14 @@ static int params_to_user(struct tee_ioctl_param __user *uparams, switch (p->attr) { case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT: - if (put_user(p->u.value.a, &up->u.value.a) || - put_user(p->u.value.b, &up->u.value.b) || - put_user(p->u.value.c, &up->u.value.c)) + if (put_user(p->u.value.a, &up->a) || + put_user(p->u.value.b, &up->b) || + put_user(p->u.value.c, &up->c)) return -EFAULT; break; case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: - if (put_user((u64)p->u.memref.size, &up->u.memref.size)) + if (put_user((u64)p->u.memref.size, &up->b)) return -EFAULT; default: break; @@ -250,8 +250,7 @@ static int tee_ioctl_open_session(struct tee_context *ctx, buf.buf_len < sizeof(struct tee_ioctl_open_session_arg)) return -EINVAL; - uarg = (struct tee_ioctl_open_session_arg __user *)(unsigned long) - buf.buf_ptr; + uarg = u64_to_user_ptr(buf.buf_ptr); if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; @@ -263,7 +262,7 @@ static int tee_ioctl_open_session(struct tee_context *ctx, GFP_KERNEL); if (!params) return -ENOMEM; - uparams = (struct tee_ioctl_param __user *)(uarg + 1); + uparams = uarg->params; rc = params_from_user(ctx, params, arg.num_params, uparams); if (rc) goto out; @@ -322,7 +321,7 @@ static int tee_ioctl_invoke(struct tee_context *ctx, buf.buf_len < sizeof(struct tee_ioctl_invoke_arg)) return -EINVAL; - uarg = (struct tee_ioctl_invoke_arg __user *)(unsigned long)buf.buf_ptr; + uarg = u64_to_user_ptr(buf.buf_ptr); if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; @@ -334,7 +333,7 @@ static int tee_ioctl_invoke(struct tee_context *ctx, GFP_KERNEL); if (!params) return -ENOMEM; - uparams = (struct tee_ioctl_param __user *)(uarg + 1); + uparams = uarg->params; rc = params_from_user(ctx, params, arg.num_params, uparams); if (rc) goto out; @@ -406,24 +405,26 @@ static int params_to_supp(struct tee_context *ctx, switch (p->attr) { case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT: - ip.u.value.a = p->u.value.a; - ip.u.value.b = p->u.value.b; - ip.u.value.c = p->u.value.c; + ip.a = p->u.value.a; + ip.b = p->u.value.b; + ip.c = p->u.value.c; break; case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: - ip.u.memref.size = p->u.memref.size; + ip.b = p->u.memref.size; if (!p->u.memref.shm) { - ip.u.memref.shm_offs = 0; - ip.u.memref.shm_id = -1; + ip.a = 0; + ip.c = (u64)-1; /* invalid shm id */ break; } - ip.u.memref.shm_offs = p->u.memref.shm_offs; - ip.u.memref.shm_id = p->u.memref.shm->id; + ip.a = p->u.memref.shm_offs; + ip.c = p->u.memref.shm->id; break; default: - memset(&ip.u, 0, sizeof(ip.u)); + ip.a = 0; + ip.b = 0; + ip.c = 0; break; } @@ -441,7 +442,6 @@ static int tee_ioctl_supp_recv(struct tee_context *ctx, struct tee_ioctl_buf_data buf; struct tee_iocl_supp_recv_arg __user *uarg; struct tee_param *params; - struct tee_ioctl_param __user *uparams; u32 num_params; u32 func; @@ -455,8 +455,7 @@ static int tee_ioctl_supp_recv(struct tee_context *ctx, buf.buf_len < sizeof(struct tee_iocl_supp_recv_arg)) return -EINVAL; - uarg = (struct tee_iocl_supp_recv_arg __user *)(unsigned long) - buf.buf_ptr; + uarg = u64_to_user_ptr(buf.buf_ptr); if (get_user(num_params, &uarg->num_params)) return -EFAULT; @@ -477,8 +476,7 @@ static int tee_ioctl_supp_recv(struct tee_context *ctx, goto out; } - uparams = (struct tee_ioctl_param __user *)(uarg + 1); - rc = params_to_supp(ctx, uparams, num_params, params); + rc = params_to_supp(ctx, uarg->params, num_params, params); out: kfree(params); return rc; @@ -505,9 +503,9 @@ static int params_from_supp(struct tee_param *params, size_t num_params, case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT: /* Only out and in/out values can be updated */ - p->u.value.a = ip.u.value.a; - p->u.value.b = ip.u.value.b; - p->u.value.c = ip.u.value.c; + p->u.value.a = ip.a; + p->u.value.b = ip.b; + p->u.value.c = ip.c; break; case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: @@ -520,7 +518,7 @@ static int params_from_supp(struct tee_param *params, size_t num_params, */ p->u.memref.shm = NULL; p->u.memref.shm_offs = 0; - p->u.memref.size = ip.u.memref.size; + p->u.memref.size = ip.b; break; default: memset(&p->u, 0, sizeof(p->u)); @@ -537,7 +535,6 @@ static int tee_ioctl_supp_send(struct tee_context *ctx, struct tee_ioctl_buf_data buf; struct tee_iocl_supp_send_arg __user *uarg; struct tee_param *params; - struct tee_ioctl_param __user *uparams; u32 num_params; u32 ret; @@ -552,8 +549,7 @@ static int tee_ioctl_supp_send(struct tee_context *ctx, buf.buf_len < sizeof(struct tee_iocl_supp_send_arg)) return -EINVAL; - uarg = (struct tee_iocl_supp_send_arg __user *)(unsigned long) - buf.buf_ptr; + uarg = u64_to_user_ptr(buf.buf_ptr); if (get_user(ret, &uarg->ret) || get_user(num_params, &uarg->num_params)) return -EFAULT; @@ -565,8 +561,7 @@ static int tee_ioctl_supp_send(struct tee_context *ctx, if (!params) return -ENOMEM; - uparams = (struct tee_ioctl_param __user *)(uarg + 1); - rc = params_from_supp(params, num_params, uparams); + rc = params_from_supp(params, num_params, uarg->params); if (rc) goto out; @@ -619,6 +614,7 @@ static void tee_release_device(struct device *dev) clear_bit(teedev->id, dev_mask); spin_unlock(&driver_lock); mutex_destroy(&teedev->mutex); + idr_destroy(&teedev->idr); kfree(teedev); } @@ -646,7 +642,7 @@ struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, if (!teedesc || !teedesc->name || !teedesc->ops || !teedesc->ops->get_version || !teedesc->ops->open || - !teedesc->ops->release || !dev || !pool) + !teedesc->ops->release || !pool) return ERR_PTR(-EINVAL); teedev = kzalloc(sizeof(*teedev), GFP_KERNEL); @@ -696,6 +692,7 @@ struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, teedev->num_users = 1; init_completion(&teedev->c_no_users); mutex_init(&teedev->mutex); + idr_init(&teedev->idr); teedev->desc = teedesc; teedev->pool = pool; @@ -704,8 +701,8 @@ struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, err_devt: unregister_chrdev_region(teedev->dev.devt, 1); err: - dev_err(dev, "could not register %s driver\n", - teedesc->flags & TEE_DESC_PRIVILEGED ? "privileged" : "client"); + pr_err("could not register %s driver\n", + teedesc->flags & TEE_DESC_PRIVILEGED ? "privileged" : "client"); if (teedev && teedev->id < TEE_NUM_DEVICES) { spin_lock(&driver_lock); clear_bit(teedev->id, dev_mask); @@ -749,14 +746,9 @@ int tee_device_register(struct tee_device *teedev) { int rc; - /* - * If the teedev already is registered, don't do it again. It's - * obviously an error to try to register twice, but if we return - * an error we'll force the driver to remove the teedev. - */ if (teedev->flags & TEE_DEVICE_FLAG_REGISTERED) { dev_err(&teedev->dev, "attempt to register twice\n"); - return 0; + return -EINVAL; } rc = cdev_add(&teedev->cdev, teedev->dev.devt, 1); diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 9fd501c8e22e..0be1e3e93bee 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -309,7 +309,8 @@ int tee_shm_get_pa(struct tee_shm *shm, size_t offs, phys_addr_t *pa) EXPORT_SYMBOL_GPL(tee_shm_get_pa); /** - * tee_shm_get_from_id() - Find shared memory object and increase referece count + * tee_shm_get_from_id() - Find shared memory object and increase reference + * count * @ctx: Context owning the shared memory * @id: Id of shared memory object * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure diff --git a/drivers/tee/tee_shm_pool.c b/drivers/tee/tee_shm_pool.c index 3cb0ad0ce99f..fb4f8522a526 100644 --- a/drivers/tee/tee_shm_pool.c +++ b/drivers/tee/tee_shm_pool.c @@ -90,7 +90,6 @@ static int pool_res_mem_mgr_init(struct tee_shm_pool_mgr *mgr, /** * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved * memory range - * @dev: Device allocating the pool * @priv_info: Information for driver private shared memory pool * @dmabuf_info: Information for dma-buf shared memory pool * @@ -102,8 +101,7 @@ static int pool_res_mem_mgr_init(struct tee_shm_pool_mgr *mgr, * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. */ struct tee_shm_pool * -tee_shm_pool_alloc_res_mem(struct device *dev, - struct tee_shm_pool_mem_info *priv_info, +tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, struct tee_shm_pool_mem_info *dmabuf_info) { struct tee_shm_pool *pool = NULL; @@ -135,7 +133,7 @@ tee_shm_pool_alloc_res_mem(struct device *dev, return pool; err: if (ret == -ENOMEM) - dev_err(dev, "can't allocate memory for res_mem shared memory pool\n"); + pr_err("%s: can't allocate memory for res_mem shared memory pool\n", __func__); if (pool && pool->private_mgr.private_data) gen_pool_destroy(pool->private_mgr.private_data); kfree(pool); diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 5b4b47ed948b..87d87ac1c8a0 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -191,8 +191,10 @@ unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) mutex_lock(&cooling_list_lock); list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) { if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) { + unsigned long level = get_level(cpufreq_dev, freq); + mutex_unlock(&cooling_list_lock); - return get_level(cpufreq_dev, freq); + return level; } } mutex_unlock(&cooling_list_lock); diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 644ddb841d9f..6d1e2f746ab4 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -114,7 +114,7 @@ #define DEFAULT_TX_BUF_COUNT 3 struct n_hdlc_buf { - struct n_hdlc_buf *link; + struct list_head list_item; int count; char buf[1]; }; @@ -122,8 +122,7 @@ struct n_hdlc_buf { #define N_HDLC_BUF_SIZE (sizeof(struct n_hdlc_buf) + maxframe) struct n_hdlc_buf_list { - struct n_hdlc_buf *head; - struct n_hdlc_buf *tail; + struct list_head list; int count; spinlock_t spinlock; }; @@ -136,7 +135,6 @@ struct n_hdlc_buf_list { * @backup_tty - TTY to use if tty gets closed * @tbusy - reentrancy flag for tx wakeup code * @woke_up - FIXME: describe this field - * @tbuf - currently transmitting tx buffer * @tx_buf_list - list of pending transmit frame buffers * @rx_buf_list - list of received frame buffers * @tx_free_buf_list - list unused transmit frame buffers @@ -149,7 +147,6 @@ struct n_hdlc { struct tty_struct *backup_tty; int tbusy; int woke_up; - struct n_hdlc_buf *tbuf; struct n_hdlc_buf_list tx_buf_list; struct n_hdlc_buf_list rx_buf_list; struct n_hdlc_buf_list tx_free_buf_list; @@ -159,7 +156,8 @@ struct n_hdlc { /* * HDLC buffer list manipulation functions */ -static void n_hdlc_buf_list_init(struct n_hdlc_buf_list *list); +static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list, + struct n_hdlc_buf *buf); static void n_hdlc_buf_put(struct n_hdlc_buf_list *list, struct n_hdlc_buf *buf); static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list); @@ -209,16 +207,9 @@ static void flush_tx_queue(struct tty_struct *tty) { struct n_hdlc *n_hdlc = tty2n_hdlc(tty); struct n_hdlc_buf *buf; - unsigned long flags; while ((buf = n_hdlc_buf_get(&n_hdlc->tx_buf_list))) n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, buf); - spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock, flags); - if (n_hdlc->tbuf) { - n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, n_hdlc->tbuf); - n_hdlc->tbuf = NULL; - } - spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags); } static struct tty_ldisc_ops n_hdlc_ldisc = { @@ -284,7 +275,6 @@ static void n_hdlc_release(struct n_hdlc *n_hdlc) } else break; } - kfree(n_hdlc->tbuf); kfree(n_hdlc); } /* end of n_hdlc_release() */ @@ -403,13 +393,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) n_hdlc->woke_up = 0; spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags); - /* get current transmit buffer or get new transmit */ - /* buffer from list of pending transmit buffers */ - - tbuf = n_hdlc->tbuf; - if (!tbuf) - tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list); - + tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list); while (tbuf) { if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)sending frame %p, count=%d\n", @@ -421,7 +405,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) /* rollback was possible and has been done */ if (actual == -ERESTARTSYS) { - n_hdlc->tbuf = tbuf; + n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf); break; } /* if transmit error, throw frame away by */ @@ -436,10 +420,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) /* free current transmit buffer */ n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, tbuf); - - /* this tx buffer is done */ - n_hdlc->tbuf = NULL; - + /* wait up sleeping writers */ wake_up_interruptible(&tty->write_wait); @@ -449,10 +430,12 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)frame %p pending\n", __FILE__,__LINE__,tbuf); - - /* buffer not accepted by driver */ - /* set this buffer as pending buffer */ - n_hdlc->tbuf = tbuf; + + /* + * the buffer was not accepted by driver, + * return it back into tx queue + */ + n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf); break; } } @@ -750,7 +733,8 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, int error = 0; int count; unsigned long flags; - + struct n_hdlc_buf *buf = NULL; + if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)n_hdlc_tty_ioctl() called %d\n", __FILE__,__LINE__,cmd); @@ -764,8 +748,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, /* report count of read data available */ /* in next available frame (if any) */ spin_lock_irqsave(&n_hdlc->rx_buf_list.spinlock,flags); - if (n_hdlc->rx_buf_list.head) - count = n_hdlc->rx_buf_list.head->count; + buf = list_first_entry_or_null(&n_hdlc->rx_buf_list.list, + struct n_hdlc_buf, list_item); + if (buf) + count = buf->count; else count = 0; spin_unlock_irqrestore(&n_hdlc->rx_buf_list.spinlock,flags); @@ -777,8 +763,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, count = tty_chars_in_buffer(tty); /* add size of next output frame in queue */ spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock,flags); - if (n_hdlc->tx_buf_list.head) - count += n_hdlc->tx_buf_list.head->count; + buf = list_first_entry_or_null(&n_hdlc->tx_buf_list.list, + struct n_hdlc_buf, list_item); + if (buf) + count += buf->count; spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock,flags); error = put_user(count, (int __user *)arg); break; @@ -826,14 +814,14 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp, poll_wait(filp, &tty->write_wait, wait); /* set bits for operations that won't block */ - if (n_hdlc->rx_buf_list.head) + if (!list_empty(&n_hdlc->rx_buf_list.list)) mask |= POLLIN | POLLRDNORM; /* readable */ if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) mask |= POLLHUP; if (tty_hung_up_p(filp)) mask |= POLLHUP; if (!tty_is_writelocked(tty) && - n_hdlc->tx_free_buf_list.head) + !list_empty(&n_hdlc->tx_free_buf_list.list)) mask |= POLLOUT | POLLWRNORM; /* writable */ } return mask; @@ -853,11 +841,16 @@ static struct n_hdlc *n_hdlc_alloc(void) if (!n_hdlc) return NULL; - n_hdlc_buf_list_init(&n_hdlc->rx_free_buf_list); - n_hdlc_buf_list_init(&n_hdlc->tx_free_buf_list); - n_hdlc_buf_list_init(&n_hdlc->rx_buf_list); - n_hdlc_buf_list_init(&n_hdlc->tx_buf_list); - + spin_lock_init(&n_hdlc->rx_free_buf_list.spinlock); + spin_lock_init(&n_hdlc->tx_free_buf_list.spinlock); + spin_lock_init(&n_hdlc->rx_buf_list.spinlock); + spin_lock_init(&n_hdlc->tx_buf_list.spinlock); + + INIT_LIST_HEAD(&n_hdlc->rx_free_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->tx_free_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->rx_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->tx_buf_list.list); + /* allocate free rx buffer list */ for(i=0;i<DEFAULT_RX_BUF_COUNT;i++) { buf = kmalloc(N_HDLC_BUF_SIZE, GFP_KERNEL); @@ -885,63 +878,65 @@ static struct n_hdlc *n_hdlc_alloc(void) } /* end of n_hdlc_alloc() */ /** - * n_hdlc_buf_list_init - initialize specified HDLC buffer list - * @list - pointer to buffer list + * n_hdlc_buf_return - put the HDLC buffer after the head of the specified list + * @buf_list - pointer to the buffer list + * @buf - pointer to the buffer */ -static void n_hdlc_buf_list_init(struct n_hdlc_buf_list *list) +static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list, + struct n_hdlc_buf *buf) { - memset(list, 0, sizeof(*list)); - spin_lock_init(&list->spinlock); -} /* end of n_hdlc_buf_list_init() */ + unsigned long flags; + + spin_lock_irqsave(&buf_list->spinlock, flags); + + list_add(&buf->list_item, &buf_list->list); + buf_list->count++; + + spin_unlock_irqrestore(&buf_list->spinlock, flags); +} /** * n_hdlc_buf_put - add specified HDLC buffer to tail of specified list - * @list - pointer to buffer list + * @buf_list - pointer to buffer list * @buf - pointer to buffer */ -static void n_hdlc_buf_put(struct n_hdlc_buf_list *list, +static void n_hdlc_buf_put(struct n_hdlc_buf_list *buf_list, struct n_hdlc_buf *buf) { unsigned long flags; - spin_lock_irqsave(&list->spinlock,flags); - - buf->link=NULL; - if (list->tail) - list->tail->link = buf; - else - list->head = buf; - list->tail = buf; - (list->count)++; - - spin_unlock_irqrestore(&list->spinlock,flags); - + + spin_lock_irqsave(&buf_list->spinlock, flags); + + list_add_tail(&buf->list_item, &buf_list->list); + buf_list->count++; + + spin_unlock_irqrestore(&buf_list->spinlock, flags); } /* end of n_hdlc_buf_put() */ /** * n_hdlc_buf_get - remove and return an HDLC buffer from list - * @list - pointer to HDLC buffer list + * @buf_list - pointer to HDLC buffer list * * Remove and return an HDLC buffer from the head of the specified HDLC buffer * list. * Returns a pointer to HDLC buffer if available, otherwise %NULL. */ -static struct n_hdlc_buf* n_hdlc_buf_get(struct n_hdlc_buf_list *list) +static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *buf_list) { unsigned long flags; struct n_hdlc_buf *buf; - spin_lock_irqsave(&list->spinlock,flags); - - buf = list->head; + + spin_lock_irqsave(&buf_list->spinlock, flags); + + buf = list_first_entry_or_null(&buf_list->list, + struct n_hdlc_buf, list_item); if (buf) { - list->head = buf->link; - (list->count)--; + list_del(&buf->list_item); + buf_list->count--; } - if (!list->head) - list->tail = NULL; - - spin_unlock_irqrestore(&list->spinlock,flags); + + spin_unlock_irqrestore(&buf_list->spinlock, flags); return buf; - } /* end of n_hdlc_buf_get() */ static char hdlc_banner[] __initdata = diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c index 80f9de907563..5cc80b80c82b 100644 --- a/drivers/tty/nozomi.c +++ b/drivers/tty/nozomi.c @@ -823,7 +823,7 @@ static int receive_data(enum port_type index, struct nozomi *dc) struct tty_struct *tty = tty_port_tty_get(&port->port); int i, ret; - read_mem32((u32 *) &size, addr, 4); + size = __le32_to_cpu(readl(addr)); /* DBG1( "%d bytes port: %d", size, index); */ if (tty && test_bit(TTY_THROTTLED, &tty->flags)) { diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 807d80145686..96aa0ad32497 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -216,16 +216,11 @@ static int pty_signal(struct tty_struct *tty, int sig) static void pty_flush_buffer(struct tty_struct *tty) { struct tty_struct *to = tty->link; - struct tty_ldisc *ld; if (!to) return; - ld = tty_ldisc_ref(to); - tty_buffer_flush(to, ld); - if (ld) - tty_ldisc_deref(ld); - + tty_buffer_flush(to, NULL); if (to->packet) { spin_lock_irq(&tty->ctrl_lock); tty->ctrl_status |= TIOCPKT_FLUSHWRITE; diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 3827095460a6..5b2d92ce7c55 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -1284,7 +1284,8 @@ static int omap8250_probe(struct platform_device *pdev) pm_runtime_put_autosuspend(&pdev->dev); return 0; err: - pm_runtime_put(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); + pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); return ret; } @@ -1293,6 +1294,7 @@ static int omap8250_remove(struct platform_device *pdev) { struct omap8250_priv *priv = platform_get_drvdata(pdev); + pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); serial8250_unregister_port(priv->line); @@ -1402,6 +1404,10 @@ static int omap8250_runtime_suspend(struct device *dev) struct omap8250_priv *priv = dev_get_drvdata(dev); struct uart_8250_port *up; + /* In case runtime-pm tries this before we are setup */ + if (!priv) + return 0; + up = serial8250_get_port(priv->line); /* * When using 'no_console_suspend', the console UART must not be diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 029de3f99752..cf3da51a3536 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -57,6 +57,7 @@ struct serial_private { unsigned int nr; void __iomem *remapped_bar[PCI_NUM_BAR_RESOURCES]; struct pci_serial_quirk *quirk; + const struct pciserial_board *board; int line[0]; }; @@ -2880,6 +2881,8 @@ enum pci_board_num_t { pbn_b0_4_1152000_200, pbn_b0_8_1152000_200, + pbn_b0_4_1250000, + pbn_b0_2_1843200, pbn_b0_4_1843200, @@ -3113,6 +3116,13 @@ static struct pciserial_board pci_boards[] = { .uart_offset = 0x200, }, + [pbn_b0_4_1250000] = { + .flags = FL_BASE0, + .num_ports = 4, + .base_baud = 1250000, + .uart_offset = 8, + }, + [pbn_b0_2_1843200] = { .flags = FL_BASE0, .num_ports = 2, @@ -4049,6 +4059,7 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board) } } priv->nr = i; + priv->board = board; return priv; err_deinit: @@ -4059,7 +4070,7 @@ err_out: } EXPORT_SYMBOL_GPL(pciserial_init_ports); -void pciserial_remove_ports(struct serial_private *priv) +void pciserial_detach_ports(struct serial_private *priv) { struct pci_serial_quirk *quirk; int i; @@ -4079,7 +4090,11 @@ void pciserial_remove_ports(struct serial_private *priv) quirk = find_quirk(priv->dev); if (quirk->exit) quirk->exit(priv->dev); +} +void pciserial_remove_ports(struct serial_private *priv) +{ + pciserial_detach_ports(priv); kfree(priv); } EXPORT_SYMBOL_GPL(pciserial_remove_ports); @@ -5778,6 +5793,10 @@ static struct pci_device_id serial_pci_tbl[] = { { PCI_DEVICE(0x1c29, 0x1108), .driver_data = pbn_fintek_8 }, { PCI_DEVICE(0x1c29, 0x1112), .driver_data = pbn_fintek_12 }, + /* MKS Tenta SCOM-080x serial cards */ + { PCI_DEVICE(0x1601, 0x0800), .driver_data = pbn_b0_4_1250000 }, + { PCI_DEVICE(0x1601, 0xa801), .driver_data = pbn_b0_4_1250000 }, + /* * These entries match devices with class COMMUNICATION_SERIAL, * COMMUNICATION_MODEM or COMMUNICATION_MULTISERIAL @@ -5806,7 +5825,7 @@ static pci_ers_result_t serial8250_io_error_detected(struct pci_dev *dev, return PCI_ERS_RESULT_DISCONNECT; if (priv) - pciserial_suspend_ports(priv); + pciserial_detach_ports(priv); pci_disable_device(dev); @@ -5831,9 +5850,16 @@ static pci_ers_result_t serial8250_io_slot_reset(struct pci_dev *dev) static void serial8250_io_resume(struct pci_dev *dev) { struct serial_private *priv = pci_get_drvdata(dev); + struct serial_private *new; - if (priv) - pciserial_resume_ports(priv); + if (!priv) + return; + + new = pciserial_init_ports(dev, priv->board); + if (!IS_ERR(new)) { + pci_set_drvdata(dev, new); + kfree(priv); + } } static const struct pci_error_handlers serial8250_err_handler = { diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index a0f911641b04..53e4d5056db7 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -810,6 +810,11 @@ static void atmel_complete_tx_dma(void *arg) */ if (!uart_circ_empty(xmit)) tasklet_schedule(&atmel_port->tasklet); + else if ((port->rs485.flags & SER_RS485_ENABLED) && + !(port->rs485.flags & SER_RS485_RX_DURING_TX)) { + /* DMA done, stop TX, start RX for RS485 */ + atmel_start_rx(port); + } spin_unlock_irqrestore(&port->lock, flags); } @@ -912,12 +917,6 @@ static void atmel_tx_dma(struct uart_port *port) desc->callback = atmel_complete_tx_dma; desc->callback_param = atmel_port; atmel_port->cookie_tx = dmaengine_submit(desc); - - } else { - if (port->rs485.flags & SER_RS485_ENABLED) { - /* DMA done, stop TX, start RX for RS485 */ - atmel_start_rx(port); - } } if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) @@ -1987,6 +1986,11 @@ static void atmel_flush_buffer(struct uart_port *port) atmel_uart_writel(port, ATMEL_PDC_TCR, 0); atmel_port->pdc_tx.ofs = 0; } + /* + * in uart_flush_buffer(), the xmit circular buffer has just + * been cleared, so we have to reset tx_len accordingly. + */ + atmel_port->tx_len = 0; } /* @@ -2499,6 +2503,9 @@ static void atmel_console_write(struct console *co, const char *s, u_int count) pdc_tx = atmel_uart_readl(port, ATMEL_PDC_PTSR) & ATMEL_PDC_TXTEN; atmel_uart_writel(port, ATMEL_PDC_PTCR, ATMEL_PDC_TXTDIS); + /* Make sure that tx path is actually able to send characters */ + atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN); + uart_console_write(port, s, count, atmel_console_putchar); /* diff --git a/drivers/tty/serial/efm32-uart.c b/drivers/tty/serial/efm32-uart.c index 195acc868763..5d476916191b 100644 --- a/drivers/tty/serial/efm32-uart.c +++ b/drivers/tty/serial/efm32-uart.c @@ -27,6 +27,7 @@ #define UARTn_FRAME 0x04 #define UARTn_FRAME_DATABITS__MASK 0x000f #define UARTn_FRAME_DATABITS(n) ((n) - 3) +#define UARTn_FRAME_PARITY__MASK 0x0300 #define UARTn_FRAME_PARITY_NONE 0x0000 #define UARTn_FRAME_PARITY_EVEN 0x0200 #define UARTn_FRAME_PARITY_ODD 0x0300 @@ -572,12 +573,16 @@ static void efm32_uart_console_get_options(struct efm32_uart_port *efm_port, 16 * (4 + (clkdiv >> 6))); frame = efm32_uart_read32(efm_port, UARTn_FRAME); - if (frame & UARTn_FRAME_PARITY_ODD) + switch (frame & UARTn_FRAME_PARITY__MASK) { + case UARTn_FRAME_PARITY_ODD: *parity = 'o'; - else if (frame & UARTn_FRAME_PARITY_EVEN) + break; + case UARTn_FRAME_PARITY_EVEN: *parity = 'e'; - else + break; + default: *parity = 'n'; + } *bits = (frame & UARTn_FRAME_DATABITS__MASK) - UARTn_FRAME_DATABITS(4) + 4; diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c index 88246f7e435a..0f23dda60011 100644 --- a/drivers/tty/serial/ifx6x60.c +++ b/drivers/tty/serial/ifx6x60.c @@ -1378,9 +1378,9 @@ static struct spi_driver ifx_spi_driver = { static void __exit ifx_spi_exit(void) { /* unregister */ + spi_unregister_driver(&ifx_spi_driver); tty_unregister_driver(tty_drv); put_tty_driver(tty_drv); - spi_unregister_driver(&ifx_spi_driver); unregister_reboot_notifier(&ifx_modem_reboot_notifier_block); } diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index e1de4944e0ce..8c4707d5778e 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -1615,6 +1615,7 @@ static const struct of_device_id msm_match_table[] = { { .compatible = "qcom,msm-uartdm" }, {} }; +MODULE_DEVICE_TABLE(of, msm_match_table); static struct platform_driver msm_platform_driver = { .remove = msm_serial_remove, diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 24280d9a05e9..de1c143b475f 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1712,7 +1712,8 @@ static int serial_omap_probe(struct platform_device *pdev) return 0; err_add_port: - pm_runtime_put(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); + pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_qos_remove_request(&up->pm_qos_request); device_init_wakeup(up->dev, false); @@ -1725,9 +1726,13 @@ static int serial_omap_remove(struct platform_device *dev) { struct uart_omap_port *up = platform_get_drvdata(dev); + pm_runtime_get_sync(up->dev); + + uart_remove_one_port(&serial_omap_reg, &up->port); + + pm_runtime_dont_use_autosuspend(up->dev); pm_runtime_put_sync(up->dev); pm_runtime_disable(up->dev); - uart_remove_one_port(&serial_omap_reg, &up->port); pm_qos_remove_request(&up->pm_qos_request); device_init_wakeup(&dev->dev, false); diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c index 237ef5573c18..e6bc1a6be4a4 100644 --- a/drivers/tty/serial/samsung.c +++ b/drivers/tty/serial/samsung.c @@ -900,14 +900,13 @@ static int s3c24xx_serial_request_dma(struct s3c24xx_uart_port *p) return -ENOMEM; } - dma->rx_addr = dma_map_single(dma->rx_chan->device->dev, dma->rx_buf, + dma->rx_addr = dma_map_single(p->port.dev, dma->rx_buf, dma->rx_size, DMA_FROM_DEVICE); spin_lock_irqsave(&p->port.lock, flags); /* TX buffer */ - dma->tx_addr = dma_map_single(dma->tx_chan->device->dev, - p->port.state->xmit.buf, + dma->tx_addr = dma_map_single(p->port.dev, p->port.state->xmit.buf, UART_XMIT_SIZE, DMA_TO_DEVICE); spin_unlock_irqrestore(&p->port.lock, flags); @@ -921,7 +920,7 @@ static void s3c24xx_serial_release_dma(struct s3c24xx_uart_port *p) if (dma->rx_chan) { dmaengine_terminate_all(dma->rx_chan); - dma_unmap_single(dma->rx_chan->device->dev, dma->rx_addr, + dma_unmap_single(p->port.dev, dma->rx_addr, dma->rx_size, DMA_FROM_DEVICE); kfree(dma->rx_buf); dma_release_channel(dma->rx_chan); @@ -930,7 +929,7 @@ static void s3c24xx_serial_release_dma(struct s3c24xx_uart_port *p) if (dma->tx_chan) { dmaengine_terminate_all(dma->tx_chan); - dma_unmap_single(dma->tx_chan->device->dev, dma->tx_addr, + dma_unmap_single(p->port.dev, dma->tx_addr, UART_XMIT_SIZE, DMA_TO_DEVICE); dma_release_channel(dma->tx_chan); dma->tx_chan = NULL; @@ -1030,8 +1029,10 @@ static int s3c64xx_serial_startup(struct uart_port *port) if (ourport->dma) { ret = s3c24xx_serial_request_dma(ourport); if (ret < 0) { - dev_warn(port->dev, "DMA request failed\n"); - return ret; + dev_warn(port->dev, + "DMA request failed, DMA will not be used\n"); + devm_kfree(port->dev, ourport->dma); + ourport->dma = NULL; } } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 63a06ab6ba03..235e150d7b81 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1800,11 +1800,13 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + sci_request_dma(port); + ret = sci_request_irq(s); - if (unlikely(ret < 0)) + if (unlikely(ret < 0)) { + sci_free_dma(port); return ret; - - sci_request_dma(port); + } spin_lock_irqsave(&port->lock, flags); sci_start_tx(port); @@ -1834,8 +1836,8 @@ static void sci_shutdown(struct uart_port *port) } #endif - sci_free_dma(port); sci_free_irq(s); + sci_free_dma(port); } static unsigned int sci_scbrr_calc(struct sci_port *s, unsigned int bps, diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 7cef54334b12..1bb629ab8ecc 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2070,13 +2070,12 @@ retry_open: if (tty) { mutex_unlock(&tty_mutex); retval = tty_lock_interruptible(tty); + tty_kref_put(tty); /* drop kref from tty_driver_lookup_tty() */ if (retval) { if (retval == -EINTR) retval = -ERESTARTSYS; goto err_unref; } - /* safe to drop the kref from tty_driver_lookup_tty() */ - tty_kref_put(tty); retval = tty_reopen(tty); if (retval < 0) { tty_unlock(tty); diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c index d09293bc0e04..cff304abb619 100644 --- a/drivers/tty/tty_mutex.c +++ b/drivers/tty/tty_mutex.c @@ -24,10 +24,15 @@ EXPORT_SYMBOL(tty_lock); int tty_lock_interruptible(struct tty_struct *tty) { + int ret; + if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty)) return -EIO; tty_kref_get(tty); - return mutex_lock_interruptible(&tty->legacy_mutex); + ret = mutex_lock_interruptible(&tty->legacy_mutex); + if (ret) + tty_kref_put(tty); + return ret; } void __lockfunc tty_unlock(struct tty_struct *tty) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 5ab54ef4f304..e4f69bddcfb1 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -2708,13 +2708,13 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) * related to the kernel should not use this. */ data = vt_get_shift_state(); - ret = __put_user(data, p); + ret = put_user(data, p); break; case TIOCL_GETMOUSEREPORTING: console_lock(); /* May be overkill */ data = mouse_reporting(); console_unlock(); - ret = __put_user(data, p); + ret = put_user(data, p); break; case TIOCL_SETVESABLANK: console_lock(); @@ -2723,7 +2723,7 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) break; case TIOCL_GETKMSGREDIRECT: data = vt_get_kmsg_redirect(); - ret = __put_user(data, p); + ret = put_user(data, p); break; case TIOCL_SETKMSGREDIRECT: if (!capable(CAP_SYS_ADMIN)) { diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index 438818caf862..c101e2b430a8 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -428,9 +428,6 @@ int hw_port_test_set(struct ci_hdrc *ci, u8 mode); u8 hw_port_test_get(struct ci_hdrc *ci); -int hw_wait_reg(struct ci_hdrc *ci, enum ci_hw_regs reg, u32 mask, - u32 value, unsigned int timeout_ms); - void ci_platform_configure(struct ci_hdrc *ci); #endif /* __DRIVERS_USB_CHIPIDEA_CI_H */ diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 5a048b7b92e8..2949289bb3c5 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -244,7 +244,6 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) struct ci_hdrc_platform_data pdata = { .name = dev_name(&pdev->dev), .capoffset = DEF_CAPOFFSET, - .flags = CI_HDRC_SET_NON_ZERO_TTHA, }; int ret; const struct of_device_id *of_id; diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index ba4a2a1eb3ff..939c6ad71068 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -518,38 +518,6 @@ int hw_device_reset(struct ci_hdrc *ci) return 0; } -/** - * hw_wait_reg: wait the register value - * - * Sometimes, it needs to wait register value before going on. - * Eg, when switch to device mode, the vbus value should be lower - * than OTGSC_BSV before connects to host. - * - * @ci: the controller - * @reg: register index - * @mask: mast bit - * @value: the bit value to wait - * @timeout_ms: timeout in millisecond - * - * This function returns an error code if timeout - */ -int hw_wait_reg(struct ci_hdrc *ci, enum ci_hw_regs reg, u32 mask, - u32 value, unsigned int timeout_ms) -{ - unsigned long elapse = jiffies + msecs_to_jiffies(timeout_ms); - - while (hw_read(ci, reg, mask) != value) { - if (time_after(jiffies, elapse)) { - dev_err(ci->dev, "timeout waiting for %08x in %d\n", - mask, reg); - return -ETIMEDOUT; - } - msleep(20); - } - - return 0; -} - static irqreturn_t ci_irq(int irq, void *data) { struct ci_hdrc *ci = data; diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c index 58c8485a0715..923379972707 100644 --- a/drivers/usb/chipidea/debug.c +++ b/drivers/usb/chipidea/debug.c @@ -295,7 +295,8 @@ static int ci_role_show(struct seq_file *s, void *data) { struct ci_hdrc *ci = s->private; - seq_printf(s, "%s\n", ci_role(ci)->name); + if (ci->role != CI_ROLE_END) + seq_printf(s, "%s\n", ci_role(ci)->name); return 0; } diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c index 03b6743461d1..0cf149edddd8 100644 --- a/drivers/usb/chipidea/otg.c +++ b/drivers/usb/chipidea/otg.c @@ -44,12 +44,15 @@ u32 hw_read_otgsc(struct ci_hdrc *ci, u32 mask) else val &= ~OTGSC_BSVIS; - cable->changed = false; - if (cable->state) val |= OTGSC_BSV; else val &= ~OTGSC_BSV; + + if (cable->enabled) + val |= OTGSC_BSVIE; + else + val &= ~OTGSC_BSVIE; } cable = &ci->platdata->id_extcon; @@ -59,15 +62,18 @@ u32 hw_read_otgsc(struct ci_hdrc *ci, u32 mask) else val &= ~OTGSC_IDIS; - cable->changed = false; - if (cable->state) val |= OTGSC_ID; else val &= ~OTGSC_ID; + + if (cable->enabled) + val |= OTGSC_IDIE; + else + val &= ~OTGSC_IDIE; } - return val; + return val & mask; } /** @@ -77,6 +83,36 @@ u32 hw_read_otgsc(struct ci_hdrc *ci, u32 mask) */ void hw_write_otgsc(struct ci_hdrc *ci, u32 mask, u32 data) { + struct ci_hdrc_cable *cable; + + cable = &ci->platdata->vbus_extcon; + if (!IS_ERR(cable->edev)) { + if (data & mask & OTGSC_BSVIS) + cable->changed = false; + + /* Don't enable vbus interrupt if using external notifier */ + if (data & mask & OTGSC_BSVIE) { + cable->enabled = true; + data &= ~OTGSC_BSVIE; + } else if (mask & OTGSC_BSVIE) { + cable->enabled = false; + } + } + + cable = &ci->platdata->id_extcon; + if (!IS_ERR(cable->edev)) { + if (data & mask & OTGSC_IDIS) + cable->changed = false; + + /* Don't enable id interrupt if using external notifier */ + if (data & mask & OTGSC_IDIE) { + cable->enabled = true; + data &= ~OTGSC_IDIE; + } else if (mask & OTGSC_IDIE) { + cable->enabled = false; + } + } + hw_write(ci, OP_OTGSC, mask | OTGSC_INT_STATUS_BITS, data); } @@ -104,7 +140,31 @@ void ci_handle_vbus_change(struct ci_hdrc *ci) usb_gadget_vbus_disconnect(&ci->gadget); } -#define CI_VBUS_STABLE_TIMEOUT_MS 5000 +/** + * When we switch to device mode, the vbus value should be lower + * than OTGSC_BSV before connecting to host. + * + * @ci: the controller + * + * This function returns an error code if timeout + */ +static int hw_wait_vbus_lower_bsv(struct ci_hdrc *ci) +{ + unsigned long elapse = jiffies + msecs_to_jiffies(5000); + u32 mask = OTGSC_BSV; + + while (hw_read_otgsc(ci, mask)) { + if (time_after(jiffies, elapse)) { + dev_err(ci->dev, "timeout waiting for %08x in OTGSC\n", + mask); + return -ETIMEDOUT; + } + msleep(20); + } + + return 0; +} + static void ci_handle_id_switch(struct ci_hdrc *ci) { enum ci_role role = ci_otg_role(ci); @@ -116,9 +176,11 @@ static void ci_handle_id_switch(struct ci_hdrc *ci) ci_role_stop(ci); if (role == CI_ROLE_GADGET) - /* wait vbus lower than OTGSC_BSV */ - hw_wait_reg(ci, OP_OTGSC, OTGSC_BSV, 0, - CI_VBUS_STABLE_TIMEOUT_MS); + /* + * wait vbus lower than OTGSC_BSV before connecting + * to host + */ + hw_wait_vbus_lower_bsv(ci); ci_role_start(ci, role); } diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index d8a045fc1fdb..aff086ca97e4 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1982,6 +1982,7 @@ static void udc_id_switch_for_host(struct ci_hdrc *ci) int ci_hdrc_gadget_init(struct ci_hdrc *ci) { struct ci_role_driver *rdrv; + int ret; if (!hw_read(ci, CAP_DCCPARAMS, DCCPARAMS_DC)) return -ENXIO; @@ -1994,7 +1995,10 @@ int ci_hdrc_gadget_init(struct ci_hdrc *ci) rdrv->stop = udc_id_switch_for_host; rdrv->irq = udc_irq; rdrv->name = "gadget"; - ci->roles[CI_ROLE_GADGET] = rdrv; - return udc_start(ci); + ret = udc_start(ci); + if (!ret) + ci->roles[CI_ROLE_GADGET] = rdrv; + + return ret; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 96849e2e7435..df96f5f88c15 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -311,6 +311,12 @@ static void acm_ctrl_irq(struct urb *urb) break; case USB_CDC_NOTIFY_SERIAL_STATE: + if (le16_to_cpu(dr->wLength) != 2) { + dev_dbg(&acm->control->dev, + "%s - malformed serial state\n", __func__); + break; + } + newctrl = get_unaligned_le16(data); if (!acm->clocal && (acm->ctrlin & ~newctrl & ACM_CTRL_DCD)) { @@ -347,11 +353,10 @@ static void acm_ctrl_irq(struct urb *urb) default: dev_dbg(&acm->control->dev, - "%s - unknown notification %d received: index %d " - "len %d data0 %d data1 %d\n", + "%s - unknown notification %d received: index %d len %d\n", __func__, - dr->bNotificationType, dr->wIndex, - dr->wLength, data[0], data[1]); + dr->bNotificationType, dr->wIndex, dr->wLength); + break; } exit: @@ -1754,6 +1759,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x1576, 0x03b1), /* Maretron USB100 */ .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ }, + { USB_DEVICE(0xfff0, 0x0100), /* DATECS FP-2000 */ + .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index deaddb950c20..24337ac3323f 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1105,7 +1105,7 @@ static int usbtmc_probe(struct usb_interface *intf, dev_dbg(&intf->dev, "%s called\n", __func__); - data = kmalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -1163,6 +1163,12 @@ static int usbtmc_probe(struct usb_interface *intf, } } + if (!data->bulk_out || !data->bulk_in) { + dev_err(&intf->dev, "bulk endpoints not found\n"); + retcode = -ENODEV; + goto err_put; + } + retcode = get_capabilities(data); if (retcode) dev_err(&intf->dev, "can't read capabilities\n"); @@ -1186,6 +1192,7 @@ static int usbtmc_probe(struct usb_interface *intf, error_register: sysfs_remove_group(&intf->dev.kobj, &capability_attr_grp); sysfs_remove_group(&intf->dev.kobj, &data_attr_grp); +err_put: kref_put(&data->kref, usbtmc_delete); return retcode; } diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index ac30a051ad71..325cbc9c35d8 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -246,6 +246,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, /* * Adjust bInterval for quirked devices. + */ + /* + * This quirk fixes bIntervals reported in ms. + */ + if (to_usb_device(ddev)->quirks & + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { + n = clamp(fls(d->bInterval) + 3, i, j); + i = j = n; + } + /* * This quirk fixes bIntervals reported in * linear microframes. */ diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index f5c92d904ded..54d2d6b604c0 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -373,11 +373,11 @@ static void snoop_urb(struct usb_device *udev, if (userurb) { /* Async */ if (when == SUBMIT) - dev_info(&udev->dev, "userurb %p, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " "length %u\n", userurb, ep, t, d, length); else - dev_info(&udev->dev, "userurb %p, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " "actual_length %u status %d\n", userurb, ep, t, d, length, timeout_or_status); diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index dadd1e8dfe09..0bb380a9fcf7 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -1328,6 +1328,24 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg) */ if (udev->parent && !PMSG_IS_AUTO(msg)) status = 0; + + /* + * If the device is inaccessible, don't try to resume + * suspended interfaces and just return the error. + */ + if (status && status != -EBUSY) { + int err; + u16 devstat; + + err = usb_get_status(udev, USB_RECIP_DEVICE, 0, + &devstat); + if (err) { + dev_err(&udev->dev, + "Failed to suspend device, error %d\n", + status); + goto done; + } + } } /* If the suspend failed, resume interfaces that did get suspended */ @@ -1760,6 +1778,9 @@ static int autosuspend_check(struct usb_device *udev) int w, i; struct usb_interface *intf; + if (udev->state == USB_STATE_NOTATTACHED) + return -ENODEV; + /* Fail if autosuspend is disabled, or any interfaces are in use, or * any interface drivers require remote wakeup but it isn't available. */ diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c index ea337a718cc1..b3de806085f0 100644 --- a/drivers/usb/core/file.c +++ b/drivers/usb/core/file.c @@ -26,6 +26,7 @@ #define MAX_USB_MINORS 256 static const struct file_operations *usb_minors[MAX_USB_MINORS]; static DECLARE_RWSEM(minor_rwsem); +static DEFINE_MUTEX(init_usb_class_mutex); static int usb_open(struct inode *inode, struct file *file) { @@ -108,8 +109,9 @@ static void release_usb_class(struct kref *kref) static void destroy_usb_class(void) { - if (usb_class) - kref_put(&usb_class->kref, release_usb_class); + mutex_lock(&init_usb_class_mutex); + kref_put(&usb_class->kref, release_usb_class); + mutex_unlock(&init_usb_class_mutex); } int usb_major_init(void) @@ -171,7 +173,10 @@ int usb_register_dev(struct usb_interface *intf, if (intf->minor >= 0) return -EADDRINUSE; + mutex_lock(&init_usb_class_mutex); retval = init_usb_class(); + mutex_unlock(&init_usb_class_mutex); + if (retval) return retval; diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 7aa1cb59fb92..9fa19c5fb471 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -500,8 +500,10 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb) */ tbuf_size = max_t(u16, sizeof(struct usb_hub_descriptor), wLength); tbuf = kzalloc(tbuf_size, GFP_KERNEL); - if (!tbuf) - return -ENOMEM; + if (!tbuf) { + status = -ENOMEM; + goto err_alloc; + } bufp = tbuf; @@ -706,6 +708,7 @@ error: } kfree(tbuf); + err_alloc: /* any errors get returned through the urb completion */ spin_lock_irq(&hcd_root_hub_lock); @@ -967,7 +970,7 @@ static void usb_bus_init (struct usb_bus *bus) bus->bandwidth_allocated = 0; bus->bandwidth_int_reqs = 0; bus->bandwidth_isoc_reqs = 0; - mutex_init(&bus->usb_address0_mutex); + mutex_init(&bus->devnum_next_mutex); INIT_LIST_HEAD (&bus->bus_list); } @@ -1694,7 +1697,7 @@ int usb_hcd_unlink_urb (struct urb *urb, int status) if (retval == 0) retval = -EINPROGRESS; else if (retval != -EIDRM && retval != -EBUSY) - dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n", + dev_dbg(&udev->dev, "hcd_unlink_urb %pK fail %d\n", urb, retval); usb_put_dev(udev); } @@ -1849,7 +1852,7 @@ void usb_hcd_flush_endpoint(struct usb_device *udev, /* No more submits can occur */ spin_lock_irq(&hcd_urb_list_lock); rescan: - list_for_each_entry (urb, &ep->urb_list, urb_list) { + list_for_each_entry_reverse(urb, &ep->urb_list, urb_list) { int is_in; if (urb->unlinked) @@ -1861,7 +1864,7 @@ rescan: /* kick hcd */ unlink1(hcd, urb, -ESHUTDOWN); dev_dbg (hcd->self.controller, - "shutdown urb %p ep%d%s%s\n", + "shutdown urb %pK ep%d%s%s\n", urb, usb_endpoint_num(&ep->desc), is_in ? "in" : "out", ({ char *s; @@ -2446,6 +2449,8 @@ void usb_hc_died (struct usb_hcd *hcd) } if (usb_hcd_is_primary_hcd(hcd) && hcd->shared_hcd) { hcd = hcd->shared_hcd; + clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags); + set_bit(HCD_FLAG_DEAD, &hcd->flags); if (hcd->rh_registered) { clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); @@ -2498,9 +2503,18 @@ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver, return NULL; } if (primary_hcd == NULL) { + hcd->address0_mutex = kmalloc(sizeof(*hcd->address0_mutex), + GFP_KERNEL); + if (!hcd->address0_mutex) { + kfree(hcd); + dev_dbg(dev, "hcd address0 mutex alloc failed\n"); + return NULL; + } + mutex_init(hcd->address0_mutex); hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex), GFP_KERNEL); if (!hcd->bandwidth_mutex) { + kfree(hcd->address0_mutex); kfree(hcd); dev_dbg(dev, "hcd bandwidth mutex alloc failed\n"); return NULL; @@ -2509,6 +2523,7 @@ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver, dev_set_drvdata(dev, hcd); } else { mutex_lock(&usb_port_peer_mutex); + hcd->address0_mutex = primary_hcd->address0_mutex; hcd->bandwidth_mutex = primary_hcd->bandwidth_mutex; hcd->primary_hcd = primary_hcd; primary_hcd->primary_hcd = primary_hcd; @@ -2565,24 +2580,23 @@ EXPORT_SYMBOL_GPL(usb_create_hcd); * Don't deallocate the bandwidth_mutex until the last shared usb_hcd is * deallocated. * - * Make sure to only deallocate the bandwidth_mutex when the primary HCD is - * freed. When hcd_release() is called for either hcd in a peer set - * invalidate the peer's ->shared_hcd and ->primary_hcd pointers to - * block new peering attempts + * Make sure to deallocate the bandwidth_mutex only when the last HCD is + * freed. When hcd_release() is called for either hcd in a peer set, + * invalidate the peer's ->shared_hcd and ->primary_hcd pointers. */ static void hcd_release(struct kref *kref) { struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref); mutex_lock(&usb_port_peer_mutex); - if (usb_hcd_is_primary_hcd(hcd)) - kfree(hcd->bandwidth_mutex); if (hcd->shared_hcd) { struct usb_hcd *peer = hcd->shared_hcd; peer->shared_hcd = NULL; - if (peer->primary_hcd == hcd) - peer->primary_hcd = NULL; + peer->primary_hcd = NULL; + } else { + kfree(hcd->address0_mutex); + kfree(hcd->bandwidth_mutex); } mutex_unlock(&usb_port_peer_mutex); kfree(hcd); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 2f1c4b22ae1c..9dc72e53712f 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -358,7 +358,8 @@ static void usb_set_lpm_parameters(struct usb_device *udev) } /* USB 2.0 spec Section 11.24.4.5 */ -static int get_hub_descriptor(struct usb_device *hdev, void *data) +static int get_hub_descriptor(struct usb_device *hdev, + struct usb_hub_descriptor *desc) { int i, ret, size; unsigned dtype; @@ -374,10 +375,18 @@ static int get_hub_descriptor(struct usb_device *hdev, void *data) for (i = 0; i < 3; i++) { ret = usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0), USB_REQ_GET_DESCRIPTOR, USB_DIR_IN | USB_RT_HUB, - dtype << 8, 0, data, size, + dtype << 8, 0, desc, size, USB_CTRL_GET_TIMEOUT); - if (ret >= (USB_DT_HUB_NONVAR_SIZE + 2)) + if (hub_is_superspeed(hdev)) { + if (ret == size) + return ret; + } else if (ret >= USB_DT_HUB_NONVAR_SIZE + 2) { + /* Make sure we have the DeviceRemovable field. */ + size = USB_DT_HUB_NONVAR_SIZE + desc->bNbrPorts / 8 + 1; + if (ret < size) + return -EMSGSIZE; return ret; + } } return -EINVAL; } @@ -1048,6 +1057,9 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) portstatus = portchange = 0; status = hub_port_status(hub, port1, &portstatus, &portchange); + if (status) + goto abort; + if (udev || (portstatus & USB_PORT_STAT_CONNECTION)) dev_dbg(&port_dev->dev, "status %04x change %04x\n", portstatus, portchange); @@ -1180,7 +1192,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) /* Scan all ports that need attention */ kick_hub_wq(hub); - + abort: if (type == HUB_INIT2 || type == HUB_INIT3) { /* Allow autosuspend if it was suppressed */ disconnected: @@ -1292,7 +1304,7 @@ static int hub_configure(struct usb_hub *hub, } mutex_init(&hub->status_mutex); - hub->descriptor = kmalloc(sizeof(*hub->descriptor), GFP_KERNEL); + hub->descriptor = kzalloc(sizeof(*hub->descriptor), GFP_KERNEL); if (!hub->descriptor) { ret = -ENOMEM; goto fail; @@ -1300,13 +1312,19 @@ static int hub_configure(struct usb_hub *hub, /* Request the entire hub descriptor. * hub->descriptor can handle USB_MAXCHILDREN ports, - * but the hub can/will return fewer bytes here. + * but a (non-SS) hub can/will return fewer bytes here. */ ret = get_hub_descriptor(hdev, hub->descriptor); if (ret < 0) { message = "can't read hub descriptor"; goto fail; - } else if (hub->descriptor->bNbrPorts > USB_MAXCHILDREN) { + } + + maxchild = USB_MAXCHILDREN; + if (hub_is_superspeed(hdev)) + maxchild = min_t(unsigned, maxchild, USB_SS_MAXPORTS); + + if (hub->descriptor->bNbrPorts > maxchild) { message = "hub has too many ports!"; ret = -ENODEV; goto fail; @@ -1980,7 +1998,7 @@ static void choose_devnum(struct usb_device *udev) struct usb_bus *bus = udev->bus; /* be safe when more hub events are proceed in parallel */ - mutex_lock(&bus->usb_address0_mutex); + mutex_lock(&bus->devnum_next_mutex); if (udev->wusb) { devnum = udev->portnum + 1; BUG_ON(test_bit(devnum, bus->devmap.devicemap)); @@ -1998,7 +2016,7 @@ static void choose_devnum(struct usb_device *udev) set_bit(devnum, bus->devmap.devicemap); udev->devnum = devnum; } - mutex_unlock(&bus->usb_address0_mutex); + mutex_unlock(&bus->devnum_next_mutex); } static void release_devnum(struct usb_device *udev) @@ -2068,6 +2086,12 @@ void usb_disconnect(struct usb_device **pdev) dev_info(&udev->dev, "USB disconnect, device number %d\n", udev->devnum); + /* + * Ensure that the pm runtime code knows that the USB device + * is in the process of being disconnected. + */ + pm_runtime_barrier(&udev->dev); + usb_lock_device(udev); hub_disconnect_children(udev); @@ -2609,8 +2633,15 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1, if (ret < 0) return ret; - /* The port state is unknown until the reset completes. */ - if (!(portstatus & USB_PORT_STAT_RESET)) + /* + * The port state is unknown until the reset completes. + * + * On top of that, some chips may require additional time + * to re-establish a connection after the reset is complete, + * so also wait for the connection to be re-established. + */ + if (!(portstatus & USB_PORT_STAT_RESET) && + (portstatus & USB_PORT_STAT_CONNECTION)) break; /* switch to the long delay after two short delay failures */ @@ -4206,7 +4237,7 @@ static void hub_set_initial_usb2_lpm_policy(struct usb_device *udev) struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent); int connect_type = USB_PORT_CONNECT_TYPE_UNKNOWN; - if (!udev->usb2_hw_lpm_capable) + if (!udev->usb2_hw_lpm_capable || !udev->bos) return; if (hub) @@ -4274,7 +4305,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, if (oldspeed == USB_SPEED_LOW) delay = HUB_LONG_RESET_TIME; - mutex_lock(&hdev->bus->usb_address0_mutex); + mutex_lock(hcd->address0_mutex); /* Reset the device; full speed may morph to high speed */ /* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */ @@ -4560,7 +4591,7 @@ fail: hub_port_disable(hub, port1, 0); update_devnum(udev, devnum); /* for disconnect processing */ } - mutex_unlock(&hdev->bus->usb_address0_mutex); + mutex_unlock(hcd->address0_mutex); return retval; } @@ -4642,7 +4673,8 @@ hub_power_remaining(struct usb_hub *hub) static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, u16 portchange) { - int status, i; + int status = -ENODEV; + int i; unsigned unit_load; struct usb_device *hdev = hub->hdev; struct usb_hcd *hcd = bus_to_hcd(hdev->bus); @@ -4846,9 +4878,10 @@ loop: done: hub_port_disable(hub, port1, 1); - if (hcd->driver->relinquish_port && !hub->hdev->parent) - hcd->driver->relinquish_port(hcd, port1); - + if (hcd->driver->relinquish_port && !hub->hdev->parent) { + if (status != -ENOTCONN && status != -ENODEV) + hcd->driver->relinquish_port(hcd, port1); + } } /* Handle physical or logical connection change events. diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index d2e50a27140c..574da2b4529c 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -37,6 +37,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* CBM - Flash disk */ { USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME }, + /* WORLDE easy key (easykey.25) MIDI controller */ + { USB_DEVICE(0x0218, 0x0401), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* HP 5300/5370C scanner */ { USB_DEVICE(0x03f0, 0x0701), .driver_info = USB_QUIRK_STRING_FETCH_255 }, @@ -146,6 +150,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* appletouch */ { USB_DEVICE(0x05ac, 0x021a), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */ + { USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM }, + /* Avision AV600U */ { USB_DEVICE(0x0638, 0x0a13), .driver_info = USB_QUIRK_STRING_FETCH_255 }, @@ -166,6 +173,14 @@ static const struct usb_device_id usb_quirk_list[] = { /* M-Systems Flash Disk Pioneers */ { USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Baum Vario Ultra */ + { USB_DEVICE(0x0904, 0x6101), .driver_info = + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + { USB_DEVICE(0x0904, 0x6102), .driver_info = + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + { USB_DEVICE(0x0904, 0x6103), .driver_info = + USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + /* Keytouch QWERTY Panel keyboard */ { USB_DEVICE(0x0926, 0x3333), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -211,6 +226,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* Blackmagic Design UltraStudio SDI */ { USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM }, + /* Hauppauge HVR-950q */ + { USB_DEVICE(0x2040, 0x7200), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -233,6 +252,7 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { { USB_DEVICE(0x093a, 0x2500), .driver_info = USB_QUIRK_RESET_RESUME }, { USB_DEVICE(0x093a, 0x2510), .driver_info = USB_QUIRK_RESET_RESUME }, { USB_DEVICE(0x093a, 0x2521), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x03f0, 0x2b4a), .driver_info = USB_QUIRK_RESET_RESUME }, /* Logitech Optical Mouse M90/M100 */ { USB_DEVICE(0x046d, 0xc05a), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index c601e25b609f..e43ef7d2d00e 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -335,7 +335,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags) if (!urb || !urb->complete) return -EINVAL; if (urb->hcpriv) { - WARN_ONCE(1, "URB %p submitted while active\n", urb); + WARN_ONCE(1, "URB %pK submitted while active\n", urb); return -EBUSY; } diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c index 2776cfe64c09..ef9cf4a21afe 100644 --- a/drivers/usb/core/usb-acpi.c +++ b/drivers/usb/core/usb-acpi.c @@ -127,6 +127,22 @@ out: */ #define USB_ACPI_LOCATION_VALID (1 << 31) +static struct acpi_device *usb_acpi_find_port(struct acpi_device *parent, + int raw) +{ + struct acpi_device *adev; + + if (!parent) + return NULL; + + list_for_each_entry(adev, &parent->children, node) { + if (acpi_device_adr(adev) == raw) + return adev; + } + + return acpi_find_child_device(parent, raw, false); +} + static struct acpi_device *usb_acpi_find_companion(struct device *dev) { struct usb_device *udev; @@ -174,8 +190,10 @@ static struct acpi_device *usb_acpi_find_companion(struct device *dev) int raw; raw = usb_hcd_find_raw_port_number(hcd, port1); - adev = acpi_find_child_device(ACPI_COMPANION(&udev->dev), - raw, false); + + adev = usb_acpi_find_port(ACPI_COMPANION(&udev->dev), + raw); + if (!adev) return NULL; } else { @@ -186,7 +204,9 @@ static struct acpi_device *usb_acpi_find_companion(struct device *dev) return NULL; acpi_bus_get_device(parent_handle, &adev); - adev = acpi_find_child_device(adev, port1, false); + + adev = usb_acpi_find_port(adev, port1); + if (!adev) return NULL; } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 40d45b3a8754..b66723a77db3 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -854,7 +854,7 @@ struct dwc3 { struct usb_gadget gadget; struct usb_gadget_driver *gadget_driver; - struct completion reset_event; /* used for run/stop workaround */ + bool reset_event; /* used for run/stop workaround */ struct usb_phy *usb2_phy; struct usb_phy *usb3_phy; diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 2f1fb7e7aa54..9eba51b92f72 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -148,7 +148,8 @@ static int dwc3_exynos_probe(struct platform_device *pdev) exynos->axius_clk = devm_clk_get(dev, "usbdrd30_axius_clk"); if (IS_ERR(exynos->axius_clk)) { dev_err(dev, "no AXI UpScaler clk specified\n"); - return -ENODEV; + ret = -ENODEV; + goto axius_clk_err; } clk_prepare_enable(exynos->axius_clk); } else { @@ -206,6 +207,7 @@ err3: regulator_disable(exynos->vdd33); err2: clk_disable_unprepare(exynos->axius_clk); +axius_clk_err: clk_disable_unprepare(exynos->susp_clk); clk_disable_unprepare(exynos->clk); return ret; diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c index 5c0adb9c6fb2..81db2fa08cad 100644 --- a/drivers/usb/dwc3/dwc3-st.c +++ b/drivers/usb/dwc3/dwc3-st.c @@ -224,7 +224,7 @@ static int st_dwc3_probe(struct platform_device *pdev) dwc3_data->syscfg_reg_off = res->start; - dev_vdbg(&pdev->dev, "glue-logic addr 0x%p, syscfg-reg offset 0x%x\n", + dev_vdbg(&pdev->dev, "glue-logic addr 0x%pK, syscfg-reg offset 0x%x\n", dwc3_data->glue_base, dwc3_data->syscfg_reg_off); dwc3_data->rstc_pwrdn = devm_reset_control_get(dev, "powerdown"); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index fbb6da302319..c778c511ea90 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -238,6 +238,7 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req, int status) { struct dwc3 *dwc = dep->dwc; + unsigned int unmap_after_complete = false; int i; if (req->queued) { @@ -262,11 +263,19 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req, if (req->request.status == -EINPROGRESS) req->request.status = status; - if (dwc->ep0_bounced && dep->number <= 1) + /* + * NOTICE we don't want to unmap before calling ->complete() if we're + * dealing with a bounced ep0 request. If we unmap it here, we would end + * up overwritting the contents of req->buf and this could confuse the + * gadget driver. + */ + if (dwc->ep0_bounced && dep->number <= 1) { dwc->ep0_bounced = false; - - usb_gadget_unmap_request(&dwc->gadget, &req->request, - req->direction); + unmap_after_complete = true; + } else { + usb_gadget_unmap_request(&dwc->gadget, + &req->request, req->direction); + } dev_dbg(dwc->dev, "request %p from %s completed %d/%d ===> %d\n", req, dep->name, req->request.actual, @@ -276,6 +285,10 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req, spin_unlock(&dwc->lock); usb_gadget_giveback_request(&dep->endpoint, &req->request); spin_lock(&dwc->lock); + + if (unmap_after_complete) + usb_gadget_unmap_request(&dwc->gadget, + &req->request, req->direction); } int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned cmd, u32 param) @@ -1221,7 +1234,7 @@ static int dwc3_gadget_ep_queue(struct usb_ep *ep, struct usb_request *request, goto out; } - if (WARN(req->dep != dep, "request %p belongs to '%s'\n", + if (WARN(req->dep != dep, "request %pK belongs to '%s'\n", request, req->dep->name)) { ret = -EINVAL; goto out; @@ -1276,7 +1289,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, dwc3_stop_active_transfer(dwc, dep->number, true); goto out1; } - dev_err(dwc->dev, "request %p was not queued to %s\n", + dev_err(dwc->dev, "request %pK was not queued to %s\n", request, ep->name); ret = -EINVAL; goto out0; @@ -1566,11 +1579,10 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) is_on = !!is_on; - if (is_on) - reinit_completion(&dwc->reset_event); - spin_lock_irqsave(&dwc->lock, flags); ret = dwc3_gadget_run_stop(dwc, is_on, false); + if (is_on) + dwc->reset_event = 0; spin_unlock_irqrestore(&dwc->lock, flags); try: @@ -1593,7 +1605,7 @@ try: if (is_on && dwc->revision < DWC3_REVISION_220A && dwc->current_mode == DWC3_GCTL_PRTCAP_DEVICE) { u32 devspd, ltssm; - unsigned long t; + int i; /* only applicable if devspd != SUPERSPEED */ devspd = dwc3_readl(dwc->regs, DWC3_DCFG) & DWC3_DCFG_SPEED_MASK; @@ -1605,17 +1617,25 @@ try: * metastability issue. If we got a reset event then we are * safe and can continue. */ - t = wait_for_completion_timeout(&dwc->reset_event, - msecs_to_jiffies(100)); - if (t) - goto done; + for (i = 0; i < 100; i++) { + if (dwc->reset_event) + goto done; + + /* get link state */ + ltssm = dwc3_readl(dwc->regs, DWC3_GDBGLTSSM); + ltssm = (ltssm >> 22) & 0xf; + + /** + * If link state != 4 we've hit the metastability issue. + */ + if (ltssm != 4) + break; - /* get link state */ - ltssm = dwc3_readl(dwc->regs, DWC3_GDBGLTSSM); - ltssm = (ltssm >> 22) & 0xf; + mdelay(1); + } /** - * If link state != 4 we've hit the metastability issue, soft reset. + * If link state == 4 after 100ms, we've not hit the metastability issue. */ if (ltssm == 4) goto done; @@ -1643,7 +1663,6 @@ try: return ret; } - reinit_completion(&dwc->reset_event); /* restart gadget */ ret = dwc3_gadget_restart(dwc); if (ret) { @@ -1983,7 +2002,7 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, * would help. Lets hope that if this occurs, someone * fixes the root cause instead of looking away :) */ - dev_err(dwc->dev, "%s's TRB (%p) still owned by HW\n", + dev_err(dwc->dev, "%s's TRB (%pK) still owned by HW\n", dep->name, trb); count = trb->size & DWC3_TRB_SIZE_MASK; @@ -2417,7 +2436,7 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) } /* notify run/stop metastability workaround */ - complete(&dwc->reset_event); + dwc->reset_event = 1; dwc3_reset_gadget(dwc); @@ -2958,8 +2977,6 @@ int dwc3_gadget_init(struct dwc3 *dwc) */ dwc->gadget.quirk_ep_out_aligned_size = true; - init_completion(&dwc->reset_event); - /* * REVISIT: Here we should clear all pending IRQs to be * sure we're starting from a well known location. diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index 18ae3eaa8b6f..ccd9694f8e36 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -28,23 +28,23 @@ struct dwc3; #define gadget_to_dwc(g) (container_of(g, struct dwc3, gadget)) /* DEPCFG parameter 1 */ -#define DWC3_DEPCFG_INT_NUM(n) ((n) << 0) +#define DWC3_DEPCFG_INT_NUM(n) (((n) & 0x1f) << 0) #define DWC3_DEPCFG_XFER_COMPLETE_EN (1 << 8) #define DWC3_DEPCFG_XFER_IN_PROGRESS_EN (1 << 9) #define DWC3_DEPCFG_XFER_NOT_READY_EN (1 << 10) #define DWC3_DEPCFG_FIFO_ERROR_EN (1 << 11) #define DWC3_DEPCFG_STREAM_EVENT_EN (1 << 13) -#define DWC3_DEPCFG_BINTERVAL_M1(n) ((n) << 16) +#define DWC3_DEPCFG_BINTERVAL_M1(n) (((n) & 0xff) << 16) #define DWC3_DEPCFG_STREAM_CAPABLE (1 << 24) -#define DWC3_DEPCFG_EP_NUMBER(n) ((n) << 25) +#define DWC3_DEPCFG_EP_NUMBER(n) (((n) & 0x1f) << 25) #define DWC3_DEPCFG_BULK_BASED (1 << 30) #define DWC3_DEPCFG_FIFO_BASED (1 << 31) /* DEPCFG parameter 0 */ -#define DWC3_DEPCFG_EP_TYPE(n) ((n) << 1) -#define DWC3_DEPCFG_MAX_PACKET_SIZE(n) ((n) << 3) -#define DWC3_DEPCFG_FIFO_NUMBER(n) ((n) << 17) -#define DWC3_DEPCFG_BURST_SIZE(n) ((n) << 22) +#define DWC3_DEPCFG_EP_TYPE(n) (((n) & 0x3) << 1) +#define DWC3_DEPCFG_MAX_PACKET_SIZE(n) (((n) & 0x7ff) << 3) +#define DWC3_DEPCFG_FIFO_NUMBER(n) (((n) & 0x1f) << 17) +#define DWC3_DEPCFG_BURST_SIZE(n) (((n) & 0xf) << 22) #define DWC3_DEPCFG_DATA_SEQ_NUM(n) ((n) << 26) /* This applies for core versions earlier than 1.94a */ #define DWC3_DEPCFG_IGN_SEQ_NUM (1 << 31) diff --git a/drivers/usb/gadget/function/f_accessory.c b/drivers/usb/gadget/function/f_accessory.c index 9d3ec0e37475..76b8ae08a551 100644 --- a/drivers/usb/gadget/function/f_accessory.c +++ b/drivers/usb/gadget/function/f_accessory.c @@ -77,9 +77,13 @@ struct acc_dev { struct usb_ep *ep_in; struct usb_ep *ep_out; - /* set to 1 when we connect */ + /* online indicates state of function_set_alt & function_unbind + * set to 1 when we connect + */ int online:1; - /* Set to 1 when we disconnect. + + /* disconnected indicates state of open & release + * Set to 1 when we disconnect. * Not cleared until our file is closed. */ int disconnected:1; @@ -263,7 +267,6 @@ static struct usb_request *req_get(struct acc_dev *dev, struct list_head *head) static void acc_set_disconnected(struct acc_dev *dev) { - dev->online = 0; dev->disconnected = 1; } @@ -676,9 +679,10 @@ static ssize_t acc_write(struct file *fp, const char __user *buf, req->zero = 0; } else { xfer = count; - /* If the data length is a multple of the + /* + * If the data length is a multple of the * maxpacket size then send a zero length packet(ZLP). - */ + */ req->zero = ((xfer % dev->ep_in->maxpacket) == 0); } if (copy_from_user(req->buf, buf, xfer)) { @@ -763,7 +767,10 @@ static int acc_release(struct inode *ip, struct file *fp) printk(KERN_INFO "acc_release\n"); WARN_ON(!atomic_xchg(&_acc_dev->open_excl, 0)); - _acc_dev->disconnected = 0; + /* indicate that we are disconnected + * still could be online so don't touch online flag + */ + _acc_dev->disconnected = 1; return 0; } @@ -820,11 +827,11 @@ int acc_ctrlrequest(struct usb_composite_dev *cdev, unsigned long flags; /* - printk(KERN_INFO "acc_ctrlrequest " - "%02x.%02x v%04x i%04x l%u\n", - b_requestType, b_request, - w_value, w_index, w_length); -*/ + * printk(KERN_INFO "acc_ctrlrequest " + * "%02x.%02x v%04x i%04x l%u\n", + * b_requestType, b_request, + * w_value, w_index, w_length); + */ if (b_requestType == (USB_DIR_OUT | USB_TYPE_VENDOR)) { if (b_request == ACCESSORY_START) { @@ -1011,6 +1018,10 @@ acc_function_unbind(struct usb_configuration *c, struct usb_function *f) struct usb_request *req; int i; + dev->online = 0; /* clear online flag */ + wake_up(&dev->read_wq); /* unblock reads on closure */ + wake_up(&dev->write_wq); /* likewise for writes */ + while ((req = req_get(dev, &dev->tx_idle))) acc_request_free(req, dev->ep_in); for (i = 0; i < RX_REQ_MAX; i++) @@ -1142,6 +1153,7 @@ static int acc_function_set_alt(struct usb_function *f, } dev->online = 1; + dev->disconnected = 0; /* if online then not disconnected */ /* readers may be blocked waiting for us to go online */ wake_up(&dev->read_wq); @@ -1154,7 +1166,8 @@ static void acc_function_disable(struct usb_function *f) struct usb_composite_dev *cdev = dev->cdev; DBG(cdev, "acc_function_disable\n"); - acc_set_disconnected(dev); + acc_set_disconnected(dev); /* this now only sets disconnected */ + dev->online = 0; /* so now need to clear online flag here too */ usb_ep_disable(dev->ep_in); usb_ep_disable(dev->ep_out); diff --git a/drivers/usb/gadget/function/f_acm.c b/drivers/usb/gadget/function/f_acm.c index 2fa1e80a3ce7..67e474b13fca 100644 --- a/drivers/usb/gadget/function/f_acm.c +++ b/drivers/usb/gadget/function/f_acm.c @@ -535,13 +535,15 @@ static int acm_notify_serial_state(struct f_acm *acm) { struct usb_composite_dev *cdev = acm->port.func.config->cdev; int status; + __le16 serial_state; spin_lock(&acm->lock); if (acm->notify_req) { dev_dbg(&cdev->gadget->dev, "acm ttyGS%d serial state %04x\n", acm->port_num, acm->serial_state); + serial_state = cpu_to_le16(acm->serial_state); status = acm_cdc_notify(acm, USB_CDC_NOTIFY_SERIAL_STATE, - 0, &acm->serial_state, sizeof(acm->serial_state)); + 0, &serial_state, sizeof(acm->serial_state)); } else { acm->pending = true; status = 0; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 803c503a2e3d..732e6ed5d7b4 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1643,11 +1643,14 @@ static int ffs_func_eps_enable(struct ffs_function *func) spin_lock_irqsave(&func->ffs->eps_lock, flags); do { struct usb_endpoint_descriptor *ds; + struct usb_ss_ep_comp_descriptor *comp_desc = NULL; + int needs_comp_desc = false; int desc_idx; - if (ffs->gadget->speed == USB_SPEED_SUPER) + if (ffs->gadget->speed == USB_SPEED_SUPER) { desc_idx = 2; - else if (ffs->gadget->speed == USB_SPEED_HIGH) + needs_comp_desc = true; + } else if (ffs->gadget->speed == USB_SPEED_HIGH) desc_idx = 1; else desc_idx = 0; @@ -1664,6 +1667,14 @@ static int ffs_func_eps_enable(struct ffs_function *func) ep->ep->driver_data = ep; ep->ep->desc = ds; + + if (needs_comp_desc) { + comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds + + USB_DT_ENDPOINT_SIZE); + ep->ep->maxburst = comp_desc->bMaxBurst + 1; + ep->ep->comp_desc = comp_desc; + } + ret = usb_ep_enable(ep->ep); if (likely(!ret)) { epfile->ep = ep; @@ -2079,6 +2090,8 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type, if (len < sizeof(*d) || h->interface >= ffs->interfaces_count) return -EINVAL; length = le32_to_cpu(d->dwSize); + if (len < length) + return -EINVAL; type = le32_to_cpu(d->dwPropertyDataType); if (type < USB_EXT_PROP_UNICODE || type > USB_EXT_PROP_UNICODE_MULTI) { @@ -2087,6 +2100,11 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type, return -EINVAL; } pnl = le16_to_cpu(d->wPropertyNameLength); + if (length < 14 + pnl) { + pr_vdebug("invalid os descriptor length: %d pnl:%d (descriptor %d)\n", + length, pnl, type); + return -EINVAL; + } pdl = le32_to_cpu(*(u32 *)((u8 *)data + 10 + pnl)); if (length != 14 + pnl + pdl) { pr_vdebug("invalid os descriptor length: %d pnl:%d pdl:%d (descriptor %d)\n", @@ -2171,6 +2189,9 @@ static int __ffs_data_got_descs(struct ffs_data *ffs, } } if (flags & (1 << i)) { + if (len < 4) { + goto error; + } os_descs_count = get_unaligned_le32(data); data += 4; len -= 4; @@ -2243,7 +2264,8 @@ static int __ffs_data_got_strings(struct ffs_data *ffs, ENTER(); - if (unlikely(get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC || + if (unlikely(len < 16 || + get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC || get_unaligned_le32(data + 4) != len)) goto error; str_count = get_unaligned_le32(data + 8); @@ -3441,6 +3463,7 @@ static void ffs_closed(struct ffs_data *ffs) { struct ffs_dev *ffs_obj; struct f_fs_opts *opts; + struct config_item *ci; ENTER(); ffs_dev_lock(); @@ -3464,8 +3487,11 @@ static void ffs_closed(struct ffs_data *ffs) || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount)) goto done; - unregister_gadget_item(ffs_obj->opts-> - func_inst.group.cg_item.ci_parent->ci_parent); + ci = opts->func_inst.group.cg_item.ci_parent->ci_parent; + ffs_dev_unlock(); + + unregister_gadget_item(ci); + return; done: ffs_dev_unlock(); } diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 99285b416308..ee579ba2b59e 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -539,7 +539,7 @@ static int hidg_set_alt(struct usb_function *f, unsigned intf, unsigned alt) } status = usb_ep_enable(hidg->out_ep); if (status < 0) { - ERROR(cdev, "Enable IN endpoint FAILED!\n"); + ERROR(cdev, "Enable OUT endpoint FAILED!\n"); goto fail; } hidg->out_ep->driver_data = hidg; diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index a4f664062e0c..a069726da72a 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -399,7 +399,11 @@ static int fsg_set_halt(struct fsg_dev *fsg, struct usb_ep *ep) /* Caller must hold fsg->lock */ static void wakeup_thread(struct fsg_common *common) { - smp_wmb(); /* ensure the write of bh->state is complete */ + /* + * Ensure the reading of thread_wakeup_needed + * and the writing of bh->state are completed + */ + smp_mb(); /* Tell the main thread that something has happened */ common->thread_wakeup_needed = 1; if (common->thread_task) @@ -630,7 +634,12 @@ static int sleep_thread(struct fsg_common *common, bool can_freeze) } __set_current_state(TASK_RUNNING); common->thread_wakeup_needed = 0; - smp_rmb(); /* ensure the latest bh->state is visible */ + + /* + * Ensure the writing of thread_wakeup_needed + * and the reading of bh->state are completed + */ + smp_mb(); return rc; } diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 847f70363477..315c2690afe1 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -361,7 +361,9 @@ static int f_midi_set_alt(struct usb_function *f, unsigned intf, unsigned alt) /* allocate a bunch of read buffers and queue them all at once. */ for (i = 0; i < midi->qlen && err == 0; i++) { struct usb_request *req = - midi_alloc_ep_req(midi->out_ep, midi->buflen); + midi_alloc_ep_req(midi->out_ep, + max_t(unsigned, midi->buflen, + bulk_out_desc.wMaxPacketSize)); if (req == NULL) return -ENOMEM; diff --git a/drivers/usb/gadget/function/f_mtp.c b/drivers/usb/gadget/function/f_mtp.c index d8b69af6e335..b37cc8d87ca4 100644 --- a/drivers/usb/gadget/function/f_mtp.c +++ b/drivers/usb/gadget/function/f_mtp.c @@ -540,10 +540,12 @@ static ssize_t mtp_read(struct file *fp, char __user *buf, ssize_t r = count; unsigned xfer; int ret = 0; + size_t len; DBG(cdev, "mtp_read(%zu)\n", count); - if (count > MTP_BULK_BUFFER_SIZE) + len = usb_ep_align_maybe(cdev->gadget, dev->ep_out, count); + if (len > MTP_BULK_BUFFER_SIZE) return -EINVAL; /* we will block until we're online */ @@ -567,7 +569,7 @@ static ssize_t mtp_read(struct file *fp, char __user *buf, requeue_req: /* queue a request */ req = dev->rx_req[0]; - req->length = count; + req->length = len; dev->rx_done = 0; ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL); if (ret < 0) { diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index 29b41b5dee04..c7689d05356c 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -625,7 +625,7 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f) uvc_ss_streaming_comp.bMaxBurst = opts->streaming_maxburst; uvc_ss_streaming_comp.wBytesPerInterval = cpu_to_le16(max_packet_size * max_packet_mult * - opts->streaming_maxburst); + (opts->streaming_maxburst + 1)); /* Allocate endpoints. */ ep = usb_ep_autoconfig(cdev->gadget, &uvc_control_ep); diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index e4920e5e1d64..21bf0a8423d5 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -66,7 +66,7 @@ struct eth_dev { spinlock_t req_lock; /* guard {rx,tx}_reqs */ struct list_head tx_reqs, rx_reqs; - unsigned tx_qlen; + atomic_t tx_qlen; /* Minimum number of TX USB request queued to UDC */ #define TX_REQ_THRESHOLD 5 int no_tx_req_used; @@ -568,6 +568,7 @@ static void tx_complete(struct usb_ep *ep, struct usb_request *req) dev_kfree_skb_any(skb); } + atomic_dec(&dev->tx_qlen); if (netif_carrier_ok(dev->net)) netif_wake_queue(dev->net); } @@ -741,20 +742,13 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb, req->length = length; - /* throttle highspeed IRQ rate back slightly */ - if (gadget_is_dualspeed(dev->gadget) && - (dev->gadget->speed == USB_SPEED_HIGH) && - !list_empty(&dev->tx_reqs)) { - dev->tx_qlen++; - if (dev->tx_qlen == (dev->qmult/2)) { - req->no_interrupt = 0; - dev->tx_qlen = 0; - } else { - req->no_interrupt = 1; - } - } else { - req->no_interrupt = 0; - } + /* throttle high/super speed IRQ rate back slightly */ + if (gadget_is_dualspeed(dev->gadget)) + req->no_interrupt = (((dev->gadget->speed == USB_SPEED_HIGH || + dev->gadget->speed == USB_SPEED_SUPER)) && + !list_empty(&dev->tx_reqs)) + ? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0) + : 0; retval = usb_ep_queue(in, req, GFP_ATOMIC); switch (retval) { @@ -763,6 +757,7 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb, break; case 0: net->trans_start = jiffies; + atomic_inc(&dev->tx_qlen); } if (retval) { @@ -791,7 +786,7 @@ static void eth_start(struct eth_dev *dev, gfp_t gfp_flags) rx_fill(dev, gfp_flags); /* and open the tx floodgates */ - dev->tx_qlen = 0; + atomic_set(&dev->tx_qlen, 0); netif_wake_queue(dev->net); } diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 684c2a85f29c..2edb6948c552 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1675,9 +1675,10 @@ static void gadgetfs_suspend (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); + unsigned long flags; INFO (dev, "suspended from state %d\n", dev->state); - spin_lock (&dev->lock); + spin_lock_irqsave(&dev->lock, flags); switch (dev->state) { case STATE_DEV_SETUP: // VERY odd... host died?? case STATE_DEV_CONNECTED: @@ -1688,7 +1689,7 @@ gadgetfs_suspend (struct usb_gadget *gadget) default: break; } - spin_unlock (&dev->lock); + spin_unlock_irqrestore(&dev->lock, flags); } static struct usb_gadget_driver gadgetfs_driver = { diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index 22d067cd5aa3..64f404a1a072 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -442,23 +442,16 @@ static void set_link_state(struct dummy_hcd *dum_hcd) /* Report reset and disconnect events to the driver */ if (dum->driver && (disconnect || reset)) { stop_activity(dum); - spin_unlock(&dum->lock); if (reset) usb_gadget_udc_reset(&dum->gadget, dum->driver); else dum->driver->disconnect(&dum->gadget); - spin_lock(&dum->lock); } } else if (dum_hcd->active != dum_hcd->old_active) { - if (dum_hcd->old_active && dum->driver->suspend) { - spin_unlock(&dum->lock); + if (dum_hcd->old_active && dum->driver->suspend) dum->driver->suspend(&dum->gadget); - spin_lock(&dum->lock); - } else if (!dum_hcd->old_active && dum->driver->resume) { - spin_unlock(&dum->lock); + else if (!dum_hcd->old_active && dum->driver->resume) dum->driver->resume(&dum->gadget); - spin_lock(&dum->lock); - } } dum_hcd->old_status = dum_hcd->port_status; @@ -985,7 +978,9 @@ static int dummy_udc_stop(struct usb_gadget *g) struct dummy_hcd *dum_hcd = gadget_to_dummy_hcd(g); struct dummy *dum = dum_hcd->dum; + spin_lock_irq(&dum->lock); dum->driver = NULL; + spin_unlock_irq(&dum->lock); return 0; } @@ -1033,6 +1028,8 @@ static int dummy_udc_probe(struct platform_device *pdev) int rc; dum = *((void **)dev_get_platdata(&pdev->dev)); + /* Clear usb_gadget region for new registration to udc-core */ + memzero_explicit(&dum->gadget, sizeof(struct usb_gadget)); dum->gadget.name = gadget_name; dum->gadget.ops = &dummy_ops; dum->gadget.max_speed = USB_SPEED_SUPER; @@ -2009,7 +2006,7 @@ ss_hub_descriptor(struct usb_hub_descriptor *desc) HUB_CHAR_COMMON_OCPM); desc->bNbrPorts = 1; desc->u.ss.bHubHdrDecLat = 0x04; /* Worst case: 0.4 micro sec*/ - desc->u.ss.DeviceRemovable = 0xffff; + desc->u.ss.DeviceRemovable = 0; } static inline void hub_descriptor(struct usb_hub_descriptor *desc) @@ -2021,8 +2018,8 @@ static inline void hub_descriptor(struct usb_hub_descriptor *desc) HUB_CHAR_INDV_PORT_LPSM | HUB_CHAR_COMMON_OCPM); desc->bNbrPorts = 1; - desc->u.hs.DeviceRemovable[0] = 0xff; - desc->u.hs.DeviceRemovable[1] = 0xff; + desc->u.hs.DeviceRemovable[0] = 0; + desc->u.hs.DeviceRemovable[1] = 0xff; /* PortPwrCtrlMask */ } static int dummy_hub_control( diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index aab5221d6c2e..aac0ce8aeb0b 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -1249,6 +1249,12 @@ static const struct usb_gadget_ops fsl_gadget_ops = { .udc_stop = fsl_udc_stop, }; +/* + * Empty complete function used by this driver to fill in the req->complete + * field when creating a request since the complete field is mandatory. + */ +static void fsl_noop_complete(struct usb_ep *ep, struct usb_request *req) { } + /* Set protocol stall on ep0, protocol stall will automatically be cleared on new transaction */ static void ep0stall(struct fsl_udc *udc) @@ -1283,7 +1289,7 @@ static int ep0_prime_status(struct fsl_udc *udc, int direction) req->req.length = 0; req->req.status = -EINPROGRESS; req->req.actual = 0; - req->req.complete = NULL; + req->req.complete = fsl_noop_complete; req->dtd_count = 0; ret = usb_gadget_map_request(&ep->udc->gadget, &req->req, ep_is_in(ep)); @@ -1366,7 +1372,7 @@ static void ch9getstatus(struct fsl_udc *udc, u8 request_type, u16 value, req->req.length = 2; req->req.status = -EINPROGRESS; req->req.actual = 0; - req->req.complete = NULL; + req->req.complete = fsl_noop_complete; req->dtd_count = 0; ret = usb_gadget_map_request(&ep->udc->gadget, &req->req, ep_is_in(ep)); diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index 6706aef907f4..a47de8c31ce9 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -2425,11 +2425,8 @@ static void stop_activity(struct net2280 *dev, struct usb_gadget_driver *driver) nuke(&dev->ep[i]); /* report disconnect; the driver is already quiesced */ - if (driver) { - spin_unlock(&dev->lock); + if (driver) driver->disconnect(&dev->gadget); - spin_lock(&dev->lock); - } usb_reinit(dev); } @@ -3275,8 +3272,6 @@ next_endpoints: BIT(PCI_RETRY_ABORT_INTERRUPT)) static void handle_stat1_irqs(struct net2280 *dev, u32 stat) -__releases(dev->lock) -__acquires(dev->lock) { struct net2280_ep *ep; u32 tmp, num, mask, scratch; @@ -3317,14 +3312,12 @@ __acquires(dev->lock) if (disconnect || reset) { stop_activity(dev, dev->driver); ep0_start(dev); - spin_unlock(&dev->lock); if (reset) usb_gadget_udc_reset (&dev->gadget, dev->driver); else (dev->driver->disconnect) (&dev->gadget); - spin_lock(&dev->lock); return; } } diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c index df538fd10aa4..46f5354c534d 100644 --- a/drivers/usb/host/ehci-exynos.c +++ b/drivers/usb/host/ehci-exynos.c @@ -77,10 +77,12 @@ static int exynos_ehci_get_phy(struct device *dev, if (IS_ERR(phy)) { ret = PTR_ERR(phy); if (ret == -EPROBE_DEFER) { + of_node_put(child); return ret; } else if (ret != -ENOSYS && ret != -ENODEV) { dev_err(dev, "Error retrieving usb2 phy: %d\n", ret); + of_node_put(child); return ret; } } diff --git a/drivers/usb/host/ohci-exynos.c b/drivers/usb/host/ohci-exynos.c index 2cd105be7319..6865b919403f 100644 --- a/drivers/usb/host/ohci-exynos.c +++ b/drivers/usb/host/ohci-exynos.c @@ -66,10 +66,12 @@ static int exynos_ohci_get_phy(struct device *dev, if (IS_ERR(phy)) { ret = PTR_ERR(phy); if (ret == -EPROBE_DEFER) { + of_node_put(child); return ret; } else if (ret != -ENOSYS && ret != -ENODEV) { dev_err(dev, "Error retrieving usb2 phy: %d\n", ret); + of_node_put(child); return ret; } } diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index f9400564cb72..03b9a372636f 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -89,6 +89,7 @@ enum amd_chipset_gen { AMD_CHIPSET_HUDSON2, AMD_CHIPSET_BOLTON, AMD_CHIPSET_YANGTZE, + AMD_CHIPSET_TAISHAN, AMD_CHIPSET_UNKNOWN, }; @@ -132,6 +133,11 @@ static int amd_chipset_sb_type_init(struct amd_chipset_info *pinfo) pinfo->sb_type.gen = AMD_CHIPSET_SB700; else if (rev >= 0x40 && rev <= 0x4f) pinfo->sb_type.gen = AMD_CHIPSET_SB800; + } + pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, + 0x145c, NULL); + if (pinfo->smbus_dev) { + pinfo->sb_type.gen = AMD_CHIPSET_TAISHAN; } else { pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, NULL); @@ -251,11 +257,12 @@ int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev) { /* Make sure amd chipset type has already been initialized */ usb_amd_find_chipset_info(); - if (amd_chipset.sb_type.gen != AMD_CHIPSET_YANGTZE) - return 0; - - dev_dbg(&pdev->dev, "QUIRK: Enable AMD remote wakeup fix\n"); - return 1; + if (amd_chipset.sb_type.gen == AMD_CHIPSET_YANGTZE || + amd_chipset.sb_type.gen == AMD_CHIPSET_TAISHAN) { + dev_dbg(&pdev->dev, "QUIRK: Enable AMD remote wakeup fix\n"); + return 1; + } + return 0; } EXPORT_SYMBOL_GPL(usb_hcd_amd_remote_wakeup_quirk); diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c index 4cbd0633c5c2..a11c2c8bda53 100644 --- a/drivers/usb/host/r8a66597-hcd.c +++ b/drivers/usb/host/r8a66597-hcd.c @@ -1269,7 +1269,7 @@ static void set_td_timer(struct r8a66597 *r8a66597, struct r8a66597_td *td) time = 30; break; default: - time = 300; + time = 50; break; } @@ -1785,6 +1785,7 @@ static void r8a66597_td_timer(unsigned long _r8a66597) pipe = td->pipe; pipe_stop(r8a66597, pipe); + /* Select a different address or endpoint */ new_td = td; do { list_move_tail(&new_td->queue, @@ -1794,7 +1795,8 @@ static void r8a66597_td_timer(unsigned long _r8a66597) new_td = td; break; } - } while (td != new_td && td->address == new_td->address); + } while (td != new_td && td->address == new_td->address && + td->pipe->info.epnum == new_td->pipe->info.epnum); start_transfer(r8a66597, new_td); diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c index 74c42f722678..3425154baf8b 100644 --- a/drivers/usb/host/xhci-dbg.c +++ b/drivers/usb/host/xhci-dbg.c @@ -111,7 +111,7 @@ static void xhci_print_cap_regs(struct xhci_hcd *xhci) xhci_dbg(xhci, "RTSOFF 0x%x:\n", temp & RTSOFF_MASK); /* xhci 1.1 controllers have the HCCPARAMS2 register */ - if (hci_version > 100) { + if (hci_version > 0x100) { temp = readl(&xhci->cap_regs->hcc_params2); xhci_dbg(xhci, "HCC PARAMS2 0x%x:\n", (unsigned int) temp); xhci_dbg(xhci, " HC %s Force save context capability", diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index efd31d1d0727..08ab83e6f527 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -774,6 +774,9 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, clear_bit(wIndex, &bus_state->resuming_ports); set_bit(wIndex, &bus_state->rexit_ports); + + xhci_test_and_clear_bit(xhci, port_array, wIndex, + PORT_PLC); xhci_set_link_state(xhci, port_array, wIndex, XDEV_U0); diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 998a738e6359..cf6bbaff42d0 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1709,7 +1709,7 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags) xhci->dcbaa->dev_context_ptrs[0] = cpu_to_le64(xhci->scratchpad->sp_dma); for (i = 0; i < num_sp; i++) { dma_addr_t dma; - void *buf = dma_alloc_coherent(dev, xhci->page_size, &dma, + void *buf = dma_zalloc_coherent(dev, xhci->page_size, &dma, flags); if (!buf) goto fail_sp5; @@ -2493,7 +2493,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) (xhci->cmd_ring->first_seg->dma & (u64) ~CMD_RING_RSVD_BITS) | xhci->cmd_ring->cycle_state; xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "// Setting command ring address to 0x%x", val); + "// Setting command ring address to 0x%016llx", val_64); xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring); xhci_dbg_cmd_ptrs(xhci); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index dd262f418140..e8f990642281 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -52,6 +52,7 @@ #define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI 0x0aa8 #define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI 0x1aa8 #define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8 +#define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0 static const char hcd_name[] = "xhci_hcd"; @@ -167,12 +168,14 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI)) { + pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) { xhci->quirks |= XHCI_PME_STUCK_QUIRK; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) xhci->quirks |= XHCI_MISSING_CAS; if (pdev->vendor == PCI_VENDOR_ID_ETRON && @@ -195,6 +198,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1042) xhci->quirks |= XHCI_BROKEN_STREAMS; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && + pdev->device == 0x1142) + xhci->quirks |= XHCI_TRUST_TX_LENGTH; if (xhci->quirks & XHCI_RESET_ON_RESUME) xhci_dbg_trace(xhci, trace_xhci_dbg_quirks, diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 82775ef31376..e01d353a5978 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -92,7 +92,7 @@ static int xhci_plat_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENODEV; + return irq; /* Try to set 64-bit DMA first */ if (WARN_ON(!pdev->dev.dma_mask)) @@ -184,6 +184,9 @@ static int xhci_plat_probe(struct platform_device *pdev) if (ret) goto disable_usb_phy; + if (HCC_MAX_PSA(xhci->hcc_params) >= 4) + xhci->shared_hcd->can_do_streams = 1; + ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED); if (ret) goto dealloc_usb2_hcd; @@ -216,6 +219,8 @@ static int xhci_plat_remove(struct platform_device *dev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct clk *clk = xhci->clk; + xhci->xhc_state |= XHCI_STATE_REMOVING; + usb_remove_hcd(xhci->shared_hcd); usb_phy_shutdown(hcd->usb_phy); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index de7dce6eb474..ece0787d62bf 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -856,13 +856,16 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci, (ep->ep_state & EP_GETTING_NO_STREAMS)) { int stream_id; - for (stream_id = 0; stream_id < ep->stream_info->num_streams; + for (stream_id = 1; stream_id < ep->stream_info->num_streams; stream_id++) { + ring = ep->stream_info->stream_rings[stream_id]; + if (!ring) + continue; + xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "Killing URBs for slot ID %u, ep index %u, stream %u", - slot_id, ep_index, stream_id + 1); - xhci_kill_ring_urbs(xhci, - ep->stream_info->stream_rings[stream_id]); + slot_id, ep_index, stream_id); + xhci_kill_ring_urbs(xhci, ring); } } else { ring = ep->ring; diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c index 4e38683c653c..6d4e75785710 100644 --- a/drivers/usb/misc/idmouse.c +++ b/drivers/usb/misc/idmouse.c @@ -346,6 +346,9 @@ static int idmouse_probe(struct usb_interface *interface, if (iface_desc->desc.bInterfaceClass != 0x0A) return -ENODEV; + if (iface_desc->desc.bNumEndpoints < 1) + return -ENODEV; + /* allocate memory for our device state and initialize it */ dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (dev == NULL) diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index 1950e87b4219..5e43fd881a9c 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -557,7 +557,7 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd, info.revision = le16_to_cpu(dev->udev->descriptor.bcdDevice); /* 0==UNKNOWN, 1==LOW(usb1.1) ,2=FULL(usb1.1), 3=HIGH(usb2.0) */ - info.speed = le16_to_cpu(dev->udev->speed); + info.speed = dev->udev->speed; info.if_num = dev->interface->cur_altsetting->desc.bInterfaceNumber; info.report_size = dev->report_size; @@ -787,12 +787,6 @@ static int iowarrior_probe(struct usb_interface *interface, iface_desc = interface->cur_altsetting; dev->product_id = le16_to_cpu(udev->descriptor.idProduct); - if (iface_desc->desc.bNumEndpoints < 1) { - dev_err(&interface->dev, "Invalid number of endpoints\n"); - retval = -EINVAL; - goto error; - } - /* set up the endpoint information */ for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; @@ -803,6 +797,21 @@ static int iowarrior_probe(struct usb_interface *interface, /* this one will match for the IOWarrior56 only */ dev->int_out_endpoint = endpoint; } + + if (!dev->int_in_endpoint) { + dev_err(&interface->dev, "no interrupt-in endpoint found\n"); + retval = -ENODEV; + goto error; + } + + if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) { + if (!dev->int_out_endpoint) { + dev_err(&interface->dev, "no interrupt-out endpoint found\n"); + retval = -ENODEV; + goto error; + } + } + /* we have to check the report_size often, so remember it in the endianness suitable for our machine */ dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint); if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) && diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c index 4dd531ac5a7f..0ec9ee573ffa 100644 --- a/drivers/usb/misc/legousbtower.c +++ b/drivers/usb/misc/legousbtower.c @@ -317,9 +317,16 @@ static int tower_open (struct inode *inode, struct file *file) int subminor; int retval = 0; struct usb_interface *interface; - struct tower_reset_reply reset_reply; + struct tower_reset_reply *reset_reply; int result; + reset_reply = kmalloc(sizeof(*reset_reply), GFP_KERNEL); + + if (!reset_reply) { + retval = -ENOMEM; + goto exit; + } + nonseekable_open(inode, file); subminor = iminor(inode); @@ -364,8 +371,8 @@ static int tower_open (struct inode *inode, struct file *file) USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE, 0, 0, - &reset_reply, - sizeof(reset_reply), + reset_reply, + sizeof(*reset_reply), 1000); if (result < 0) { dev_err(&dev->udev->dev, @@ -406,6 +413,7 @@ unlock_exit: mutex_unlock(&dev->lock); exit: + kfree(reset_reply); return retval; } @@ -808,7 +816,7 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device struct lego_usb_tower *dev = NULL; struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor* endpoint; - struct tower_get_version_reply get_version_reply; + struct tower_get_version_reply *get_version_reply = NULL; int i; int retval = -ENOMEM; int result; @@ -898,6 +906,13 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device dev->interrupt_in_interval = interrupt_in_interval ? interrupt_in_interval : dev->interrupt_in_endpoint->bInterval; dev->interrupt_out_interval = interrupt_out_interval ? interrupt_out_interval : dev->interrupt_out_endpoint->bInterval; + get_version_reply = kmalloc(sizeof(*get_version_reply), GFP_KERNEL); + + if (!get_version_reply) { + retval = -ENOMEM; + goto error; + } + /* get the firmware version and log it */ result = usb_control_msg (udev, usb_rcvctrlpipe(udev, 0), @@ -905,18 +920,19 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE, 0, 0, - &get_version_reply, - sizeof(get_version_reply), + get_version_reply, + sizeof(*get_version_reply), 1000); if (result < 0) { dev_err(idev, "LEGO USB Tower get version control request failed\n"); retval = result; goto error; } - dev_info(&interface->dev, "LEGO USB Tower firmware version is %d.%d " - "build %d\n", get_version_reply.major, - get_version_reply.minor, - le16_to_cpu(get_version_reply.build_no)); + dev_info(&interface->dev, + "LEGO USB Tower firmware version is %d.%d build %d\n", + get_version_reply->major, + get_version_reply->minor, + le16_to_cpu(get_version_reply->build_no)); /* we can register the device now, as it is ready */ usb_set_intfdata (interface, dev); @@ -937,9 +953,11 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device USB_MAJOR, dev->minor); exit: + kfree(get_version_reply); return retval; error: + kfree(get_version_reply); tower_delete(dev); return retval; } diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c index 86b4e4b2ab9a..383fa007348f 100644 --- a/drivers/usb/misc/lvstest.c +++ b/drivers/usb/misc/lvstest.c @@ -370,6 +370,10 @@ static int lvs_rh_probe(struct usb_interface *intf, hdev = interface_to_usbdev(intf); desc = intf->cur_altsetting; + + if (desc->desc.bNumEndpoints < 1) + return -ENODEV; + endpoint = &desc->endpoint[0].desc; /* valid only for SS root hub */ diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index 1624b09d9748..2e947dc94e32 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -135,6 +135,7 @@ get_endpoints(struct usbtest_dev *dev, struct usb_interface *intf) case USB_ENDPOINT_XFER_INT: if (dev->info->intr) goto try_intr; + continue; case USB_ENDPOINT_XFER_ISOC: if (dev->info->iso) goto try_iso; diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index bbd029c9c725..442b6631162e 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -711,6 +711,11 @@ static int uss720_probe(struct usb_interface *intf, interface = intf->cur_altsetting; + if (interface->desc.bNumEndpoints < 3) { + usb_put_dev(usbdev); + return -ENODEV; + } + /* * Allocate parport interface */ diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c index b03d3b867fca..9a9c82a4d35d 100644 --- a/drivers/usb/musb/da8xx.c +++ b/drivers/usb/musb/da8xx.c @@ -458,15 +458,11 @@ static int da8xx_musb_exit(struct musb *musb) } static const struct musb_platform_ops da8xx_ops = { - .quirks = MUSB_DMA_CPPI | MUSB_INDEXED_EP, + .quirks = MUSB_INDEXED_EP, .init = da8xx_musb_init, .exit = da8xx_musb_exit, .fifo_mode = 2, -#ifdef CONFIG_USB_TI_CPPI_DMA - .dma_init = cppi_dma_controller_create, - .dma_exit = cppi_dma_controller_destroy, -#endif .enable = da8xx_musb_enable, .disable = da8xx_musb_disable, diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c index e499b862a946..88f26ac2a185 100644 --- a/drivers/usb/musb/musb_cppi41.c +++ b/drivers/usb/musb/musb_cppi41.c @@ -250,8 +250,27 @@ static void cppi41_dma_callback(void *private_data) transferred < cppi41_channel->packet_sz) cppi41_channel->prog_len = 0; - if (cppi41_channel->is_tx) - empty = musb_is_tx_fifo_empty(hw_ep); + if (cppi41_channel->is_tx) { + u8 type; + + if (is_host_active(musb)) + type = hw_ep->out_qh->type; + else + type = hw_ep->ep_in.type; + + if (type == USB_ENDPOINT_XFER_ISOC) + /* + * Don't use the early-TX-interrupt workaround below + * for Isoch transfter. Since Isoch are periodic + * transfer, by the time the next transfer is + * scheduled, the current one should be done already. + * + * This avoids audio playback underrun issue. + */ + empty = true; + else + empty = musb_is_tx_fifo_empty(hw_ep); + } if (!cppi41_channel->is_tx || empty) { cppi41_trans_done(cppi41_channel); diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index fc25a140548a..22358ab524b0 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -138,6 +138,7 @@ static void musb_h_tx_flush_fifo(struct musb_hw_ep *ep) "Could not flush host TX%d fifo: csr: %04x\n", ep->epnum, csr)) return; + mdelay(1); } } diff --git a/drivers/usb/musb/tusb6010_omap.c b/drivers/usb/musb/tusb6010_omap.c index 4c82077da475..6020024cb87c 100644 --- a/drivers/usb/musb/tusb6010_omap.c +++ b/drivers/usb/musb/tusb6010_omap.c @@ -220,6 +220,7 @@ static int tusb_omap_dma_program(struct dma_channel *channel, u16 packet_sz, u32 dma_remaining; int src_burst, dst_burst; u16 csr; + u32 psize; int ch; s8 dmareq; s8 sync_dev; @@ -391,15 +392,19 @@ static int tusb_omap_dma_program(struct dma_channel *channel, u16 packet_sz, if (chdat->tx) { /* Send transfer_packet_sz packets at a time */ - musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, - chdat->transfer_packet_sz); + psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET); + psize &= ~0x7ff; + psize |= chdat->transfer_packet_sz; + musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize); musb_writel(ep_conf, TUSB_EP_TX_OFFSET, TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len)); } else { /* Receive transfer_packet_sz packets at a time */ - musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, - chdat->transfer_packet_sz << 16); + psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET); + psize &= ~(0x7ff << 16); + psize |= (chdat->transfer_packet_sz << 16); + musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize); musb_writel(ep_conf, TUSB_EP_RX_OFFSET, TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len)); diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index d82fa36c3465..005da0866836 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -733,8 +733,10 @@ static int usbhsc_resume(struct device *dev) struct usbhs_priv *priv = dev_get_drvdata(dev); struct platform_device *pdev = usbhs_priv_to_pdev(priv); - if (!usbhsc_flags_has(priv, USBHSF_RUNTIME_PWCTRL)) + if (!usbhsc_flags_has(priv, USBHSF_RUNTIME_PWCTRL)) { usbhsc_power_ctrl(priv, 1); + usbhs_mod_autonomy_mode(priv); + } usbhs_platform_call(priv, phy_reset, pdev); diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index efc4fae123a4..8647d2c2a8c4 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -37,6 +37,7 @@ struct usbhsg_gpriv; struct usbhsg_uep { struct usb_ep ep; struct usbhs_pipe *pipe; + spinlock_t lock; /* protect the pipe */ char ep_name[EP_NAME_SIZE]; @@ -638,10 +639,16 @@ usbhsg_ep_enable_end: static int usbhsg_ep_disable(struct usb_ep *ep) { struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep); - struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep); + struct usbhs_pipe *pipe; + unsigned long flags; + int ret = 0; - if (!pipe) - return -EINVAL; + spin_lock_irqsave(&uep->lock, flags); + pipe = usbhsg_uep_to_pipe(uep); + if (!pipe) { + ret = -EINVAL; + goto out; + } usbhsg_pipe_disable(uep); usbhs_pipe_free(pipe); @@ -649,6 +656,9 @@ static int usbhsg_ep_disable(struct usb_ep *ep) uep->pipe->mod_private = NULL; uep->pipe = NULL; +out: + spin_unlock_irqrestore(&uep->lock, flags); + return 0; } @@ -698,8 +708,11 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req) { struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep); struct usbhsg_request *ureq = usbhsg_req_to_ureq(req); - struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep); + struct usbhs_pipe *pipe; + unsigned long flags; + spin_lock_irqsave(&uep->lock, flags); + pipe = usbhsg_uep_to_pipe(uep); if (pipe) usbhs_pkt_pop(pipe, usbhsg_ureq_to_pkt(ureq)); @@ -708,6 +721,7 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req) * even if the pipe is NULL. */ usbhsg_queue_pop(uep, ureq, -ECONNRESET); + spin_unlock_irqrestore(&uep->lock, flags); return 0; } @@ -854,10 +868,10 @@ static int usbhsg_try_stop(struct usbhs_priv *priv, u32 status) { struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv); struct usbhs_mod *mod = usbhs_mod_get_current(priv); - struct usbhsg_uep *dcp = usbhsg_gpriv_to_dcp(gpriv); + struct usbhsg_uep *uep; struct device *dev = usbhs_priv_to_dev(priv); unsigned long flags; - int ret = 0; + int ret = 0, i; /******************** spin lock ********************/ usbhs_lock(priv, flags); @@ -889,7 +903,9 @@ static int usbhsg_try_stop(struct usbhs_priv *priv, u32 status) usbhs_sys_set_test_mode(priv, 0); usbhs_sys_function_ctrl(priv, 0); - usbhsg_ep_disable(&dcp->ep); + /* disable all eps */ + usbhsg_for_each_uep_with_dcp(uep, gpriv, i) + usbhsg_ep_disable(&uep->ep); dev_dbg(dev, "stop gadget\n"); @@ -1072,6 +1088,7 @@ int usbhs_mod_gadget_probe(struct usbhs_priv *priv) ret = -ENOMEM; goto usbhs_mod_gadget_probe_err_gpriv; } + spin_lock_init(&uep->lock); gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED); dev_info(dev, "%stransceiver found\n", diff --git a/drivers/usb/serial/ark3116.c b/drivers/usb/serial/ark3116.c index 1532cde8a437..754fc3e41005 100644 --- a/drivers/usb/serial/ark3116.c +++ b/drivers/usb/serial/ark3116.c @@ -99,10 +99,17 @@ static int ark3116_read_reg(struct usb_serial *serial, usb_rcvctrlpipe(serial->dev, 0), 0xfe, 0xc0, 0, reg, buf, 1, ARK_TIMEOUT); - if (result < 0) + if (result < 1) { + dev_err(&serial->interface->dev, + "failed to read register %u: %d\n", + reg, result); + if (result >= 0) + result = -EIO; + return result; - else - return buf[0]; + } + + return buf[0]; } static inline int calc_divisor(int bps) @@ -366,23 +373,29 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port) dev_dbg(&port->dev, "%s - usb_serial_generic_open failed: %d\n", __func__, result); - goto err_out; + goto err_free; } /* remove any data still left: also clears error state */ ark3116_read_reg(serial, UART_RX, buf); /* read modem status */ - priv->msr = ark3116_read_reg(serial, UART_MSR, buf); + result = ark3116_read_reg(serial, UART_MSR, buf); + if (result < 0) + goto err_close; + priv->msr = *buf; + /* read line status */ - priv->lsr = ark3116_read_reg(serial, UART_LSR, buf); + result = ark3116_read_reg(serial, UART_LSR, buf); + if (result < 0) + goto err_close; + priv->lsr = *buf; result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); if (result) { dev_err(&port->dev, "submit irq_in urb failed %d\n", result); - ark3116_close(port); - goto err_out; + goto err_close; } /* activate interrupts */ @@ -395,8 +408,15 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port) if (tty) ark3116_set_termios(tty, port, NULL); -err_out: kfree(buf); + + return 0; + +err_close: + usb_serial_generic_close(port); +err_free: + kfree(buf); + return result; } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index fe7452f0f38a..41a6513646de 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -134,6 +134,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */ { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */ { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */ + { USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */ + { USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */ @@ -171,6 +173,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ { USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */ + { USB_DEVICE(0x1901, 0x0195) }, /* GE B850/B650/B450 CP2104 DP UART interface */ + { USB_DEVICE(0x1901, 0x0196) }, /* GE B850 CP2105 DP UART interface */ { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c index 3df7b7ec178e..be93b9ff2d98 100644 --- a/drivers/usb/serial/digi_acceleport.c +++ b/drivers/usb/serial/digi_acceleport.c @@ -1399,25 +1399,30 @@ static int digi_read_inb_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct digi_port *priv = usb_get_serial_port_data(port); - int opcode = ((unsigned char *)urb->transfer_buffer)[0]; - int len = ((unsigned char *)urb->transfer_buffer)[1]; - int port_status = ((unsigned char *)urb->transfer_buffer)[2]; - unsigned char *data = ((unsigned char *)urb->transfer_buffer) + 3; + unsigned char *buf = urb->transfer_buffer; + int opcode; + int len; + int port_status; + unsigned char *data; int flag, throttled; - int status = urb->status; - - /* do not process callbacks on closed ports */ - /* but do continue the read chain */ - if (urb->status == -ENOENT) - return 0; /* short/multiple packet check */ + if (urb->actual_length < 2) { + dev_warn(&port->dev, "short packet received\n"); + return -1; + } + + opcode = buf[0]; + len = buf[1]; + if (urb->actual_length != len + 2) { - dev_err(&port->dev, "%s: INCOMPLETE OR MULTIPLE PACKET, " - "status=%d, port=%d, opcode=%d, len=%d, " - "actual_length=%d, status=%d\n", __func__, status, - priv->dp_port_num, opcode, len, urb->actual_length, - port_status); + dev_err(&port->dev, "malformed packet received: port=%d, opcode=%d, len=%d, actual_length=%u\n", + priv->dp_port_num, opcode, len, urb->actual_length); + return -1; + } + + if (opcode == DIGI_CMD_RECEIVE_DATA && len < 1) { + dev_err(&port->dev, "malformed data packet received\n"); return -1; } @@ -1431,6 +1436,9 @@ static int digi_read_inb_callback(struct urb *urb) /* receive data */ if (opcode == DIGI_CMD_RECEIVE_DATA) { + port_status = buf[2]; + data = &buf[3]; + /* get flag from port_status */ flag = 0; @@ -1483,16 +1491,20 @@ static int digi_read_oob_callback(struct urb *urb) struct usb_serial *serial = port->serial; struct tty_struct *tty; struct digi_port *priv = usb_get_serial_port_data(port); + unsigned char *buf = urb->transfer_buffer; int opcode, line, status, val; int i; unsigned int rts; + if (urb->actual_length < 4) + return -1; + /* handle each oob command */ - for (i = 0; i < urb->actual_length - 3;) { - opcode = ((unsigned char *)urb->transfer_buffer)[i++]; - line = ((unsigned char *)urb->transfer_buffer)[i++]; - status = ((unsigned char *)urb->transfer_buffer)[i++]; - val = ((unsigned char *)urb->transfer_buffer)[i++]; + for (i = 0; i < urb->actual_length - 3; i += 4) { + opcode = buf[i]; + line = buf[i + 1]; + status = buf[i + 2]; + val = buf[i + 3]; dev_dbg(&port->dev, "digi_read_oob_callback: opcode=%d, line=%d, status=%d, val=%d\n", opcode, line, status, val); diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index d3d6ec455151..e0385d6c0abb 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -809,10 +809,10 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) }, { USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_H_PID, 1) }, { USB_DEVICE(FIC_VID, FIC_NEO1973_DEBUG_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_OOCDLINK_PID), @@ -873,6 +873,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE_AND_INTERFACE_INFO(MICROCHIP_VID, MICROCHIP_USB_BOARD_PID, USB_CLASS_VENDOR_SPEC, USB_SUBCLASS_VENDOR_SPEC, 0x00) }, + { USB_DEVICE_INTERFACE_NUMBER(ACTEL_VID, MICROSEMI_ARROW_SF2PLUS_BOARD_PID, 2) }, { USB_DEVICE(JETI_VID, JETI_SPC1201_PID) }, { USB_DEVICE(MARVELL_VID, MARVELL_SHEEVAPLUG_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, @@ -1439,10 +1440,13 @@ static int read_latency_timer(struct usb_serial_port *port) FTDI_SIO_GET_LATENCY_TIMER_REQUEST_TYPE, 0, priv->interface, buf, 1, WDR_TIMEOUT); - if (rv < 0) + if (rv < 1) { dev_err(&port->dev, "Unable to read latency timer: %i\n", rv); - else + if (rv >= 0) + rv = -EIO; + } else { priv->latency = buf[0]; + } kfree(buf); @@ -1504,9 +1508,9 @@ static int set_serial_info(struct tty_struct *tty, (new_serial.flags & ASYNC_FLAGS)); priv->custom_divisor = new_serial.custom_divisor; +check_and_exit: write_latency_timer(port); -check_and_exit: if ((old_priv.flags & ASYNC_SPD_MASK) != (priv->flags & ASYNC_SPD_MASK)) { if ((priv->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI) @@ -1807,8 +1811,6 @@ static int ftdi_sio_port_probe(struct usb_serial_port *port) mutex_init(&priv->cfg_lock); - priv->flags = ASYNC_LOW_LATENCY; - if (quirk && quirk->port_probe) quirk->port_probe(priv); @@ -2072,6 +2074,20 @@ static int ftdi_process_packet(struct usb_serial_port *port, priv->prev_status = status; } + /* save if the transmitter is empty or not */ + if (packet[1] & FTDI_RS_TEMT) + priv->transmit_empty = 1; + else + priv->transmit_empty = 0; + + len -= 2; + if (!len) + return 0; /* status only */ + + /* + * Break and error status must only be processed for packets with + * data payload to avoid over-reporting. + */ flag = TTY_NORMAL; if (packet[1] & FTDI_RS_ERR_MASK) { /* Break takes precedence over parity, which takes precedence @@ -2094,15 +2110,6 @@ static int ftdi_process_packet(struct usb_serial_port *port, } } - /* save if the transmitter is empty or not */ - if (packet[1] & FTDI_RS_TEMT) - priv->transmit_empty = 1; - else - priv->transmit_empty = 0; - - len -= 2; - if (!len) - return 0; /* status only */ port->icount.rx += len; ch = packet + 2; @@ -2433,8 +2440,12 @@ static int ftdi_get_modem_status(struct usb_serial_port *port, FTDI_SIO_GET_MODEM_STATUS_REQUEST_TYPE, 0, priv->interface, buf, len, WDR_TIMEOUT); - if (ret < 0) { + + /* NOTE: We allow short responses and handle that below. */ + if (ret < 1) { dev_err(&port->dev, "failed to get modem status: %d\n", ret); + if (ret >= 0) + ret = -EIO; ret = usb_translate_errors(ret); goto out; } diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 48ee04c94a75..4fcf1cecb6d7 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -873,9 +873,17 @@ #define FIC_VID 0x1457 #define FIC_NEO1973_DEBUG_PID 0x5118 +/* + * Actel / Microsemi + */ +#define ACTEL_VID 0x1514 +#define MICROSEMI_ARROW_SF2PLUS_BOARD_PID 0x2008 + /* Olimex */ #define OLIMEX_VID 0x15BA #define OLIMEX_ARM_USB_OCD_PID 0x0003 +#define OLIMEX_ARM_USB_TINY_PID 0x0004 +#define OLIMEX_ARM_USB_TINY_H_PID 0x002a #define OLIMEX_ARM_USB_OCD_H_PID 0x002b /* diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c index b63a6c3899c5..749e1b674145 100644 --- a/drivers/usb/serial/io_edgeport.c +++ b/drivers/usb/serial/io_edgeport.c @@ -492,20 +492,24 @@ static int get_epic_descriptor(struct edgeport_serial *ep) int result; struct usb_serial *serial = ep->serial; struct edgeport_product_info *product_info = &ep->product_info; - struct edge_compatibility_descriptor *epic = &ep->epic_descriptor; + struct edge_compatibility_descriptor *epic; struct edge_compatibility_bits *bits; struct device *dev = &serial->dev->dev; ep->is_epic = 0; + + epic = kmalloc(sizeof(*epic), GFP_KERNEL); + if (!epic) + return -ENOMEM; + result = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0), USB_REQUEST_ION_GET_EPIC_DESC, 0xC0, 0x00, 0x00, - &ep->epic_descriptor, - sizeof(struct edge_compatibility_descriptor), + epic, sizeof(*epic), 300); - - if (result > 0) { + if (result == sizeof(*epic)) { ep->is_epic = 1; + memcpy(&ep->epic_descriptor, epic, sizeof(*epic)); memset(product_info, 0, sizeof(struct edgeport_product_info)); product_info->NumPorts = epic->NumPorts; @@ -534,8 +538,16 @@ static int get_epic_descriptor(struct edgeport_serial *ep) dev_dbg(dev, " IOSPWriteLCR : %s\n", bits->IOSPWriteLCR ? "TRUE": "FALSE"); dev_dbg(dev, " IOSPSetBaudRate : %s\n", bits->IOSPSetBaudRate ? "TRUE": "FALSE"); dev_dbg(dev, " TrueEdgeport : %s\n", bits->TrueEdgeport ? "TRUE": "FALSE"); + + result = 0; + } else if (result >= 0) { + dev_warn(&serial->interface->dev, "short epic descriptor received: %d\n", + result); + result = -EIO; } + kfree(epic); + return result; } @@ -2097,8 +2109,7 @@ static int rom_write(struct usb_serial *serial, __u16 extAddr, __u16 addr, * rom_read * reads a number of bytes from the Edgeport device starting at the given * address. - * If successful returns the number of bytes read, otherwise it returns - * a negative error number of the problem. + * Returns zero on success or a negative error number. ****************************************************************************/ static int rom_read(struct usb_serial *serial, __u16 extAddr, __u16 addr, __u16 length, __u8 *data) @@ -2123,12 +2134,17 @@ static int rom_read(struct usb_serial *serial, __u16 extAddr, USB_REQUEST_ION_READ_ROM, 0xC0, addr, extAddr, transfer_buffer, current_length, 300); - if (result < 0) + if (result < current_length) { + if (result >= 0) + result = -EIO; break; + } memcpy(data, transfer_buffer, current_length); length -= current_length; addr += current_length; data += current_length; + + result = 0; } kfree(transfer_buffer); @@ -2585,9 +2601,10 @@ static void get_manufacturing_desc(struct edgeport_serial *edge_serial) EDGE_MANUF_DESC_LEN, (__u8 *)(&edge_serial->manuf_descriptor)); - if (response < 1) - dev_err(dev, "error in getting manufacturer descriptor\n"); - else { + if (response < 0) { + dev_err(dev, "error in getting manufacturer descriptor: %d\n", + response); + } else { char string[30]; dev_dbg(dev, "**Manufacturer Descriptor\n"); dev_dbg(dev, " RomSize: %dK\n", @@ -2644,9 +2661,10 @@ static void get_boot_desc(struct edgeport_serial *edge_serial) EDGE_BOOT_DESC_LEN, (__u8 *)(&edge_serial->boot_descriptor)); - if (response < 1) - dev_err(dev, "error in getting boot descriptor\n"); - else { + if (response < 0) { + dev_err(dev, "error in getting boot descriptor: %d\n", + response); + } else { dev_dbg(dev, "**Boot Descriptor:\n"); dev_dbg(dev, " BootCodeLength: %d\n", le16_to_cpu(edge_serial->boot_descriptor.BootCodeLength)); @@ -2789,7 +2807,7 @@ static int edge_startup(struct usb_serial *serial) dev_info(&serial->dev->dev, "%s detected\n", edge_serial->name); /* Read the epic descriptor */ - if (get_epic_descriptor(edge_serial) <= 0) { + if (get_epic_descriptor(edge_serial) < 0) { /* memcpy descriptor to Supports structures */ memcpy(&edge_serial->epic_descriptor.Supports, descriptor, sizeof(struct edge_compatibility_bits)); diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c index c02808a30436..e98532feb0cc 100644 --- a/drivers/usb/serial/io_ti.c +++ b/drivers/usb/serial/io_ti.c @@ -1674,6 +1674,12 @@ static void edge_interrupt_callback(struct urb *urb) function = TIUMP_GET_FUNC_FROM_CODE(data[0]); dev_dbg(dev, "%s - port_number %d, function %d, info 0x%x\n", __func__, port_number, function, data[1]); + + if (port_number >= edge_serial->serial->num_ports) { + dev_err(dev, "bad port number %d\n", port_number); + goto exit; + } + port = edge_serial->serial->port[port_number]; edge_port = usb_get_serial_port_data(port); if (!edge_port) { @@ -1755,7 +1761,7 @@ static void edge_bulk_in_callback(struct urb *urb) port_number = edge_port->port->port_number; - if (edge_port->lsr_event) { + if (urb->actual_length > 0 && edge_port->lsr_event) { edge_port->lsr_event = 0; dev_dbg(dev, "%s ===== Port %u LSR Status = %02x, Data = %02x ======\n", __func__, port_number, edge_port->lsr_mask, *data); @@ -2343,8 +2349,11 @@ static void change_port_settings(struct tty_struct *tty, if (!baud) { /* pick a default, any default... */ baud = 9600; - } else + } else { + /* Avoid a zero divisor. */ + baud = min(baud, 461550); tty_encode_baud_rate(tty, baud, baud); + } edge_port->baud_rate = baud; config->wBaudRate = (__u16)((461550L + baud/2) / baud); diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c index 930be98d59b3..6b0942428917 100644 --- a/drivers/usb/serial/keyspan_pda.c +++ b/drivers/usb/serial/keyspan_pda.c @@ -139,6 +139,7 @@ static void keyspan_pda_rx_interrupt(struct urb *urb) { struct usb_serial_port *port = urb->context; unsigned char *data = urb->transfer_buffer; + unsigned int len = urb->actual_length; int retval; int status = urb->status; struct keyspan_pda_private *priv; @@ -159,18 +160,26 @@ static void keyspan_pda_rx_interrupt(struct urb *urb) goto exit; } + if (len < 1) { + dev_warn(&port->dev, "short message received\n"); + goto exit; + } + /* see if the message is data or a status interrupt */ switch (data[0]) { case 0: /* rest of message is rx data */ - if (urb->actual_length) { - tty_insert_flip_string(&port->port, data + 1, - urb->actual_length - 1); - tty_flip_buffer_push(&port->port); - } + if (len < 2) + break; + tty_insert_flip_string(&port->port, data + 1, len - 1); + tty_flip_buffer_push(&port->port); break; case 1: /* status interrupt */ + if (len < 3) { + dev_warn(&port->dev, "short interrupt message received\n"); + break; + } dev_dbg(&port->dev, "rx int, d1=%d, d2=%d\n", data[1], data[2]); switch (data[1]) { case 1: /* modemline change */ diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c index 89726f702202..a6c07c6be25f 100644 --- a/drivers/usb/serial/mct_u232.c +++ b/drivers/usb/serial/mct_u232.c @@ -189,7 +189,7 @@ static int mct_u232_set_baud_rate(struct tty_struct *tty, return -ENOMEM; divisor = mct_u232_calculate_baud_rate(serial, value, &speed); - put_unaligned_le32(cpu_to_le32(divisor), buf); + put_unaligned_le32(divisor, buf); rc = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), MCT_U232_SET_BAUD_RATE_REQUEST, MCT_U232_SET_REQUEST_TYPE, @@ -322,8 +322,12 @@ static int mct_u232_get_modem_stat(struct usb_serial_port *port, MCT_U232_GET_REQUEST_TYPE, 0, 0, buf, MCT_U232_GET_MODEM_STAT_SIZE, WDR_TIMEOUT); - if (rc < 0) { + if (rc < MCT_U232_GET_MODEM_STAT_SIZE) { dev_err(&port->dev, "Get MODEM STATus failed (error = %d)\n", rc); + + if (rc >= 0) + rc = -EIO; + *msr = 0; } else { *msr = buf[0]; diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index 97ea52b5cfd4..d17685cc00c9 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -1024,6 +1024,7 @@ static int mos7840_open(struct tty_struct *tty, struct usb_serial_port *port) * (can't set it up in mos7840_startup as the structures * * were not set up at that time.) */ if (port0->open_ports == 1) { + /* FIXME: Buffer never NULL, so URB is not submitted. */ if (serial->port[0]->interrupt_in_buffer == NULL) { /* set up interrupt urb */ usb_fill_int_urb(serial->port[0]->interrupt_in_urb, @@ -2119,7 +2120,8 @@ static int mos7840_calc_num_ports(struct usb_serial *serial) static int mos7840_attach(struct usb_serial *serial) { if (serial->num_bulk_in < serial->num_ports || - serial->num_bulk_out < serial->num_ports) { + serial->num_bulk_out < serial->num_ports || + serial->num_interrupt_in < 1) { dev_err(&serial->interface->dev, "missing endpoints\n"); return -ENODEV; } diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c index a180b17d2432..76564b3bebb9 100644 --- a/drivers/usb/serial/omninet.c +++ b/drivers/usb/serial/omninet.c @@ -142,12 +142,6 @@ static int omninet_port_remove(struct usb_serial_port *port) static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port) { - struct usb_serial *serial = port->serial; - struct usb_serial_port *wport; - - wport = serial->port[1]; - tty_port_tty_set(&wport->port, tty); - return usb_serial_generic_open(tty, port); } diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c index 4b7bfb394a32..64bf258e7e00 100644 --- a/drivers/usb/serial/opticon.c +++ b/drivers/usb/serial/opticon.c @@ -142,7 +142,7 @@ static int opticon_open(struct tty_struct *tty, struct usb_serial_port *port) usb_clear_halt(port->serial->dev, port->read_urb->pipe); res = usb_serial_generic_open(tty, port); - if (!res) + if (res) return res; /* Request CTS line state, sometimes during opening the current diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 7ce31a4c7e7f..fe123153b1a5 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -233,6 +233,14 @@ static void option_instat_callback(struct urb *urb); #define BANDRICH_PRODUCT_1012 0x1012 #define QUALCOMM_VENDOR_ID 0x05C6 +/* These Quectel products use Qualcomm's vendor ID */ +#define QUECTEL_PRODUCT_UC20 0x9003 +#define QUECTEL_PRODUCT_UC15 0x9090 + +#define QUECTEL_VENDOR_ID 0x2c7c +/* These Quectel products use Quectel's vendor ID */ +#define QUECTEL_PRODUCT_EC21 0x0121 +#define QUECTEL_PRODUCT_EC25 0x0125 #define CMOTECH_VENDOR_ID 0x16d8 #define CMOTECH_PRODUCT_6001 0x6001 @@ -273,6 +281,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_LE922_USBCFG0 0x1042 #define TELIT_PRODUCT_LE922_USBCFG3 0x1043 #define TELIT_PRODUCT_LE922_USBCFG5 0x1045 +#define TELIT_PRODUCT_ME910 0x1100 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 #define TELIT_PRODUCT_LE910_USBCFG4 0x1206 @@ -632,6 +641,11 @@ static const struct option_blacklist_info simcom_sim7100e_blacklist = { .reserved = BIT(5) | BIT(6), }; +static const struct option_blacklist_info telit_me910_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(3), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -1161,7 +1175,14 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ - { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */ + /* Quectel products using Qualcomm vendor ID */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)}, + { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + /* Quectel products using Quectel vendor ID */ + { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, @@ -1220,6 +1241,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff), .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), + .driver_info = (kernel_ulong_t)&telit_me910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), @@ -1854,6 +1877,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&four_g_w100_blacklist }, { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) }, + { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9801, 0xff), + .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, + { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) }, { USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) }, @@ -1998,6 +2025,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d04, 0xff) }, /* D-Link DWM-158 */ { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e19, 0xff), /* D-Link DWM-221 B1 */ .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff), /* D-Link DWM-222 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ @@ -2007,6 +2036,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, 0xff, 0xff, 0xff) }, /* HP lt2523 (Novatel E371) */ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 46fca6b75846..a51b28379850 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -49,6 +49,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) }, + { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_UC485) }, + { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID2) }, { USB_DEVICE(ATEN_VENDOR_ID2, ATEN_PRODUCT_ID) }, { USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID) }, { USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID_UCSGT) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index e3b7af8adfb7..3b5a15d1dc0d 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -27,6 +27,8 @@ #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 #define ATEN_PRODUCT_ID 0x2008 +#define ATEN_PRODUCT_UC485 0x2021 +#define ATEN_PRODUCT_ID2 0x2118 #define IODATA_VENDOR_ID 0x04bb #define IODATA_PRODUCT_ID 0x0a03 diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 1bc6089b9008..652b4334b26d 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -124,6 +124,7 @@ static const struct usb_device_id id_table[] = { {USB_DEVICE(0x1410, 0xa021)}, /* Novatel Gobi 3000 Composite */ {USB_DEVICE(0x413c, 0x8193)}, /* Dell Gobi 3000 QDL */ {USB_DEVICE(0x413c, 0x8194)}, /* Dell Gobi 3000 Composite */ + {USB_DEVICE(0x413c, 0x81a6)}, /* Dell DW5570 QDL (MC8805) */ {USB_DEVICE(0x1199, 0x68a4)}, /* Sierra Wireless QDL */ {USB_DEVICE(0x1199, 0x68a5)}, /* Sierra Wireless Modem */ {USB_DEVICE(0x1199, 0x68a8)}, /* Sierra Wireless QDL */ @@ -157,10 +158,13 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9056)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9060)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9061)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x1199, 0x9063)}, /* Sierra Wireless EM7305 */ {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx */ {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */ {DEVICE_SWI(0x1199, 0x9078)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */ + {DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ @@ -168,6 +172,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81b1)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ + {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c index a3ed07c58754..af0c87276299 100644 --- a/drivers/usb/serial/quatech2.c +++ b/drivers/usb/serial/quatech2.c @@ -188,22 +188,22 @@ static inline int qt2_setdevice(struct usb_device *dev, u8 *data) } -static inline int qt2_getdevice(struct usb_device *dev, u8 *data) -{ - return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), - QT_SET_GET_DEVICE, 0xc0, 0, 0, - data, 3, QT2_USB_TIMEOUT); -} - static inline int qt2_getregister(struct usb_device *dev, u8 uart, u8 reg, u8 *data) { - return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), - QT_SET_GET_REGISTER, 0xc0, reg, - uart, data, sizeof(*data), QT2_USB_TIMEOUT); + int ret; + + ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), + QT_SET_GET_REGISTER, 0xc0, reg, + uart, data, sizeof(*data), QT2_USB_TIMEOUT); + if (ret < sizeof(*data)) { + if (ret >= 0) + ret = -EIO; + } + return ret; } static inline int qt2_setregister(struct usb_device *dev, @@ -372,9 +372,11 @@ static int qt2_open(struct tty_struct *tty, struct usb_serial_port *port) 0xc0, 0, device_port, data, 2, QT2_USB_TIMEOUT); - if (status < 0) { + if (status < 2) { dev_err(&port->dev, "%s - open port failed %i\n", __func__, status); + if (status >= 0) + status = -EIO; kfree(data); return status; } diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c index b2dff0f14743..236ea43f7815 100644 --- a/drivers/usb/serial/safe_serial.c +++ b/drivers/usb/serial/safe_serial.c @@ -205,6 +205,11 @@ static void safe_process_read_urb(struct urb *urb) if (!safe) goto out; + if (length < 2) { + dev_err(&port->dev, "malformed packet\n"); + return; + } + fcs = fcs_compute10(data, length, CRC10_INITFCS); if (fcs) { dev_err(&port->dev, "%s - bad CRC %x\n", __func__, fcs); diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c index 475e6c31b266..ddfd787c461c 100644 --- a/drivers/usb/serial/spcp8x5.c +++ b/drivers/usb/serial/spcp8x5.c @@ -232,11 +232,17 @@ static int spcp8x5_get_msr(struct usb_serial_port *port, u8 *status) ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), GET_UART_STATUS, GET_UART_STATUS_TYPE, 0, GET_UART_STATUS_MSR, buf, 1, 100); - if (ret < 0) + if (ret < 1) { dev_err(&port->dev, "failed to get modem status: %d\n", ret); + if (ret >= 0) + ret = -EIO; + goto out; + } dev_dbg(&port->dev, "0xc0:0x22:0:6 %d - 0x02%x\n", ret, *buf); *status = *buf; + ret = 0; +out: kfree(buf); return ret; diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c index 70a098de429f..886e1294b120 100644 --- a/drivers/usb/serial/ssu100.c +++ b/drivers/usb/serial/ssu100.c @@ -80,9 +80,17 @@ static inline int ssu100_setdevice(struct usb_device *dev, u8 *data) static inline int ssu100_getdevice(struct usb_device *dev, u8 *data) { - return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), - QT_SET_GET_DEVICE, 0xc0, 0, 0, - data, 3, 300); + int ret; + + ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), + QT_SET_GET_DEVICE, 0xc0, 0, 0, + data, 3, 300); + if (ret < 3) { + if (ret >= 0) + ret = -EIO; + } + + return ret; } static inline int ssu100_getregister(struct usb_device *dev, @@ -90,10 +98,17 @@ static inline int ssu100_getregister(struct usb_device *dev, unsigned short reg, u8 *data) { - return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), - QT_SET_GET_REGISTER, 0xc0, reg, - uart, data, sizeof(*data), 300); + int ret; + + ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), + QT_SET_GET_REGISTER, 0xc0, reg, + uart, data, sizeof(*data), 300); + if (ret < sizeof(*data)) { + if (ret >= 0) + ret = -EIO; + } + return ret; } @@ -289,8 +304,10 @@ static int ssu100_open(struct tty_struct *tty, struct usb_serial_port *port) QT_OPEN_CLOSE_CHANNEL, QT_TRANSFER_IN, 0x01, 0, data, 2, 300); - if (result < 0) { + if (result < 2) { dev_dbg(&port->dev, "%s - open failed %i\n", __func__, result); + if (result >= 0) + result = -EIO; kfree(data); return result; } diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index 535fcfafc097..fe7f5ace6064 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -1352,13 +1352,10 @@ static int ti_command_out_sync(struct ti_device *tdev, __u8 command, (USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT), value, moduleid, data, size, 1000); - if (status == size) - status = 0; - - if (status > 0) - status = -ECOMM; + if (status < 0) + return status; - return status; + return 0; } @@ -1374,8 +1371,7 @@ static int ti_command_in_sync(struct ti_device *tdev, __u8 command, if (status == size) status = 0; - - if (status > 0) + else if (status >= 0) status = -ECOMM; return status; diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c index f3cf4cecd2b7..091e8ec7a6c0 100644 --- a/drivers/usb/storage/ene_ub6250.c +++ b/drivers/usb/storage/ene_ub6250.c @@ -446,6 +446,10 @@ struct ms_lib_ctrl { #define SD_BLOCK_LEN 9 struct ene_ub6250_info { + + /* I/O bounce buffer */ + u8 *bbuf; + /* for 6250 code */ struct SD_STATUS SD_Status; struct MS_STATUS MS_Status; @@ -493,8 +497,11 @@ static int ene_load_bincode(struct us_data *us, unsigned char flag); static void ene_ub6250_info_destructor(void *extra) { + struct ene_ub6250_info *info = (struct ene_ub6250_info *) extra; + if (!extra) return; + kfree(info->bbuf); } static int ene_send_scsi_cmd(struct us_data *us, u8 fDir, void *buf, int use_sg) @@ -858,8 +865,9 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr, u8 PageNum, u32 *PageBuf, struct ms_lib_type_extdat *ExtraDat) { struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; + struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; int result; - u8 ExtBuf[4]; u32 bn = PhyBlockAddr * 0x20 + PageNum; /* printk(KERN_INFO "MS --- MS_ReaderReadPage, @@ -902,7 +910,7 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr, bcb->CDB[2] = (unsigned char)(PhyBlockAddr>>16); bcb->CDB[6] = 0x01; - result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; @@ -911,9 +919,9 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr, ExtraDat->status0 = 0x10; /* Not yet,fireware support */ ExtraDat->status1 = 0x00; /* Not yet,fireware support */ - ExtraDat->ovrflg = ExtBuf[0]; - ExtraDat->mngflg = ExtBuf[1]; - ExtraDat->logadr = memstick_logaddr(ExtBuf[2], ExtBuf[3]); + ExtraDat->ovrflg = bbuf[0]; + ExtraDat->mngflg = bbuf[1]; + ExtraDat->logadr = memstick_logaddr(bbuf[2], bbuf[3]); return USB_STOR_TRANSPORT_GOOD; } @@ -1339,8 +1347,9 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock, u8 PageNum, struct ms_lib_type_extdat *ExtraDat) { struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; + struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; int result; - u8 ExtBuf[4]; /* printk("MS_LibReadExtra --- PhyBlock = %x, PageNum = %x\n", PhyBlock, PageNum); */ memset(bcb, 0, sizeof(struct bulk_cb_wrap)); @@ -1355,7 +1364,7 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock, bcb->CDB[2] = (unsigned char)(PhyBlock>>16); bcb->CDB[6] = 0x01; - result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; @@ -1363,9 +1372,9 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock, ExtraDat->intr = 0x80; /* Not yet, waiting for fireware support */ ExtraDat->status0 = 0x10; /* Not yet, waiting for fireware support */ ExtraDat->status1 = 0x00; /* Not yet, waiting for fireware support */ - ExtraDat->ovrflg = ExtBuf[0]; - ExtraDat->mngflg = ExtBuf[1]; - ExtraDat->logadr = memstick_logaddr(ExtBuf[2], ExtBuf[3]); + ExtraDat->ovrflg = bbuf[0]; + ExtraDat->mngflg = bbuf[1]; + ExtraDat->logadr = memstick_logaddr(bbuf[2], bbuf[3]); return USB_STOR_TRANSPORT_GOOD; } @@ -1569,9 +1578,9 @@ static int ms_lib_scan_logicalblocknumber(struct us_data *us, u16 btBlk1st) u16 PhyBlock, newblk, i; u16 LogStart, LogEnde; struct ms_lib_type_extdat extdat; - u8 buf[0x200]; u32 count = 0, index = 0; struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; for (PhyBlock = 0; PhyBlock < info->MS_Lib.NumberOfPhyBlock;) { ms_lib_phy_to_log_range(PhyBlock, &LogStart, &LogEnde); @@ -1585,14 +1594,16 @@ static int ms_lib_scan_logicalblocknumber(struct us_data *us, u16 btBlk1st) } if (count == PhyBlock) { - ms_lib_read_extrablock(us, PhyBlock, 0, 0x80, &buf); + ms_lib_read_extrablock(us, PhyBlock, 0, 0x80, + bbuf); count += 0x80; } index = (PhyBlock % 0x80) * 4; - extdat.ovrflg = buf[index]; - extdat.mngflg = buf[index+1]; - extdat.logadr = memstick_logaddr(buf[index+2], buf[index+3]); + extdat.ovrflg = bbuf[index]; + extdat.mngflg = bbuf[index+1]; + extdat.logadr = memstick_logaddr(bbuf[index+2], + bbuf[index+3]); if ((extdat.ovrflg & MS_REG_OVR_BKST) != MS_REG_OVR_BKST_OK) { ms_lib_setacquired_errorblock(us, PhyBlock); @@ -2075,9 +2086,9 @@ static int ene_ms_init(struct us_data *us) { struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; int result; - u8 buf[0x200]; u16 MSP_BlockSize, MSP_UserAreaBlocks; struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; printk(KERN_INFO "transport --- ENE_MSInit\n"); @@ -2096,13 +2107,13 @@ static int ene_ms_init(struct us_data *us) bcb->CDB[0] = 0xF1; bcb->CDB[1] = 0x01; - result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) { printk(KERN_ERR "Execution MS Init Code Fail !!\n"); return USB_STOR_TRANSPORT_ERROR; } /* the same part to test ENE */ - info->MS_Status = *(struct MS_STATUS *)&buf[0]; + info->MS_Status = *(struct MS_STATUS *) bbuf; if (info->MS_Status.Insert && info->MS_Status.Ready) { printk(KERN_INFO "Insert = %x\n", info->MS_Status.Insert); @@ -2111,15 +2122,15 @@ static int ene_ms_init(struct us_data *us) printk(KERN_INFO "IsMSPHG = %x\n", info->MS_Status.IsMSPHG); printk(KERN_INFO "WtP= %x\n", info->MS_Status.WtP); if (info->MS_Status.IsMSPro) { - MSP_BlockSize = (buf[6] << 8) | buf[7]; - MSP_UserAreaBlocks = (buf[10] << 8) | buf[11]; + MSP_BlockSize = (bbuf[6] << 8) | bbuf[7]; + MSP_UserAreaBlocks = (bbuf[10] << 8) | bbuf[11]; info->MSP_TotalBlock = MSP_BlockSize * MSP_UserAreaBlocks; } else { ms_card_init(us); /* Card is MS (to ms.c)*/ } usb_stor_dbg(us, "MS Init Code OK !!\n"); } else { - usb_stor_dbg(us, "MS Card Not Ready --- %x\n", buf[0]); + usb_stor_dbg(us, "MS Card Not Ready --- %x\n", bbuf[0]); return USB_STOR_TRANSPORT_ERROR; } @@ -2129,9 +2140,9 @@ static int ene_ms_init(struct us_data *us) static int ene_sd_init(struct us_data *us) { int result; - u8 buf[0x200]; struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; usb_stor_dbg(us, "transport --- ENE_SDInit\n"); /* SD Init Part-1 */ @@ -2165,17 +2176,17 @@ static int ene_sd_init(struct us_data *us) bcb->Flags = US_BULK_FLAG_IN; bcb->CDB[0] = 0xF1; - result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) { usb_stor_dbg(us, "Execution SD Init Code Fail !!\n"); return USB_STOR_TRANSPORT_ERROR; } - info->SD_Status = *(struct SD_STATUS *)&buf[0]; + info->SD_Status = *(struct SD_STATUS *) bbuf; if (info->SD_Status.Insert && info->SD_Status.Ready) { struct SD_STATUS *s = &info->SD_Status; - ene_get_card_status(us, (unsigned char *)&buf); + ene_get_card_status(us, bbuf); usb_stor_dbg(us, "Insert = %x\n", s->Insert); usb_stor_dbg(us, "Ready = %x\n", s->Ready); usb_stor_dbg(us, "IsMMC = %x\n", s->IsMMC); @@ -2183,7 +2194,7 @@ static int ene_sd_init(struct us_data *us) usb_stor_dbg(us, "HiSpeed = %x\n", s->HiSpeed); usb_stor_dbg(us, "WtP = %x\n", s->WtP); } else { - usb_stor_dbg(us, "SD Card Not Ready --- %x\n", buf[0]); + usb_stor_dbg(us, "SD Card Not Ready --- %x\n", bbuf[0]); return USB_STOR_TRANSPORT_ERROR; } return USB_STOR_TRANSPORT_GOOD; @@ -2193,13 +2204,15 @@ static int ene_sd_init(struct us_data *us) static int ene_init(struct us_data *us) { int result; - u8 misc_reg03 = 0; + u8 misc_reg03; struct ene_ub6250_info *info = (struct ene_ub6250_info *)(us->extra); + u8 *bbuf = info->bbuf; - result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03); + result = ene_get_card_type(us, REG_CARD_STATUS, bbuf); if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; + misc_reg03 = bbuf[0]; if (misc_reg03 & 0x01) { if (!info->SD_Status.Ready) { result = ene_sd_init(us); @@ -2316,8 +2329,9 @@ static int ene_ub6250_probe(struct usb_interface *intf, const struct usb_device_id *id) { int result; - u8 misc_reg03 = 0; + u8 misc_reg03; struct us_data *us; + struct ene_ub6250_info *info; result = usb_stor_probe1(&us, intf, id, (id - ene_ub6250_usb_ids) + ene_ub6250_unusual_dev_list, @@ -2326,11 +2340,16 @@ static int ene_ub6250_probe(struct usb_interface *intf, return result; /* FIXME: where should the code alloc extra buf ? */ - if (!us->extra) { - us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL); - if (!us->extra) - return -ENOMEM; - us->extra_destructor = ene_ub6250_info_destructor; + us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL); + if (!us->extra) + return -ENOMEM; + us->extra_destructor = ene_ub6250_info_destructor; + + info = (struct ene_ub6250_info *)(us->extra); + info->bbuf = kmalloc(512, GFP_KERNEL); + if (!info->bbuf) { + kfree(us->extra); + return -ENOMEM; } us->transport_name = "ene_ub6250"; @@ -2342,12 +2361,13 @@ static int ene_ub6250_probe(struct usb_interface *intf, return result; /* probe card type */ - result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03); + result = ene_get_card_type(us, REG_CARD_STATUS, info->bbuf); if (result != USB_STOR_XFER_GOOD) { usb_stor_disconnect(intf); return USB_STOR_TRANSPORT_ERROR; } + misc_reg03 = info->bbuf[0]; if (!(misc_reg03 & 0x01)) { pr_info("ums_eneub6250: This driver only supports SD/MS cards. " "It does not support SM cards.\n"); diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c index 39afd7045c43..7bb5f8da5357 100644 --- a/drivers/usb/storage/isd200.c +++ b/drivers/usb/storage/isd200.c @@ -1520,8 +1520,11 @@ static void isd200_ata_command(struct scsi_cmnd *srb, struct us_data *us) /* Make sure driver was initialized */ - if (us->extra == NULL) + if (us->extra == NULL) { usb_stor_dbg(us, "ERROR Driver not initialized\n"); + srb->result = DID_ERROR << 16; + return; + } scsi_set_resid(srb, 0); /* scsi_bufflen might change in protocol translation to ata */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 53341a77d89f..a37ed1e59e99 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -123,9 +123,9 @@ UNUSUAL_DEV(0x0bc2, 0xab2a, 0x0000, 0x9999, /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */ UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999, "Initio Corporation", - "", + "INIC-3069", USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_NO_ATA_1X), + US_FL_NO_ATA_1X | US_FL_IGNORE_RESIDUE), /* Reported-by: Tom Arild Naess <tanaess@gmail.com> */ UNUSUAL_DEV(0x152d, 0x0539, 0x0000, 0x9999, diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c index 44ab43fc4fcc..af10f7b131a4 100644 --- a/drivers/usb/usbip/stub_main.c +++ b/drivers/usb/usbip/stub_main.c @@ -262,7 +262,11 @@ void stub_device_cleanup_urbs(struct stub_device *sdev) kmem_cache_free(stub_priv_cache, priv); kfree(urb->transfer_buffer); + urb->transfer_buffer = NULL; + kfree(urb->setup_packet); + urb->setup_packet = NULL; + usb_free_urb(urb); } } diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c index dbcabc9dbe0d..021003c4de53 100644 --- a/drivers/usb/usbip/stub_tx.c +++ b/drivers/usb/usbip/stub_tx.c @@ -28,7 +28,11 @@ static void stub_free_priv_and_urb(struct stub_priv *priv) struct urb *urb = priv->urb; kfree(urb->setup_packet); + urb->setup_packet = NULL; + kfree(urb->transfer_buffer); + urb->transfer_buffer = NULL; + list_del(&priv->list); kmem_cache_free(stub_priv_cache, priv); usb_free_urb(urb); diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 7fbe19d5279e..81b2b9f808b5 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -215,14 +215,19 @@ done: static inline void hub_descriptor(struct usb_hub_descriptor *desc) { + int width; + memset(desc, 0, sizeof(*desc)); desc->bDescriptorType = USB_DT_HUB; - desc->bDescLength = 9; desc->wHubCharacteristics = cpu_to_le16( HUB_CHAR_INDV_PORT_LPSM | HUB_CHAR_COMMON_OCPM); + desc->bNbrPorts = VHCI_NPORTS; - desc->u.hs.DeviceRemovable[0] = 0xff; - desc->u.hs.DeviceRemovable[1] = 0xff; + BUILD_BUG_ON(VHCI_NPORTS > USB_MAXCHILDREN); + width = desc->bNbrPorts / 8 + 1; + desc->bDescLength = USB_DT_HUB_NONVAR_SIZE + 2 * width; + memset(&desc->u.hs.DeviceRemovable[0], 0, width); + memset(&desc->u.hs.DeviceRemovable[width], 0xff, width); } static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, diff --git a/drivers/usb/wusbcore/wa-hc.c b/drivers/usb/wusbcore/wa-hc.c index 252c7bd9218a..d01496fd27fe 100644 --- a/drivers/usb/wusbcore/wa-hc.c +++ b/drivers/usb/wusbcore/wa-hc.c @@ -39,6 +39,9 @@ int wa_create(struct wahc *wa, struct usb_interface *iface, int result; struct device *dev = &iface->dev; + if (iface->cur_altsetting->desc.bNumEndpoints < 3) + return -ENODEV; + result = wa_rpipes_create(wa); if (result < 0) goto error_rpipes_create; diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c index 0257f35cfb9d..e75bbe5a10cd 100644 --- a/drivers/uwb/hwa-rc.c +++ b/drivers/uwb/hwa-rc.c @@ -825,6 +825,9 @@ static int hwarc_probe(struct usb_interface *iface, struct hwarc *hwarc; struct device *dev = &iface->dev; + if (iface->cur_altsetting->desc.bNumEndpoints < 1) + return -ENODEV; + result = -ENOMEM; uwb_rc = uwb_rc_alloc(); if (uwb_rc == NULL) { diff --git a/drivers/uwb/i1480/dfu/usb.c b/drivers/uwb/i1480/dfu/usb.c index 2bfc846ac071..a50cf45e530f 100644 --- a/drivers/uwb/i1480/dfu/usb.c +++ b/drivers/uwb/i1480/dfu/usb.c @@ -341,6 +341,7 @@ error_submit_ep1: static int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id) { + struct usb_device *udev = interface_to_usbdev(iface); struct i1480_usb *i1480_usb; struct i1480 *i1480; struct device *dev = &iface->dev; @@ -352,8 +353,8 @@ int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id) iface->cur_altsetting->desc.bInterfaceNumber); goto error; } - if (iface->num_altsetting > 1 - && interface_to_usbdev(iface)->descriptor.idProduct == 0xbabe) { + if (iface->num_altsetting > 1 && + le16_to_cpu(udev->descriptor.idProduct) == 0xbabe) { /* Need altsetting #1 [HW QUIRK] or EP1 won't work */ result = usb_set_interface(interface_to_usbdev(iface), 0, 1); if (result < 0) @@ -362,6 +363,9 @@ int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id) result); } + if (iface->cur_altsetting->desc.bNumEndpoints < 1) + return -ENODEV; + result = -ENOMEM; i1480_usb = kzalloc(sizeof(*i1480_usb), GFP_KERNEL); if (i1480_usb == NULL) { diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 9982cb176ce8..b31b84f56e8f 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -562,8 +562,9 @@ static long vfio_pci_ioctl(void *device_data, } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; + size_t size; u8 *data = NULL; - int ret = 0; + int max, ret = 0; minsz = offsetofend(struct vfio_irq_set, count); @@ -571,23 +572,31 @@ static long vfio_pci_ioctl(void *device_data, return -EFAULT; if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS || + hdr.count >= (U32_MAX - hdr.start) || hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK | VFIO_IRQ_SET_ACTION_TYPE_MASK)) return -EINVAL; - if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) { - size_t size; - int max = vfio_pci_get_irq_count(vdev, hdr.index); + max = vfio_pci_get_irq_count(vdev, hdr.index); + if (hdr.start >= max || hdr.start + hdr.count > max) + return -EINVAL; - if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL) - size = sizeof(uint8_t); - else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD) - size = sizeof(int32_t); - else - return -EINVAL; + switch (hdr.flags & VFIO_IRQ_SET_DATA_TYPE_MASK) { + case VFIO_IRQ_SET_DATA_NONE: + size = 0; + break; + case VFIO_IRQ_SET_DATA_BOOL: + size = sizeof(uint8_t); + break; + case VFIO_IRQ_SET_DATA_EVENTFD: + size = sizeof(int32_t); + break; + default: + return -EINVAL; + } - if (hdr.argsz - minsz < hdr.count * size || - hdr.start >= max || hdr.start + hdr.count > max) + if (size) { + if (hdr.argsz - minsz < hdr.count * size) return -EINVAL; data = memdup_user((void __user *)(arg + minsz), @@ -893,6 +902,10 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) return ret; vdev->barmap[index] = pci_iomap(pdev, index, 0); + if (!vdev->barmap[index]) { + pci_release_selected_regions(pdev, 1 << index); + return -ENOMEM; + } } vma->vm_private_data = vdev; diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 20e9a86d2dcf..5c8f767b6368 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -255,7 +255,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) if (!is_irq_none(vdev)) return -EINVAL; - vdev->ctx = kzalloc(nvec * sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); + vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); if (!vdev->ctx) return -ENOMEM; diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 210db24d2204..4d39f7959adf 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -190,7 +190,10 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf, if (!vdev->has_vga) return -EINVAL; - switch (pos) { + if (pos > 0xbfffful) + return -EINVAL; + + switch ((u32)pos) { case 0xa0000 ... 0xbffff: count = min(count, (size_t)(0xc0000 - pos)); iomem = ioremap_nocache(0xa0000, 0xbffff - 0xa0000 + 1); diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 6070b793cbcb..1e01e28f40f3 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -296,6 +296,34 @@ static void vfio_group_put(struct vfio_group *group) kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock); } +struct vfio_group_put_work { + struct work_struct work; + struct vfio_group *group; +}; + +static void vfio_group_put_bg(struct work_struct *work) +{ + struct vfio_group_put_work *do_work; + + do_work = container_of(work, struct vfio_group_put_work, work); + + vfio_group_put(do_work->group); + kfree(do_work); +} + +static void vfio_group_schedule_put(struct vfio_group *group) +{ + struct vfio_group_put_work *do_work; + + do_work = kmalloc(sizeof(*do_work), GFP_KERNEL); + if (WARN_ON(!do_work)) + return; + + INIT_WORK(&do_work->work, vfio_group_put_bg); + do_work->group = group; + schedule_work(&do_work->work); +} + /* Assume group_lock or group reference is held */ static void vfio_group_get(struct vfio_group *group) { @@ -620,7 +648,14 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb, break; } - vfio_group_put(group); + /* + * If we're the last reference to the group, the group will be + * released, which includes unregistering the iommu group notifier. + * We hold a read-lock on that notifier list, unregistering needs + * a write-lock... deadlock. Release our reference asynchronously + * to avoid that situation. + */ + vfio_group_schedule_put(group); return NOTIFY_OK; } @@ -1552,6 +1587,15 @@ void vfio_group_put_external_user(struct vfio_group *group) } EXPORT_SYMBOL_GPL(vfio_group_put_external_user); +bool vfio_external_group_match_file(struct vfio_group *test_group, + struct file *filep) +{ + struct vfio_group *group = filep->private_data; + + return (filep->f_op == &vfio_group_fops) && (group == test_group); +} +EXPORT_SYMBOL_GPL(vfio_external_group_match_file); + int vfio_external_user_iommu_id(struct vfio_group *group) { return iommu_group_id(group->iommu_group); diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 0582b72ef377..34e4b3ad8b92 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -511,6 +511,12 @@ static long tce_iommu_build_v2(struct tce_container *container, unsigned long hpa; enum dma_data_direction dirtmp; + if (!tbl->it_userspace) { + ret = tce_iommu_userspace_view_alloc(tbl); + if (ret) + return ret; + } + for (i = 0; i < pages; ++i) { struct mm_iommu_table_group_mem_t *mem = NULL; unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, @@ -584,15 +590,6 @@ static long tce_iommu_create_table(struct tce_container *container, WARN_ON(!ret && !(*ptbl)->it_ops->free); WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size)); - if (!ret && container->v2) { - ret = tce_iommu_userspace_view_alloc(*ptbl); - if (ret) - (*ptbl)->it_ops->free(*ptbl); - } - - if (ret) - decrement_locked_vm(table_size >> PAGE_SHIFT); - return ret; } @@ -1064,10 +1061,7 @@ static int tce_iommu_take_ownership(struct tce_container *container, if (!tbl || !tbl->it_map) continue; - rc = tce_iommu_userspace_view_alloc(tbl); - if (!rc) - rc = iommu_take_ownership(tbl); - + rc = iommu_take_ownership(tbl); if (rc) { for (j = 0; j < i; ++j) iommu_release_ownership( @@ -1169,6 +1163,10 @@ static int tce_iommu_attach_group(void *iommu_data, /* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n", iommu_group_id(iommu_group), iommu_group); */ table_group = iommu_group_get_iommudata(iommu_group); + if (!table_group) { + ret = -ENODEV; + goto unlock_exit; + } if (tce_groups_attached(container) && (!table_group->ops || !table_group->ops->take_ownership || diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index ecb826eefe02..2fa280671c1e 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -130,57 +130,34 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old) rb_erase(&old->node, &iommu->dma_list); } -struct vwork { - struct mm_struct *mm; - long npage; - struct work_struct work; -}; - -/* delayed decrement/increment for locked_vm */ -static void vfio_lock_acct_bg(struct work_struct *work) +static int vfio_lock_acct(long npage, bool *lock_cap) { - struct vwork *vwork = container_of(work, struct vwork, work); - struct mm_struct *mm; - - mm = vwork->mm; - down_write(&mm->mmap_sem); - mm->locked_vm += vwork->npage; - up_write(&mm->mmap_sem); - mmput(mm); - kfree(vwork); -} + int ret = 0; -static void vfio_lock_acct(long npage) -{ - struct vwork *vwork; - struct mm_struct *mm; + if (!npage) + return 0; - if (!current->mm || !npage) - return; /* process exited or nothing to do */ + if (!current->mm) + return -ESRCH; /* process exited */ - if (down_write_trylock(¤t->mm->mmap_sem)) { - current->mm->locked_vm += npage; - up_write(¤t->mm->mmap_sem); - return; - } + down_write(¤t->mm->mmap_sem); + if (npage > 0) { + if (lock_cap ? !*lock_cap : !capable(CAP_IPC_LOCK)) { + unsigned long limit; - /* - * Couldn't get mmap_sem lock, so must setup to update - * mm->locked_vm later. If locked_vm were atomic, we - * wouldn't need this silliness - */ - vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL); - if (!vwork) - return; - mm = get_task_mm(current); - if (!mm) { - kfree(vwork); - return; + limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + if (current->mm->locked_vm + npage > limit) + ret = -ENOMEM; + } } - INIT_WORK(&vwork->work, vfio_lock_acct_bg); - vwork->mm = mm; - vwork->npage = npage; - schedule_work(&vwork->work); + + if (!ret) + current->mm->locked_vm += npage; + + up_write(¤t->mm->mmap_sem); + + return ret; } /* @@ -262,9 +239,9 @@ static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn) static long vfio_pin_pages(unsigned long vaddr, long npage, int prot, unsigned long *pfn_base) { - unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + unsigned long pfn = 0, limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; bool lock_cap = capable(CAP_IPC_LOCK); - long ret, i; + long ret, i = 1; bool rsvd; if (!current->mm) @@ -283,16 +260,11 @@ static long vfio_pin_pages(unsigned long vaddr, long npage, return -ENOMEM; } - if (unlikely(disable_hugepages)) { - if (!rsvd) - vfio_lock_acct(1); - return 1; - } + if (unlikely(disable_hugepages)) + goto out; /* Lock all the consecutive pages from pfn_base */ - for (i = 1, vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) { - unsigned long pfn = 0; - + for (vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) { ret = vaddr_get_pfn(vaddr, prot, &pfn); if (ret) break; @@ -308,12 +280,24 @@ static long vfio_pin_pages(unsigned long vaddr, long npage, put_pfn(pfn, prot); pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__, limit << PAGE_SHIFT); - break; + ret = -ENOMEM; + goto unpin_out; } } +out: if (!rsvd) - vfio_lock_acct(i); + ret = vfio_lock_acct(i, &lock_cap); + +unpin_out: + if (ret) { + if (!rsvd) { + for (pfn = *pfn_base ; i ; pfn++, i--) + put_pfn(pfn, prot); + } + + return ret; + } return i; } @@ -328,7 +312,7 @@ static long vfio_unpin_pages(unsigned long pfn, long npage, unlocked += put_pfn(pfn++, prot); if (do_accounting) - vfio_lock_acct(-unlocked); + vfio_lock_acct(-unlocked, NULL); return unlocked; } @@ -390,7 +374,7 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma) cond_resched(); } - vfio_lock_acct(-unlocked); + vfio_lock_acct(-unlocked, NULL); } static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma) diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 6e92917ba77a..4e3c78d88832 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -1168,6 +1168,8 @@ static void fbcon_free_font(struct display *p, bool freefont) p->userfont = 0; } +static void set_vc_hi_font(struct vc_data *vc, bool set); + static void fbcon_deinit(struct vc_data *vc) { struct display *p = &fb_display[vc->vc_num]; @@ -1203,6 +1205,9 @@ finished: if (free_font) vc->vc_font.data = NULL; + if (vc->vc_hi_font_mask) + set_vc_hi_font(vc, false); + if (!con_is_bound(&fb_con)) fbcon_exit(); @@ -2439,32 +2444,10 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) return 0; } -static int fbcon_do_set_font(struct vc_data *vc, int w, int h, - const u8 * data, int userfont) +/* set/clear vc_hi_font_mask and update vc attrs accordingly */ +static void set_vc_hi_font(struct vc_data *vc, bool set) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct display *p = &fb_display[vc->vc_num]; - int resize; - int cnt; - char *old_data = NULL; - - if (CON_IS_VISIBLE(vc) && softback_lines) - fbcon_set_origin(vc); - - resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); - if (p->userfont) - old_data = vc->vc_font.data; - if (userfont) - cnt = FNTCHARCNT(data); - else - cnt = 256; - vc->vc_font.data = (void *)(p->fontdata = data); - if ((p->userfont = userfont)) - REFCOUNT(data)++; - vc->vc_font.width = w; - vc->vc_font.height = h; - if (vc->vc_hi_font_mask && cnt == 256) { + if (!set) { vc->vc_hi_font_mask = 0; if (vc->vc_can_do_color) { vc->vc_complement_mask >>= 1; @@ -2487,7 +2470,7 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, ((c & 0xfe00) >> 1) | (c & 0xff); vc->vc_attr >>= 1; } - } else if (!vc->vc_hi_font_mask && cnt == 512) { + } else { vc->vc_hi_font_mask = 0x100; if (vc->vc_can_do_color) { vc->vc_complement_mask <<= 1; @@ -2519,8 +2502,38 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, } else vc->vc_video_erase_char = c & ~0x100; } - } +} + +static int fbcon_do_set_font(struct vc_data *vc, int w, int h, + const u8 * data, int userfont) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct display *p = &fb_display[vc->vc_num]; + int resize; + int cnt; + char *old_data = NULL; + + if (CON_IS_VISIBLE(vc) && softback_lines) + fbcon_set_origin(vc); + + resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); + if (p->userfont) + old_data = vc->vc_font.data; + if (userfont) + cnt = FNTCHARCNT(data); + else + cnt = 256; + vc->vc_font.data = (void *)(p->fontdata = data); + if ((p->userfont = userfont)) + REFCOUNT(data)++; + vc->vc_font.width = w; + vc->vc_font.height = h; + if (vc->vc_hi_font_mask && cnt == 256) + set_vc_hi_font(vc, false); + else if (!vc->vc_hi_font_mask && cnt == 512) + set_vc_hi_font(vc, true); if (resize) { int cols, rows; diff --git a/drivers/video/fbdev/cobalt_lcdfb.c b/drivers/video/fbdev/cobalt_lcdfb.c index 07675d6f323e..d4530b54479c 100644 --- a/drivers/video/fbdev/cobalt_lcdfb.c +++ b/drivers/video/fbdev/cobalt_lcdfb.c @@ -350,6 +350,11 @@ static int cobalt_lcdfb_probe(struct platform_device *dev) info->screen_size = resource_size(res); info->screen_base = devm_ioremap(&dev->dev, res->start, info->screen_size); + if (!info->screen_base) { + framebuffer_release(info); + return -ENOMEM; + } + info->fbops = &cobalt_lcd_fbops; info->fix = cobalt_lcdfb_fix; info->fix.smem_start = res->start; diff --git a/drivers/video/fbdev/core/fbcmap.c b/drivers/video/fbdev/core/fbcmap.c index f89245b8ba8e..68a113594808 100644 --- a/drivers/video/fbdev/core/fbcmap.c +++ b/drivers/video/fbdev/core/fbcmap.c @@ -163,17 +163,18 @@ void fb_dealloc_cmap(struct fb_cmap *cmap) int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to) { - int tooff = 0, fromoff = 0; - int size; + unsigned int tooff = 0, fromoff = 0; + size_t size; if (to->start > from->start) fromoff = to->start - from->start; else tooff = from->start - to->start; - size = to->len - tooff; - if (size > (int) (from->len - fromoff)) - size = from->len - fromoff; - if (size <= 0) + if (fromoff >= from->len || tooff >= to->len) + return -EINVAL; + + size = min_t(size_t, to->len - tooff, from->len - fromoff); + if (size == 0) return -EINVAL; size *= sizeof(u16); @@ -187,17 +188,18 @@ int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to) int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to) { - int tooff = 0, fromoff = 0; - int size; + unsigned int tooff = 0, fromoff = 0; + size_t size; if (to->start > from->start) fromoff = to->start - from->start; else tooff = from->start - to->start; - size = to->len - tooff; - if (size > (int) (from->len - fromoff)) - size = from->len - fromoff; - if (size <= 0) + if (fromoff >= from->len || tooff >= to->len) + return -EINVAL; + + size = min_t(size_t, to->len - tooff, from->len - fromoff); + if (size == 0) return -EINVAL; size *= sizeof(u16); diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index 0567d517eed3..ea2f19f5fbde 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -644,7 +644,6 @@ static void xenfb_backend_changed(struct xenbus_device *dev, break; case XenbusStateInitWait: -InitWait: xenbus_switch_state(dev, XenbusStateConnected); break; @@ -655,7 +654,8 @@ InitWait: * get Connected twice here. */ if (dev->state != XenbusStateConnected) - goto InitWait; /* no InitWait seen yet, fudge it */ + /* no InitWait seen yet, fudge it */ + xenbus_switch_state(dev, XenbusStateConnected); if (xenbus_scanf(XBT_NIL, info->xbdev->otherend, "request-update", "%d", &val) < 0) diff --git a/drivers/video/serdes/fpd3_i2c_adap.c b/drivers/video/serdes/fpd3_i2c_adap.c index d43de5a43c06..8cc866fc1221 100644 --- a/drivers/video/serdes/fpd3_i2c_adap.c +++ b/drivers/video/serdes/fpd3_i2c_adap.c @@ -100,8 +100,10 @@ static int fpd3_serdes_setup_aliases(struct i2c_client *client) count++; } - if (count >= FPD3_MAX_POLL_COUNT) + if (count >= FPD3_MAX_POLL_COUNT) { + dev_err(&client->dev, "Unable to sync with remote slave"); return -EIO; + } dev_dbg(&client->dev, "Remote signal detected"); return 0; @@ -197,7 +199,7 @@ static int fpd3_master_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) { struct i2c_adapter *alias_adap; - struct i2c_msg new_msg; + struct i2c_msg *new_msg; u8 alias_addr; int i, ret = 0; @@ -206,22 +208,26 @@ static int fpd3_master_xfer(struct i2c_adapter *adap, alias_adap = __get_alias_adapter(adap); + new_msg = kcalloc(num, sizeof(*new_msg), GFP_KERNEL); + for (i = 0; i < num; i++) { alias_addr = __get_alias_addr(adap, msgs[i].addr); if (alias_addr == 0) { ret = -EINVAL; - break; + goto cleanup; } /* Copy the i2c_msgs into temporary buffer; xlate address */ - new_msg = msgs[i]; - new_msg.addr = alias_addr; - /* Issue the messages on the alias adapter */ - ret = i2c_transfer(alias_adap, &new_msg, 1); - if (ret) - break; + new_msg[i] = msgs[i]; + new_msg[i].addr = alias_addr; } + /* Issue the messages on the alias adapter */ + ret = i2c_transfer(alias_adap, new_msg, num); + + cleanup: + kfree(new_msg); + return ret; } diff --git a/drivers/video/serdes/fpd3_serdes.c b/drivers/video/serdes/fpd3_serdes.c index 90de8d559f2f..3598683a3d31 100644 --- a/drivers/video/serdes/fpd3_serdes.c +++ b/drivers/video/serdes/fpd3_serdes.c @@ -23,6 +23,8 @@ * DS90UB913aq/DS90UB914aq http://www.ti.com/lit/ds/snls443a/snls443a.pdf * DS90UH925Q http://www.ti.com/lit/ds/symlink/ds90uh925q-q1.pdf * DS90UH928Q http://www.ti.com/lit/ds/snls440a/snls440a.pdf + * DS90UB924Q http://www.ti.com/lit/ds/snls512/snls512.pdf + * DS90UB921Q http://www.ti.com/lit/ds/symlink/ds90ub921-q1.pdf * * Documentation:- * -> Documentation/video-serdes.txt @@ -78,6 +80,20 @@ static const unsigned int fpd3_24bit_des_init[] = { FPD3_DES_CONFIG1, 0x4c, }; +static const unsigned int fpd3_921_ser_init[] = { + /* Reset entire digital block except registers */ + FPD3_SER_RESET, 0x01, + /* back chan en, auto ack WR, i2c passthrough, rising edge pclk */ + FPD3_SER_CONFIG1, 0x8b, +}; + +static const unsigned int fpd3_924_des_init[] = { + /* digital reset1 */ + FPD3_DES_RESET, 0x02, + /* back channel en */ + FPD3_DES_RESET, 0x04, +}; + static struct fpd3_serdes_platform_data fpd3_serdes_pdata[] = { { .name = "fpd3_12b_ser", @@ -119,6 +135,26 @@ static struct fpd3_serdes_platform_data fpd3_serdes_pdata[] = { .init_seq = fpd3_24bit_des_init, .init_len = ARRAY_SIZE(fpd3_24bit_des_init), }, + { + .name = "fpd3_924_des", + .dev_type = FPD3_DES_DEV, + .ngpio = 4, + .nslaves = 8, + .device_id = 0x58, + .gpio_2reg = 2 * FPD3_DES_GPIO_01 + 1, + .init_seq = fpd3_924_des_init, + .init_len = ARRAY_SIZE(fpd3_924_des_init), + }, + { + .name = "fpd3_921_ser", + .dev_type = FPD3_SER_DEV, + .ngpio = 4, + .nslaves = 1, + .device_id = 0x18, + .gpio_2reg = 2 * FPD3_SER_GPIO_01 + 1, + .init_seq = fpd3_921_ser_init, + .init_len = ARRAY_SIZE(fpd3_921_ser_init), + }, }; /* GPIO operations */ @@ -309,6 +345,8 @@ static const struct i2c_device_id fpd3_serdes_i2c_ids[] = { { "ds90ub914aq", 8 }, { "ds90uh925q", 8 }, { "ds90uh928q", 8 }, + { "ds90ub924q", 8 }, + { "ds90ub921q", 8 }, { } }; MODULE_DEVICE_TABLE(i2c, fpd3_serdes_i2c_ids); @@ -318,6 +356,8 @@ static const struct of_device_id fpd3_serdes_dt_ids[] = { {.compatible = "ti,ds90ub914aq", &fpd3_serdes_pdata[1], }, {.compatible = "ti,ds90uh925q", &fpd3_serdes_pdata[2], }, {.compatible = "ti,ds90uh928q", &fpd3_serdes_pdata[3], }, + {.compatible = "ti,ds90ub924q", &fpd3_serdes_pdata[4], }, + {.compatible = "ti,ds90ub921q", &fpd3_serdes_pdata[5], }, { } }; diff --git a/drivers/video/serdes/fpd3_serdes.h b/drivers/video/serdes/fpd3_serdes.h index e5d05cdcf718..45c695ab27da 100644 --- a/drivers/video/serdes/fpd3_serdes.h +++ b/drivers/video/serdes/fpd3_serdes.h @@ -14,7 +14,6 @@ #define FPD3_DES_SLAVE_AL0 0x10 #define FPD3_DES_GN_STS 0x1c - #define SIGNAL_DETECT (1<<1) #define FPD3_DES_GPIO_01 0x1d #define FPD3_DES_GPIO_23 0x1e @@ -34,7 +33,6 @@ #define FPD3_SER_SLAVE_AL0 0x08 #define FPD3_SER_GN_STS 0x0c - #define SIGNAL_DETECT (1<<1) #define FPD3_SER_GPIO_01 0x0d #define FPD3_SER_GPIO_23 0x0e @@ -48,6 +46,8 @@ #define GPIO_DIR_INPUT 1 #define GPIO_DIR_OUTPUT 0 +#define SIGNAL_DETECT (1<<0) + #define FPD3_MAX_POLL_COUNT 100 #define FPD3_SERDES_MAX_SLAVES 10 diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 66082c99f6ea..0c5533813cde 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -416,6 +416,8 @@ static int init_vqs(struct virtio_balloon *vb) * Prime this virtqueue with one buffer so the hypervisor can * use it to signal us later (it can't be broken yet!). */ + update_balloon_stats(vb); + sg_init_one(&sg, vb->stats, sizeof vb->stats); if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL) < 0) diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c index 049a884a756f..59d74d1b47a8 100644 --- a/drivers/w1/masters/ds2490.c +++ b/drivers/w1/masters/ds2490.c @@ -153,6 +153,9 @@ struct ds_device */ u16 spu_bit; + u8 st_buf[ST_SIZE]; + u8 byte_buf; + struct w1_bus_master master; }; @@ -174,7 +177,6 @@ struct ds_status u8 data_in_buffer_status; u8 reserved1; u8 reserved2; - }; static struct usb_device_id ds_id_table [] = { @@ -244,28 +246,6 @@ static int ds_send_control(struct ds_device *dev, u16 value, u16 index) return err; } -static int ds_recv_status_nodump(struct ds_device *dev, struct ds_status *st, - unsigned char *buf, int size) -{ - int count, err; - - memset(st, 0, sizeof(*st)); - - count = 0; - err = usb_interrupt_msg(dev->udev, usb_rcvintpipe(dev->udev, - dev->ep[EP_STATUS]), buf, size, &count, 1000); - if (err < 0) { - pr_err("Failed to read 1-wire data from 0x%x: err=%d.\n", - dev->ep[EP_STATUS], err); - return err; - } - - if (count >= sizeof(*st)) - memcpy(st, buf, sizeof(*st)); - - return count; -} - static inline void ds_print_msg(unsigned char *buf, unsigned char *str, int off) { pr_info("%45s: %8x\n", str, buf[off]); @@ -324,6 +304,35 @@ static void ds_dump_status(struct ds_device *dev, unsigned char *buf, int count) } } +static int ds_recv_status(struct ds_device *dev, struct ds_status *st, + bool dump) +{ + int count, err; + + if (st) + memset(st, 0, sizeof(*st)); + + count = 0; + err = usb_interrupt_msg(dev->udev, + usb_rcvintpipe(dev->udev, + dev->ep[EP_STATUS]), + dev->st_buf, sizeof(dev->st_buf), + &count, 1000); + if (err < 0) { + pr_err("Failed to read 1-wire data from 0x%x: err=%d.\n", + dev->ep[EP_STATUS], err); + return err; + } + + if (dump) + ds_dump_status(dev, dev->st_buf, count); + + if (st && count >= sizeof(*st)) + memcpy(st, dev->st_buf, sizeof(*st)); + + return count; +} + static void ds_reset_device(struct ds_device *dev) { ds_send_control_cmd(dev, CTL_RESET_DEVICE, 0); @@ -344,7 +353,6 @@ static void ds_reset_device(struct ds_device *dev) static int ds_recv_data(struct ds_device *dev, unsigned char *buf, int size) { int count, err; - struct ds_status st; /* Careful on size. If size is less than what is available in * the input buffer, the device fails the bulk transfer and @@ -359,14 +367,9 @@ static int ds_recv_data(struct ds_device *dev, unsigned char *buf, int size) err = usb_bulk_msg(dev->udev, usb_rcvbulkpipe(dev->udev, dev->ep[EP_DATA_IN]), buf, size, &count, 1000); if (err < 0) { - u8 buf[ST_SIZE]; - int count; - pr_info("Clearing ep0x%x.\n", dev->ep[EP_DATA_IN]); usb_clear_halt(dev->udev, usb_rcvbulkpipe(dev->udev, dev->ep[EP_DATA_IN])); - - count = ds_recv_status_nodump(dev, &st, buf, sizeof(buf)); - ds_dump_status(dev, buf, count); + ds_recv_status(dev, NULL, true); return err; } @@ -404,7 +407,6 @@ int ds_stop_pulse(struct ds_device *dev, int limit) { struct ds_status st; int count = 0, err = 0; - u8 buf[ST_SIZE]; do { err = ds_send_control(dev, CTL_HALT_EXE_IDLE, 0); @@ -413,7 +415,7 @@ int ds_stop_pulse(struct ds_device *dev, int limit) err = ds_send_control(dev, CTL_RESUME_EXE, 0); if (err) break; - err = ds_recv_status_nodump(dev, &st, buf, sizeof(buf)); + err = ds_recv_status(dev, &st, false); if (err) break; @@ -456,18 +458,17 @@ int ds_detect(struct ds_device *dev, struct ds_status *st) static int ds_wait_status(struct ds_device *dev, struct ds_status *st) { - u8 buf[ST_SIZE]; int err, count = 0; do { st->status = 0; - err = ds_recv_status_nodump(dev, st, buf, sizeof(buf)); + err = ds_recv_status(dev, st, false); #if 0 if (err >= 0) { int i; printk("0x%x: count=%d, status: ", dev->ep[EP_STATUS], err); for (i=0; i<err; ++i) - printk("%02x ", buf[i]); + printk("%02x ", dev->st_buf[i]); printk("\n"); } #endif @@ -485,7 +486,7 @@ static int ds_wait_status(struct ds_device *dev, struct ds_status *st) * can do something with it). */ if (err > 16 || count >= 100 || err < 0) - ds_dump_status(dev, buf, err); + ds_dump_status(dev, dev->st_buf, err); /* Extended data isn't an error. Well, a short is, but the dump * would have already told the user that and we can't do anything @@ -608,7 +609,6 @@ static int ds_write_byte(struct ds_device *dev, u8 byte) { int err; struct ds_status st; - u8 rbyte; err = ds_send_control(dev, COMM_BYTE_IO | COMM_IM | dev->spu_bit, byte); if (err) @@ -621,11 +621,11 @@ static int ds_write_byte(struct ds_device *dev, u8 byte) if (err) return err; - err = ds_recv_data(dev, &rbyte, sizeof(rbyte)); + err = ds_recv_data(dev, &dev->byte_buf, 1); if (err < 0) return err; - return !(byte == rbyte); + return !(byte == dev->byte_buf); } static int ds_read_byte(struct ds_device *dev, u8 *byte) @@ -712,7 +712,6 @@ static void ds9490r_search(void *data, struct w1_master *master, int err; u16 value, index; struct ds_status st; - u8 st_buf[ST_SIZE]; int search_limit; int found = 0; int i; @@ -724,7 +723,12 @@ static void ds9490r_search(void *data, struct w1_master *master, /* FIFO 128 bytes, bulk packet size 64, read a multiple of the * packet size. */ - u64 buf[2*64/8]; + const size_t bufsize = 2 * 64; + u64 *buf; + + buf = kmalloc(bufsize, GFP_KERNEL); + if (!buf) + return; mutex_lock(&master->bus_mutex); @@ -745,10 +749,9 @@ static void ds9490r_search(void *data, struct w1_master *master, do { schedule_timeout(jtime); - if (ds_recv_status_nodump(dev, &st, st_buf, sizeof(st_buf)) < - sizeof(st)) { + err = ds_recv_status(dev, &st, false); + if (err < 0 || err < sizeof(st)) break; - } if (st.data_in_buffer_status) { /* Bulk in can receive partial ids, but when it does @@ -758,7 +761,7 @@ static void ds9490r_search(void *data, struct w1_master *master, * bulk without first checking if status says there * is data to read. */ - err = ds_recv_data(dev, (u8 *)buf, sizeof(buf)); + err = ds_recv_data(dev, (u8 *)buf, bufsize); if (err < 0) break; for (i = 0; i < err/8; ++i) { @@ -794,9 +797,14 @@ static void ds9490r_search(void *data, struct w1_master *master, } search_out: mutex_unlock(&master->bus_mutex); + kfree(buf); } #if 0 +/* + * FIXME: if this disabled code is ever used in the future all ds_send_data() + * calls must be changed to use a DMAable buffer. + */ static int ds_match_access(struct ds_device *dev, u64 init) { int err; @@ -845,13 +853,12 @@ static int ds_set_path(struct ds_device *dev, u64 init) static u8 ds9490r_touch_bit(void *data, u8 bit) { - u8 ret; struct ds_device *dev = data; - if (ds_touch_bit(dev, bit, &ret)) + if (ds_touch_bit(dev, bit, &dev->byte_buf)) return 0; - return ret; + return dev->byte_buf; } #if 0 @@ -866,13 +873,12 @@ static u8 ds9490r_read_bit(void *data) { struct ds_device *dev = data; int err; - u8 bit = 0; - err = ds_touch_bit(dev, 1, &bit); + err = ds_touch_bit(dev, 1, &dev->byte_buf); if (err) return 0; - return bit & 1; + return dev->byte_buf & 1; } #endif @@ -887,32 +893,52 @@ static u8 ds9490r_read_byte(void *data) { struct ds_device *dev = data; int err; - u8 byte = 0; - err = ds_read_byte(dev, &byte); + err = ds_read_byte(dev, &dev->byte_buf); if (err) return 0; - return byte; + return dev->byte_buf; } static void ds9490r_write_block(void *data, const u8 *buf, int len) { struct ds_device *dev = data; + u8 *tbuf; + + if (len <= 0) + return; + + tbuf = kmalloc(len, GFP_KERNEL); + if (!tbuf) + return; - ds_write_block(dev, (u8 *)buf, len); + memcpy(tbuf, buf, len); + ds_write_block(dev, tbuf, len); + + kfree(tbuf); } static u8 ds9490r_read_block(void *data, u8 *buf, int len) { struct ds_device *dev = data; int err; + u8 *tbuf; - err = ds_read_block(dev, buf, len); - if (err < 0) + if (len <= 0) + return 0; + + tbuf = kmalloc(len, GFP_KERNEL); + if (!tbuf) return 0; - return len; + err = ds_read_block(dev, tbuf, len); + if (err >= 0) + memcpy(buf, tbuf, len); + + kfree(tbuf); + + return err >= 0 ? len : 0; } static u8 ds9490r_reset(void *data) diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index c9a7ff67d395..39886edfa222 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -763,6 +763,7 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) dev_err(&dev->dev, "%s: Attaching %s failed.\n", __func__, sl->name); w1_family_put(sl->family); + atomic_dec(&sl->master->refcnt); kfree(sl); return err; } diff --git a/drivers/watchdog/bcm_kona_wdt.c b/drivers/watchdog/bcm_kona_wdt.c index e0c98423f2c9..11a72bc2c71b 100644 --- a/drivers/watchdog/bcm_kona_wdt.c +++ b/drivers/watchdog/bcm_kona_wdt.c @@ -304,6 +304,8 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev) if (!wdt) return -ENOMEM; + spin_lock_init(&wdt->lock); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); wdt->base = devm_ioremap_resource(dev, res); if (IS_ERR(wdt->base)) @@ -316,7 +318,6 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev) return ret; } - spin_lock_init(&wdt->lock); platform_set_drvdata(pdev, wdt); watchdog_set_drvdata(&bcm_kona_wdt_wdd, wdt); bcm_kona_wdt_wdd.parent = &pdev->dev; diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c index 1a11aedc4fe8..9eb5b314ba06 100644 --- a/drivers/watchdog/pcwd_usb.c +++ b/drivers/watchdog/pcwd_usb.c @@ -630,6 +630,9 @@ static int usb_pcwd_probe(struct usb_interface *interface, return -ENODEV; } + if (iface_desc->desc.bNumEndpoints < 1) + return -ENODEV; + /* check out the endpoint: it has to be Interrupt & IN */ endpoint = &iface_desc->endpoint[0].desc; diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c index 4da69dbf7dca..1bdd02a6d6ac 100644 --- a/drivers/xen/biomerge.c +++ b/drivers/xen/biomerge.c @@ -10,8 +10,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, unsigned long bfn1 = pfn_to_bfn(page_to_pfn(vec1->bv_page)); unsigned long bfn2 = pfn_to_bfn(page_to_pfn(vec2->bv_page)); - return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) && - ((bfn1 == bfn2) || ((bfn1+1) == bfn2)); + return bfn1 + PFN_DOWN(vec1->bv_offset + vec1->bv_len) == bfn2; #else /* * XXX: Add support for merging bio_vec when using different page diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index df2e6f783318..527de56f832f 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -335,8 +335,8 @@ static int mmap_batch_fn(void *data, int nr, void *state) st->global_error = 1; } } - st->va += PAGE_SIZE * nr; - st->index += nr; + st->va += XEN_PAGE_SIZE * nr; + st->index += nr / XEN_PFN_PER_PAGE; return 0; } diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 7399782c0998..8a58bbc14de2 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -409,9 +409,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, if (map == SWIOTLB_MAP_ERROR) return DMA_ERROR_CODE; + dev_addr = xen_phys_to_bus(map); xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT), dev_addr, map & ~PAGE_MASK, size, dir, attrs); - dev_addr = xen_phys_to_bus(map); /* * Ensure that the address returned is DMA'ble @@ -567,13 +567,14 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, sg_dma_len(sgl) = 0; return 0; } + dev_addr = xen_phys_to_bus(map); xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT), dev_addr, map & ~PAGE_MASK, sg->length, dir, attrs); - sg->dma_address = xen_phys_to_bus(map); + sg->dma_address = dev_addr; } else { /* we are not interested in the dma_addr returned by * xen_dma_map_page, only in the potential cache flushes executed diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index 611f9c11da85..2e319d0c395d 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -27,10 +27,10 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/types.h> +#include <linux/syscore_ops.h> #include <linux/acpi.h> #include <acpi/processor.h> #include <xen/xen.h> -#include <xen/xen-ops.h> #include <xen/interface/platform.h> #include <asm/xen/hypercall.h> @@ -466,15 +466,33 @@ static int xen_upload_processor_pm_data(void) return rc; } -static int xen_acpi_processor_resume(struct notifier_block *nb, - unsigned long action, void *data) +static void xen_acpi_processor_resume_worker(struct work_struct *dummy) { + int rc; + bitmap_zero(acpi_ids_done, nr_acpi_bits); - return xen_upload_processor_pm_data(); + + rc = xen_upload_processor_pm_data(); + if (rc != 0) + pr_info("ACPI data upload failed, error = %d\n", rc); +} + +static void xen_acpi_processor_resume(void) +{ + static DECLARE_WORK(wq, xen_acpi_processor_resume_worker); + + /* + * xen_upload_processor_pm_data() calls non-atomic code. + * However, the context for xen_acpi_processor_resume is syscore + * with only the boot CPU online and in an atomic context. + * + * So defer the upload for some point safer. + */ + schedule_work(&wq); } -struct notifier_block xen_acpi_processor_resume_nb = { - .notifier_call = xen_acpi_processor_resume, +static struct syscore_ops xap_syscore_ops = { + .resume = xen_acpi_processor_resume, }; static int __init xen_acpi_processor_init(void) @@ -527,7 +545,7 @@ static int __init xen_acpi_processor_init(void) if (rc) goto err_unregister; - xen_resume_notifier_register(&xen_acpi_processor_resume_nb); + register_syscore_ops(&xap_syscore_ops); return 0; err_unregister: @@ -544,7 +562,7 @@ static void __exit xen_acpi_processor_exit(void) { int i; - xen_resume_notifier_unregister(&xen_acpi_processor_resume_nb); + unregister_syscore_ops(&xap_syscore_ops); kfree(acpi_ids_done); kfree(acpi_id_present); kfree(acpi_id_cst_present); diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 929b618da43b..c30c6ceac2c4 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -283,6 +283,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, case ACL_TYPE_ACCESS: if (acl) { struct iattr iattr; + struct posix_acl *old_acl = acl; retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); if (retval) @@ -293,6 +294,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, * by the mode bits. So don't * update ACL. */ + posix_acl_release(old_acl); value = NULL; size = 0; } diff --git a/fs/Makefile b/fs/Makefile index 3b54070cd629..dee237540bc0 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -41,7 +41,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += compat_binfmt_elf.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o obj-$(CONFIG_BINFMT_FLAT) += binfmt_flat.o -obj-$(CONFIG_FS_MBCACHE) += mbcache.o +obj-$(CONFIG_FS_MBCACHE) += mbcache.o mbcache2.o obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ obj-$(CONFIG_COREDUMP) += coredump.o diff --git a/fs/attr.c b/fs/attr.c index d62f674a605f..c86b37c38fb7 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -187,7 +187,7 @@ EXPORT_SYMBOL(setattr_copy); * the file open for write, as there can be no conflicting delegation in * that case. */ -int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) +int notify_change2(struct vfsmount *mnt, struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; @@ -211,7 +211,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de return -EPERM; if (!inode_owner_or_capable(inode)) { - error = inode_permission(inode, MAY_WRITE); + error = inode_permission2(mnt, inode, MAY_WRITE); if (error) return error; } @@ -277,7 +277,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de if (error) return error; - if (inode->i_op->setattr) + if (mnt && inode->i_op->setattr2) + error = inode->i_op->setattr2(mnt, dentry, attr); + else if (inode->i_op->setattr) error = inode->i_op->setattr(dentry, attr); else error = simple_setattr(dentry, attr); @@ -290,4 +292,10 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de return error; } +EXPORT_SYMBOL(notify_change2); + +int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) +{ + return notify_change2(NULL, dentry, attr, delegated_inode); +} EXPORT_SYMBOL(notify_change); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index ac7d921ed984..257425511d10 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -331,7 +331,7 @@ static int autofs_dev_ioctl_fail(struct file *fp, int status; token = (autofs_wqt_t) param->fail.token; - status = param->fail.status ? param->fail.status : -ENOENT; + status = param->fail.status < 0 ? param->fail.status : -ENOENT; return autofs4_wait_release(sbi, token, status); } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0c52941dd62c..8a0243efd359 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -905,17 +905,60 @@ static int load_elf_binary(struct linux_binprm *bprm) elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; vaddr = elf_ppnt->p_vaddr; + /* + * If we are loading ET_EXEC or we have already performed + * the ET_DYN load_addr calculations, proceed normally. + */ if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) { elf_flags |= MAP_FIXED; } else if (loc->elf_ex.e_type == ET_DYN) { - /* Try and get dynamic programs out of the way of the - * default mmap base, as well as whatever program they - * might try to exec. This is because the brk will - * follow the loader, and is not movable. */ - load_bias = ELF_ET_DYN_BASE - vaddr; - if (current->flags & PF_RANDOMIZE) - load_bias += arch_mmap_rnd(); - load_bias = ELF_PAGESTART(load_bias); + /* + * This logic is run once for the first LOAD Program + * Header for ET_DYN binaries to calculate the + * randomization (load_bias) for all the LOAD + * Program Headers, and to calculate the entire + * size of the ELF mapping (total_size). (Note that + * load_addr_set is set to true later once the + * initial mapping is performed.) + * + * There are effectively two types of ET_DYN + * binaries: programs (i.e. PIE: ET_DYN with INTERP) + * and loaders (ET_DYN without INTERP, since they + * _are_ the ELF interpreter). The loaders must + * be loaded away from programs since the program + * may otherwise collide with the loader (especially + * for ET_EXEC which does not have a randomized + * position). For example to handle invocations of + * "./ld.so someprog" to test out a new version of + * the loader, the subsequent program that the + * loader loads must avoid the loader itself, so + * they cannot share the same load range. Sufficient + * room for the brk must be allocated with the + * loader as well, since brk must be available with + * the loader. + * + * Therefore, programs are loaded offset from + * ELF_ET_DYN_BASE and loaders are loaded into the + * independently randomized mmap region (0 load_bias + * without MAP_FIXED). + */ + if (elf_interpreter) { + load_bias = ELF_ET_DYN_BASE; + if (current->flags & PF_RANDOMIZE) + load_bias += arch_mmap_rnd(); + elf_flags |= MAP_FIXED; + } else + load_bias = 0; + + /* + * Since load_bias is used for all subsequent loading + * calculations, we must lower it by the first vaddr + * so that the remaining calculations based on the + * ELF vaddrs will be correctly offset. The result + * is then page aligned. + */ + load_bias = ELF_PAGESTART(load_bias - vaddr); + total_size = total_mapping_size(elf_phdata, loc->elf_ex.e_phnum); if (!total_size) { @@ -2295,6 +2338,7 @@ static int elf_core_dump(struct coredump_params *cprm) goto end_coredump; } } + dump_truncate(cprm); if (!elf_core_write_extra_data(cprm)) goto end_coredump; diff --git a/fs/block_dev.c b/fs/block_dev.c index 198aea66fe71..26bbaaefdff4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -88,12 +88,11 @@ void invalidate_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; - if (mapping->nrpages == 0) - return; - - invalidate_bh_lrus(); - lru_add_drain_all(); /* make sure all lru add caches are flushed */ - invalidate_mapping_pages(mapping, 0, -1); + if (mapping->nrpages) { + invalidate_bh_lrus(); + lru_add_drain_all(); /* make sure all lru add caches are flushed */ + invalidate_mapping_pages(mapping, 0, -1); + } /* 99% of the time, we don't need to flush the cleancache on the bdev. * But, for the strange corners, lets be cautious */ @@ -1098,7 +1097,6 @@ int revalidate_disk(struct gendisk *disk) if (disk->fops->revalidate_disk) ret = disk->fops->revalidate_disk(disk); - blk_integrity_revalidate(disk); bdev = bdget_disk(disk, 0); if (!bdev) return ret; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2a2e370399ba..c36a03fa7678 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3854,6 +3854,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, info->space_info_kobj, "%s", alloc_name(found->flags)); if (ret) { + percpu_counter_destroy(&found->total_bytes_pinned); kfree(found); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 353f4bae658c..d4a6eef31854 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2771,7 +2771,7 @@ static long btrfs_fallocate(struct file *file, int mode, if (!ret) ret = btrfs_prealloc_file_range(inode, mode, range->start, - range->len, 1 << inode->i_blkbits, + range->len, i_blocksize(inode), offset + len, &alloc_hint); list_del(&range->list); kfree(range); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3cff6523f27d..bebd6517355d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4397,8 +4397,19 @@ search_again: if (found_type > min_type) { del_item = 1; } else { - if (item_end < new_size) + if (item_end < new_size) { + /* + * With NO_HOLES mode, for the following mapping + * + * [0-4k][hole][8k-12k] + * + * if truncating isize down to 6k, it ends up + * isize being 8k. + */ + if (btrfs_fs_incompat(root->fs_info, NO_HOLES)) + last_size = new_size; break; + } if (found_key.offset >= new_size) del_item = 1; else @@ -7318,8 +7329,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) int found = false; void **pagep = NULL; struct page *page = NULL; - int start_idx; - int end_idx; + unsigned long start_idx; + unsigned long end_idx; start_idx = start >> PAGE_CACHE_SHIFT; @@ -7510,11 +7521,18 @@ static void adjust_dio_outstanding_extents(struct inode *inode, * within our reservation, otherwise we need to adjust our inode * counter appropriately. */ - if (dio_data->outstanding_extents) { + if (dio_data->outstanding_extents >= num_extents) { dio_data->outstanding_extents -= num_extents; } else { + /* + * If dio write length has been split due to no large enough + * contiguous space, we need to compensate our inode counter + * appropriately. + */ + u64 num_needed = num_extents - dio_data->outstanding_extents; + spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents += num_extents; + BTRFS_I(inode)->outstanding_extents += num_needed; spin_unlock(&BTRFS_I(inode)->lock); } } diff --git a/fs/buffer.c b/fs/buffer.c index 4f4cd959da7c..6f7d519a093b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2298,7 +2298,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; + unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata; pgoff_t index, curidx; @@ -2378,8 +2378,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; - unsigned zerofrom; + unsigned int blocksize = i_blocksize(inode); + unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); @@ -2741,7 +2741,7 @@ int nobh_truncate_page(struct address_space *mapping, struct buffer_head map_bh; int err; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ @@ -2819,7 +2819,7 @@ int block_truncate_page(struct address_space *mapping, struct buffer_head *bh; int err; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ @@ -2931,7 +2931,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block, struct inode *inode = mapping->host; tmp.b_state = 0; tmp.b_blocknr = 0; - tmp.b_size = 1 << inode->i_blkbits; + tmp.b_size = i_blocksize(inode); get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 4d8caeb94a11..bdb9c94335f1 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -128,7 +128,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (new_mode != old_mode) { newattrs.ia_mode = new_mode; newattrs.ia_valid = ATTR_MODE; - ret = ceph_setattr(dentry, &newattrs); + ret = __ceph_setattr(dentry, &newattrs); if (ret) goto out_dput; } @@ -138,7 +138,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (new_mode != old_mode) { newattrs.ia_mode = old_mode; newattrs.ia_valid = ATTR_MODE; - ceph_setattr(dentry, &newattrs); + __ceph_setattr(dentry, &newattrs); } goto out_dput; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b7d218a168fb..c6a1ec110c01 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -697,7 +697,7 @@ static int ceph_writepages_start(struct address_space *mapping, struct pagevec pvec; int done = 0; int rc = 0; - unsigned wsize = 1 << inode->i_blkbits; + unsigned int wsize = i_blocksize(inode); struct ceph_osd_request *req = NULL; int do_sync = 0; loff_t snap_size, i_size; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 9314b4ea2375..be7d187d53fd 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -247,6 +247,11 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, if (ret < 0) err = ret; dput(last); + /* last_name no longer match cache index */ + if (fi->readdir_cache_idx >= 0) { + fi->readdir_cache_idx = -1; + fi->dir_release_count = 0; + } } return err; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d98536c8abfc..9f0d99094cc1 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1773,7 +1773,7 @@ static const struct inode_operations ceph_symlink_iops = { /* * setattr */ -int ceph_setattr(struct dentry *dentry, struct iattr *attr) +int __ceph_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct ceph_inode_info *ci = ceph_inode(inode); @@ -1975,11 +1975,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) if (inode_dirty_flags) __mark_inode_dirty(inode, inode_dirty_flags); - if (ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, attr->ia_mode); - if (err) - goto out_put; - } if (mask) { req->r_inode = inode; @@ -1993,13 +1988,23 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) ceph_cap_string(dirtied), mask); ceph_mdsc_put_request(req); - if (mask & CEPH_SETATTR_SIZE) - __ceph_do_pending_vmtruncate(inode); ceph_free_cap_flush(prealloc_cf); + + if (err >= 0 && (mask & CEPH_SETATTR_SIZE)) + __ceph_do_pending_vmtruncate(inode); + return err; -out_put: - ceph_mdsc_put_request(req); - ceph_free_cap_flush(prealloc_cf); +} + +int ceph_setattr(struct dentry *dentry, struct iattr *attr) +{ + int err; + + err = __ceph_setattr(dentry, attr); + + if (err >= 0 && (attr->ia_valid & ATTR_MODE)) + err = posix_acl_chmod(d_inode(dentry), attr->ia_mode); + return err; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 239bc9cba28c..f54f77037d22 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -644,6 +644,9 @@ static void __unregister_request(struct ceph_mds_client *mdsc, { dout("__unregister_request %p tid %lld\n", req, req->r_tid); + /* Never leave an unregistered request on an unsafe list! */ + list_del_init(&req->r_unsafe_item); + if (req->r_tid == mdsc->oldest_tid) { struct rb_node *p = rb_next(&req->r_node); mdsc->oldest_tid = 0; @@ -1051,7 +1054,6 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc, while (!list_empty(&session->s_unsafe)) { req = list_first_entry(&session->s_unsafe, struct ceph_mds_request, r_unsafe_item); - list_del_init(&req->r_unsafe_item); pr_warn_ratelimited(" dropping unsafe request %llu\n", req->r_tid); __unregister_request(mdsc, req); @@ -2477,7 +2479,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) * useful we could do with a revised return value. */ dout("got safe reply %llu, mds%d\n", tid, mds); - list_del_init(&req->r_unsafe_item); /* last unsafe request during umount? */ if (mdsc->stopping && !__get_oldest_req(mdsc)) diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 75b7d125ce66..8c8cb8fe3d32 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -788,6 +788,7 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force) return __ceph_do_getattr(inode, NULL, mask, force); } extern int ceph_permission(struct inode *inode, int mask); +extern int __ceph_setattr(struct dentry *dentry, struct iattr *attr); extern int ceph_setattr(struct dentry *dentry, struct iattr *attr); extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 819163d8313b..b24275ef97f7 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -369,6 +369,7 @@ static int __set_xattr(struct ceph_inode_info *ci, if (update_xattr) { int err = 0; + if (xattr && (flags & XATTR_CREATE)) err = -EEXIST; else if (!xattr && (flags & XATTR_REPLACE)) @@ -376,12 +377,14 @@ static int __set_xattr(struct ceph_inode_info *ci, if (err) { kfree(name); kfree(val); + kfree(*newxattr); return err; } if (update_xattr < 0) { if (xattr) __remove_xattr(ci, xattr); kfree(name); + kfree(*newxattr); return 0; } } diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 02b071bf3732..a0b3e7d1be48 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -83,6 +83,9 @@ convert_sfm_char(const __u16 src_char, char *target) case SFM_COLON: *target = ':'; break; + case SFM_DOUBLEQUOTE: + *target = '"'; + break; case SFM_ASTERISK: *target = '*'; break; @@ -418,6 +421,9 @@ static __le16 convert_to_sfm_char(char src_char, bool end_of_string) case ':': dest_char = cpu_to_le16(SFM_COLON); break; + case '"': + dest_char = cpu_to_le16(SFM_DOUBLEQUOTE); + break; case '*': dest_char = cpu_to_le16(SFM_ASTERISK); break; diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index 479bc0a941f3..07ade707fa60 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -57,6 +57,7 @@ * not conflict (although almost does) with the mapping above. */ +#define SFM_DOUBLEQUOTE ((__u16) 0xF020) #define SFM_ASTERISK ((__u16) 0xF021) #define SFM_QUESTION ((__u16) 0xF025) #define SFM_COLON ((__u16) 0xF022) @@ -64,8 +65,8 @@ #define SFM_LESSTHAN ((__u16) 0xF023) #define SFM_PIPE ((__u16) 0xF027) #define SFM_SLASH ((__u16) 0xF026) -#define SFM_PERIOD ((__u16) 0xF028) -#define SFM_SPACE ((__u16) 0xF029) +#define SFM_SPACE ((__u16) 0xF028) +#define SFM_PERIOD ((__u16) 0xF029) /* * Mapping mechanism to use when one of the seven reserved characters is diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index b76883606e4b..e2f6a79e9b01 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -227,6 +227,7 @@ struct smb_version_operations { /* verify the message */ int (*check_message)(char *, unsigned int); bool (*is_oplock_break)(char *, struct TCP_Server_Info *); + int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *); void (*downgrade_oplock)(struct TCP_Server_Info *, struct cifsInodeInfo *, bool); /* process transaction2 response */ @@ -906,7 +907,6 @@ struct cifs_tcon { bool use_persistent:1; /* use persistent instead of durable handles */ #ifdef CONFIG_CIFS_SMB2 bool print:1; /* set if connection to printer share */ - bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */ __le32 capabilities; __u32 share_flags; __u32 maximal_access; @@ -1290,12 +1290,19 @@ struct mid_q_entry { void *callback_data; /* general purpose pointer for callback */ void *resp_buf; /* pointer to received SMB header */ int mid_state; /* wish this were enum but can not pass to wait_event */ + unsigned int mid_flags; __le16 command; /* smb command code */ bool large_buf:1; /* if valid response, is pointer to large buf */ bool multiRsp:1; /* multiple trans2 responses for one request */ bool multiEnd:1; /* both received */ }; +struct close_cancelled_open { + struct cifs_fid fid; + struct cifs_tcon *tcon; + struct work_struct work; +}; + /* Make code in transport.c a little cleaner by moving update of optional stats into function below */ #ifdef CONFIG_CIFS_STATS2 @@ -1427,6 +1434,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, #define MID_RESPONSE_MALFORMED 0x10 #define MID_SHUTDOWN 0x20 +/* Flags */ +#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */ + /* Types of response buffer returned from SendReceive2 */ #define CIFS_NO_BUFFER 0 /* Response buffer not returned */ #define CIFS_SMALL_BUFFER 1 diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index b1104ed8f54c..b60150e5b5ce 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -717,6 +717,9 @@ CIFSSMBEcho(struct TCP_Server_Info *server) if (rc) return rc; + if (server->capabilities & CAP_UNICODE) + smb->hdr.Flags2 |= SMBFLG2_UNICODE; + /* set up echo request */ smb->hdr.Tid = 0xffff; smb->hdr.WordCount = 1; @@ -1424,6 +1427,8 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) length = discard_remaining_data(server); dequeue_mid(mid, rdata->result); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; return length; } @@ -1538,6 +1543,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return cifs_readv_discard(server, mid); dequeue_mid(mid, false); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; return length; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 5d59f25521ce..53a827c6d8b1 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -412,6 +412,9 @@ cifs_reconnect(struct TCP_Server_Info *server) } } while (server->tcpStatus == CifsNeedReconnect); + if (server->tcpStatus == CifsNeedNegotiate) + mod_delayed_work(cifsiod_wq, &server->echo, 0); + return rc; } @@ -421,18 +424,27 @@ cifs_echo_request(struct work_struct *work) int rc; struct TCP_Server_Info *server = container_of(work, struct TCP_Server_Info, echo.work); + unsigned long echo_interval; /* - * We cannot send an echo if it is disabled or until the - * NEGOTIATE_PROTOCOL request is done, which is indicated by - * server->ops->need_neg() == true. Also, no need to ping if - * we got a response recently. + * If we need to renegotiate, set echo interval to zero to + * immediately call echo service where we can renegotiate. + */ + if (server->tcpStatus == CifsNeedNegotiate) + echo_interval = 0; + else + echo_interval = SMB_ECHO_INTERVAL; + + /* + * We cannot send an echo if it is disabled. + * Also, no need to ping if we got a response recently. */ if (server->tcpStatus == CifsNeedReconnect || - server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew || + server->tcpStatus == CifsExiting || + server->tcpStatus == CifsNew || (server->ops->can_echo && !server->ops->can_echo(server)) || - time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ)) + time_before(jiffies, server->lstrp + echo_interval - HZ)) goto requeue_echo; rc = server->ops->echo ? server->ops->echo(server) : -ENOSYS; @@ -924,10 +936,19 @@ cifs_demultiplex_thread(void *p) server->lstrp = jiffies; if (mid_entry != NULL) { + if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) && + mid_entry->mid_state == MID_RESPONSE_RECEIVED && + server->ops->handle_cancelled_mid) + server->ops->handle_cancelled_mid( + mid_entry->resp_buf, + server); + if (!mid_entry->multiRsp || mid_entry->multiEnd) mid_entry->callback(mid_entry); - } else if (!server->ops->is_oplock_break || - !server->ops->is_oplock_break(buf, server)) { + } else if (server->ops->is_oplock_break && + server->ops->is_oplock_break(buf, server)) { + cifs_dbg(FYI, "Received oplock break\n"); + } else { cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n", atomic_read(&midCount)); cifs_dump_mem("Received Data is: ", buf, diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 72f270d4bd17..a0c0a49b6620 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2545,7 +2545,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, wdata->credits = credits; if (!wdata->cfile->invalidHandle || - !cifs_reopen_file(wdata->cfile, false)) + !(rc = cifs_reopen_file(wdata->cfile, false))) rc = server->ops->async_writev(wdata, cifs_uncached_writedata_release); if (rc) { @@ -2958,7 +2958,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, rdata->credits = credits; if (!rdata->cfile->invalidHandle || - !cifs_reopen_file(rdata->cfile, true)) + !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); error: if (rc) { @@ -3544,7 +3544,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, } if (!rdata->cfile->invalidHandle || - !cifs_reopen_file(rdata->cfile, true)) + !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); if (rc) { add_credits_and_wake_if(server, rdata->credits, 0); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 35cf990f87d3..a8f5b31636dc 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -272,6 +272,8 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) rc = -EOPNOTSUPP; break; case CIFS_IOC_GET_MNT_INFO: + if (pSMBFile == NULL) + break; tcon = tlink_tcon(pSMBFile->tlink); rc = smb_mnt_get_fsinfo(xid, tcon, (void __user *)arg); break; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 833e5844a2db..97d1a15873c5 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -282,6 +282,7 @@ initiate_cifs_search(const unsigned int xid, struct file *file) rc = -ENOMEM; goto error_exit; } + spin_lock_init(&cifsFile->file_info_lock); file->private_data = cifsFile; cifsFile->tlink = cifs_get_tlink(tlink); tcon = tlink_tcon(tlink); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index fc537c29044e..efd72e1fae74 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -849,8 +849,13 @@ cifs_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid, __u16 search_flags, struct cifs_search_info *srch_inf) { - return CIFSFindFirst(xid, tcon, path, cifs_sb, - &fid->netfid, search_flags, srch_inf, true); + int rc; + + rc = CIFSFindFirst(xid, tcon, path, cifs_sb, + &fid->netfid, search_flags, srch_inf, true); + if (rc) + cifs_dbg(FYI, "find first failed=%d\n", rc); + return rc; } static int @@ -1015,6 +1020,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile) return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; } +static bool +cifs_can_echo(struct TCP_Server_Info *server) +{ + if (server->tcpStatus == CifsGood) + return true; + + return false; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1049,6 +1063,7 @@ struct smb_version_operations smb1_operations = { .get_dfs_refer = CIFSGetDFSRefer, .qfs_tcon = cifs_qfs_tcon, .is_path_accessible = cifs_is_path_accessible, + .can_echo = cifs_can_echo, .query_path_info = cifs_query_path_info, .query_file_info = cifs_query_file_info, .get_srv_inum = cifs_get_srv_inum, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index e5bc85e49be7..76ccf20fbfb7 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -630,3 +630,47 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n"); return false; } + +void +smb2_cancelled_close_fid(struct work_struct *work) +{ + struct close_cancelled_open *cancelled = container_of(work, + struct close_cancelled_open, work); + + cifs_dbg(VFS, "Close unmatched open\n"); + + SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid, + cancelled->fid.volatile_fid); + cifs_put_tcon(cancelled->tcon); + kfree(cancelled); +} + +int +smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server) +{ + struct smb2_hdr *hdr = (struct smb2_hdr *)buffer; + struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer; + struct cifs_tcon *tcon; + struct close_cancelled_open *cancelled; + + if (hdr->Command != SMB2_CREATE || hdr->Status != STATUS_SUCCESS) + return 0; + + cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL); + if (!cancelled) + return -ENOMEM; + + tcon = smb2_find_smb_tcon(server, hdr->SessionId, hdr->TreeId); + if (!tcon) { + kfree(cancelled); + return -ENOENT; + } + + cancelled->fid.persistent_fid = rsp->PersistentFileId; + cancelled->fid.volatile_fid = rsp->VolatileFileId; + cancelled->tcon = tcon; + INIT_WORK(&cancelled->work, smb2_cancelled_close_fid); + queue_work(cifsiod_wq, &cancelled->work); + + return 0; +} diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index be34b4860675..1d125d3d0d89 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -909,7 +909,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); kfree(utf16_path); if (rc) { - cifs_dbg(VFS, "open dir failed\n"); + cifs_dbg(FYI, "open dir failed rc=%d\n", rc); return rc; } @@ -919,7 +919,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_query_directory(xid, tcon, fid->persistent_fid, fid->volatile_fid, 0, srch_inf); if (rc) { - cifs_dbg(VFS, "query directory failed\n"); + cifs_dbg(FYI, "query directory failed rc=%d\n", rc); SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } return rc; @@ -1511,6 +1511,7 @@ struct smb_version_operations smb20_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -1589,6 +1590,7 @@ struct smb_version_operations smb21_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -1670,6 +1672,7 @@ struct smb_version_operations smb30_operations = { .print_stats = smb2_print_stats, .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -1757,6 +1760,7 @@ struct smb_version_operations smb311_operations = { .print_stats = smb2_print_stats, .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2fa754c5fd62..f4afa3b1cc56 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -564,8 +564,12 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) } if (rsplen != sizeof(struct validate_negotiate_info_rsp)) { - cifs_dbg(VFS, "invalid size of protocol negotiate response\n"); - return -EIO; + cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n", + rsplen); + + /* relax check since Mac returns max bufsize allowed on ioctl */ + if (rsplen > CIFSMaxBufSize) + return -EIO; } /* check validate negotiate info response matches what we got earlier */ @@ -932,9 +936,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, else return -EIO; - if (tcon && tcon->bad_network_name) - return -ENOENT; - if ((tcon && tcon->seal) && ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) { cifs_dbg(VFS, "encryption requested but no server support"); @@ -952,6 +953,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, return -EINVAL; } + /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */ + if (tcon) + tcon->tid = 0; + rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req); if (rc) { kfree(unc_path); @@ -1032,8 +1037,6 @@ tcon_exit: tcon_error_exit: if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) { cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); - if (tcon) - tcon->bad_network_name = true; } goto tcon_exit; } @@ -1519,8 +1522,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, * than one credit. Windows typically sets this smaller, but for some * ioctls it may be useful to allow server to send more. No point * limiting what the server can send as long as fits in one credit + * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE + * (by default, note that it can be overridden to make max larger) + * in responses (except for read responses which can be bigger. + * We may want to bump this limit up */ - req->MaxOutputResponse = cpu_to_le32(0xFF00); /* < 64K uses 1 credit */ + req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize); if (is_fsctl) req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 0a406ae78129..adc5234486c3 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -47,6 +47,10 @@ extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst); extern struct mid_q_entry *smb2_setup_async_request( struct TCP_Server_Info *server, struct smb_rqst *rqst); +extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server, + __u64 ses_id); +extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server, + __u64 ses_id, __u32 tid); extern int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server); extern int smb3_calc_signature(struct smb_rqst *rqst, @@ -157,6 +161,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, const u64 persistent_fid, const u64 volatile_fid, const __u8 oplock_level); +extern int smb2_handle_cancelled_mid(char *buffer, + struct TCP_Server_Info *server); +void smb2_cancelled_close_fid(struct work_struct *work); extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, struct kstatfs *FSData); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index d4c5b6f109a7..69e3b322bbfe 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -115,22 +115,68 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server) } static struct cifs_ses * -smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server) +smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id) { struct cifs_ses *ses; - spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - if (ses->Suid != smb2hdr->SessionId) + if (ses->Suid != ses_id) continue; - spin_unlock(&cifs_tcp_ses_lock); return ses; } + + return NULL; +} + +struct cifs_ses * +smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id) +{ + struct cifs_ses *ses; + + spin_lock(&cifs_tcp_ses_lock); + ses = smb2_find_smb_ses_unlocked(server, ses_id); spin_unlock(&cifs_tcp_ses_lock); + return ses; +} + +static struct cifs_tcon * +smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid) +{ + struct cifs_tcon *tcon; + + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + if (tcon->tid != tid) + continue; + ++tcon->tc_count; + return tcon; + } + return NULL; } +/* + * Obtain tcon corresponding to the tid in the given + * cifs_ses + */ + +struct cifs_tcon * +smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) +{ + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + spin_lock(&cifs_tcp_ses_lock); + ses = smb2_find_smb_ses_unlocked(server, ses_id); + if (!ses) { + spin_unlock(&cifs_tcp_ses_lock); + return NULL; + } + tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); + spin_unlock(&cifs_tcp_ses_lock); + + return tcon; +} int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) @@ -143,7 +189,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base; struct cifs_ses *ses; - ses = smb2_find_smb_ses(smb2_pdu, server); + ses = smb2_find_smb_ses(server, smb2_pdu->SessionId); if (!ses) { cifs_dbg(VFS, "%s: Could not find session\n", __func__); return 0; @@ -314,7 +360,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base; struct cifs_ses *ses; - ses = smb2_find_smb_ses(smb2_pdu, server); + ses = smb2_find_smb_ses(server, smb2_pdu->SessionId); if (!ses) { cifs_dbg(VFS, "%s: Could not find session\n", __func__); return 0; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 87abe8ed074c..54af10204e83 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -786,9 +786,11 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(ses->server, midQ); if (rc != 0) { + cifs_dbg(FYI, "Cancelling wait for mid %llu\n", midQ->mid); send_cancel(ses->server, buf, midQ); spin_lock(&GlobalMid_Lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + midQ->mid_flags |= MID_WAIT_CANCELLED; midQ->callback = DeleteMidQEntry; spin_unlock(&GlobalMid_Lock); cifs_small_buf_release(buf); diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index ec5c8325b503..0525ebc3aea2 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -83,14 +83,13 @@ static int create_link(struct config_item *parent_item, ret = -ENOMEM; sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL); if (sl) { - sl->sl_target = config_item_get(item); spin_lock(&configfs_dirent_lock); if (target_sd->s_type & CONFIGFS_USET_DROPPING) { spin_unlock(&configfs_dirent_lock); - config_item_put(item); kfree(sl); return -ENOENT; } + sl->sl_target = config_item_get(item); list_add(&sl->sl_list, &target_sd->s_links); spin_unlock(&configfs_dirent_lock); ret = configfs_create_link(sl, parent_item->ci_dentry, diff --git a/fs/coredump.c b/fs/coredump.c index 5d15c4975ba1..2ce5ef429c48 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -720,7 +720,7 @@ void do_coredump(const siginfo_t *siginfo) goto close_fail; if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) goto close_fail; - if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file)) + if (do_truncate2(cprm.file->f_path.mnt, cprm.file->f_path.dentry, 0, 0, cprm.file)) goto close_fail; } @@ -810,3 +810,21 @@ int dump_align(struct coredump_params *cprm, int align) return mod ? dump_skip(cprm, align - mod) : 1; } EXPORT_SYMBOL(dump_align); + +/* + * Ensures that file size is big enough to contain the current file + * postion. This prevents gdb from complaining about a truncated file + * if the last "write" to the file was dump_skip. + */ +void dump_truncate(struct coredump_params *cprm) +{ + struct file *file = cprm->file; + loff_t offset; + + if (file->f_op->llseek && file->f_op->llseek != no_llseek) { + offset = file->f_op->llseek(file, 0, SEEK_CUR); + if (i_size_read(file->f_mapping->host) < offset) + do_truncate(file->f_path.dentry, offset, 0, file); + } +} +EXPORT_SYMBOL(dump_truncate); diff --git a/fs/dcache.c b/fs/dcache.c index 7b8feb6d60c8..5bf7b4a188e9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,6 +269,33 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } +void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + if (unlikely(dname_external(dentry))) { + struct external_name *p = external_name(dentry); + atomic_inc(&p->u.count); + spin_unlock(&dentry->d_lock); + name->name = p->name; + } else { + memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN); + spin_unlock(&dentry->d_lock); + name->name = name->inline_name; + } +} +EXPORT_SYMBOL(take_dentry_name_snapshot); + +void release_dentry_name_snapshot(struct name_snapshot *name) +{ + if (unlikely(name->name != name->inline_name)) { + struct external_name *p; + p = container_of(name->name, struct external_name, name[0]); + if (unlikely(atomic_dec_and_test(&p->u.count))) + kfree_rcu(p, u.head); + } +} +EXPORT_SYMBOL(release_dentry_name_snapshot); + static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -1128,11 +1155,12 @@ void shrink_dcache_sb(struct super_block *sb) LIST_HEAD(dispose); freed = list_lru_walk(&sb->s_dentry_lru, - dentry_lru_isolate_shrink, &dispose, UINT_MAX); + dentry_lru_isolate_shrink, &dispose, 1024); this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); - } while (freed > 0); + cond_resched(); + } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 0f5d05bf2131..e49ba072bd64 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -669,7 +669,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, { int error; struct dentry *dentry = NULL, *trap; - const char *old_name; + struct name_snapshot old_name; trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ @@ -684,19 +684,19 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) goto exit; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir), dentry); if (error) { - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); goto exit; } d_move(old_dentry, dentry); - fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name, + fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name, d_is_dir(old_dentry), NULL, old_dentry); - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); unlock_rename(new_dir, old_dir); dput(dentry); return old_dentry; diff --git a/fs/direct-io.c b/fs/direct-io.c index 01171d8a6ee9..c772fdf36cd9 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -575,7 +575,7 @@ static int dio_set_defer_completion(struct dio *dio) /* * Call into the fs to map some more disk blocks. We record the current number * of available blocks at sdio->blocks_available. These are in units of the - * fs blocksize, (1 << inode->i_blkbits). + * fs blocksize, i_blocksize(inode). * * The fs is allowed to map lots of blocks at once. If it wants to do that, * it uses the passed inode-relative block number as the file offset, as usual. diff --git a/fs/exec.c b/fs/exec.c index 3a6de10d3891..dd3a59420506 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -206,7 +206,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, if (write) { unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; - struct rlimit *rlim; + unsigned long ptr_size, limit; + + /* + * Since the stack will hold pointers to the strings, we + * must account for them as well. + * + * The size calculation is the entire vma while each arg page is + * built, so each time we get here it's calculating how far it + * is currently (rather than each call being just the newly + * added size from the arg page). As a result, we need to + * always add the entire size of the pointers, so that on the + * last call to get_arg_page() we'll actually have the entire + * correct size. + */ + ptr_size = (bprm->argc + bprm->envc) * sizeof(void *); + if (ptr_size > ULONG_MAX - size) + goto fail; + size += ptr_size; acct_arg_size(bprm, size / PAGE_SIZE); @@ -218,20 +235,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, return page; /* - * Limit to 1/4-th the stack size for the argv+env strings. + * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM + * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ - rlim = current->signal->rlim; - if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) { - put_page(page); - return NULL; - } + limit = _STK_LIM / 4 * 3; + limit = min(limit, rlimit(RLIMIT_STACK) / 4); + if (size > limit) + goto fail; } return page; + +fail: + put_page(page); + return NULL; } static void put_arg_page(struct page *page) @@ -1132,7 +1153,7 @@ EXPORT_SYMBOL(flush_old_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); - if (inode_permission(inode, MAY_READ) < 0) { + if (inode_permission2(file->f_path.mnt, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 4c69c94cafd8..f98ce7e60a0f 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -61,6 +61,8 @@ struct ext2_block_alloc_info { #define rsv_start rsv_window._rsv_start #define rsv_end rsv_window._rsv_end +struct mb2_cache; + /* * second extended-fs super-block data in memory */ @@ -111,6 +113,7 @@ struct ext2_sb_info { * of the mount options. */ spinlock_t s_lock; + struct mb2_cache *s_mb_cache; }; static inline spinlock_t * diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 748d35afc902..111a31761ffa 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -131,7 +131,10 @@ static void ext2_put_super (struct super_block * sb) dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); - ext2_xattr_put_super(sb); + if (sbi->s_mb_cache) { + ext2_xattr_destroy_cache(sbi->s_mb_cache); + sbi->s_mb_cache = NULL; + } if (!(sb->s_flags & MS_RDONLY)) { struct ext2_super_block *es = sbi->s_es; @@ -1104,6 +1107,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) ext2_msg(sb, KERN_ERR, "error: insufficient memory"); goto failed_mount3; } + +#ifdef CONFIG_EXT2_FS_XATTR + sbi->s_mb_cache = ext2_xattr_create_cache(); + if (!sbi->s_mb_cache) { + ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache"); + goto failed_mount3; + } +#endif /* * set up enough so that it can read an inode */ @@ -1149,6 +1160,8 @@ cantfind_ext2: sb->s_id); goto failed_mount; failed_mount3: + if (sbi->s_mb_cache) + ext2_xattr_destroy_cache(sbi->s_mb_cache); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -1555,20 +1568,17 @@ MODULE_ALIAS_FS("ext2"); static int __init init_ext2_fs(void) { - int err = init_ext2_xattr(); - if (err) - return err; + int err; + err = init_inodecache(); if (err) - goto out1; + return err; err = register_filesystem(&ext2_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); -out1: - exit_ext2_xattr(); return err; } @@ -1576,7 +1586,6 @@ static void __exit exit_ext2_fs(void) { unregister_filesystem(&ext2_fs_type); destroy_inodecache(); - exit_ext2_xattr(); } MODULE_AUTHOR("Remy Card and others"); diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index fa70848afa8f..24736c8b3d51 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -56,7 +56,7 @@ #include <linux/buffer_head.h> #include <linux/init.h> #include <linux/slab.h> -#include <linux/mbcache.h> +#include <linux/mbcache2.h> #include <linux/quotaops.h> #include <linux/rwsem.h> #include <linux/security.h> @@ -92,14 +92,12 @@ static int ext2_xattr_set2(struct inode *, struct buffer_head *, struct ext2_xattr_header *); -static int ext2_xattr_cache_insert(struct buffer_head *); +static int ext2_xattr_cache_insert(struct mb2_cache *, struct buffer_head *); static struct buffer_head *ext2_xattr_cache_find(struct inode *, struct ext2_xattr_header *); static void ext2_xattr_rehash(struct ext2_xattr_header *, struct ext2_xattr_entry *); -static struct mb_cache *ext2_xattr_cache; - static const struct xattr_handler *ext2_xattr_handler_map[] = { [EXT2_XATTR_INDEX_USER] = &ext2_xattr_user_handler, #ifdef CONFIG_EXT2_FS_POSIX_ACL @@ -154,6 +152,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name, size_t name_len, size; char *end; int error; + struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -198,7 +197,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_get", goto found; entry = next; } - if (ext2_xattr_cache_insert(bh)) + if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) ea_idebug(inode, "cache insert failed"); error = -ENODATA; goto cleanup; @@ -211,7 +210,7 @@ found: le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize) goto bad_block; - if (ext2_xattr_cache_insert(bh)) + if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) ea_idebug(inode, "cache insert failed"); if (buffer) { error = -ERANGE; @@ -249,6 +248,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) char *end; size_t rest = buffer_size; int error; + struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -283,7 +283,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", goto bad_block; entry = next; } - if (ext2_xattr_cache_insert(bh)) + if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) ea_idebug(inode, "cache insert failed"); /* list the attribute names */ @@ -480,22 +480,23 @@ bad_block: ext2_error(sb, "ext2_xattr_set", /* Here we know that we can set the new attribute. */ if (header) { - struct mb_cache_entry *ce; - /* assert(header == HDR(bh)); */ - ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, - bh->b_blocknr); lock_buffer(bh); if (header->h_refcount == cpu_to_le32(1)) { + __u32 hash = le32_to_cpu(header->h_hash); + ea_bdebug(bh, "modifying in-place"); - if (ce) - mb_cache_entry_free(ce); + /* + * This must happen under buffer lock for + * ext2_xattr_set2() to reliably detect modified block + */ + mb2_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache, + hash, bh->b_blocknr); + /* keep the buffer locked while modifying it. */ } else { int offset; - if (ce) - mb_cache_entry_release(ce); unlock_buffer(bh); ea_bdebug(bh, "cloning"); header = kmalloc(bh->b_size, GFP_KERNEL); @@ -623,6 +624,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; int error; + struct mb2_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache; if (header) { new_bh = ext2_xattr_cache_find(inode, header); @@ -650,7 +652,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, don't need to change the reference count. */ new_bh = old_bh; get_bh(new_bh); - ext2_xattr_cache_insert(new_bh); + ext2_xattr_cache_insert(ext2_mb_cache, new_bh); } else { /* We need to allocate a new block */ ext2_fsblk_t goal = ext2_group_first_block_no(sb, @@ -671,7 +673,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, memcpy(new_bh->b_data, header, new_bh->b_size); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); - ext2_xattr_cache_insert(new_bh); + ext2_xattr_cache_insert(ext2_mb_cache, new_bh); ext2_xattr_update_super_block(sb); } @@ -704,19 +706,21 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, error = 0; if (old_bh && old_bh != new_bh) { - struct mb_cache_entry *ce; - /* * If there was an old block and we are no longer using it, * release the old block. */ - ce = mb_cache_entry_get(ext2_xattr_cache, old_bh->b_bdev, - old_bh->b_blocknr); lock_buffer(old_bh); if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) { + __u32 hash = le32_to_cpu(HDR(old_bh)->h_hash); + + /* + * This must happen under buffer lock for + * ext2_xattr_set2() to reliably detect freed block + */ + mb2_cache_entry_delete_block(ext2_mb_cache, + hash, old_bh->b_blocknr); /* Free the old block. */ - if (ce) - mb_cache_entry_free(ce); ea_bdebug(old_bh, "freeing"); ext2_free_blocks(inode, old_bh->b_blocknr, 1); mark_inode_dirty(inode); @@ -727,8 +731,6 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, } else { /* Decrement the refcount only. */ le32_add_cpu(&HDR(old_bh)->h_refcount, -1); - if (ce) - mb_cache_entry_release(ce); dquot_free_block_nodirty(inode, 1); mark_inode_dirty(inode); mark_buffer_dirty(old_bh); @@ -754,7 +756,6 @@ void ext2_xattr_delete_inode(struct inode *inode) { struct buffer_head *bh = NULL; - struct mb_cache_entry *ce; down_write(&EXT2_I(inode)->xattr_sem); if (!EXT2_I(inode)->i_file_acl) @@ -774,19 +775,22 @@ ext2_xattr_delete_inode(struct inode *inode) EXT2_I(inode)->i_file_acl); goto cleanup; } - ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, bh->b_blocknr); lock_buffer(bh); if (HDR(bh)->h_refcount == cpu_to_le32(1)) { - if (ce) - mb_cache_entry_free(ce); + __u32 hash = le32_to_cpu(HDR(bh)->h_hash); + + /* + * This must happen under buffer lock for ext2_xattr_set2() to + * reliably detect freed block + */ + mb2_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache, + hash, bh->b_blocknr); ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1); get_bh(bh); bforget(bh); unlock_buffer(bh); } else { le32_add_cpu(&HDR(bh)->h_refcount, -1); - if (ce) - mb_cache_entry_release(ce); ea_bdebug(bh, "refcount now=%d", le32_to_cpu(HDR(bh)->h_refcount)); unlock_buffer(bh); @@ -803,18 +807,6 @@ cleanup: } /* - * ext2_xattr_put_super() - * - * This is called when a file system is unmounted. - */ -void -ext2_xattr_put_super(struct super_block *sb) -{ - mb_cache_shrink(sb->s_bdev); -} - - -/* * ext2_xattr_cache_insert() * * Create a new entry in the extended attribute cache, and insert @@ -823,28 +815,20 @@ ext2_xattr_put_super(struct super_block *sb) * Returns 0, or a negative error number on failure. */ static int -ext2_xattr_cache_insert(struct buffer_head *bh) +ext2_xattr_cache_insert(struct mb2_cache *cache, struct buffer_head *bh) { __u32 hash = le32_to_cpu(HDR(bh)->h_hash); - struct mb_cache_entry *ce; int error; - ce = mb_cache_entry_alloc(ext2_xattr_cache, GFP_NOFS); - if (!ce) - return -ENOMEM; - error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash); + error = mb2_cache_entry_create(cache, GFP_NOFS, hash, bh->b_blocknr); if (error) { - mb_cache_entry_free(ce); if (error == -EBUSY) { ea_bdebug(bh, "already in cache (%d cache entries)", atomic_read(&ext2_xattr_cache->c_entry_count)); error = 0; } - } else { - ea_bdebug(bh, "inserting [%x] (%d cache entries)", (int)hash, - atomic_read(&ext2_xattr_cache->c_entry_count)); - mb_cache_entry_release(ce); - } + } else + ea_bdebug(bh, "inserting [%x]", (int)hash); return error; } @@ -900,23 +884,17 @@ static struct buffer_head * ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header) { __u32 hash = le32_to_cpu(header->h_hash); - struct mb_cache_entry *ce; + struct mb2_cache_entry *ce; + struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); again: - ce = mb_cache_entry_find_first(ext2_xattr_cache, inode->i_sb->s_bdev, - hash); + ce = mb2_cache_entry_find_first(ext2_mb_cache, hash); while (ce) { struct buffer_head *bh; - if (IS_ERR(ce)) { - if (PTR_ERR(ce) == -EAGAIN) - goto again; - break; - } - bh = sb_bread(inode->i_sb, ce->e_block); if (!bh) { ext2_error(inode->i_sb, "ext2_xattr_cache_find", @@ -924,7 +902,21 @@ again: inode->i_ino, (unsigned long) ce->e_block); } else { lock_buffer(bh); - if (le32_to_cpu(HDR(bh)->h_refcount) > + /* + * We have to be careful about races with freeing or + * rehashing of xattr block. Once we hold buffer lock + * xattr block's state is stable so we can check + * whether the block got freed / rehashed or not. + * Since we unhash mbcache entry under buffer lock when + * freeing / rehashing xattr block, checking whether + * entry is still hashed is reliable. + */ + if (hlist_bl_unhashed(&ce->e_hash_list)) { + mb2_cache_entry_put(ext2_mb_cache, ce); + unlock_buffer(bh); + brelse(bh); + goto again; + } else if (le32_to_cpu(HDR(bh)->h_refcount) > EXT2_XATTR_REFCOUNT_MAX) { ea_idebug(inode, "block %ld refcount %d>%d", (unsigned long) ce->e_block, @@ -933,13 +925,14 @@ again: } else if (!ext2_xattr_cmp(header, HDR(bh))) { ea_bdebug(bh, "b_count=%d", atomic_read(&(bh->b_count))); - mb_cache_entry_release(ce); + mb2_cache_entry_touch(ext2_mb_cache, ce); + mb2_cache_entry_put(ext2_mb_cache, ce); return bh; } unlock_buffer(bh); brelse(bh); } - ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash); + ce = mb2_cache_entry_find_next(ext2_mb_cache, ce); } return NULL; } @@ -1012,17 +1005,15 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *header, #undef BLOCK_HASH_SHIFT -int __init -init_ext2_xattr(void) +#define HASH_BUCKET_BITS 10 + +struct mb2_cache *ext2_xattr_create_cache(void) { - ext2_xattr_cache = mb_cache_create("ext2_xattr", 6); - if (!ext2_xattr_cache) - return -ENOMEM; - return 0; + return mb2_cache_create(HASH_BUCKET_BITS); } -void -exit_ext2_xattr(void) +void ext2_xattr_destroy_cache(struct mb2_cache *cache) { - mb_cache_destroy(ext2_xattr_cache); + if (cache) + mb2_cache_destroy(cache); } diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h index 60edf298644e..6ea38aa9563a 100644 --- a/fs/ext2/xattr.h +++ b/fs/ext2/xattr.h @@ -53,6 +53,8 @@ struct ext2_xattr_entry { #define EXT2_XATTR_SIZE(size) \ (((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND) +struct mb2_cache; + # ifdef CONFIG_EXT2_FS_XATTR extern const struct xattr_handler ext2_xattr_user_handler; @@ -65,10 +67,9 @@ extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t); extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int); extern void ext2_xattr_delete_inode(struct inode *); -extern void ext2_xattr_put_super(struct super_block *); -extern int init_ext2_xattr(void); -extern void exit_ext2_xattr(void); +extern struct mb2_cache *ext2_xattr_create_cache(void); +extern void ext2_xattr_destroy_cache(struct mb2_cache *cache); extern const struct xattr_handler *ext2_xattr_handlers[]; @@ -93,19 +94,7 @@ ext2_xattr_delete_inode(struct inode *inode) { } -static inline void -ext2_xattr_put_super(struct super_block *sb) -{ -} - -static inline int -init_ext2_xattr(void) -{ - return 0; -} - -static inline void -exit_ext2_xattr(void) +static inline void ext2_xattr_destroy_cache(struct mb2_cache *cache) { } diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index b46e9fc64196..3c8293215603 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -106,6 +106,7 @@ config EXT4_ENCRYPTION select CRYPTO_ECB select CRYPTO_XTS select CRYPTO_CTS + select CRYPTO_HEH select CRYPTO_CTR select CRYPTO_SHA256 select KEYS diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index 1a0835073663..f240cef8b326 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -34,6 +34,7 @@ #include <linux/random.h> #include <linux/scatterlist.h> #include <linux/spinlock_types.h> +#include <linux/namei.h> #include "ext4_extents.h" #include "xattr.h" @@ -93,7 +94,8 @@ void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx) * Return: An allocated and initialized encryption context on success; error * value or NULL otherwise. */ -struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode) +struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode, + gfp_t gfp_flags) { struct ext4_crypto_ctx *ctx = NULL; int res = 0; @@ -120,7 +122,7 @@ struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode) list_del(&ctx->free_list); spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags); if (!ctx) { - ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS); + ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, gfp_flags); if (!ctx) { res = -ENOMEM; goto out; @@ -257,7 +259,8 @@ static int ext4_page_crypto(struct inode *inode, ext4_direction_t rw, pgoff_t index, struct page *src_page, - struct page *dest_page) + struct page *dest_page, + gfp_t gfp_flags) { u8 xts_tweak[EXT4_XTS_TWEAK_SIZE]; @@ -268,7 +271,7 @@ static int ext4_page_crypto(struct inode *inode, struct crypto_ablkcipher *tfm = ci->ci_ctfm; int res = 0; - req = ablkcipher_request_alloc(tfm, GFP_NOFS); + req = ablkcipher_request_alloc(tfm, gfp_flags); if (!req) { printk_ratelimited(KERN_ERR "%s: crypto_request_alloc() failed\n", @@ -309,9 +312,10 @@ static int ext4_page_crypto(struct inode *inode, return 0; } -static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx) +static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx, + gfp_t gfp_flags) { - ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, GFP_NOWAIT); + ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, gfp_flags); if (ctx->w.bounce_page == NULL) return ERR_PTR(-ENOMEM); ctx->flags |= EXT4_WRITE_PATH_FL; @@ -334,7 +338,8 @@ static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx) * error value or NULL. */ struct page *ext4_encrypt(struct inode *inode, - struct page *plaintext_page) + struct page *plaintext_page, + gfp_t gfp_flags) { struct ext4_crypto_ctx *ctx; struct page *ciphertext_page = NULL; @@ -342,17 +347,17 @@ struct page *ext4_encrypt(struct inode *inode, BUG_ON(!PageLocked(plaintext_page)); - ctx = ext4_get_crypto_ctx(inode); + ctx = ext4_get_crypto_ctx(inode, gfp_flags); if (IS_ERR(ctx)) return (struct page *) ctx; /* The encryption operation will require a bounce page. */ - ciphertext_page = alloc_bounce_page(ctx); + ciphertext_page = alloc_bounce_page(ctx, gfp_flags); if (IS_ERR(ciphertext_page)) goto errout; ctx->w.control_page = plaintext_page; err = ext4_page_crypto(inode, EXT4_ENCRYPT, plaintext_page->index, - plaintext_page, ciphertext_page); + plaintext_page, ciphertext_page, gfp_flags); if (err) { ciphertext_page = ERR_PTR(err); errout: @@ -380,8 +385,8 @@ int ext4_decrypt(struct page *page) { BUG_ON(!PageLocked(page)); - return ext4_page_crypto(page->mapping->host, - EXT4_DECRYPT, page->index, page, page); + return ext4_page_crypto(page->mapping->host, EXT4_DECRYPT, + page->index, page, page, GFP_NOFS); } int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) @@ -402,11 +407,11 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE); - ctx = ext4_get_crypto_ctx(inode); + ctx = ext4_get_crypto_ctx(inode, GFP_NOFS); if (IS_ERR(ctx)) return PTR_ERR(ctx); - ciphertext_page = alloc_bounce_page(ctx); + ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT); if (IS_ERR(ciphertext_page)) { err = PTR_ERR(ciphertext_page); goto errout; @@ -414,11 +419,12 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) while (len--) { err = ext4_page_crypto(inode, EXT4_ENCRYPT, lblk, - ZERO_PAGE(0), ciphertext_page); + ZERO_PAGE(0), ciphertext_page, + GFP_NOFS); if (err) goto errout; - bio = bio_alloc(GFP_KERNEL, 1); + bio = bio_alloc(GFP_NOWAIT, 1); if (!bio) { err = -ENOMEM; goto errout; @@ -469,3 +475,61 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size) return size; return 0; } + +/* + * Validate dentries for encrypted directories to make sure we aren't + * potentially caching stale data after a key has been added or + * removed. + */ +static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct dentry *dir; + struct ext4_crypt_info *ci; + int dir_has_key, cached_with_key; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + dir = dget_parent(dentry); + if (!ext4_encrypted_inode(d_inode(dir))) { + dput(dir); + return 0; + } + ci = EXT4_I(d_inode(dir))->i_crypt_info; + + /* this should eventually be an flag in d_flags */ + cached_with_key = dentry->d_fsdata != NULL; + dir_has_key = (ci != NULL); + dput(dir); + + /* + * If the dentry was cached without the key, and it is a + * negative dentry, it might be a valid name. We can't check + * if the key has since been made available due to locking + * reasons, so we fail the validation so ext4_lookup() can do + * this check. + * + * We also fail the validation if the dentry was created with + * the key present, but we no longer have the key, or vice versa. + */ + if ((!cached_with_key && d_is_negative(dentry)) || + (!cached_with_key && dir_has_key) || + (cached_with_key && !dir_has_key)) { +#if 0 /* Revalidation debug */ + char buf[80]; + char *cp = simple_dname(dentry, buf, sizeof(buf)); + + if (IS_ERR(cp)) + cp = (char *) "???"; + pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata, + cached_with_key, d_is_negative(dentry), + dir_has_key); +#endif + return 0; + } + return 1; +} + +const struct dentry_operations ext4_encrypted_d_ops = { + .d_revalidate = ext4_d_revalidate, +}; diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c index 2fbef8a14760..026716bdbbfc 100644 --- a/fs/ext4/crypto_fname.c +++ b/fs/ext4/crypto_fname.c @@ -44,7 +44,8 @@ static void ext4_dir_crypt_complete(struct crypto_async_request *req, int res) bool ext4_valid_filenames_enc_mode(uint32_t mode) { - return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS); + return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS || + mode == EXT4_ENCRYPTION_MODE_AES_256_HEH); } static unsigned max_name_len(struct inode *inode) @@ -343,7 +344,7 @@ int _ext4_fname_disk_to_usr(struct inode *inode, memcpy(buf+4, &hinfo->minor_hash, 4); } else memset(buf, 0, 8); - memcpy(buf + 8, iname->name + iname->len - 16, 16); + memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16); oname->name[0] = '_'; ret = digest_encode(buf, 24, oname->name+1); oname->len = ret + 1; diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c index 9a16d1e75a49..22096e31a720 100644 --- a/fs/ext4/crypto_key.c +++ b/fs/ext4/crypto_key.c @@ -29,16 +29,16 @@ static void derive_crypt_complete(struct crypto_async_request *req, int rc) } /** - * ext4_derive_key_aes() - Derive a key using AES-128-ECB + * ext4_derive_key_v1() - Derive a key using AES-128-ECB * @deriving_key: Encryption key used for derivation. * @source_key: Source key to which to apply derivation. * @derived_key: Derived key. * - * Return: Zero on success; non-zero otherwise. + * Return: 0 on success, -errno on failure */ -static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE], - char source_key[EXT4_AES_256_XTS_KEY_SIZE], - char derived_key[EXT4_AES_256_XTS_KEY_SIZE]) +static int ext4_derive_key_v1(const char deriving_key[EXT4_AES_128_ECB_KEY_SIZE], + const char source_key[EXT4_AES_256_XTS_KEY_SIZE], + char derived_key[EXT4_AES_256_XTS_KEY_SIZE]) { int res = 0; struct ablkcipher_request *req = NULL; @@ -83,13 +83,96 @@ out: return res; } +/** + * ext4_derive_key_v2() - Derive a key non-reversibly + * @nonce: the nonce associated with the file + * @master_key: the master key referenced by the file + * @derived_key: (output) the resulting derived key + * + * This function computes the following: + * derived_key[0:127] = AES-256-ENCRYPT(master_key[0:255], nonce) + * derived_key[128:255] = AES-256-ENCRYPT(master_key[0:255], nonce ^ 0x01) + * derived_key[256:383] = AES-256-ENCRYPT(master_key[256:511], nonce) + * derived_key[384:511] = AES-256-ENCRYPT(master_key[256:511], nonce ^ 0x01) + * + * 'nonce ^ 0x01' denotes flipping the low order bit of the last byte. + * + * Unlike the v1 algorithm, the v2 algorithm is "non-reversible", meaning that + * compromising a derived key does not also compromise the master key. + * + * Return: 0 on success, -errno on failure + */ +static int ext4_derive_key_v2(const char nonce[EXT4_KEY_DERIVATION_NONCE_SIZE], + const char master_key[EXT4_MAX_KEY_SIZE], + char derived_key[EXT4_MAX_KEY_SIZE]) +{ + const int noncelen = EXT4_KEY_DERIVATION_NONCE_SIZE; + struct crypto_cipher *tfm; + int err; + int i; + + /* + * Since we only use each transform for a small number of encryptions, + * requesting just "aes" turns out to be significantly faster than + * "ecb(aes)", by about a factor of two. + */ + tfm = crypto_alloc_cipher("aes", 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + BUILD_BUG_ON(4 * EXT4_KEY_DERIVATION_NONCE_SIZE != EXT4_MAX_KEY_SIZE); + BUILD_BUG_ON(2 * EXT4_AES_256_ECB_KEY_SIZE != EXT4_MAX_KEY_SIZE); + for (i = 0; i < 2; i++) { + memcpy(derived_key, nonce, noncelen); + memcpy(derived_key + noncelen, nonce, noncelen); + derived_key[2 * noncelen - 1] ^= 0x01; + err = crypto_cipher_setkey(tfm, master_key, + EXT4_AES_256_ECB_KEY_SIZE); + if (err) + break; + crypto_cipher_encrypt_one(tfm, derived_key, derived_key); + crypto_cipher_encrypt_one(tfm, derived_key + noncelen, + derived_key + noncelen); + master_key += EXT4_AES_256_ECB_KEY_SIZE; + derived_key += 2 * noncelen; + } + crypto_free_cipher(tfm); + return err; +} + +/** + * ext4_derive_key() - Derive a per-file key from a nonce and master key + * @ctx: the encryption context associated with the file + * @master_key: the master key referenced by the file + * @derived_key: (output) the resulting derived key + * + * Return: 0 on success, -errno on failure + */ +static int ext4_derive_key(const struct ext4_encryption_context *ctx, + const char master_key[EXT4_MAX_KEY_SIZE], + char derived_key[EXT4_MAX_KEY_SIZE]) +{ + BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE != EXT4_KEY_DERIVATION_NONCE_SIZE); + BUILD_BUG_ON(EXT4_AES_256_XTS_KEY_SIZE != EXT4_MAX_KEY_SIZE); + + /* + * Although the key derivation algorithm is logically independent of the + * choice of encryption modes, in this kernel it is bundled with HEH + * encryption of filenames, which is another crypto improvement that + * requires an on-disk format change and requires userspace to specify + * different encryption policies. + */ + if (ctx->filenames_encryption_mode == EXT4_ENCRYPTION_MODE_AES_256_HEH) + return ext4_derive_key_v2(ctx->nonce, master_key, derived_key); + else + return ext4_derive_key_v1(ctx->nonce, master_key, derived_key); +} + void ext4_free_crypt_info(struct ext4_crypt_info *ci) { if (!ci) return; - if (ci->ci_keyring_key) - key_put(ci->ci_keyring_key); crypto_free_ablkcipher(ci->ci_ctfm); kmem_cache_free(ext4_crypt_info_cachep, ci); } @@ -111,7 +194,7 @@ void ext4_free_encryption_info(struct inode *inode, ext4_free_crypt_info(ci); } -int _ext4_get_encryption_info(struct inode *inode) +int ext4_get_encryption_info(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_crypt_info *crypt_info; @@ -128,22 +211,15 @@ int _ext4_get_encryption_info(struct inode *inode) char mode; int res; + if (ei->i_crypt_info) + return 0; + if (!ext4_read_workqueue) { res = ext4_init_crypto(); if (res) return res; } -retry: - crypt_info = ACCESS_ONCE(ei->i_crypt_info); - if (crypt_info) { - if (!crypt_info->ci_keyring_key || - key_validate(crypt_info->ci_keyring_key) == 0) - return 0; - ext4_free_encryption_info(inode, crypt_info); - goto retry; - } - res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx, sizeof(ctx)); @@ -166,7 +242,6 @@ retry: crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; crypt_info->ci_ctfm = NULL; - crypt_info->ci_keyring_key = NULL; memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, sizeof(crypt_info->ci_master_key)); if (S_ISREG(inode->i_mode)) @@ -182,6 +257,9 @@ retry: case EXT4_ENCRYPTION_MODE_AES_256_CTS: cipher_str = "cts(cbc(aes))"; break; + case EXT4_ENCRYPTION_MODE_AES_256_HEH: + cipher_str = "heh(aes)"; + break; default: printk_once(KERN_WARNING "ext4: unsupported key mode %d (ino %u)\n", @@ -206,7 +284,6 @@ retry: keyring_key = NULL; goto out; } - crypt_info->ci_keyring_key = keyring_key; if (keyring_key->type != &key_type_logon) { printk_once(KERN_WARNING "ext4: key type must be logon\n"); @@ -231,8 +308,7 @@ retry: up_read(&keyring_key->sem); goto out; } - res = ext4_derive_key_aes(ctx.nonce, master_key->raw, - raw_key); + res = ext4_derive_key(&ctx, master_key->raw, raw_key); up_read(&keyring_key->sem); if (res) goto out; @@ -253,16 +329,13 @@ got_key: ext4_encryption_key_size(mode)); if (res) goto out; - memzero_explicit(raw_key, sizeof(raw_key)); - if (cmpxchg(&ei->i_crypt_info, NULL, crypt_info) != NULL) { - ext4_free_crypt_info(crypt_info); - goto retry; - } - return 0; + if (cmpxchg(&ei->i_crypt_info, NULL, crypt_info) == NULL) + crypt_info = NULL; out: if (res == -ENOKEY) res = 0; + key_put(keyring_key); ext4_free_crypt_info(crypt_info); memzero_explicit(raw_key, sizeof(raw_key)); return res; diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c index 8a9feb341f31..e4f4fc4e56ab 100644 --- a/fs/ext4/crypto_policy.c +++ b/fs/ext4/crypto_policy.c @@ -148,20 +148,38 @@ int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy) int ext4_is_child_context_consistent_with_parent(struct inode *parent, struct inode *child) { - struct ext4_crypt_info *parent_ci, *child_ci; + const struct ext4_crypt_info *parent_ci, *child_ci; + struct ext4_encryption_context parent_ctx, child_ctx; int res; - if ((parent == NULL) || (child == NULL)) { - pr_err("parent %p child %p\n", parent, child); - WARN_ON(1); /* Should never happen */ - return 0; - } - /* no restrictions if the parent directory is not encrypted */ + /* No restrictions on file types which are never encrypted */ + if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) && + !S_ISLNK(child->i_mode)) + return 1; + + /* No restrictions if the parent directory is unencrypted */ if (!ext4_encrypted_inode(parent)) return 1; - /* if the child directory is not encrypted, this is always a problem */ + + /* Encrypted directories must not contain unencrypted files */ if (!ext4_encrypted_inode(child)) return 0; + + /* + * Both parent and child are encrypted, so verify they use the same + * encryption policy. Compare the fscrypt_info structs if the keys are + * available, otherwise retrieve and compare the fscrypt_contexts. + * + * Note that the fscrypt_context retrieval will be required frequently + * when accessing an encrypted directory tree without the key. + * Performance-wise this is not a big deal because we already don't + * really optimize for file access without the key (to the extent that + * such access is even possible), given that any attempted access + * already causes a fscrypt_context retrieval and keyring search. + * + * In any case, if an unexpected error occurs, fall back to "forbidden". + */ + res = ext4_get_encryption_info(parent); if (res) return 0; @@ -170,17 +188,35 @@ int ext4_is_child_context_consistent_with_parent(struct inode *parent, return 0; parent_ci = EXT4_I(parent)->i_crypt_info; child_ci = EXT4_I(child)->i_crypt_info; - if (!parent_ci && !child_ci) - return 1; - if (!parent_ci || !child_ci) + if (parent_ci && child_ci) { + return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key, + EXT4_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ci->ci_data_mode == child_ci->ci_data_mode) && + (parent_ci->ci_filename_mode == + child_ci->ci_filename_mode) && + (parent_ci->ci_flags == child_ci->ci_flags); + } + + res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &parent_ctx, sizeof(parent_ctx)); + if (res != sizeof(parent_ctx)) + return 0; + + res = ext4_xattr_get(child, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + &child_ctx, sizeof(child_ctx)); + if (res != sizeof(child_ctx)) return 0; - return (memcmp(parent_ci->ci_master_key, - child_ci->ci_master_key, - EXT4_KEY_DESCRIPTOR_SIZE) == 0 && - (parent_ci->ci_data_mode == child_ci->ci_data_mode) && - (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) && - (parent_ci->ci_flags == child_ci->ci_flags)); + return memcmp(parent_ctx.master_key_descriptor, + child_ctx.master_key_descriptor, + EXT4_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ctx.contents_encryption_mode == + child_ctx.contents_encryption_mode) && + (parent_ctx.filenames_encryption_mode == + child_ctx.filenames_encryption_mode) && + (parent_ctx.flags == child_ctx.flags); } /** diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 1d1bca74f844..6d17f31a31d7 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) int dir_has_error = 0; struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + if (ext4_encrypted_inode(inode)) { + err = ext4_get_encryption_info(inode); + if (err && err != -ENOKEY) + return err; + } + if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); if (err != ERR_BAD_DX_DIR) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9f31991a5e05..6edacb849e48 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -589,6 +589,7 @@ enum { #define EXT4_ENCRYPTION_MODE_AES_256_GCM 2 #define EXT4_ENCRYPTION_MODE_AES_256_CBC 3 #define EXT4_ENCRYPTION_MODE_AES_256_CTS 4 +#define EXT4_ENCRYPTION_MODE_AES_256_HEH 126 #include "ext4_crypto.h" @@ -1441,7 +1442,7 @@ struct ext4_sb_info { struct list_head s_es_list; /* List of inodes with reclaimable extents */ long s_es_nr_inode; struct ext4_es_stats s_es_stats; - struct mb_cache *s_mb_cache; + struct mb2_cache *s_mb_cache; spinlock_t s_es_lock ____cacheline_aligned_in_smp; /* Ratelimit ext4 messages. */ @@ -2261,13 +2262,16 @@ extern struct kmem_cache *ext4_crypt_info_cachep; bool ext4_valid_contents_enc_mode(uint32_t mode); uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size); extern struct workqueue_struct *ext4_read_workqueue; -struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode); +struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode, + gfp_t gfp_flags); void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx); void ext4_restore_control_page(struct page *data_page); struct page *ext4_encrypt(struct inode *inode, - struct page *plaintext_page); + struct page *plaintext_page, + gfp_t gfp_flags); int ext4_decrypt(struct page *page); int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex); +extern const struct dentry_operations ext4_encrypted_d_ops; #ifdef CONFIG_EXT4_FS_ENCRYPTION int ext4_init_crypto(void); @@ -2330,23 +2334,11 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } /* crypto_key.c */ void ext4_free_crypt_info(struct ext4_crypt_info *ci); void ext4_free_encryption_info(struct inode *inode, struct ext4_crypt_info *ci); -int _ext4_get_encryption_info(struct inode *inode); #ifdef CONFIG_EXT4_FS_ENCRYPTION int ext4_has_encryption_key(struct inode *inode); -static inline int ext4_get_encryption_info(struct inode *inode) -{ - struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info; - - if (!ci || - (ci->ci_keyring_key && - (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED) | - (1 << KEY_FLAG_DEAD))))) - return _ext4_get_encryption_info(inode); - return 0; -} +int ext4_get_encryption_info(struct inode *inode); static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode) { diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h index ac7d4e813796..e52637d969db 100644 --- a/fs/ext4/ext4_crypto.h +++ b/fs/ext4/ext4_crypto.h @@ -58,8 +58,10 @@ struct ext4_encryption_context { #define EXT4_XTS_TWEAK_SIZE 16 #define EXT4_AES_128_ECB_KEY_SIZE 16 #define EXT4_AES_256_GCM_KEY_SIZE 32 +#define EXT4_AES_256_ECB_KEY_SIZE 32 #define EXT4_AES_256_CBC_KEY_SIZE 32 #define EXT4_AES_256_CTS_KEY_SIZE 32 +#define EXT4_AES_256_HEH_KEY_SIZE 32 #define EXT4_AES_256_XTS_KEY_SIZE 64 #define EXT4_MAX_KEY_SIZE 64 @@ -78,7 +80,6 @@ struct ext4_crypt_info { char ci_filename_mode; char ci_flags; struct crypto_ablkcipher *ci_ctfm; - struct key *ci_keyring_key; char ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE]; }; @@ -121,6 +122,8 @@ static inline int ext4_encryption_key_size(int mode) return EXT4_AES_256_CBC_KEY_SIZE; case EXT4_ENCRYPTION_MODE_AES_256_CTS: return EXT4_AES_256_CTS_KEY_SIZE; + case EXT4_ENCRYPTION_MODE_AES_256_HEH: + return EXT4_AES_256_HEH_KEY_SIZE; default: BUG(); } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9da42ace762a..61d5bfc7318c 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4902,6 +4902,8 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); if (file->f_flags & O_SYNC) ext4_handle_sync(handle); @@ -5362,7 +5364,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, ext4_lblk_t stop, *iterator, ex_start, ex_end; /* Let path point to the last extent */ - path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0); + path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, + EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); @@ -5371,15 +5374,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, if (!extent) goto out; - stop = le32_to_cpu(extent->ee_block) + - ext4_ext_get_actual_len(extent); + stop = le32_to_cpu(extent->ee_block); /* * In case of left shift, Don't start shifting extents until we make * sure the hole is big enough to accommodate the shift. */ if (SHIFT == SHIFT_LEFT) { - path = ext4_find_extent(inode, start - 1, &path, 0); + path = ext4_find_extent(inode, start - 1, &path, + EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; @@ -5411,9 +5414,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, else iterator = &stop; - /* Its safe to start updating extents */ - while (start < stop) { - path = ext4_find_extent(inode, *iterator, &path, 0); + /* + * Its safe to start updating extents. Start and stop are unsigned, so + * in case of right shift if extent with 0 block is reached, iterator + * becomes NULL to indicate the end of the loop. + */ + while (iterator && start <= stop) { + path = ext4_find_extent(inode, *iterator, &path, + EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; @@ -5440,8 +5448,11 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); - *iterator = le32_to_cpu(extent->ee_block) > 0 ? - le32_to_cpu(extent->ee_block) - 1 : 0; + if (le32_to_cpu(extent->ee_block) > 0) + *iterator = le32_to_cpu(extent->ee_block) - 1; + else + /* Beginning is reached, end of the loop */ + iterator = NULL; /* Update path extent in case we need to stop */ while (le32_to_cpu(extent->ee_block) < start) extent++; @@ -5588,6 +5599,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); @@ -5761,6 +5773,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0d24ebcd7c9e..45ef9975caec 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -463,47 +463,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, num = min_t(pgoff_t, end - index, PAGEVEC_SIZE); nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, (pgoff_t)num); - if (nr_pages == 0) { - if (whence == SEEK_DATA) - break; - - BUG_ON(whence != SEEK_HOLE); - /* - * If this is the first time to go into the loop and - * offset is not beyond the end offset, it will be a - * hole at this offset - */ - if (lastoff == startoff || lastoff < endoff) - found = 1; + if (nr_pages == 0) break; - } - - /* - * If this is the first time to go into the loop and - * offset is smaller than the first page offset, it will be a - * hole at this offset. - */ - if (lastoff == startoff && whence == SEEK_HOLE && - lastoff < page_offset(pvec.pages[0])) { - found = 1; - break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; struct buffer_head *bh, *head; /* - * If the current offset is not beyond the end of given - * range, it will be a hole. + * If current offset is smaller than the page offset, + * there is a hole at this offset. */ - if (lastoff < endoff && whence == SEEK_HOLE && - page->index > end) { + if (whence == SEEK_HOLE && lastoff < endoff && + lastoff < page_offset(pvec.pages[i])) { found = 1; *offset = lastoff; goto out; } + if (page->index > end) + goto out; + lock_page(page); if (unlikely(page->mapping != inode->i_mapping)) { @@ -520,6 +500,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, lastoff = page_offset(page); bh = head = page_buffers(page); do { + if (lastoff + bh->b_size <= startoff) + goto next; if (buffer_uptodate(bh) || buffer_unwritten(bh)) { if (whence == SEEK_DATA) @@ -534,6 +516,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); goto out; } +next: lastoff += bh->b_size; bh = bh->b_this_page; } while (bh != head); @@ -543,20 +526,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); } - /* - * The no. of pages is less than our desired, that would be a - * hole in there. - */ - if (nr_pages < num && whence == SEEK_HOLE) { - found = 1; - *offset = lastoff; + /* The no. of pages is less than our desired, we are done. */ + if (nr_pages < num) break; - } index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + if (whence == SEEK_HOLE && lastoff < endoff) { + found = 1; + *offset = lastoff; + } out: pagevec_release(&pvec); return found; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 43dcaab85201..bc7c082b7913 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -503,8 +503,16 @@ int ext4_readpage_inline(struct inode *inode, struct page *page) return -EAGAIN; } - trace_android_fs_dataread_start(inode, page_offset(page), PAGE_SIZE, - current->pid, current->comm); + if (trace_android_fs_dataread_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_dataread_start(inode, page_offset(page), + PAGE_SIZE, current->pid, + path, current->comm); + } /* * Current inline data can only exist in the 1st page, @@ -939,8 +947,15 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, struct page *page) { int i_size_changed = 0; + int ret; - copied = ext4_write_inline_data_end(inode, pos, len, copied, page); + ret = ext4_write_inline_data_end(inode, pos, len, copied, page); + if (ret < 0) { + unlock_page(page); + put_page(page); + return ret; + } + copied = ret; /* * No need to use i_size_read() here, the i_size @@ -1157,10 +1172,9 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, set_buffer_uptodate(dir_block); err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); if (err) - goto out; + return err; set_buffer_verified(dir_block); -out: - return err; + return ext4_mark_inode_dirty(handle, inode); } static int ext4_convert_inline_data_nolock(handle_t *handle, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c33fcb4f8533..e3d425eeab4a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -72,10 +72,9 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size); offset += csum_size; - csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset, - EXT4_INODE_SIZE(inode->i_sb) - - offset); } + csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset, + EXT4_INODE_SIZE(inode->i_sb) - offset); } return csum; @@ -1017,8 +1016,16 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, pgoff_t index; unsigned from, to; - trace_android_fs_datawrite_start(inode, pos, len, - current->pid, current->comm); + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, path, + current->comm); + } trace_ext4_write_begin(inode, pos, len, flags); /* * Reserve one block more for addition to orphan list in case @@ -1169,8 +1176,11 @@ static int ext4_write_end(struct file *file, if (ext4_has_inline_data(inode)) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); - if (ret < 0) + if (ret < 0) { + unlock_page(page); + put_page(page); goto errout; + } copied = ret; } else copied = block_write_end(file, mapping, pos, @@ -1224,7 +1234,9 @@ errout: * set the buffer to be dirty, since in data=journalled mode we need * to call ext4_handle_dirty_metadata() instead. */ -static void zero_new_buffers(struct page *page, unsigned from, unsigned to) +static void ext4_journalled_zero_new_buffers(handle_t *handle, + struct page *page, + unsigned from, unsigned to) { unsigned int block_start = 0, block_end; struct buffer_head *head, *bh; @@ -1241,7 +1253,7 @@ static void zero_new_buffers(struct page *page, unsigned from, unsigned to) size = min(to, block_end) - start; zero_user(page, start, size); - set_buffer_uptodate(bh); + write_end_fn(handle, bh); } clear_buffer_new(bh); } @@ -1271,18 +1283,25 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (ext4_has_inline_data(inode)) - copied = ext4_write_inline_data_end(inode, pos, len, - copied, page); - else { - if (copied < len) { - if (!PageUptodate(page)) - copied = 0; - zero_new_buffers(page, from+copied, to); + if (ext4_has_inline_data(inode)) { + ret = ext4_write_inline_data_end(inode, pos, len, + copied, page); + if (ret < 0) { + unlock_page(page); + put_page(page); + goto errout; } - + copied = ret; + } else if (unlikely(copied < len) && !PageUptodate(page)) { + copied = 0; + ext4_journalled_zero_new_buffers(handle, page, from, to); + } else { + if (unlikely(copied < len)) + ext4_journalled_zero_new_buffers(handle, page, + from + copied, to); ret = ext4_walk_page_buffers(handle, page_buffers(page), from, - to, &partial, write_end_fn); + from + copied, &partial, + write_end_fn); if (!partial) SetPageUptodate(page); } @@ -1308,6 +1327,7 @@ static int ext4_journalled_write_end(struct file *file, */ ext4_orphan_add(handle, inode); +errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -2037,7 +2057,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd, { struct inode *inode = mpd->inode; int err; - ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) + ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1) >> inode->i_blkbits; do { @@ -2732,8 +2752,16 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, len, flags, pagep, fsdata); } *fsdata = (void *)0; - trace_android_fs_datawrite_start(inode, pos, len, - current->pid, current->comm); + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, + path, current->comm); + } trace_ext4_da_write_begin(inode, pos, len, flags); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { @@ -3342,16 +3370,27 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return 0; if (trace_android_fs_dataread_start_enabled() && - (iov_iter_rw(iter) == READ)) + (iov_iter_rw(iter) == READ)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); trace_android_fs_dataread_start(inode, offset, count, - current->pid, + current->pid, path, current->comm); + } if (trace_android_fs_datawrite_start_enabled() && - (iov_iter_rw(iter) == WRITE)) + (iov_iter_rw(iter) == WRITE)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); trace_android_fs_datawrite_start(inode, offset, count, - current->pid, + current->pid, path, current->comm); - + } trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_direct_IO(iocb, iter, offset); @@ -3587,6 +3626,10 @@ static int ext4_block_truncate_page(handle_t *handle, unsigned blocksize; struct inode *inode = mapping->host; + /* If we are processing an encrypted inode during orphan list handling */ + if (ext4_encrypted_inode(inode) && !ext4_has_encryption_key(inode)) + return 0; + blocksize = inode->i_sb->s_blocksize; length = blocksize - (offset & (blocksize - 1)); @@ -3804,6 +3847,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); out_dio: @@ -5173,8 +5218,9 @@ static int ext4_expand_extra_isize(struct inode *inode, /* No extended attributes present */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) || header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { - memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0, - new_extra_isize); + memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + + EXT4_I(inode)->i_extra_isize, 0, + new_extra_isize - EXT4_I(inode)->i_extra_isize); EXT4_I(inode)->i_extra_isize = new_extra_isize; return 0; } @@ -5404,6 +5450,11 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) file_update_time(vma->vm_file); down_read(&EXT4_I(inode)->i_mmap_sem); + + ret = ext4_convert_inline_data(inode); + if (ret) + goto out_ret; + /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 7e974878d9a9..c21826be1cb3 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -626,6 +626,9 @@ resizefs_out: struct ext4_encryption_policy policy; int err = 0; + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + if (copy_from_user(&policy, (struct ext4_encryption_policy __user *)arg, sizeof(policy))) { @@ -637,8 +640,12 @@ resizefs_out: if (err) goto encryption_policy_out; + mutex_lock(&inode->i_mutex); + err = ext4_process_policy(&policy, inode); + mutex_unlock(&inode->i_mutex); + mnt_drop_write_file(filp); encryption_policy_out: return err; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index be1227c196d8..c2810503eb50 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3121,6 +3121,13 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, if (ar->pright && start + size - 1 >= ar->lright) size -= start + size - ar->lright; + /* + * Trim allocation request for filesystems with artificially small + * groups. + */ + if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) + size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb); + end = start + size; /* check we don't cross already preallocated blocks */ diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 7861d801b048..05048fcfd602 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) if (PageUptodate(page)) return 0; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 573b4cbb0cb9..1d007e853f5c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1243,9 +1243,9 @@ static inline int ext4_match(struct ext4_filename *fname, if (unlikely(!name)) { if (fname->usr_fname->name[0] == '_') { int ret; - if (de->name_len < 16) + if (de->name_len <= 32) return 0; - ret = memcmp(de->name + de->name_len - 16, + ret = memcmp(de->name + ((de->name_len - 17) & ~15), fname->crypto_buf.name + 8, 16); return (ret == 0) ? 1 : 0; } @@ -1557,6 +1557,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi struct ext4_dir_entry_2 *de; struct buffer_head *bh; + if (ext4_encrypted_inode(dir)) { + int res = ext4_get_encryption_info(dir); + + /* + * This should be a properly defined flag for + * dentry->d_flags when we uplift this to the VFS. + * d_fsdata is set to (void *) 1 if if the dentry is + * created while the directory was encrypted and we + * don't have access to the key. + */ + dentry->d_fsdata = NULL; + if (ext4_encryption_info(dir)) + dentry->d_fsdata = (void *) 1; + d_set_d_op(dentry, &ext4_encrypted_d_ops); + if (res && res != -ENOKEY) + return ERR_PTR(res); + } + if (dentry->d_name.len > EXT4_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 17fbe3882b8e..6ca56f5f72b5 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -23,6 +23,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/backing-dev.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -485,9 +486,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io, if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode) && nr_to_submit) { - data_page = ext4_encrypt(inode, page); + gfp_t gfp_flags = GFP_NOFS; + + retry_encrypt: + data_page = ext4_encrypt(inode, page, gfp_flags); if (IS_ERR(data_page)) { ret = PTR_ERR(data_page); + if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) { + if (io->io_bio) { + ext4_io_submit(io); + congestion_wait(BLK_RW_ASYNC, HZ/50); + } + gfp_flags |= __GFP_NOFAIL; + goto retry_encrypt; + } data_page = NULL; goto out; } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 1ce24a6759a0..783e33d839cf 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -152,11 +152,17 @@ ext4_submit_bio_read(struct bio *bio) struct page *first_page = bio->bi_io_vec[0].bv_page; if (first_page != NULL) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + first_page->mapping->host); trace_android_fs_dataread_start( first_page->mapping->host, page_offset(first_page), bio->bi_iter.bi_size, current->pid, + path, current->comm); } } @@ -312,7 +318,7 @@ int ext4_mpage_readpages(struct address_space *mapping, if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { - ctx = ext4_get_crypto_ctx(inode); + ctx = ext4_get_crypto_ctx(inode, GFP_NOFS); if (IS_ERR(ctx)) goto set_error_page; } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 34038e3598d5..74516efd874c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1926,7 +1926,8 @@ retry: n_desc_blocks = o_desc_blocks + le16_to_cpu(es->s_reserved_gdt_blocks); n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); - n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb); + n_blocks_count = (ext4_fsblk_t)n_group * + EXT4_BLOCKS_PER_GROUP(sb); n_group--; /* set to last group number */ } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 68640e6f95c5..bd8831bfbafe 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -793,6 +793,7 @@ static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; + int aborted = 0; int i, err; ext4_unregister_li_request(sb); @@ -802,9 +803,10 @@ static void ext4_put_super(struct super_block *sb) destroy_workqueue(sbi->rsv_conversion_wq); if (sbi->s_journal) { + aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; - if (err < 0) + if ((err < 0) && !aborted) ext4_abort(sb, "Couldn't clean up the journal"); } @@ -814,9 +816,8 @@ static void ext4_put_super(struct super_block *sb) ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); - ext4_xattr_put_super(sb); - if (!(sb->s_flags & MS_RDONLY)) { + if (!(sb->s_flags & MS_RDONLY) && !aborted) { ext4_clear_feature_journal_needs_recovery(sb); es->s_state = cpu_to_le16(sbi->s_mount_state); } @@ -3663,6 +3664,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); + if (ext4_has_feature_meta_bg(sb)) { + if (le32_to_cpu(es->s_first_meta_bg) > db_count) { + ext4_msg(sb, KERN_WARNING, + "first meta block group too large: %u " + "(group descriptor block count %u)", + le32_to_cpu(es->s_first_meta_bg), db_count); + goto failed_mount; + } + } sbi->s_group_desc = ext4_kvmalloc(db_count * sizeof(struct buffer_head *), GFP_KERNEL); @@ -3737,7 +3747,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * root first: it may be modified in the journal! */ if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) { - if (ext4_load_journal(sb, es, journal_devnum)) + err = ext4_load_journal(sb, es, journal_devnum); + if (err) goto failed_mount3a; } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) && ext4_has_feature_journal_needs_recovery(sb)) { @@ -3821,7 +3832,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) no_journal: if (ext4_mballoc_ready) { - sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id); + sbi->s_mb_cache = ext4_xattr_create_cache(); if (!sbi->s_mb_cache) { ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache"); goto failed_mount_wq; @@ -4053,6 +4064,10 @@ failed_mount4: if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); failed_mount_wq: + if (sbi->s_mb_cache) { + ext4_xattr_destroy_cache(sbi->s_mb_cache); + sbi->s_mb_cache = NULL; + } if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 5d09ea585840..c2ee23acf359 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a, int ret; ret = kstrtoull(skip_spaces(buf), 0, &val); - if (!ret || val >= clusters) + if (ret || val >= clusters) return -EINVAL; atomic64_set(&sbi->s_resv_clusters, val); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 263002f0389d..b310ed81c10e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -53,7 +53,7 @@ #include <linux/init.h> #include <linux/fs.h> #include <linux/slab.h> -#include <linux/mbcache.h> +#include <linux/mbcache2.h> #include <linux/quotaops.h> #include "ext4_jbd2.h" #include "ext4.h" @@ -80,10 +80,10 @@ # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif -static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *); +static void ext4_xattr_cache_insert(struct mb2_cache *, struct buffer_head *); static struct buffer_head *ext4_xattr_cache_find(struct inode *, struct ext4_xattr_header *, - struct mb_cache_entry **); + struct mb2_cache_entry **); static void ext4_xattr_rehash(struct ext4_xattr_header *, struct ext4_xattr_entry *); static int ext4_xattr_list(struct dentry *dentry, char *buffer, @@ -233,6 +233,27 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) return error; } +static int +__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header, + void *end, const char *function, unsigned int line) +{ + struct ext4_xattr_entry *entry = IFIRST(header); + int error = -EFSCORRUPTED; + + if (((void *) header >= end) || + (header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC))) + goto errout; + error = ext4_xattr_check_names(entry, end, entry); +errout: + if (error) + __ext4_error_inode(inode, function, line, 0, + "corrupted in-inode xattr"); + return error; +} + +#define xattr_check_inode(inode, header, end) \ + __xattr_check_inode((inode), (header), (end), __func__, __LINE__) + static inline int ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size) { @@ -279,7 +300,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, struct ext4_xattr_entry *entry; size_t size; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -344,7 +365,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, header = IHDR(inode, raw_inode); entry = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(entry, end, entry); + error = xattr_check_inode(inode, header, end); if (error) goto cleanup; error = ext4_xattr_find_entry(&entry, name_index, name, @@ -426,7 +447,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -475,7 +496,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header)); + error = xattr_check_inode(inode, header, end); if (error) goto cleanup; error = ext4_xattr_list_entries(dentry, IFIRST(header), @@ -543,11 +564,8 @@ static void ext4_xattr_release_block(handle_t *handle, struct inode *inode, struct buffer_head *bh) { - struct mb_cache_entry *ce = NULL; int error = 0; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); - ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr); BUFFER_TRACE(bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bh); if (error) @@ -555,9 +573,15 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, lock_buffer(bh); if (BHDR(bh)->h_refcount == cpu_to_le32(1)) { + __u32 hash = le32_to_cpu(BHDR(bh)->h_hash); + ea_bdebug(bh, "refcount now=0; freeing"); - if (ce) - mb_cache_entry_free(ce); + /* + * This must happen under buffer lock for + * ext4_xattr_block_set() to reliably detect freed block + */ + mb2_cache_entry_delete_block(EXT4_GET_MB_CACHE(inode), hash, + bh->b_blocknr); get_bh(bh); unlock_buffer(bh); ext4_free_blocks(handle, inode, bh, 0, 1, @@ -565,8 +589,6 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, EXT4_FREE_BLOCKS_FORGET); } else { le32_add_cpu(&BHDR(bh)->h_refcount, -1); - if (ce) - mb_cache_entry_release(ce); /* * Beware of this ugliness: Releasing of xattr block references * from different inodes can race and so we have to protect @@ -779,17 +801,15 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; struct ext4_xattr_search *s = &bs->s; - struct mb_cache_entry *ce = NULL; + struct mb2_cache_entry *ce = NULL; int error = 0; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); #define header(x) ((struct ext4_xattr_header *)(x)) if (i->value && i->value_len > sb->s_blocksize) return -ENOSPC; if (s->base) { - ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev, - bs->bh->b_blocknr); BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); if (error) @@ -797,10 +817,15 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, lock_buffer(bs->bh); if (header(s->base)->h_refcount == cpu_to_le32(1)) { - if (ce) { - mb_cache_entry_free(ce); - ce = NULL; - } + __u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash); + + /* + * This must happen under buffer lock for + * ext4_xattr_block_set() to reliably detect modified + * block + */ + mb2_cache_entry_delete_block(ext4_mb_cache, hash, + bs->bh->b_blocknr); ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s); if (!error) { @@ -824,10 +849,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, int offset = (char *)s->here - bs->bh->b_data; unlock_buffer(bs->bh); - if (ce) { - mb_cache_entry_release(ce); - ce = NULL; - } ea_bdebug(bs->bh, "cloning"); s->base = kmalloc(bs->bh->b_size, GFP_NOFS); error = -ENOMEM; @@ -882,6 +903,31 @@ inserted: if (error) goto cleanup_dquot; lock_buffer(new_bh); + /* + * We have to be careful about races with + * freeing or rehashing of xattr block. Once we + * hold buffer lock xattr block's state is + * stable so we can check whether the block got + * freed / rehashed or not. Since we unhash + * mbcache entry under buffer lock when freeing + * / rehashing xattr block, checking whether + * entry is still hashed is reliable. + */ + if (hlist_bl_unhashed(&ce->e_hash_list)) { + /* + * Undo everything and check mbcache + * again. + */ + unlock_buffer(new_bh); + dquot_free_block(inode, + EXT4_C2B(EXT4_SB(sb), + 1)); + brelse(new_bh); + mb2_cache_entry_put(ext4_mb_cache, ce); + ce = NULL; + new_bh = NULL; + goto inserted; + } le32_add_cpu(&BHDR(new_bh)->h_refcount, 1); ea_bdebug(new_bh, "reusing; refcount now=%d", le32_to_cpu(BHDR(new_bh)->h_refcount)); @@ -892,7 +938,8 @@ inserted: if (error) goto cleanup_dquot; } - mb_cache_entry_release(ce); + mb2_cache_entry_touch(ext4_mb_cache, ce); + mb2_cache_entry_put(ext4_mb_cache, ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ @@ -957,7 +1004,7 @@ getblk_failed: cleanup: if (ce) - mb_cache_entry_release(ce); + mb2_cache_entry_put(ext4_mb_cache, ce); brelse(new_bh); if (!(bs->bh && s->base == bs->bh->b_data)) kfree(s->base); @@ -991,8 +1038,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, is->s.here = is->s.first; is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { - error = ext4_xattr_check_names(IFIRST(header), is->s.end, - IFIRST(header)); + error = xattr_check_inode(inode, header, is->s.end); if (error) return error; /* Find the named attribute. */ @@ -1293,6 +1339,10 @@ retry: last = entry; total_ino = sizeof(struct ext4_xattr_ibody_header); + error = xattr_check_inode(inode, header, end); + if (error) + goto cleanup; + free = ext4_xattr_free_space(last, &min_offs, base, &total_ino); if (free >= isize_diff) { entry = IFIRST(header); @@ -1519,17 +1569,6 @@ cleanup: } /* - * ext4_xattr_put_super() - * - * This is called when a file system is unmounted. - */ -void -ext4_xattr_put_super(struct super_block *sb) -{ - mb_cache_shrink(sb->s_bdev); -} - -/* * ext4_xattr_cache_insert() * * Create a new entry in the extended attribute cache, and insert @@ -1538,28 +1577,18 @@ ext4_xattr_put_super(struct super_block *sb) * Returns 0, or a negative error number on failure. */ static void -ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh) +ext4_xattr_cache_insert(struct mb2_cache *ext4_mb_cache, struct buffer_head *bh) { __u32 hash = le32_to_cpu(BHDR(bh)->h_hash); - struct mb_cache_entry *ce; int error; - ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS); - if (!ce) { - ea_bdebug(bh, "out of memory"); - return; - } - error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash); + error = mb2_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash, + bh->b_blocknr); if (error) { - mb_cache_entry_free(ce); - if (error == -EBUSY) { + if (error == -EBUSY) ea_bdebug(bh, "already in cache"); - error = 0; - } - } else { + } else ea_bdebug(bh, "inserting [%x]", (int)hash); - mb_cache_entry_release(ce); - } } /* @@ -1612,26 +1641,19 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, */ static struct buffer_head * ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, - struct mb_cache_entry **pce) + struct mb2_cache_entry **pce) { __u32 hash = le32_to_cpu(header->h_hash); - struct mb_cache_entry *ce; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb2_cache_entry *ce; + struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); -again: - ce = mb_cache_entry_find_first(ext4_mb_cache, inode->i_sb->s_bdev, - hash); + ce = mb2_cache_entry_find_first(ext4_mb_cache, hash); while (ce) { struct buffer_head *bh; - if (IS_ERR(ce)) { - if (PTR_ERR(ce) == -EAGAIN) - goto again; - break; - } bh = sb_bread(inode->i_sb, ce->e_block); if (!bh) { EXT4_ERROR_INODE(inode, "block %lu read error", @@ -1647,7 +1669,7 @@ again: return bh; } brelse(bh); - ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash); + ce = mb2_cache_entry_find_next(ext4_mb_cache, ce); } return NULL; } @@ -1722,15 +1744,15 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header, #define HASH_BUCKET_BITS 10 -struct mb_cache * -ext4_xattr_create_cache(char *name) +struct mb2_cache * +ext4_xattr_create_cache(void) { - return mb_cache_create(name, HASH_BUCKET_BITS); + return mb2_cache_create(HASH_BUCKET_BITS); } -void ext4_xattr_destroy_cache(struct mb_cache *cache) +void ext4_xattr_destroy_cache(struct mb2_cache *cache) { if (cache) - mb_cache_destroy(cache); + mb2_cache_destroy(cache); } diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index ddc0957760ba..10b0f7323ed6 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -108,7 +108,6 @@ extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_ extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int); extern void ext4_xattr_delete_inode(handle_t *, struct inode *); -extern void ext4_xattr_put_super(struct super_block *); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); @@ -124,8 +123,8 @@ extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is); -extern struct mb_cache *ext4_xattr_create_cache(char *name); -extern void ext4_xattr_destroy_cache(struct mb_cache *); +extern struct mb2_cache *ext4_xattr_create_cache(void); +extern void ext4_xattr_destroy_cache(struct mb2_cache *); #ifdef CONFIG_EXT4_FS_SECURITY extern int ext4_init_security(handle_t *handle, struct inode *inode, diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index e9a8d676c6bc..83dcf7bfd7b8 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -213,7 +213,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { + if (acl && !ipage) { error = posix_acl_update_mode(inode, &inode->i_mode, &acl); if (error) return error; diff --git a/fs/f2fs/crypto_fname.c b/fs/f2fs/crypto_fname.c index ab377d496a39..38349ed5ea51 100644 --- a/fs/f2fs/crypto_fname.c +++ b/fs/f2fs/crypto_fname.c @@ -333,7 +333,7 @@ int f2fs_fname_disk_to_usr(struct inode *inode, memset(buf + 4, 0, 4); } else memset(buf, 0, 8); - memcpy(buf + 8, iname->name + iname->len - 16, 16); + memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16); oname->name[0] = '_'; ret = digest_encode(buf, 24, oname->name + 1); oname->len = ret + 1; diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c index 5de2d866a25c..18595d7a0efc 100644 --- a/fs/f2fs/crypto_key.c +++ b/fs/f2fs/crypto_key.c @@ -92,7 +92,6 @@ static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci) if (!ci) return; - key_put(ci->ci_keyring_key); crypto_free_ablkcipher(ci->ci_ctfm); kmem_cache_free(f2fs_crypt_info_cachep, ci); } @@ -113,7 +112,7 @@ void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci) f2fs_free_crypt_info(ci); } -int _f2fs_get_encryption_info(struct inode *inode) +int f2fs_get_encryption_info(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_crypt_info *crypt_info; @@ -129,18 +128,12 @@ int _f2fs_get_encryption_info(struct inode *inode) char mode; int res; + if (fi->i_crypt_info) + return 0; + res = f2fs_crypto_initialize(); if (res) return res; -retry: - crypt_info = ACCESS_ONCE(fi->i_crypt_info); - if (crypt_info) { - if (!crypt_info->ci_keyring_key || - key_validate(crypt_info->ci_keyring_key) == 0) - return 0; - f2fs_free_encryption_info(inode, crypt_info); - goto retry; - } res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, @@ -159,7 +152,6 @@ retry: crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; crypt_info->ci_ctfm = NULL; - crypt_info->ci_keyring_key = NULL; memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, sizeof(crypt_info->ci_master_key)); if (S_ISREG(inode->i_mode)) @@ -197,7 +189,6 @@ retry: keyring_key = NULL; goto out; } - crypt_info->ci_keyring_key = keyring_key; BUG_ON(keyring_key->type != &key_type_logon); ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct f2fs_encryption_key)) { @@ -230,17 +221,12 @@ retry: if (res) goto out; - memzero_explicit(raw_key, sizeof(raw_key)); - if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) { - f2fs_free_crypt_info(crypt_info); - goto retry; - } - return 0; - + if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) == NULL) + crypt_info = NULL; out: if (res == -ENOKEY && !S_ISREG(inode->i_mode)) res = 0; - + key_put(keyring_key); f2fs_free_crypt_info(crypt_info); memzero_explicit(raw_key, sizeof(raw_key)); return res; diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c index e504f548b64e..884f3f0fe29d 100644 --- a/fs/f2fs/crypto_policy.c +++ b/fs/f2fs/crypto_policy.c @@ -141,20 +141,38 @@ int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy) int f2fs_is_child_context_consistent_with_parent(struct inode *parent, struct inode *child) { - struct f2fs_crypt_info *parent_ci, *child_ci; + const struct f2fs_crypt_info *parent_ci, *child_ci; + struct f2fs_encryption_context parent_ctx, child_ctx; int res; - if ((parent == NULL) || (child == NULL)) { - pr_err("parent %p child %p\n", parent, child); - BUG_ON(1); - } + /* No restrictions on file types which are never encrypted */ + if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) && + !S_ISLNK(child->i_mode)) + return 1; - /* no restrictions if the parent directory is not encrypted */ + /* No restrictions if the parent directory is unencrypted */ if (!f2fs_encrypted_inode(parent)) return 1; - /* if the child directory is not encrypted, this is always a problem */ + + /* Encrypted directories must not contain unencrypted files */ if (!f2fs_encrypted_inode(child)) return 0; + + /* + * Both parent and child are encrypted, so verify they use the same + * encryption policy. Compare the fscrypt_info structs if the keys are + * available, otherwise retrieve and compare the fscrypt_contexts. + * + * Note that the fscrypt_context retrieval will be required frequently + * when accessing an encrypted directory tree without the key. + * Performance-wise this is not a big deal because we already don't + * really optimize for file access without the key (to the extent that + * such access is even possible), given that any attempted access + * already causes a fscrypt_context retrieval and keyring search. + * + * In any case, if an unexpected error occurs, fall back to "forbidden". + */ + res = f2fs_get_encryption_info(parent); if (res) return 0; @@ -163,17 +181,35 @@ int f2fs_is_child_context_consistent_with_parent(struct inode *parent, return 0; parent_ci = F2FS_I(parent)->i_crypt_info; child_ci = F2FS_I(child)->i_crypt_info; - if (!parent_ci && !child_ci) - return 1; - if (!parent_ci || !child_ci) + if (parent_ci && child_ci) { + return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key, + F2FS_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ci->ci_data_mode == child_ci->ci_data_mode) && + (parent_ci->ci_filename_mode == + child_ci->ci_filename_mode) && + (parent_ci->ci_flags == child_ci->ci_flags); + } + + res = f2fs_getxattr(parent, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + &parent_ctx, sizeof(parent_ctx), NULL); + if (res != sizeof(parent_ctx)) + return 0; + + res = f2fs_getxattr(child, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + &child_ctx, sizeof(child_ctx), NULL); + if (res != sizeof(child_ctx)) return 0; - return (memcmp(parent_ci->ci_master_key, - child_ci->ci_master_key, - F2FS_KEY_DESCRIPTOR_SIZE) == 0 && - (parent_ci->ci_data_mode == child_ci->ci_data_mode) && - (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) && - (parent_ci->ci_flags == child_ci->ci_flags)); + return memcmp(parent_ctx.master_key_descriptor, + child_ctx.master_key_descriptor, + F2FS_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ctx.contents_encryption_mode == + child_ctx.contents_encryption_mode) && + (parent_ctx.filenames_encryption_mode == + child_ctx.filenames_encryption_mode) && + (parent_ctx.flags == child_ctx.flags); } /** diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index e692958d6e78..8936044dee4c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1402,8 +1402,16 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, struct dnode_of_data dn; int err = 0; - trace_android_fs_datawrite_start(inode, pos, len, - current->pid, current->comm); + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, path, + current->comm); + } trace_f2fs_write_begin(inode, pos, len, flags); f2fs_balance_fs(sbi); @@ -1587,15 +1595,27 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (trace_android_fs_dataread_start_enabled() && - (iov_iter_rw(iter) == READ)) + (iov_iter_rw(iter) == READ)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); trace_android_fs_dataread_start(inode, offset, - count, current->pid, + count, current->pid, path, current->comm); + } if (trace_android_fs_datawrite_start_enabled() && - (iov_iter_rw(iter) == WRITE)) - trace_android_fs_datawrite_start(inode, offset, count, - current->pid, current->comm); + (iov_iter_rw(iter) == WRITE)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, offset, count, + current->pid, path, + current->comm); + } if (iov_iter_rw(iter) == WRITE) { __allocate_data_blocks(inode, offset, count); if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 7c1678ba8f92..60972a559685 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -124,19 +124,29 @@ struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname, de = &d->dentry[bit_pos]; - /* encrypted case */ + if (de->hash_code != namehash) + goto not_match; + de_name.name = d->filename[bit_pos]; de_name.len = le16_to_cpu(de->name_len); - /* show encrypted name */ - if (fname->hash) { - if (de->hash_code == fname->hash) - goto found; - } else if (de_name.len == name->len && - de->hash_code == namehash && - !memcmp(de_name.name, name->name, name->len)) +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (unlikely(!name->name)) { + if (fname->usr_fname->name[0] == '_') { + if (de_name.len > 32 && + !memcmp(de_name.name + ((de_name.len - 17) & ~15), + fname->crypto_buf.name + 8, 16)) + goto found; + goto not_match; + } + name->name = fname->crypto_buf.name; + name->len = fname->crypto_buf.len; + } +#endif + if (de_name.len == name->len && + !memcmp(de_name.name, name->name, name->len)) goto found; - +not_match: if (max_slots && max_len > *max_slots) *max_slots = max_len; max_len = 0; @@ -170,7 +180,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, int max_slots; f2fs_hash_t namehash; - namehash = f2fs_dentry_hash(&name); + namehash = f2fs_dentry_hash(&name, fname); f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH); @@ -547,7 +557,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, level = 0; slots = GET_DENTRY_SLOTS(new_name.len); - dentry_hash = f2fs_dentry_hash(&new_name); + dentry_hash = f2fs_dentry_hash(&new_name, NULL); current_depth = F2FS_I(dir)->i_current_depth; if (F2FS_I(dir)->chash == dentry_hash) { diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9db5500d63d9..2871576fbca4 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1722,7 +1722,8 @@ void f2fs_msg(struct super_block *, const char *, const char *, ...); /* * hash.c */ -f2fs_hash_t f2fs_dentry_hash(const struct qstr *); +f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, + struct f2fs_filename *fname); /* * node.c @@ -2149,7 +2150,6 @@ void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *); /* crypto_key.c */ void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *); -int _f2fs_get_encryption_info(struct inode *inode); /* crypto_fname.c */ bool f2fs_valid_filenames_enc_mode(uint32_t); @@ -2170,18 +2170,7 @@ void f2fs_exit_crypto(void); int f2fs_has_encryption_key(struct inode *); -static inline int f2fs_get_encryption_info(struct inode *inode) -{ - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; - - if (!ci || - (ci->ci_keyring_key && - (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED) | - (1 << KEY_FLAG_DEAD))))) - return _f2fs_get_encryption_info(inode); - return 0; -} +int f2fs_get_encryption_info(struct inode *inode); void f2fs_fname_crypto_free_buffer(struct f2fs_str *); int f2fs_fname_setup_filename(struct inode *, const struct qstr *, diff --git a/fs/f2fs/f2fs_crypto.h b/fs/f2fs/f2fs_crypto.h index c2c1c2b63b25..f113f1a1e8c1 100644 --- a/fs/f2fs/f2fs_crypto.h +++ b/fs/f2fs/f2fs_crypto.h @@ -79,7 +79,6 @@ struct f2fs_crypt_info { char ci_filename_mode; char ci_flags; struct crypto_ablkcipher *ci_ctfm; - struct key *ci_keyring_key; char ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE]; }; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a197215ad52b..4b449d263333 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1535,12 +1535,19 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) #ifdef CONFIG_F2FS_FS_ENCRYPTION struct f2fs_encryption_policy policy; struct inode *inode = file_inode(filp); + int err; if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg, sizeof(policy))) return -EFAULT; - return f2fs_process_policy(&policy, inode); + mutex_lock(&inode->i_mutex); + + err = f2fs_process_policy(&policy, inode); + + mutex_unlock(&inode->i_mutex); + + return err; #else return -EOPNOTSUPP; #endif diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index 71b7206c431e..b238d2fec3e5 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -70,7 +70,8 @@ static void str2hashbuf(const unsigned char *msg, size_t len, *buf++ = pad; } -f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info) +f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, + struct f2fs_filename *fname) { __u32 hash; f2fs_hash_t f2fs_hash; @@ -79,6 +80,10 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info) const unsigned char *name = name_info->name; size_t len = name_info->len; + /* encrypted bigname case */ + if (fname && !fname->disk_name.name) + return cpu_to_le32(fname->hash); + if (is_dot_dotdot(name_info)) return 0; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index d2c5d69ba0b1..f35f3eb3541f 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -85,9 +85,16 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) { struct page *ipage; - trace_android_fs_dataread_start(inode, page_offset(page), - PAGE_SIZE, current->pid, - current->comm); + if (trace_android_fs_dataread_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_dataread_start(inode, page_offset(page), + PAGE_SIZE, current->pid, + path, current->comm); + } ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) { @@ -314,7 +321,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, if (IS_ERR(ipage)) return NULL; - namehash = f2fs_dentry_hash(&name); + namehash = f2fs_dentry_hash(&name, fname); inline_dentry = inline_data_addr(ipage); @@ -479,7 +486,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, f2fs_wait_on_page_writeback(ipage, NODE); - name_hash = f2fs_dentry_hash(name); + name_hash = f2fs_dentry_hash(name, NULL); make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2); f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3a65e0132352..4f666368aa85 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -918,6 +918,79 @@ static loff_t max_file_size(unsigned bits) return result; } +static inline bool sanity_check_area_boundary(struct super_block *sb, + struct f2fs_super_block *raw_super) +{ + u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr); + u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr); + u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr); + u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr); + u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr); + u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr); + u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt); + u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit); + u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat); + u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa); + u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main); + u32 segment_count = le32_to_cpu(raw_super->segment_count); + u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); + + if (segment0_blkaddr != cp_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Mismatch start address, segment0(%u) cp_blkaddr(%u)", + segment0_blkaddr, cp_blkaddr); + return true; + } + + if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) != + sit_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong CP boundary, start(%u) end(%u) blocks(%u)", + cp_blkaddr, sit_blkaddr, + segment_count_ckpt << log_blocks_per_seg); + return true; + } + + if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) != + nat_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong SIT boundary, start(%u) end(%u) blocks(%u)", + sit_blkaddr, nat_blkaddr, + segment_count_sit << log_blocks_per_seg); + return true; + } + + if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) != + ssa_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong NAT boundary, start(%u) end(%u) blocks(%u)", + nat_blkaddr, ssa_blkaddr, + segment_count_nat << log_blocks_per_seg); + return true; + } + + if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) != + main_blkaddr) { + f2fs_msg(sb, KERN_INFO, + "Wrong SSA boundary, start(%u) end(%u) blocks(%u)", + ssa_blkaddr, main_blkaddr, + segment_count_ssa << log_blocks_per_seg); + return true; + } + + if (main_blkaddr + (segment_count_main << log_blocks_per_seg) != + segment0_blkaddr + (segment_count << log_blocks_per_seg)) { + f2fs_msg(sb, KERN_INFO, + "Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)", + main_blkaddr, + segment0_blkaddr + (segment_count << log_blocks_per_seg), + segment_count_main << log_blocks_per_seg); + return true; + } + + return false; +} + static int sanity_check_raw_super(struct super_block *sb, struct f2fs_super_block *raw_super) { @@ -947,6 +1020,14 @@ static int sanity_check_raw_super(struct super_block *sb, return 1; } + /* check log blocks per segment */ + if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { + f2fs_msg(sb, KERN_INFO, + "Invalid log blocks per segment (%u)\n", + le32_to_cpu(raw_super->log_blocks_per_seg)); + return 1; + } + /* Currently, support 512/1024/2048/4096 bytes sector size */ if (le32_to_cpu(raw_super->log_sectorsize) > F2FS_MAX_LOG_SECTOR_SIZE || @@ -965,6 +1046,30 @@ static int sanity_check_raw_super(struct super_block *sb, le32_to_cpu(raw_super->log_sectorsize)); return 1; } + + /* check reserved ino info */ + if (le32_to_cpu(raw_super->node_ino) != 1 || + le32_to_cpu(raw_super->meta_ino) != 2 || + le32_to_cpu(raw_super->root_ino) != 3) { + f2fs_msg(sb, KERN_INFO, + "Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)", + le32_to_cpu(raw_super->node_ino), + le32_to_cpu(raw_super->meta_ino), + le32_to_cpu(raw_super->root_ino)); + return 1; + } + + if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) { + f2fs_msg(sb, KERN_INFO, + "Invalid segment count (%u)", + le32_to_cpu(raw_super->segment_count)); + return 1; + } + + /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ + if (sanity_check_area_boundary(sb, raw_super)) + return 1; + return 0; } @@ -973,6 +1078,8 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int total, fsmeta; struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned int main_segs, blocks_per_seg; + int i; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -984,6 +1091,20 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi) if (unlikely(fsmeta >= total)) return 1; + main_segs = le32_to_cpu(raw_super->segment_count_main); + blocks_per_seg = sbi->blocks_per_seg; + + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || + le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) + return 1; + } + for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || + le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) + return 1; + } + if (unlikely(f2fs_cp_error(sbi))) { f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck"); return 1; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 509411dd3698..cf644d52c0cf 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1269,6 +1269,16 @@ out: return 0; } +static void fat_dummy_inode_init(struct inode *inode) +{ + /* Initialize this dummy inode to work as no-op. */ + MSDOS_I(inode)->mmu_private = 0; + MSDOS_I(inode)->i_start = 0; + MSDOS_I(inode)->i_logstart = 0; + MSDOS_I(inode)->i_attrs = 0; + MSDOS_I(inode)->i_pos = 0; +} + static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); @@ -1713,12 +1723,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - MSDOS_I(fat_inode)->i_pos = 0; + fat_dummy_inode_init(fat_inode); sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; + fat_dummy_inode_init(fsinfo_inode); fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); diff --git a/fs/fcntl.c b/fs/fcntl.c index ee85cd4e136a..62376451bbce 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -740,16 +740,10 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( - O_RDONLY | O_WRONLY | O_RDWR | - O_CREAT | O_EXCL | O_NOCTTY | - O_TRUNC | O_APPEND | /* O_NONBLOCK | */ - __O_SYNC | O_DSYNC | FASYNC | - O_DIRECT | O_LARGEFILE | O_DIRECTORY | - O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - __FMODE_EXEC | O_PATH | __O_TMPFILE | - __FMODE_NONOTIFY - )); + BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != + HWEIGHT32( + (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | + __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL); diff --git a/fs/fs_struct.c b/fs/fs_struct.c index 7dca743b2ce1..940c683561dd 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -44,6 +44,7 @@ void set_fs_pwd(struct fs_struct *fs, const struct path *path) if (old_pwd.dentry) path_put(&old_pwd); } +EXPORT_SYMBOL(set_fs_pwd); static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { @@ -89,6 +90,7 @@ void free_fs_struct(struct fs_struct *fs) path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } +EXPORT_SYMBOL(free_fs_struct); void exit_fs(struct task_struct *tsk) { @@ -127,6 +129,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old) } return fs; } +EXPORT_SYMBOL_GPL(copy_fs_struct); int unshare_fs_struct(void) { diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 4304072161aa..40d61077bead 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -542,6 +542,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate) hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) { if (invalidate) set_bit(FSCACHE_OBJECT_RETIRED, &object->flags); + clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL); } } else { @@ -560,6 +561,10 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate) wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t, TASK_UNINTERRUPTIBLE); + /* Make sure any pending writes are cancelled. */ + if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) + fscache_invalidate_writes(cookie); + /* Reset the cookie state if it wasn't relinquished */ if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) { atomic_inc(&cookie->n_active); diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c index 9b28649df3a1..a8aa00be4444 100644 --- a/fs/fscache/netfs.c +++ b/fs/fscache/netfs.c @@ -48,6 +48,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) cookie->flags = 1 << FSCACHE_COOKIE_ENABLED; spin_lock_init(&cookie->lock); + spin_lock_init(&cookie->stores_lock); INIT_HLIST_HEAD(&cookie->backing_objects); /* check the netfs type is not already present */ diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 9e792e30f4db..7a182c87f378 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -30,6 +30,7 @@ static const struct fscache_state *fscache_look_up_object(struct fscache_object static const struct fscache_state *fscache_object_available(struct fscache_object *, int); static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int); static const struct fscache_state *fscache_update_object(struct fscache_object *, int); +static const struct fscache_state *fscache_object_dead(struct fscache_object *, int); #define __STATE_NAME(n) fscache_osm_##n #define STATE(n) (&__STATE_NAME(n)) @@ -91,7 +92,7 @@ static WORK_STATE(LOOKUP_FAILURE, "LCFL", fscache_lookup_failure); static WORK_STATE(KILL_OBJECT, "KILL", fscache_kill_object); static WORK_STATE(KILL_DEPENDENTS, "KDEP", fscache_kill_dependents); static WORK_STATE(DROP_OBJECT, "DROP", fscache_drop_object); -static WORK_STATE(OBJECT_DEAD, "DEAD", (void*)2UL); +static WORK_STATE(OBJECT_DEAD, "DEAD", fscache_object_dead); static WAIT_STATE(WAIT_FOR_INIT, "?INI", TRANSIT_TO(INIT_OBJECT, 1 << FSCACHE_OBJECT_EV_NEW_CHILD)); @@ -229,6 +230,10 @@ execute_work_state: event = -1; if (new_state == NO_TRANSIT) { _debug("{OBJ%x} %s notrans", object->debug_id, state->name); + if (unlikely(state == STATE(OBJECT_DEAD))) { + _leave(" [dead]"); + return; + } fscache_enqueue_object(object); event_mask = object->oob_event_mask; goto unmask_events; @@ -239,7 +244,7 @@ execute_work_state: object->state = state = new_state; if (state->work) { - if (unlikely(state->work == ((void *)2UL))) { + if (unlikely(state == STATE(OBJECT_DEAD))) { _leave(" [dead]"); return; } @@ -645,6 +650,12 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob fscache_mark_object_dead(object); object->oob_event_mask = 0; + if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) { + /* Reject any new read/write ops and abort any that are pending. */ + clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); + fscache_cancel_all_ops(object); + } + if (list_empty(&object->dependents) && object->n_ops == 0 && object->n_children == 0) @@ -1077,3 +1088,20 @@ void fscache_object_mark_killed(struct fscache_object *object, } } EXPORT_SYMBOL(fscache_object_mark_killed); + +/* + * The object is dead. We can get here if an object gets queued by an event + * that would lead to its death (such as EV_KILL) when the dispatcher is + * already running (and so can be requeued) but hasn't yet cleared the event + * mask. + */ +static const struct fscache_state *fscache_object_dead(struct fscache_object *object, + int event) +{ + if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD, + &object->flags)) + return NO_TRANSIT; + + WARN(true, "FS-Cache object redispatched after death"); + return NO_TRANSIT; +} diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 7f18063f1655..fbfec06b054d 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -420,6 +420,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { spin_lock(&fiq->waitq.lock); + if (test_bit(FR_FINISHED, &req->flags)) { + spin_unlock(&fiq->waitq.lock); + return; + } if (list_empty(&req->intr_entry)) { list_add_tail(&req->intr_entry, &fiq->interrupts); wake_up_locked(&fiq->waitq); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 8821c380a71a..1a063cbfe503 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -46,7 +46,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc) { struct fuse_file *ff; - ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL); + ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL); if (unlikely(!ff)) return NULL; @@ -100,6 +100,7 @@ static void fuse_file_put(struct fuse_file *ff, bool sync) iput(req->misc.release.inode); fuse_put_request(ff->fc, req); } else if (sync) { + __set_bit(FR_FORCE, &req->flags); __clear_bit(FR_BACKGROUND, &req->flags); fuse_request_send(ff->fc, req); iput(req->misc.release.inode); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index ad8a5b757cc7..a443c6e54412 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -760,7 +760,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index, int error; error = get_leaf_nr(dip, index, &leaf_no); - if (!error) + if (!IS_ERR_VALUE(error)) error = get_leaf(dip, leaf_no, bh_out); return error; @@ -976,7 +976,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) index = name->hash >> (32 - dip->i_depth); error = get_leaf_nr(dip, index, &leaf_no); - if (error) + if (IS_ERR_VALUE(error)) return error; /* Get the old leaf block */ diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 32e74710b1aa..070901e76653 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -80,9 +80,9 @@ static struct rhashtable_params ht_parms = { static struct rhashtable gl_hash_table; -void gfs2_glock_free(struct gfs2_glock *gl) +static void gfs2_glock_dealloc(struct rcu_head *rcu) { - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu); if (gl->gl_ops->go_flags & GLOF_ASPACE) { kmem_cache_free(gfs2_glock_aspace_cachep, gl); @@ -90,6 +90,13 @@ void gfs2_glock_free(struct gfs2_glock *gl) kfree(gl->gl_lksb.sb_lvbptr); kmem_cache_free(gfs2_glock_cachep, gl); } +} + +void gfs2_glock_free(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + call_rcu(&gl->gl_rcu, gfs2_glock_dealloc); if (atomic_dec_and_test(&sdp->sd_glock_disposal)) wake_up(&sdp->sd_glock_wait); } @@ -651,9 +658,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, struct kmem_cache *cachep; int ret, tries = 0; + rcu_read_lock(); gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); if (gl && !lockref_get_not_dead(&gl->gl_lockref)) gl = NULL; + rcu_read_unlock(); *glp = gl; if (gl) @@ -721,15 +730,18 @@ again: if (ret == -EEXIST) { ret = 0; + rcu_read_lock(); tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) { if (++tries < 100) { + rcu_read_unlock(); cond_resched(); goto again; } tmp = NULL; ret = -ENOMEM; } + rcu_read_unlock(); } else { WARN_ON_ONCE(ret); } diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index de7b4f97ac75..4a9077ec9313 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -207,7 +207,7 @@ struct lm_lockname { struct gfs2_sbd *ln_sbd; u64 ln_number; unsigned int ln_type; -}; +} __packed __aligned(sizeof(int)); #define lm_name_equal(name1, name2) \ (((name1)->ln_number == (name2)->ln_number) && \ @@ -367,6 +367,7 @@ struct gfs2_glock { loff_t end; } gl_vm; }; + struct rcu_head gl_rcu; struct rhash_head gl_node; }; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 595ebdb41846..a17da8b57fc6 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -191,7 +191,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/fs/inode.c b/fs/inode.c index 2c16b758831d..6a7234f0afea 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1721,7 +1721,7 @@ int dentry_needs_remove_privs(struct dentry *dentry) } EXPORT_SYMBOL(dentry_needs_remove_privs); -static int __remove_privs(struct dentry *dentry, int kill) +static int __remove_privs(struct vfsmount *mnt, struct dentry *dentry, int kill) { struct iattr newattrs; @@ -1730,7 +1730,7 @@ static int __remove_privs(struct dentry *dentry, int kill) * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ - return notify_change(dentry, &newattrs, NULL); + return notify_change2(mnt, dentry, &newattrs, NULL); } /* @@ -1752,7 +1752,7 @@ int file_remove_privs(struct file *file) if (kill < 0) return kill; if (kill) - error = __remove_privs(dentry, kill); + error = __remove_privs(file->f_path.mnt, dentry, kill); if (!error) inode_has_no_xattr(inode); diff --git a/fs/internal.h b/fs/internal.h index 71859c4d0b41..6387b35a1c0d 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -84,9 +84,11 @@ extern struct file *get_empty_filp(void); * super.c */ extern int do_remount_sb(struct super_block *, int, void *, int); +extern int do_remount_sb2(struct vfsmount *, struct super_block *, int, + void *, int); extern bool trylock_super(struct super_block *sb); extern struct dentry *mount_fs(struct file_system_type *, - int, const char *, void *); + int, const char *, struct vfsmount *, void *); extern struct super_block *user_get_super(dev_t); /* diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index fa1b8e0dcacf..a2e724053919 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1876,7 +1876,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) __blist_del_buffer(list, jh); jh->b_jlist = BJ_None; - if (test_clear_buffer_jbddirty(bh)) + if (transaction && is_journal_aborted(transaction->t_journal)) + clear_buffer_jbddirty(bh); + else if (test_clear_buffer_jbddirty(bh)) mark_buffer_dirty(bh); /* Expose it to the VM */ } diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8f9176caf098..c8d58c5ac8ae 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -758,7 +758,7 @@ static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data, sb->s_blocksize - offset : toread; tmp_bh.b_state = 0; - tmp_bh.b_size = 1 << inode->i_blkbits; + tmp_bh.b_size = i_blocksize(inode); err = jfs_get_block(inode, blk, &tmp_bh, 0); if (err) return err; @@ -798,7 +798,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type, sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; - tmp_bh.b_size = 1 << inode->i_blkbits; + tmp_bh.b_size = i_blocksize(inode); err = jfs_get_block(inode, blk, &tmp_bh, 1); if (err) goto out; diff --git a/fs/mbcache2.c b/fs/mbcache2.c new file mode 100644 index 000000000000..5c3e1a8c38f6 --- /dev/null +++ b/fs/mbcache2.c @@ -0,0 +1,359 @@ +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/list_bl.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/mbcache2.h> + +/* + * Mbcache is a simple key-value store. Keys need not be unique, however + * key-value pairs are expected to be unique (we use this fact in + * mb2_cache_entry_delete_block()). + * + * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. + * They use hash of a block contents as a key and block number as a value. + * That's why keys need not be unique (different xattr blocks may end up having + * the same hash). However block number always uniquely identifies a cache + * entry. + * + * We provide functions for creation and removal of entries, search by key, + * and a special "delete entry with given key-value pair" operation. Fixed + * size hash table is used for fast key lookups. + */ + +struct mb2_cache { + /* Hash table of entries */ + struct hlist_bl_head *c_hash; + /* log2 of hash table size */ + int c_bucket_bits; + /* Protects c_lru_list, c_entry_count */ + spinlock_t c_lru_list_lock; + struct list_head c_lru_list; + /* Number of entries in cache */ + unsigned long c_entry_count; + struct shrinker c_shrink; +}; + +static struct kmem_cache *mb2_entry_cache; + +/* + * mb2_cache_entry_create - create entry in cache + * @cache - cache where the entry should be created + * @mask - gfp mask with which the entry should be allocated + * @key - key of the entry + * @block - block that contains data + * + * Creates entry in @cache with key @key and records that data is stored in + * block @block. The function returns -EBUSY if entry with the same key + * and for the same block already exists in cache. Otherwise 0 is returned. + */ +int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key, + sector_t block) +{ + struct mb2_cache_entry *entry, *dup; + struct hlist_bl_node *dup_node; + struct hlist_bl_head *head; + + entry = kmem_cache_alloc(mb2_entry_cache, mask); + if (!entry) + return -ENOMEM; + + INIT_LIST_HEAD(&entry->e_lru_list); + /* One ref for hash, one ref returned */ + atomic_set(&entry->e_refcnt, 1); + entry->e_key = key; + entry->e_block = block; + head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)]; + entry->e_hash_list_head = head; + hlist_bl_lock(head); + hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) { + if (dup->e_key == key && dup->e_block == block) { + hlist_bl_unlock(head); + kmem_cache_free(mb2_entry_cache, entry); + return -EBUSY; + } + } + hlist_bl_add_head(&entry->e_hash_list, head); + hlist_bl_unlock(head); + + spin_lock(&cache->c_lru_list_lock); + list_add_tail(&entry->e_lru_list, &cache->c_lru_list); + /* Grab ref for LRU list */ + atomic_inc(&entry->e_refcnt); + cache->c_entry_count++; + spin_unlock(&cache->c_lru_list_lock); + + return 0; +} +EXPORT_SYMBOL(mb2_cache_entry_create); + +void __mb2_cache_entry_free(struct mb2_cache_entry *entry) +{ + kmem_cache_free(mb2_entry_cache, entry); +} +EXPORT_SYMBOL(__mb2_cache_entry_free); + +static struct mb2_cache_entry *__entry_find(struct mb2_cache *cache, + struct mb2_cache_entry *entry, + u32 key) +{ + struct mb2_cache_entry *old_entry = entry; + struct hlist_bl_node *node; + struct hlist_bl_head *head; + + if (entry) + head = entry->e_hash_list_head; + else + head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)]; + hlist_bl_lock(head); + if (entry && !hlist_bl_unhashed(&entry->e_hash_list)) + node = entry->e_hash_list.next; + else + node = hlist_bl_first(head); + while (node) { + entry = hlist_bl_entry(node, struct mb2_cache_entry, + e_hash_list); + if (entry->e_key == key) { + atomic_inc(&entry->e_refcnt); + goto out; + } + node = node->next; + } + entry = NULL; +out: + hlist_bl_unlock(head); + if (old_entry) + mb2_cache_entry_put(cache, old_entry); + + return entry; +} + +/* + * mb2_cache_entry_find_first - find the first entry in cache with given key + * @cache: cache where we should search + * @key: key to look for + * + * Search in @cache for entry with key @key. Grabs reference to the first + * entry found and returns the entry. + */ +struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache, + u32 key) +{ + return __entry_find(cache, NULL, key); +} +EXPORT_SYMBOL(mb2_cache_entry_find_first); + +/* + * mb2_cache_entry_find_next - find next entry in cache with the same + * @cache: cache where we should search + * @entry: entry to start search from + * + * Finds next entry in the hash chain which has the same key as @entry. + * If @entry is unhashed (which can happen when deletion of entry races + * with the search), finds the first entry in the hash chain. The function + * drops reference to @entry and returns with a reference to the found entry. + */ +struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache, + struct mb2_cache_entry *entry) +{ + return __entry_find(cache, entry, entry->e_key); +} +EXPORT_SYMBOL(mb2_cache_entry_find_next); + +/* mb2_cache_entry_delete_block - remove information about block from cache + * @cache - cache we work with + * @key - key of the entry to remove + * @block - block containing data for @key + * + * Remove entry from cache @cache with key @key with data stored in @block. + */ +void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key, + sector_t block) +{ + struct hlist_bl_node *node; + struct hlist_bl_head *head; + struct mb2_cache_entry *entry; + + head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)]; + hlist_bl_lock(head); + hlist_bl_for_each_entry(entry, node, head, e_hash_list) { + if (entry->e_key == key && entry->e_block == block) { + /* We keep hash list reference to keep entry alive */ + hlist_bl_del_init(&entry->e_hash_list); + hlist_bl_unlock(head); + spin_lock(&cache->c_lru_list_lock); + if (!list_empty(&entry->e_lru_list)) { + list_del_init(&entry->e_lru_list); + cache->c_entry_count--; + atomic_dec(&entry->e_refcnt); + } + spin_unlock(&cache->c_lru_list_lock); + mb2_cache_entry_put(cache, entry); + return; + } + } + hlist_bl_unlock(head); +} +EXPORT_SYMBOL(mb2_cache_entry_delete_block); + +/* mb2_cache_entry_touch - cache entry got used + * @cache - cache the entry belongs to + * @entry - entry that got used + * + * Move entry in lru list to reflect the fact that it was used. + */ +void mb2_cache_entry_touch(struct mb2_cache *cache, + struct mb2_cache_entry *entry) +{ + spin_lock(&cache->c_lru_list_lock); + if (!list_empty(&entry->e_lru_list)) + list_move_tail(&cache->c_lru_list, &entry->e_lru_list); + spin_unlock(&cache->c_lru_list_lock); +} +EXPORT_SYMBOL(mb2_cache_entry_touch); + +static unsigned long mb2_cache_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct mb2_cache *cache = container_of(shrink, struct mb2_cache, + c_shrink); + + return cache->c_entry_count; +} + +/* Shrink number of entries in cache */ +static unsigned long mb2_cache_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + int nr_to_scan = sc->nr_to_scan; + struct mb2_cache *cache = container_of(shrink, struct mb2_cache, + c_shrink); + struct mb2_cache_entry *entry; + struct hlist_bl_head *head; + unsigned int shrunk = 0; + + spin_lock(&cache->c_lru_list_lock); + while (nr_to_scan-- && !list_empty(&cache->c_lru_list)) { + entry = list_first_entry(&cache->c_lru_list, + struct mb2_cache_entry, e_lru_list); + list_del_init(&entry->e_lru_list); + cache->c_entry_count--; + /* + * We keep LRU list reference so that entry doesn't go away + * from under us. + */ + spin_unlock(&cache->c_lru_list_lock); + head = entry->e_hash_list_head; + hlist_bl_lock(head); + if (!hlist_bl_unhashed(&entry->e_hash_list)) { + hlist_bl_del_init(&entry->e_hash_list); + atomic_dec(&entry->e_refcnt); + } + hlist_bl_unlock(head); + if (mb2_cache_entry_put(cache, entry)) + shrunk++; + cond_resched(); + spin_lock(&cache->c_lru_list_lock); + } + spin_unlock(&cache->c_lru_list_lock); + + return shrunk; +} + +/* + * mb2_cache_create - create cache + * @bucket_bits: log2 of the hash table size + * + * Create cache for keys with 2^bucket_bits hash entries. + */ +struct mb2_cache *mb2_cache_create(int bucket_bits) +{ + struct mb2_cache *cache; + int bucket_count = 1 << bucket_bits; + int i; + + if (!try_module_get(THIS_MODULE)) + return NULL; + + cache = kzalloc(sizeof(struct mb2_cache), GFP_KERNEL); + if (!cache) + goto err_out; + cache->c_bucket_bits = bucket_bits; + INIT_LIST_HEAD(&cache->c_lru_list); + spin_lock_init(&cache->c_lru_list_lock); + cache->c_hash = kmalloc(bucket_count * sizeof(struct hlist_bl_head), + GFP_KERNEL); + if (!cache->c_hash) { + kfree(cache); + goto err_out; + } + for (i = 0; i < bucket_count; i++) + INIT_HLIST_BL_HEAD(&cache->c_hash[i]); + + cache->c_shrink.count_objects = mb2_cache_count; + cache->c_shrink.scan_objects = mb2_cache_scan; + cache->c_shrink.seeks = DEFAULT_SEEKS; + register_shrinker(&cache->c_shrink); + + return cache; + +err_out: + module_put(THIS_MODULE); + return NULL; +} +EXPORT_SYMBOL(mb2_cache_create); + +/* + * mb2_cache_destroy - destroy cache + * @cache: the cache to destroy + * + * Free all entries in cache and cache itself. Caller must make sure nobody + * (except shrinker) can reach @cache when calling this. + */ +void mb2_cache_destroy(struct mb2_cache *cache) +{ + struct mb2_cache_entry *entry, *next; + + unregister_shrinker(&cache->c_shrink); + + /* + * We don't bother with any locking. Cache must not be used at this + * point. + */ + list_for_each_entry_safe(entry, next, &cache->c_lru_list, e_lru_list) { + if (!hlist_bl_unhashed(&entry->e_hash_list)) { + hlist_bl_del_init(&entry->e_hash_list); + atomic_dec(&entry->e_refcnt); + } else + WARN_ON(1); + list_del(&entry->e_lru_list); + WARN_ON(atomic_read(&entry->e_refcnt) != 1); + mb2_cache_entry_put(cache, entry); + } + kfree(cache->c_hash); + kfree(cache); + module_put(THIS_MODULE); +} +EXPORT_SYMBOL(mb2_cache_destroy); + +static int __init mb2cache_init(void) +{ + mb2_entry_cache = kmem_cache_create("mbcache", + sizeof(struct mb2_cache_entry), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL); + BUG_ON(!mb2_entry_cache); + return 0; +} + +static void __exit mb2cache_exit(void) +{ + kmem_cache_destroy(mb2_entry_cache); +} + +module_init(mb2cache_init) +module_exit(mb2cache_exit) + +MODULE_AUTHOR("Jan Kara <jack@suse.cz>"); +MODULE_DESCRIPTION("Meta block cache (for extended attributes)"); +MODULE_LICENSE("GPL"); diff --git a/fs/mount.h b/fs/mount.h index 14db05d424f7..37c64bbe840c 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -13,6 +13,8 @@ struct mnt_namespace { u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; + unsigned int mounts; /* # of mounts in the namespace */ + unsigned int pending_mounts; }; struct mnt_pcp { @@ -55,6 +57,7 @@ struct mount { struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ + struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct hlist_head mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; @@ -86,7 +89,6 @@ static inline int is_mounted(struct vfsmount *mnt) } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); -extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); extern bool legitimize_mnt(struct vfsmount *, unsigned); diff --git a/fs/mpage.c b/fs/mpage.c index 5c65d8942692..f37bb01a333b 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -79,11 +79,17 @@ static struct bio *mpage_bio_submit(int rw, struct bio *bio) struct page *first_page = bio->bi_io_vec[0].bv_page; if (first_page != NULL) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + first_page->mapping->host); trace_android_fs_dataread_start( first_page->mapping->host, page_offset(first_page), bio->bi_iter.bi_size, current->pid, + path, current->comm); } } @@ -141,7 +147,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) SetPageUptodate(page); return; } - create_empty_buffers(page, 1 << inode->i_blkbits, 0); + create_empty_buffers(page, i_blocksize(inode), 0); } head = page_buffers(page); page_bh = head; diff --git a/fs/namei.c b/fs/namei.c index 0b0acba72a71..f8eeea956503 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -373,9 +373,11 @@ EXPORT_SYMBOL(generic_permission); * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ -static inline int do_inode_permission(struct inode *inode, int mask) +static inline int do_inode_permission(struct vfsmount *mnt, struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { + if (likely(mnt && inode->i_op->permission2)) + return inode->i_op->permission2(mnt, inode, mask); if (likely(inode->i_op->permission)) return inode->i_op->permission(inode, mask); @@ -399,7 +401,7 @@ static inline int do_inode_permission(struct inode *inode, int mask) * This does not check for a read-only file system. You probably want * inode_permission(). */ -int __inode_permission(struct inode *inode, int mask) +int __inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask) { int retval; @@ -411,7 +413,7 @@ int __inode_permission(struct inode *inode, int mask) return -EACCES; } - retval = do_inode_permission(inode, mask); + retval = do_inode_permission(mnt, inode, mask); if (retval) return retval; @@ -419,7 +421,14 @@ int __inode_permission(struct inode *inode, int mask) if (retval) return retval; - return security_inode_permission(inode, mask); + retval = security_inode_permission(inode, mask); + return retval; +} +EXPORT_SYMBOL(__inode_permission2); + +int __inode_permission(struct inode *inode, int mask) +{ + return __inode_permission2(NULL, inode, mask); } EXPORT_SYMBOL(__inode_permission); @@ -455,14 +464,20 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ -int inode_permission(struct inode *inode, int mask) +int inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (retval) return retval; - return __inode_permission(inode, mask); + return __inode_permission2(mnt, inode, mask); +} +EXPORT_SYMBOL(inode_permission2); + +int inode_permission(struct inode *inode, int mask) +{ + return inode_permission2(NULL, inode, mask); } EXPORT_SYMBOL(inode_permission); @@ -1645,13 +1660,13 @@ static int lookup_slow(struct nameidata *nd, struct path *path) static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { - int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); + int err = inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD) return err; if (unlazy_walk(nd, NULL, 0)) return -ECHILD; } - return inode_permission(nd->inode, MAY_EXEC); + return inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC); } static inline int handle_dots(struct nameidata *nd, int type) @@ -2005,11 +2020,12 @@ static const char *path_init(struct nameidata *nd, unsigned flags) nd->depth = 0; if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; + struct vfsmount *mnt = nd->root.mnt; struct inode *inode = root->d_inode; if (*s) { if (!d_can_lookup(root)) return ERR_PTR(-ENOTDIR); - retval = inode_permission(inode, MAY_EXEC); + retval = inode_permission2(mnt, inode, MAY_EXEC); if (retval) return ERR_PTR(retval); } @@ -2280,13 +2296,14 @@ EXPORT_SYMBOL(vfs_path_lookup); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup + * @mnt: mount we are looking up on * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. */ -struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) +struct dentry *lookup_one_len2(const char *name, struct vfsmount *mnt, struct dentry *base, int len) { struct qstr this; unsigned int c; @@ -2320,12 +2337,18 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) return ERR_PTR(err); } - err = inode_permission(base->d_inode, MAY_EXEC); + err = inode_permission2(mnt, base->d_inode, MAY_EXEC); if (err) return ERR_PTR(err); return __lookup_hash(&this, base, 0); } +EXPORT_SYMBOL(lookup_one_len2); + +struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) +{ + return lookup_one_len2(name, NULL, base, len); +} EXPORT_SYMBOL(lookup_one_len); int user_path_at_empty(int dfd, const char __user *name, unsigned flags, @@ -2552,7 +2575,7 @@ EXPORT_SYMBOL(__check_sticky); * 10. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ -static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) +static int may_delete(struct vfsmount *mnt, struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; @@ -2564,7 +2587,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) BUG_ON(victim->d_parent->d_inode != dir); audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) @@ -2595,14 +2618,14 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) * 3. We should have write and exec permissions on dir * 4. We can't do it if dir is immutable (done in permission()) */ -static inline int may_create(struct inode *dir, struct dentry *child) +static inline int may_create(struct vfsmount *mnt, struct inode *dir, struct dentry *child) { audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - return inode_permission(dir, MAY_WRITE | MAY_EXEC); + return inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC); } /* @@ -2649,10 +2672,10 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } EXPORT_SYMBOL(unlock_rename); -int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool want_excl) +int vfs_create2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, + umode_t mode, bool want_excl) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); if (error) return error; @@ -2668,11 +2691,19 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, fsnotify_create(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_create2); + +int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool want_excl) +{ + return vfs_create2(NULL, dir, dentry, mode, want_excl); +} EXPORT_SYMBOL(vfs_create); static int may_open(struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; + struct vfsmount *mnt = path->mnt; struct inode *inode = dentry->d_inode; int error; @@ -2701,7 +2732,7 @@ static int may_open(struct path *path, int acc_mode, int flag) break; } - error = inode_permission(inode, acc_mode); + error = inode_permission2(mnt, inode, acc_mode); if (error) return error; @@ -2736,7 +2767,7 @@ static int handle_truncate(struct file *filp) if (!error) error = security_path_truncate(path); if (!error) { - error = do_truncate(path->dentry, 0, + error = do_truncate2(path->mnt, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } @@ -2757,7 +2788,7 @@ static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode) if (error) return error; - error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); + error = inode_permission2(dir->mnt, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -2943,6 +2974,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, bool got_write, int *opened) { struct dentry *dir = nd->path.dentry; + struct vfsmount *mnt = nd->path.mnt; struct inode *dir_inode = dir->d_inode; struct dentry *dentry; int error; @@ -2990,7 +3022,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, error = security_path_mknod(&nd->path, dentry, mode, 0); if (error) goto out_dput; - error = vfs_create(dir->d_inode, dentry, mode, + error = vfs_create2(mnt, dir->d_inode, dentry, mode, nd->flags & LOOKUP_EXCL); if (error) goto out_dput; @@ -3252,7 +3284,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, goto out; dir = path.dentry->d_inode; /* we want directory to be writable */ - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission2(path.mnt, dir, MAY_WRITE | MAY_EXEC); if (error) goto out2; if (!dir->i_op->tmpfile) { @@ -3486,9 +3518,9 @@ inline struct dentry *user_path_create(int dfd, const char __user *pathname, } EXPORT_SYMBOL(user_path_create); -int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +int vfs_mknod2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); if (error) return error; @@ -3512,6 +3544,12 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) fsnotify_create(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_mknod2); + +int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +{ + return vfs_mknod2(NULL, dir, dentry, mode, dev); +} EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) @@ -3554,10 +3592,10 @@ retry: goto out; switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(path.dentry->d_inode,dentry,mode,true); + error = vfs_create2(path.mnt, path.dentry->d_inode,dentry,mode,true); break; case S_IFCHR: case S_IFBLK: - error = vfs_mknod(path.dentry->d_inode,dentry,mode, + error = vfs_mknod2(path.mnt, path.dentry->d_inode,dentry,mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: @@ -3578,9 +3616,9 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d return sys_mknodat(AT_FDCWD, filename, mode, dev); } -int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +int vfs_mkdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) @@ -3602,6 +3640,12 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) fsnotify_mkdir(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_mkdir2); + +int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + return vfs_mkdir2(NULL, dir, dentry, mode); +} EXPORT_SYMBOL(vfs_mkdir); SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) @@ -3620,7 +3664,7 @@ retry: mode &= ~current_umask(); error = security_path_mkdir(&path, dentry, mode); if (!error) - error = vfs_mkdir(path.dentry->d_inode, dentry, mode); + error = vfs_mkdir2(path.mnt, path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -3659,9 +3703,9 @@ void dentry_unhash(struct dentry *dentry) } EXPORT_SYMBOL(dentry_unhash); -int vfs_rmdir(struct inode *dir, struct dentry *dentry) +int vfs_rmdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry) { - int error = may_delete(dir, dentry, 1); + int error = may_delete(mnt, dir, dentry, 1); if (error) return error; @@ -3696,6 +3740,12 @@ out: d_delete(dentry); return error; } +EXPORT_SYMBOL(vfs_rmdir2); + +int vfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + return vfs_rmdir2(NULL, dir, dentry); +} EXPORT_SYMBOL(vfs_rmdir); static long do_rmdir(int dfd, const char __user *pathname) @@ -3741,7 +3791,7 @@ retry: error = security_path_rmdir(&path, dentry); if (error) goto exit3; - error = vfs_rmdir(path.dentry->d_inode, dentry); + error = vfs_rmdir2(path.mnt, path.dentry->d_inode, dentry); exit3: dput(dentry); exit2: @@ -3780,10 +3830,10 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ -int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) +int vfs_unlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; - int error = may_delete(dir, dentry, 0); + int error = may_delete(mnt, dir, dentry, 0); if (error) return error; @@ -3818,6 +3868,12 @@ out: return error; } +EXPORT_SYMBOL(vfs_unlink2); + +int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) +{ + return vfs_unlink2(NULL, dir, dentry, delegated_inode); +} EXPORT_SYMBOL(vfs_unlink); /* @@ -3865,7 +3921,7 @@ retry_deleg: error = security_path_unlink(&path, dentry); if (error) goto exit2; - error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode); + error = vfs_unlink2(path.mnt, path.dentry->d_inode, dentry, &delegated_inode); exit2: dput(dentry); } @@ -3915,9 +3971,9 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) return do_unlinkat(AT_FDCWD, pathname); } -int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) +int vfs_symlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, const char *oldname) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); if (error) return error; @@ -3934,6 +3990,12 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) fsnotify_create(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_symlink2); + +int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) +{ + return vfs_symlink2(NULL, dir, dentry, oldname); +} EXPORT_SYMBOL(vfs_symlink); SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, @@ -3956,7 +4018,7 @@ retry: error = security_path_symlink(&path, dentry, from->name); if (!error) - error = vfs_symlink(path.dentry->d_inode, dentry, from->name); + error = vfs_symlink2(path.mnt, path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -3991,7 +4053,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ -int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) +int vfs_link2(struct vfsmount *mnt, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; @@ -4000,7 +4062,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de if (!inode) return -ENOENT; - error = may_create(dir, new_dentry); + error = may_create(mnt, dir, new_dentry); if (error) return error; @@ -4043,6 +4105,12 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de fsnotify_link(dir, inode, new_dentry); return error; } +EXPORT_SYMBOL(vfs_link2); + +int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) +{ + return vfs_link2(NULL, old_dentry, dir, new_dentry, delegated_inode); +} EXPORT_SYMBOL(vfs_link); /* @@ -4098,7 +4166,7 @@ retry: error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); + error = vfs_link2(old_path.mnt, old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { @@ -4173,17 +4241,18 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ -int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, +int vfs_rename2(struct vfsmount *mnt, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, struct inode **delegated_inode, unsigned int flags) { int error; bool is_dir = d_is_dir(old_dentry); - const unsigned char *old_name; struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; + struct name_snapshot old_name; /* * Check source == target. @@ -4192,19 +4261,19 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0)) return 0; - error = may_delete(old_dir, old_dentry, is_dir); + error = may_delete(mnt, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { - error = may_create(new_dir, new_dentry); + error = may_create(mnt, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) - error = may_delete(new_dir, new_dentry, is_dir); + error = may_delete(mnt, new_dir, new_dentry, is_dir); else - error = may_delete(new_dir, new_dentry, new_is_dir); + error = may_delete(mnt, new_dir, new_dentry, new_is_dir); } if (error) return error; @@ -4221,12 +4290,12 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, */ if (new_dir != old_dir) { if (is_dir) { - error = inode_permission(source, MAY_WRITE); + error = inode_permission2(mnt, source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { - error = inode_permission(target, MAY_WRITE); + error = inode_permission2(mnt, target, MAY_WRITE); if (error) return error; } @@ -4237,7 +4306,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (error) return error; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); if (!is_dir || (flags & RENAME_EXCHANGE)) lock_two_nondirectories(source, target); @@ -4298,17 +4367,25 @@ out: mutex_unlock(&target->i_mutex); dput(new_dentry); if (!error) { - fsnotify_move(old_dir, new_dir, old_name, is_dir, + fsnotify_move(old_dir, new_dir, old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, old_dentry->d_name.name, new_is_dir, NULL, new_dentry); } } - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); return error; } +EXPORT_SYMBOL(vfs_rename2); + +int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + struct inode **delegated_inode, unsigned int flags) +{ + return vfs_rename2(NULL, old_dir, old_dentry, new_dir, new_dentry, delegated_inode, flags); +} EXPORT_SYMBOL(vfs_rename); SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, @@ -4422,7 +4499,7 @@ retry_deleg: &new_path, new_dentry, flags); if (error) goto exit5; - error = vfs_rename(old_path.dentry->d_inode, old_dentry, + error = vfs_rename2(old_path.mnt, old_path.dentry->d_inode, old_dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode, flags); exit5: @@ -4467,7 +4544,7 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna int vfs_whiteout(struct inode *dir, struct dentry *dentry) { - int error = may_create(dir, dentry); + int error = may_create(NULL, dir, dentry); if (error) return error; diff --git a/fs/namespace.c b/fs/namespace.c index da98a1bbd8b5..15b91b36ecab 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -27,6 +27,9 @@ #include "pnode.h" #include "internal.h" +/* Maximum number of mounts in a mount namespace */ +unsigned int sysctl_mount_max __read_mostly = 100000; + static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; @@ -234,6 +237,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); + INIT_LIST_HEAD(&mnt->mnt_umounting); #ifdef CONFIG_FSNOTIFY INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks); #endif @@ -577,6 +581,7 @@ int sb_prepare_remount_readonly(struct super_block *sb) static void free_vfsmnt(struct mount *mnt) { + kfree(mnt->mnt.data); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); @@ -638,28 +643,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) } /* - * find the last mount at @dentry on vfsmount @mnt. - * mount_lock must be held. - */ -struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) -{ - struct mount *p, *res = NULL; - p = __lookup_mnt(mnt, dentry); - if (!p) - goto out; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - hlist_for_each_entry_continue(p, mnt_hash) { - if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) - break; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - } -out: - return res; -} - -/* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the @@ -879,6 +862,13 @@ void mnt_set_mountpoint(struct mount *mnt, hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } +static void __attach_mnt(struct mount *mnt, struct mount *parent) +{ + hlist_add_head_rcu(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); +} + /* * vfsmount lock must be held for write */ @@ -887,28 +877,45 @@ static void attach_mnt(struct mount *mnt, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); - hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + __attach_mnt(mnt, parent); } -static void attach_shadowed(struct mount *mnt, - struct mount *parent, - struct mount *shadows) +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { - if (shadows) { - hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash); - list_add(&mnt->mnt_child, &shadows->mnt_child); - } else { - hlist_add_head_rcu(&mnt->mnt_hash, - m_hash(&parent->mnt, mnt->mnt_mountpoint)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); - } + struct mountpoint *old_mp = mnt->mnt_mp; + struct dentry *old_mountpoint = mnt->mnt_mountpoint; + struct mount *old_parent = mnt->mnt_parent; + + list_del_init(&mnt->mnt_child); + hlist_del_init(&mnt->mnt_mp_list); + hlist_del_init_rcu(&mnt->mnt_hash); + + attach_mnt(mnt, parent, mp); + + put_mountpoint(old_mp); + + /* + * Safely avoid even the suggestion this code might sleep or + * lock the mount hash by taking advantage of the knowledge that + * mnt_change_mountpoint will not release the final reference + * to a mountpoint. + * + * During mounting, the mount passed in as the parent mount will + * continue to use the old mountpoint and during unmounting, the + * old mountpoint will continue to exist until namespace_unlock, + * which happens well after mnt_change_mountpoint. + */ + spin_lock(&old_mountpoint->d_lock); + old_mountpoint->d_lockref.count--; + spin_unlock(&old_mountpoint->d_lock); + + mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ -static void commit_tree(struct mount *mnt, struct mount *shadows) +static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; @@ -923,7 +930,10 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) list_splice(&head, n->list.prev); - attach_shadowed(mnt, parent, shadows); + n->mounts += n->pending_mounts; + n->pending_mounts = 0; + + __attach_mnt(mnt, parent); touch_mnt_namespace(n); } @@ -966,11 +976,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void if (!mnt) return ERR_PTR(-ENOMEM); + mnt->mnt.data = NULL; + if (type->alloc_mnt_data) { + mnt->mnt.data = type->alloc_mnt_data(); + if (!mnt->mnt.data) { + mnt_free_id(mnt); + free_vfsmnt(mnt); + return ERR_PTR(-ENOMEM); + } + } if (flags & MS_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; - root = mount_fs(type, flags, name, data); + root = mount_fs(type, flags, name, &mnt->mnt, data); if (IS_ERR(root)) { + kfree(mnt->mnt.data); mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_CAST(root); @@ -998,6 +1018,14 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, if (!mnt) return ERR_PTR(-ENOMEM); + if (sb->s_op->clone_mnt_data) { + mnt->mnt.data = sb->s_op->clone_mnt_data(old->mnt.data); + if (!mnt->mnt.data) { + err = -ENOMEM; + goto out_free; + } + } + if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else @@ -1066,6 +1094,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, return mnt; out_free: + kfree(mnt->mnt.data); mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); @@ -1443,11 +1472,16 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { + struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); - __touch_mnt_namespace(p->mnt_ns); + ns = p->mnt_ns; + if (ns) { + ns->mounts--; + __touch_mnt_namespace(ns); + } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; @@ -1718,7 +1752,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, continue; for (s = r; s; s = next_mnt(s, r)) { - struct mount *t = NULL; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { s = skip_mnt_tree(s); @@ -1740,14 +1773,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - mnt_set_mountpoint(parent, p->mnt_mp, q); - if (!list_empty(&parent->mnt_mounts)) { - t = list_last_entry(&parent->mnt_mounts, - struct mount, mnt_child); - if (t->mnt_mp != p->mnt_mp) - t = NULL; - } - attach_shadowed(q, parent, t); + attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } @@ -1856,6 +1882,28 @@ static int invent_group_ids(struct mount *mnt, bool recurse) return 0; } +int count_mounts(struct mnt_namespace *ns, struct mount *mnt) +{ + unsigned int max = READ_ONCE(sysctl_mount_max); + unsigned int mounts = 0, old, pending, sum; + struct mount *p; + + for (p = mnt; p; p = next_mnt(p, mnt)) + mounts++; + + old = ns->mounts; + pending = ns->pending_mounts; + sum = old + pending; + if ((old > sum) || + (pending > sum) || + (max < sum) || + (mounts > (max - sum))) + return -ENOSPC; + + ns->pending_mounts = pending + mounts; + return 0; +} + /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached @@ -1925,10 +1973,26 @@ static int attach_recursive_mnt(struct mount *source_mnt, struct path *parent_path) { HLIST_HEAD(tree_list); + struct mnt_namespace *ns = dest_mnt->mnt_ns; + struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; + /* Preallocate a mountpoint in case the new mounts need + * to be tucked under other mounts. + */ + smp = get_mountpoint(source_mnt->mnt.mnt_root); + if (IS_ERR(smp)) + return PTR_ERR(smp); + + /* Is there space to add these mounts to the mount namespace? */ + if (!parent_path) { + err = count_mounts(ns, source_mnt); + if (err) + goto out; + } + if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) @@ -1948,16 +2012,19 @@ static int attach_recursive_mnt(struct mount *source_mnt, touch_mnt_namespace(source_mnt->mnt_ns); } else { mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); - commit_tree(source_mnt, NULL); + commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); - q = __lookup_mnt_last(&child->mnt_parent->mnt, - child->mnt_mountpoint); - commit_tree(child, q); + q = __lookup_mnt(&child->mnt_parent->mnt, + child->mnt_mountpoint); + if (q) + mnt_change_mountpoint(child, smp, q); + commit_tree(child); } + put_mountpoint(smp); unlock_mount_hash(); return 0; @@ -1965,11 +2032,18 @@ static int attach_recursive_mnt(struct mount *source_mnt, out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); + child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: + ns->pending_mounts = 0; + + read_seqlock_excl(&mount_lock); + put_mountpoint(smp); + read_sequnlock_excl(&mount_lock); + return err; } @@ -2234,8 +2308,14 @@ static int do_remount(struct path *path, int flags, int mnt_flags, err = change_mount_flags(path->mnt, flags); else if (!capable(CAP_SYS_ADMIN)) err = -EPERM; - else - err = do_remount_sb(sb, flags, data, 0); + else { + err = do_remount_sb2(path->mnt, sb, flags, data, 0); + namespace_lock(); + lock_mount_hash(); + propagate_remount(mnt); + unlock_mount_hash(); + namespace_unlock(); + } if (!err) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; @@ -2795,6 +2875,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns) init_waitqueue_head(&new_ns->poll); new_ns->event = 0; new_ns->user_ns = get_user_ns(user_ns); + new_ns->mounts = 0; + new_ns->pending_mounts = 0; return new_ns; } @@ -2844,6 +2926,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, q = new; while (p) { q->mnt_ns = new_ns; + new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); @@ -2882,6 +2965,7 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m) struct mount *mnt = real_mount(m); mnt->mnt_ns = new_ns; new_ns->root = mnt; + new_ns->mounts++; list_add(&mnt->mnt_list, &new_ns->list); } else { mntput(m); diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index f31fd0dd92c6..b1daeafbea92 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -121,6 +121,7 @@ config PNFS_FILE_LAYOUT config PNFS_BLOCK tristate depends on NFS_V4_1 && BLK_DEV_DM + depends on 64BIT || LBDAF default NFS_V4 config PNFS_OBJLAYOUT diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 52ee0b73ab4a..348e0a05bd18 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1135,11 +1135,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) /* Force a full look up iff the parent directory has changed */ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) { - - if (nfs_lookup_verify_inode(inode, flags)) { + error = nfs_lookup_verify_inode(inode, flags); + if (error) { if (flags & LOOKUP_RCU) return -ECHILD; - goto out_zap_parent; + if (error == -ESTALE) + goto out_zap_parent; + goto out_error; } goto out_valid; } @@ -1163,8 +1165,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) trace_nfs_lookup_revalidate_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); - if (error) + if (error == -ESTALE || error == -ENOENT) goto out_bad; + if (error) + goto out_error; if (nfs_compare_fh(NFS_FH(inode), fhandle)) goto out_bad; if ((error = nfs_refresh_inode(inode, fattr)) != 0) @@ -2421,6 +2425,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) } EXPORT_SYMBOL_GPL(nfs_may_open); +static int nfs_execute_ok(struct inode *inode, int mask) +{ + struct nfs_server *server = NFS_SERVER(inode); + int ret; + + if (mask & MAY_NOT_BLOCK) + ret = nfs_revalidate_inode_rcu(server, inode); + else + ret = nfs_revalidate_inode(server, inode); + if (ret == 0 && !execute_ok(inode)) + ret = -EACCES; + return ret; +} + int nfs_permission(struct inode *inode, int mask) { struct rpc_cred *cred; @@ -2438,6 +2456,9 @@ int nfs_permission(struct inode *inode, int mask) case S_IFLNK: goto out; case S_IFREG: + if ((mask & MAY_OPEN) && + nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)) + return 0; break; case S_IFDIR: /* @@ -2470,8 +2491,8 @@ force_lookup: res = PTR_ERR(cred); } out: - if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) - res = -EACCES; + if (!res && (mask & MAY_EXEC)) + res = nfs_execute_ok(inode, mask); dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n", inode->i_sb->s_id, inode->i_ino, mask, res); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e125e55de86d..2603d7589946 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -30,6 +30,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds) { nfs4_print_deviceid(&mirror_ds->id_node.deviceid); nfs4_pnfs_ds_put(mirror_ds->ds); + kfree(mirror_ds->ds_versions); kfree_rcu(mirror_ds, id_node.rcu); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index f714b98cfd74..668ac19af58f 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1241,9 +1241,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat return 0; /* Has the inode gone and changed behind our back? */ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) - return -EIO; + return -ESTALE; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) - return -EIO; + return -ESTALE; if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && inode->i_version != fattr->change_attr) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3c69299c01ab..8e425f2c5ddd 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2188,8 +2188,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred, if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0) return 0; - /* even though OPEN succeeded, access is denied. Close the file */ - nfs4_close_state(state, fmode); return -EACCES; } @@ -2422,7 +2420,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, sattr->ia_valid |= ATTR_MTIME; /* Except MODE, it seems harmless of setting twice. */ - if ((attrset[1] & FATTR4_WORD1_MODE)) + if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE && + attrset[1] & FATTR4_WORD1_MODE) sattr->ia_valid &= ~ATTR_MODE; if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL) @@ -2451,6 +2450,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, ret = PTR_ERR(state); if (IS_ERR(state)) goto out; + ctx->state = state; if (server->caps & NFS_CAP_POSIX_LOCK) set_bit(NFS_STATE_POSIX_LOCKS, &state->flags); @@ -2473,7 +2473,6 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, if (ret != 0) goto out; - ctx->state = state; if (d_inode(dentry) == state->inode) { nfs_inode_attach_open_context(ctx); if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) @@ -4710,7 +4709,7 @@ out: */ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) { - struct page *pages[NFS4ACL_MAXPAGES] = {NULL, }; + struct page *pages[NFS4ACL_MAXPAGES + 1] = {NULL, }; struct nfs_getaclargs args = { .fh = NFS_FH(inode), .acl_pages = pages, @@ -4724,13 +4723,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu .rpc_argp = &args, .rpc_resp = &res, }; - unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); + unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1; int ret = -ENOMEM, i; - /* As long as we're doing a round trip to the server anyway, - * let's be prepared for a page of acl data. */ - if (npages == 0) - npages = 1; if (npages > ARRAY_SIZE(pages)) return -ERANGE; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 82dc3035ea45..e8d1d6c5000c 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1072,6 +1072,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) case -NFS4ERR_BADXDR: case -NFS4ERR_RESOURCE: case -NFS4ERR_NOFILEHANDLE: + case -NFS4ERR_MOVED: /* Non-seqid mutating errors */ return; }; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 4e4441216804..1cb50bb898b0 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2487,7 +2487,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); - replen = hdr.replen + op_decode_hdr_maxsz + 1; + replen = hdr.replen + op_decode_hdr_maxsz; encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr); xdr_inline_pages(&req->rq_rcv_buf, replen << 2, diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index c29d9421bd5e..0976f8dad4ce 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -50,7 +50,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, { struct nfsd4_layout_seg *seg = &args->lg_seg; struct super_block *sb = inode->i_sb; - u32 block_size = (1 << inode->i_blkbits); + u32 block_size = i_blocksize(inode); struct pnfs_block_extent *bex; struct iomap iomap; u32 device_generation = 0; @@ -151,7 +151,7 @@ nfsd4_block_proc_layoutcommit(struct inode *inode, int error; nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits); + lcp->lc_up_len, &iomaps, i_blocksize(inode)); if (nr_iomaps < 0) return nfserrno(nr_iomaps); diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 00575d776d91..7162ab7bc093 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -358,6 +358,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, { unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); + struct kvec *head = rqstp->rq_arg.head; p = decode_fh(p, &args->fh); if (!p) @@ -367,6 +368,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, args->count = ntohl(*p++); args->stable = ntohl(*p++); len = args->len = ntohl(*p++); + if ((void *)p > head->iov_base + head->iov_len) + return 0; /* * The count must equal the amount of data passed. */ @@ -377,9 +380,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Check to make sure that we got the right number of * bytes. */ - hdr = (void*)p - rqstp->rq_arg.head[0].iov_base; - dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len - - hdr; + hdr = (void*)p - head->iov_base; + dlen = head->iov_len + rqstp->rq_arg.page_len - hdr; /* * Round the length of the data which was specified up to * the next multiple of XDR units and then compare that @@ -396,7 +398,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, len = args->len = max_blocksize; } rqstp->rq_vec[0].iov_base = (void*)p; - rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr; + rqstp->rq_vec[0].iov_len = head->iov_len - hdr; v = 0; while (len > rqstp->rq_vec[v].iov_len) { len -= rqstp->rq_vec[v].iov_len; @@ -471,6 +473,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, /* first copy and check from the first page */ old = (char*)p; vec = &rqstp->rq_arg.head[0]; + if ((void *)old > vec->iov_base + vec->iov_len) + return 0; avail = vec->iov_len - (old - (char*)vec->iov_base); while (len && avail && *old) { *new++ = *old++; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index c9d6c715c0fb..9eed219f57a5 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -189,10 +189,11 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, struct nfs4_layout_stateid *ls; struct nfs4_stid *stp; - stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache); + stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache, + nfsd4_free_layout_stateid); if (!stp) return NULL; - stp->sc_free = nfsd4_free_layout_stateid; + get_nfs4_file(fp); stp->sc_file = fp; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 7d5351cd67fb..209dbfc50cd4 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1690,6 +1690,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, opdesc->op_get_currentstateid(cstate, &op->u); op->status = opdesc->op_func(rqstp, cstate, &op->u); + /* Only from SEQUENCE */ + if (cstate->status == nfserr_replay_cache) { + dprintk("%s NFS4.1 replay from cache\n", __func__); + status = op->status; + goto out; + } if (!op->status) { if (opdesc->op_set_currentstateid) opdesc->op_set_currentstateid(cstate, &op->u); @@ -1700,14 +1706,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, if (need_wrongsec_check(rqstp)) op->status = check_nfsd_access(current_fh->fh_export, rqstp); } - encode_op: - /* Only from SEQUENCE */ - if (cstate->status == nfserr_replay_cache) { - dprintk("%s NFS4.1 replay from cache\n", __func__); - status = op->status; - goto out; - } if (op->status == nfserr_replay_me) { op->replay = &cstate->replay_owner->so_replay; nfsd4_encode_replay(&resp->xdr, op); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 55638110cb06..c7f1ce41442a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -553,8 +553,8 @@ out: return co; } -struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, - struct kmem_cache *slab) +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, + void (*sc_free)(struct nfs4_stid *)) { struct nfs4_stid *stid; int new_id; @@ -570,6 +570,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, idr_preload_end(); if (new_id < 0) goto out_free; + + stid->sc_free = sc_free; stid->sc_client = cl; stid->sc_stateid.si_opaque.so_id = new_id; stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; @@ -595,15 +597,12 @@ out_free: static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) { struct nfs4_stid *stid; - struct nfs4_ol_stateid *stp; - stid = nfs4_alloc_stid(clp, stateid_slab); + stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid); if (!stid) return NULL; - stp = openlockstateid(stid); - stp->st_stid.sc_free = nfs4_free_ol_stateid; - return stp; + return openlockstateid(stid); } static void nfs4_free_deleg(struct nfs4_stid *stid) @@ -701,11 +700,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh, goto out_dec; if (delegation_blocked(¤t_fh->fh_handle)) goto out_dec; - dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab)); + dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); if (dp == NULL) goto out_dec; - dp->dl_stid.sc_free = nfs4_free_deleg; /* * delegation seqid's are never incremented. The 4.1 special * meaning of seqid 0 isn't meaningful, really, but let's avoid @@ -5396,7 +5394,6 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; - stp->st_stid.sc_free = nfs4_free_lock_stateid; stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; @@ -5439,7 +5436,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, lst = find_lock_stateid(lo, fi); if (lst == NULL) { spin_unlock(&clp->cl_lock); - ns = nfs4_alloc_stid(clp, stateid_slab); + ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid); if (ns == NULL) return NULL; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 12935209deca..3f68a25f2169 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2753,9 +2753,16 @@ out_acl: } #endif /* CONFIG_NFSD_PNFS */ if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { - status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0, - NFSD_SUPPATTR_EXCLCREAT_WORD1, - NFSD_SUPPATTR_EXCLCREAT_WORD2); + u32 supp[3]; + + supp[0] = nfsd_suppattrs0(minorversion); + supp[1] = nfsd_suppattrs1(minorversion); + supp[2] = nfsd_suppattrs2(minorversion); + supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; + supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; + supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; + + status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]); if (status) goto out; } @@ -4041,8 +4048,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getdeviceinfo *gdev) { struct xdr_stream *xdr = &resp->xdr; - const struct nfsd4_layout_ops *ops = - nfsd4_layout_ops[gdev->gd_layout_type]; + const struct nfsd4_layout_ops *ops; u32 starting_len = xdr->buf->len, needed_len; __be32 *p; @@ -4059,6 +4065,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, /* If maxcount is 0 then just update notifications */ if (gdev->gd_maxcount != 0) { + ops = nfsd4_layout_ops[gdev->gd_layout_type]; nfserr = ops->encode_getdeviceinfo(xdr, gdev); if (nfserr) { /* @@ -4111,8 +4118,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_layoutget *lgp) { struct xdr_stream *xdr = &resp->xdr; - const struct nfsd4_layout_ops *ops = - nfsd4_layout_ops[lgp->lg_layout_type]; + const struct nfsd4_layout_ops *ops; __be32 *p; dprintk("%s: err %d\n", __func__, nfserr); @@ -4135,6 +4141,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(lgp->lg_seg.iomode); *p++ = cpu_to_be32(lgp->lg_layout_type); + ops = nfsd4_layout_ops[lgp->lg_layout_type]; nfserr = ops->encode_layoutget(xdr, lgp); out: kfree(lgp->lg_content); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ad4e2377dd63..5be1fa6b676d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -656,6 +656,37 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr) return nfserr; } +/* + * A write procedure can have a large argument, and a read procedure can + * have a large reply, but no NFSv2 or NFSv3 procedure has argument and + * reply that can both be larger than a page. The xdr code has taken + * advantage of this assumption to be a sloppy about bounds checking in + * some cases. Pending a rewrite of the NFSv2/v3 xdr code to fix that + * problem, we enforce these assumptions here: + */ +static bool nfs_request_too_big(struct svc_rqst *rqstp, + struct svc_procedure *proc) +{ + /* + * The ACL code has more careful bounds-checking and is not + * susceptible to this problem: + */ + if (rqstp->rq_prog != NFS_PROGRAM) + return false; + /* + * Ditto NFSv4 (which can in theory have argument and reply both + * more than a page): + */ + if (rqstp->rq_vers >= 4) + return false; + /* The reply will be small, we're OK: */ + if (proc->pc_xdrressize > 0 && + proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE)) + return false; + + return rqstp->rq_arg.len > PAGE_SIZE; +} + int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { @@ -668,6 +699,11 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_vers, rqstp->rq_proc); proc = rqstp->rq_procinfo; + if (nfs_request_too_big(rqstp, proc)) { + dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers); + *statp = rpc_garbage_args; + return 1; + } /* * Give the xdr decoder a chance to change this if it wants * (necessary in the NFSv4.0 compound case) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 79d964aa8079..bf913201a6ad 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_writeargs *args) { unsigned int len, hdr, dlen; + struct kvec *head = rqstp->rq_arg.head; int v; p = decode_fh(p, &args->fh); @@ -300,9 +301,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Check to make sure that we got the right number of * bytes. */ - hdr = (void*)p - rqstp->rq_arg.head[0].iov_base; - dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len - - hdr; + hdr = (void*)p - head->iov_base; + if (hdr > head->iov_len) + return 0; + dlen = head->iov_len + rqstp->rq_arg.page_len - hdr; /* * Round the length of the data which was specified up to @@ -316,7 +318,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, return 0; rqstp->rq_vec[0].iov_base = (void*)p; - rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr; + rqstp->rq_vec[0].iov_len = head->iov_len - hdr; v = 0; while (len > rqstp->rq_vec[v].iov_len) { len -= rqstp->rq_vec[v].iov_len; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 77860b75da9d..5134eedcb16c 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -583,8 +583,8 @@ extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); -struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, - struct kmem_cache *slab); +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, + void (*sc_free)(struct nfs4_stid *)); void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 994d66fbb446..91e0c5429b4d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -369,7 +369,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, __be32 err; int host_err; bool get_write_count; - int size_change = 0; + bool size_change = (iap->ia_valid & ATTR_SIZE); if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; @@ -382,11 +382,11 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, /* Get inode */ err = fh_verify(rqstp, fhp, ftype, accmode); if (err) - goto out; + return err; if (get_write_count) { host_err = fh_want_write(fhp); if (host_err) - return nfserrno(host_err); + goto out; } dentry = fhp->fh_dentry; @@ -397,20 +397,28 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, iap->ia_valid &= ~ATTR_MODE; if (!iap->ia_valid) - goto out; + return 0; nfsd_sanitize_attrs(inode, iap); + if (check_guard && guardtime != inode->i_ctime.tv_sec) + return nfserr_notsync; + /* * The size case is special, it changes the file in addition to the - * attributes. + * attributes, and file systems don't expect it to be mixed with + * "random" attribute changes. We thus split out the size change + * into a separate call to ->setattr, and do the rest as a separate + * setattr call. */ - if (iap->ia_valid & ATTR_SIZE) { + if (size_change) { err = nfsd_get_write_access(rqstp, fhp, iap); if (err) - goto out; - size_change = 1; + return err; + } + fh_lock(fhp); + if (size_change) { /* * RFC5661, Section 18.30.4: * Changing the size of a file with SETATTR indirectly @@ -418,29 +426,36 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, * * (and similar for the older RFCs) */ - if (iap->ia_size != i_size_read(inode)) - iap->ia_valid |= ATTR_MTIME; - } + struct iattr size_attr = { + .ia_valid = ATTR_SIZE | ATTR_CTIME | ATTR_MTIME, + .ia_size = iap->ia_size, + }; - iap->ia_valid |= ATTR_CTIME; + host_err = notify_change(dentry, &size_attr, NULL); + if (host_err) + goto out_unlock; + iap->ia_valid &= ~ATTR_SIZE; - if (check_guard && guardtime != inode->i_ctime.tv_sec) { - err = nfserr_notsync; - goto out_put_write_access; + /* + * Avoid the additional setattr call below if the only other + * attribute that the client sends is the mtime, as we update + * it as part of the size change above. + */ + if ((iap->ia_valid & ~ATTR_MTIME) == 0) + goto out_unlock; } - fh_lock(fhp); + iap->ia_valid |= ATTR_CTIME; host_err = notify_change(dentry, iap, NULL); - fh_unlock(fhp); - err = nfserrno(host_err); -out_put_write_access: +out_unlock: + fh_unlock(fhp); if (size_change) put_write_access(inode); - if (!err) - err = nfserrno(commit_metadata(fhp)); out: - return err; + if (!host_err) + host_err = commit_metadata(fhp); + return nfserrno(host_err); } #if defined(CONFIG_NFSD_V4) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index a35ae35e6932..cd39b57288c2 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -55,7 +55,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) brelse(bh); BUG(); } - memset(bh->b_data, 0, 1 << inode->i_blkbits); + memset(bh->b_data, 0, i_blocksize(inode)); bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = blocknr; set_buffer_mapped(bh); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index ac2f64943ff4..00877ef0b120 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -55,7 +55,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; - inode_add_bytes(inode, (1 << inode->i_blkbits) * n); + inode_add_bytes(inode, i_blocksize(inode) * n); if (root) atomic64_add(n, &root->blocks_count); } @@ -64,7 +64,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; - inode_sub_bytes(inode, (1 << inode->i_blkbits) * n); + inode_sub_bytes(inode, i_blocksize(inode) * n); if (root) atomic64_sub(n, &root->blocks_count); } diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 1125f40233ff..612a2457243d 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -60,7 +60,7 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block, set_buffer_mapped(bh); kaddr = kmap_atomic(bh->b_page); - memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits); + memset(kaddr + bh_offset(bh), 0, i_blocksize(inode)); if (init_block) init_block(inode, bh, kaddr); flush_dcache_page(bh->b_page); @@ -503,7 +503,7 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size, struct nilfs_mdt_info *mi = NILFS_MDT(inode); mi->mi_entry_size = entry_size; - mi->mi_entries_per_block = (1 << inode->i_blkbits) / entry_size; + mi->mi_entries_per_block = i_blocksize(inode) / entry_size; mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size); } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 3b65adaae7e4..2f27c935bd57 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -719,7 +719,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, lock_page(page); if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << inode->i_blkbits, 0); + create_empty_buffers(page, i_blocksize(inode), 0); unlock_page(page); bh = head = page_buffers(page); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index a64313868d3a..2958e7a81f9c 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -488,7 +488,7 @@ static int fanotify_find_path(int dfd, const char __user *filename, } /* you can only watch an inode if you have read permissions on it */ - ret = inode_permission(path->dentry->d_inode, MAY_READ); + ret = inode_permission2(path->mnt, path->dentry->d_inode, MAY_READ); if (ret) path_put(path); out: diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index db39de2dd4cb..a64adc2fced9 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -104,16 +104,20 @@ int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) if (unlikely(!fsnotify_inode_watches_children(p_inode))) __fsnotify_update_child_dentry_flags(p_inode); else if (p_inode->i_fsnotify_mask & mask) { + struct name_snapshot name; + /* we are notifying a parent so come up with the new mask which * specifies these are events which came from a child. */ mask |= FS_EVENT_ON_CHILD; + take_dentry_name_snapshot(&name, dentry); if (path) ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH, - dentry->d_name.name, 0); + name.name, 0); else ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE, - dentry->d_name.name, 0); + name.name, 0); + release_dentry_name_snapshot(&name); } dput(parent); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index e2893f17dde2..4c5b43d15e6e 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -337,7 +337,7 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns if (error) return error; /* you can only watch an inode if you have read permissions on it */ - error = inode_permission(path->dentry->d_inode, MAY_READ); + error = inode_permission2(path->mnt, path->dentry->d_inode, MAY_READ); if (error) path_put(path); return error; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index e6795c7c76a8..e4184bd2a954 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1103,7 +1103,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, int ret = 0; struct buffer_head *head, *bh, *wait[2], **wait_bh = wait; unsigned int block_end, block_start; - unsigned int bsize = 1 << inode->i_blkbits; + unsigned int bsize = i_blocksize(inode); if (!page_has_buffers(page)) create_empty_buffers(page, bsize, 0); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 709fbbd44c65..acebc350e98d 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -2070,13 +2070,13 @@ unlock: spin_unlock(&o2hb_live_lock); } -static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item, +static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item, char *page) { return sprintf(page, "%u\n", o2hb_dead_threshold); } -static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item, +static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item, const char *page, size_t count) { unsigned long tmp; @@ -2125,11 +2125,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item, } -CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold); +CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold); CONFIGFS_ATTR(o2hb_heartbeat_group_, mode); static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = { - &o2hb_heartbeat_group_attr_threshold, + &o2hb_heartbeat_group_attr_dead_threshold, &o2hb_heartbeat_group_attr_mode, NULL, }; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 56dd3957cc91..1d738723a41a 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -808,7 +808,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, /* We know that zero_from is block aligned */ for (block_start = zero_from; block_start < zero_to; block_start = block_end) { - block_end = block_start + (1 << inode->i_blkbits); + block_end = block_start + i_blocksize(inode); /* * block_start is block-aligned. Bump it by one to force diff --git a/fs/open.c b/fs/open.c index 157b9940dd73..1fd96c5d3895 100644 --- a/fs/open.c +++ b/fs/open.c @@ -34,8 +34,8 @@ #include "internal.h" -int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, - struct file *filp) +int do_truncate2(struct vfsmount *mnt, struct dentry *dentry, loff_t length, + unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; @@ -60,17 +60,24 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, mutex_lock(&dentry->d_inode->i_mutex); /* Note any delegations or leases have already been broken: */ - ret = notify_change(dentry, &newattrs, NULL); + ret = notify_change2(mnt, dentry, &newattrs, NULL); mutex_unlock(&dentry->d_inode->i_mutex); return ret; } +int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, + struct file *filp) +{ + return do_truncate2(NULL, dentry, length, time_attrs, filp); +} long vfs_truncate(struct path *path, loff_t length) { struct inode *inode; + struct vfsmount *mnt; long error; inode = path->dentry->d_inode; + mnt = path->mnt; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) @@ -82,7 +89,7 @@ long vfs_truncate(struct path *path, loff_t length) if (error) goto out; - error = inode_permission(inode, MAY_WRITE); + error = inode_permission2(mnt, inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; @@ -106,7 +113,7 @@ long vfs_truncate(struct path *path, loff_t length) if (!error) error = security_path_truncate(path); if (!error) - error = do_truncate(path->dentry, length, 0, NULL); + error = do_truncate2(mnt, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); @@ -155,6 +162,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct inode *inode; struct dentry *dentry; + struct vfsmount *mnt; struct fd f; int error; @@ -171,6 +179,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) small = 0; dentry = f.file->f_path.dentry; + mnt = f.file->f_path.mnt; inode = dentry->d_inode; error = -EINVAL; if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE)) @@ -190,7 +199,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) if (!error) error = security_path_truncate(&f.file->f_path); if (!error) - error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); + error = do_truncate2(mnt, dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); sb_end_write(inode->i_sb); out_putf: fdput(f); @@ -340,6 +349,7 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) struct cred *override_cred; struct path path; struct inode *inode; + struct vfsmount *mnt; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; @@ -370,6 +380,7 @@ retry: goto out; inode = d_backing_inode(path.dentry); + mnt = path.mnt; if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* @@ -381,7 +392,7 @@ retry: goto out_path_release; } - res = inode_permission(inode, mode | MAY_ACCESS); + res = inode_permission2(mnt, inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; @@ -425,7 +436,7 @@ retry: if (error) goto out; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = inode_permission2(path.mnt, path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; @@ -445,6 +456,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); struct inode *inode; + struct vfsmount *mnt; int error = -EBADF; error = -EBADF; @@ -452,12 +464,13 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) goto out; inode = file_inode(f.file); + mnt = f.file->f_path.mnt; error = -ENOTDIR; if (!S_ISDIR(inode->i_mode)) goto out_putf; - error = inode_permission(inode, MAY_EXEC | MAY_CHDIR); + error = inode_permission2(mnt, inode, MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &f.file->f_path); out_putf: @@ -476,7 +489,7 @@ retry: if (error) goto out; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = inode_permission2(path.mnt, path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; @@ -516,7 +529,7 @@ retry_deleg: goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode); out_unlock: mutex_unlock(&inode->i_mutex); if (delegated_inode) { @@ -596,7 +609,7 @@ retry_deleg: mutex_lock(&inode->i_mutex); error = security_path_chown(path, uid, gid); if (!error) - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode); mutex_unlock(&inode->i_mutex); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); @@ -885,6 +898,12 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o int lookup_flags = 0; int acc_mode; + /* + * Clear out all open flags we don't know about so that we don't report + * them in fcntl(F_GETFD) or similar interfaces. + */ + flags &= VALID_OPEN_FLAGS; + if (flags & (O_CREAT | __O_TMPFILE)) op->mode = (mode & S_IALLUGO) | S_IFREG; else diff --git a/fs/pnode.c b/fs/pnode.c index 99899705b105..1cafb8c2bdb0 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p) return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave); } +static inline struct mount *last_slave(struct mount *p) +{ + return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave); +} + static inline struct mount *next_slave(struct mount *p) { return list_entry(p->mnt_slave.next, struct mount, mnt_slave); @@ -164,6 +169,19 @@ static struct mount *propagation_next(struct mount *m, } } +static struct mount *skip_propagation_subtree(struct mount *m, + struct mount *origin) +{ + /* + * Advance m such that propagation_next will not return + * the slaves of m. + */ + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + m = last_slave(m); + + return m; +} + static struct mount *next_group(struct mount *m, struct mount *origin) { while (1) { @@ -259,7 +277,7 @@ static int propagate_one(struct mount *m) read_sequnlock_excl(&mount_lock); } hlist_add_head(&child->mnt_hash, list); - return 0; + return count_mounts(m->mnt_ns, child); } /* @@ -324,6 +342,21 @@ out: return ret; } +static struct mount *find_topper(struct mount *mnt) +{ + /* If there is exactly one mount covering mnt completely return it. */ + struct mount *child; + + if (!list_is_singular(&mnt->mnt_mounts)) + return NULL; + + child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child); + if (child->mnt_mountpoint != mnt->mnt.mnt_root) + return NULL; + + return child; +} + /* * return true if the refcount is greater than count */ @@ -344,9 +377,8 @@ static inline int do_refcount_check(struct mount *mnt, int count) */ int propagate_mount_busy(struct mount *mnt, int refcnt) { - struct mount *m, *child; + struct mount *m, *child, *topper; struct mount *parent = mnt->mnt_parent; - int ret = 0; if (mnt == parent) return do_refcount_check(mnt, refcnt); @@ -361,12 +393,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); - if (child && list_empty(&child->mnt_mounts) && - (ret = do_refcount_check(child, 1))) - break; + int count = 1; + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); + if (!child) + continue; + + /* Is there exactly one mount on the child that covers + * it completely whose reference should be ignored? + */ + topper = find_topper(child); + if (topper) + count += 1; + else if (!list_empty(&child->mnt_mounts)) + continue; + + if (do_refcount_check(child, count)) + return 1; } - return ret; + return 0; } /* @@ -383,63 +427,113 @@ void propagate_mount_unlock(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); if (child) child->mnt.mnt_flags &= ~MNT_LOCKED; } } -/* - * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted. - */ -static void mark_umount_candidates(struct mount *mnt) +static void umount_one(struct mount *mnt, struct list_head *to_umount) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; - - BUG_ON(parent == mnt); - - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { - struct mount *child = __lookup_mnt_last(&m->mnt, - mnt->mnt_mountpoint); - if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) { - SET_MNT_MARK(child); - } - } + CLEAR_MNT_MARK(mnt); + mnt->mnt.mnt_flags |= MNT_UMOUNT; + list_del_init(&mnt->mnt_child); + list_del_init(&mnt->mnt_umounting); + list_move_tail(&mnt->mnt_list, to_umount); } /* * NOTE: unmounting 'mnt' naturally propagates to all other mounts its * parent propagates to. */ -static void __propagate_umount(struct mount *mnt) +static bool __propagate_umount(struct mount *mnt, + struct list_head *to_umount, + struct list_head *to_restore) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; - - BUG_ON(parent == mnt); + bool progress = false; + struct mount *child; - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { + /* + * The state of the parent won't change if this mount is + * already unmounted or marked as without children. + */ + if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED)) + goto out; - struct mount *child = __lookup_mnt_last(&m->mnt, - mnt->mnt_mountpoint); - /* - * umount the child only if the child has no children - * and the child is marked safe to unmount. - */ - if (!child || !IS_MNT_MARKED(child)) + /* Verify topper is the only grandchild that has not been + * speculatively unmounted. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (child->mnt_mountpoint == mnt->mnt.mnt_root) + continue; + if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child)) continue; - CLEAR_MNT_MARK(child); - if (list_empty(&child->mnt_mounts)) { - list_del_init(&child->mnt_child); - child->mnt.mnt_flags |= MNT_UMOUNT; - list_move_tail(&child->mnt_list, &mnt->mnt_list); + /* Found a mounted child */ + goto children; + } + + /* Mark mounts that can be unmounted if not locked */ + SET_MNT_MARK(mnt); + progress = true; + + /* If a mount is without children and not locked umount it. */ + if (!IS_MNT_LOCKED(mnt)) { + umount_one(mnt, to_umount); + } else { +children: + list_move_tail(&mnt->mnt_umounting, to_restore); + } +out: + return progress; +} + +static void umount_list(struct list_head *to_umount, + struct list_head *to_restore) +{ + struct mount *mnt, *child, *tmp; + list_for_each_entry(mnt, to_umount, mnt_list) { + list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) { + /* topper? */ + if (child->mnt_mountpoint == mnt->mnt.mnt_root) + list_move_tail(&child->mnt_umounting, to_restore); + else + umount_one(child, to_umount); } } } +static void restore_mounts(struct list_head *to_restore) +{ + /* Restore mounts to a clean working state */ + while (!list_empty(to_restore)) { + struct mount *mnt, *parent; + struct mountpoint *mp; + + mnt = list_first_entry(to_restore, struct mount, mnt_umounting); + CLEAR_MNT_MARK(mnt); + list_del_init(&mnt->mnt_umounting); + + /* Should this mount be reparented? */ + mp = mnt->mnt_mp; + parent = mnt->mnt_parent; + while (parent->mnt.mnt_flags & MNT_UMOUNT) { + mp = parent->mnt_mp; + parent = parent->mnt_parent; + } + if (parent != mnt->mnt_parent) + mnt_change_mountpoint(parent, mp, mnt); + } +} + +static void cleanup_umount_visitations(struct list_head *visited) +{ + while (!list_empty(visited)) { + struct mount *mnt = + list_first_entry(visited, struct mount, mnt_umounting); + list_del_init(&mnt->mnt_umounting); + } +} + /* * collect all mounts that receive propagation from the mount in @list, * and return these additional mounts in the same list. @@ -450,11 +544,97 @@ static void __propagate_umount(struct mount *mnt) int propagate_umount(struct list_head *list) { struct mount *mnt; + LIST_HEAD(to_restore); + LIST_HEAD(to_umount); + LIST_HEAD(visited); - list_for_each_entry_reverse(mnt, list, mnt_list) - mark_umount_candidates(mnt); + /* Find candidates for unmounting */ + list_for_each_entry_reverse(mnt, list, mnt_list) { + struct mount *parent = mnt->mnt_parent; + struct mount *m; + + /* + * If this mount has already been visited it is known that it's + * entire peer group and all of their slaves in the propagation + * tree for the mountpoint has already been visited and there is + * no need to visit them again. + */ + if (!list_empty(&mnt->mnt_umounting)) + continue; + + list_add_tail(&mnt->mnt_umounting, &visited); + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + struct mount *child = __lookup_mnt(&m->mnt, + mnt->mnt_mountpoint); + if (!child) + continue; + + if (!list_empty(&child->mnt_umounting)) { + /* + * If the child has already been visited it is + * know that it's entire peer group and all of + * their slaves in the propgation tree for the + * mountpoint has already been visited and there + * is no need to visit this subtree again. + */ + m = skip_propagation_subtree(m, parent); + continue; + } else if (child->mnt.mnt_flags & MNT_UMOUNT) { + /* + * We have come accross an partially unmounted + * mount in list that has not been visited yet. + * Remember it has been visited and continue + * about our merry way. + */ + list_add_tail(&child->mnt_umounting, &visited); + continue; + } + + /* Check the child and parents while progress is made */ + while (__propagate_umount(child, + &to_umount, &to_restore)) { + /* Is the parent a umount candidate? */ + child = child->mnt_parent; + if (list_empty(&child->mnt_umounting)) + break; + } + } + } + + umount_list(&to_umount, &to_restore); + restore_mounts(&to_restore); + cleanup_umount_visitations(&visited); + list_splice_tail(&to_umount, list); - list_for_each_entry(mnt, list, mnt_list) - __propagate_umount(mnt); return 0; } + +/* + * Iterates over all slaves, and slaves of slaves. + */ +static struct mount *next_descendent(struct mount *root, struct mount *cur) +{ + if (!IS_MNT_NEW(cur) && !list_empty(&cur->mnt_slave_list)) + return first_slave(cur); + do { + if (cur->mnt_slave.next != &cur->mnt_master->mnt_slave_list) + return next_slave(cur); + cur = cur->mnt_master; + } while (cur != root); + return NULL; +} + +void propagate_remount(struct mount *mnt) +{ + struct mount *m = mnt; + struct super_block *sb = mnt->mnt.mnt_sb; + + if (sb->s_op->copy_mnt_data) { + m = next_descendent(mnt, m); + while (m) { + sb->s_op->copy_mnt_data(m->mnt.data, mnt->mnt.data); + m = next_descendent(mnt, m); + } + } +} diff --git a/fs/pnode.h b/fs/pnode.h index 0fcdbe7ca648..a9a6576540ad 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -44,12 +44,16 @@ int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, int propagate_umount(struct list_head *); int propagate_mount_busy(struct mount *, int); void propagate_mount_unlock(struct mount *); +void propagate_remount(struct mount *); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); unsigned int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, + struct mount *mnt); struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); +int count_mounts(struct mnt_namespace *ns, struct mount *mnt); #endif /* _LINUX_PNODE_H */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 0c9ea52ab399..deafb880368b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3145,6 +3145,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) iter.tgid += 1, iter = next_tgid(ns, iter)) { char name[PROC_NUMBUF]; int len; + + cond_resched(); if (!has_pid_permissions(ns, iter.task, 2)) continue; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index ff3ffc76a937..3773335791da 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -469,6 +469,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent->data = NULL; ent->proc_fops = NULL; ent->proc_iops = NULL; + parent->nlink++; if (proc_register(parent, ent) < 0) { kfree(ent); parent->nlink--; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 200e3b29aa22..38be952b2fe7 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -345,11 +345,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; - if (stack_guard_page_start(vma, start)) - start += PAGE_SIZE; end = vma->vm_end; - if (stack_guard_page_end(vma, end)) - end -= PAGE_SIZE; seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", @@ -865,7 +861,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp); + pmd_t pmd = *pmdp; + + /* See comment in change_huge_pmd() */ + pmdp_invalidate(vma, addr, pmdp); + if (pmd_dirty(*pmdp)) + pmd = pmd_mkdirty(pmd); + if (pmd_young(*pmdp)) + pmd = pmd_mkyoung(pmd); pmd = pmd_wrprotect(pmd); pmd = pmd_clear_soft_dirty(pmd); diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 87645955990d..961e597acfc6 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -118,7 +118,9 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) if (err) goto out; show_mnt_opts(m, mnt); - if (sb->s_op->show_options) + if (sb->s_op->show_options2) + err = sb->s_op->show_options2(mnt, m, mnt_path.dentry); + else if (sb->s_op->show_options) err = sb->s_op->show_options(m, mnt_path.dentry); seq_puts(m, " 0 0\n"); out: @@ -178,7 +180,9 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) err = show_sb_opts(m, sb); if (err) goto out; - if (sb->s_op->show_options) + if (sb->s_op->show_options2) { + err = sb->s_op->show_options2(mnt, m, mnt->mnt_root); + } else if (sb->s_op->show_options) err = sb->s_op->show_options(m, mnt->mnt_root); seq_putc(m, '\n'); out: diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 8d1e5e2db6a1..c9e4bc47c79d 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -434,7 +434,7 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, for (i = 0; i < cxt->max_dump_cnt; i++) { cxt->przs[i] = persistent_ram_new(*paddr, cxt->record_size, 0, &cxt->ecc_info, - cxt->memtype); + cxt->memtype, 0); if (IS_ERR(cxt->przs[i])) { err = PTR_ERR(cxt->przs[i]); dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", @@ -471,7 +471,8 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt, return -ENOMEM; } - *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype); + *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, + cxt->memtype, 0); if (IS_ERR(*prz)) { int err = PTR_ERR(*prz); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 3975deec02f8..e11672aa4575 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -48,16 +48,15 @@ static inline size_t buffer_start(struct persistent_ram_zone *prz) return atomic_read(&prz->buffer->start); } -static DEFINE_RAW_SPINLOCK(buffer_lock); - /* increase and wrap the start pointer, returning the old value */ static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a) { int old; int new; - unsigned long flags; + unsigned long flags = 0; - raw_spin_lock_irqsave(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_lock_irqsave(&prz->buffer_lock, flags); old = atomic_read(&prz->buffer->start); new = old + a; @@ -65,7 +64,8 @@ static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a) new -= prz->buffer_size; atomic_set(&prz->buffer->start, new); - raw_spin_unlock_irqrestore(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_unlock_irqrestore(&prz->buffer_lock, flags); return old; } @@ -75,9 +75,10 @@ static void buffer_size_add(struct persistent_ram_zone *prz, size_t a) { size_t old; size_t new; - unsigned long flags; + unsigned long flags = 0; - raw_spin_lock_irqsave(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_lock_irqsave(&prz->buffer_lock, flags); old = atomic_read(&prz->buffer->size); if (old == prz->buffer_size) @@ -89,7 +90,8 @@ static void buffer_size_add(struct persistent_ram_zone *prz, size_t a) atomic_set(&prz->buffer->size, new); exit: - raw_spin_unlock_irqrestore(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_unlock_irqrestore(&prz->buffer_lock, flags); } static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz, @@ -491,6 +493,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, prz->buffer->sig); } + /* Rewind missing or invalid memory area. */ prz->buffer->sig = sig; persistent_ram_zap(prz); @@ -517,7 +520,7 @@ void persistent_ram_free(struct persistent_ram_zone *prz) struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype) + unsigned int memtype, u32 flags) { struct persistent_ram_zone *prz; int ret = -ENOMEM; @@ -528,6 +531,10 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, goto err; } + /* Initialize general buffer state. */ + raw_spin_lock_init(&prz->buffer_lock); + prz->flags = flags; + ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) goto err; diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 8f5ccdf81c25..38187300a2b4 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -189,7 +189,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page, int ret = 0; th.t_trans_id = 0; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); if (logit) { reiserfs_write_lock(s); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 3d8e7e671d5b..60ba35087d12 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -524,7 +524,7 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode, * referenced in convert_tail_for_hole() that may be called from * reiserfs_get_block() */ - bh_result->b_size = (1 << inode->i_blkbits); + bh_result->b_size = i_blocksize(inode); ret = reiserfs_get_block(inode, iblock, bh_result, create | GET_BLOCK_NO_DANGLE); diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 268733cda397..5f4f1882dc7d 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -74,6 +74,7 @@ #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/uaccess.h> +#include <linux/major.h> #include "internal.h" static struct kmem_cache *romfs_inode_cachep; @@ -415,7 +416,22 @@ static void romfs_destroy_inode(struct inode *inode) static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; - u64 id = huge_encode_dev(sb->s_bdev->bd_dev); + u64 id = 0; + + /* When calling huge_encode_dev(), + * use sb->s_bdev->bd_dev when, + * - CONFIG_ROMFS_ON_BLOCK defined + * use sb->s_dev when, + * - CONFIG_ROMFS_ON_BLOCK undefined and + * - CONFIG_ROMFS_ON_MTD defined + * leave id as 0 when, + * - CONFIG_ROMFS_ON_BLOCK undefined and + * - CONFIG_ROMFS_ON_MTD undefined + */ + if (sb->s_bdev) + id = huge_encode_dev(sb->s_bdev->bd_dev); + else if (sb->s_dev) + id = huge_encode_dev(sb->s_dev); buf->f_type = ROMFS_MAGIC; buf->f_namelen = ROMFS_MAXFN; @@ -488,6 +504,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= MS_RDONLY | MS_NOATIME; sb->s_op = &romfs_super_ops; +#ifdef CONFIG_ROMFS_ON_MTD + /* Use same dev ID from the underlying mtdblock device */ + if (sb->s_mtd) + sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index); +#endif /* read the image superblock and check it */ rsb = kmalloc(512, GFP_KERNEL); if (!rsb) diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c index 971928ab6c21..7a19e77fce99 100644 --- a/fs/sdcardfs/dentry.c +++ b/fs/sdcardfs/dentry.c @@ -46,7 +46,8 @@ static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags) spin_unlock(&dentry->d_lock); /* check uninitialized obb_dentry and - * whether the base obbpath has been changed or not */ + * whether the base obbpath has been changed or not + */ if (is_obbpath_invalid(dentry)) { d_drop(dentry); return 0; @@ -59,6 +60,14 @@ static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags) lower_dentry = lower_path.dentry; lower_cur_parent_dentry = dget_parent(lower_dentry); + if ((lower_dentry->d_flags & DCACHE_OP_REVALIDATE)) { + err = lower_dentry->d_op->d_revalidate(lower_dentry, flags); + if (err == 0) { + d_drop(dentry); + goto out; + } + } + spin_lock(&lower_dentry->d_lock); if (d_unhashed(lower_dentry)) { spin_unlock(&lower_dentry->d_lock); @@ -76,17 +85,13 @@ static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags) if (dentry < lower_dentry) { spin_lock(&dentry->d_lock); - spin_lock(&lower_dentry->d_lock); + spin_lock_nested(&lower_dentry->d_lock, DENTRY_D_LOCK_NESTED); } else { spin_lock(&lower_dentry->d_lock); - spin_lock(&dentry->d_lock); + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); } - if (dentry->d_name.len != lower_dentry->d_name.len) { - __d_drop(dentry); - err = 0; - } else if (strncasecmp(dentry->d_name.name, lower_dentry->d_name.name, - dentry->d_name.len) != 0) { + if (!qstr_case_eq(&dentry->d_name, &lower_dentry->d_name)) { __d_drop(dentry); err = 0; } @@ -110,12 +115,10 @@ out: static void sdcardfs_d_release(struct dentry *dentry) { /* release and reset the lower paths */ - if(has_graft_path(dentry)) { + if (has_graft_path(dentry)) sdcardfs_put_reset_orig_path(dentry); - } sdcardfs_put_reset_lower_path(dentry); free_dentry_private_data(dentry); - return; } static int sdcardfs_hash_ci(const struct dentry *dentry, @@ -132,12 +135,10 @@ static int sdcardfs_hash_ci(const struct dentry *dentry, unsigned long hash; name = qstr->name; - //len = vfat_striptail_len(qstr); len = qstr->len; hash = init_name_hash(); while (len--) - //hash = partial_name_hash(nls_tolower(t, *name++), hash); hash = partial_name_hash(tolower(*name++), hash); qstr->hash = end_name_hash(hash); @@ -151,35 +152,25 @@ static int sdcardfs_cmp_ci(const struct dentry *parent, const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { - /* This function is copy of vfat_cmpi */ - // FIXME Should we support national language? - //struct nls_table *t = MSDOS_SB(parent->d_sb)->nls_io; - //unsigned int alen, blen; + /* FIXME Should we support national language? */ - /* A filename cannot end in '.' or we treat it like it has none */ - /* - alen = vfat_striptail_len(name); - blen = __vfat_striptail_len(len, str); - if (alen == blen) { - if (nls_strnicmp(t, name->name, str, alen) == 0) - return 0; - } - */ if (name->len == len) { - if (strncasecmp(name->name, str, len) == 0) + if (str_n_case_eq(name->name, str, len)) return 0; } return 1; } -static void sdcardfs_canonical_path(const struct path *path, struct path *actual_path) { +static void sdcardfs_canonical_path(const struct path *path, + struct path *actual_path) +{ sdcardfs_get_real_lower(path->dentry, actual_path); } const struct dentry_operations sdcardfs_ci_dops = { .d_revalidate = sdcardfs_d_revalidate, .d_release = sdcardfs_d_release, - .d_hash = sdcardfs_hash_ci, + .d_hash = sdcardfs_hash_ci, .d_compare = sdcardfs_cmp_ci, .d_canonical_path = sdcardfs_canonical_path, }; diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c index 41e0e11b3c35..b4595aab5713 100644 --- a/fs/sdcardfs/derived_perm.c +++ b/fs/sdcardfs/derived_perm.c @@ -30,11 +30,15 @@ static void inherit_derived_state(struct inode *parent, struct inode *child) ci->userid = pi->userid; ci->d_uid = pi->d_uid; ci->under_android = pi->under_android; + ci->under_cache = pi->under_cache; + ci->under_obb = pi->under_obb; + set_top(ci, pi->top); } /* helper function for derived state */ -void setup_derived_state(struct inode *inode, perm_t perm, - userid_t userid, uid_t uid, bool under_android) +void setup_derived_state(struct inode *inode, perm_t perm, userid_t userid, + uid_t uid, bool under_android, + struct inode *top) { struct sdcardfs_inode_info *info = SDCARDFS_I(inode); @@ -42,84 +46,276 @@ void setup_derived_state(struct inode *inode, perm_t perm, info->userid = userid; info->d_uid = uid; info->under_android = under_android; + info->under_cache = false; + info->under_obb = false; + set_top(info, top); } -/* While renaming, there is a point where we want the path from dentry, but the name from newdentry */ -void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry) +/* While renaming, there is a point where we want the path from dentry, + * but the name from newdentry + */ +void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, + const struct qstr *name) { - struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); - struct sdcardfs_inode_info *info = SDCARDFS_I(dentry->d_inode); - struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + struct sdcardfs_inode_info *info = SDCARDFS_I(d_inode(dentry)); + struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent)); appid_t appid; + unsigned long user_num; + int err; + struct qstr q_Android = QSTR_LITERAL("Android"); + struct qstr q_data = QSTR_LITERAL("data"); + struct qstr q_obb = QSTR_LITERAL("obb"); + struct qstr q_media = QSTR_LITERAL("media"); + struct qstr q_cache = QSTR_LITERAL("cache"); /* By default, each inode inherits from its parent. * the properties are maintained on its private fields * because the inode attributes will be modified with that of * its lower inode. - * The derived state will be updated on the last - * stage of each system call by fix_derived_permission(inode). + * These values are used by our custom permission call instead + * of using the inode permissions. */ - inherit_derived_state(parent->d_inode, dentry->d_inode); + inherit_derived_state(d_inode(parent), d_inode(dentry)); + /* Files don't get special labels */ + if (!S_ISDIR(d_inode(dentry)->i_mode)) + return; /* Derive custom permissions based on parent and current node */ switch (parent_info->perm) { - case PERM_INHERIT: - /* Already inherited above */ - break; - case PERM_PRE_ROOT: - /* Legacy internal layout places users at top level */ - info->perm = PERM_ROOT; - info->userid = simple_strtoul(newdentry->d_name.name, NULL, 10); - break; - case PERM_ROOT: - /* Assume masked off by default. */ - if (!strcasecmp(newdentry->d_name.name, "Android")) { - /* App-specific directories inside; let anyone traverse */ - info->perm = PERM_ANDROID; - info->under_android = true; - } - break; - case PERM_ANDROID: - if (!strcasecmp(newdentry->d_name.name, "data")) { - /* App-specific directories inside; let anyone traverse */ - info->perm = PERM_ANDROID_DATA; - } else if (!strcasecmp(newdentry->d_name.name, "obb")) { - /* App-specific directories inside; let anyone traverse */ - info->perm = PERM_ANDROID_OBB; - /* Single OBB directory is always shared */ - } else if (!strcasecmp(newdentry->d_name.name, "media")) { - /* App-specific directories inside; let anyone traverse */ - info->perm = PERM_ANDROID_MEDIA; - } - break; - case PERM_ANDROID_DATA: - case PERM_ANDROID_OBB: - case PERM_ANDROID_MEDIA: - appid = get_appid(sbi->pkgl_id, newdentry->d_name.name); - if (appid != 0) { - info->d_uid = multiuser_get_uid(parent_info->userid, appid); - } - break; + case PERM_INHERIT: + case PERM_ANDROID_PACKAGE_CACHE: + /* Already inherited above */ + break; + case PERM_PRE_ROOT: + /* Legacy internal layout places users at top level */ + info->perm = PERM_ROOT; + err = kstrtoul(name->name, 10, &user_num); + if (err) + info->userid = 0; + else + info->userid = user_num; + set_top(info, &info->vfs_inode); + break; + case PERM_ROOT: + /* Assume masked off by default. */ + if (qstr_case_eq(name, &q_Android)) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID; + info->under_android = true; + set_top(info, &info->vfs_inode); + } + break; + case PERM_ANDROID: + if (qstr_case_eq(name, &q_data)) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_DATA; + set_top(info, &info->vfs_inode); + } else if (qstr_case_eq(name, &q_obb)) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_OBB; + info->under_obb = true; + set_top(info, &info->vfs_inode); + /* Single OBB directory is always shared */ + } else if (qstr_case_eq(name, &q_media)) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_MEDIA; + set_top(info, &info->vfs_inode); + } + break; + case PERM_ANDROID_OBB: + case PERM_ANDROID_DATA: + case PERM_ANDROID_MEDIA: + info->perm = PERM_ANDROID_PACKAGE; + appid = get_appid(name->name); + if (appid != 0 && !is_excluded(name->name, parent_info->userid)) + info->d_uid = multiuser_get_uid(parent_info->userid, appid); + set_top(info, &info->vfs_inode); + break; + case PERM_ANDROID_PACKAGE: + if (qstr_case_eq(name, &q_cache)) { + info->perm = PERM_ANDROID_PACKAGE_CACHE; + info->under_cache = true; + } + break; } } void get_derived_permission(struct dentry *parent, struct dentry *dentry) { - get_derived_permission_new(parent, dentry, dentry); + get_derived_permission_new(parent, dentry, &dentry->d_name); } -void get_derive_permissions_recursive(struct dentry *parent) { - struct dentry *dentry; - list_for_each_entry(dentry, &parent->d_subdirs, d_child) { - if (dentry->d_inode) { - mutex_lock(&dentry->d_inode->i_mutex); - get_derived_permission(parent, dentry); - fix_derived_permission(dentry->d_inode); - get_derive_permissions_recursive(dentry); - mutex_unlock(&dentry->d_inode->i_mutex); +static appid_t get_type(const char *name) +{ + const char *ext = strrchr(name, '.'); + appid_t id; + + if (ext && ext[0]) { + ext = &ext[1]; + id = get_ext_gid(ext); + return id?:AID_MEDIA_RW; + } + return AID_MEDIA_RW; +} + +void fixup_lower_ownership(struct dentry *dentry, const char *name) +{ + struct path path; + struct inode *inode; + struct inode *delegated_inode = NULL; + int error; + struct sdcardfs_inode_info *info; + struct sdcardfs_inode_info *info_top; + perm_t perm; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + uid_t uid = sbi->options.fs_low_uid; + gid_t gid = sbi->options.fs_low_gid; + struct iattr newattrs; + + info = SDCARDFS_I(d_inode(dentry)); + perm = info->perm; + if (info->under_obb) { + perm = PERM_ANDROID_OBB; + } else if (info->under_cache) { + perm = PERM_ANDROID_PACKAGE_CACHE; + } else if (perm == PERM_INHERIT) { + info_top = SDCARDFS_I(grab_top(info)); + perm = info_top->perm; + release_top(info); + } + + switch (perm) { + case PERM_ROOT: + case PERM_ANDROID: + case PERM_ANDROID_DATA: + case PERM_ANDROID_MEDIA: + case PERM_ANDROID_PACKAGE: + case PERM_ANDROID_PACKAGE_CACHE: + uid = multiuser_get_uid(info->userid, uid); + break; + case PERM_ANDROID_OBB: + uid = AID_MEDIA_OBB; + break; + case PERM_PRE_ROOT: + default: + break; + } + switch (perm) { + case PERM_ROOT: + case PERM_ANDROID: + case PERM_ANDROID_DATA: + case PERM_ANDROID_MEDIA: + if (S_ISDIR(d_inode(dentry)->i_mode)) + gid = multiuser_get_uid(info->userid, AID_MEDIA_RW); + else + gid = multiuser_get_uid(info->userid, get_type(name)); + break; + case PERM_ANDROID_OBB: + gid = AID_MEDIA_OBB; + break; + case PERM_ANDROID_PACKAGE: + if (uid_is_app(info->d_uid)) + gid = multiuser_get_ext_gid(info->d_uid); + else + gid = multiuser_get_uid(info->userid, AID_MEDIA_RW); + break; + case PERM_ANDROID_PACKAGE_CACHE: + if (uid_is_app(info->d_uid)) + gid = multiuser_get_ext_cache_gid(info->d_uid); + else + gid = multiuser_get_uid(info->userid, AID_MEDIA_RW); + break; + case PERM_PRE_ROOT: + default: + break; + } + + sdcardfs_get_lower_path(dentry, &path); + inode = d_inode(path.dentry); + if (d_inode(path.dentry)->i_gid.val != gid || d_inode(path.dentry)->i_uid.val != uid) { +retry_deleg: + newattrs.ia_valid = ATTR_GID | ATTR_UID | ATTR_FORCE; + newattrs.ia_uid = make_kuid(current_user_ns(), uid); + newattrs.ia_gid = make_kgid(current_user_ns(), gid); + if (!S_ISDIR(inode->i_mode)) + newattrs.ia_valid |= + ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; + mutex_lock(&inode->i_mutex); + error = security_path_chown(&path, newattrs.ia_uid, newattrs.ia_gid); + if (!error) + error = notify_change2(path.mnt, path.dentry, &newattrs, &delegated_inode); + mutex_unlock(&inode->i_mutex); + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; } + if (error) + pr_debug("sdcardfs: Failed to touch up lower fs gid/uid for %s\n", name); } + sdcardfs_put_lower_path(dentry, &path); +} + +static int descendant_may_need_fixup(struct sdcardfs_inode_info *info, struct limit_search *limit) +{ + if (info->perm == PERM_ROOT) + return (limit->flags & BY_USERID)?info->userid == limit->userid:1; + if (info->perm == PERM_PRE_ROOT || info->perm == PERM_ANDROID) + return 1; + return 0; +} + +static int needs_fixup(perm_t perm) +{ + if (perm == PERM_ANDROID_DATA || perm == PERM_ANDROID_OBB + || perm == PERM_ANDROID_MEDIA) + return 1; + return 0; +} + +static void __fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit, int depth) +{ + struct dentry *child; + struct sdcardfs_inode_info *info; + + /* + * All paths will terminate their recursion on hitting PERM_ANDROID_OBB, + * PERM_ANDROID_MEDIA, or PERM_ANDROID_DATA. This happens at a depth of + * at most 3. + */ + WARN(depth > 3, "%s: Max expected depth exceeded!\n", __func__); + spin_lock_nested(&dentry->d_lock, depth); + if (!d_inode(dentry)) { + spin_unlock(&dentry->d_lock); + return; + } + info = SDCARDFS_I(d_inode(dentry)); + + if (needs_fixup(info->perm)) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { + spin_lock_nested(&child->d_lock, depth + 1); + if (!(limit->flags & BY_NAME) || qstr_case_eq(&child->d_name, &limit->name)) { + if (d_inode(child)) { + get_derived_permission(dentry, child); + fixup_tmp_permissions(d_inode(child)); + spin_unlock(&child->d_lock); + break; + } + } + spin_unlock(&child->d_lock); + } + } else if (descendant_may_need_fixup(info, limit)) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { + __fixup_perms_recursive(child, limit, depth + 1); + } + } + spin_unlock(&dentry->d_lock); +} + +void fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit) +{ + __fixup_perms_recursive(dentry, limit, 0); } /* main function for updating derived permission */ @@ -127,40 +323,37 @@ inline void update_derived_permission_lock(struct dentry *dentry) { struct dentry *parent; - if(!dentry || !dentry->d_inode) { - printk(KERN_ERR "sdcardfs: %s: invalid dentry\n", __func__); + if (!dentry || !d_inode(dentry)) { + pr_err("sdcardfs: %s: invalid dentry\n", __func__); return; } /* FIXME: * 1. need to check whether the dentry is updated or not * 2. remove the root dentry update */ - mutex_lock(&dentry->d_inode->i_mutex); - if(IS_ROOT(dentry)) { - //setup_default_pre_root_state(dentry->d_inode); - } else { + if (!IS_ROOT(dentry)) { parent = dget_parent(dentry); - if(parent) { + if (parent) { get_derived_permission(parent, dentry); dput(parent); } } - fix_derived_permission(dentry->d_inode); - mutex_unlock(&dentry->d_inode->i_mutex); + fixup_tmp_permissions(d_inode(dentry)); } int need_graft_path(struct dentry *dentry) { int ret = 0; struct dentry *parent = dget_parent(dentry); - struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent)); struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct qstr obb = QSTR_LITERAL("obb"); - if(parent_info->perm == PERM_ANDROID && - !strcasecmp(dentry->d_name.name, "obb")) { + if (parent_info->perm == PERM_ANDROID && + qstr_case_eq(&dentry->d_name, &obb)) { /* /Android/obb is the base obbpath of DERIVED_UNIFIED */ - if(!(sbi->options.multiuser == false + if (!(sbi->options.multiuser == false && parent_info->userid == 0)) { ret = 1; } @@ -175,36 +368,40 @@ int is_obbpath_invalid(struct dentry *dent) struct sdcardfs_dentry_info *di = SDCARDFS_D(dent); struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dent->d_sb); char *path_buf, *obbpath_s; + int need_put = 0; + struct path lower_path; /* check the base obbpath has been changed. * this routine can check an uninitialized obb dentry as well. - * regarding the uninitialized obb, refer to the sdcardfs_mkdir() */ + * regarding the uninitialized obb, refer to the sdcardfs_mkdir() + */ spin_lock(&di->lock); - if(di->orig_path.dentry) { - if(!di->lower_path.dentry) { + if (di->orig_path.dentry) { + if (!di->lower_path.dentry) { ret = 1; } else { path_get(&di->lower_path); - //lower_parent = lock_parent(lower_path->dentry); path_buf = kmalloc(PATH_MAX, GFP_ATOMIC); - if(!path_buf) { + if (!path_buf) { ret = 1; - printk(KERN_ERR "sdcardfs: fail to allocate path_buf in %s.\n", __func__); + pr_err("sdcardfs: fail to allocate path_buf in %s.\n", __func__); } else { obbpath_s = d_path(&di->lower_path, path_buf, PATH_MAX); if (d_unhashed(di->lower_path.dentry) || - strcasecmp(sbi->obbpath_s, obbpath_s)) { + !str_case_eq(sbi->obbpath_s, obbpath_s)) { ret = 1; } kfree(path_buf); } - //unlock_dir(lower_parent); - path_put(&di->lower_path); + pathcpy(&lower_path, &di->lower_path); + need_put = 1; } } spin_unlock(&di->lock); + if (need_put) + path_put(&lower_path); return ret; } @@ -212,17 +409,18 @@ int is_base_obbpath(struct dentry *dentry) { int ret = 0; struct dentry *parent = dget_parent(dentry); - struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent)); struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct qstr q_obb = QSTR_LITERAL("obb"); spin_lock(&SDCARDFS_D(dentry)->lock); if (sbi->options.multiuser) { - if(parent_info->perm == PERM_PRE_ROOT && - !strcasecmp(dentry->d_name.name, "obb")) { + if (parent_info->perm == PERM_PRE_ROOT && + qstr_case_eq(&dentry->d_name, &q_obb)) { ret = 1; } } else if (parent_info->perm == PERM_ANDROID && - !strcasecmp(dentry->d_name.name, "obb")) { + qstr_case_eq(&dentry->d_name, &q_obb)) { ret = 1; } spin_unlock(&SDCARDFS_D(dentry)->lock); @@ -232,7 +430,8 @@ int is_base_obbpath(struct dentry *dentry) /* The lower_path will be stored to the dentry's orig_path * and the base obbpath will be copyed to the lower_path variable. * if an error returned, there's no change in the lower_path - * returns: -ERRNO if error (0: no error) */ + * returns: -ERRNO if error (0: no error) + */ int setup_obb_dentry(struct dentry *dentry, struct path *lower_path) { int err = 0; @@ -241,23 +440,24 @@ int setup_obb_dentry(struct dentry *dentry, struct path *lower_path) /* A local obb dentry must have its own orig_path to support rmdir * and mkdir of itself. Usually, we expect that the sbi->obbpath - * is avaiable on this stage. */ + * is avaiable on this stage. + */ sdcardfs_set_orig_path(dentry, lower_path); err = kern_path(sbi->obbpath_s, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &obbpath); - if(!err) { + if (!err) { /* the obbpath base has been found */ - printk(KERN_INFO "sdcardfs: the sbi->obbpath is found\n"); pathcpy(lower_path, &obbpath); } else { /* if the sbi->obbpath is not available, we can optionally * setup the lower_path with its orig_path. * but, the current implementation just returns an error * because the sdcard daemon also regards this case as - * a lookup fail. */ - printk(KERN_INFO "sdcardfs: the sbi->obbpath is not available\n"); + * a lookup fail. + */ + pr_info("sdcardfs: the sbi->obbpath is not available\n"); } return err; } diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c index c249fa982d3c..6076c342dae6 100644 --- a/fs/sdcardfs/file.c +++ b/fs/sdcardfs/file.c @@ -65,7 +65,7 @@ static ssize_t sdcardfs_write(struct file *file, const char __user *buf, /* check disk space */ if (!check_min_free_space(dentry, count, 0)) { - printk(KERN_INFO "No minimum free space.\n"); + pr_err("No minimum free space.\n"); return -ENOSPC; } @@ -113,6 +113,10 @@ static long sdcardfs_unlocked_ioctl(struct file *file, unsigned int cmd, if (lower_file->f_op->unlocked_ioctl) err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); + /* some ioctls can change inode attributes (EXT2_IOC_SETFLAGS) */ + if (!err) + sdcardfs_copy_and_fix_attrs(file_inode(file), + file_inode(lower_file)); out: return err; } @@ -160,8 +164,7 @@ static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma) lower_file = sdcardfs_lower_file(file); if (willwrite && !lower_file->f_mapping->a_ops->writepage) { err = -EINVAL; - printk(KERN_ERR "sdcardfs: lower file system does not " - "support writeable mmap\n"); + pr_err("sdcardfs: lower file system does not support writeable mmap\n"); goto out; } @@ -173,16 +176,10 @@ static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma) if (!SDCARDFS_F(file)->lower_vm_ops) { err = lower_file->f_op->mmap(lower_file, vma); if (err) { - printk(KERN_ERR "sdcardfs: lower mmap failed %d\n", err); + pr_err("sdcardfs: lower mmap failed %d\n", err); goto out; } saved_vm_ops = vma->vm_ops; /* save: came from lower ->mmap */ - err = do_munmap(current->mm, vma->vm_start, - vma->vm_end - vma->vm_start); - if (err) { - printk(KERN_ERR "sdcardfs: do_munmap failed %d\n", err); - goto out; - } } /* @@ -195,6 +192,9 @@ static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma) file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */ if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */ SDCARDFS_F(file)->lower_vm_ops = saved_vm_ops; + vma->vm_private_data = file; + get_file(lower_file); + vma->vm_file = lower_file; out: return err; @@ -216,16 +216,13 @@ static int sdcardfs_open(struct inode *inode, struct file *file) goto out_err; } - if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) { err = -EACCES; goto out_err; } /* save current_cred and override it */ - OVERRIDE_CRED(sbi, saved_cred); + OVERRIDE_CRED(sbi, saved_cred, SDCARDFS_I(inode)); file->private_data = kzalloc(sizeof(struct sdcardfs_file_info), GFP_KERNEL); @@ -251,9 +248,8 @@ static int sdcardfs_open(struct inode *inode, struct file *file) if (err) kfree(SDCARDFS_F(file)); - else { + else sdcardfs_copy_and_fix_attrs(inode, sdcardfs_lower_inode(inode)); - } out_revert_cred: REVERT_CRED(saved_cred); @@ -323,6 +319,85 @@ static int sdcardfs_fasync(int fd, struct file *file, int flag) return err; } +/* + * Sdcardfs cannot use generic_file_llseek as ->llseek, because it would + * only set the offset of the upper file. So we have to implement our + * own method to set both the upper and lower file offsets + * consistently. + */ +static loff_t sdcardfs_file_llseek(struct file *file, loff_t offset, int whence) +{ + int err; + struct file *lower_file; + + err = generic_file_llseek(file, offset, whence); + if (err < 0) + goto out; + + lower_file = sdcardfs_lower_file(file); + err = generic_file_llseek(lower_file, offset, whence); + +out: + return err; +} + +/* + * Sdcardfs read_iter, redirect modified iocb to lower read_iter + */ +ssize_t sdcardfs_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + int err; + struct file *file = iocb->ki_filp, *lower_file; + + lower_file = sdcardfs_lower_file(file); + if (!lower_file->f_op->read_iter) { + err = -EINVAL; + goto out; + } + + get_file(lower_file); /* prevent lower_file from being released */ + iocb->ki_filp = lower_file; + err = lower_file->f_op->read_iter(iocb, iter); + iocb->ki_filp = file; + fput(lower_file); + /* update upper inode atime as needed */ + if (err >= 0 || err == -EIOCBQUEUED) + fsstack_copy_attr_atime(file->f_path.dentry->d_inode, + file_inode(lower_file)); +out: + return err; +} + +/* + * Sdcardfs write_iter, redirect modified iocb to lower write_iter + */ +ssize_t sdcardfs_write_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + int err; + struct file *file = iocb->ki_filp, *lower_file; + + lower_file = sdcardfs_lower_file(file); + if (!lower_file->f_op->write_iter) { + err = -EINVAL; + goto out; + } + + get_file(lower_file); /* prevent lower_file from being released */ + iocb->ki_filp = lower_file; + err = lower_file->f_op->write_iter(iocb, iter); + iocb->ki_filp = file; + fput(lower_file); + /* update upper inode times/sizes as needed */ + if (err >= 0 || err == -EIOCBQUEUED) { + fsstack_copy_inode_size(file->f_path.dentry->d_inode, + file_inode(lower_file)); + fsstack_copy_attr_times(file->f_path.dentry->d_inode, + file_inode(lower_file)); + } +out: + return err; +} + const struct file_operations sdcardfs_main_fops = { .llseek = generic_file_llseek, .read = sdcardfs_read, @@ -337,11 +412,13 @@ const struct file_operations sdcardfs_main_fops = { .release = sdcardfs_file_release, .fsync = sdcardfs_fsync, .fasync = sdcardfs_fasync, + .read_iter = sdcardfs_read_iter, + .write_iter = sdcardfs_write_iter, }; /* trimmed directory options */ const struct file_operations sdcardfs_dir_fops = { - .llseek = generic_file_llseek, + .llseek = sdcardfs_file_llseek, .read = generic_read_dir, .iterate = sdcardfs_readdir, .unlocked_ioctl = sdcardfs_unlocked_ioctl, diff --git a/fs/sdcardfs/inode.c b/fs/sdcardfs/inode.c index 2528da0d3ae1..f15cb11ca8fd 100644 --- a/fs/sdcardfs/inode.c +++ b/fs/sdcardfs/inode.c @@ -19,18 +19,25 @@ */ #include "sdcardfs.h" +#include <linux/fs_struct.h> +#include <linux/ratelimit.h> /* Do not directly use this function. Use OVERRIDE_CRED() instead. */ -const struct cred * override_fsids(struct sdcardfs_sb_info* sbi) +const struct cred *override_fsids(struct sdcardfs_sb_info *sbi, struct sdcardfs_inode_info *info) { - struct cred * cred; - const struct cred * old_cred; + struct cred *cred; + const struct cred *old_cred; + uid_t uid; cred = prepare_creds(); if (!cred) return NULL; - cred->fsuid = make_kuid(&init_user_ns, sbi->options.fs_low_uid); + if (info->under_obb) + uid = AID_MEDIA_OBB; + else + uid = multiuser_get_uid(info->userid, sbi->options.fs_low_uid); + cred->fsuid = make_kuid(&init_user_ns, uid); cred->fsgid = make_kgid(&init_user_ns, sbi->options.fs_low_gid); old_cred = override_creds(cred); @@ -39,9 +46,9 @@ const struct cred * override_fsids(struct sdcardfs_sb_info* sbi) } /* Do not directly use this function, use REVERT_CRED() instead. */ -void revert_fsids(const struct cred * old_cred) +void revert_fsids(const struct cred *old_cred) { - const struct cred * cur_cred; + const struct cred *cur_cred; cur_cred = current->cred; revert_creds(old_cred); @@ -53,28 +60,39 @@ static int sdcardfs_create(struct inode *dir, struct dentry *dentry, { int err; struct dentry *lower_dentry; + struct vfsmount *lower_dentry_mnt; struct dentry *lower_parent_dentry = NULL; struct path lower_path; const struct cred *saved_cred = NULL; + struct fs_struct *saved_fs; + struct fs_struct *copied_fs; - if(!check_caller_access_to_name(dir, dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(dir, &dentry->d_name)) { err = -EACCES; goto out_eacces; } /* save current_cred and override it */ - OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir)); sdcardfs_get_lower_path(dentry, &lower_path); lower_dentry = lower_path.dentry; + lower_dentry_mnt = lower_path.mnt; lower_parent_dentry = lock_parent(lower_dentry); /* set last 16bytes of mode field to 0664 */ mode = (mode & S_IFMT) | 00664; - err = vfs_create(d_inode(lower_parent_dentry), lower_dentry, mode, want_excl); + + /* temporarily change umask for lower fs write */ + saved_fs = current->fs; + copied_fs = copy_fs_struct(current->fs); + if (!copied_fs) { + err = -ENOMEM; + goto out_unlock; + } + current->fs = copied_fs; + current->fs->umask = 0; + err = vfs_create2(lower_dentry_mnt, d_inode(lower_parent_dentry), lower_dentry, mode, want_excl); if (err) goto out; @@ -83,8 +101,12 @@ static int sdcardfs_create(struct inode *dir, struct dentry *dentry, goto out; fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + fixup_lower_ownership(dentry, dentry->d_name.name); out: + current->fs = saved_fs; + free_fs_struct(copied_fs); +out_unlock: unlock_dir(lower_parent_dentry); sdcardfs_put_lower_path(dentry, &lower_path); REVERT_CRED(saved_cred); @@ -138,28 +160,27 @@ static int sdcardfs_unlink(struct inode *dir, struct dentry *dentry) { int err; struct dentry *lower_dentry; + struct vfsmount *lower_mnt; struct inode *lower_dir_inode = sdcardfs_lower_inode(dir); struct dentry *lower_dir_dentry; struct path lower_path; const struct cred *saved_cred = NULL; - if(!check_caller_access_to_name(dir, dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(dir, &dentry->d_name)) { err = -EACCES; goto out_eacces; } /* save current_cred and override it */ - OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir)); sdcardfs_get_lower_path(dentry, &lower_path); lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; dget(lower_dentry); lower_dir_dentry = lock_parent(lower_dentry); - err = vfs_unlink(lower_dir_inode, lower_dentry, NULL); + err = vfs_unlink2(lower_mnt, lower_dir_inode, lower_dentry, NULL); /* * Note: unlinking on top of NFS can cause silly-renamed files. @@ -219,14 +240,15 @@ out: } #endif -static int touch(char *abs_path, mode_t mode) { +static int touch(char *abs_path, mode_t mode) +{ struct file *filp = filp_open(abs_path, O_RDWR|O_CREAT|O_EXCL|O_NOFOLLOW, mode); + if (IS_ERR(filp)) { if (PTR_ERR(filp) == -EEXIST) { return 0; - } - else { - printk(KERN_ERR "sdcardfs: failed to open(%s): %ld\n", + } else { + pr_err("sdcardfs: failed to open(%s): %ld\n", abs_path, PTR_ERR(filp)); return PTR_ERR(filp); } @@ -240,31 +262,29 @@ static int sdcardfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode int err; int make_nomedia_in_obb = 0; struct dentry *lower_dentry; + struct vfsmount *lower_mnt; struct dentry *lower_parent_dentry = NULL; struct path lower_path; struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); const struct cred *saved_cred = NULL; struct sdcardfs_inode_info *pi = SDCARDFS_I(dir); - char *page_buf; - char *nomedia_dir_name; - char *nomedia_fullpath; - int fullpath_namelen; int touch_err = 0; + struct fs_struct *saved_fs; + struct fs_struct *copied_fs; + struct qstr q_obb = QSTR_LITERAL("obb"); + struct qstr q_data = QSTR_LITERAL("data"); - if(!check_caller_access_to_name(dir, dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(dir, &dentry->d_name)) { err = -EACCES; goto out_eacces; } /* save current_cred and override it */ - OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir)); /* check disk space */ if (!check_min_free_space(dentry, 0, 1)) { - printk(KERN_INFO "sdcardfs: No minimum free space.\n"); + pr_err("sdcardfs: No minimum free space.\n"); err = -ENOSPC; goto out_revert; } @@ -272,87 +292,83 @@ static int sdcardfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode /* the lower_dentry is negative here */ sdcardfs_get_lower_path(dentry, &lower_path); lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; lower_parent_dentry = lock_parent(lower_dentry); /* set last 16bytes of mode field to 0775 */ mode = (mode & S_IFMT) | 00775; - err = vfs_mkdir(d_inode(lower_parent_dentry), lower_dentry, mode); - if (err) + /* temporarily change umask for lower fs write */ + saved_fs = current->fs; + copied_fs = copy_fs_struct(current->fs); + if (!copied_fs) { + err = -ENOMEM; + unlock_dir(lower_parent_dentry); + goto out_unlock; + } + current->fs = copied_fs; + current->fs->umask = 0; + err = vfs_mkdir2(lower_mnt, d_inode(lower_parent_dentry), lower_dentry, mode); + + if (err) { + unlock_dir(lower_parent_dentry); goto out; + } /* if it is a local obb dentry, setup it with the base obbpath */ - if(need_graft_path(dentry)) { + if (need_graft_path(dentry)) { err = setup_obb_dentry(dentry, &lower_path); - if(err) { + if (err) { /* if the sbi->obbpath is not available, the lower_path won't be * changed by setup_obb_dentry() but the lower path is saved to * its orig_path. this dentry will be revalidated later. - * but now, the lower_path should be NULL */ + * but now, the lower_path should be NULL + */ sdcardfs_put_reset_lower_path(dentry); /* the newly created lower path which saved to its orig_path or * the lower_path is the base obbpath. - * therefore, an additional path_get is required */ + * therefore, an additional path_get is required + */ path_get(&lower_path); } else make_nomedia_in_obb = 1; } err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, pi->userid); - if (err) + if (err) { + unlock_dir(lower_parent_dentry); goto out; + } fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); /* update number of links on parent directory */ set_nlink(dir, sdcardfs_lower_inode(dir)->i_nlink); - - if ((!sbi->options.multiuser) && (!strcasecmp(dentry->d_name.name, "obb")) + fixup_lower_ownership(dentry, dentry->d_name.name); + unlock_dir(lower_parent_dentry); + if ((!sbi->options.multiuser) && (qstr_case_eq(&dentry->d_name, &q_obb)) && (pi->perm == PERM_ANDROID) && (pi->userid == 0)) make_nomedia_in_obb = 1; /* When creating /Android/data and /Android/obb, mark them as .nomedia */ if (make_nomedia_in_obb || - ((pi->perm == PERM_ANDROID) && (!strcasecmp(dentry->d_name.name, "data")))) { - - page_buf = (char *)__get_free_page(GFP_KERNEL); - if (!page_buf) { - printk(KERN_ERR "sdcardfs: failed to allocate page buf\n"); - goto out; - } - - nomedia_dir_name = d_absolute_path(&lower_path, page_buf, PAGE_SIZE); - if (IS_ERR(nomedia_dir_name)) { - free_page((unsigned long)page_buf); - printk(KERN_ERR "sdcardfs: failed to get .nomedia dir name\n"); - goto out; - } - - fullpath_namelen = page_buf + PAGE_SIZE - nomedia_dir_name - 1; - fullpath_namelen += strlen("/.nomedia"); - nomedia_fullpath = kzalloc(fullpath_namelen + 1, GFP_KERNEL); - if (!nomedia_fullpath) { - free_page((unsigned long)page_buf); - printk(KERN_ERR "sdcardfs: failed to allocate .nomedia fullpath buf\n"); - goto out; - } - - strcpy(nomedia_fullpath, nomedia_dir_name); - free_page((unsigned long)page_buf); - strcat(nomedia_fullpath, "/.nomedia"); - touch_err = touch(nomedia_fullpath, 0664); + ((pi->perm == PERM_ANDROID) && (qstr_case_eq(&dentry->d_name, &q_data)))) { + REVERT_CRED(saved_cred); + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(d_inode(dentry))); + set_fs_pwd(current->fs, &lower_path); + touch_err = touch(".nomedia", 0664); if (touch_err) { - printk(KERN_ERR "sdcardfs: failed to touch(%s): %d\n", - nomedia_fullpath, touch_err); - kfree(nomedia_fullpath); + pr_err("sdcardfs: failed to create .nomedia in %s: %d\n", + lower_path.dentry->d_name.name, touch_err); goto out; } - kfree(nomedia_fullpath); } out: - unlock_dir(lower_parent_dentry); + current->fs = saved_fs; + free_fs_struct(copied_fs); +out_unlock: sdcardfs_put_lower_path(dentry, &lower_path); out_revert: REVERT_CRED(saved_cred); @@ -364,29 +380,29 @@ static int sdcardfs_rmdir(struct inode *dir, struct dentry *dentry) { struct dentry *lower_dentry; struct dentry *lower_dir_dentry; + struct vfsmount *lower_mnt; int err; struct path lower_path; const struct cred *saved_cred = NULL; - if(!check_caller_access_to_name(dir, dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(dir, &dentry->d_name)) { err = -EACCES; goto out_eacces; } /* save current_cred and override it */ - OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir)); /* sdcardfs_get_real_lower(): in case of remove an user's obb dentry - * the dentry on the original path should be deleted. */ + * the dentry on the original path should be deleted. + */ sdcardfs_get_real_lower(dentry, &lower_path); lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; lower_dir_dentry = lock_parent(lower_dentry); - err = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry); + err = vfs_rmdir2(lower_mnt, d_inode(lower_dir_dentry), lower_dentry); if (err) goto out; @@ -450,27 +466,25 @@ static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct dentry *lower_new_dentry = NULL; struct dentry *lower_old_dir_dentry = NULL; struct dentry *lower_new_dir_dentry = NULL; + struct vfsmount *lower_mnt = NULL; struct dentry *trap = NULL; - struct dentry *new_parent = NULL; struct path lower_old_path, lower_new_path; const struct cred *saved_cred = NULL; - if(!check_caller_access_to_name(old_dir, old_dentry->d_name.name) || - !check_caller_access_to_name(new_dir, new_dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " new_dentry: %s, task:%s\n", - __func__, new_dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(old_dir, &old_dentry->d_name) || + !check_caller_access_to_name(new_dir, &new_dentry->d_name)) { err = -EACCES; goto out_eacces; } /* save current_cred and override it */ - OVERRIDE_CRED(SDCARDFS_SB(old_dir->i_sb), saved_cred); + OVERRIDE_CRED(SDCARDFS_SB(old_dir->i_sb), saved_cred, SDCARDFS_I(new_dir)); sdcardfs_get_real_lower(old_dentry, &lower_old_path); sdcardfs_get_lower_path(new_dentry, &lower_new_path); lower_old_dentry = lower_old_path.dentry; lower_new_dentry = lower_new_path.dentry; + lower_mnt = lower_old_path.mnt; lower_old_dir_dentry = dget_parent(lower_old_dentry); lower_new_dir_dentry = dget_parent(lower_new_dentry); @@ -486,7 +500,8 @@ static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } - err = vfs_rename(d_inode(lower_old_dir_dentry), lower_old_dentry, + err = vfs_rename2(lower_mnt, + d_inode(lower_old_dir_dentry), lower_old_dentry, d_inode(lower_new_dir_dentry), lower_new_dentry, NULL, 0); if (err) @@ -499,25 +514,11 @@ static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dir != old_dir) { sdcardfs_copy_and_fix_attrs(old_dir, d_inode(lower_old_dir_dentry)); fsstack_copy_inode_size(old_dir, d_inode(lower_old_dir_dentry)); - - /* update the derived permission of the old_dentry - * with its new parent - */ - new_parent = dget_parent(new_dentry); - if(new_parent) { - if(d_inode(old_dentry)) { - update_derived_permission_lock(old_dentry); - } - dput(new_parent); - } } - /* At this point, not all dentry information has been moved, so - * we pass along new_dentry for the name.*/ - mutex_lock(&d_inode(old_dentry)->i_mutex); - get_derived_permission_new(new_dentry->d_parent, old_dentry, new_dentry); - fix_derived_permission(d_inode(old_dentry)); - get_derive_permissions_recursive(old_dentry); - mutex_unlock(&d_inode(old_dentry)->i_mutex); + get_derived_permission_new(new_dentry->d_parent, old_dentry, &new_dentry->d_name); + fixup_tmp_permissions(d_inode(old_dentry)); + fixup_lower_ownership(old_dentry, new_dentry->d_name.name); + d_invalidate(old_dentry); /* Can't fixup ownership recursively :( */ out: unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); dput(lower_old_dir_dentry); @@ -586,16 +587,63 @@ static const char *sdcardfs_follow_link(struct dentry *dentry, void **cookie) } #endif -static int sdcardfs_permission(struct inode *inode, int mask) +static int sdcardfs_permission_wrn(struct inode *inode, int mask) +{ + WARN_RATELIMIT(1, "sdcardfs does not support permission. Use permission2.\n"); + return -EINVAL; +} + +void copy_attrs(struct inode *dest, const struct inode *src) +{ + dest->i_mode = src->i_mode; + dest->i_uid = src->i_uid; + dest->i_gid = src->i_gid; + dest->i_rdev = src->i_rdev; + dest->i_atime = src->i_atime; + dest->i_mtime = src->i_mtime; + dest->i_ctime = src->i_ctime; + dest->i_blkbits = src->i_blkbits; + dest->i_flags = src->i_flags; +#ifdef CONFIG_FS_POSIX_ACL + dest->i_acl = src->i_acl; +#endif +#ifdef CONFIG_SECURITY + dest->i_security = src->i_security; +#endif +} + +static int sdcardfs_permission(struct vfsmount *mnt, struct inode *inode, int mask) { int err; + struct inode tmp; + struct inode *top = grab_top(SDCARDFS_I(inode)); + + if (!top) { + release_top(SDCARDFS_I(inode)); + WARN(1, "Top value was null!\n"); + return -EINVAL; + } /* * Permission check on sdcardfs inode. * Calling process should have AID_SDCARD_RW permission + * Since generic_permission only needs i_mode, i_uid, + * i_gid, and i_sb, we can create a fake inode to pass + * this information down in. + * + * The underlying code may attempt to take locks in some + * cases for features we're not using, but if that changes, + * locks must be dealt with to avoid undefined behavior. */ - err = generic_permission(inode, mask); - + copy_attrs(&tmp, inode); + tmp.i_uid = make_kuid(&init_user_ns, SDCARDFS_I(top)->d_uid); + tmp.i_gid = make_kgid(&init_user_ns, get_gid(mnt, SDCARDFS_I(top))); + tmp.i_mode = (inode->i_mode & S_IFMT) | get_mode(mnt, SDCARDFS_I(top)); + release_top(SDCARDFS_I(inode)); + tmp.i_sb = inode->i_sb; + if (IS_POSIXACL(inode)) + pr_warn("%s: This may be undefined behavior...\n", __func__); + err = generic_permission(&tmp, mask); /* XXX * Original sdcardfs code calls inode_permission(lower_inode,.. ) * for checking inode permission. But doing such things here seems @@ -612,6 +660,7 @@ static int sdcardfs_permission(struct inode *inode, int mask) * we check it with AID_MEDIA_RW permission */ struct inode *lower_inode; + OVERRIDE_CRED(SDCARDFS_SB(inode->sb)); lower_inode = sdcardfs_lower_inode(inode); @@ -624,47 +673,86 @@ static int sdcardfs_permission(struct inode *inode, int mask) } -static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia) +static int sdcardfs_setattr_wrn(struct dentry *dentry, struct iattr *ia) +{ + WARN_RATELIMIT(1, "sdcardfs does not support setattr. User setattr2.\n"); + return -EINVAL; +} + +static int sdcardfs_setattr(struct vfsmount *mnt, struct dentry *dentry, struct iattr *ia) { int err; struct dentry *lower_dentry; + struct vfsmount *lower_mnt; struct inode *inode; struct inode *lower_inode; struct path lower_path; struct iattr lower_ia; struct dentry *parent; + struct inode tmp; + struct inode *top; + const struct cred *saved_cred = NULL; inode = d_inode(dentry); + top = grab_top(SDCARDFS_I(inode)); + + if (!top) { + release_top(SDCARDFS_I(inode)); + return -EINVAL; + } + + /* + * Permission check on sdcardfs inode. + * Calling process should have AID_SDCARD_RW permission + * Since generic_permission only needs i_mode, i_uid, + * i_gid, and i_sb, we can create a fake inode to pass + * this information down in. + * + * The underlying code may attempt to take locks in some + * cases for features we're not using, but if that changes, + * locks must be dealt with to avoid undefined behavior. + * + */ + copy_attrs(&tmp, inode); + tmp.i_uid = make_kuid(&init_user_ns, SDCARDFS_I(top)->d_uid); + tmp.i_gid = make_kgid(&init_user_ns, get_gid(mnt, SDCARDFS_I(top))); + tmp.i_mode = (inode->i_mode & S_IFMT) | get_mode(mnt, SDCARDFS_I(top)); + tmp.i_size = i_size_read(inode); + release_top(SDCARDFS_I(inode)); + tmp.i_sb = inode->i_sb; /* * Check if user has permission to change inode. We don't check if * this user can change the lower inode: that should happen when * calling notify_change on the lower inode. */ - err = inode_change_ok(inode, ia); + /* prepare our own lower struct iattr (with the lower file) */ + memcpy(&lower_ia, ia, sizeof(lower_ia)); + /* Allow touch updating timestamps. A previous permission check ensures + * we have write access. Changes to mode, owner, and group are ignored + */ + ia->ia_valid |= ATTR_FORCE; + err = inode_change_ok(&tmp, ia); - /* no vfs_XXX operations required, cred overriding will be skipped. wj*/ if (!err) { /* check the Android group ID */ parent = dget_parent(dentry); - if(!check_caller_access_to_name(d_inode(parent), dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) err = -EACCES; - } dput(parent); } if (err) goto out_err; + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dentry->d_sb), saved_cred, SDCARDFS_I(inode)); + sdcardfs_get_lower_path(dentry, &lower_path); lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; lower_inode = sdcardfs_lower_inode(inode); - /* prepare our own lower struct iattr (with the lower file) */ - memcpy(&lower_ia, ia, sizeof(lower_ia)); if (ia->ia_valid & ATTR_FILE) lower_ia.ia_file = sdcardfs_lower_file(ia->ia_file); @@ -681,7 +769,7 @@ static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia) if (current->mm) down_write(¤t->mm->mmap_sem); if (ia->ia_valid & ATTR_SIZE) { - err = inode_newsize_ok(inode, ia->ia_size); + err = inode_newsize_ok(&tmp, ia->ia_size); if (err) { if (current->mm) up_write(¤t->mm->mmap_sem); @@ -704,7 +792,7 @@ static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia) * tries to open(), unlink(), then ftruncate() a file. */ mutex_lock(&d_inode(lower_dentry)->i_mutex); - err = notify_change(lower_dentry, &lower_ia, /* note: lower_ia */ + err = notify_change2(lower_mnt, lower_dentry, &lower_ia, /* note: lower_ia */ NULL); mutex_unlock(&d_inode(lower_dentry)->i_mutex); if (current->mm) @@ -723,48 +811,68 @@ static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia) out: sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(saved_cred); out_err: return err; } +static int sdcardfs_fillattr(struct vfsmount *mnt, + struct inode *inode, struct kstat *stat) +{ + struct sdcardfs_inode_info *info = SDCARDFS_I(inode); + struct inode *top = grab_top(info); + + if (!top) + return -EINVAL; + + stat->dev = inode->i_sb->s_dev; + stat->ino = inode->i_ino; + stat->mode = (inode->i_mode & S_IFMT) | get_mode(mnt, SDCARDFS_I(top)); + stat->nlink = inode->i_nlink; + stat->uid = make_kuid(&init_user_ns, SDCARDFS_I(top)->d_uid); + stat->gid = make_kgid(&init_user_ns, get_gid(mnt, SDCARDFS_I(top))); + stat->rdev = inode->i_rdev; + stat->size = i_size_read(inode); + stat->atime = inode->i_atime; + stat->mtime = inode->i_mtime; + stat->ctime = inode->i_ctime; + stat->blksize = (1 << inode->i_blkbits); + stat->blocks = inode->i_blocks; + release_top(info); + return 0; +} + static int sdcardfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { - struct dentry *lower_dentry; - struct inode *inode; - struct inode *lower_inode; + struct kstat lower_stat; struct path lower_path; struct dentry *parent; + int err; parent = dget_parent(dentry); - if(!check_caller_access_to_name(d_inode(parent), dentry->d_name.name)) { - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) { dput(parent); return -EACCES; } dput(parent); - inode = d_inode(dentry); - sdcardfs_get_lower_path(dentry, &lower_path); - lower_dentry = lower_path.dentry; - lower_inode = sdcardfs_lower_inode(inode); - - - sdcardfs_copy_and_fix_attrs(inode, lower_inode); - fsstack_copy_inode_size(inode, lower_inode); - - - generic_fillattr(inode, stat); + err = vfs_getattr(&lower_path, &lower_stat); + if (err) + goto out; + sdcardfs_copy_and_fix_attrs(d_inode(dentry), + d_inode(lower_path.dentry)); + err = sdcardfs_fillattr(mnt, d_inode(dentry), stat); + stat->blocks = lower_stat.blocks; +out: sdcardfs_put_lower_path(dentry, &lower_path); - return 0; + return err; } const struct inode_operations sdcardfs_symlink_iops = { - .permission = sdcardfs_permission, - .setattr = sdcardfs_setattr, + .permission2 = sdcardfs_permission, + .setattr2 = sdcardfs_setattr, /* XXX Following operations are implemented, * but FUSE(sdcard) or FAT does not support them * These methods are *NOT* perfectly tested. @@ -777,14 +885,14 @@ const struct inode_operations sdcardfs_symlink_iops = { const struct inode_operations sdcardfs_dir_iops = { .create = sdcardfs_create, .lookup = sdcardfs_lookup, -#if 0 - .permission = sdcardfs_permission, -#endif + .permission = sdcardfs_permission_wrn, + .permission2 = sdcardfs_permission, .unlink = sdcardfs_unlink, .mkdir = sdcardfs_mkdir, .rmdir = sdcardfs_rmdir, .rename = sdcardfs_rename, - .setattr = sdcardfs_setattr, + .setattr = sdcardfs_setattr_wrn, + .setattr2 = sdcardfs_setattr, .getattr = sdcardfs_getattr, /* XXX Following operations are implemented, * but FUSE(sdcard) or FAT does not support them @@ -796,7 +904,9 @@ const struct inode_operations sdcardfs_dir_iops = { }; const struct inode_operations sdcardfs_main_iops = { - .permission = sdcardfs_permission, - .setattr = sdcardfs_setattr, + .permission = sdcardfs_permission_wrn, + .permission2 = sdcardfs_permission, + .setattr = sdcardfs_setattr_wrn, + .setattr2 = sdcardfs_setattr, .getattr = sdcardfs_getattr, }; diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c index a01b06a514fd..509d5fbcb472 100644 --- a/fs/sdcardfs/lookup.c +++ b/fs/sdcardfs/lookup.c @@ -36,8 +36,7 @@ int sdcardfs_init_dentry_cache(void) void sdcardfs_destroy_dentry_cache(void) { - if (sdcardfs_dentry_cachep) - kmem_cache_destroy(sdcardfs_dentry_cachep); + kmem_cache_destroy(sdcardfs_dentry_cachep); } void free_dentry_private_data(struct dentry *dentry) @@ -73,6 +72,7 @@ static int sdcardfs_inode_test(struct inode *inode, void *candidate_data/*void * { struct inode *current_lower_inode = sdcardfs_lower_inode(inode); userid_t current_userid = SDCARDFS_I(inode)->userid; + if (current_lower_inode == ((struct inode_data *)candidate_data)->lower_inode && current_userid == ((struct inode_data *)candidate_data)->id) return 1; /* found a match */ @@ -91,7 +91,9 @@ struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, u struct sdcardfs_inode_info *info; struct inode_data data; struct inode *inode; /* the new inode to return */ - int err; + + if (!igrab(lower_inode)) + return ERR_PTR(-ESTALE); data.id = id; data.lower_inode = lower_inode; @@ -102,26 +104,23 @@ struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, u * instead. */ lower_inode->i_ino, /* hashval */ - sdcardfs_inode_test, /* inode comparison function */ + sdcardfs_inode_test, /* inode comparison function */ sdcardfs_inode_set, /* inode init function */ &data); /* data passed to test+set fxns */ if (!inode) { - err = -EACCES; iput(lower_inode); - return ERR_PTR(err); + return ERR_PTR(-ENOMEM); } - /* if found a cached inode, then just return it */ - if (!(inode->i_state & I_NEW)) + /* if found a cached inode, then just return it (after iput) */ + if (!(inode->i_state & I_NEW)) { + iput(lower_inode); return inode; + } /* initialize new inode */ info = SDCARDFS_I(inode); inode->i_ino = lower_inode->i_ino; - if (!igrab(lower_inode)) { - err = -ESTALE; - return ERR_PTR(err); - } sdcardfs_set_lower_inode(inode, lower_inode); inode->i_version++; @@ -164,27 +163,25 @@ struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, u } /* - * Connect a sdcardfs inode dentry/inode with several lower ones. This is - * the classic stackable file system "vnode interposition" action. - * - * @dentry: sdcardfs's dentry which interposes on lower one - * @sb: sdcardfs's super_block - * @lower_path: the lower path (caller does path_get/put) + * Helper interpose routine, called directly by ->lookup to handle + * spliced dentries. */ -int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, - struct path *lower_path, userid_t id) +static struct dentry *__sdcardfs_interpose(struct dentry *dentry, + struct super_block *sb, + struct path *lower_path, + userid_t id) { - int err = 0; struct inode *inode; struct inode *lower_inode; struct super_block *lower_sb; + struct dentry *ret_dentry; - lower_inode = lower_path->dentry->d_inode; + lower_inode = d_inode(lower_path->dentry); lower_sb = sdcardfs_lower_super(sb); /* check that the lower file system didn't cross a mount point */ if (lower_inode->i_sb != lower_sb) { - err = -EXDEV; + ret_dentry = ERR_PTR(-EXDEV); goto out; } @@ -196,14 +193,54 @@ int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, /* inherit lower inode number for sdcardfs's inode */ inode = sdcardfs_iget(sb, lower_inode, id); if (IS_ERR(inode)) { - err = PTR_ERR(inode); + ret_dentry = ERR_CAST(inode); goto out; } - d_add(dentry, inode); + ret_dentry = d_splice_alias(inode, dentry); + dentry = ret_dentry ?: dentry; update_derived_permission_lock(dentry); out: - return err; + return ret_dentry; +} + +/* + * Connect an sdcardfs inode dentry/inode with several lower ones. This is + * the classic stackable file system "vnode interposition" action. + * + * @dentry: sdcardfs's dentry which interposes on lower one + * @sb: sdcardfs's super_block + * @lower_path: the lower path (caller does path_get/put) + */ +int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, + struct path *lower_path, userid_t id) +{ + struct dentry *ret_dentry; + + ret_dentry = __sdcardfs_interpose(dentry, sb, lower_path, id); + return PTR_ERR(ret_dentry); +} + +struct sdcardfs_name_data { + struct dir_context ctx; + const struct qstr *to_find; + char *name; + bool found; +}; + +static int sdcardfs_name_match(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, unsigned int d_type) +{ + struct sdcardfs_name_data *buf = container_of(ctx, struct sdcardfs_name_data, ctx); + struct qstr candidate = QSTR_INIT(name, namelen); + + if (qstr_case_eq(buf->to_find, &candidate)) { + memcpy(buf->name, name, namelen); + buf->name[namelen] = 0; + buf->found = true; + return 1; + } + return 0; } /* @@ -219,9 +256,10 @@ static struct dentry *__sdcardfs_lookup(struct dentry *dentry, struct vfsmount *lower_dir_mnt; struct dentry *lower_dir_dentry = NULL; struct dentry *lower_dentry; - const char *name; + const struct qstr *name; struct path lower_path; - struct qstr this; + struct qstr dname; + struct dentry *ret_dentry = NULL; struct sdcardfs_sb_info *sbi; sbi = SDCARDFS_SB(dentry->d_sb); @@ -231,47 +269,90 @@ static struct dentry *__sdcardfs_lookup(struct dentry *dentry, if (IS_ROOT(dentry)) goto out; - name = dentry->d_name.name; + name = &dentry->d_name; /* now start the actual lookup procedure */ lower_dir_dentry = lower_parent_path->dentry; lower_dir_mnt = lower_parent_path->mnt; /* Use vfs_path_lookup to check if the dentry exists or not */ - err = vfs_path_lookup(lower_dir_dentry, lower_dir_mnt, name, 0, + err = vfs_path_lookup(lower_dir_dentry, lower_dir_mnt, name->name, 0, &lower_path); + /* check for other cases */ + if (err == -ENOENT) { + struct file *file; + const struct cred *cred = current_cred(); + + struct sdcardfs_name_data buffer = { + .ctx.actor = sdcardfs_name_match, + .to_find = name, + .name = __getname(), + .found = false, + }; + + if (!buffer.name) { + err = -ENOMEM; + goto out; + } + file = dentry_open(lower_parent_path, O_RDONLY, cred); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto put_name; + } + err = iterate_dir(file, &buffer.ctx); + fput(file); + if (err) + goto put_name; + + if (buffer.found) + err = vfs_path_lookup(lower_dir_dentry, + lower_dir_mnt, + buffer.name, 0, + &lower_path); + else + err = -ENOENT; +put_name: + __putname(buffer.name); + } /* no error: handle positive dentries */ if (!err) { /* check if the dentry is an obb dentry * if true, the lower_inode must be replaced with - * the inode of the graft path */ + * the inode of the graft path + */ - if(need_graft_path(dentry)) { + if (need_graft_path(dentry)) { /* setup_obb_dentry() - * The lower_path will be stored to the dentry's orig_path + * The lower_path will be stored to the dentry's orig_path * and the base obbpath will be copyed to the lower_path variable. * if an error returned, there's no change in the lower_path - * returns: -ERRNO if error (0: no error) */ + * returns: -ERRNO if error (0: no error) + */ err = setup_obb_dentry(dentry, &lower_path); - if(err) { + if (err) { /* if the sbi->obbpath is not available, we can optionally * setup the lower_path with its orig_path. * but, the current implementation just returns an error * because the sdcard daemon also regards this case as - * a lookup fail. */ - printk(KERN_INFO "sdcardfs: base obbpath is not available\n"); + * a lookup fail. + */ + pr_info("sdcardfs: base obbpath is not available\n"); sdcardfs_put_reset_orig_path(dentry); goto out; } } sdcardfs_set_lower_path(dentry, &lower_path); - err = sdcardfs_interpose(dentry, dentry->d_sb, &lower_path, id); - if (err) /* path_put underlying path on error */ + ret_dentry = + __sdcardfs_interpose(dentry, dentry->d_sb, &lower_path, id); + if (IS_ERR(ret_dentry)) { + err = PTR_ERR(ret_dentry); + /* path_put underlying path on error */ sdcardfs_put_reset_lower_path(dentry); + } goto out; } @@ -283,21 +364,24 @@ static struct dentry *__sdcardfs_lookup(struct dentry *dentry, goto out; /* instatiate a new negative dentry */ - this.name = name; - this.len = strlen(name); - this.hash = full_name_hash(this.name, this.len); - lower_dentry = d_lookup(lower_dir_dentry, &this); - if (lower_dentry) - goto setup_lower; - - lower_dentry = d_alloc(lower_dir_dentry, &this); + dname.name = name->name; + dname.len = name->len; + + /* See if the low-level filesystem might want + * to use its own hash + */ + lower_dentry = d_hash_and_lookup(lower_dir_dentry, &dname); + if (IS_ERR(lower_dentry)) + return lower_dentry; if (!lower_dentry) { - err = -ENOMEM; + /* We called vfs_path_lookup earlier, and did not get a negative + * dentry then. Don't confuse the lower filesystem by forcing + * one on it now... + */ + err = -ENOENT; goto out; } - d_add(lower_dentry, NULL); /* instantiate and hash */ -setup_lower: lower_path.dentry = lower_dentry; lower_path.mnt = mntget(lower_dir_mnt); sdcardfs_set_lower_path(dentry, &lower_path); @@ -311,14 +395,16 @@ setup_lower: err = 0; out: - return ERR_PTR(err); + if (err) + return ERR_PTR(err); + return ret_dentry; } /* * On success: - * fills dentry object appropriate values and returns NULL. + * fills dentry object appropriate values and returns NULL. * On fail (== error) - * returns error ptr + * returns error ptr * * @dir : Parent inode. It is locked (dir->i_mutex) * @dentry : Target dentry to lookup. we should set each of fields. @@ -335,16 +421,13 @@ struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, parent = dget_parent(dentry); - if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) { + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) { ret = ERR_PTR(-EACCES); - printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" - " dentry: %s, task:%s\n", - __func__, dentry->d_name.name, current->comm); goto out_err; - } + } /* save current_cred and override it */ - OVERRIDE_CRED_PTR(SDCARDFS_SB(dir->i_sb), saved_cred); + OVERRIDE_CRED_PTR(SDCARDFS_SB(dir->i_sb), saved_cred, SDCARDFS_I(dir)); sdcardfs_get_lower_path(parent, &lower_parent_path); @@ -357,23 +440,20 @@ struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, ret = __sdcardfs_lookup(dentry, flags, &lower_parent_path, SDCARDFS_I(dir)->userid); if (IS_ERR(ret)) - { goto out; - } if (ret) dentry = ret; - if (dentry->d_inode) { - fsstack_copy_attr_times(dentry->d_inode, - sdcardfs_lower_inode(dentry->d_inode)); - /* get drived permission */ - mutex_lock(&dentry->d_inode->i_mutex); + if (d_inode(dentry)) { + fsstack_copy_attr_times(d_inode(dentry), + sdcardfs_lower_inode(d_inode(dentry))); + /* get derived permission */ get_derived_permission(parent, dentry); - fix_derived_permission(dentry->d_inode); - mutex_unlock(&dentry->d_inode->i_mutex); + fixup_tmp_permissions(d_inode(dentry)); + fixup_lower_ownership(dentry, dentry->d_name.name); } /* update parent directory's atime */ - fsstack_copy_attr_atime(parent->d_inode, - sdcardfs_lower_inode(parent->d_inode)); + fsstack_copy_attr_atime(d_inode(parent), + sdcardfs_lower_inode(d_inode(parent))); out: sdcardfs_put_lower_path(parent, &lower_parent_path); diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c index a6522286d731..953d2156d2e9 100644 --- a/fs/sdcardfs/main.c +++ b/fs/sdcardfs/main.c @@ -28,9 +28,8 @@ enum { Opt_fsgid, Opt_gid, Opt_debug, - Opt_lower_fs, Opt_mask, - Opt_multiuser, // May need? + Opt_multiuser, Opt_userid, Opt_reserved_mb, Opt_err, @@ -49,7 +48,8 @@ static const match_table_t sdcardfs_tokens = { }; static int parse_options(struct super_block *sb, char *options, int silent, - int *debug, struct sdcardfs_mount_options *opts) + int *debug, struct sdcardfs_vfsmount_options *vfsopts, + struct sdcardfs_mount_options *opts) { char *p; substring_t args[MAX_OPT_ARGS]; @@ -58,10 +58,10 @@ static int parse_options(struct super_block *sb, char *options, int silent, /* by default, we use AID_MEDIA_RW as uid, gid */ opts->fs_low_uid = AID_MEDIA_RW; opts->fs_low_gid = AID_MEDIA_RW; - opts->mask = 0; + vfsopts->mask = 0; opts->multiuser = false; opts->fs_user_id = 0; - opts->gid = 0; + vfsopts->gid = 0; /* by default, 0MB is reserved */ opts->reserved_mb = 0; @@ -72,6 +72,7 @@ static int parse_options(struct super_block *sb, char *options, int silent, while ((p = strsep(&options, ",")) != NULL) { int token; + if (!*p) continue; @@ -94,7 +95,7 @@ static int parse_options(struct super_block *sb, char *options, int silent, case Opt_gid: if (match_int(&args[0], &option)) return 0; - opts->gid = option; + vfsopts->gid = option; break; case Opt_userid: if (match_int(&args[0], &option)) @@ -104,7 +105,7 @@ static int parse_options(struct super_block *sb, char *options, int silent, case Opt_mask: if (match_int(&args[0], &option)) return 0; - opts->mask = option; + vfsopts->mask = option; break; case Opt_multiuser: opts->multiuser = true; @@ -116,25 +117,81 @@ static int parse_options(struct super_block *sb, char *options, int silent, break; /* unknown option */ default: - if (!silent) { - printk( KERN_ERR "Unrecognized mount option \"%s\" " - "or missing value", p); - } + if (!silent) + pr_err("Unrecognized mount option \"%s\" or missing value", p); return -EINVAL; } } if (*debug) { - printk( KERN_INFO "sdcardfs : options - debug:%d\n", *debug); - printk( KERN_INFO "sdcardfs : options - uid:%d\n", + pr_info("sdcardfs : options - debug:%d\n", *debug); + pr_info("sdcardfs : options - uid:%d\n", opts->fs_low_uid); - printk( KERN_INFO "sdcardfs : options - gid:%d\n", + pr_info("sdcardfs : options - gid:%d\n", opts->fs_low_gid); } return 0; } +int parse_options_remount(struct super_block *sb, char *options, int silent, + struct sdcardfs_vfsmount_options *vfsopts) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int option; + int debug; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + + if (!*p) + continue; + + token = match_token(p, sdcardfs_tokens, args); + + switch (token) { + case Opt_debug: + debug = 1; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return 0; + vfsopts->gid = option; + + break; + case Opt_mask: + if (match_int(&args[0], &option)) + return 0; + vfsopts->mask = option; + break; + case Opt_multiuser: + case Opt_userid: + case Opt_fsuid: + case Opt_fsgid: + case Opt_reserved_mb: + pr_warn("Option \"%s\" can't be changed during remount\n", p); + break; + /* unknown option */ + default: + if (!silent) + pr_err("Unrecognized mount option \"%s\" or missing value", p); + return -EINVAL; + } + } + + if (debug) { + pr_info("sdcardfs : options - debug:%d\n", debug); + pr_info("sdcardfs : options - gid:%d\n", vfsopts->gid); + pr_info("sdcardfs : options - mask:%d\n", vfsopts->mask); + } + + return 0; +} + #if 0 /* * our custom d_alloc_root work-alike @@ -164,57 +221,58 @@ static struct dentry *sdcardfs_d_alloc_root(struct super_block *sb) #endif DEFINE_MUTEX(sdcardfs_super_list_lock); -LIST_HEAD(sdcardfs_super_list); EXPORT_SYMBOL_GPL(sdcardfs_super_list_lock); +LIST_HEAD(sdcardfs_super_list); EXPORT_SYMBOL_GPL(sdcardfs_super_list); /* * There is no need to lock the sdcardfs_super_info's rwsem as there is no * way anyone can have a reference to the superblock at this point in time. */ -static int sdcardfs_read_super(struct super_block *sb, const char *dev_name, - void *raw_data, int silent) +static int sdcardfs_read_super(struct vfsmount *mnt, struct super_block *sb, + const char *dev_name, void *raw_data, int silent) { int err = 0; int debug; struct super_block *lower_sb; struct path lower_path; struct sdcardfs_sb_info *sb_info; + struct sdcardfs_vfsmount_options *mnt_opt = mnt->data; struct inode *inode; - printk(KERN_INFO "sdcardfs version 2.0\n"); + pr_info("sdcardfs version 2.0\n"); if (!dev_name) { - printk(KERN_ERR - "sdcardfs: read_super: missing dev_name argument\n"); + pr_err("sdcardfs: read_super: missing dev_name argument\n"); err = -EINVAL; goto out; } - printk(KERN_INFO "sdcardfs: dev_name -> %s\n", dev_name); - printk(KERN_INFO "sdcardfs: options -> %s\n", (char *)raw_data); + pr_info("sdcardfs: dev_name -> %s\n", dev_name); + pr_info("sdcardfs: options -> %s\n", (char *)raw_data); + pr_info("sdcardfs: mnt -> %p\n", mnt); /* parse lower path */ err = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &lower_path); if (err) { - printk(KERN_ERR "sdcardfs: error accessing lower directory '%s'\n", dev_name); + pr_err("sdcardfs: error accessing lower directory '%s'\n", dev_name); goto out; } /* allocate superblock private data */ sb->s_fs_info = kzalloc(sizeof(struct sdcardfs_sb_info), GFP_KERNEL); if (!SDCARDFS_SB(sb)) { - printk(KERN_CRIT "sdcardfs: read_super: out of memory\n"); + pr_crit("sdcardfs: read_super: out of memory\n"); err = -ENOMEM; goto out_free; } sb_info = sb->s_fs_info; /* parse options */ - err = parse_options(sb, raw_data, silent, &debug, &sb_info->options); + err = parse_options(sb, raw_data, silent, &debug, mnt_opt, &sb_info->options); if (err) { - printk(KERN_ERR "sdcardfs: invalid options\n"); + pr_err("sdcardfs: invalid options\n"); goto out_freesbi; } @@ -236,7 +294,7 @@ static int sdcardfs_read_super(struct super_block *sb, const char *dev_name, sb->s_op = &sdcardfs_sops; /* get a new inode and allocate our root dentry */ - inode = sdcardfs_iget(sb, lower_path.dentry->d_inode, 0); + inode = sdcardfs_iget(sb, d_inode(lower_path.dentry), 0); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_sput; @@ -267,23 +325,24 @@ static int sdcardfs_read_super(struct super_block *sb, const char *dev_name, /* setup permission policy */ sb_info->obbpath_s = kzalloc(PATH_MAX, GFP_KERNEL); mutex_lock(&sdcardfs_super_list_lock); - if(sb_info->options.multiuser) { - setup_derived_state(sb->s_root->d_inode, PERM_PRE_ROOT, sb_info->options.fs_user_id, AID_ROOT, false); + if (sb_info->options.multiuser) { + setup_derived_state(d_inode(sb->s_root), PERM_PRE_ROOT, + sb_info->options.fs_user_id, AID_ROOT, + false, d_inode(sb->s_root)); snprintf(sb_info->obbpath_s, PATH_MAX, "%s/obb", dev_name); - /*err = prepare_dir(sb_info->obbpath_s, - sb_info->options.fs_low_uid, - sb_info->options.fs_low_gid, 00755);*/ } else { - setup_derived_state(sb->s_root->d_inode, PERM_ROOT, sb_info->options.fs_low_uid, AID_ROOT, false); + setup_derived_state(d_inode(sb->s_root), PERM_ROOT, + sb_info->options.fs_user_id, AID_ROOT, + false, d_inode(sb->s_root)); snprintf(sb_info->obbpath_s, PATH_MAX, "%s/Android/obb", dev_name); } - fix_derived_permission(sb->s_root->d_inode); + fixup_tmp_permissions(d_inode(sb->s_root)); sb_info->sb = sb; list_add(&sb_info->list, &sdcardfs_super_list); mutex_unlock(&sdcardfs_super_list_lock); if (!silent) - printk(KERN_INFO "sdcardfs: mounted on top of %s type %s\n", + pr_info("sdcardfs: mounted on top of %s type %s\n", dev_name, lower_sb->s_type->name); goto out; /* all is well */ @@ -306,9 +365,11 @@ out: } /* A feature which supports mount_nodev() with options */ -static struct dentry *mount_nodev_with_options(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, const char *, void *, int)) +static struct dentry *mount_nodev_with_options(struct vfsmount *mnt, + struct file_system_type *fs_type, int flags, + const char *dev_name, void *data, + int (*fill_super)(struct vfsmount *, struct super_block *, + const char *, void *, int)) { int error; @@ -319,7 +380,7 @@ static struct dentry *mount_nodev_with_options(struct file_system_type *fs_type, s->s_flags = flags; - error = fill_super(s, dev_name, data, flags & MS_SILENT ? 1 : 0); + error = fill_super(mnt, s, dev_name, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); return ERR_PTR(error); @@ -328,19 +389,34 @@ static struct dentry *mount_nodev_with_options(struct file_system_type *fs_type, return dget(s->s_root); } -struct dentry *sdcardfs_mount(struct file_system_type *fs_type, int flags, +static struct dentry *sdcardfs_mount(struct vfsmount *mnt, + struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data) { /* * dev_name is a lower_path_name, * raw_data is a option string. */ - return mount_nodev_with_options(fs_type, flags, dev_name, - raw_data, sdcardfs_read_super); + return mount_nodev_with_options(mnt, fs_type, flags, dev_name, + raw_data, sdcardfs_read_super); +} + +static struct dentry *sdcardfs_mount_wrn(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + WARN(1, "sdcardfs does not support mount. Use mount2.\n"); + return ERR_PTR(-EINVAL); } -void sdcardfs_kill_sb(struct super_block *sb) { +void *sdcardfs_alloc_mnt_data(void) +{ + return kmalloc(sizeof(struct sdcardfs_vfsmount_options), GFP_KERNEL); +} + +void sdcardfs_kill_sb(struct super_block *sb) +{ struct sdcardfs_sb_info *sbi; + if (sb->s_magic == SDCARDFS_SUPER_MAGIC) { sbi = SDCARDFS_SB(sb); mutex_lock(&sdcardfs_super_list_lock); @@ -353,10 +429,13 @@ void sdcardfs_kill_sb(struct super_block *sb) { static struct file_system_type sdcardfs_fs_type = { .owner = THIS_MODULE, .name = SDCARDFS_NAME, - .mount = sdcardfs_mount, + .mount = sdcardfs_mount_wrn, + .mount2 = sdcardfs_mount, + .alloc_mnt_data = sdcardfs_alloc_mnt_data, .kill_sb = sdcardfs_kill_sb, .fs_flags = 0, }; +MODULE_ALIAS_FS(SDCARDFS_NAME); static int __init init_sdcardfs_fs(void) { @@ -392,10 +471,15 @@ static void __exit exit_sdcardfs_fs(void) pr_info("Completed sdcardfs module unload\n"); } -MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University" - " (http://www.fsl.cs.sunysb.edu/)"); -MODULE_DESCRIPTION("Wrapfs " SDCARDFS_VERSION - " (http://wrapfs.filesystems.org/)"); +/* Original wrapfs authors */ +MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University (http://www.fsl.cs.sunysb.edu/)"); + +/* Original sdcardfs authors */ +MODULE_AUTHOR("Woojoong Lee, Daeho Jeong, Kitae Lee, Yeongjin Gil System Memory Lab., Samsung Electronics"); + +/* Current maintainer */ +MODULE_AUTHOR("Daniel Rosenberg, Google"); +MODULE_DESCRIPTION("Sdcardfs " SDCARDFS_VERSION); MODULE_LICENSE("GPL"); module_init(init_sdcardfs_fs); diff --git a/fs/sdcardfs/mmap.c b/fs/sdcardfs/mmap.c index e21f64675a80..b61f82275e7d 100644 --- a/fs/sdcardfs/mmap.c +++ b/fs/sdcardfs/mmap.c @@ -23,28 +23,46 @@ static int sdcardfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { int err; - struct file *file, *lower_file; + struct file *file; const struct vm_operations_struct *lower_vm_ops; - struct vm_area_struct lower_vma; - memcpy(&lower_vma, vma, sizeof(struct vm_area_struct)); - file = lower_vma.vm_file; + file = (struct file *)vma->vm_private_data; lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops; BUG_ON(!lower_vm_ops); - lower_file = sdcardfs_lower_file(file); - /* - * XXX: vm_ops->fault may be called in parallel. Because we have to - * resort to temporarily changing the vma->vm_file to point to the - * lower file, a concurrent invocation of sdcardfs_fault could see a - * different value. In this workaround, we keep a different copy of - * the vma structure in our stack, so we never expose a different - * value of the vma->vm_file called to us, even temporarily. A - * better fix would be to change the calling semantics of ->fault to - * take an explicit file pointer. - */ - lower_vma.vm_file = lower_file; - err = lower_vm_ops->fault(&lower_vma, vmf); + err = lower_vm_ops->fault(vma, vmf); + return err; +} + +static void sdcardfs_vm_open(struct vm_area_struct *vma) +{ + struct file *file = (struct file *)vma->vm_private_data; + + get_file(file); +} + +static void sdcardfs_vm_close(struct vm_area_struct *vma) +{ + struct file *file = (struct file *)vma->vm_private_data; + + fput(file); +} + +static int sdcardfs_page_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + int err = 0; + struct file *file; + const struct vm_operations_struct *lower_vm_ops; + + file = (struct file *)vma->vm_private_data; + lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops; + BUG_ON(!lower_vm_ops); + if (!lower_vm_ops->page_mkwrite) + goto out; + + err = lower_vm_ops->page_mkwrite(vma, vmf); +out: return err; } @@ -52,30 +70,20 @@ static ssize_t sdcardfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { /* - * This function returns zero on purpose in order to support direct IO. - * __dentry_open checks a_ops->direct_IO and returns EINVAL if it is null. - * - * However, this function won't be called by certain file operations - * including generic fs functions. * reads and writes are delivered to - * the lower file systems and the direct IOs will be handled by them. - * - * NOTE: exceptionally, on the recent kernels (since Linux 3.8.x), - * swap_writepage invokes this function directly. + * This function should never be called directly. We need it + * to exist, to get past a check in open_check_o_direct(), + * which is called from do_last(). */ - printk(KERN_INFO "%s, operation is not supported\n", __func__); - return 0; + return -EINVAL; } -/* - * XXX: the default address_space_ops for sdcardfs is empty. We cannot set - * our inode->i_mapping->a_ops to NULL because too many code paths expect - * the a_ops vector to be non-NULL. - */ const struct address_space_operations sdcardfs_aops = { - /* empty on purpose */ .direct_IO = sdcardfs_direct_IO, }; const struct vm_operations_struct sdcardfs_vm_ops = { .fault = sdcardfs_fault, + .page_mkwrite = sdcardfs_page_mkwrite, + .open = sdcardfs_vm_open, + .close = sdcardfs_vm_close, }; diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h index 923ba101dfa9..85341e753f8c 100644 --- a/fs/sdcardfs/multiuser.h +++ b/fs/sdcardfs/multiuser.h @@ -18,20 +18,36 @@ * General Public License. */ -#define MULTIUSER_APP_PER_USER_RANGE 100000 +#define AID_USER_OFFSET 100000 /* offset for uid ranges for each user */ +#define AID_APP_START 10000 /* first app user */ +#define AID_APP_END 19999 /* last app user */ +#define AID_CACHE_GID_START 20000 /* start of gids for apps to mark cached data */ +#define AID_EXT_GID_START 30000 /* start of gids for apps to mark external data */ +#define AID_EXT_CACHE_GID_START 40000 /* start of gids for apps to mark external cached data */ +#define AID_EXT_CACHE_GID_END 49999 /* end of gids for apps to mark external cached data */ +#define AID_SHARED_GID_START 50000 /* start of gids for apps in each user to share */ typedef uid_t userid_t; typedef uid_t appid_t; -static inline userid_t multiuser_get_user_id(uid_t uid) { - return uid / MULTIUSER_APP_PER_USER_RANGE; +static inline uid_t multiuser_get_uid(userid_t user_id, appid_t app_id) +{ + return (user_id * AID_USER_OFFSET) + (app_id % AID_USER_OFFSET); } -static inline appid_t multiuser_get_app_id(uid_t uid) { - return uid % MULTIUSER_APP_PER_USER_RANGE; +static inline bool uid_is_app(uid_t uid) +{ + appid_t appid = uid % AID_USER_OFFSET; + + return appid >= AID_APP_START && appid <= AID_APP_END; } -static inline uid_t multiuser_get_uid(userid_t userId, appid_t appId) { - return userId * MULTIUSER_APP_PER_USER_RANGE + (appId % MULTIUSER_APP_PER_USER_RANGE); +static inline gid_t multiuser_get_ext_cache_gid(uid_t uid) +{ + return uid - AID_APP_START + AID_EXT_CACHE_GID_START; } +static inline gid_t multiuser_get_ext_gid(uid_t uid) +{ + return uid - AID_APP_START + AID_EXT_GID_START; +} diff --git a/fs/sdcardfs/packagelist.c b/fs/sdcardfs/packagelist.c index 9c3340528eee..89196e31073e 100644 --- a/fs/sdcardfs/packagelist.c +++ b/fs/sdcardfs/packagelist.c @@ -20,8 +20,10 @@ #include "sdcardfs.h" #include <linux/hashtable.h> +#include <linux/ctype.h> #include <linux/delay.h> - +#include <linux/radix-tree.h> +#include <linux/dcache.h> #include <linux/init.h> #include <linux/module.h> @@ -29,386 +31,835 @@ #include <linux/configfs.h> -#define STRING_BUF_SIZE (512) - struct hashtable_entry { struct hlist_node hlist; - void *key; - unsigned int value; + struct hlist_node dlist; /* for deletion cleanup */ + struct qstr key; + atomic_t value; }; -struct sb_list { - struct super_block *sb; - struct list_head list; -}; +static DEFINE_HASHTABLE(package_to_appid, 8); +static DEFINE_HASHTABLE(package_to_userid, 8); +static DEFINE_HASHTABLE(ext_to_groupid, 8); -struct packagelist_data { - DECLARE_HASHTABLE(package_to_appid,8); - struct mutex hashtable_lock; -}; +static struct kmem_cache *hashtable_entry_cachep; -static struct packagelist_data *pkgl_data_all; +static unsigned int full_name_case_hash(const unsigned char *name, unsigned int len) +{ + unsigned long hash = init_name_hash(); -static struct kmem_cache *hashtable_entry_cachep; + while (len--) + hash = partial_name_hash(tolower(*name++), hash); + return end_name_hash(hash); +} -static unsigned int str_hash(const char *key) { - int i; - unsigned int h = strlen(key); - char *data = (char *)key; +static inline void qstr_init(struct qstr *q, const char *name) +{ + q->name = name; + q->len = strlen(q->name); + q->hash = full_name_case_hash(q->name, q->len); +} + +static inline int qstr_copy(const struct qstr *src, struct qstr *dest) +{ + dest->name = kstrdup(src->name, GFP_KERNEL); + dest->hash_len = src->hash_len; + return !!dest->name; +} + + +static appid_t __get_appid(const struct qstr *key) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + appid_t ret_id; - for (i = 0; i < strlen(key); i++) { - h = h * 31 + *data; - data++; + rcu_read_lock(); + hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + ret_id = atomic_read(&hash_cur->value); + rcu_read_unlock(); + return ret_id; + } } - return h; + rcu_read_unlock(); + return 0; +} + +appid_t get_appid(const char *key) +{ + struct qstr q; + + qstr_init(&q, key); + return __get_appid(&q); } -appid_t get_appid(void *pkgl_id, const char *app_name) +static appid_t __get_ext_gid(const struct qstr *key) { - struct packagelist_data *pkgl_dat = pkgl_data_all; struct hashtable_entry *hash_cur; - unsigned int hash = str_hash(app_name); + unsigned int hash = key->hash; appid_t ret_id; - mutex_lock(&pkgl_dat->hashtable_lock); - hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { - if (!strcasecmp(app_name, hash_cur->key)) { - ret_id = (appid_t)hash_cur->value; - mutex_unlock(&pkgl_dat->hashtable_lock); + rcu_read_lock(); + hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + ret_id = atomic_read(&hash_cur->value); + rcu_read_unlock(); return ret_id; } } - mutex_unlock(&pkgl_dat->hashtable_lock); + rcu_read_unlock(); + return 0; +} + +appid_t get_ext_gid(const char *key) +{ + struct qstr q; + + qstr_init(&q, key); + return __get_ext_gid(&q); +} + +static appid_t __is_excluded(const struct qstr *app_name, userid_t user) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = app_name->hash; + + rcu_read_lock(); + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (atomic_read(&hash_cur->value) == user && + qstr_case_eq(app_name, &hash_cur->key)) { + rcu_read_unlock(); + return 1; + } + } + rcu_read_unlock(); return 0; } +appid_t is_excluded(const char *key, userid_t user) +{ + struct qstr q; + qstr_init(&q, key); + return __is_excluded(&q, user); +} + /* Kernel has already enforced everything we returned through * derive_permissions_locked(), so this is used to lock down access - * even further, such as enforcing that apps hold sdcard_rw. */ -int check_caller_access_to_name(struct inode *parent_node, const char* name) { + * even further, such as enforcing that apps hold sdcard_rw. + */ +int check_caller_access_to_name(struct inode *parent_node, const struct qstr *name) +{ + struct qstr q_autorun = QSTR_LITERAL("autorun.inf"); + struct qstr q__android_secure = QSTR_LITERAL(".android_secure"); + struct qstr q_android_secure = QSTR_LITERAL("android_secure"); /* Always block security-sensitive files at root */ if (parent_node && SDCARDFS_I(parent_node)->perm == PERM_ROOT) { - if (!strcasecmp(name, "autorun.inf") - || !strcasecmp(name, ".android_secure") - || !strcasecmp(name, "android_secure")) { + if (qstr_case_eq(name, &q_autorun) + || qstr_case_eq(name, &q__android_secure) + || qstr_case_eq(name, &q_android_secure)) { return 0; } } /* Root always has access; access for any other UIDs should always - * be controlled through packages.list. */ - if (from_kuid(&init_user_ns, current_fsuid()) == 0) { + * be controlled through packages.list. + */ + if (from_kuid(&init_user_ns, current_fsuid()) == 0) return 1; - } /* No extra permissions to enforce */ return 1; } /* This function is used when file opening. The open flags must be - * checked before calling check_caller_access_to_name() */ -int open_flags_to_access_mode(int open_flags) { - if((open_flags & O_ACCMODE) == O_RDONLY) { + * checked before calling check_caller_access_to_name() + */ +int open_flags_to_access_mode(int open_flags) +{ + if ((open_flags & O_ACCMODE) == O_RDONLY) return 0; /* R_OK */ - } else if ((open_flags & O_ACCMODE) == O_WRONLY) { + if ((open_flags & O_ACCMODE) == O_WRONLY) return 1; /* W_OK */ - } else { - /* Probably O_RDRW, but treat as default to be safe */ + /* Probably O_RDRW, but treat as default to be safe */ return 1; /* R_OK | W_OK */ +} + +static struct hashtable_entry *alloc_hashtable_entry(const struct qstr *key, + appid_t value) +{ + struct hashtable_entry *ret = kmem_cache_alloc(hashtable_entry_cachep, + GFP_KERNEL); + if (!ret) + return NULL; + INIT_HLIST_NODE(&ret->dlist); + INIT_HLIST_NODE(&ret->hlist); + + if (!qstr_copy(key, &ret->key)) { + kmem_cache_free(hashtable_entry_cachep, ret); + return NULL; } + + atomic_set(&ret->value, value); + return ret; } -static int insert_str_to_int_lock(struct packagelist_data *pkgl_dat, char *key, - unsigned int value) +static int insert_packagelist_appid_entry_locked(const struct qstr *key, appid_t value) { struct hashtable_entry *hash_cur; struct hashtable_entry *new_entry; - unsigned int hash = str_hash(key); + unsigned int hash = key->hash; - hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { - if (!strcasecmp(key, hash_cur->key)) { - hash_cur->value = value; + hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + atomic_set(&hash_cur->value, value); return 0; } } - new_entry = kmem_cache_alloc(hashtable_entry_cachep, GFP_KERNEL); + new_entry = alloc_hashtable_entry(key, value); if (!new_entry) return -ENOMEM; - new_entry->key = kstrdup(key, GFP_KERNEL); - new_entry->value = value; - hash_add(pkgl_dat->package_to_appid, &new_entry->hlist, hash); + hash_add_rcu(package_to_appid, &new_entry->hlist, hash); return 0; } -static void fixup_perms(struct super_block *sb) { - if (sb && sb->s_magic == SDCARDFS_SUPER_MAGIC) { - mutex_lock(&sb->s_root->d_inode->i_mutex); - get_derive_permissions_recursive(sb->s_root); - mutex_unlock(&sb->s_root->d_inode->i_mutex); +static int insert_ext_gid_entry_locked(const struct qstr *key, appid_t value) +{ + struct hashtable_entry *hash_cur; + struct hashtable_entry *new_entry; + unsigned int hash = key->hash; + + /* An extension can only belong to one gid */ + hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) + return -EINVAL; } + new_entry = alloc_hashtable_entry(key, value); + if (!new_entry) + return -ENOMEM; + hash_add_rcu(ext_to_groupid, &new_entry->hlist, hash); + return 0; } -static int insert_str_to_int(struct packagelist_data *pkgl_dat, char *key, - unsigned int value) { - int ret; +static int insert_userid_exclude_entry_locked(const struct qstr *key, userid_t value) +{ + struct hashtable_entry *hash_cur; + struct hashtable_entry *new_entry; + unsigned int hash = key->hash; + + /* Only insert if not already present */ + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (atomic_read(&hash_cur->value) == value && + qstr_case_eq(key, &hash_cur->key)) + return 0; + } + new_entry = alloc_hashtable_entry(key, value); + if (!new_entry) + return -ENOMEM; + hash_add_rcu(package_to_userid, &new_entry->hlist, hash); + return 0; +} + +static void fixup_all_perms_name(const struct qstr *key) +{ struct sdcardfs_sb_info *sbinfo; - mutex_lock(&sdcardfs_super_list_lock); - mutex_lock(&pkgl_dat->hashtable_lock); - ret = insert_str_to_int_lock(pkgl_dat, key, value); - mutex_unlock(&pkgl_dat->hashtable_lock); + struct limit_search limit = { + .flags = BY_NAME, + .name = QSTR_INIT(key->name, key->len), + }; + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo_has_sdcard_magic(sbinfo)) + fixup_perms_recursive(sbinfo->sb->s_root, &limit); + } +} +static void fixup_all_perms_name_userid(const struct qstr *key, userid_t userid) +{ + struct sdcardfs_sb_info *sbinfo; + struct limit_search limit = { + .flags = BY_NAME | BY_USERID, + .name = QSTR_INIT(key->name, key->len), + .userid = userid, + }; list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { - if (sbinfo) { - fixup_perms(sbinfo->sb); - } + if (sbinfo_has_sdcard_magic(sbinfo)) + fixup_perms_recursive(sbinfo->sb->s_root, &limit); } +} + +static void fixup_all_perms_userid(userid_t userid) +{ + struct sdcardfs_sb_info *sbinfo; + struct limit_search limit = { + .flags = BY_USERID, + .userid = userid, + }; + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo_has_sdcard_magic(sbinfo)) + fixup_perms_recursive(sbinfo->sb->s_root, &limit); + } +} + +static int insert_packagelist_entry(const struct qstr *key, appid_t value) +{ + int err; + + mutex_lock(&sdcardfs_super_list_lock); + err = insert_packagelist_appid_entry_locked(key, value); + if (!err) + fixup_all_perms_name(key); mutex_unlock(&sdcardfs_super_list_lock); - return ret; + + return err; } -static void remove_str_to_int_lock(struct hashtable_entry *h_entry) { - kfree(h_entry->key); - hash_del(&h_entry->hlist); - kmem_cache_free(hashtable_entry_cachep, h_entry); +static int insert_ext_gid_entry(const struct qstr *key, appid_t value) +{ + int err; + + mutex_lock(&sdcardfs_super_list_lock); + err = insert_ext_gid_entry_locked(key, value); + mutex_unlock(&sdcardfs_super_list_lock); + + return err; } -static void remove_str_to_int(struct packagelist_data *pkgl_dat, const char *key) +static int insert_userid_exclude_entry(const struct qstr *key, userid_t value) { - struct sdcardfs_sb_info *sbinfo; - struct hashtable_entry *hash_cur; - unsigned int hash = str_hash(key); + int err; + mutex_lock(&sdcardfs_super_list_lock); - mutex_lock(&pkgl_dat->hashtable_lock); - hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { - if (!strcasecmp(key, hash_cur->key)) { - remove_str_to_int_lock(hash_cur); + err = insert_userid_exclude_entry_locked(key, value); + if (!err) + fixup_all_perms_name_userid(key, value); + mutex_unlock(&sdcardfs_super_list_lock); + + return err; +} + +static void free_hashtable_entry(struct hashtable_entry *entry) +{ + kfree(entry->key.name); + kmem_cache_free(hashtable_entry_cachep, entry); +} + +static void remove_packagelist_entry_locked(const struct qstr *key) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + struct hlist_node *h_t; + HLIST_HEAD(free_list); + + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + } + hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); break; } } - mutex_unlock(&pkgl_dat->hashtable_lock); - list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { - if (sbinfo) { - fixup_perms(sbinfo->sb); + synchronize_rcu(); + hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist) + free_hashtable_entry(hash_cur); +} + +static void remove_packagelist_entry(const struct qstr *key) +{ + mutex_lock(&sdcardfs_super_list_lock); + remove_packagelist_entry_locked(key); + fixup_all_perms_name(key); + mutex_unlock(&sdcardfs_super_list_lock); +} + +static void remove_ext_gid_entry_locked(const struct qstr *key, gid_t group) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + + hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key) && atomic_read(&hash_cur->value) == group) { + hash_del_rcu(&hash_cur->hlist); + synchronize_rcu(); + free_hashtable_entry(hash_cur); + break; } } +} + +static void remove_ext_gid_entry(const struct qstr *key, gid_t group) +{ + mutex_lock(&sdcardfs_super_list_lock); + remove_ext_gid_entry_locked(key, group); mutex_unlock(&sdcardfs_super_list_lock); - return; } -static void remove_all_hashentrys(struct packagelist_data *pkgl_dat) +static void remove_userid_all_entry_locked(userid_t userid) { struct hashtable_entry *hash_cur; struct hlist_node *h_t; + HLIST_HEAD(free_list); int i; - mutex_lock(&pkgl_dat->hashtable_lock); - hash_for_each_safe(pkgl_dat->package_to_appid, i, h_t, hash_cur, hlist) - remove_str_to_int_lock(hash_cur); - mutex_unlock(&pkgl_dat->hashtable_lock); - hash_init(pkgl_dat->package_to_appid); + + hash_for_each_rcu(package_to_userid, i, hash_cur, hlist) { + if (atomic_read(&hash_cur->value) == userid) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + } + synchronize_rcu(); + hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist) { + free_hashtable_entry(hash_cur); + } } -static struct packagelist_data * packagelist_create(void) +static void remove_userid_all_entry(userid_t userid) { - struct packagelist_data *pkgl_dat; + mutex_lock(&sdcardfs_super_list_lock); + remove_userid_all_entry_locked(userid); + fixup_all_perms_userid(userid); + mutex_unlock(&sdcardfs_super_list_lock); +} - pkgl_dat = kmalloc(sizeof(*pkgl_dat), GFP_KERNEL | __GFP_ZERO); - if (!pkgl_dat) { - printk(KERN_ERR "sdcardfs: Failed to create hash\n"); - return ERR_PTR(-ENOMEM); +static void remove_userid_exclude_entry_locked(const struct qstr *key, userid_t userid) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key) && + atomic_read(&hash_cur->value) == userid) { + hash_del_rcu(&hash_cur->hlist); + synchronize_rcu(); + free_hashtable_entry(hash_cur); + break; + } } +} - mutex_init(&pkgl_dat->hashtable_lock); - hash_init(pkgl_dat->package_to_appid); - - return pkgl_dat; +static void remove_userid_exclude_entry(const struct qstr *key, userid_t userid) +{ + mutex_lock(&sdcardfs_super_list_lock); + remove_userid_exclude_entry_locked(key, userid); + fixup_all_perms_name_userid(key, userid); + mutex_unlock(&sdcardfs_super_list_lock); } -static void packagelist_destroy(struct packagelist_data *pkgl_dat) +static void packagelist_destroy(void) { - remove_all_hashentrys(pkgl_dat); - printk(KERN_INFO "sdcardfs: destroyed packagelist pkgld\n"); - kfree(pkgl_dat); + struct hashtable_entry *hash_cur; + struct hlist_node *h_t; + HLIST_HEAD(free_list); + int i; + + mutex_lock(&sdcardfs_super_list_lock); + hash_for_each_rcu(package_to_appid, i, hash_cur, hlist) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + hash_for_each_rcu(package_to_userid, i, hash_cur, hlist) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + synchronize_rcu(); + hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist) + free_hashtable_entry(hash_cur); + mutex_unlock(&sdcardfs_super_list_lock); + pr_info("sdcardfs: destroyed packagelist pkgld\n"); +} + +#define SDCARDFS_CONFIGFS_ATTR(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO | S_IWUGO, \ + .ca_owner = THIS_MODULE, \ + .show = _pfx##_name##_show, \ + .store = _pfx##_name##_store, \ +} + +#define SDCARDFS_CONFIGFS_ATTR_RO(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO, \ + .ca_owner = THIS_MODULE, \ + .show = _pfx##_name##_show, \ +} + +#define SDCARDFS_CONFIGFS_ATTR_WO(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IWUGO, \ + .ca_owner = THIS_MODULE, \ + .store = _pfx##_name##_store, \ } -struct package_appid { +struct package_details { struct config_item item; - int add_pid; + struct qstr name; }; -static inline struct package_appid *to_package_appid(struct config_item *item) +static inline struct package_details *to_package_details(struct config_item *item) { - return item ? container_of(item, struct package_appid, item) : NULL; + return item ? container_of(item, struct package_details, item) : NULL; +} + +static ssize_t package_details_appid_show(struct config_item *item, char *page) +{ + return scnprintf(page, PAGE_SIZE, "%u\n", __get_appid(&to_package_details(item)->name)); +} + +static ssize_t package_details_appid_store(struct config_item *item, + const char *page, size_t count) +{ + unsigned int tmp; + int ret; + + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + + ret = insert_packagelist_entry(&to_package_details(item)->name, tmp); + + if (ret) + return ret; + + return count; } -static ssize_t package_appid_attr_show(struct config_item *item, +static ssize_t package_details_excluded_userids_show(struct config_item *item, char *page) { - ssize_t count; - count = sprintf(page, "%d\n", get_appid(pkgl_data_all, item->ci_name)); + struct package_details *package_details = to_package_details(item); + struct hashtable_entry *hash_cur; + unsigned int hash = package_details->name.hash; + int count = 0; + + rcu_read_lock(); + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (qstr_case_eq(&package_details->name, &hash_cur->key)) + count += scnprintf(page + count, PAGE_SIZE - count, + "%d ", atomic_read(&hash_cur->value)); + } + rcu_read_unlock(); + if (count) + count--; + count += scnprintf(page + count, PAGE_SIZE - count, "\n"); return count; } -static ssize_t package_appid_attr_store(struct config_item *item, +static ssize_t package_details_excluded_userids_store(struct config_item *item, const char *page, size_t count) { - struct package_appid *package_appid = to_package_appid(item); - unsigned long tmp; - char *p = (char *) page; + unsigned int tmp; int ret; - tmp = simple_strtoul(p, &p, 10); - if (!p || (*p && (*p != '\n'))) - return -EINVAL; + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + + ret = insert_userid_exclude_entry(&to_package_details(item)->name, tmp); - if (tmp > INT_MAX) - return -ERANGE; - ret = insert_str_to_int(pkgl_data_all, item->ci_name, (unsigned int)tmp); - package_appid->add_pid = tmp; if (ret) return ret; return count; } -static struct configfs_attribute package_appid_attr_add_pid = { - .ca_owner = THIS_MODULE, - .ca_name = "appid", - .ca_mode = S_IRUGO | S_IWUGO, - .show = package_appid_attr_show, - .store = package_appid_attr_store, -}; +static ssize_t package_details_clear_userid_store(struct config_item *item, + const char *page, size_t count) +{ + unsigned int tmp; + int ret; -static struct configfs_attribute *package_appid_attrs[] = { - &package_appid_attr_add_pid, - NULL, -}; + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + remove_userid_exclude_entry(&to_package_details(item)->name, tmp); + return count; +} -static void package_appid_release(struct config_item *item) +static void package_details_release(struct config_item *item) { - printk(KERN_INFO "sdcardfs: removing %s\n", item->ci_dentry->d_name.name); - /* item->ci_name is freed already, so we rely on the dentry */ - remove_str_to_int(pkgl_data_all, item->ci_dentry->d_name.name); - kfree(to_package_appid(item)); + struct package_details *package_details = to_package_details(item); + + pr_info("sdcardfs: removing %s\n", package_details->name.name); + remove_packagelist_entry(&package_details->name); + kfree(package_details->name.name); + kfree(package_details); } -static struct configfs_item_operations package_appid_item_ops = { - .release = package_appid_release, +SDCARDFS_CONFIGFS_ATTR(package_details_, appid); +SDCARDFS_CONFIGFS_ATTR(package_details_, excluded_userids); +SDCARDFS_CONFIGFS_ATTR_WO(package_details_, clear_userid); + +static struct configfs_attribute *package_details_attrs[] = { + &package_details_attr_appid, + &package_details_attr_excluded_userids, + &package_details_attr_clear_userid, + NULL, +}; + +static struct configfs_item_operations package_details_item_ops = { + .release = package_details_release, }; static struct config_item_type package_appid_type = { - .ct_item_ops = &package_appid_item_ops, - .ct_attrs = package_appid_attrs, + .ct_item_ops = &package_details_item_ops, + .ct_attrs = package_details_attrs, .ct_owner = THIS_MODULE, }; - -struct sdcardfs_packages { +struct extensions_value { struct config_group group; + unsigned int num; +}; + +struct extension_details { + struct config_item item; + struct qstr name; + unsigned int num; +}; + +static inline struct extensions_value *to_extensions_value(struct config_item *item) +{ + return item ? container_of(to_config_group(item), struct extensions_value, group) : NULL; +} + +static inline struct extension_details *to_extension_details(struct config_item *item) +{ + return item ? container_of(item, struct extension_details, item) : NULL; +} + +static void extension_details_release(struct config_item *item) +{ + struct extension_details *extension_details = to_extension_details(item); + + pr_info("sdcardfs: No longer mapping %s files to gid %d\n", + extension_details->name.name, extension_details->num); + remove_ext_gid_entry(&extension_details->name, extension_details->num); + kfree(extension_details->name.name); + kfree(extension_details); +} + +static struct configfs_item_operations extension_details_item_ops = { + .release = extension_details_release, +}; + +static struct config_item_type extension_details_type = { + .ct_item_ops = &extension_details_item_ops, + .ct_owner = THIS_MODULE, }; -static inline struct sdcardfs_packages *to_sdcardfs_packages(struct config_item *item) +static struct config_item *extension_details_make_item(struct config_group *group, const char *name) { - return item ? container_of(to_config_group(item), struct sdcardfs_packages, group) : NULL; + struct extensions_value *extensions_value = to_extensions_value(&group->cg_item); + struct extension_details *extension_details = kzalloc(sizeof(struct extension_details), GFP_KERNEL); + const char *tmp; + int ret; + + if (!extension_details) + return ERR_PTR(-ENOMEM); + + tmp = kstrdup(name, GFP_KERNEL); + if (!tmp) { + kfree(extension_details); + return ERR_PTR(-ENOMEM); + } + qstr_init(&extension_details->name, tmp); + ret = insert_ext_gid_entry(&extension_details->name, extensions_value->num); + + if (ret) { + kfree(extension_details->name.name); + kfree(extension_details); + return ERR_PTR(ret); + } + config_item_init_type_name(&extension_details->item, name, &extension_details_type); + + return &extension_details->item; } -static struct config_item *sdcardfs_packages_make_item(struct config_group *group, const char *name) +static struct configfs_group_operations extensions_value_group_ops = { + .make_item = extension_details_make_item, +}; + +static struct config_item_type extensions_name_type = { + .ct_group_ops = &extensions_value_group_ops, + .ct_owner = THIS_MODULE, +}; + +static struct config_group *extensions_make_group(struct config_group *group, const char *name) { - struct package_appid *package_appid; + struct extensions_value *extensions_value; + unsigned int tmp; + int ret; - package_appid = kzalloc(sizeof(struct package_appid), GFP_KERNEL); - if (!package_appid) + extensions_value = kzalloc(sizeof(struct extensions_value), GFP_KERNEL); + if (!extensions_value) return ERR_PTR(-ENOMEM); + ret = kstrtouint(name, 10, &tmp); + if (ret) { + kfree(extensions_value); + return ERR_PTR(ret); + } + + extensions_value->num = tmp; + config_group_init_type_name(&extensions_value->group, name, + &extensions_name_type); + return &extensions_value->group; +} + +static void extensions_drop_group(struct config_group *group, struct config_item *item) +{ + struct extensions_value *value = to_extensions_value(item); + + pr_info("sdcardfs: No longer mapping any files to gid %d\n", value->num); + kfree(value); +} + +static struct configfs_group_operations extensions_group_ops = { + .make_group = extensions_make_group, + .drop_item = extensions_drop_group, +}; - config_item_init_type_name(&package_appid->item, name, - &package_appid_type); +static struct config_item_type extensions_type = { + .ct_group_ops = &extensions_group_ops, + .ct_owner = THIS_MODULE, +}; - package_appid->add_pid = 0; +struct config_group extension_group = { + .cg_item = { + .ci_namebuf = "extensions", + .ci_type = &extensions_type, + }, +}; - return &package_appid->item; +static struct config_item *packages_make_item(struct config_group *group, const char *name) +{ + struct package_details *package_details; + const char *tmp; + + package_details = kzalloc(sizeof(struct package_details), GFP_KERNEL); + if (!package_details) + return ERR_PTR(-ENOMEM); + tmp = kstrdup(name, GFP_KERNEL); + if (!tmp) { + kfree(package_details); + return ERR_PTR(-ENOMEM); + } + qstr_init(&package_details->name, tmp); + config_item_init_type_name(&package_details->item, name, + &package_appid_type); + + return &package_details->item; } -static ssize_t packages_attr_show(struct config_item *item, - char *page) +static ssize_t packages_list_show(struct config_item *item, char *page) { - struct hashtable_entry *hash_cur; - struct hlist_node *h_t; + struct hashtable_entry *hash_cur_app; + struct hashtable_entry *hash_cur_user; int i; int count = 0, written = 0; - char errormsg[] = "<truncated>\n"; - - mutex_lock(&pkgl_data_all->hashtable_lock); - hash_for_each_safe(pkgl_data_all->package_to_appid, i, h_t, hash_cur, hlist) { - written = scnprintf(page + count, PAGE_SIZE - sizeof(errormsg) - count, "%s %d\n", (char *)hash_cur->key, hash_cur->value); - if (count + written == PAGE_SIZE - sizeof(errormsg)) { + const char errormsg[] = "<truncated>\n"; + unsigned int hash; + + rcu_read_lock(); + hash_for_each_rcu(package_to_appid, i, hash_cur_app, hlist) { + written = scnprintf(page + count, PAGE_SIZE - sizeof(errormsg) - count, "%s %d\n", + hash_cur_app->key.name, atomic_read(&hash_cur_app->value)); + hash = hash_cur_app->key.hash; + hash_for_each_possible_rcu(package_to_userid, hash_cur_user, hlist, hash) { + if (qstr_case_eq(&hash_cur_app->key, &hash_cur_user->key)) { + written += scnprintf(page + count + written - 1, + PAGE_SIZE - sizeof(errormsg) - count - written + 1, + " %d\n", atomic_read(&hash_cur_user->value)) - 1; + } + } + if (count + written == PAGE_SIZE - sizeof(errormsg) - 1) { count += scnprintf(page + count, PAGE_SIZE - count, errormsg); break; } count += written; } - mutex_unlock(&pkgl_data_all->hashtable_lock); + rcu_read_unlock(); return count; } -static struct configfs_attribute sdcardfs_packages_attr_description = { - .ca_owner = THIS_MODULE, - .ca_name = "packages_gid.list", - .ca_mode = S_IRUGO, - .show = packages_attr_show, -}; - -static struct configfs_attribute *sdcardfs_packages_attrs[] = { - &sdcardfs_packages_attr_description, - NULL, -}; - -static void sdcardfs_packages_release(struct config_item *item) +static ssize_t packages_remove_userid_store(struct config_item *item, + const char *page, size_t count) { + unsigned int tmp; + int ret; - printk(KERN_INFO "sdcardfs: destroyed something?\n"); - kfree(to_sdcardfs_packages(item)); + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + remove_userid_all_entry(tmp); + return count; } -static struct configfs_item_operations sdcardfs_packages_item_ops = { - .release = sdcardfs_packages_release, +static struct configfs_attribute packages_attr_packages_gid_list = { + .ca_name = "packages_gid.list", + .ca_mode = S_IRUGO, + .ca_owner = THIS_MODULE, + .show = packages_list_show, +}; + +SDCARDFS_CONFIGFS_ATTR_WO(packages_, remove_userid); + +static struct configfs_attribute *packages_attrs[] = { + &packages_attr_packages_gid_list, + &packages_attr_remove_userid, + NULL, }; /* * Note that, since no extra work is required on ->drop_item(), * no ->drop_item() is provided. */ -static struct configfs_group_operations sdcardfs_packages_group_ops = { - .make_item = sdcardfs_packages_make_item, +static struct configfs_group_operations packages_group_ops = { + .make_item = packages_make_item, }; -static struct config_item_type sdcardfs_packages_type = { - .ct_item_ops = &sdcardfs_packages_item_ops, - .ct_group_ops = &sdcardfs_packages_group_ops, - .ct_attrs = sdcardfs_packages_attrs, +static struct config_item_type packages_type = { + .ct_group_ops = &packages_group_ops, + .ct_attrs = packages_attrs, .ct_owner = THIS_MODULE, }; -static struct configfs_subsystem sdcardfs_packages_subsys = { +struct config_group *sd_default_groups[] = { + &extension_group, + NULL, +}; + +static struct configfs_subsystem sdcardfs_packages = { .su_group = { .cg_item = { .ci_namebuf = "sdcardfs", - .ci_type = &sdcardfs_packages_type, + .ci_type = &packages_type, }, + .default_groups = sd_default_groups, }, }; static int configfs_sdcardfs_init(void) { - int ret; - struct configfs_subsystem *subsys = &sdcardfs_packages_subsys; + int ret, i; + struct configfs_subsystem *subsys = &sdcardfs_packages; + for (i = 0; sd_default_groups[i]; i++) + config_group_init(sd_default_groups[i]); config_group_init(&subsys->su_group); mutex_init(&subsys->su_mutex); ret = configfs_register_subsystem(subsys); if (ret) { - printk(KERN_ERR "Error %d while registering subsystem %s\n", + pr_err("Error %d while registering subsystem %s\n", ret, subsys->su_group.cg_item.ci_namebuf); } @@ -417,7 +868,7 @@ static int configfs_sdcardfs_init(void) static void configfs_sdcardfs_exit(void) { - configfs_unregister_subsystem(&sdcardfs_packages_subsys); + configfs_unregister_subsystem(&sdcardfs_packages); } int packagelist_init(void) @@ -426,19 +877,17 @@ int packagelist_init(void) kmem_cache_create("packagelist_hashtable_entry", sizeof(struct hashtable_entry), 0, 0, NULL); if (!hashtable_entry_cachep) { - printk(KERN_ERR "sdcardfs: failed creating pkgl_hashtable entry slab cache\n"); + pr_err("sdcardfs: failed creating pkgl_hashtable entry slab cache\n"); return -ENOMEM; } - pkgl_data_all = packagelist_create(); configfs_sdcardfs_init(); - return 0; + return 0; } void packagelist_exit(void) { configfs_sdcardfs_exit(); - packagelist_destroy(pkgl_data_all); - if (hashtable_entry_cachep) - kmem_cache_destroy(hashtable_entry_cachep); + packagelist_destroy(); + kmem_cache_destroy(hashtable_entry_cachep); } diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h index f111f898b630..2b67b9a8ef9f 100644 --- a/fs/sdcardfs/sdcardfs.h +++ b/fs/sdcardfs/sdcardfs.h @@ -29,6 +29,7 @@ #include <linux/dcache.h> #include <linux/file.h> #include <linux/fs.h> +#include <linux/aio.h> #include <linux/mm.h> #include <linux/mount.h> #include <linux/namei.h> @@ -52,7 +53,7 @@ #define SDCARDFS_ROOT_INO 1 /* useful for tracking code reachability */ -#define UDBG printk(KERN_DEFAULT "DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__) +#define UDBG pr_default("DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__) #define SDCARDFS_DIRENT_SIZE 256 @@ -65,71 +66,87 @@ #define AID_SDCARD_PICS 1033 /* external storage photos access */ #define AID_SDCARD_AV 1034 /* external storage audio/video access */ #define AID_SDCARD_ALL 1035 /* access all users external storage */ +#define AID_MEDIA_OBB 1059 /* obb files */ + +#define AID_SDCARD_IMAGE 1057 #define AID_PACKAGE_INFO 1027 -#define fix_derived_permission(x) \ + +/* + * Permissions are handled by our permission function. + * We don't want anyone who happens to look at our inode value to prematurely + * block access, so store more permissive values. These are probably never + * used. + */ +#define fixup_tmp_permissions(x) \ do { \ (x)->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(x)->d_uid); \ - (x)->i_gid = make_kgid(&init_user_ns, get_gid(SDCARDFS_I(x))); \ - (x)->i_mode = ((x)->i_mode & S_IFMT) | get_mode(SDCARDFS_I(x));\ + (x)->i_gid = make_kgid(&init_user_ns, AID_SDCARD_RW); \ + (x)->i_mode = ((x)->i_mode & S_IFMT) | 0775;\ } while (0) - /* OVERRIDE_CRED() and REVERT_CRED() - * OVERRID_CRED() - * backup original task->cred - * and modifies task->cred->fsuid/fsgid to specified value. + * OVERRIDE_CRED() + * backup original task->cred + * and modifies task->cred->fsuid/fsgid to specified value. * REVERT_CRED() - * restore original task->cred->fsuid/fsgid. + * restore original task->cred->fsuid/fsgid. * These two macro should be used in pair, and OVERRIDE_CRED() should be * placed at the beginning of a function, right after variable declaration. */ -#define OVERRIDE_CRED(sdcardfs_sbi, saved_cred) \ - saved_cred = override_fsids(sdcardfs_sbi); \ - if (!saved_cred) { return -ENOMEM; } +#define OVERRIDE_CRED(sdcardfs_sbi, saved_cred, info) \ + do { \ + saved_cred = override_fsids(sdcardfs_sbi, info); \ + if (!saved_cred) \ + return -ENOMEM; \ + } while (0) -#define OVERRIDE_CRED_PTR(sdcardfs_sbi, saved_cred) \ - saved_cred = override_fsids(sdcardfs_sbi); \ - if (!saved_cred) { return ERR_PTR(-ENOMEM); } +#define OVERRIDE_CRED_PTR(sdcardfs_sbi, saved_cred, info) \ + do { \ + saved_cred = override_fsids(sdcardfs_sbi, info); \ + if (!saved_cred) \ + return ERR_PTR(-ENOMEM); \ + } while (0) #define REVERT_CRED(saved_cred) revert_fsids(saved_cred) -#define DEBUG_CRED() \ - printk("KAKJAGI: %s:%d fsuid %d fsgid %d\n", \ - __FUNCTION__, __LINE__, \ - (int)current->cred->fsuid, \ - (int)current->cred->fsgid); - /* Android 5.0 support */ /* Permission mode for a specific node. Controls how file permissions - * are derived for children nodes. */ + * are derived for children nodes. + */ typedef enum { - /* Nothing special; this node should just inherit from its parent. */ - PERM_INHERIT, - /* This node is one level above a normal root; used for legacy layouts - * which use the first level to represent user_id. */ - PERM_PRE_ROOT, - /* This node is "/" */ - PERM_ROOT, - /* This node is "/Android" */ - PERM_ANDROID, - /* This node is "/Android/data" */ - PERM_ANDROID_DATA, - /* This node is "/Android/obb" */ - PERM_ANDROID_OBB, - /* This node is "/Android/media" */ - PERM_ANDROID_MEDIA, + /* Nothing special; this node should just inherit from its parent. */ + PERM_INHERIT, + /* This node is one level above a normal root; used for legacy layouts + * which use the first level to represent user_id. + */ + PERM_PRE_ROOT, + /* This node is "/" */ + PERM_ROOT, + /* This node is "/Android" */ + PERM_ANDROID, + /* This node is "/Android/data" */ + PERM_ANDROID_DATA, + /* This node is "/Android/obb" */ + PERM_ANDROID_OBB, + /* This node is "/Android/media" */ + PERM_ANDROID_MEDIA, + /* This node is "/Android/[data|media|obb]/[package]" */ + PERM_ANDROID_PACKAGE, + /* This node is "/Android/[data|media|obb]/[package]/cache" */ + PERM_ANDROID_PACKAGE_CACHE, } perm_t; struct sdcardfs_sb_info; struct sdcardfs_mount_options; +struct sdcardfs_inode_info; /* Do not directly use this function. Use OVERRIDE_CRED() instead. */ -const struct cred * override_fsids(struct sdcardfs_sb_info* sbi); +const struct cred *override_fsids(struct sdcardfs_sb_info *sbi, struct sdcardfs_inode_info *info); /* Do not directly use this function, use REVERT_CRED() instead. */ -void revert_fsids(const struct cred * old_cred); +void revert_fsids(const struct cred *old_cred); /* operations vectors defined in specific files */ extern const struct file_operations sdcardfs_main_fops; @@ -169,6 +186,10 @@ struct sdcardfs_inode_info { userid_t userid; uid_t d_uid; bool under_android; + bool under_cache; + bool under_obb; + /* top folder for ownership */ + struct inode *top; struct inode vfs_inode; }; @@ -185,18 +206,25 @@ struct sdcardfs_mount_options { uid_t fs_low_uid; gid_t fs_low_gid; userid_t fs_user_id; - gid_t gid; - mode_t mask; bool multiuser; unsigned int reserved_mb; }; +struct sdcardfs_vfsmount_options { + gid_t gid; + mode_t mask; +}; + +extern int parse_options_remount(struct super_block *sb, char *options, int silent, + struct sdcardfs_vfsmount_options *vfsopts); + /* sdcardfs super-block data in memory */ struct sdcardfs_sb_info { struct super_block *sb; struct super_block *lower_sb; /* derived perm policy : some of options have been added - * to sdcardfs_mount_options (Android 4.4 support) */ + * to sdcardfs_mount_options (Android 4.4 support) + */ struct sdcardfs_mount_options options; spinlock_t lock; /* protects obbpath */ char *obbpath_s; @@ -307,7 +335,7 @@ static inline void sdcardfs_put_reset_##pname(const struct dentry *dent) \ { \ struct path pname; \ spin_lock(&SDCARDFS_D(dent)->lock); \ - if(SDCARDFS_D(dent)->pname.dentry) { \ + if (SDCARDFS_D(dent)->pname.dentry) { \ pathcpy(&pname, &SDCARDFS_D(dent)->pname); \ SDCARDFS_D(dent)->pname.dentry = NULL; \ SDCARDFS_D(dent)->pname.mnt = NULL; \ @@ -321,38 +349,78 @@ static inline void sdcardfs_put_reset_##pname(const struct dentry *dent) \ SDCARDFS_DENT_FUNC(lower_path) SDCARDFS_DENT_FUNC(orig_path) -static inline int get_gid(struct sdcardfs_inode_info *info) { - struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb); - if (sb_info->options.gid == AID_SDCARD_RW) { +static inline bool sbinfo_has_sdcard_magic(struct sdcardfs_sb_info *sbinfo) +{ + return sbinfo && sbinfo->sb && sbinfo->sb->s_magic == SDCARDFS_SUPER_MAGIC; +} + +/* grab a refererence if we aren't linking to ourself */ +static inline void set_top(struct sdcardfs_inode_info *info, struct inode *top) +{ + struct inode *old_top = NULL; + + BUG_ON(IS_ERR_OR_NULL(top)); + if (info->top && info->top != &info->vfs_inode) + old_top = info->top; + if (top != &info->vfs_inode) + igrab(top); + info->top = top; + iput(old_top); +} + +static inline struct inode *grab_top(struct sdcardfs_inode_info *info) +{ + struct inode *top = info->top; + + if (top) + return igrab(top); + else + return NULL; +} + +static inline void release_top(struct sdcardfs_inode_info *info) +{ + iput(info->top); +} + +static inline int get_gid(struct vfsmount *mnt, struct sdcardfs_inode_info *info) +{ + struct sdcardfs_vfsmount_options *opts = mnt->data; + + if (opts->gid == AID_SDCARD_RW) /* As an optimization, certain trusted system components only run * as owner but operate across all users. Since we're now handing * out the sdcard_rw GID only to trusted apps, we're okay relaxing * the user boundary enforcement for the default view. The UIDs - * assigned to app directories are still multiuser aware. */ + * assigned to app directories are still multiuser aware. + */ return AID_SDCARD_RW; - } else { - return multiuser_get_uid(info->userid, sb_info->options.gid); - } + else + return multiuser_get_uid(info->userid, opts->gid); } -static inline int get_mode(struct sdcardfs_inode_info *info) { + +static inline int get_mode(struct vfsmount *mnt, struct sdcardfs_inode_info *info) +{ int owner_mode; int filtered_mode; - struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb); - int visible_mode = 0775 & ~sb_info->options.mask; + struct sdcardfs_vfsmount_options *opts = mnt->data; + int visible_mode = 0775 & ~opts->mask; + if (info->perm == PERM_PRE_ROOT) { /* Top of multi-user view should always be visible to ensure - * secondary users can traverse inside. */ + * secondary users can traverse inside. + */ visible_mode = 0711; } else if (info->under_android) { /* Block "other" access to Android directories, since only apps * belonging to a specific user should be in there; we still - * leave +x open for the default view. */ - if (sb_info->options.gid == AID_SDCARD_RW) { + * leave +x open for the default view. + */ + if (opts->gid == AID_SDCARD_RW) visible_mode = visible_mode & ~0006; - } else { + else visible_mode = visible_mode & ~0007; - } } owner_mode = info->lower_inode->i_mode & 0700; filtered_mode = visible_mode & (owner_mode | (owner_mode >> 3) | (owner_mode >> 6)); @@ -377,7 +445,7 @@ static inline void sdcardfs_get_real_lower(const struct dentry *dent, /* in case of a local obb dentry * the orig_path should be returned */ - if(has_graft_path(dent)) + if (has_graft_path(dent)) sdcardfs_get_orig_path(dent, real_lower); else sdcardfs_get_lower_path(dent, real_lower); @@ -386,7 +454,7 @@ static inline void sdcardfs_get_real_lower(const struct dentry *dent, static inline void sdcardfs_put_real_lower(const struct dentry *dent, struct path *real_lower) { - if(has_graft_path(dent)) + if (has_graft_path(dent)) sdcardfs_put_orig_path(dent, real_lower); else sdcardfs_put_lower_path(dent, real_lower); @@ -396,20 +464,31 @@ extern struct mutex sdcardfs_super_list_lock; extern struct list_head sdcardfs_super_list; /* for packagelist.c */ -extern appid_t get_appid(void *pkgl_id, const char *app_name); -extern int check_caller_access_to_name(struct inode *parent_node, const char* name); +extern appid_t get_appid(const char *app_name); +extern appid_t get_ext_gid(const char *app_name); +extern appid_t is_excluded(const char *app_name, userid_t userid); +extern int check_caller_access_to_name(struct inode *parent_node, const struct qstr *name); extern int open_flags_to_access_mode(int open_flags); extern int packagelist_init(void); extern void packagelist_exit(void); /* for derived_perm.c */ -extern void setup_derived_state(struct inode *inode, perm_t perm, - userid_t userid, uid_t uid, bool under_android); +#define BY_NAME (1 << 0) +#define BY_USERID (1 << 1) +struct limit_search { + unsigned int flags; + struct qstr name; + userid_t userid; +}; + +extern void setup_derived_state(struct inode *inode, perm_t perm, userid_t userid, + uid_t uid, bool under_android, struct inode *top); extern void get_derived_permission(struct dentry *parent, struct dentry *dentry); -extern void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry); -extern void get_derive_permissions_recursive(struct dentry *parent); +extern void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, const struct qstr *name); +extern void fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit); extern void update_derived_permission_lock(struct dentry *dentry); +void fixup_lower_ownership(struct dentry *dentry, const char *name); extern int need_graft_path(struct dentry *dentry); extern int is_base_obbpath(struct dentry *dentry); extern int is_obbpath_invalid(struct dentry *dentry); @@ -419,6 +498,7 @@ extern int setup_obb_dentry(struct dentry *dentry, struct path *lower_path); static inline struct dentry *lock_parent(struct dentry *dentry) { struct dentry *dir = dget_parent(dentry); + mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT); return dir; } @@ -444,7 +524,7 @@ static inline int prepare_dir(const char *path_s, uid_t uid, gid_t gid, mode_t m goto out_unlock; } - err = vfs_mkdir(d_inode(parent.dentry), dent, mode); + err = vfs_mkdir2(parent.mnt, d_inode(parent.dentry), dent, mode); if (err) { if (err == -EEXIST) err = 0; @@ -455,7 +535,7 @@ static inline int prepare_dir(const char *path_s, uid_t uid, gid_t gid, mode_t m attrs.ia_gid = make_kgid(&init_user_ns, gid); attrs.ia_valid = ATTR_UID | ATTR_GID; mutex_lock(&d_inode(dent)->i_mutex); - notify_change(dent, &attrs, NULL); + notify_change2(parent.mnt, dent, &attrs, NULL); mutex_unlock(&d_inode(dent)->i_mutex); out_dput: @@ -513,12 +593,16 @@ static inline int check_min_free_space(struct dentry *dentry, size_t size, int d return 1; } -/* Copies attrs and maintains sdcardfs managed attrs */ +/* + * Copies attrs and maintains sdcardfs managed attrs + * Since our permission check handles all special permissions, set those to be open + */ static inline void sdcardfs_copy_and_fix_attrs(struct inode *dest, const struct inode *src) { - dest->i_mode = (src->i_mode & S_IFMT) | get_mode(SDCARDFS_I(dest)); + dest->i_mode = (src->i_mode & S_IFMT) | S_IRWXU | S_IRWXG | + S_IROTH | S_IXOTH; /* 0775 */ dest->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(dest)->d_uid); - dest->i_gid = make_kgid(&init_user_ns, get_gid(SDCARDFS_I(dest))); + dest->i_gid = make_kgid(&init_user_ns, AID_SDCARD_RW); dest->i_rdev = src->i_rdev; dest->i_atime = src->i_atime; dest->i_mtime = src->i_mtime; @@ -527,4 +611,22 @@ static inline void sdcardfs_copy_and_fix_attrs(struct inode *dest, const struct dest->i_flags = src->i_flags; set_nlink(dest, src->i_nlink); } + +static inline bool str_case_eq(const char *s1, const char *s2) +{ + return !strcasecmp(s1, s2); +} + +static inline bool str_n_case_eq(const char *s1, const char *s2, size_t len) +{ + return !strncasecmp(s1, s2, len); +} + +static inline bool qstr_case_eq(const struct qstr *q1, const struct qstr *q2) +{ + return q1->len == q2->len && str_case_eq(q1->name, q2->name); +} + +#define QSTR_LITERAL(string) QSTR_INIT(string, sizeof(string)-1) + #endif /* not _SDCARDFS_H_ */ diff --git a/fs/sdcardfs/super.c b/fs/sdcardfs/super.c index 1d6490128c99..a3393e959c63 100644 --- a/fs/sdcardfs/super.c +++ b/fs/sdcardfs/super.c @@ -36,7 +36,7 @@ static void sdcardfs_put_super(struct super_block *sb) if (!spd) return; - if(spd->obbpath_s) { + if (spd->obbpath_s) { kfree(spd->obbpath_s); path_put(&spd->obbpath); } @@ -64,7 +64,7 @@ static int sdcardfs_statfs(struct dentry *dentry, struct kstatfs *buf) if (sbi->options.reserved_mb) { /* Invalid statfs informations. */ if (buf->f_bsize == 0) { - printk(KERN_ERR "Returned block size is zero.\n"); + pr_err("Returned block size is zero.\n"); return -EINVAL; } @@ -100,8 +100,7 @@ static int sdcardfs_remount_fs(struct super_block *sb, int *flags, char *options * SILENT, but anything else left over is an error. */ if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT)) != 0) { - printk(KERN_ERR - "sdcardfs: remount flags 0x%x unsupported\n", *flags); + pr_err("sdcardfs: remount flags 0x%x unsupported\n", *flags); err = -EINVAL; } @@ -109,6 +108,54 @@ static int sdcardfs_remount_fs(struct super_block *sb, int *flags, char *options } /* + * @mnt: mount point we are remounting + * @sb: superblock we are remounting + * @flags: numeric mount options + * @options: mount options string + */ +static int sdcardfs_remount_fs2(struct vfsmount *mnt, struct super_block *sb, + int *flags, char *options) +{ + int err = 0; + + /* + * The VFS will take care of "ro" and "rw" flags among others. We + * can safely accept a few flags (RDONLY, MANDLOCK), and honor + * SILENT, but anything else left over is an error. + */ + if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT | MS_REMOUNT)) != 0) { + pr_err("sdcardfs: remount flags 0x%x unsupported\n", *flags); + err = -EINVAL; + } + pr_info("Remount options were %s for vfsmnt %p.\n", options, mnt); + err = parse_options_remount(sb, options, *flags & ~MS_SILENT, mnt->data); + + + return err; +} + +static void *sdcardfs_clone_mnt_data(void *data) +{ + struct sdcardfs_vfsmount_options *opt = kmalloc(sizeof(struct sdcardfs_vfsmount_options), GFP_KERNEL); + struct sdcardfs_vfsmount_options *old = data; + + if (!opt) + return NULL; + opt->gid = old->gid; + opt->mask = old->mask; + return opt; +} + +static void sdcardfs_copy_mnt_data(void *data, void *newdata) +{ + struct sdcardfs_vfsmount_options *old = data; + struct sdcardfs_vfsmount_options *new = newdata; + + old->gid = new->gid; + old->mask = new->mask; +} + +/* * Called by iput() when the inode reference count reached zero * and the inode is not hashed anywhere. Used to clear anything * that needs to be, before the inode is completely destroyed and put @@ -126,6 +173,7 @@ static void sdcardfs_evict_inode(struct inode *inode) */ lower_inode = sdcardfs_lower_inode(inode); sdcardfs_set_lower_inode(inode, NULL); + set_top(SDCARDFS_I(inode), inode); iput(lower_inode); } @@ -173,8 +221,7 @@ int sdcardfs_init_inode_cache(void) /* sdcardfs inode cache destructor */ void sdcardfs_destroy_inode_cache(void) { - if (sdcardfs_inode_cachep) - kmem_cache_destroy(sdcardfs_inode_cachep); + kmem_cache_destroy(sdcardfs_inode_cachep); } /* @@ -190,19 +237,25 @@ static void sdcardfs_umount_begin(struct super_block *sb) lower_sb->s_op->umount_begin(lower_sb); } -static int sdcardfs_show_options(struct seq_file *m, struct dentry *root) +static int sdcardfs_show_options(struct vfsmount *mnt, struct seq_file *m, + struct dentry *root) { struct sdcardfs_sb_info *sbi = SDCARDFS_SB(root->d_sb); struct sdcardfs_mount_options *opts = &sbi->options; + struct sdcardfs_vfsmount_options *vfsopts = mnt->data; if (opts->fs_low_uid != 0) - seq_printf(m, ",uid=%u", opts->fs_low_uid); + seq_printf(m, ",fsuid=%u", opts->fs_low_uid); if (opts->fs_low_gid != 0) - seq_printf(m, ",gid=%u", opts->fs_low_gid); - + seq_printf(m, ",fsgid=%u", opts->fs_low_gid); + if (vfsopts->gid != 0) + seq_printf(m, ",gid=%u", vfsopts->gid); if (opts->multiuser) - seq_printf(m, ",multiuser"); - + seq_puts(m, ",multiuser"); + if (vfsopts->mask) + seq_printf(m, ",mask=%u", vfsopts->mask); + if (opts->fs_user_id) + seq_printf(m, ",userid=%u", opts->fs_user_id); if (opts->reserved_mb != 0) seq_printf(m, ",reserved=%uMB", opts->reserved_mb); @@ -213,9 +266,12 @@ const struct super_operations sdcardfs_sops = { .put_super = sdcardfs_put_super, .statfs = sdcardfs_statfs, .remount_fs = sdcardfs_remount_fs, + .remount_fs2 = sdcardfs_remount_fs2, + .clone_mnt_data = sdcardfs_clone_mnt_data, + .copy_mnt_data = sdcardfs_copy_mnt_data, .evict_inode = sdcardfs_evict_inode, .umount_begin = sdcardfs_umount_begin, - .show_options = sdcardfs_show_options, + .show_options2 = sdcardfs_show_options, .alloc_inode = sdcardfs_alloc_inode, .destroy_inode = sdcardfs_destroy_inode, .drop_inode = generic_delete_inode, diff --git a/fs/seq_file.c b/fs/seq_file.c index d672e2fec459..6dc4296eed62 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -72,9 +72,10 @@ int seq_open(struct file *file, const struct seq_operations *op) mutex_init(&p->lock); p->op = op; -#ifdef CONFIG_USER_NS - p->user_ns = file->f_cred->user_ns; -#endif + + // No refcounting: the lifetime of 'p' is constrained + // to the lifetime of the file. + p->file = file; /* * Wrappers around seq_open(e.g. swaps_open) need to be diff --git a/fs/splice.c b/fs/splice.c index 0f77e9682857..8398974e1538 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -211,6 +211,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, buf->len = spd->partial[page_nr].len; buf->private = spd->partial[page_nr].private; buf->ops = spd->ops; + buf->flags = 0; if (spd->flags & SPLICE_F_GIFT) buf->flags |= PIPE_BUF_FLAG_GIFT; diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig index ffb093e72b6c..6dd158a216f4 100644 --- a/fs/squashfs/Kconfig +++ b/fs/squashfs/Kconfig @@ -26,34 +26,6 @@ config SQUASHFS If unsure, say N. choice - prompt "File decompression options" - depends on SQUASHFS - help - Squashfs now supports two options for decompressing file - data. Traditionally Squashfs has decompressed into an - intermediate buffer and then memcopied it into the page cache. - Squashfs now supports the ability to decompress directly into - the page cache. - - If unsure, select "Decompress file data into an intermediate buffer" - -config SQUASHFS_FILE_CACHE - bool "Decompress file data into an intermediate buffer" - help - Decompress file data into an intermediate buffer and then - memcopy it into the page cache. - -config SQUASHFS_FILE_DIRECT - bool "Decompress files directly into the page cache" - help - Directly decompress file data into the page cache. - Doing so can significantly improve performance because - it eliminates a memcpy and it also removes the lock contention - on the single buffer. - -endchoice - -choice prompt "Decompressor parallelisation options" depends on SQUASHFS help diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile index 246a6f329d89..fe51f1507ed1 100644 --- a/fs/squashfs/Makefile +++ b/fs/squashfs/Makefile @@ -5,8 +5,7 @@ obj-$(CONFIG_SQUASHFS) += squashfs.o squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o squashfs-y += namei.o super.o symlink.o decompressor.o -squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o -squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o +squashfs-y += file_direct.o page_actor.o squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 0cea9b9236d0..2eb66decc5ab 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -28,9 +28,12 @@ #include <linux/fs.h> #include <linux/vfs.h> +#include <linux/bio.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/pagemap.h> #include <linux/buffer_head.h> +#include <linux/workqueue.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -38,177 +41,434 @@ #include "decompressor.h" #include "page_actor.h" -/* - * Read the metadata block length, this is stored in the first two - * bytes of the metadata block. - */ -static struct buffer_head *get_block_length(struct super_block *sb, - u64 *cur_index, int *offset, int *length) +static struct workqueue_struct *squashfs_read_wq; + +struct squashfs_read_request { + struct super_block *sb; + u64 index; + int length; + int compressed; + int offset; + u64 read_end; + struct squashfs_page_actor *output; + enum { + SQUASHFS_COPY, + SQUASHFS_DECOMPRESS, + SQUASHFS_METADATA, + } data_processing; + bool synchronous; + + /* + * If the read is synchronous, it is possible to retrieve information + * about the request by setting these pointers. + */ + int *res; + int *bytes_read; + int *bytes_uncompressed; + + int nr_buffers; + struct buffer_head **bh; + struct work_struct offload; +}; + +struct squashfs_bio_request { + struct buffer_head **bh; + int nr_buffers; +}; + +static int squashfs_bio_submit(struct squashfs_read_request *req); + +int squashfs_init_read_wq(void) { - struct squashfs_sb_info *msblk = sb->s_fs_info; - struct buffer_head *bh; + squashfs_read_wq = create_workqueue("SquashFS read wq"); + return !!squashfs_read_wq; +} + +void squashfs_destroy_read_wq(void) +{ + flush_workqueue(squashfs_read_wq); + destroy_workqueue(squashfs_read_wq); +} + +static void free_read_request(struct squashfs_read_request *req, int error) +{ + if (!req->synchronous) + squashfs_page_actor_free(req->output, error); + if (req->res) + *(req->res) = error; + kfree(req->bh); + kfree(req); +} + +static void squashfs_process_blocks(struct squashfs_read_request *req) +{ + int error = 0; + int bytes, i, length; + struct squashfs_sb_info *msblk = req->sb->s_fs_info; + struct squashfs_page_actor *actor = req->output; + struct buffer_head **bh = req->bh; + int nr_buffers = req->nr_buffers; + + for (i = 0; i < nr_buffers; ++i) { + if (!bh[i]) + continue; + wait_on_buffer(bh[i]); + if (!buffer_uptodate(bh[i])) + error = -EIO; + } + if (error) + goto cleanup; + + if (req->data_processing == SQUASHFS_METADATA) { + /* Extract the length of the metadata block */ + if (req->offset != msblk->devblksize - 1) + length = *((u16 *)(bh[0]->b_data + req->offset)); + else { + length = bh[0]->b_data[req->offset]; + length |= bh[1]->b_data[0] << 8; + } + req->compressed = SQUASHFS_COMPRESSED(length); + req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS + : SQUASHFS_COPY; + length = SQUASHFS_COMPRESSED_SIZE(length); + if (req->index + length + 2 > req->read_end) { + for (i = 0; i < nr_buffers; ++i) + put_bh(bh[i]); + kfree(bh); + req->length = length; + req->index += 2; + squashfs_bio_submit(req); + return; + } + req->length = length; + req->offset = (req->offset + 2) % PAGE_SIZE; + if (req->offset < 2) { + put_bh(bh[0]); + ++bh; + --nr_buffers; + } + } + if (req->bytes_read) + *(req->bytes_read) = req->length; - bh = sb_bread(sb, *cur_index); - if (bh == NULL) - return NULL; - - if (msblk->devblksize - *offset == 1) { - *length = (unsigned char) bh->b_data[*offset]; - put_bh(bh); - bh = sb_bread(sb, ++(*cur_index)); - if (bh == NULL) - return NULL; - *length |= (unsigned char) bh->b_data[0] << 8; - *offset = 1; - } else { - *length = (unsigned char) bh->b_data[*offset] | - (unsigned char) bh->b_data[*offset + 1] << 8; - *offset += 2; - - if (*offset == msblk->devblksize) { - put_bh(bh); - bh = sb_bread(sb, ++(*cur_index)); - if (bh == NULL) - return NULL; - *offset = 0; + if (req->data_processing == SQUASHFS_COPY) { + squashfs_bh_to_actor(bh, nr_buffers, req->output, req->offset, + req->length, msblk->devblksize); + } else if (req->data_processing == SQUASHFS_DECOMPRESS) { + req->length = squashfs_decompress(msblk, bh, nr_buffers, + req->offset, req->length, actor); + if (req->length < 0) { + error = -EIO; + goto cleanup; } } - return bh; + /* Last page may have trailing bytes not filled */ + bytes = req->length % PAGE_SIZE; + if (bytes && actor->page[actor->pages - 1]) + zero_user_segment(actor->page[actor->pages - 1], bytes, + PAGE_SIZE); + +cleanup: + if (req->bytes_uncompressed) + *(req->bytes_uncompressed) = req->length; + if (error) { + for (i = 0; i < nr_buffers; ++i) + if (bh[i]) + put_bh(bh[i]); + } + free_read_request(req, error); } +static void read_wq_handler(struct work_struct *work) +{ + squashfs_process_blocks(container_of(work, + struct squashfs_read_request, offload)); +} -/* - * Read and decompress a metadata block or datablock. Length is non-zero - * if a datablock is being read (the size is stored elsewhere in the - * filesystem), otherwise the length is obtained from the first two bytes of - * the metadata block. A bit in the length field indicates if the block - * is stored uncompressed in the filesystem (usually because compression - * generated a larger block - this does occasionally happen with compression - * algorithms). - */ -int squashfs_read_data(struct super_block *sb, u64 index, int length, - u64 *next_index, struct squashfs_page_actor *output) +static void squashfs_bio_end_io(struct bio *bio) { - struct squashfs_sb_info *msblk = sb->s_fs_info; - struct buffer_head **bh; - int offset = index & ((1 << msblk->devblksize_log2) - 1); - u64 cur_index = index >> msblk->devblksize_log2; - int bytes, compressed, b = 0, k = 0, avail, i; + int i; + int error = bio->bi_error; + struct squashfs_bio_request *bio_req = bio->bi_private; + + bio_put(bio); + + for (i = 0; i < bio_req->nr_buffers; ++i) { + if (!bio_req->bh[i]) + continue; + if (!error) + set_buffer_uptodate(bio_req->bh[i]); + else + clear_buffer_uptodate(bio_req->bh[i]); + unlock_buffer(bio_req->bh[i]); + } + kfree(bio_req); +} + +static int bh_is_optional(struct squashfs_read_request *req, int idx) +{ + int start_idx, end_idx; + struct squashfs_sb_info *msblk = req->sb->s_fs_info; - bh = kcalloc(((output->length + msblk->devblksize - 1) - >> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL); - if (bh == NULL) + start_idx = (idx * msblk->devblksize - req->offset) / PAGE_CACHE_SIZE; + end_idx = ((idx + 1) * msblk->devblksize - req->offset + 1) / PAGE_CACHE_SIZE; + if (start_idx >= req->output->pages) + return 1; + if (start_idx < 0) + start_idx = end_idx; + if (end_idx >= req->output->pages) + end_idx = start_idx; + return !req->output->page[start_idx] && !req->output->page[end_idx]; +} + +static int actor_getblks(struct squashfs_read_request *req, u64 block) +{ + int i; + + req->bh = kmalloc_array(req->nr_buffers, sizeof(*(req->bh)), GFP_NOIO); + if (!req->bh) return -ENOMEM; - if (length) { + for (i = 0; i < req->nr_buffers; ++i) { /* - * Datablock. + * When dealing with an uncompressed block, the actor may + * contains NULL pages. There's no need to read the buffers + * associated with these pages. */ - bytes = -offset; - compressed = SQUASHFS_COMPRESSED_BLOCK(length); - length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length); - if (next_index) - *next_index = index + length; - - TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n", - index, compressed ? "" : "un", length, output->length); - - if (length < 0 || length > output->length || - (index + length) > msblk->bytes_used) - goto read_failure; - - for (b = 0; bytes < length; b++, cur_index++) { - bh[b] = sb_getblk(sb, cur_index); - if (bh[b] == NULL) - goto block_release; - bytes += msblk->devblksize; + if (!req->compressed && bh_is_optional(req, i)) { + req->bh[i] = NULL; + continue; } - ll_rw_block(READ, b, bh); - } else { - /* - * Metadata block. - */ - if ((index + 2) > msblk->bytes_used) - goto read_failure; + req->bh[i] = sb_getblk(req->sb, block + i); + if (!req->bh[i]) { + while (--i) { + if (req->bh[i]) + put_bh(req->bh[i]); + } + return -1; + } + } + return 0; +} - bh[0] = get_block_length(sb, &cur_index, &offset, &length); - if (bh[0] == NULL) - goto read_failure; - b = 1; +static int squashfs_bio_submit(struct squashfs_read_request *req) +{ + struct bio *bio = NULL; + struct buffer_head *bh; + struct squashfs_bio_request *bio_req = NULL; + int b = 0, prev_block = 0; + struct squashfs_sb_info *msblk = req->sb->s_fs_info; - bytes = msblk->devblksize - offset; - compressed = SQUASHFS_COMPRESSED(length); - length = SQUASHFS_COMPRESSED_SIZE(length); - if (next_index) - *next_index = index + length + 2; + u64 read_start = round_down(req->index, msblk->devblksize); + u64 read_end = round_up(req->index + req->length, msblk->devblksize); + sector_t block = read_start >> msblk->devblksize_log2; + sector_t block_end = read_end >> msblk->devblksize_log2; + int offset = read_start - round_down(req->index, PAGE_SIZE); + int nr_buffers = block_end - block; + int blksz = msblk->devblksize; + int bio_max_pages = nr_buffers > BIO_MAX_PAGES ? BIO_MAX_PAGES + : nr_buffers; - TRACE("Block @ 0x%llx, %scompressed size %d\n", index, - compressed ? "" : "un", length); + /* Setup the request */ + req->read_end = read_end; + req->offset = req->index - read_start; + req->nr_buffers = nr_buffers; + if (actor_getblks(req, block) < 0) + goto getblk_failed; - if (length < 0 || length > output->length || - (index + length) > msblk->bytes_used) - goto block_release; + /* Create and submit the BIOs */ + for (b = 0; b < nr_buffers; ++b, offset += blksz) { + bh = req->bh[b]; + if (!bh || !trylock_buffer(bh)) + continue; + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + continue; + } + offset %= PAGE_SIZE; - for (; bytes < length; b++) { - bh[b] = sb_getblk(sb, ++cur_index); - if (bh[b] == NULL) - goto block_release; - bytes += msblk->devblksize; + /* Append the buffer to the current BIO if it is contiguous */ + if (bio && bio_req && prev_block + 1 == b) { + if (bio_add_page(bio, bh->b_page, blksz, offset)) { + bio_req->nr_buffers += 1; + prev_block = b; + continue; + } } - ll_rw_block(READ, b - 1, bh + 1); + + /* Otherwise, submit the current BIO and create a new one */ + if (bio) + submit_bio(READ, bio); + bio_req = kcalloc(1, sizeof(struct squashfs_bio_request), + GFP_NOIO); + if (!bio_req) + goto req_alloc_failed; + bio_req->bh = &req->bh[b]; + bio = bio_alloc(GFP_NOIO, bio_max_pages); + if (!bio) + goto bio_alloc_failed; + bio->bi_bdev = req->sb->s_bdev; + bio->bi_iter.bi_sector = (block + b) + << (msblk->devblksize_log2 - 9); + bio->bi_private = bio_req; + bio->bi_end_io = squashfs_bio_end_io; + + bio_add_page(bio, bh->b_page, blksz, offset); + bio_req->nr_buffers += 1; + prev_block = b; } + if (bio) + submit_bio(READ, bio); - for (i = 0; i < b; i++) { - wait_on_buffer(bh[i]); - if (!buffer_uptodate(bh[i])) - goto block_release; + if (req->synchronous) + squashfs_process_blocks(req); + else { + INIT_WORK(&req->offload, read_wq_handler); + schedule_work(&req->offload); } + return 0; - if (compressed) { - length = squashfs_decompress(msblk, bh, b, offset, length, - output); - if (length < 0) - goto read_failure; - } else { - /* - * Block is uncompressed. - */ - int in, pg_offset = 0; - void *data = squashfs_first_page(output); - - for (bytes = length; k < b; k++) { - in = min(bytes, msblk->devblksize - offset); - bytes -= in; - while (in) { - if (pg_offset == PAGE_CACHE_SIZE) { - data = squashfs_next_page(output); - pg_offset = 0; - } - avail = min_t(int, in, PAGE_CACHE_SIZE - - pg_offset); - memcpy(data + pg_offset, bh[k]->b_data + offset, - avail); - in -= avail; - pg_offset += avail; - offset += avail; - } - offset = 0; - put_bh(bh[k]); - } - squashfs_finish_page(output); +bio_alloc_failed: + kfree(bio_req); +req_alloc_failed: + unlock_buffer(bh); + while (--nr_buffers >= b) + if (req->bh[nr_buffers]) + put_bh(req->bh[nr_buffers]); + while (--b >= 0) + if (req->bh[b]) + wait_on_buffer(req->bh[b]); +getblk_failed: + free_read_request(req, -ENOMEM); + return -ENOMEM; +} + +static int read_metadata_block(struct squashfs_read_request *req, + u64 *next_index) +{ + int ret, error, bytes_read = 0, bytes_uncompressed = 0; + struct squashfs_sb_info *msblk = req->sb->s_fs_info; + + if (req->index + 2 > msblk->bytes_used) { + free_read_request(req, -EINVAL); + return -EINVAL; + } + req->length = 2; + + /* Do not read beyond the end of the device */ + if (req->index + req->length > msblk->bytes_used) + req->length = msblk->bytes_used - req->index; + req->data_processing = SQUASHFS_METADATA; + + /* + * Reading metadata is always synchronous because we don't know the + * length in advance and the function is expected to update + * 'next_index' and return the length. + */ + req->synchronous = true; + req->res = &error; + req->bytes_read = &bytes_read; + req->bytes_uncompressed = &bytes_uncompressed; + + TRACE("Metadata block @ 0x%llx, %scompressed size %d, src size %d\n", + req->index, req->compressed ? "" : "un", bytes_read, + req->output->length); + + ret = squashfs_bio_submit(req); + if (ret) + return ret; + if (error) + return error; + if (next_index) + *next_index += 2 + bytes_read; + return bytes_uncompressed; +} + +static int read_data_block(struct squashfs_read_request *req, int length, + u64 *next_index, bool synchronous) +{ + int ret, error = 0, bytes_uncompressed = 0, bytes_read = 0; + + req->compressed = SQUASHFS_COMPRESSED_BLOCK(length); + req->length = length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length); + req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS + : SQUASHFS_COPY; + + req->synchronous = synchronous; + if (synchronous) { + req->res = &error; + req->bytes_read = &bytes_read; + req->bytes_uncompressed = &bytes_uncompressed; + } + + TRACE("Data block @ 0x%llx, %scompressed size %d, src size %d\n", + req->index, req->compressed ? "" : "un", req->length, + req->output->length); + + ret = squashfs_bio_submit(req); + if (ret) + return ret; + if (synchronous) + ret = error ? error : bytes_uncompressed; + if (next_index) + *next_index += length; + return ret; +} + +/* + * Read and decompress a metadata block or datablock. Length is non-zero + * if a datablock is being read (the size is stored elsewhere in the + * filesystem), otherwise the length is obtained from the first two bytes of + * the metadata block. A bit in the length field indicates if the block + * is stored uncompressed in the filesystem (usually because compression + * generated a larger block - this does occasionally happen with compression + * algorithms). + */ +static int __squashfs_read_data(struct super_block *sb, u64 index, int length, + u64 *next_index, struct squashfs_page_actor *output, bool sync) +{ + struct squashfs_read_request *req; + + req = kcalloc(1, sizeof(struct squashfs_read_request), GFP_KERNEL); + if (!req) { + if (!sync) + squashfs_page_actor_free(output, -ENOMEM); + return -ENOMEM; + } + + req->sb = sb; + req->index = index; + req->output = output; + + if (next_index) + *next_index = index; + + if (length) + length = read_data_block(req, length, next_index, sync); + else + length = read_metadata_block(req, next_index); + + if (length < 0) { + ERROR("squashfs_read_data failed to read block 0x%llx\n", + (unsigned long long)index); + return -EIO; } - kfree(bh); return length; +} -block_release: - for (; k < b; k++) - put_bh(bh[k]); +int squashfs_read_data(struct super_block *sb, u64 index, int length, + u64 *next_index, struct squashfs_page_actor *output) +{ + return __squashfs_read_data(sb, index, length, next_index, output, + true); +} + +int squashfs_read_data_async(struct super_block *sb, u64 index, int length, + u64 *next_index, struct squashfs_page_actor *output) +{ -read_failure: - ERROR("squashfs_read_data failed to read block 0x%llx\n", - (unsigned long long) index); - kfree(bh); - return -EIO; + return __squashfs_read_data(sb, index, length, next_index, output, + false); } diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 1cb70a0b2168..6785d086ab38 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -209,17 +209,14 @@ void squashfs_cache_put(struct squashfs_cache_entry *entry) */ void squashfs_cache_delete(struct squashfs_cache *cache) { - int i, j; + int i; if (cache == NULL) return; for (i = 0; i < cache->entries; i++) { - if (cache->entry[i].data) { - for (j = 0; j < cache->pages; j++) - kfree(cache->entry[i].data[j]); - kfree(cache->entry[i].data); - } + if (cache->entry[i].page) + free_page_array(cache->entry[i].page, cache->pages); kfree(cache->entry[i].actor); } @@ -236,7 +233,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache) struct squashfs_cache *squashfs_cache_init(char *name, int entries, int block_size) { - int i, j; + int i; struct squashfs_cache *cache = kzalloc(sizeof(*cache), GFP_KERNEL); if (cache == NULL) { @@ -268,22 +265,13 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries, init_waitqueue_head(&cache->entry[i].wait_queue); entry->cache = cache; entry->block = SQUASHFS_INVALID_BLK; - entry->data = kcalloc(cache->pages, sizeof(void *), GFP_KERNEL); - if (entry->data == NULL) { + entry->page = alloc_page_array(cache->pages, GFP_KERNEL); + if (!entry->page) { ERROR("Failed to allocate %s cache entry\n", name); goto cleanup; } - - for (j = 0; j < cache->pages; j++) { - entry->data[j] = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL); - if (entry->data[j] == NULL) { - ERROR("Failed to allocate %s buffer\n", name); - goto cleanup; - } - } - - entry->actor = squashfs_page_actor_init(entry->data, - cache->pages, 0); + entry->actor = squashfs_page_actor_init(entry->page, + cache->pages, 0, NULL); if (entry->actor == NULL) { ERROR("Failed to allocate %s cache entry\n", name); goto cleanup; @@ -314,18 +302,20 @@ int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry, return min(length, entry->length - offset); while (offset < entry->length) { - void *buff = entry->data[offset / PAGE_CACHE_SIZE] - + (offset % PAGE_CACHE_SIZE); + void *buff = kmap_atomic(entry->page[offset / PAGE_CACHE_SIZE]) + + (offset % PAGE_CACHE_SIZE); int bytes = min_t(int, entry->length - offset, PAGE_CACHE_SIZE - (offset % PAGE_CACHE_SIZE)); if (bytes >= remaining) { memcpy(buffer, buff, remaining); + kunmap_atomic(buff); remaining = 0; break; } memcpy(buffer, buff, bytes); + kunmap_atomic(buff); buffer += bytes; remaining -= bytes; offset += bytes; @@ -416,43 +406,38 @@ struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb, void *squashfs_read_table(struct super_block *sb, u64 block, int length) { int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - int i, res; - void *table, *buffer, **data; + struct page **page; + void *buff; + int res; struct squashfs_page_actor *actor; - table = buffer = kmalloc(length, GFP_KERNEL); - if (table == NULL) + page = alloc_page_array(pages, GFP_KERNEL); + if (!page) return ERR_PTR(-ENOMEM); - data = kcalloc(pages, sizeof(void *), GFP_KERNEL); - if (data == NULL) { - res = -ENOMEM; - goto failed; - } - - actor = squashfs_page_actor_init(data, pages, length); + actor = squashfs_page_actor_init(page, pages, length, NULL); if (actor == NULL) { res = -ENOMEM; - goto failed2; + goto failed; } - for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE) - data[i] = buffer; - res = squashfs_read_data(sb, block, length | SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor); - kfree(data); - kfree(actor); - if (res < 0) - goto failed; + goto failed2; - return table; + buff = kmalloc(length, GFP_KERNEL); + if (!buff) + goto failed2; + squashfs_actor_to_buf(actor, buff, length); + squashfs_page_actor_free(actor, 0); + free_page_array(page, pages); + return buff; failed2: - kfree(data); + squashfs_page_actor_free(actor, 0); failed: - kfree(table); + free_page_array(page, pages); return ERR_PTR(res); } diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c index e9034bf6e5ae..7de35bf297aa 100644 --- a/fs/squashfs/decompressor.c +++ b/fs/squashfs/decompressor.c @@ -24,7 +24,8 @@ #include <linux/types.h> #include <linux/mutex.h> #include <linux/slab.h> -#include <linux/buffer_head.h> +#include <linux/highmem.h> +#include <linux/fs.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -94,40 +95,44 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id) static void *get_comp_opts(struct super_block *sb, unsigned short flags) { struct squashfs_sb_info *msblk = sb->s_fs_info; - void *buffer = NULL, *comp_opts; + void *comp_opts, *buffer = NULL; + struct page *page; struct squashfs_page_actor *actor = NULL; int length = 0; + if (!SQUASHFS_COMP_OPTS(flags)) + return squashfs_comp_opts(msblk, buffer, length); + /* * Read decompressor specific options from file system if present */ - if (SQUASHFS_COMP_OPTS(flags)) { - buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL); - if (buffer == NULL) { - comp_opts = ERR_PTR(-ENOMEM); - goto out; - } - - actor = squashfs_page_actor_init(&buffer, 1, 0); - if (actor == NULL) { - comp_opts = ERR_PTR(-ENOMEM); - goto out; - } - - length = squashfs_read_data(sb, - sizeof(struct squashfs_super_block), 0, NULL, actor); - - if (length < 0) { - comp_opts = ERR_PTR(length); - goto out; - } + + page = alloc_page(GFP_KERNEL); + if (!page) + return ERR_PTR(-ENOMEM); + + actor = squashfs_page_actor_init(&page, 1, 0, NULL); + if (actor == NULL) { + comp_opts = ERR_PTR(-ENOMEM); + goto actor_error; + } + + length = squashfs_read_data(sb, + sizeof(struct squashfs_super_block), 0, NULL, actor); + + if (length < 0) { + comp_opts = ERR_PTR(length); + goto read_error; } + buffer = kmap_atomic(page); comp_opts = squashfs_comp_opts(msblk, buffer, length); + kunmap_atomic(buffer); -out: - kfree(actor); - kfree(buffer); +read_error: + squashfs_page_actor_free(actor, 0); +actor_error: + __free_page(page); return comp_opts; } diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index e5c9689062ba..6f5ef8d7e55a 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -47,12 +47,16 @@ #include <linux/string.h> #include <linux/pagemap.h> #include <linux/mutex.h> +#include <linux/mm_inline.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs_fs_i.h" #include "squashfs.h" +// Backported from 4.5 +#define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) + /* * Locate cache slot in range [offset, index] for specified inode. If * there's more than one return the slot closest to index. @@ -438,6 +442,21 @@ static int squashfs_readpage_fragment(struct page *page) return res; } +static int squashfs_readpages_fragment(struct page *page, + struct list_head *readahead_pages, struct address_space *mapping) +{ + if (!page) { + page = lru_to_page(readahead_pages); + list_del(&page->lru); + if (add_to_page_cache_lru(page, mapping, page->index, + mapping_gfp_constraint(mapping, GFP_KERNEL))) { + put_page(page); + return 0; + } + } + return squashfs_readpage_fragment(page); +} + static int squashfs_readpage_sparse(struct page *page, int index, int file_end) { struct inode *inode = page->mapping->host; @@ -450,54 +469,105 @@ static int squashfs_readpage_sparse(struct page *page, int index, int file_end) return 0; } -static int squashfs_readpage(struct file *file, struct page *page) +static int squashfs_readpages_sparse(struct page *page, + struct list_head *readahead_pages, int index, int file_end, + struct address_space *mapping) { - struct inode *inode = page->mapping->host; + if (!page) { + page = lru_to_page(readahead_pages); + list_del(&page->lru); + if (add_to_page_cache_lru(page, mapping, page->index, + mapping_gfp_constraint(mapping, GFP_KERNEL))) { + put_page(page); + return 0; + } + } + return squashfs_readpage_sparse(page, index, file_end); +} + +static int __squashfs_readpages(struct file *file, struct page *page, + struct list_head *readahead_pages, unsigned int nr_pages, + struct address_space *mapping) +{ + struct inode *inode = mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT); int file_end = i_size_read(inode) >> msblk->block_log; int res; - void *pageaddr; - TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", - page->index, squashfs_i(inode)->start); + do { + struct page *cur_page = page ? page + : lru_to_page(readahead_pages); + int page_index = cur_page->index; + int index = page_index >> (msblk->block_log - PAGE_CACHE_SHIFT); + + if (page_index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT)) + return 1; + + if (index < file_end || squashfs_i(inode)->fragment_block == + SQUASHFS_INVALID_BLK) { + u64 block = 0; + int bsize = read_blocklist(inode, index, &block); + + if (bsize < 0) + return -1; + + if (bsize == 0) { + res = squashfs_readpages_sparse(page, + readahead_pages, index, file_end, + mapping); + } else { + res = squashfs_readpages_block(page, + readahead_pages, &nr_pages, mapping, + page_index, block, bsize); + } + } else { + res = squashfs_readpages_fragment(page, + readahead_pages, mapping); + } + if (res) + return 0; + page = NULL; + } while (readahead_pages && !list_empty(readahead_pages)); - if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT)) - goto out; + return 0; +} - if (index < file_end || squashfs_i(inode)->fragment_block == - SQUASHFS_INVALID_BLK) { - u64 block = 0; - int bsize = read_blocklist(inode, index, &block); - if (bsize < 0) - goto error_out; +static int squashfs_readpage(struct file *file, struct page *page) +{ + int ret; - if (bsize == 0) - res = squashfs_readpage_sparse(page, index, file_end); + TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", + page->index, squashfs_i(page->mapping->host)->start); + + get_page(page); + + ret = __squashfs_readpages(file, page, NULL, 1, page->mapping); + if (ret) { + flush_dcache_page(page); + if (ret < 0) + SetPageError(page); else - res = squashfs_readpage_block(page, block, bsize); - } else - res = squashfs_readpage_fragment(page); - - if (!res) - return 0; - -error_out: - SetPageError(page); -out: - pageaddr = kmap_atomic(page); - memset(pageaddr, 0, PAGE_CACHE_SIZE); - kunmap_atomic(pageaddr); - flush_dcache_page(page); - if (!PageError(page)) - SetPageUptodate(page); - unlock_page(page); + SetPageUptodate(page); + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + unlock_page(page); + put_page(page); + } return 0; } +static int squashfs_readpages(struct file *file, struct address_space *mapping, + struct list_head *pages, unsigned int nr_pages) +{ + TRACE("Entered squashfs_readpages, %u pages, first page index %lx\n", + nr_pages, lru_to_page(pages)->index); + __squashfs_readpages(file, NULL, pages, nr_pages, mapping); + return 0; +} + const struct address_space_operations squashfs_aops = { - .readpage = squashfs_readpage + .readpage = squashfs_readpage, + .readpages = squashfs_readpages, }; diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c deleted file mode 100644 index f2310d2a2019..000000000000 --- a/fs/squashfs/file_cache.c +++ /dev/null @@ -1,38 +0,0 @@ -/* - * Copyright (c) 2013 - * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - */ - -#include <linux/fs.h> -#include <linux/vfs.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/string.h> -#include <linux/pagemap.h> -#include <linux/mutex.h> - -#include "squashfs_fs.h" -#include "squashfs_fs_sb.h" -#include "squashfs_fs_i.h" -#include "squashfs.h" - -/* Read separately compressed datablock and memcopy into page cache */ -int squashfs_readpage_block(struct page *page, u64 block, int bsize) -{ - struct inode *i = page->mapping->host; - struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, - block, bsize); - int res = buffer->error; - - if (res) - ERROR("Unable to read page, block %llx, size %x\n", block, - bsize); - else - squashfs_copy_cache(page, buffer, buffer->length, 0); - - squashfs_cache_put(buffer); - return res; -} diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index 43e7a7eddac0..c97af4c6ccd0 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -13,6 +13,7 @@ #include <linux/string.h> #include <linux/pagemap.h> #include <linux/mutex.h> +#include <linux/mm_inline.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -20,157 +21,139 @@ #include "squashfs.h" #include "page_actor.h" -static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page); - -/* Read separately compressed datablock directly into page cache */ -int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) +// Backported from 4.5 +#define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) +static void release_actor_pages(struct page **page, int pages, int error) { - struct inode *inode = target_page->mapping->host; - struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int i; - int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; - int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; - int start_index = target_page->index & ~mask; - int end_index = start_index | mask; - int i, n, pages, missing_pages, bytes, res = -ENOMEM; + for (i = 0; i < pages; i++) { + if (!page[i]) + continue; + flush_dcache_page(page[i]); + if (!error) + SetPageUptodate(page[i]); + else { + SetPageError(page[i]); + zero_user_segment(page[i], 0, PAGE_CACHE_SIZE); + } + unlock_page(page[i]); + put_page(page[i]); + } + kfree(page); +} + +/* + * Create a "page actor" which will kmap and kunmap the + * page cache pages appropriately within the decompressor + */ +static struct squashfs_page_actor *actor_from_page_cache( + unsigned int actor_pages, struct page *target_page, + struct list_head *rpages, unsigned int *nr_pages, int start_index, + struct address_space *mapping) +{ struct page **page; struct squashfs_page_actor *actor; - void *pageaddr; - - if (end_index > file_end) - end_index = file_end; - - pages = end_index - start_index + 1; - - page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL); - if (page == NULL) - return res; - - /* - * Create a "page actor" which will kmap and kunmap the - * page cache pages appropriately within the decompressor - */ - actor = squashfs_page_actor_init_special(page, pages, 0); - if (actor == NULL) - goto out; - - /* Try to grab all the pages covered by the Squashfs block */ - for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) { - page[i] = (n == target_page->index) ? target_page : - grab_cache_page_nowait(target_page->mapping, n); + int i, n; + gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); + + page = kmalloc_array(actor_pages, sizeof(void *), GFP_KERNEL); + if (!page) + return NULL; + + for (i = 0, n = start_index; i < actor_pages; i++, n++) { + if (target_page == NULL && rpages && !list_empty(rpages)) { + struct page *cur_page = lru_to_page(rpages); + + if (cur_page->index < start_index + actor_pages) { + list_del(&cur_page->lru); + --(*nr_pages); + if (add_to_page_cache_lru(cur_page, mapping, + cur_page->index, gfp)) + put_page(cur_page); + else + target_page = cur_page; + } else + rpages = NULL; + } - if (page[i] == NULL) { - missing_pages++; - continue; + if (target_page && target_page->index == n) { + page[i] = target_page; + target_page = NULL; + } else { + page[i] = grab_cache_page_nowait(mapping, n); + if (page[i] == NULL) + continue; } if (PageUptodate(page[i])) { unlock_page(page[i]); - page_cache_release(page[i]); + put_page(page[i]); page[i] = NULL; - missing_pages++; } } - if (missing_pages) { - /* - * Couldn't get one or more pages, this page has either - * been VM reclaimed, but others are still in the page cache - * and uptodate, or we're racing with another thread in - * squashfs_readpage also trying to grab them. Fall back to - * using an intermediate buffer. - */ - res = squashfs_read_cache(target_page, block, bsize, pages, - page); - if (res < 0) - goto mark_errored; - - goto out; + actor = squashfs_page_actor_init(page, actor_pages, 0, + release_actor_pages); + if (!actor) { + release_actor_pages(page, actor_pages, -ENOMEM); + kfree(page); + return NULL; } - - /* Decompress directly into the page cache buffers */ - res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); - if (res < 0) - goto mark_errored; - - /* Last page may have trailing bytes not filled */ - bytes = res % PAGE_CACHE_SIZE; - if (bytes) { - pageaddr = kmap_atomic(page[pages - 1]); - memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes); - kunmap_atomic(pageaddr); - } - - /* Mark pages as uptodate, unlock and release */ - for (i = 0; i < pages; i++) { - flush_dcache_page(page[i]); - SetPageUptodate(page[i]); - unlock_page(page[i]); - if (page[i] != target_page) - page_cache_release(page[i]); - } - - kfree(actor); - kfree(page); - - return 0; - -mark_errored: - /* Decompression failed, mark pages as errored. Target_page is - * dealt with by the caller - */ - for (i = 0; i < pages; i++) { - if (page[i] == NULL || page[i] == target_page) - continue; - flush_dcache_page(page[i]); - SetPageError(page[i]); - unlock_page(page[i]); - page_cache_release(page[i]); - } - -out: - kfree(actor); - kfree(page); - return res; + return actor; } +int squashfs_readpages_block(struct page *target_page, + struct list_head *readahead_pages, + unsigned int *nr_pages, + struct address_space *mapping, + int page_index, u64 block, int bsize) -static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page) { - struct inode *i = target_page->mapping->host; - struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, - block, bsize); - int bytes = buffer->length, res = buffer->error, n, offset = 0; - void *pageaddr; - - if (res) { - ERROR("Unable to read page, block %llx, size %x\n", block, - bsize); - goto out; - } - - for (n = 0; n < pages && bytes > 0; n++, - bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) { - int avail = min_t(int, bytes, PAGE_CACHE_SIZE); - - if (page[n] == NULL) - continue; + struct squashfs_page_actor *actor; + struct inode *inode = mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int start_index, end_index, file_end, actor_pages, res; + int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; - pageaddr = kmap_atomic(page[n]); - squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail); - kunmap_atomic(pageaddr); - flush_dcache_page(page[n]); - SetPageUptodate(page[n]); - unlock_page(page[n]); - if (page[n] != target_page) - page_cache_release(page[n]); + /* + * If readpage() is called on an uncompressed datablock, we can just + * read the pages instead of fetching the whole block. + * This greatly improves the performance when a process keep doing + * random reads because we only fetch the necessary data. + * The readahead algorithm will take care of doing speculative reads + * if necessary. + * We can't read more than 1 block even if readahead provides use more + * pages because we don't know yet if the next block is compressed or + * not. + */ + if (bsize && !SQUASHFS_COMPRESSED_BLOCK(bsize)) { + u64 block_end = block + msblk->block_size; + + block += (page_index & mask) * PAGE_CACHE_SIZE; + actor_pages = (block_end - block) / PAGE_CACHE_SIZE; + if (*nr_pages < actor_pages) + actor_pages = *nr_pages; + start_index = page_index; + bsize = min_t(int, bsize, (PAGE_CACHE_SIZE * actor_pages) + | SQUASHFS_COMPRESSED_BIT_BLOCK); + } else { + file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + start_index = page_index & ~mask; + end_index = start_index | mask; + if (end_index > file_end) + end_index = file_end; + actor_pages = end_index - start_index + 1; } -out: - squashfs_cache_put(buffer); - return res; + actor = actor_from_page_cache(actor_pages, target_page, + readahead_pages, nr_pages, start_index, + mapping); + if (!actor) + return -ENOMEM; + + res = squashfs_read_data_async(inode->i_sb, block, bsize, NULL, + actor); + return res < 0 ? res : 0; } diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c index c31e2bc9c081..df4fa3c7ddd0 100644 --- a/fs/squashfs/lz4_wrapper.c +++ b/fs/squashfs/lz4_wrapper.c @@ -94,39 +94,17 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, struct buffer_head **bh, int b, int offset, int length, struct squashfs_page_actor *output) { - struct squashfs_lz4 *stream = strm; - void *buff = stream->input, *data; - int avail, i, bytes = length, res; + int res; size_t dest_len = output->length; + struct squashfs_lz4 *stream = strm; - for (i = 0; i < b; i++) { - avail = min(bytes, msblk->devblksize - offset); - memcpy(buff, bh[i]->b_data + offset, avail); - buff += avail; - bytes -= avail; - offset = 0; - put_bh(bh[i]); - } - + squashfs_bh_to_buf(bh, b, stream->input, offset, length, + msblk->devblksize); res = lz4_decompress_unknownoutputsize(stream->input, length, stream->output, &dest_len); if (res) return -EIO; - - bytes = dest_len; - data = squashfs_first_page(output); - buff = stream->output; - while (data) { - if (bytes <= PAGE_CACHE_SIZE) { - memcpy(data, buff, bytes); - break; - } - memcpy(data, buff, PAGE_CACHE_SIZE); - buff += PAGE_CACHE_SIZE; - bytes -= PAGE_CACHE_SIZE; - data = squashfs_next_page(output); - } - squashfs_finish_page(output); + squashfs_buf_to_actor(stream->output, output, dest_len); return dest_len; } diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c index 244b9fbfff7b..2c844d53a59e 100644 --- a/fs/squashfs/lzo_wrapper.c +++ b/fs/squashfs/lzo_wrapper.c @@ -79,45 +79,19 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm, struct buffer_head **bh, int b, int offset, int length, struct squashfs_page_actor *output) { - struct squashfs_lzo *stream = strm; - void *buff = stream->input, *data; - int avail, i, bytes = length, res; + int res; size_t out_len = output->length; + struct squashfs_lzo *stream = strm; - for (i = 0; i < b; i++) { - avail = min(bytes, msblk->devblksize - offset); - memcpy(buff, bh[i]->b_data + offset, avail); - buff += avail; - bytes -= avail; - offset = 0; - put_bh(bh[i]); - } - + squashfs_bh_to_buf(bh, b, stream->input, offset, length, + msblk->devblksize); res = lzo1x_decompress_safe(stream->input, (size_t)length, stream->output, &out_len); if (res != LZO_E_OK) - goto failed; + return -EIO; + squashfs_buf_to_actor(stream->output, output, out_len); - res = bytes = (int)out_len; - data = squashfs_first_page(output); - buff = stream->output; - while (data) { - if (bytes <= PAGE_CACHE_SIZE) { - memcpy(data, buff, bytes); - break; - } else { - memcpy(data, buff, PAGE_CACHE_SIZE); - buff += PAGE_CACHE_SIZE; - bytes -= PAGE_CACHE_SIZE; - data = squashfs_next_page(output); - } - } - squashfs_finish_page(output); - - return res; - -failed: - return -EIO; + return out_len; } const struct squashfs_decompressor squashfs_lzo_comp_ops = { diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c index 5a1c11f56441..53863508e400 100644 --- a/fs/squashfs/page_actor.c +++ b/fs/squashfs/page_actor.c @@ -9,39 +9,11 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/pagemap.h> +#include <linux/buffer_head.h> #include "page_actor.h" -/* - * This file contains implementations of page_actor for decompressing into - * an intermediate buffer, and for decompressing directly into the - * page cache. - * - * Calling code should avoid sleeping between calls to squashfs_first_page() - * and squashfs_finish_page(). - */ - -/* Implementation of page_actor for decompressing into intermediate buffer */ -static void *cache_first_page(struct squashfs_page_actor *actor) -{ - actor->next_page = 1; - return actor->buffer[0]; -} - -static void *cache_next_page(struct squashfs_page_actor *actor) -{ - if (actor->next_page == actor->pages) - return NULL; - - return actor->buffer[actor->next_page++]; -} - -static void cache_finish_page(struct squashfs_page_actor *actor) -{ - /* empty */ -} - -struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, - int pages, int length) +struct squashfs_page_actor *squashfs_page_actor_init(struct page **page, + int pages, int length, void (*release_pages)(struct page **, int, int)) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); @@ -49,52 +21,133 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, return NULL; actor->length = length ? : pages * PAGE_CACHE_SIZE; - actor->buffer = buffer; + actor->page = page; actor->pages = pages; actor->next_page = 0; - actor->squashfs_first_page = cache_first_page; - actor->squashfs_next_page = cache_next_page; - actor->squashfs_finish_page = cache_finish_page; + actor->pageaddr = NULL; + actor->release_pages = release_pages; return actor; } -/* Implementation of page_actor for decompressing directly into page cache. */ -static void *direct_first_page(struct squashfs_page_actor *actor) +void squashfs_page_actor_free(struct squashfs_page_actor *actor, int error) +{ + if (!actor) + return; + + if (actor->release_pages) + actor->release_pages(actor->page, actor->pages, error); + kfree(actor); +} + +void squashfs_actor_to_buf(struct squashfs_page_actor *actor, void *buf, + int length) { - actor->next_page = 1; - return actor->pageaddr = kmap_atomic(actor->page[0]); + void *pageaddr; + int pos = 0, avail, i; + + for (i = 0; i < actor->pages && pos < length; ++i) { + avail = min_t(int, length - pos, PAGE_CACHE_SIZE); + if (actor->page[i]) { + pageaddr = kmap_atomic(actor->page[i]); + memcpy(buf + pos, pageaddr, avail); + kunmap_atomic(pageaddr); + } + pos += avail; + } } -static void *direct_next_page(struct squashfs_page_actor *actor) +void squashfs_buf_to_actor(void *buf, struct squashfs_page_actor *actor, + int length) { - if (actor->pageaddr) - kunmap_atomic(actor->pageaddr); + void *pageaddr; + int pos = 0, avail, i; + + for (i = 0; i < actor->pages && pos < length; ++i) { + avail = min_t(int, length - pos, PAGE_CACHE_SIZE); + if (actor->page[i]) { + pageaddr = kmap_atomic(actor->page[i]); + memcpy(pageaddr, buf + pos, avail); + kunmap_atomic(pageaddr); + } + pos += avail; + } +} - return actor->pageaddr = actor->next_page == actor->pages ? NULL : - kmap_atomic(actor->page[actor->next_page++]); +void squashfs_bh_to_actor(struct buffer_head **bh, int nr_buffers, + struct squashfs_page_actor *actor, int offset, int length, int blksz) +{ + void *kaddr = NULL; + int bytes = 0, pgoff = 0, b = 0, p = 0, avail, i; + + while (bytes < length) { + if (actor->page[p]) { + kaddr = kmap_atomic(actor->page[p]); + while (pgoff < PAGE_CACHE_SIZE && bytes < length) { + avail = min_t(int, blksz - offset, + PAGE_CACHE_SIZE - pgoff); + memcpy(kaddr + pgoff, bh[b]->b_data + offset, + avail); + pgoff += avail; + bytes += avail; + offset = (offset + avail) % blksz; + if (!offset) { + put_bh(bh[b]); + ++b; + } + } + kunmap_atomic(kaddr); + pgoff = 0; + } else { + for (i = 0; i < PAGE_CACHE_SIZE / blksz; ++i) { + if (bh[b]) + put_bh(bh[b]); + ++b; + } + bytes += PAGE_CACHE_SIZE; + } + ++p; + } } -static void direct_finish_page(struct squashfs_page_actor *actor) +void squashfs_bh_to_buf(struct buffer_head **bh, int nr_buffers, void *buf, + int offset, int length, int blksz) { - if (actor->pageaddr) - kunmap_atomic(actor->pageaddr); + int i, avail, bytes = 0; + + for (i = 0; i < nr_buffers && bytes < length; ++i) { + avail = min_t(int, length - bytes, blksz - offset); + if (bh[i]) { + memcpy(buf + bytes, bh[i]->b_data + offset, avail); + put_bh(bh[i]); + } + bytes += avail; + offset = 0; + } } -struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page, - int pages, int length) +void free_page_array(struct page **page, int nr_pages) { - struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); + int i; - if (actor == NULL) - return NULL; + for (i = 0; i < nr_pages; ++i) + __free_page(page[i]); + kfree(page); +} - actor->length = length ? : pages * PAGE_CACHE_SIZE; - actor->page = page; - actor->pages = pages; - actor->next_page = 0; - actor->pageaddr = NULL; - actor->squashfs_first_page = direct_first_page; - actor->squashfs_next_page = direct_next_page; - actor->squashfs_finish_page = direct_finish_page; - return actor; +struct page **alloc_page_array(int nr_pages, int gfp_mask) +{ + int i; + struct page **page; + + page = kcalloc(nr_pages, sizeof(struct page *), gfp_mask); + if (!page) + return NULL; + for (i = 0; i < nr_pages; ++i) { + page[i] = alloc_page(gfp_mask); + if (!page[i]) { + free_page_array(page, i); + return NULL; + } + } + return page; } diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h index 26dd82008b82..aa1ed790b5a3 100644 --- a/fs/squashfs/page_actor.h +++ b/fs/squashfs/page_actor.h @@ -5,77 +5,61 @@ * Phillip Lougher <phillip@squashfs.org.uk> * * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. + * the COPYING file in the top-level squashfsory. */ -#ifndef CONFIG_SQUASHFS_FILE_DIRECT struct squashfs_page_actor { - void **page; + struct page **page; + void *pageaddr; int pages; int length; int next_page; + void (*release_pages)(struct page **, int, int); }; -static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page, - int pages, int length) -{ - struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); - - if (actor == NULL) - return NULL; +extern struct squashfs_page_actor *squashfs_page_actor_init(struct page **, + int, int, void (*)(struct page **, int, int)); +extern void squashfs_page_actor_free(struct squashfs_page_actor *, int); - actor->length = length ? : pages * PAGE_CACHE_SIZE; - actor->page = page; - actor->pages = pages; - actor->next_page = 0; - return actor; -} +extern void squashfs_actor_to_buf(struct squashfs_page_actor *, void *, int); +extern void squashfs_buf_to_actor(void *, struct squashfs_page_actor *, int); +extern void squashfs_bh_to_actor(struct buffer_head **, int, + struct squashfs_page_actor *, int, int, int); +extern void squashfs_bh_to_buf(struct buffer_head **, int, void *, int, int, + int); +/* + * Calling code should avoid sleeping between calls to squashfs_first_page() + * and squashfs_finish_page(). + */ static inline void *squashfs_first_page(struct squashfs_page_actor *actor) { actor->next_page = 1; - return actor->page[0]; + return actor->pageaddr = actor->page[0] ? kmap_atomic(actor->page[0]) + : NULL; } static inline void *squashfs_next_page(struct squashfs_page_actor *actor) { - return actor->next_page == actor->pages ? NULL : - actor->page[actor->next_page++]; -} + if (!IS_ERR_OR_NULL(actor->pageaddr)) + kunmap_atomic(actor->pageaddr); -static inline void squashfs_finish_page(struct squashfs_page_actor *actor) -{ - /* empty */ -} -#else -struct squashfs_page_actor { - union { - void **buffer; - struct page **page; - }; - void *pageaddr; - void *(*squashfs_first_page)(struct squashfs_page_actor *); - void *(*squashfs_next_page)(struct squashfs_page_actor *); - void (*squashfs_finish_page)(struct squashfs_page_actor *); - int pages; - int length; - int next_page; -}; + if (actor->next_page == actor->pages) + return actor->pageaddr = ERR_PTR(-ENODATA); -extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int); -extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page - **, int, int); -static inline void *squashfs_first_page(struct squashfs_page_actor *actor) -{ - return actor->squashfs_first_page(actor); -} -static inline void *squashfs_next_page(struct squashfs_page_actor *actor) -{ - return actor->squashfs_next_page(actor); + actor->pageaddr = actor->page[actor->next_page] ? + kmap_atomic(actor->page[actor->next_page]) : NULL; + ++actor->next_page; + return actor->pageaddr; } + static inline void squashfs_finish_page(struct squashfs_page_actor *actor) { - actor->squashfs_finish_page(actor); + if (!IS_ERR_OR_NULL(actor->pageaddr)) + kunmap_atomic(actor->pageaddr); } -#endif + +extern struct page **alloc_page_array(int, int); +extern void free_page_array(struct page **, int); + #endif diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 887d6d270080..6093579c6c5d 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -28,8 +28,14 @@ #define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args) /* block.c */ +extern int squashfs_init_read_wq(void); +extern void squashfs_destroy_read_wq(void); extern int squashfs_read_data(struct super_block *, u64, int, u64 *, struct squashfs_page_actor *); +extern int squashfs_read_data(struct super_block *, u64, int, u64 *, + struct squashfs_page_actor *); +extern int squashfs_read_data_async(struct super_block *, u64, int, u64 *, + struct squashfs_page_actor *); /* cache.c */ extern struct squashfs_cache *squashfs_cache_init(char *, int, int); @@ -70,8 +76,9 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *, void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int, int); -/* file_xxx.c */ -extern int squashfs_readpage_block(struct page *, u64, int); +/* file_direct.c */ +extern int squashfs_readpages_block(struct page *, struct list_head *, + unsigned int *, struct address_space *, int, u64, int); /* id.c */ extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 1da565cb50c3..8a6995de0277 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -49,7 +49,7 @@ struct squashfs_cache_entry { int num_waiters; wait_queue_head_t wait_queue; struct squashfs_cache *cache; - void **data; + struct page **page; struct squashfs_page_actor *actor; }; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 5056babe00df..61cd0b39ed0e 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -444,9 +444,15 @@ static int __init init_squashfs_fs(void) if (err) return err; + if (!squashfs_init_read_wq()) { + destroy_inodecache(); + return -ENOMEM; + } + err = register_filesystem(&squashfs_fs_type); if (err) { destroy_inodecache(); + squashfs_destroy_read_wq(); return err; } @@ -460,6 +466,7 @@ static void __exit exit_squashfs_fs(void) { unregister_filesystem(&squashfs_fs_type); destroy_inodecache(); + squashfs_destroy_read_wq(); } diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c index c609624e4b8a..14cd373e1897 100644 --- a/fs/squashfs/xz_wrapper.c +++ b/fs/squashfs/xz_wrapper.c @@ -55,7 +55,7 @@ static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk, struct comp_opts *opts; int err = 0, n; - opts = kmalloc(sizeof(*opts), GFP_KERNEL); + opts = kmalloc(sizeof(*opts), GFP_ATOMIC); if (opts == NULL) { err = -ENOMEM; goto out2; @@ -136,6 +136,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, enum xz_ret xz_err; int avail, total = 0, k = 0; struct squashfs_xz *stream = strm; + void *buf = NULL; xz_dec_reset(stream->state); stream->buf.in_pos = 0; @@ -156,12 +157,20 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, if (stream->buf.out_pos == stream->buf.out_size) { stream->buf.out = squashfs_next_page(output); - if (stream->buf.out != NULL) { + if (!IS_ERR(stream->buf.out)) { stream->buf.out_pos = 0; total += PAGE_CACHE_SIZE; } } + if (!stream->buf.out) { + if (!buf) { + buf = kmalloc(PAGE_CACHE_SIZE, GFP_ATOMIC); + if (!buf) + goto out; + } + stream->buf.out = buf; + } xz_err = xz_dec_run(stream->state, &stream->buf); if (stream->buf.in_pos == stream->buf.in_size && k < b) @@ -173,11 +182,13 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, if (xz_err != XZ_STREAM_END || k < b) goto out; + kfree(buf); return total + stream->buf.out_pos; out: for (; k < b; k++) put_bh(bh[k]); + kfree(buf); return -EIO; } diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c index 8727caba6882..09c892b5308e 100644 --- a/fs/squashfs/zlib_wrapper.c +++ b/fs/squashfs/zlib_wrapper.c @@ -66,6 +66,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, struct buffer_head **bh, int b, int offset, int length, struct squashfs_page_actor *output) { + void *buf = NULL; int zlib_err, zlib_init = 0, k = 0; z_stream *stream = strm; @@ -84,10 +85,19 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, if (stream->avail_out == 0) { stream->next_out = squashfs_next_page(output); - if (stream->next_out != NULL) + if (!IS_ERR(stream->next_out)) stream->avail_out = PAGE_CACHE_SIZE; } + if (!stream->next_out) { + if (!buf) { + buf = kmalloc(PAGE_CACHE_SIZE, GFP_ATOMIC); + if (!buf) + goto out; + } + stream->next_out = buf; + } + if (!zlib_init) { zlib_err = zlib_inflateInit(stream); if (zlib_err != Z_OK) { @@ -115,11 +125,13 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, if (k < b) goto out; + kfree(buf); return stream->total_out; out: for (; k < b; k++) put_bh(bh[k]); + kfree(buf); return -EIO; } diff --git a/fs/stat.c b/fs/stat.c index d4a61d8dc021..004dd77c3b93 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -31,7 +31,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; - stat->blksize = (1 << inode->i_blkbits); + stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; } @@ -454,6 +454,7 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes) inode->i_bytes -= 512; } } +EXPORT_SYMBOL(__inode_add_bytes); void inode_add_bytes(struct inode *inode, loff_t bytes) { diff --git a/fs/super.c b/fs/super.c index b938b14f6041..c96434ea71e2 100644 --- a/fs/super.c +++ b/fs/super.c @@ -703,7 +703,8 @@ rescan: } /** - * do_remount_sb - asks filesystem to change mount options. + * do_remount_sb2 - asks filesystem to change mount options. + * @mnt: mount we are looking at * @sb: superblock in question * @flags: numeric part of options * @data: the rest of options @@ -711,7 +712,7 @@ rescan: * * Alters the mount options of a mounted file system. */ -int do_remount_sb(struct super_block *sb, int flags, void *data, int force) +int do_remount_sb2(struct vfsmount *mnt, struct super_block *sb, int flags, void *data, int force) { int retval; int remount_ro; @@ -753,7 +754,16 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) } } - if (sb->s_op->remount_fs) { + if (mnt && sb->s_op->remount_fs2) { + retval = sb->s_op->remount_fs2(mnt, sb, &flags, data); + if (retval) { + if (!force) + goto cancel_readonly; + /* If forced remount, go ahead despite any errors */ + WARN(1, "forced remount of a %s fs returned %i\n", + sb->s_type->name, retval); + } + } else if (sb->s_op->remount_fs) { retval = sb->s_op->remount_fs(sb, &flags, data); if (retval) { if (!force) @@ -785,6 +795,11 @@ cancel_readonly: return retval; } +int do_remount_sb(struct super_block *sb, int flags, void *data, int force) +{ + return do_remount_sb2(NULL, sb, flags, data, force); +} + static void do_emergency_remount(struct work_struct *work) { struct super_block *sb, *p = NULL; @@ -1104,7 +1119,7 @@ struct dentry *mount_single(struct file_system_type *fs_type, EXPORT_SYMBOL(mount_single); struct dentry * -mount_fs(struct file_system_type *type, int flags, const char *name, void *data) +mount_fs(struct file_system_type *type, int flags, const char *name, struct vfsmount *mnt, void *data) { struct dentry *root; struct super_block *sb; @@ -1121,7 +1136,10 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) goto out_free_secdata; } - root = type->mount(type, flags, name, data); + if (type->mount2) + root = type->mount2(mnt, type, flags, name, data); + else + root = type->mount(type, flags, name, data); if (IS_ERR(root)) { error = PTR_ERR(root); goto out_free_secdata; diff --git a/fs/sync.c b/fs/sync.c index dd5d1711c7ac..452179e31c39 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -218,6 +218,7 @@ static int do_fsync(unsigned int fd, int datasync) if (f.file) { ret = vfs_fsync(f.file, datasync); fdput(f); + inc_syscfs(current); } return ret; } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index b803213d1307..39c75a86c67f 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; - size_t len; + ssize_t len; /* * If buf != of->prealloc_buf, we don't know how @@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, if (WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; len = ops->show(kobj, of->kn->priv, buf); + if (len < 0) + return len; if (pos) { if (len <= pos) return 0; len -= pos; memmove(buf, buf + pos, len); } - return min(count, len); + return min_t(ssize_t, count, len); } /* kernfs write callback for regular sysfs files */ diff --git a/fs/timerfd.c b/fs/timerfd.c index 053818dd6c18..1327a02ec778 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -40,6 +40,7 @@ struct timerfd_ctx { short unsigned settime_flags; /* to show in fdinfo */ struct rcu_head rcu; struct list_head clist; + spinlock_t cancel_lock; bool might_cancel; }; @@ -112,7 +113,7 @@ void timerfd_clock_was_set(void) rcu_read_unlock(); } -static void timerfd_remove_cancel(struct timerfd_ctx *ctx) +static void __timerfd_remove_cancel(struct timerfd_ctx *ctx) { if (ctx->might_cancel) { ctx->might_cancel = false; @@ -122,6 +123,13 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx) } } +static void timerfd_remove_cancel(struct timerfd_ctx *ctx) +{ + spin_lock(&ctx->cancel_lock); + __timerfd_remove_cancel(ctx); + spin_unlock(&ctx->cancel_lock); +} + static bool timerfd_canceled(struct timerfd_ctx *ctx) { if (!ctx->might_cancel || ctx->moffs.tv64 != KTIME_MAX) @@ -132,6 +140,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx) static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) { + spin_lock(&ctx->cancel_lock); if ((ctx->clockid == CLOCK_REALTIME || ctx->clockid == CLOCK_REALTIME_ALARM) && (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) { @@ -141,9 +150,10 @@ static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) list_add_rcu(&ctx->clist, &cancel_list); spin_unlock(&cancel_lock); } - } else if (ctx->might_cancel) { - timerfd_remove_cancel(ctx); + } else { + __timerfd_remove_cancel(ctx); } + spin_unlock(&ctx->cancel_lock); } static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) @@ -395,6 +405,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) return -ENOMEM; init_waitqueue_head(&ctx->wqh); + spin_lock_init(&ctx->cancel_lock); ctx->clockid = clockid; if (isalarm(ctx)) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 566df9b5a6cb..0e659d9c69a1 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1206,7 +1206,7 @@ int udf_setsize(struct inode *inode, loff_t newsize) { int err; struct udf_inode_info *iinfo; - int bsize = 1 << inode->i_blkbits; + int bsize = i_blocksize(inode); if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) @@ -1235,8 +1235,8 @@ int udf_setsize(struct inode *inode, loff_t newsize) return err; } set_size: - truncate_setsize(inode, newsize); up_write(&iinfo->i_data_sem); + truncate_setsize(inode, newsize); } else { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); @@ -1253,9 +1253,9 @@ set_size: udf_get_block); if (err) return err; + truncate_setsize(inode, newsize); down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); - truncate_setsize(inode, newsize); udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); } diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index dc5fae601c24..637e17cb0edd 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -81,7 +81,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) ufs_error (sb, "ufs_free_fragments", "bit already cleared for fragment %u", i); } - + + inode_sub_bytes(inode, count << uspi->s_fshift); fs32_add(sb, &ucg->cg_cs.cs_nffree, count); uspi->cs_total.cs_nffree += count; fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count); @@ -183,6 +184,7 @@ do_more: ufs_error(sb, "ufs_free_blocks", "freeing free fragment"); } ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno); + inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift); if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD) ufs_clusteracct (sb, ucpi, blkno, 1); @@ -494,6 +496,20 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, return 0; } +static bool try_add_frags(struct inode *inode, unsigned frags) +{ + unsigned size = frags * i_blocksize(inode); + spin_lock(&inode->i_lock); + __inode_add_bytes(inode, size); + if (unlikely((u32)inode->i_blocks != inode->i_blocks)) { + __inode_sub_bytes(inode, size); + spin_unlock(&inode->i_lock); + return false; + } + spin_unlock(&inode->i_lock); + return true; +} + static u64 ufs_add_fragments(struct inode *inode, u64 fragment, unsigned oldcount, unsigned newcount) { @@ -530,6 +546,9 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, for (i = oldcount; i < newcount; i++) if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i)) return 0; + + if (!try_add_frags(inode, count)) + return 0; /* * Block can be extended */ @@ -647,6 +666,7 @@ cg_found: ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i); i = uspi->s_fpb - count; + inode_sub_bytes(inode, i << uspi->s_fshift); fs32_add(sb, &ucg->cg_cs.cs_nffree, i); uspi->cs_total.cs_nffree += i; fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i); @@ -657,6 +677,8 @@ cg_found: result = ufs_bitmap_search (sb, ucpi, goal, allocsize); if (result == INVBLOCK) return 0; + if (!try_add_frags(inode, count)) + return 0; for (i = 0; i < count; i++) ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i); @@ -716,6 +738,8 @@ norot: return INVBLOCK; ucpi->c_rotor = result; gotit: + if (!try_add_frags(inode, uspi->s_fpb)) + return 0; blkno = ufs_fragstoblks(result); ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno); if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD) diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index a064cf44b143..1f69bb9b1e9d 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -235,7 +235,8 @@ ufs_extend_tail(struct inode *inode, u64 writes_to, p = ufs_get_direct_data_ptr(uspi, ufsi, block); tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p), - new_size, err, locked_page); + new_size - (lastfrag & uspi->s_fpbmask), err, + locked_page); return tmp != 0; } @@ -284,7 +285,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index, goal += uspi->s_fpb; } tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment), - goal, uspi->s_fpb, err, locked_page); + goal, nfrags, err, locked_page); if (!tmp) { *err = -ENOSPC; @@ -402,7 +403,9 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff if (!create) { phys64 = ufs_frag_map(inode, offsets, depth); - goto out; + if (phys64) + map_bh(bh_result, sb, phys64 + frag); + return 0; } /* This code entered only while writing ....? */ diff --git a/fs/ufs/super.c b/fs/ufs/super.c index f6390eec02ca..10f364490833 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -746,6 +746,23 @@ static void ufs_put_super(struct super_block *sb) return; } +static u64 ufs_max_bytes(struct super_block *sb) +{ + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + int bits = uspi->s_apbshift; + u64 res; + + if (bits > 21) + res = ~0ULL; + else + res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) + + (1LL << (3*bits)); + + if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift)) + return MAX_LFS_FILESIZE; + return res << uspi->s_bshift; +} + static int ufs_fill_super(struct super_block *sb, void *data, int silent) { struct ufs_sb_info * sbi; @@ -1212,6 +1229,7 @@ magic_found: "fast symlink size (%u)\n", uspi->s_maxsymlinklen); uspi->s_maxsymlinklen = maxsymlen; } + sb->s_maxbytes = ufs_max_bytes(sb); sb->s_max_links = UFS_LINK_MAX; inode = ufs_iget(sb, UFS_ROOTINO); diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 954175928240..3f9463f8cf2f 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -473,15 +473,19 @@ static inline unsigned _ubh_find_last_zero_bit_( static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi, struct ufs_buffer_head * ubh, unsigned begin, unsigned block) { + u8 mask; switch (uspi->s_fpb) { case 8: return (*ubh_get_addr (ubh, begin + block) == 0xff); case 4: - return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2))); + mask = 0x0f << ((block & 0x01) << 2); + return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask; case 2: - return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1))); + mask = 0x03 << ((block & 0x03) << 1); + return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask; case 1: - return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07))); + mask = 0x01 << (block & 0x07); + return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask; } return 0; } diff --git a/fs/utimes.c b/fs/utimes.c index cb771c30d102..a35e909cf8e3 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -91,7 +91,7 @@ static int utimes_common(struct path *path, struct timespec *times) } retry_deleg: mutex_lock(&inode->i_mutex); - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode); mutex_unlock(&inode->i_mutex); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); diff --git a/fs/xattr.c b/fs/xattr.c index 9b932b95d74e..f0da9d24e9ca 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -442,7 +442,7 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, size = XATTR_SIZE_MAX; kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!kvalue) { - vvalue = vmalloc(size); + vvalue = vzalloc(size); if (!vvalue) return -ENOMEM; kvalue = vvalue; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 119c2422aac7..75884aecf920 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -2179,8 +2179,10 @@ xfs_bmap_add_extent_delay_real( } temp = xfs_bmap_worst_indlen(bma->ip, temp); temp2 = xfs_bmap_worst_indlen(bma->ip, temp2); - diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) - - (bma->cur ? bma->cur->bc_private.b.allocated : 0)); + diff = (int)(temp + temp2 - + (startblockval(PREV.br_startblock) - + (bma->cur ? + bma->cur->bc_private.b.allocated : 0))); if (diff > 0) { error = xfs_mod_fdblocks(bma->ip->i_mount, -((int64_t)diff), false); @@ -2232,7 +2234,6 @@ xfs_bmap_add_extent_delay_real( temp = da_new; if (bma->cur) temp += bma->cur->bc_private.b.allocated; - ASSERT(temp <= da_old); if (temp < da_old) xfs_mod_fdblocks(bma->ip->i_mount, (int64_t)(da_old - temp), false); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index af1bbee5586e..28bc5e78b110 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4064,7 +4064,7 @@ xfs_btree_change_owner( xfs_btree_readahead_ptr(cur, ptr, 1); /* save for the next iteration of the loop */ - lptr = *ptr; + xfs_btree_copy_ptrs(cur, &lptr, ptr, 1); } /* for each buffer in the level */ diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 1aabfda669b0..7183b7ea065b 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -299,6 +299,14 @@ xfs_dinode_verify( if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC)) return false; + /* don't allow invalid i_size */ + if (be64_to_cpu(dip->di_size) & (1ULL << 63)) + return false; + + /* No zero-length symlinks. */ + if (S_ISLNK(be16_to_cpu(dip->di_mode)) && dip->di_size == 0) + return false; + /* only version 3 or greater inodes are extensively verified here */ if (dip->di_version < 3) return true; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 29e7e5dd5178..a9063ac50c4e 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -288,7 +288,7 @@ xfs_map_blocks( { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - ssize_t count = 1 << inode->i_blkbits; + ssize_t count = i_blocksize(inode); xfs_fileoff_t offset_fsb, end_fsb; int error = 0; int bmapi_flags = XFS_BMAPI_ENTIRE; @@ -921,7 +921,7 @@ xfs_aops_discard_page( break; } next_buffer: - offset += 1 << inode->i_blkbits; + offset += i_blocksize(inode); } while ((bh = bh->b_this_page) != head); @@ -1363,7 +1363,7 @@ xfs_map_trim_size( offset + mapping_size >= i_size_read(inode)) { /* limit mapping to block that spans EOF */ mapping_size = roundup_64(i_size_read(inode) - offset, - 1 << inode->i_blkbits); + i_blocksize(inode)); } if (mapping_size > LONG_MAX) mapping_size = LONG_MAX; @@ -1395,7 +1395,7 @@ __xfs_get_blocks( return -EIO; offset = (xfs_off_t)iblock << inode->i_blkbits; - ASSERT(bh_result->b_size >= (1 << inode->i_blkbits)); + ASSERT(bh_result->b_size >= i_blocksize(inode)); size = bh_result->b_size; if (!create && direct && offset >= i_size_read(inode)) @@ -1426,6 +1426,26 @@ __xfs_get_blocks( if (error) goto out_unlock; + /* + * The only time we can ever safely find delalloc blocks on direct I/O + * is a dio write to post-eof speculative preallocation. All other + * scenarios are indicative of a problem or misuse (such as mixing + * direct and mapped I/O). + * + * The file may be unmapped by the time we get here so we cannot + * reliably fail the I/O based on mapping. Instead, fail the I/O if this + * is a read or a write within eof. Otherwise, carry on but warn as a + * precuation if the file happens to be mapped. + */ + if (direct && imap.br_startblock == DELAYSTARTBLOCK) { + if (!create || offset < i_size_read(VFS_I(ip))) { + WARN_ON_ONCE(1); + error = -EIO; + goto out_unlock; + } + WARN_ON_ONCE(mapping_mapped(VFS_I(ip)->i_mapping)); + } + /* for DAX, we convert unwritten extents directly */ if (create && (!nimaps || @@ -1525,7 +1545,6 @@ __xfs_get_blocks( set_buffer_new(bh_result); if (imap.br_startblock == DELAYSTARTBLOCK) { - BUG_ON(direct); if (create) { set_buffer_uptodate(bh_result); set_buffer_mapped(bh_result); @@ -1968,7 +1987,7 @@ xfs_vm_set_page_dirty( if (offset < end_offset) set_buffer_dirty(bh); bh = bh->b_this_page; - offset += 1 << inode->i_blkbits; + offset += i_blocksize(inode); } while (bh != head); } /* diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h index dd4824589470..234331227c0c 100644 --- a/fs/xfs/xfs_attr.h +++ b/fs/xfs/xfs_attr.h @@ -112,6 +112,7 @@ typedef struct attrlist_cursor_kern { *========================================================================*/ +/* Return 0 on success, or -errno; other state communicated via *context */ typedef int (*put_listent_func_t)(struct xfs_attr_list_context *, int, unsigned char *, int, int, unsigned char *); diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 4fa14820e2e2..c8be331a3196 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -108,16 +108,14 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context) (int)sfe->namelen, (int)sfe->valuelen, &sfe->nameval[sfe->namelen]); - + if (error) + return error; /* * Either search callback finished early or * didn't fit it all in the buffer after all. */ if (context->seen_enough) break; - - if (error) - return error; sfe = XFS_ATTR_SF_NEXTENTRY(sfe); } trace_xfs_attr_list_sf_all(context); @@ -581,7 +579,7 @@ xfs_attr_put_listent( trace_xfs_attr_list_full(context); alist->al_more = 1; context->seen_enough = 1; - return 1; + return 0; } aep = (attrlist_ent_t *)&context->alist[context->firstu]; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index dbae6490a79a..863e1bff403b 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -682,7 +682,7 @@ xfs_getbmap( * extents. */ if (map[i].br_startblock == DELAYSTARTBLOCK && - map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) + map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) ASSERT((iflags & BMV_IF_DELALLOC) != 0); if (map[i].br_startblock == HOLESTARTBLOCK && @@ -1713,6 +1713,7 @@ xfs_swap_extents( xfs_trans_t *tp; xfs_bstat_t *sbp = &sxp->sx_stat; xfs_ifork_t *tempifp, *ifp, *tifp; + xfs_extnum_t nextents; int src_log_flags, target_log_flags; int error = 0; int aforkblks = 0; @@ -1899,7 +1900,8 @@ xfs_swap_extents( * pointer. Otherwise it's already NULL or * pointing to the extent. */ - if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) { + nextents = ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + if (nextents <= XFS_INLINE_EXTS) { ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext; } @@ -1918,7 +1920,8 @@ xfs_swap_extents( * pointer. Otherwise it's already NULL or * pointing to the extent. */ - if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) { + nextents = tip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t); + if (nextents <= XFS_INLINE_EXTS) { tifp->if_u1.if_extents = tifp->if_u2.if_inline_ext; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index eb1b8c8acfcb..dcb70969ff1c 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -375,6 +375,7 @@ retry: out_free_pages: for (i = 0; i < bp->b_page_count; i++) __free_page(bp->b_pages[i]); + bp->b_flags &= ~_XBF_PAGES; return error; } @@ -978,6 +979,8 @@ void xfs_buf_unlock( struct xfs_buf *bp) { + ASSERT(xfs_buf_islocked(bp)); + XB_CLEAR_OWNER(bp); up(&bp->b_sema); @@ -1712,6 +1715,28 @@ error: } /* + * Cancel a delayed write list. + * + * Remove each buffer from the list, clear the delwri queue flag and drop the + * associated buffer reference. + */ +void +xfs_buf_delwri_cancel( + struct list_head *list) +{ + struct xfs_buf *bp; + + while (!list_empty(list)) { + bp = list_first_entry(list, struct xfs_buf, b_list); + + xfs_buf_lock(bp); + bp->b_flags &= ~_XBF_DELWRI_Q; + list_del_init(&bp->b_list); + xfs_buf_relse(bp); + } +} + +/* * Add a buffer to the delayed write list. * * This queues a buffer for writeout if it hasn't already been. Note that diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index c75721acd867..149bbd451731 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -304,6 +304,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, extern void *xfs_buf_offset(struct xfs_buf *, size_t); /* Delayed Write Buffer Routines */ +extern void xfs_buf_delwri_cancel(struct list_head *); extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); extern int xfs_buf_delwri_submit(struct list_head *); extern int xfs_buf_delwri_submit_nowait(struct list_head *); diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 642d55d10075..2fbf643fa10a 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -406,6 +406,7 @@ xfs_dir2_leaf_readbuf( /* * Do we need more readahead? + * Each loop tries to process 1 full dir blk; last may be partial. */ blk_start_plug(&plug); for (mip->ra_index = mip->ra_offset = i = 0; @@ -416,7 +417,8 @@ xfs_dir2_leaf_readbuf( * Read-ahead a contiguous directory block. */ if (i > mip->ra_current && - map[mip->ra_index].br_blockcount >= geo->fsbcount) { + (map[mip->ra_index].br_blockcount - mip->ra_offset) >= + geo->fsbcount) { xfs_dir3_data_readahead(dp, map[mip->ra_index].br_startoff + mip->ra_offset, XFS_FSB_TO_DADDR(dp->i_mount, @@ -437,14 +439,19 @@ xfs_dir2_leaf_readbuf( } /* - * Advance offset through the mapping table. + * Advance offset through the mapping table, processing a full + * dir block even if it is fragmented into several extents. + * But stop if we have consumed all valid mappings, even if + * it's not yet a full directory block. */ - for (j = 0; j < geo->fsbcount; j += length ) { + for (j = 0; + j < geo->fsbcount && mip->ra_index < mip->map_valid; + j += length ) { /* * The rest of this extent but not more than a dir * block. */ - length = min_t(int, geo->fsbcount, + length = min_t(int, geo->fsbcount - j, map[mip->ra_index].br_blockcount - mip->ra_offset); mip->ra_offset += length; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f5392ab2def1..3dd47307363f 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -947,7 +947,7 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { - unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + unsigned int blksize_mask = i_blocksize(inode) - 1; if (offset & blksize_mask || len & blksize_mask) { error = -EINVAL; @@ -969,7 +969,7 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_INSERT_RANGE) { - unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + unsigned int blksize_mask = i_blocksize(inode) - 1; new_size = i_size_read(inode) + len; if (offset & blksize_mask || len & blksize_mask) { @@ -1208,7 +1208,7 @@ xfs_find_get_desired_pgoff( unsigned nr_pages; unsigned int i; - want = min_t(pgoff_t, end - index, PAGEVEC_SIZE); + want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want); /* @@ -1235,17 +1235,6 @@ xfs_find_get_desired_pgoff( break; } - /* - * At lease we found one page. If this is the first time we - * step into the loop, and if the first page index offset is - * greater than the given search offset, a hole was found. - */ - if (type == HOLE_OFF && lastoff == startoff && - lastoff < page_offset(pvec.pages[0])) { - found = true; - break; - } - for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; loff_t b_offset; @@ -1257,18 +1246,18 @@ xfs_find_get_desired_pgoff( * file mapping. However, page->index will not change * because we have a reference on the page. * - * Searching done if the page index is out of range. - * If the current offset is not reaches the end of - * the specified search range, there should be a hole - * between them. + * If current page offset is beyond where we've ended, + * we've found a hole. */ - if (page->index > end) { - if (type == HOLE_OFF && lastoff < endoff) { - *offset = lastoff; - found = true; - } + if (type == HOLE_OFF && lastoff < endoff && + lastoff < page_offset(pvec.pages[i])) { + found = true; + *offset = lastoff; goto out; } + /* Searching done if the page index is out of range. */ + if (page->index > end) + goto out; lock_page(page); /* diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index d7a490f24ead..adbc1f59969a 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -210,14 +210,17 @@ xfs_iget_cache_hit( error = inode_init_always(mp->m_super, inode); if (error) { + bool wake; /* * Re-initializing the inode failed, and we are in deep * trouble. Try to re-add it to the reclaim list. */ rcu_read_lock(); spin_lock(&ip->i_flags_lock); - + wake = !!__xfs_iflags_test(ip, XFS_INEW); ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); + if (wake) + wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); ASSERT(ip->i_flags & XFS_IRECLAIMABLE); trace_xfs_iget_reclaim_fail(ip); goto out_error; @@ -363,6 +366,22 @@ out_destroy: return error; } +static void +xfs_inew_wait( + struct xfs_inode *ip) +{ + wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT); + DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT); + + do { + prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + if (!xfs_iflags_test(ip, XFS_INEW)) + break; + schedule(); + } while (true); + finish_wait(wq, &wait.wait); +} + /* * Look up an inode by number in the given file system. * The inode is looked up in the cache held in each AG. @@ -467,9 +486,11 @@ out_error_or_again: STATIC int xfs_inode_ag_walk_grab( - struct xfs_inode *ip) + struct xfs_inode *ip, + int flags) { struct inode *inode = VFS_I(ip); + bool newinos = !!(flags & XFS_AGITER_INEW_WAIT); ASSERT(rcu_read_lock_held()); @@ -487,7 +508,8 @@ xfs_inode_ag_walk_grab( goto out_unlock_noent; /* avoid new or reclaimable inodes. Leave for reclaim code to flush */ - if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM)) + if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) || + __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM)) goto out_unlock_noent; spin_unlock(&ip->i_flags_lock); @@ -515,7 +537,8 @@ xfs_inode_ag_walk( void *args), int flags, void *args, - int tag) + int tag, + int iter_flags) { uint32_t first_index; int last_error = 0; @@ -557,7 +580,7 @@ restart: for (i = 0; i < nr_found; i++) { struct xfs_inode *ip = batch[i]; - if (done || xfs_inode_ag_walk_grab(ip)) + if (done || xfs_inode_ag_walk_grab(ip, iter_flags)) batch[i] = NULL; /* @@ -585,6 +608,9 @@ restart: for (i = 0; i < nr_found; i++) { if (!batch[i]) continue; + if ((iter_flags & XFS_AGITER_INEW_WAIT) && + xfs_iflags_test(batch[i], XFS_INEW)) + xfs_inew_wait(batch[i]); error = execute(batch[i], flags, args); IRELE(batch[i]); if (error == -EAGAIN) { @@ -637,12 +663,13 @@ xfs_eofblocks_worker( } int -xfs_inode_ag_iterator( +xfs_inode_ag_iterator_flags( struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, int flags, void *args), int flags, - void *args) + void *args, + int iter_flags) { struct xfs_perag *pag; int error = 0; @@ -652,7 +679,8 @@ xfs_inode_ag_iterator( ag = 0; while ((pag = xfs_perag_get(mp, ag))) { ag = pag->pag_agno + 1; - error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1); + error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1, + iter_flags); xfs_perag_put(pag); if (error) { last_error = error; @@ -664,6 +692,17 @@ xfs_inode_ag_iterator( } int +xfs_inode_ag_iterator( + struct xfs_mount *mp, + int (*execute)(struct xfs_inode *ip, int flags, + void *args), + int flags, + void *args) +{ + return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0); +} + +int xfs_inode_ag_iterator_tag( struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, int flags, @@ -680,7 +719,8 @@ xfs_inode_ag_iterator_tag( ag = 0; while ((pag = xfs_perag_get_tag(mp, ag, tag))) { ag = pag->pag_agno + 1; - error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag); + error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag, + 0); xfs_perag_put(pag); if (error) { last_error = error; diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 62f1f91c32cb..147a79212e63 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -48,6 +48,11 @@ struct xfs_eofblocks { #define XFS_IGET_UNTRUSTED 0x2 #define XFS_IGET_DONTCACHE 0x4 +/* + * flags for AG inode iterator + */ +#define XFS_AGITER_INEW_WAIT 0x1 /* wait on new inodes */ + int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, uint flags, uint lock_flags, xfs_inode_t **ipp); @@ -72,6 +77,9 @@ void xfs_eofblocks_worker(struct work_struct *); int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, int flags, void *args), int flags, void *args); +int xfs_inode_ag_iterator_flags(struct xfs_mount *mp, + int (*execute)(struct xfs_inode *ip, int flags, void *args), + int flags, void *args, int iter_flags); int xfs_inode_ag_iterator_tag(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, int flags, void *args), int flags, void *args, int tag); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index ca9e11989cbd..ae1a49845744 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -208,7 +208,8 @@ xfs_get_initial_prid(struct xfs_inode *dp) #define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */ #define XFS_ISTALE (1 << 1) /* inode has been staled */ #define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */ -#define XFS_INEW (1 << 3) /* inode has just been allocated */ +#define __XFS_INEW_BIT 3 /* inode has just been allocated */ +#define XFS_INEW (1 << __XFS_INEW_BIT) #define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */ #define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */ #define __XFS_IFLOCK_BIT 7 /* inode is being flushed right now */ @@ -453,6 +454,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip) xfs_iflags_clear(ip, XFS_INEW); barrier(); unlock_new_inode(VFS_I(ip)); + wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); } static inline void xfs_setup_existing_inode(struct xfs_inode *ip) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index d42738deec6d..e4a4f82ea13f 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -403,6 +403,7 @@ xfs_attrlist_by_handle( { int error = -ENOMEM; attrlist_cursor_kern_t *cursor; + struct xfs_fsop_attrlist_handlereq __user *p = arg; xfs_fsop_attrlist_handlereq_t al_hreq; struct dentry *dentry; char *kbuf; @@ -435,6 +436,11 @@ xfs_attrlist_by_handle( if (error) goto out_kfree; + if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) { + error = -EFAULT; + goto out_kfree; + } + if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen)) error = -EFAULT; @@ -1379,10 +1385,11 @@ xfs_ioc_getbmap( unsigned int cmd, void __user *arg) { - struct getbmapx bmx; + struct getbmapx bmx = { 0 }; int error; - if (copy_from_user(&bmx, arg, sizeof(struct getbmapx))) + /* struct getbmap is a strict subset of struct getbmapx. */ + if (copy_from_user(&bmx, arg, offsetof(struct getbmapx, bmv_iflags))) return -EFAULT; if (bmx.bmv_count < 2) diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 532ab79d38fe..572b64a135b3 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1355,12 +1355,7 @@ xfs_qm_quotacheck( mp->m_qflags |= flags; error_return: - while (!list_empty(&buffer_list)) { - struct xfs_buf *bp = - list_first_entry(&buffer_list, struct xfs_buf, b_list); - list_del_init(&bp->b_list); - xfs_buf_relse(bp); - } + xfs_buf_delwri_cancel(&buffer_list); if (error) { xfs_warn(mp, diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 3640c6e896af..4d334440bd94 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -764,5 +764,6 @@ xfs_qm_dqrele_all_inodes( uint flags) { ASSERT(mp->m_quotainfo); - xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, NULL); + xfs_inode_ag_iterator_flags(mp, xfs_dqrele_inode, flags, NULL, + XFS_AGITER_INEW_WAIT); } diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 839b35ca21c6..9beaf192b4bb 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -180,7 +180,8 @@ xfs_xattr_put_listent( arraytop = context->count + prefix_len + namelen + 1; if (arraytop > context->firstu) { context->count = -1; /* insufficient space */ - return 1; + context->seen_enough = 1; + return 0; } offset = (char *)context->alist + context->count; strncpy(offset, xfs_xattr_prefix(flags), prefix_len); @@ -222,12 +223,15 @@ list_one_attr(const char *name, const size_t len, void *data, } ssize_t -xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) +xfs_vn_listxattr( + struct dentry *dentry, + char *data, + size_t size) { struct xfs_attr_list_context context; struct attrlist_cursor_kern cursor = { 0 }; - struct inode *inode = d_inode(dentry); - int error; + struct inode *inode = d_inode(dentry); + int error; /* * First read the regular on-disk attributes. @@ -245,7 +249,9 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) else context.put_listent = xfs_xattr_put_listent_sizes; - xfs_attr_list_int(&context); + error = xfs_attr_list_int(&context); + if (error) + return error; if (context.count < 0) return -ERANGE; diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index c9fe145f7dd3..04661e1fb625 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -202,6 +202,9 @@ int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc, struct blkcipher_walk *walk, struct crypto_aead *tfm, unsigned int blocksize); +int blkcipher_ablkcipher_walk_virt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk, + struct crypto_ablkcipher *tfm); int ablkcipher_walk_done(struct ablkcipher_request *req, struct ablkcipher_walk *walk, int err); diff --git a/include/crypto/gf128mul.h b/include/crypto/gf128mul.h index da2530e34b26..230760aef93b 100644 --- a/include/crypto/gf128mul.h +++ b/include/crypto/gf128mul.h @@ -43,7 +43,7 @@ --------------------------------------------------------------------------- Issue Date: 31/01/2006 - An implementation of field multiplication in Galois Field GF(128) + An implementation of field multiplication in Galois Field GF(2^128) */ #ifndef _CRYPTO_GF128MUL_H @@ -65,7 +65,7 @@ * are left and the lsb's are right. char b[16] is an array and b[0] is * the first octet. * - * 80000000 00000000 00000000 00000000 .... 00000000 00000000 00000000 + * 10000000 00000000 00000000 00000000 .... 00000000 00000000 00000000 * b[0] b[1] b[2] b[3] b[13] b[14] b[15] * * Every bit is a coefficient of some power of X. We can store the bits @@ -99,21 +99,21 @@ * * bbe on a little endian machine u32 x[4]: * - * MS x[0] LS MS x[1] LS + * MS x[0] LS MS x[1] LS * ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls * 103..96 111.104 119.112 127.120 71...64 79...72 87...80 95...88 * - * MS x[2] LS MS x[3] LS + * MS x[2] LS MS x[3] LS * ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls * 39...32 47...40 55...48 63...56 07...00 15...08 23...16 31...24 * * ble on a little endian machine * - * MS x[0] LS MS x[1] LS + * MS x[0] LS MS x[1] LS * ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls * 31...24 23...16 15...08 07...00 63...56 55...48 47...40 39...32 * - * MS x[2] LS MS x[3] LS + * MS x[2] LS MS x[3] LS * ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls * 95...88 87...80 79...72 71...64 127.120 199.112 111.104 103..96 * @@ -127,7 +127,7 @@ * machines this will automatically aligned to wordsize and on a 64-bit * machine also. */ -/* Multiply a GF128 field element by x. Field elements are held in arrays +/* Multiply a GF128 field element by x. Field elements are held in arrays of bytes in which field bits 8n..8n + 7 are held in byte[n], with lower indexed bits placed in the more numerically significant bit positions within bytes. @@ -135,62 +135,65 @@ On little endian machines the bit indexes translate into the bit positions within four 32-bit words in the following way - MS x[0] LS MS x[1] LS + MS x[0] LS MS x[1] LS ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls 24...31 16...23 08...15 00...07 56...63 48...55 40...47 32...39 - MS x[2] LS MS x[3] LS + MS x[2] LS MS x[3] LS ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls 88...95 80...87 72...79 64...71 120.127 112.119 104.111 96..103 On big endian machines the bit indexes translate into the bit positions within four 32-bit words in the following way - MS x[0] LS MS x[1] LS + MS x[0] LS MS x[1] LS ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls 00...07 08...15 16...23 24...31 32...39 40...47 48...55 56...63 - MS x[2] LS MS x[3] LS + MS x[2] LS MS x[3] LS ms ls ms ls ms ls ms ls ms ls ms ls ms ls ms ls 64...71 72...79 80...87 88...95 96..103 104.111 112.119 120.127 */ -/* A slow generic version of gf_mul, implemented for lle and bbe - * It multiplies a and b and puts the result in a */ +/* A slow generic version of gf_mul, implemented for lle, bbe, and ble. + * It multiplies a and b and puts the result in a + */ void gf128mul_lle(be128 *a, const be128 *b); - void gf128mul_bbe(be128 *a, const be128 *b); +void gf128mul_ble(be128 *a, const be128 *b); -/* multiply by x in ble format, needed by XTS */ +/* multiply by x in ble format, needed by XTS and HEH */ void gf128mul_x_ble(be128 *a, const be128 *b); /* 4k table optimization */ - struct gf128mul_4k { be128 t[256]; }; struct gf128mul_4k *gf128mul_init_4k_lle(const be128 *g); struct gf128mul_4k *gf128mul_init_4k_bbe(const be128 *g); +struct gf128mul_4k *gf128mul_init_4k_ble(const be128 *g); void gf128mul_4k_lle(be128 *a, struct gf128mul_4k *t); void gf128mul_4k_bbe(be128 *a, struct gf128mul_4k *t); +void gf128mul_4k_ble(be128 *a, struct gf128mul_4k *t); static inline void gf128mul_free_4k(struct gf128mul_4k *t) { - kfree(t); + kzfree(t); } -/* 64k table optimization, implemented for lle and bbe */ +/* 64k table optimization, implemented for lle, ble, and bbe */ struct gf128mul_64k { struct gf128mul_4k *t[16]; }; -/* first initialize with the constant factor with which you - * want to multiply and then call gf128_64k_lle with the other - * factor in the first argument, the table in the second and a - * scratch register in the third. Afterwards *a = *r. */ +/* First initialize with the constant factor with which you + * want to multiply and then call gf128mul_64k_bbe with the other + * factor in the first argument, and the table in the second. + * Afterwards, the result is stored in *a. + */ struct gf128mul_64k *gf128mul_init_64k_lle(const be128 *g); struct gf128mul_64k *gf128mul_init_64k_bbe(const be128 *g); void gf128mul_free_64k(struct gf128mul_64k *t); diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 3b4af1d7c7e9..611b3d3bbab5 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -102,6 +102,8 @@ int shash_register_instance(struct crypto_template *tmpl, struct shash_instance *inst); void shash_free_instance(struct crypto_instance *inst); +int crypto_grab_shash(struct crypto_shash_spawn *spawn, + const char *name, u32 type, u32 mask); int crypto_init_shash_spawn(struct crypto_shash_spawn *spawn, struct shash_alg *alg, struct crypto_instance *inst); @@ -111,6 +113,12 @@ static inline void crypto_drop_shash(struct crypto_shash_spawn *spawn) crypto_drop_spawn(&spawn->base); } +static inline struct shash_alg *crypto_spawn_shash_alg( + struct crypto_shash_spawn *spawn) +{ + return container_of(spawn->base.alg, struct shash_alg, base); +} + struct shash_alg *shash_attr_alg(struct rtattr *rta, u32 type, u32 mask); int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc); @@ -173,6 +181,16 @@ static inline struct ahash_instance *ahash_alloc_instance( return crypto_alloc_instance2(name, alg, ahash_instance_headroom()); } +static inline void ahash_request_complete(struct ahash_request *req, int err) +{ + req->base.complete(&req->base, err); +} + +static inline u32 ahash_request_flags(struct ahash_request *req) +{ + return req->base.flags; +} + static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 2cae7511d11f..5da4e900eb0c 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -1522,6 +1522,12 @@ extern int drm_format_plane_cpp(uint32_t format, int plane); extern int drm_format_horz_chroma_subsampling(uint32_t format); extern int drm_format_vert_chroma_subsampling(uint32_t format); extern const char *drm_get_format_name(uint32_t format); + +static inline bool drm_rotation_90_or_270(unsigned int rotation) +{ + return rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270)); +} + extern struct drm_property *drm_mode_create_rotation_property(struct drm_device *dev, unsigned int supported_rotations); extern unsigned int drm_rotation_simplify(unsigned int rotation, diff --git a/include/drm/ttm/ttm_object.h b/include/drm/ttm/ttm_object.h index ed953f98f0e1..1487011fe057 100644 --- a/include/drm/ttm/ttm_object.h +++ b/include/drm/ttm/ttm_object.h @@ -229,6 +229,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base); * @ref_type: The type of reference. * @existed: Upon completion, indicates that an identical reference object * already existed, and the refcount was upped on that object instead. + * @require_existed: Fail with -EPERM if an identical ref object didn't + * already exist. * * Checks that the base object is shareable and adds a ref object to it. * @@ -243,7 +245,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base); */ extern int ttm_ref_object_add(struct ttm_object_file *tfile, struct ttm_base_object *base, - enum ttm_ref_type ref_type, bool *existed); + enum ttm_ref_type ref_type, bool *existed, + bool require_existed); extern bool ttm_ref_object_exists(struct ttm_object_file *tfile, struct ttm_base_object *base); diff --git a/include/linux/can/core.h b/include/linux/can/core.h index a0875001b13c..df08a41d5be5 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -45,10 +45,9 @@ struct can_proto { extern int can_proto_register(const struct can_proto *cp); extern void can_proto_unregister(const struct can_proto *cp); -extern int can_rx_register(struct net_device *dev, canid_t can_id, - canid_t mask, - void (*func)(struct sk_buff *, void *), - void *data, char *ident); +int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, + void (*func)(struct sk_buff *, void *), + void *data, char *ident, struct sock *sk); extern void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index e55c08bc3a96..0abc56140c83 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -49,7 +49,7 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool) case CEPH_POOL_TYPE_EC: return false; default: - BUG_ON(1); + BUG(); } } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cb91b44f5f78..210ccc4ea44b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -340,6 +340,26 @@ static inline bool css_tryget_online(struct cgroup_subsys_state *css) } /** + * css_is_dying - test whether the specified css is dying + * @css: target css + * + * Test whether @css is in the process of offlining or already offline. In + * most cases, ->css_online() and ->css_offline() callbacks should be + * enough; however, the actual offline operations are RCU delayed and this + * test returns %true also when @css is scheduled to be offlined. + * + * This is useful, for example, when the use case requires synchronous + * behavior with respect to cgroup removal. cgroup removal schedules css + * offlining but the css can seem alive while the operation is being + * delayed. If the delay affects user visible semantics, this test can be + * used to resolve the situation. + */ +static inline bool css_is_dying(struct cgroup_subsys_state *css) +{ + return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); +} + +/** * css_put - put a css reference * @css: target css * @@ -528,6 +548,25 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline void cgroup_init_kthreadd(void) +{ + /* + * kthreadd is inherited by all kthreads, keep it in the root so + * that the new kthreads are guaranteed to stay in the root until + * initialization is finished. + */ + current->no_cgroup_migration = 1; +} + +static inline void cgroup_kthread_ready(void) +{ + /* + * This kthread finished initialization. The creator should have + * set PF_NO_SETAFFINITY if this kthread should stay in the root. + */ + current->no_cgroup_migration = 0; +} + #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -551,6 +590,8 @@ static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } +static inline void cgroup_init_kthreadd(void) {} +static inline void cgroup_kthread_ready(void) {} #endif /* !CONFIG_CGROUPS */ diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d016a121a8c4..28ffa94aed6b 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -14,6 +14,7 @@ struct coredump_params; extern int dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); +extern void dump_truncate(struct coredump_params *cprm); #ifdef CONFIG_COREDUMP extern void do_coredump(const siginfo_t *siginfo); #else diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 59915ea5373c..a91b3b75da0f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -556,7 +556,7 @@ static inline void cpumask_copy(struct cpumask *dstp, static inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { - return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids); + return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** @@ -571,7 +571,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), - nr_cpu_ids); + nr_cpumask_bits); } /** @@ -586,7 +586,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) char *nl = strchr(buf, '\n'); unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf); - return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids); + return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** @@ -598,7 +598,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) */ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) { - return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids); + return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 85a868ccb493..8397dc235e84 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -16,6 +16,7 @@ #ifdef CONFIG_CPUSETS +extern struct static_key cpusets_pre_enable_key; extern struct static_key cpusets_enabled_key; static inline bool cpusets_enabled(void) { @@ -30,12 +31,14 @@ static inline int nr_cpusets(void) static inline void cpuset_inc(void) { + static_key_slow_inc(&cpusets_pre_enable_key); static_key_slow_inc(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_key_slow_dec(&cpusets_enabled_key); + static_key_slow_dec(&cpusets_pre_enable_key); } extern int cpuset_init(void); @@ -104,7 +107,7 @@ extern void cpuset_print_current_mems_allowed(void); */ static inline unsigned int read_mems_allowed_begin(void) { - if (!cpusets_enabled()) + if (!static_key_false(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); @@ -118,7 +121,7 @@ static inline unsigned int read_mems_allowed_begin(void) */ static inline bool read_mems_allowed_retry(unsigned int seq) { - if (!cpusets_enabled()) + if (!static_key_false(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 702b6c53c12f..0acbb85ff9ff 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -616,5 +616,11 @@ static inline struct inode *d_real_inode(struct dentry *dentry) return d_backing_inode(d_real(dentry)); } +struct name_snapshot { + const char *name; + char inline_name[DNAME_INLINE_LEN]; +}; +void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); +void release_dentry_name_snapshot(struct name_snapshot *); #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 61d042bbbf60..68449293c4b6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -163,6 +163,7 @@ struct dccp_request_sock { __u64 dreq_isr; __u64 dreq_gsr; __be32 dreq_service; + spinlock_t dreq_lock; struct list_head dreq_featneg; __u32 dreq_timestamp_echo; __u32 dreq_timestamp_time; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index b874d5b61ffc..f3f87db34429 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -415,6 +415,13 @@ union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); +void dm_lock_md_type(struct mapped_device *md); +void dm_unlock_md_type(struct mapped_device *md); +void dm_set_md_type(struct mapped_device *md, unsigned type); +unsigned dm_get_md_type(struct mapped_device *md); +int dm_setup_md_queue(struct mapped_device *md); +unsigned dm_table_get_type(struct dm_table *t); + /* * Geometry functions. */ diff --git a/include/linux/device.h b/include/linux/device.h index b8f411b57dcb..7075a2485ed3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -368,6 +368,7 @@ int subsys_virtual_register(struct bus_type *subsys, * @suspend: Used to put the device to sleep mode, usually to a low power * state. * @resume: Used to bring the device from the sleep mode. + * @shutdown: Called at shut-down time to quiesce the device. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. * @pm: The default device power management operations of this class. @@ -396,6 +397,7 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + int (*shutdown)(struct device *dev); const struct kobj_ns_type_operations *ns_type; const void *(*namespace)(struct device *dev); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 25c6324a0dd0..3d6e6ce44c5c 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -284,6 +284,12 @@ struct f2fs_nat_block { #define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry)) /* + * F2FS uses 4 bytes to represent block address. As a result, supported size of + * disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments. + */ +#define F2FS_MAX_SEGMENT ((16 * 1024 * 1024) / 2) + +/* * Note that f2fs_sit_entry->vblocks has the following bit-field information. * [15:10] : allocation type such as CURSEG_XXXX_TYPE * [9:0] : valid block count diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 76ce329e656d..1b48d9c9a561 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -3,6 +3,12 @@ #include <uapi/linux/fcntl.h> +/* list of all valid flags for the open/openat flags argument: */ +#define VALID_OPEN_FLAGS \ + (O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \ + O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \ + FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \ + O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE) #ifndef force_o_largefile #define force_o_largefile() (BITS_PER_LONG != 32) diff --git a/include/linux/fs.h b/include/linux/fs.h index e1a123760dbf..bff4ce57b77e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -680,6 +680,11 @@ struct inode { void *i_private; /* fs or device private pointer */ }; +static inline unsigned int i_blocksize(const struct inode *node) +{ + return (1 << node->i_blkbits); +} + static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); @@ -1539,13 +1544,21 @@ extern bool inode_owner_or_capable(const struct inode *inode); * VFS helper functions.. */ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); +extern int vfs_create2(struct vfsmount *, struct inode *, struct dentry *, umode_t, bool); extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); +extern int vfs_mkdir2(struct vfsmount *, struct inode *, struct dentry *, umode_t); extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); +extern int vfs_mknod2(struct vfsmount *, struct inode *, struct dentry *, umode_t, dev_t); extern int vfs_symlink(struct inode *, struct dentry *, const char *); +extern int vfs_symlink2(struct vfsmount *, struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); +extern int vfs_link2(struct vfsmount *, struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); +extern int vfs_rmdir2(struct vfsmount *, struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); +extern int vfs_unlink2(struct vfsmount *, struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); +extern int vfs_rename2(struct vfsmount *, struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); extern int vfs_whiteout(struct inode *, struct dentry *); /* @@ -1671,6 +1684,7 @@ struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*follow_link) (struct dentry *, void **); int (*permission) (struct inode *, int); + int (*permission2) (struct vfsmount *, struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); @@ -1688,6 +1702,7 @@ struct inode_operations { int (*rename2) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); + int (*setattr2) (struct vfsmount *, struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); @@ -1733,9 +1748,13 @@ struct super_operations { int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); + int (*remount_fs2) (struct vfsmount *, struct super_block *, int *, char *); + void *(*clone_mnt_data) (void *); + void (*copy_mnt_data) (void *, void *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); + int (*show_options2)(struct vfsmount *,struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); @@ -1967,6 +1986,9 @@ struct file_system_type { #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); + struct dentry *(*mount2) (struct vfsmount *, struct file_system_type *, int, + const char *, void *); + void *(*alloc_mnt_data) (void); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; @@ -2246,6 +2268,8 @@ struct filename { extern long vfs_truncate(struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); +extern int do_truncate2(struct vfsmount *, struct dentry *, loff_t start, + unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, @@ -2470,8 +2494,11 @@ extern void emergency_remount(void); extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); +extern int notify_change2(struct vfsmount *, struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); +extern int inode_permission2(struct vfsmount *, struct inode *, int); extern int __inode_permission(struct inode *, int); +extern int __inode_permission2(struct vfsmount *, struct inode *, int); extern int generic_permission(struct inode *, int); extern int __check_sticky(struct inode *dir, struct inode *inode); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 604e1526cd00..eb19bf2b2a81 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -360,6 +360,7 @@ struct fscache_object { #define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */ #define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */ #define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */ +#define FSCACHE_OBJECT_RUN_AFTER_DEAD 8 /* T if object has been dispatched after death */ struct list_head cache_link; /* link in cache->object_list */ struct hlist_node cookie_link; /* link in cookie->backing_objects */ diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 7ee1774edee5..a7789559078b 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -310,35 +310,4 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) } } -#if defined(CONFIG_FSNOTIFY) /* notify helpers */ - -/* - * fsnotify_oldname_init - save off the old filename before we change it - */ -static inline const unsigned char *fsnotify_oldname_init(const unsigned char *name) -{ - return kstrdup(name, GFP_KERNEL); -} - -/* - * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init - */ -static inline void fsnotify_oldname_free(const unsigned char *old_name) -{ - kfree(old_name); -} - -#else /* CONFIG_FSNOTIFY */ - -static inline const char *fsnotify_oldname_init(const unsigned char *name) -{ - return NULL; -} - -static inline void fsnotify_oldname_free(const unsigned char *old_name) -{ -} - -#endif /* CONFIG_FSNOTIFY */ - #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 847cc1d91634..5012fcdb4c9e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -742,11 +742,9 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) #if defined(CONFIG_BLK_DEV_INTEGRITY) extern void blk_integrity_add(struct gendisk *); extern void blk_integrity_del(struct gendisk *); -extern void blk_integrity_revalidate(struct gendisk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void blk_integrity_add(struct gendisk *disk) { } static inline void blk_integrity_del(struct gendisk *disk) { } -static inline void blk_integrity_revalidate(struct gendisk *disk) { } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #else /* CONFIG_BLOCK */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 67ce5bd3b56a..19db03dbbd00 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -616,15 +616,16 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, netdev_features_t features) { - if (skb_vlan_tagged_multi(skb)) - features = netdev_intersect_features(features, - NETIF_F_SG | - NETIF_F_HIGHDMA | - NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX); - + if (skb_vlan_tagged_multi(skb)) { + /* In the case of multi-tagged packets, use a direct mask + * instead of using netdev_interesect_features(), to make + * sure that only devices supporting NETIF_F_HW_CSUM will + * have checksum offloading support. + */ + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | + NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + } return features; } diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d49e26c6cdc7..23e129ef6726 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -153,8 +153,8 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60) #define DMA_TLB_DSI_FLUSH (((u64)2) << 60) #define DMA_TLB_PSI_FLUSH (((u64)3) << 60) -#define DMA_TLB_IIRG(type) ((type >> 60) & 7) -#define DMA_TLB_IAIG(val) (((val) >> 57) & 7) +#define DMA_TLB_IIRG(type) ((type >> 60) & 3) +#define DMA_TLB_IAIG(val) (((val) >> 57) & 3) #define DMA_TLB_READ_DRAIN (((u64)1) << 49) #define DMA_TLB_WRITE_DRAIN (((u64)1) << 48) #define DMA_TLB_DID(id) (((u64)((id) & 0xffff)) << 32) @@ -164,9 +164,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* INVALID_DESC */ #define DMA_CCMD_INVL_GRANU_OFFSET 61 -#define DMA_ID_TLB_GLOBAL_FLUSH (((u64)1) << 3) -#define DMA_ID_TLB_DSI_FLUSH (((u64)2) << 3) -#define DMA_ID_TLB_PSI_FLUSH (((u64)3) << 3) +#define DMA_ID_TLB_GLOBAL_FLUSH (((u64)1) << 4) +#define DMA_ID_TLB_DSI_FLUSH (((u64)2) << 4) +#define DMA_ID_TLB_PSI_FLUSH (((u64)3) << 4) #define DMA_ID_TLB_READ_DRAIN (((u64)1) << 7) #define DMA_ID_TLB_WRITE_DRAIN (((u64)1) << 6) #define DMA_ID_TLB_DID(id) (((u64)((id & 0xffff) << 16))) @@ -316,8 +316,8 @@ enum { #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) #define QI_DEV_EIOTLB_GLOB(g) ((u64)g) #define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) -#define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) -#define QI_DEV_EIOTLB_QDEP(qd) (((qd) & 0x1f) << 16) +#define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) +#define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) #define QI_DEV_EIOTLB_MAX_INVS 32 #define QI_PGRP_IDX(idx) (((u64)(idx)) << 55) diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ce777260e9ea..a0fc3cf932af 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -18,6 +18,7 @@ struct ipv6_devconf { __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; + __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; @@ -36,6 +37,7 @@ struct ipv6_devconf { __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; #ifdef CONFIG_IPV6_ROUTE_INFO + __s32 accept_ra_rt_info_min_plen; __s32 accept_ra_rt_info_max_plen; #endif #endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 50220cab738c..05b63a1e9f84 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -53,6 +53,13 @@ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) +#define u64_to_user_ptr(x) ( \ +{ \ + typecheck(u64, x); \ + (void __user *)(uintptr_t)x; \ +} \ +) + /* * This looks more complex than it should be. But we need to * get the type for the ~ right in round_down (it needs to be diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8f6849084248..e23392517db9 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -330,7 +330,9 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif - +extern void wait_for_kprobe_optimizer(void); +#else +static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c923350ca20a..d7ce4e3280db 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -182,8 +182,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); -int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev); +void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev); #ifdef CONFIG_KVM_ASYNC_PF struct kvm_async_pf { diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 3f021dc5da8c..30201b9be7bc 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -83,6 +83,8 @@ struct nd_cmd_desc { struct nd_interleave_set { u64 cookie; + /* compatibility with initial buggy Linux implementation */ + u64 altcookie; }; struct nd_region_desc { diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 2a6b9947aaa3..743b34f56f2b 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -44,6 +44,7 @@ struct list_lru_node { /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg *memcg_lrus; #endif + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c15373894a42..b37dee3acaba 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -355,7 +355,8 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp) static inline int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { - return fl1->fl_pid == fl2->fl_pid + return file_inode(fl1->fl_file) == file_inode(fl2->fl_file) + && fl1->fl_pid == fl2->fl_pid && fl1->fl_owner == fl2->fl_owner && fl1->fl_start == fl2->fl_start && fl1->fl_end == fl2->fl_end diff --git a/include/linux/log2.h b/include/linux/log2.h index fd7ff3d91e6a..c373295f359f 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -16,12 +16,6 @@ #include <linux/bitops.h> /* - * deal with unrepresentable constant logarithms - */ -extern __attribute__((const, noreturn)) -int ____ilog2_NaN(void); - -/* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() @@ -85,7 +79,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n) < 1 ? ____ilog2_NaN() : \ + (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ @@ -148,10 +142,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - (n) & (1ULL << 1) ? 1 : \ - (n) & (1ULL << 0) ? 0 : \ - ____ilog2_NaN() \ - ) : \ + 1 ) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ @@ -203,6 +194,17 @@ unsigned long __rounddown_pow_of_two(unsigned long n) * ... and so on. */ -#define order_base_2(n) ilog2(roundup_pow_of_two(n)) +static inline __attribute_const__ +int __order_base_2(unsigned long n) +{ + return n > 1 ? ilog2(n - 1) + 1 : 0; +} +#define order_base_2(n) \ +( \ + __builtin_constant_p(n) ? ( \ + ((n) == 0 || (n) == 1) ? 0 : \ + ilog2((n) - 1) + 1) : \ + __order_base_2(n) \ +) #endif /* _LINUX_LOG2_H */ diff --git a/include/linux/mbcache2.h b/include/linux/mbcache2.h new file mode 100644 index 000000000000..b6f160ff2533 --- /dev/null +++ b/include/linux/mbcache2.h @@ -0,0 +1,50 @@ +#ifndef _LINUX_MB2CACHE_H +#define _LINUX_MB2CACHE_H + +#include <linux/hash.h> +#include <linux/list_bl.h> +#include <linux/list.h> +#include <linux/atomic.h> +#include <linux/fs.h> + +struct mb2_cache; + +struct mb2_cache_entry { + /* LRU list - protected by cache->c_lru_list_lock */ + struct list_head e_lru_list; + /* Hash table list - protected by bitlock in e_hash_list_head */ + struct hlist_bl_node e_hash_list; + atomic_t e_refcnt; + /* Key in hash - stable during lifetime of the entry */ + u32 e_key; + /* Block number of hashed block - stable during lifetime of the entry */ + sector_t e_block; + /* Head of hash list (for list bit lock) - stable */ + struct hlist_bl_head *e_hash_list_head; +}; + +struct mb2_cache *mb2_cache_create(int bucket_bits); +void mb2_cache_destroy(struct mb2_cache *cache); + +int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key, + sector_t block); +void __mb2_cache_entry_free(struct mb2_cache_entry *entry); +static inline int mb2_cache_entry_put(struct mb2_cache *cache, + struct mb2_cache_entry *entry) +{ + if (!atomic_dec_and_test(&entry->e_refcnt)) + return 0; + __mb2_cache_entry_free(entry); + return 1; +} + +void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key, + sector_t block); +struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache, + u32 key); +struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache, + struct mb2_cache_entry *entry); +void mb2_cache_entry_touch(struct mb2_cache *cache, + struct mb2_cache_entry *entry); + +#endif /* _LINUX_MB2CACHE_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fec66f86eeff..e3d461f19cbc 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -84,6 +84,7 @@ int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); +int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); ulong choose_memblock_flags(void); /* Low level functions */ @@ -325,10 +326,12 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); -int memblock_is_memory(phys_addr_t addr); +void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size); +void memblock_mem_limit_remove_map(phys_addr_t limit); +bool memblock_is_memory(phys_addr_t addr); int memblock_is_map_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); -int memblock_is_reserved(phys_addr_t addr); +bool memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); extern void __memblock_dump_all(void); @@ -416,12 +419,20 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) } #endif +extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr); #else static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) { return 0; } +static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr) +{ + return 0; +} + #endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2ea574ff9714..538488bd1d3d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -85,7 +85,8 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* VM interface that may be used by firmware interface */ extern int online_pages(unsigned long, unsigned long, int); -extern int test_pages_in_a_zone(unsigned long, unsigned long); +extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, + unsigned long *valid_start, unsigned long *valid_end); extern void __offline_isolated_pages(unsigned long, unsigned long); typedef void (*online_page_callback_t)(struct page *page); diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h new file mode 100644 index 000000000000..d0c91ba65525 --- /dev/null +++ b/include/linux/mfd/lp87565.h @@ -0,0 +1,270 @@ +/* + * Functions to access LP87565 power management chip. + * + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + */ + +#ifndef __LINUX_MFD_LP87565_H +#define __LINUX_MFD_LP87565_H + +#include <linux/i2c.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> + +enum lp87565_device_type { + LP87565_DEVICE_TYPE_UNKNOWN = 0, + LP87565_DEVICE_TYPE_LP87565_Q1, +}; + +/* All register addresses */ +#define LP87565_REG_DEV_REV 0X00 +#define LP87565_REG_OTP_REV 0X01 +#define LP87565_REG_BUCK0_CTRL_1 0X02 +#define LP87565_REG_BUCK0_CTRL_2 0X03 + +#define LP87565_REG_BUCK1_CTRL_1 0X04 +#define LP87565_REG_BUCK1_CTRL_2 0X05 + +#define LP87565_REG_BUCK2_CTRL_1 0X06 +#define LP87565_REG_BUCK2_CTRL_2 0X07 + +#define LP87565_REG_BUCK3_CTRL_1 0X08 +#define LP87565_REG_BUCK3_CTRL_2 0X09 + +#define LP87565_REG_BUCK0_VOUT 0X0A +#define LP87565_REG_BUCK0_FLOOR_VOUT 0X0B + +#define LP87565_REG_BUCK1_VOUT 0X0C +#define LP87565_REG_BUCK1_FLOOR_VOUT 0X0D + +#define LP87565_REG_BUCK2_VOUT 0X0E +#define LP87565_REG_BUCK2_FLOOR_VOUT 0X0F + +#define LP87565_REG_BUCK3_VOUT 0X10 +#define LP87565_REG_BUCK3_FLOOR_VOUT 0X11 + +#define LP87565_REG_BUCK0_DELAY 0X12 +#define LP87565_REG_BUCK1_DELAY 0X13 + +#define LP87565_REG_BUCK2_DELAY 0X14 +#define LP87565_REG_BUCK3_DELAY 0X15 + +#define LP87565_REG_GPO2_DELAY 0X16 +#define LP87565_REG_GPO3_DELAY 0X17 +#define LP87565_REG_RESET 0X18 +#define LP87565_REG_CONFIG 0X19 + +#define LP87565_REG_INT_TOP_1 0X1A +#define LP87565_REG_INT_TOP_2 0X1B + +#define LP87565_REG_INT_BUCK_0_1 0X1C +#define LP87565_REG_INT_BUCK_2_3 0X1D +#define LP87565_REG_TOP_STAT 0X1E +#define LP87565_REG_BUCK_0_1_STAT 0X1F +#define LP87565_REG_BUCK_2_3_STAT 0x20 + +#define LP87565_REG_TOP_MASK_1 0x21 +#define LP87565_REG_TOP_MASK_2 0x22 + +#define LP87565_REG_BUCK_0_1_MASK 0x23 +#define LP87565_REG_BUCK_2_3_MASK 0x24 +#define LP87565_REG_SEL_I_LOAD 0x25 + +#define LP87565_REG_I_LOAD_2 0x26 +#define LP87565_REG_I_LOAD_1 0x27 + +#define LP87565_REG_PGOOD_CTRL1 0x28 +#define LP87565_REG_PGOOD_CTRL2 0x29 +#define LP87565_REG_PGOOD_FLT 0x2A +#define LP87565_REG_PLL_CTRL 0x2B +#define LP87565_REG_PIN_FUNCTION 0x2C +#define LP87565_REG_GPIO_CONFIG 0x2D +#define LP87565_REG_GPIO_IN 0x2E +#define LP87565_REG_GPIO_OUT 0x2F + +#define LP87565_REG_MAX LP87565_REG_GPIO_OUT + +/* Register field definitions */ +#define LP87565_DEV_REV_DEV_ID 0xC0 +#define LP87565_DEV_REV_ALL_LAYER 0x30 +#define LP87565_DEV_REV_METAL_LAYER 0x0F + +#define LP87565_OTP_REV_OTP_ID 0xFF + +#define LP87565_BUCK_CTRL_1_EN BIT(7) +#define LP87565_BUCK_CTRL_1_EN_PIN_CTRL BIT(6) +#define LP87565_BUCK_CTRL_1_PIN_SELECT_EN 0x30 + +#define LP87565_BUCK_CTRL_1_ROOF_FLOOR_EN BIT(3) +#define LP87565_BUCK_CTRL_1_RDIS_EN BIT(2) +#define LP87565_BUCK_CTRL_1_FPWM BIT(1) +/* Bit0 is reserved for BUCK1 and BUCK3 and valid only for BUCK0 and BUCK2 */ +#define LP87565_BUCK_CTRL_1_FPWM_MP_0_2 BIT(0) + +#define LP87565_BUCK_CTRL_2_ILIM 0x38 +#define LP87565_BUCK_CTRL_2_SLEW_RATE 0x07 + +#define LP87565_BUCK_VSET 0xFF +#define LP87565_BUCK_FLOOR_VSET 0xFF + +#define LP87565_BUCK_SHUTDOWN_DELAY 0xF0 +#define LP87565_BUCK_STARTUP_DELAY 0x0F + +#define LP87565_GPIO_SHUTDOWN_DELAY 0xF0 +#define LP87565_GPIO_STARTUP_DELAY 0x0F + +#define LP87565_RESET_SW_RESET BIT(0) + +#define LP87565_CONFIG_DOUBLE_DELAY BIT(7) +#define LP87565_CONFIG_CLKIN_PD BIT(6) +#define LP87565_CONFIG_EN4_PD BIT(5) +#define LP87565_CONFIG_EN3_PD BIT(4) +#define LP87565_CONFIG_TDIE_WARN_LEVEL BIT(3) +#define LP87565_CONFIG_EN2_PD BIT(2) +#define LP87565_CONFIG_EN1_PD BIT(1) + +#define LP87565_INT_GPIO BIT(7) +#define LP87565_INT_BUCK23 BIT(6) +#define LP87565_INT_BUCK01 BIT(5) +#define LP87565_NO_SYNC_CLK BIT(4) +#define LP87565_TDIE_SD BIT(3) +#define LP87565_TDIE_WARN BIT(2) +#define LP87565_INT_OVP BIT(1) +#define LP87565_I_LOAD_READY BIT(0) + +#define LP87565_INT_TOP2_RESET_REG BIT(0) + +#define LP87565_BUCK1_PG_INT BIT(6) +#define LP87565_BUCK1_SC_INT BIT(5) +#define LP87565_BUCK1_ILIM_INT BIT(4) +#define LP87565_BUCK0_PG_INT BIT(2) +#define LP87565_BUCK0_SC_INT BIT(1) +#define LP87565_BUCK0_ILIM_INT BIT(0) + +#define LP87565_BUCK3_PG_INT BIT(6) +#define LP87565_BUCK3_SC_INT BIT(5) +#define LP87565_BUCK3_ILIM_INT BIT(4) +#define LP87565_BUCK2_PG_INT BIT(2) +#define LP87565_BUCK2_SC_INT BIT(1) +#define LP87565_BUCK2_ILIM_INT BIT(0) + +#define LP87565_SYNC_CLK_STAT BIT(4) +#define LP87565_TDIE_SD_STAT BIT(3) +#define LP87565_TDIE_WARN_STAT BIT(2) +#define LP87565_OVP_STAT BIT(1) + +#define LP87565_BUCK1_STAT BIT(7) +#define LP87565_BUCK1_PG_STAT BIT(6) +#define LP87565_BUCK1_ILIM_STAT BIT(4) +#define LP87565_BUCK0_STAT BIT(3) +#define LP87565_BUCK0_PG_STAT BIT(2) +#define LP87565_BUCK0_ILIM_STAT BIT(0) + +#define LP87565_BUCK3_STAT BIT(7) +#define LP87565_BUCK3_PG_STAT BIT(6) +#define LP87565_BUCK3_ILIM_STAT BIT(4) +#define LP87565_BUCK2_STAT BIT(3) +#define LP87565_BUCK2_PG_STAT BIT(2) +#define LP87565_BUCK2_ILIM_STAT BIT(0) + +#define LPL87565_GPIO_MASK BIT(7) +#define LPL87565_SYNC_CLK_MASK BIT(4) +#define LPL87565_TDIE_WARN_MASK BIT(2) +#define LPL87565_I_LOAD_READY_MASK BIT(0) + +#define LPL87565_RESET_REG_MASK BIT(0) + +#define LPL87565_BUCK1_PG_MASK BIT(6) +#define LPL87565_BUCK1_ILIM_MASK BIT(4) +#define LPL87565_BUCK0_PG_MASK BIT(2) +#define LPL87565_BUCK0_ILIM_MASK BIT(0) + +#define LPL87565_BUCK3_PG_MASK BIT(6) +#define LPL87565_BUCK3_ILIM_MASK BIT(4) +#define LPL87565_BUCK2_PG_MASK BIT(2) +#define LPL87565_BUCK2_ILIM_MASK BIT(0) + +#define LP87565_LOAD_CURRENT_BUCK_SELECT 0x3 + +#define LP87565_I_LOAD2_BUCK_LOAD_CURRENT 0x3 +#define LP87565_I_LOAD1_BUCK_LOAD_CURRENT 0xFF + +#define LP87565_PG3_SEL 0xC0 +#define LP87565_PG2_SEL 0x30 +#define LP87565_PG1_SEL 0x0C +#define LP87565_PG0_SEL 0x03 + +#define LP87565_HALF_DAY BIT(7) +#define LP87565_EN_PG0_NINT BIT(6) +#define LP87565_PGOOD_SET_DELAY BIT(5) +#define LP87565_EN_PGFLT_STAT BIT(4) +#define LP87565_PGOOD_WINDOW BIT(2) +#define LP87565_PGOOD_OD BIT(1) +#define LP87565_PGOOD_POL BIT(0) + +#define LP87565_PG3_FLT BIT(3) +#define LP87565_PG2_FLT BIT(2) +#define LP87565_PG1_FLT BIT(1) +#define LP87565_PG0_FLT BIT(0) + +#define LP87565_PLL_MODE 0xC0 +#define LP87565_EXT_CLK_FREQ 0x1F + +#define LP87565_EN_SPREAD_SPEC BIT(7) +#define LP87565_EN_PIN_CTRL_GPIO3 BIT(6) +#define LP87565_EN_PIN_SELECT_GPIO3 BIT(5) +#define LP87565_EN_PIN_CTRL_GPIO2 BIT(4) +#define LP87565_EN_PIN_SELECT_GPIO2 BIT(3) +#define LP87565_GPIO3_SEL BIT(2) +#define LP87565_GPIO2_SEL BIT(1) +#define LP87565_GPIO1_SEL BIT(0) + +#define LP87565_GOIO3_OD BIT(6) +#define LP87565_GOIO2_OD BIT(5) +#define LP87565_GOIO1_OD BIT(4) +#define LP87565_GOIO3_DIR BIT(2) +#define LP87565_GOIO2_DIR BIT(1) +#define LP87565_GOIO1_DIR BIT(0) + +#define LP87565_GOIO3_IN BIT(2) +#define LP87565_GOIO2_IN BIT(1) +#define LP87565_GOIO1_IN BIT(0) + +#define LP87565_GOIO3_OUT BIT(2) +#define LP87565_GOIO2_OUT BIT(1) +#define LP87565_GOIO1_OUT BIT(0) + +/* Number of step-down converters available */ +#define LP87565_NUM_BUCK 6 + +enum LP87565_regulator_id { + /* BUCK's */ + LP87565_BUCK_0, + LP87565_BUCK_1, + LP87565_BUCK_2, + LP87565_BUCK_3, + LP87565_BUCK_10, + LP87565_BUCK_23, +}; + +/** + * struct LP87565 - state holder for the LP87565 driver + * @dev: struct device pointer for MFD device + * @rev: revision of the LP87565 + * @dev_type: The device type for example lp87565-q1 + * @lock: lock guarding the data structure + * @regmap: register map of the LP87565 PMIC + * + * Device data may be used to access the LP87565 chip + */ +struct lp87565 { + struct device *dev; + u8 rev; + u8 dev_type; + struct regmap *regmap; +}; +#endif /* __LINUX_MFD_LP87565_H */ diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 7b2526f7bc9b..637522da6082 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -239,6 +239,7 @@ enum tps65917_regulators { TPS65917_REG_SMPS3, TPS65917_REG_SMPS4, TPS65917_REG_SMPS5, + TPS65917_REG_SMPS12, /* LDO regulators */ TPS65917_REG_LDO1, TPS65917_REG_LDO2, @@ -306,6 +307,7 @@ enum tps65917_external_requestor_id { TPS65917_EXTERNAL_REQSTR_ID_SMPS3, TPS65917_EXTERNAL_REQSTR_ID_SMPS4, TPS65917_EXTERNAL_REQSTR_ID_SMPS5, + TPS65917_EXTERNAL_REQSTR_ID_SMPS12, TPS65917_EXTERNAL_REQSTR_ID_LDO1, TPS65917_EXTERNAL_REQSTR_ID_LDO2, TPS65917_EXTERNAL_REQSTR_ID_LDO3, diff --git a/include/linux/mm.h b/include/linux/mm.h index f8a729751faa..f29e8aa76e39 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1290,39 +1290,11 @@ int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); -/* Is the vma a continuation of the stack vma above it? */ -static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); -} - static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } -static inline int stack_guard_page_start(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_growsdown(vma->vm_prev, addr); -} - -/* Is the vma a continuation of the stack vma below it? */ -static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP); -} - -static inline int stack_guard_page_end(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSUP) && - (vma->vm_end == addr) && - !vma_growsup(vma->vm_next, addr); -} - int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t); extern unsigned long move_page_tables(struct vm_area_struct *vma, @@ -2024,6 +1996,7 @@ void page_cache_async_readahead(struct address_space *mapping, pgoff_t offset, unsigned long size); +extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -2052,6 +2025,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m return vma; } +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long vm_start = vma->vm_start; + + if (vma->vm_flags & VM_GROWSDOWN) { + vm_start -= stack_guard_gap; + if (vm_start > vma->vm_start) + vm_start = 0; + } + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; @@ -2160,14 +2157,18 @@ kernel_map_pages(struct page *page, int numpages, int enable) } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); -#endif /* CONFIG_HIBERNATION */ -#else +#endif /* CONFIG_HIBERNATION */ +#else /* CONFIG_DEBUG_PAGEALLOC */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } -#endif /* CONFIG_HIBERNATION */ -#endif +#endif /* CONFIG_HIBERNATION */ +static inline bool debug_pagealloc_enabled(void) +{ + return false; +} +#endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index af25bc12472b..b32cb7add09c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -511,6 +511,10 @@ struct mm_struct { */ bool tlb_flush_pending; #endif +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH + /* See flush_tlb_batched_pending() */ + bool tlb_flush_batched; +#endif struct uprobes_state uprobes_state; #ifdef CONFIG_X86_INTEL_MPX /* address of the bounds directory */ diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index eb0151bac50c..8f23fb2c5ed2 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -118,6 +118,9 @@ struct mmc_ext_csd { u8 raw_pwr_cl_ddr_200_360; /* 253 */ u8 raw_bkops_status; /* 246 */ u8 raw_sectors[4]; /* 212 - 4 bytes */ + u8 pre_eol_info; /* 267 */ + u8 device_life_time_est_typ_a; /* 268 */ + u8 device_life_time_est_typ_b; /* 269 */ unsigned int feature_support; #define MMC_DISCARD_FEATURE BIT(0) /* CMD38 feature */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 15f2c4a0a62c..2c6b1d45626e 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -330,6 +330,9 @@ struct _mmc_csd { #define EXT_CSD_CACHE_SIZE 249 /* RO, 4 bytes */ #define EXT_CSD_PWR_CL_DDR_200_360 253 /* RO */ #define EXT_CSD_FIRMWARE_VERSION 254 /* RO, 8 bytes */ +#define EXT_CSD_PRE_EOL_INFO 267 /* RO */ +#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A 268 /* RO */ +#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B 269 /* RO */ #define EXT_CSD_SUPPORTED_MODE 493 /* RO */ #define EXT_CSD_TAG_UNIT_SIZE 498 /* RO */ #define EXT_CSD_DATA_TAG_SUPPORT 499 /* RO */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 71b61b0b9b45..ab993c8caec0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -690,6 +690,7 @@ typedef struct pglist_data { * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; + unsigned long static_init_size; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ } pg_data_t; diff --git a/include/linux/mount.h b/include/linux/mount.h index f822c3c11377..b606d8f57adf 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,6 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; + void *data; }; struct file; /* forward dec */ @@ -95,4 +96,6 @@ extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); +extern unsigned int sysctl_mount_max; + #endif /* _LINUX_MOUNT_H */ diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 366cf77953b5..806d0ab845e0 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -122,18 +122,13 @@ #endif #ifdef CONFIG_MTD_MAP_BANK_WIDTH_32 -# ifdef map_bankwidth -# undef map_bankwidth -# define map_bankwidth(map) ((map)->bankwidth) -# undef map_bankwidth_is_large -# define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8) -# undef map_words -# define map_words(map) map_calc_words(map) -# else -# define map_bankwidth(map) 32 -# define map_bankwidth_is_large(map) (1) -# define map_words(map) map_calc_words(map) -# endif +/* always use indirect access for 256-bit to preserve kernel stack */ +# undef map_bankwidth +# define map_bankwidth(map) ((map)->bankwidth) +# undef map_bankwidth_is_large +# define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8) +# undef map_words +# define map_words(map) map_calc_words(map) #define map_bankwidth_is_32(map) (map_bankwidth(map) == 32) #undef MAX_MAP_BANKWIDTH #define MAX_MAP_BANKWIDTH 32 diff --git a/include/linux/namei.h b/include/linux/namei.h index d53c25453aca..023359f18567 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -79,6 +79,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); +extern struct dentry *lookup_one_len2(const char *, struct vfsmount *mnt, struct dentry *, int); extern int follow_down_one(struct path *); extern int follow_down(struct path *); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 93a6a2c66d15..4035bbe40971 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1399,6 +1399,7 @@ enum netdev_priv_flags { * @mtu: Interface MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. + * @min_header_len: Minimum hardware header length * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -1619,6 +1620,7 @@ struct net_device { unsigned int mtu; unsigned short type; unsigned short hard_header_len; + unsigned short min_header_len; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -2541,6 +2543,8 @@ static inline bool dev_validate_header(const struct net_device *dev, { if (likely(len >= dev->hard_header_len)) return true; + if (len < dev->min_header_len) + return false; if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index e7e78537aea2..63a817631f06 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -266,7 +266,7 @@ enum nfsstat4 { static inline bool seqid_mutating_err(u32 err) { - /* rfc 3530 section 8.1.5: */ + /* See RFC 7530, section 9.1.7 */ switch (err) { case NFS4ERR_STALE_CLIENTID: case NFS4ERR_STALE_STATEID: @@ -275,6 +275,7 @@ static inline bool seqid_mutating_err(u32 err) case NFS4ERR_BADXDR: case NFS4ERR_RESOURCE: case NFS4ERR_NOFILEHANDLE: + case NFS4ERR_MOVED: return false; }; return true; diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 12c9b485beb7..abd7c01c84db 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -206,7 +206,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref) static inline bool percpu_ref_tryget(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; - int ret; + bool ret; rcu_read_lock_sched(); @@ -240,7 +240,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; - int ret = false; + bool ret = false; rcu_read_lock_sched(); diff --git a/include/linux/phy.h b/include/linux/phy.h index 05fde31b6dc6..b64825d6ad26 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -785,6 +785,10 @@ int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_soft_reset(struct phy_device *phydev); +static inline int genphy_no_soft_reset(struct phy_device *phydev) +{ + return 0; +} void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver); diff --git a/include/linux/pid.h b/include/linux/pid.h index 23705a53abba..97b745ddece5 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -8,7 +8,9 @@ enum pid_type PIDTYPE_PID, PIDTYPE_PGID, PIDTYPE_SID, - PIDTYPE_MAX + PIDTYPE_MAX, + /* only valid to __task_pid_nr_ns() */ + __PIDTYPE_TGID }; /* diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 45ac5a0d29ee..7097a45dbc25 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -24,6 +24,13 @@ #include <linux/list.h> #include <linux/types.h> +/* + * Choose whether access to the RAM zone requires locking or not. If a zone + * can be written to from different CPUs like with ftrace for example, then + * PRZ_FLAG_NO_LOCK is used. For all other cases, locking is required. + */ +#define PRZ_FLAG_NO_LOCK BIT(0) + struct persistent_ram_buffer; struct rs_control; @@ -40,6 +47,8 @@ struct persistent_ram_zone { void *vaddr; struct persistent_ram_buffer *buffer; size_t buffer_size; + u32 flags; + raw_spinlock_t buffer_lock; /* ECC correction */ char *par_buffer; @@ -55,7 +64,7 @@ struct persistent_ram_zone { struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype); + unsigned int memtype, u32 flags); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index e13bfdf7f314..81fdf4b8aba4 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -50,7 +50,8 @@ extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, - struct task_struct *new_parent); + struct task_struct *new_parent, + const struct cred *ptracer_cred); extern void __ptrace_unlink(struct task_struct *child); extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 @@ -202,7 +203,7 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; - __ptrace_link(child, current->parent); + __ptrace_link(child, current->parent, current->ptracer_cred); if (child->ptrace & PT_SEIZED) task_set_jobctl_pending(child, JOBCTL_TRAP_STOP); @@ -211,6 +212,8 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) set_tsk_thread_flag(child, TIF_SIGPENDING); } + else + child->ptracer_cred = NULL; } /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d92903b3a0f..43daf00967a6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -813,6 +813,16 @@ struct signal_struct { #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ +#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ + SIGNAL_STOP_CONTINUED) + +static inline void signal_set_stop_flags(struct signal_struct *sig, + unsigned int flags) +{ + WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; +} + /* If true, all threads except ->group_exit_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { @@ -1561,6 +1571,10 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif +#ifdef CONFIG_CGROUPS + /* disallow userland-initiated cgroup migration */ + unsigned no_cgroup_migration:1; +#endif unsigned long atomic_flags; /* Flags needing atomic access. */ @@ -2021,31 +2035,8 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) return tsk->tgid; } -pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); - -static inline pid_t task_tgid_vnr(struct task_struct *tsk) -{ - return pid_vnr(task_tgid(tsk)); -} - static inline int pid_alive(const struct task_struct *p); -static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) -{ - pid_t pid = 0; - - rcu_read_lock(); - if (pid_alive(tsk)) - pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); - rcu_read_unlock(); - - return pid; -} - -static inline pid_t task_ppid_nr(const struct task_struct *tsk) -{ - return task_ppid_nr_ns(tsk, &init_pid_ns); -} static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) @@ -2070,6 +2061,33 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } +static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns); +} + +static inline pid_t task_tgid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL); +} + +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + /* obsolete, do not use */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { @@ -3227,6 +3245,11 @@ static inline void inc_syscw(struct task_struct *tsk) { tsk->ioac.syscw++; } + +static inline void inc_syscfs(struct task_struct *tsk) +{ + tsk->ioac.syscfs++; +} #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { @@ -3243,6 +3266,9 @@ static inline void inc_syscr(struct task_struct *tsk) static inline void inc_syscw(struct task_struct *tsk) { } +static inline void inc_syscfs(struct task_struct *tsk) +{ +} #endif #ifndef TASK_SIZE_OF diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index dde00defbaa5..f3d45dd42695 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -7,13 +7,10 @@ #include <linux/mutex.h> #include <linux/cpumask.h> #include <linux/nodemask.h> +#include <linux/fs.h> +#include <linux/cred.h> struct seq_operations; -struct file; -struct path; -struct inode; -struct dentry; -struct user_namespace; struct seq_file { char *buf; @@ -27,9 +24,7 @@ struct seq_file { struct mutex lock; const struct seq_operations *op; int poll_event; -#ifdef CONFIG_USER_NS - struct user_namespace *user_ns; -#endif + const struct file *file; void *private; }; @@ -147,7 +142,7 @@ int seq_release_private(struct inode *, struct file *); static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { #ifdef CONFIG_USER_NS - return seq->user_ns; + return seq->file->f_cred->user_ns; #else extern struct user_namespace init_user_ns; return &init_user_ns; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d443d9ab0236..3f61c647fc5c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1084,9 +1084,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline void skb_sender_cpu_clear(struct sk_buff *skb) { -#ifdef CONFIG_XPS - skb->sender_cpu = 0; -#endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET diff --git a/include/linux/slab.h b/include/linux/slab.h index 4ef384b172e0..b4e739f04ee6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -215,7 +215,7 @@ static inline const char *__check_heap_object(const void *ptr, * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif @@ -228,7 +228,7 @@ static inline const char *__check_heap_object(const void *ptr, * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT -#define KMALLOC_SHIFT_MAX 30 +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 9b6027c51736..316a5525b730 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -180,5 +180,6 @@ const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); int rpc_localaddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_proc_name(const struct rpc_task *task); +void rpc_cleanup_clids(void); #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h index bdf855c2856f..2dd338fdf881 100644 --- a/include/linux/task_io_accounting.h +++ b/include/linux/task_io_accounting.h @@ -18,6 +18,8 @@ struct task_io_accounting { u64 syscr; /* # of write syscalls */ u64 syscw; + /* # of fsync syscalls */ + u64 syscfs; #endif /* CONFIG_TASK_XACCT */ #ifdef CONFIG_TASK_IO_ACCOUNTING diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h index 4d090f9ee608..1b505c804af3 100644 --- a/include/linux/task_io_accounting_ops.h +++ b/include/linux/task_io_accounting_ops.h @@ -96,6 +96,7 @@ static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, dst->wchar += src->wchar; dst->syscr += src->syscr; dst->syscw += src->syscw; + dst->syscfs += src->syscfs; } #else static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b386361ba3e8..318c24612458 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -56,8 +56,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { + union { + u8 val[TCP_FASTOPEN_COOKIE_MAX]; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr addr; +#endif + }; s8 len; - u8 val[TCP_FASTOPEN_COOKIE_MAX]; bool exp; /* In RFC6994 experimental option format */ }; diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index f5d5f455660c..0f175b8f6456 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -164,7 +164,6 @@ struct tee_shm_pool_mem_info { /** * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved * memory range - * @dev: Device allocating the pool * @priv_info: Information for driver private shared memory pool * @dmabuf_info: Information for dma-buf shared memory pool * @@ -176,8 +175,7 @@ struct tee_shm_pool_mem_info { * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. */ struct tee_shm_pool * -tee_shm_pool_alloc_res_mem(struct device *dev, - struct tee_shm_pool_mem_info *priv_info, +tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, struct tee_shm_pool_mem_info *dmabuf_info); /** @@ -268,7 +266,8 @@ int tee_shm_get_pa(struct tee_shm *shm, size_t offs, phys_addr_t *pa); int tee_shm_get_id(struct tee_shm *shm); /** - * tee_shm_get_from_id() - Find shared memory object and increase referece count + * tee_shm_get_from_id() - Find shared memory object and increase reference + * count * @ctx: Context owning the shared memory * @id: Id of shared memory object * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 25247220b4b7..f0f1793cfa49 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -29,7 +29,6 @@ */ struct tk_read_base { struct clocksource *clock; - cycle_t (*read)(struct clocksource *cs); cycle_t mask; cycle_t cycle_last; u32 mult; diff --git a/include/linux/usb.h b/include/linux/usb.h index 12891ffd4bf0..8c75af6b7d5b 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -371,14 +371,13 @@ struct usb_bus { int devnum_next; /* Next open device number in * round-robin allocation */ + struct mutex devnum_next_mutex; /* devnum_next mutex */ struct usb_devmap devmap; /* device address allocation map */ struct usb_device *root_hub; /* Root hub */ struct usb_bus *hs_companion; /* Companion EHCI bus, if any */ struct list_head bus_list; /* list of busses */ - struct mutex usb_address0_mutex; /* unaddressed device mutex */ - int bandwidth_allocated; /* on this bus: how much of the time * reserved for periodic (intr/iso) * requests is used, on average? diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 5dd75fa47dd8..f9be467d6695 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -14,6 +14,7 @@ struct ci_hdrc; * struct ci_hdrc_cable - structure for external connector cable state tracking * @state: current state of the line * @changed: set to true when extcon event happen + * @enabled: set to true if we've enabled the vbus or id interrupt * @edev: device which generate events * @ci: driver state of the chipidea device * @nb: hold event notification callback @@ -22,6 +23,7 @@ struct ci_hdrc; struct ci_hdrc_cable { bool state; bool changed; + bool enabled; struct extcon_dev *edev; struct ci_hdrc *ci; struct notifier_block nb; diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 7cb909ff0bd0..2d10f26f9283 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -180,6 +180,7 @@ struct usb_hcd { * bandwidth_mutex should be dropped after a successful control message * to the device, or resetting the bandwidth after a failed attempt. */ + struct mutex *address0_mutex; struct mutex *bandwidth_mutex; struct usb_hcd *shared_hcd; struct usb_hcd *primary_hcd; @@ -573,9 +574,9 @@ extern void usb_ep0_reinit(struct usb_device *); ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) #define EndpointRequest \ - ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) + ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) #define EndpointOutRequest \ - ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) + ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) /* class requests from the USB 2.0 hub spec, table 11-15 */ /* GetBusState and SetHubDescriptor are optional, omitted */ diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 1d0043dc34e4..de2a722fe3cf 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -50,4 +50,10 @@ /* device can't handle Link Power Management */ #define USB_QUIRK_NO_LPM BIT(10) +/* + * Device reports its bInterval as linear frames instead of the + * USB 2.0 calculation. + */ +#define USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL BIT(11) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ddb440975382..34851bf2e2c8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -85,6 +85,8 @@ extern void vfio_unregister_iommu_driver( */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); +extern bool vfio_external_group_match_file(struct vfio_group *group, + struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0197358f1e81..262d5c95dfc8 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -311,6 +311,7 @@ enum { __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ + __WQ_ORDERED_EXPLICIT = 1 << 18, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -408,7 +409,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ - alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) + alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \ + __WQ_ORDERED_EXPLICIT | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name)) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 3275ddf9f00d..9cba4907695c 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -1,8 +1,9 @@ #ifndef _ADDRCONF_H #define _ADDRCONF_H -#define MAX_RTR_SOLICITATIONS 3 +#define MAX_RTR_SOLICITATIONS -1 /* unlimited */ #define RTR_SOLICITATION_INTERVAL (4*HZ) +#define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ #define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ @@ -19,6 +20,8 @@ #define ADDRCONF_TIMER_FUZZ (HZ / 4) #define ADDRCONF_TIMER_FUZZ_MAX (HZ) +#define ADDRCONF_NOTIFY_PRIORITY 0 + #include <linux/in.h> #include <linux/in6.h> diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index 3ebb168b9afc..a34b141f125f 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb, } for (opt_iter = 6; opt_iter < opt_len;) { + if (opt_iter + 1 == opt_len) { + err_offset = opt_iter; + goto out; + } tag_len = opt[opt_iter + 1]; if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) { err_offset = opt_iter + 1; diff --git a/include/net/dst.h b/include/net/dst.h index c7329dcd90cc..e4f450617919 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -110,10 +110,16 @@ struct dst_entry { }; }; +struct dst_metrics { + u32 metrics[RTAX_MAX]; + atomic_t refcnt; +}; +extern const struct dst_metrics dst_default_metrics; + u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); -extern const u32 dst_default_metrics[]; #define DST_METRICS_READ_ONLY 0x1UL +#define DST_METRICS_REFCOUNTED 0x2UL #define DST_METRICS_FLAGS 0x3UL #define __DST_METRICS_PTR(Y) \ ((u32 *)((Y) & ~DST_METRICS_FLAGS)) diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 1c8b6820b694..515352c6280a 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -201,6 +201,7 @@ struct inet6_dev { struct ipv6_devstat stats; struct timer_list rs_timer; + __s32 rs_interval; /* in jiffies */ __u8 rs_probes; __u8 addr_gen_mode; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index af0e8c081191..f9bdfb096579 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -21,6 +21,7 @@ struct route_info { #include <net/flow.h> #include <net/ip6_fib.h> #include <net/sock.h> +#include <net/lwtunnel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/route.h> @@ -77,6 +78,7 @@ static inline struct dst_entry *ip6_route_output(struct net *net, struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, int flags); +void ip6_route_init_special_entries(void); int ip6_route_init(void); void ip6_route_cleanup(void); @@ -208,4 +210,11 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, return daddr; } +static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b) +{ + return a->dst.dev == b->dst.dev && + a->rt6i_idev == b->rt6i_idev && + ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) && + !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate); +} #endif diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 3f98233388fb..bda1721e9622 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -112,11 +112,11 @@ struct fib_info { unsigned char fib_type; __be32 fib_prefsrc; u32 fib_priority; - u32 *fib_metrics; -#define fib_mtu fib_metrics[RTAX_MTU-1] -#define fib_window fib_metrics[RTAX_WINDOW-1] -#define fib_rtt fib_metrics[RTAX_RTT-1] -#define fib_advmss fib_metrics[RTAX_ADVMSS-1] + struct dst_metrics *fib_metrics; +#define fib_mtu fib_metrics->metrics[RTAX_MTU-1] +#define fib_window fib_metrics->metrics[RTAX_WINDOW-1] +#define fib_rtt fib_metrics->metrics[RTAX_RTT-1] +#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_weight; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9a5c9f013784..7a8066b90289 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -744,6 +744,11 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, { u32 hash; + /* @flowlabel may include more than a flow label, eg, the traffic class. + * Here we want only the flow label value. + */ + flowlabel &= IPV6_FLOWLABEL_MASK; + if (flowlabel || net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && @@ -958,6 +963,7 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row, */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; +extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index e0f4109e64c6..c2aa73e5e6bb 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -556,7 +556,8 @@ iwe_stream_add_point(struct iw_request_info *info, char *stream, char *ends, memcpy(stream + lcp_len, ((char *) &iwe->u) + IW_EV_POINT_OFF, IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN); - memcpy(stream + point_len, extra, iwe->u.data.length); + if (iwe->u.data.length && extra) + memcpy(stream + point_len, extra, iwe->u.data.length); stream += event_len; } return stream; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c328f3548756..c493b7c0d3c8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1662,9 +1662,9 @@ struct ieee80211_sta_rates { * @supp_rates: Bitmap of supported rates (per band) * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities - * @max_rx_aggregation_subframes: restriction on rx buff size for this active - * link. Initially set to local->hw.max_rx_aggregation_subframes but can - * be modified by driver. + * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU + * that this station is allowed to transmit to us. + * Can be modified by driver. * @wme: indicates whether the STA supports QoS/WME (if local devices does, * otherwise always false) * @drv_priv: data area for driver use, will always be aligned to @@ -2678,6 +2678,33 @@ enum ieee80211_ampdu_mlme_action { }; /** + * struct ieee80211_ampdu_params - AMPDU action parameters + * + * @action: the ampdu action, value from %ieee80211_ampdu_mlme_action. + * @sta: peer of this AMPDU session + * @tid: tid of the BA session + * @ssn: start sequence number of the session. TX/RX_STOP can pass 0. When + * action is set to %IEEE80211_AMPDU_RX_START the driver passes back the + * actual ssn value used to start the session and writes the value here. + * @buf_size: reorder buffer size (number of subframes). Valid only when the + * action is set to %IEEE80211_AMPDU_RX_START or + * %IEEE80211_AMPDU_TX_OPERATIONAL + * @amsdu: indicates the peer's ability to receive A-MSDU within A-MPDU. + * valid when the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL + * @timeout: BA session timeout. Valid only when the action is set to + * %IEEE80211_AMPDU_RX_START + */ +struct ieee80211_ampdu_params { + enum ieee80211_ampdu_mlme_action action; + struct ieee80211_sta *sta; + u16 tid; + u16 ssn; + u8 buf_size; + bool amsdu; + u16 timeout; +}; + +/** * enum ieee80211_frame_release_type - frame release reason * @IEEE80211_FRAME_RELEASE_PSPOLL: frame released for PS-Poll * @IEEE80211_FRAME_RELEASE_UAPSD: frame(s) released due to @@ -3021,13 +3048,9 @@ enum ieee80211_reconfig_type { * @ampdu_action: Perform a certain A-MPDU action * The RA/TID combination determines the destination and TID we want * the ampdu action to be performed for. The action is defined through - * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) - * is the first frame we expect to perform the action on. Notice - * that TX/RX_STOP can pass NULL for this parameter. - * The @buf_size parameter is only valid when the action is set to - * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder - * buffer size (number of subframes) for this session -- the driver - * may neither send aggregates containing more subframes than this + * ieee80211_ampdu_mlme_action. + * When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver + * may neither send aggregates containing more subframes than @buf_size * nor send aggregates in a way that lost frames would exceed the * buffer size. If just limiting the aggregate size, this would be * possible with a buf_size of 8: @@ -3038,9 +3061,6 @@ enum ieee80211_reconfig_type { * buffer size of 8. Correct ways to retransmit #1 would be: * - TX: 1 or 18 or 81 * Even "189" would be wrong since 1 could be lost again. - * The @amsdu parameter is valid when the action is set to - * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's ability - * to receive A-MSDU within A-MPDU. * * Returns a negative error code on failure. * The callback can sleep. @@ -3382,9 +3402,7 @@ struct ieee80211_ops { int (*tx_last_beacon)(struct ieee80211_hw *hw); int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index ce13cf20f625..d33b17ba51d2 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -444,6 +444,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member) #define _sctp_walk_params(pos, chunk, end, member)\ for (pos.v = chunk->member;\ + (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <=\ + (void *)chunk + end) &&\ pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\ ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\ pos.v += WORD_ROUND(ntohs(pos.p->length))) @@ -454,6 +456,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) #define _sctp_walk_errors(err, chunk_hdr, end)\ for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ sizeof(sctp_chunkhdr_t));\ + ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <=\ + (void *)chunk_hdr + end) &&\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ ntohs(err->length) >= sizeof(sctp_errhdr_t); \ err = (sctp_errhdr_t *)((void *)err + WORD_ROUND(ntohs(err->length)))) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d6f6e5006ee9..185fb037b332 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -948,10 +948,6 @@ struct xfrm_dst { struct flow_cache_object flo; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols, num_xfrms; -#ifdef CONFIG_XFRM_SUB_POLICY - struct flowi *origin; - struct xfrm_selector *partner; -#endif u32 xfrm_genid; u32 policy_genid; u32 route_mtu_cached; @@ -967,12 +963,6 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); -#ifdef CONFIG_XFRM_SUB_POLICY - kfree(xdst->origin); - xdst->origin = NULL; - kfree(xdst->partner); - xdst->partner = NULL; -#endif } #endif diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h index 301969552d0a..b43e64d69734 100644 --- a/include/rdma/ib_sa.h +++ b/include/rdma/ib_sa.h @@ -138,12 +138,12 @@ struct ib_sa_path_rec { union ib_gid sgid; __be16 dlid; __be16 slid; - int raw_traffic; + u8 raw_traffic; /* reserved */ __be32 flow_label; u8 hop_limit; u8 traffic_class; - int reversible; + u8 reversible; u8 numb_path; __be16 pkey; __be16 qos_class; @@ -204,7 +204,7 @@ struct ib_sa_mcmember_rec { u8 hop_limit; u8 scope; u8 join_state; - int proxy_join; + u8 proxy_join; }; /* Service Record Component Mask Sec 15.2.5.14 Ver 1.1 */ diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 4d1c46aac331..c7b1dc713cdd 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -196,6 +196,7 @@ struct iscsi_conn { struct iscsi_task *task; /* xmit task in progress */ /* xmit */ + spinlock_t taskqueuelock; /* protects the next three lists */ struct list_head mgmtqueue; /* mgmt (control) xmit queue */ struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 4f6ba34cdee6..293b9a7f53bc 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -307,6 +307,7 @@ extern void scsi_remove_device(struct scsi_device *); extern int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh); void scsi_attach_vpd(struct scsi_device *sdev); +extern struct scsi_device *scsi_device_from_queue(struct request_queue *q); extern int scsi_device_get(struct scsi_device *); extern void scsi_device_put(struct scsi_device *); extern struct scsi_device *scsi_device_lookup(struct Scsi_Host *, diff --git a/include/soc/at91/at91sam9_ddrsdr.h b/include/soc/at91/at91sam9_ddrsdr.h index dc10c52e0e91..393362bdb860 100644 --- a/include/soc/at91/at91sam9_ddrsdr.h +++ b/include/soc/at91/at91sam9_ddrsdr.h @@ -81,6 +81,7 @@ #define AT91_DDRSDRC_LPCB_POWER_DOWN 2 #define AT91_DDRSDRC_LPCB_DEEP_POWER_DOWN 3 #define AT91_DDRSDRC_CLKFR (1 << 2) /* Clock Frozen */ +#define AT91_DDRSDRC_LPDDR2_PWOFF (1 << 3) /* LPDDR Power Off */ #define AT91_DDRSDRC_PASR (7 << 4) /* Partial Array Self Refresh */ #define AT91_DDRSDRC_TCSR (3 << 8) /* Temperature Compensated Self Refresh */ #define AT91_DDRSDRC_DS (3 << 10) /* Drive Strength */ @@ -96,7 +97,9 @@ #define AT91_DDRSDRC_MD_SDR 0 #define AT91_DDRSDRC_MD_LOW_POWER_SDR 1 #define AT91_DDRSDRC_MD_LOW_POWER_DDR 3 +#define AT91_DDRSDRC_MD_LPDDR3 5 #define AT91_DDRSDRC_MD_DDR2 6 /* [SAM9 Only] */ +#define AT91_DDRSDRC_MD_LPDDR2 7 #define AT91_DDRSDRC_DBW (1 << 4) /* Data Bus Width */ #define AT91_DDRSDRC_DBW_32BITS (0 << 4) #define AT91_DDRSDRC_DBW_16BITS (1 << 4) diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 373d3342002b..22f442ab85f9 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -64,6 +64,14 @@ #define TA_DEFAULT_FABRIC_PROT_TYPE 0 /* TPG status needs to be enabled to return sendtargets discovery endpoint info */ #define TA_DEFAULT_TPG_ENABLED_SENDTARGETS 1 +/* + * Used to control the sending of keys with optional to respond state bit, + * as a workaround for non RFC compliant initiators,that do not propose, + * nor respond to specific keys required for login to complete. + * + * See iscsi_check_proposer_for_optional_reply() for more details. + */ +#define TA_DEFAULT_LOGIN_KEYS_WORKAROUND 1 #define ISCSI_IOV_DATA_BUFFER 5 @@ -554,6 +562,7 @@ struct iscsi_conn { #define LOGIN_FLAGS_READ_ACTIVE 1 #define LOGIN_FLAGS_CLOSED 2 #define LOGIN_FLAGS_READY 4 +#define LOGIN_FLAGS_INITIAL_PDU 8 unsigned long login_flags; struct delayed_work login_work; struct delayed_work login_cleanup_work; @@ -765,6 +774,7 @@ struct iscsi_tpg_attrib { u8 t10_pi; u32 fabric_prot_type; u32 tpg_enabled_sendtargets; + u32 login_keys_workaround; struct iscsi_portal_group *tpg; }; @@ -774,6 +784,7 @@ struct iscsi_np { int np_sock_type; enum np_thread_state_table np_thread_state; bool enabled; + atomic_t np_reset_count; enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 6afc6f388edf..1adf8739980c 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -544,6 +544,7 @@ struct se_node_acl { /* Used to signal demo mode created ACL, disabled by default */ bool dynamic_node_acl; bool acl_stop:1; + bool dynamic_stop; u32 queue_depth; u32 acl_index; enum target_prot_type saved_prot_type; @@ -713,6 +714,7 @@ struct se_lun { #define SE_LUN_LINK_MAGIC 0xffff7771 u32 lun_link_magic; u32 lun_access; + bool lun_shutdown; u32 lun_index; /* RELATIVE TARGET PORT IDENTIFER */ @@ -739,6 +741,7 @@ struct se_lun { struct config_group lun_group; struct se_port_stat_grps port_stat_grps; struct completion lun_ref_comp; + struct completion lun_shutdown_comp; struct percpu_ref lun_ref; struct list_head lun_dev_link; struct hlist_node link; diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index ce9ea736f1d7..5f9b62c129fc 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -117,7 +117,7 @@ void __transport_register_session(struct se_portal_group *, struct se_node_acl *, struct se_session *, void *); void transport_register_session(struct se_portal_group *, struct se_node_acl *, struct se_session *, void *); -void target_get_session(struct se_session *); +int target_get_session(struct se_session *); void target_put_session(struct se_session *); ssize_t target_show_dynamic_sessions(struct se_portal_group *, char *); void transport_free_session(struct se_session *); @@ -168,10 +168,11 @@ void core_allocate_nexus_loss_ua(struct se_node_acl *acl); struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg, unsigned char *); +bool target_tpg_has_node_acl(struct se_portal_group *tpg, + const char *); struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *, unsigned char *); -int core_tpg_set_initiator_node_queue_depth(struct se_portal_group *, - unsigned char *, u32, int); +int core_tpg_set_initiator_node_queue_depth(struct se_node_acl *, u32); int core_tpg_set_initiator_node_tag(struct se_portal_group *, struct se_node_acl *, const char *); int core_tpg_register(struct se_wwn *, struct se_portal_group *, int); diff --git a/include/trace/events/android_fs.h b/include/trace/events/android_fs.h index 531da433a7bc..49509533d3fa 100644 --- a/include/trace/events/android_fs.h +++ b/include/trace/events/android_fs.h @@ -9,8 +9,8 @@ DEFINE_EVENT(android_fs_data_start_template, android_fs_dataread_start, TP_PROTO(struct inode *inode, loff_t offset, int bytes, - pid_t pid, char *command), - TP_ARGS(inode, offset, bytes, pid, command)); + pid_t pid, char *pathname, char *command), + TP_ARGS(inode, offset, bytes, pid, pathname, command)); DEFINE_EVENT(android_fs_data_end_template, android_fs_dataread_end, TP_PROTO(struct inode *inode, loff_t offset, int bytes), @@ -18,14 +18,48 @@ DEFINE_EVENT(android_fs_data_end_template, android_fs_dataread_end, DEFINE_EVENT(android_fs_data_start_template, android_fs_datawrite_start, TP_PROTO(struct inode *inode, loff_t offset, int bytes, - pid_t pid, char *command), - TP_ARGS(inode, offset, bytes, pid, command)); + pid_t pid, char *pathname, char *command), + TP_ARGS(inode, offset, bytes, pid, pathname, command)); DEFINE_EVENT(android_fs_data_end_template, android_fs_datawrite_end, TP_PROTO(struct inode *inode, loff_t offset, int bytes), - TP_ARGS(inode, offset, bytes)); + TP_ARGS(inode, offset, bytes)); #endif /* _TRACE_ANDROID_FS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> + +#ifndef ANDROID_FSTRACE_GET_PATHNAME +#define ANDROID_FSTRACE_GET_PATHNAME + +/* Sizes an on-stack array, so careful if sizing this up ! */ +#define MAX_TRACE_PATHBUF_LEN 256 + +static inline char * +android_fstrace_get_pathname(char *buf, int buflen, struct inode *inode) +{ + char *path; + struct dentry *d; + + /* + * d_obtain_alias() will either iput() if it locates an existing + * dentry or transfer the reference to the new dentry created. + * So get an extra reference here. + */ + ihold(inode); + d = d_obtain_alias(inode); + if (likely(!IS_ERR(d))) { + path = dentry_path_raw(d, buf, buflen); + if (unlikely(IS_ERR(path))) { + strcpy(buf, "ERROR"); + path = buf; + } + dput(d); + } else { + strcpy(buf, "ERROR"); + path = buf; + } + return path; +} +#endif diff --git a/include/trace/events/android_fs_template.h b/include/trace/events/android_fs_template.h index 618988b047c1..b23d17b56c63 100644 --- a/include/trace/events/android_fs_template.h +++ b/include/trace/events/android_fs_template.h @@ -5,11 +5,10 @@ DECLARE_EVENT_CLASS(android_fs_data_start_template, TP_PROTO(struct inode *inode, loff_t offset, int bytes, - pid_t pid, char *command), - TP_ARGS(inode, offset, bytes, pid, command), + pid_t pid, char *pathname, char *command), + TP_ARGS(inode, offset, bytes, pid, pathname, command), TP_STRUCT__entry( - __array(char, path, MAX_FILTER_STR_VAL); - __field(char *, pathname); + __string(pathbuf, pathname); __field(loff_t, offset); __field(int, bytes); __field(loff_t, i_size); @@ -19,40 +18,26 @@ DECLARE_EVENT_CLASS(android_fs_data_start_template, ), TP_fast_assign( { - struct dentry *d; - /* - * Grab a reference to the inode here because - * d_obtain_alias() will either drop the inode - * reference if it locates an existing dentry - * or transfer the reference to the new dentry - * created. In our case, the file is still open, - * so the dentry is guaranteed to exist (connected), - * so d_obtain_alias() drops the reference we - * grabbed here. + * Replace the spaces in filenames and cmdlines + * because this screws up the tooling that parses + * the traces. */ - ihold(inode); - d = d_obtain_alias(inode); - if (!IS_ERR(d)) { - __entry->pathname = dentry_path(d, - __entry->path, - MAX_FILTER_STR_VAL); - dput(d); - } else - __entry->pathname = ERR_PTR(-EINVAL); + __assign_str(pathbuf, pathname); + (void)strreplace(__get_str(pathbuf), ' ', '_'); __entry->offset = offset; __entry->bytes = bytes; __entry->i_size = i_size_read(inode); __assign_str(cmdline, command); + (void)strreplace(__get_str(cmdline), ' ', '_'); __entry->pid = pid; __entry->ino = inode->i_ino; } ), TP_printk("entry_name %s, offset %llu, bytes %d, cmdline %s," " pid %d, i_size %llu, ino %lu", - (IS_ERR(__entry->pathname) ? "ERROR" : __entry->pathname), - __entry->offset, __entry->bytes, __get_str(cmdline), - __entry->pid, __entry->i_size, + __get_str(pathbuf), __entry->offset, __entry->bytes, + __get_str(cmdline), __entry->pid, __entry->i_size, (unsigned long) __entry->ino) ); diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h index 14e49c798135..b35533b94277 100644 --- a/include/trace/events/syscalls.h +++ b/include/trace/events/syscalls.h @@ -1,5 +1,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM raw_syscalls +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE syscalls #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ) diff --git a/include/uapi/drm/omap_drm.h b/include/uapi/drm/omap_drm.h index 72e461e1e5bc..7e7322498992 100644 --- a/include/uapi/drm/omap_drm.h +++ b/include/uapi/drm/omap_drm.h @@ -36,6 +36,9 @@ struct drm_omap_param { #define OMAP_BO_SCANOUT 0x00000001 /* scanout capable (phys contiguous) */ #define OMAP_BO_CACHE_MASK 0x00000006 /* cache type mask, see cache modes */ #define OMAP_BO_TILED_MASK 0x00000f00 /* tiled mapping mask, see tiled modes */ +#define OMAP_BO_MEM_CONTIG 0x00000008 /* only use contiguous dma mem */ +#define OMAP_BO_MEM_TILER 0x00000010 /* only use TILER mem */ +#define OMAP_BO_MEM_PIN 0x00000020 /* pin the buffer when allocating */ /* cache modes */ #define OMAP_BO_CACHED 0x00000000 /* default */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 224be60ef489..75edca951804 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -103,6 +103,7 @@ header-y += dlm_netlink.h header-y += dlm_plock.h header-y += dm-ioctl.h header-y += dm-log-userspace.h +header-y += dma-buf.h header-y += dn.h header-y += dqblk_xfs.h header-y += edd.h diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 51f891fb1b18..7668b5791c91 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -132,6 +132,7 @@ enum { /* struct binder_fd_array_object - object describing an array of fds in a buffer * @hdr: common header structure + * @pad: padding to ensure correct alignment * @num_fds: number of file descriptors in the buffer * @parent: index in offset array to buffer holding the fd array * @parent_offset: start offset of fd array in the buffer @@ -152,6 +153,7 @@ enum { */ struct binder_fd_array_object { struct binder_object_header hdr; + __u32 pad; binder_size_t num_fds; binder_size_t parent; binder_size_t parent_offset; diff --git a/include/uapi/linux/hw_breakpoint.h b/include/uapi/linux/hw_breakpoint.h index b04000a2296a..2b65efd19a46 100644 --- a/include/uapi/linux/hw_breakpoint.h +++ b/include/uapi/linux/hw_breakpoint.h @@ -4,7 +4,11 @@ enum { HW_BREAKPOINT_LEN_1 = 1, HW_BREAKPOINT_LEN_2 = 2, + HW_BREAKPOINT_LEN_3 = 3, HW_BREAKPOINT_LEN_4 = 4, + HW_BREAKPOINT_LEN_5 = 5, + HW_BREAKPOINT_LEN_6 = 6, + HW_BREAKPOINT_LEN_7 = 7, HW_BREAKPOINT_LEN_8 = 8, }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 2b1533859749..c462f1dc175e 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -175,6 +175,16 @@ enum { DEVCONF_USE_OIF_ADDRS_ONLY, DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT, DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, + DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, + DEVCONF_DROP_UNSOLICITED_NA, + DEVCONF_KEEP_ADDR_ON_DOWN, + DEVCONF_RTR_SOLICIT_MAX_INTERVAL, + DEVCONF_SEG6_ENABLED, + DEVCONF_SEG6_REQUIRE_HMAC, + DEVCONF_ENHANCED_DAD, + DEVCONF_ADDR_GEN_MODE, + DEVCONF_DISABLE_POLICY, + DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN, DEVCONF_MAX }; diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index f6598d1c886e..316e838b7470 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -34,7 +34,7 @@ #define RTF_PREF(pref) ((pref) << 27) #define RTF_PREF_MASK 0x18000000 -#define RTF_PCPU 0x40000000 +#define RTF_PCPU 0x40000000 /* read-only: can not be set by user */ #define RTF_LOCAL 0x80000000 diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 99048e501b88..aae5ebf2022b 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -39,6 +39,7 @@ #define KEXEC_ARCH_SH (42 << 16) #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) +#define KEXEC_ARCH_AARCH64 (183 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index d588107c9dce..509897624fbc 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -52,7 +52,7 @@ #define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs" #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" -#define SDCARDFS_SUPER_MAGIC 0xb550ca10 +#define SDCARDFS_SUPER_MAGIC 0x5dca2df5 #define SMB_SUPER_MAGIC 0x517B #define CGROUP_SUPER_MAGIC 0x27e0eb diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index f095155d8749..0dba4e4ed2be 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -107,8 +107,10 @@ struct nlmsgerr { #define NETLINK_PKTINFO 3 #define NETLINK_BROADCAST_ERROR 4 #define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ #define NETLINK_RX_RING 6 #define NETLINK_TX_RING 7 +#endif #define NETLINK_LISTEN_ALL_NSID 8 #define NETLINK_LIST_MEMBERSHIPS 9 #define NETLINK_CAP_ACK 10 @@ -134,6 +136,7 @@ struct nl_mmap_hdr { __u32 nm_gid; }; +#ifndef __KERNEL__ enum nl_mmap_status { NL_MMAP_STATUS_UNUSED, NL_MMAP_STATUS_RESERVED, @@ -145,6 +148,7 @@ enum nl_mmap_status { #define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO #define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) #define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif #define NET_MAJOR 36 /* Major 36 is reserved for networking */ diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index f2159d30d1f5..d79399394b46 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -48,6 +48,8 @@ enum { #define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */ #define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */ +#ifndef __KERNEL__ #define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */ +#endif #endif diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index d08c63f3dd6f..0c5d5dd61b6a 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -64,7 +64,7 @@ struct packet_diag_mclist { __u32 pdmc_count; __u16 pdmc_type; __u16 pdmc_alen; - __u8 pdmc_addr[MAX_ADDR_LEN]; + __u8 pdmc_addr[32]; /* MAX_ADDR_LEN */ }; struct packet_diag_ring { diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 0956373b56db..d18980e74534 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -570,6 +570,7 @@ enum { NET_IPV6_PROXY_NDP=23, NET_IPV6_ACCEPT_SOURCE_ROUTE=25, NET_IPV6_ACCEPT_RA_FROM_LOCAL=26, + NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27, __NET_IPV6_MAX }; diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index ddc476e3c16b..370d8845ab21 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -165,54 +165,28 @@ struct tee_ioctl_buf_data { #define TEE_IOCTL_LOGIN_GROUP_APPLICATION 6 /** - * struct tee_ioctl_param_memref - memory reference - * @shm_offs: Offset into the shared memory object - * @size: Size of the buffer - * @shm_id: Shared memory identifier - * - * Shared memory is allocated with TEE_IOC_SHM_ALLOC which returns an - * identifier representing the shared memory object. A memref can reference - * a part of a shared memory by specifying an offset (@shm_offs) and @size - * of the object. To supply the entire shared memory object set @shm_offs - * to 0 and @size to the previously returned size of the object. - */ -struct tee_ioctl_param_memref { - __u64 shm_offs; - __u64 size; - __s64 shm_id; -}; - -/** - * struct tee_ioctl_param_value - values - * @a: first value - * @b: second value - * @c: third value - * - * Value parameters are passed unchecked to the destination - */ -struct tee_ioctl_param_value { - __u64 a; - __u64 b; - __u64 c; -}; - -/** * struct tee_ioctl_param - parameter * @attr: attributes - * @memref: a memory reference - * @value: a value + * @a: if a memref, offset into the shared memory object, else a value parameter + * @b: if a memref, size of the buffer, else a value parameter + * @c: if a memref, shared memory identifier, else a value parameter * * @attr & TEE_PARAM_ATTR_TYPE_MASK indicates if memref or value is used in * the union. TEE_PARAM_ATTR_TYPE_VALUE_* indicates value and * TEE_PARAM_ATTR_TYPE_MEMREF_* indicates memref. TEE_PARAM_ATTR_TYPE_NONE * indicates that none of the members are used. + * + * Shared memory is allocated with TEE_IOC_SHM_ALLOC which returns an + * identifier representing the shared memory object. A memref can reference + * a part of a shared memory by specifying an offset (@a) and size (@b) of + * the object. To supply the entire shared memory object set the offset + * (@a) to 0 and size (@b) to the previously returned size of the object. */ struct tee_ioctl_param { __u64 attr; - union { - struct tee_ioctl_param_memref memref; - struct tee_ioctl_param_value value; - } u; + __u64 a; + __u64 b; + __u64 c; }; #define TEE_IOCTL_UUID_LEN 16 @@ -237,17 +211,9 @@ struct tee_ioctl_open_session_arg { __u32 ret; __u32 ret_origin; __u32 num_params; - /* - * this struct is 8 byte aligned since the 'struct tee_ioctl_param' - * which follows requires 8 byte alignment. - * - * Commented out element used to visualize the layout dynamic part - * of the struct. This field is not available at all if - * num_params == 0. - * - * struct tee_ioctl_param params[num_params]; - */ -} __aligned(8); + /* num_params tells the actual number of element in params */ + struct tee_ioctl_param params[]; +}; /** * TEE_IOC_OPEN_SESSION - opens a session to a Trusted Application @@ -276,17 +242,9 @@ struct tee_ioctl_invoke_arg { __u32 ret; __u32 ret_origin; __u32 num_params; - /* - * this struct is 8 byte aligned since the 'struct tee_ioctl_param' - * which follows requires 8 byte alignment. - * - * Commented out element used to visualize the layout dynamic part - * of the struct. This field is not available at all if - * num_params == 0. - * - * struct tee_ioctl_param params[num_params]; - */ -} __aligned(8); + /* num_params tells the actual number of element in params */ + struct tee_ioctl_param params[]; +}; /** * TEE_IOC_INVOKE - Invokes a function in a Trusted Application @@ -339,17 +297,9 @@ struct tee_ioctl_close_session_arg { struct tee_iocl_supp_recv_arg { __u32 func; __u32 num_params; - /* - * this struct is 8 byte aligned since the 'struct tee_ioctl_param' - * which follows requires 8 byte alignment. - * - * Commented out element used to visualize the layout dynamic part - * of the struct. This field is not available at all if - * num_params == 0. - * - * struct tee_ioctl_param params[num_params]; - */ -} __aligned(8); + /* num_params tells the actual number of element in params */ + struct tee_ioctl_param params[]; +}; /** * TEE_IOC_SUPPL_RECV - Receive a request for a supplicant function @@ -368,17 +318,10 @@ struct tee_iocl_supp_recv_arg { struct tee_iocl_supp_send_arg { __u32 ret; __u32 num_params; - /* - * this struct is 8 byte aligned since the 'struct tee_ioctl_param' - * which follows requires 8 byte alignment. - * - * Commented out element used to visualize the layout dynamic part - * of the struct. This field is not available at all if - * num_params == 0. - * - * struct tee_ioctl_param params[num_params]; - */ -} __aligned(8); + /* num_params tells the actual number of element in params */ + struct tee_ioctl_param params[]; +}; + /** * TEE_IOC_SUPPL_SEND - Receive a request for a supplicant function * diff --git a/include/uapi/linux/usb/ch11.h b/include/uapi/linux/usb/ch11.h index 331499d597fa..9ce10d4a0245 100644 --- a/include/uapi/linux/usb/ch11.h +++ b/include/uapi/linux/usb/ch11.h @@ -22,6 +22,9 @@ */ #define USB_MAXCHILDREN 31 +/* See USB 3.1 spec Table 10-5 */ +#define USB_SS_MAXPORTS 15 + /* * Hub request types */ diff --git a/init/Kconfig b/init/Kconfig index acb6645ffda5..445af1262134 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -395,6 +395,7 @@ endchoice config SCHED_WALT bool "Support window based load tracking" depends on SMP + depends on FAIR_GROUP_SCHED help This feature will allow the scheduler to maintain a tunable window based set of metrics for tasks and runqueues. These metrics can be diff --git a/init/do_mounts_dm.c b/init/do_mounts_dm.c index ecda58df9a19..bce1c2fbb915 100644 --- a/init/do_mounts_dm.c +++ b/init/do_mounts_dm.c @@ -5,13 +5,17 @@ * * This file is released under the GPL. */ +#include <linux/async.h> +#include <linux/ctype.h> #include <linux/device-mapper.h> #include <linux/fs.h> #include <linux/string.h> +#include <linux/delay.h> #include "do_mounts.h" -#include "../drivers/md/dm.h" +#define DM_MAX_DEVICES 256 +#define DM_MAX_TARGETS 256 #define DM_MAX_NAME 32 #define DM_MAX_UUID 129 #define DM_NO_UUID "none" @@ -19,14 +23,47 @@ #define DM_MSG_PREFIX "init" /* Separators used for parsing the dm= argument. */ -#define DM_FIELD_SEP ' ' -#define DM_LINE_SEP ',' +#define DM_FIELD_SEP " " +#define DM_LINE_SEP "," +#define DM_ANY_SEP DM_FIELD_SEP DM_LINE_SEP /* * When the device-mapper and any targets are compiled into the kernel - * (not a module), one target may be created and used as the root device at - * boot time with the parameters given with the boot line dm=... - * The code for that is here. + * (not a module), one or more device-mappers may be created and used + * as the root device at boot time with the parameters given with the + * boot line dm=... + * + * Multiple device-mappers can be stacked specifing the number of + * devices. A device can have multiple targets if the the number of + * targets is specified. + * + * TODO(taysom:defect 32847) + * In the future, the <num> field will be mandatory. + * + * <device> ::= [<num>] <device-mapper>+ + * <device-mapper> ::= <head> "," <target>+ + * <head> ::= <name> <uuid> <mode> [<num>] + * <target> ::= <start> <length> <type> <options> "," + * <mode> ::= "ro" | "rw" + * <uuid> ::= xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx | "none" + * <type> ::= "verity" | "bootcache" | ... + * + * Example: + * 2 vboot none ro 1, + * 0 1768000 bootcache + * device=aa55b119-2a47-8c45-946a-5ac57765011f+1 + * signature=76e9be054b15884a9fa85973e9cb274c93afadb6 + * cache_start=1768000 max_blocks=100000 size_limit=23 max_trace=20000, + * vroot none ro 1, + * 0 1740800 verity payload=254:0 hashtree=254:0 hashstart=1740800 alg=sha1 + * root_hexdigest=76e9be054b15884a9fa85973e9cb274c93afadb6 + * salt=5b3549d54d6c7a3837b9b81ed72e49463a64c03680c47835bef94d768e5646fe + * + * Notes: + * 1. uuid is a label for the device and we set it to "none". + * 2. The <num> field will be optional initially and assumed to be 1. + * Once all the scripts that set these fields have been set, it will + * be made mandatory. */ struct dm_setup_target { @@ -38,381 +75,388 @@ struct dm_setup_target { struct dm_setup_target *next; }; -static struct { +struct dm_device { int minor; int ro; char name[DM_MAX_NAME]; char uuid[DM_MAX_UUID]; - char *targets; + unsigned long num_targets; struct dm_setup_target *target; int target_count; + struct dm_device *next; +}; + +struct dm_option { + char *start; + char *next; + size_t len; + char delim; +}; + +static struct { + unsigned long num_devices; + char *str; } dm_setup_args __initdata; static __initdata int dm_early_setup; -static size_t __init get_dm_option(char *str, char **next, char sep) +static int __init get_dm_option(struct dm_option *opt, const char *accept) { - size_t len = 0; - char *endp = NULL; + char *str = opt->next; + char *endp; if (!str) return 0; - endp = strchr(str, sep); + str = skip_spaces(str); + opt->start = str; + endp = strpbrk(str, accept); if (!endp) { /* act like strchrnul */ - len = strlen(str); - endp = str + len; + opt->len = strlen(str); + endp = str + opt->len; } else { - len = endp - str; + opt->len = endp - str; } - - if (endp == str) - return 0; - - if (!next) - return len; - + opt->delim = *endp; if (*endp == 0) { /* Don't advance past the nul. */ - *next = endp; + opt->next = endp; } else { - *next = endp + 1; + opt->next = endp + 1; } - return len; -} - -static int __init dm_setup_args_init(void) -{ - dm_setup_args.minor = 0; - dm_setup_args.ro = 0; - dm_setup_args.target = NULL; - dm_setup_args.target_count = 0; - return 0; + return opt->len != 0; } -static int __init dm_setup_cleanup(void) +static int __init dm_setup_cleanup(struct dm_device *devices) { - struct dm_setup_target *target = dm_setup_args.target; - struct dm_setup_target *old_target = NULL; - while (target) { - kfree(target->type); - kfree(target->params); - old_target = target; - target = target->next; - kfree(old_target); - dm_setup_args.target_count--; + struct dm_device *dev = devices; + + while (dev) { + struct dm_device *old_dev = dev; + struct dm_setup_target *target = dev->target; + while (target) { + struct dm_setup_target *old_target = target; + kfree(target->type); + kfree(target->params); + target = target->next; + kfree(old_target); + dev->target_count--; + } + BUG_ON(dev->target_count); + dev = dev->next; + kfree(old_dev); } - BUG_ON(dm_setup_args.target_count); return 0; } -static char * __init dm_setup_parse_device_args(char *str) +static char * __init dm_parse_device(struct dm_device *dev, char *str) { - char *next = NULL; - size_t len = 0; + struct dm_option opt; + size_t len; /* Grab the logical name of the device to be exported to udev */ - len = get_dm_option(str, &next, DM_FIELD_SEP); - if (!len) { + opt.next = str; + if (!get_dm_option(&opt, DM_FIELD_SEP)) { DMERR("failed to parse device name"); goto parse_fail; } - len = min(len + 1, sizeof(dm_setup_args.name)); - strlcpy(dm_setup_args.name, str, len); /* includes nul */ - str = skip_spaces(next); + len = min(opt.len + 1, sizeof(dev->name)); + strlcpy(dev->name, opt.start, len); /* includes nul */ /* Grab the UUID value or "none" */ - len = get_dm_option(str, &next, DM_FIELD_SEP); - if (!len) { + if (!get_dm_option(&opt, DM_FIELD_SEP)) { DMERR("failed to parse device uuid"); goto parse_fail; } - len = min(len + 1, sizeof(dm_setup_args.uuid)); - strlcpy(dm_setup_args.uuid, str, len); - str = skip_spaces(next); + len = min(opt.len + 1, sizeof(dev->uuid)); + strlcpy(dev->uuid, opt.start, len); /* Determine if the table/device will be read only or read-write */ - if (!strncmp("ro,", str, 3)) { - dm_setup_args.ro = 1; - } else if (!strncmp("rw,", str, 3)) { - dm_setup_args.ro = 0; + get_dm_option(&opt, DM_ANY_SEP); + if (!strncmp("ro", opt.start, opt.len)) { + dev->ro = 1; + } else if (!strncmp("rw", opt.start, opt.len)) { + dev->ro = 0; } else { DMERR("failed to parse table mode"); goto parse_fail; } - str = skip_spaces(str + 3); - return str; + /* Optional number field */ + /* XXX: The <num> field will be mandatory in the next round */ + if (opt.delim == DM_FIELD_SEP[0]) { + if (!get_dm_option(&opt, DM_LINE_SEP)) + return NULL; + dev->num_targets = simple_strtoul(opt.start, NULL, 10); + } else { + dev->num_targets = 1; + } + if (dev->num_targets > DM_MAX_TARGETS) { + DMERR("too many targets %lu > %d", + dev->num_targets, DM_MAX_TARGETS); + } + return opt.next; parse_fail: return NULL; } -static void __init dm_substitute_devices(char *str, size_t str_len) +static char * __init dm_parse_targets(struct dm_device *dev, char *str) { - char *candidate = str; - char *candidate_end = str; - char old_char; - size_t len = 0; - dev_t dev; - - if (str_len < 3) - return; - - while (str && *str) { - candidate = strchr(str, '/'); - if (!candidate) - break; - - /* Avoid embedded slashes */ - if (candidate != str && *(candidate - 1) != DM_FIELD_SEP) { - str = strchr(candidate, DM_FIELD_SEP); - continue; - } - - len = get_dm_option(candidate, &candidate_end, DM_FIELD_SEP); - str = skip_spaces(candidate_end); - if (len < 3 || len > 37) /* name_to_dev_t max; maj:mix min */ - continue; - - /* Temporarily terminate with a nul */ - if (*candidate_end) - candidate_end--; - old_char = *candidate_end; - *candidate_end = '\0'; - - DMDEBUG("converting candidate device '%s' to dev_t", candidate); - /* Use the boot-time specific device naming */ - dev = name_to_dev_t(candidate); - *candidate_end = old_char; - - DMDEBUG(" -> %u", dev); - /* No suitable replacement found */ - if (!dev) - continue; - - /* Rewrite the /dev/path as a major:minor */ - len = snprintf(candidate, len, "%u:%u", MAJOR(dev), MINOR(dev)); - if (!len) { - DMERR("error substituting device major/minor."); - break; - } - candidate += len; - /* Pad out with spaces (fixing our nul) */ - while (candidate < candidate_end) - *(candidate++) = DM_FIELD_SEP; - } -} - -static int __init dm_setup_parse_targets(char *str) -{ - char *next = NULL; - size_t len = 0; - struct dm_setup_target **target = NULL; + struct dm_option opt; + struct dm_setup_target **target = &dev->target; + unsigned long num_targets = dev->num_targets; + unsigned long i; /* Targets are defined as per the table format but with a * comma as a newline separator. */ - target = &dm_setup_args.target; - while (str && *str) { + opt.next = str; + for (i = 0; i < num_targets; i++) { *target = kzalloc(sizeof(struct dm_setup_target), GFP_KERNEL); if (!*target) { - DMERR("failed to allocate memory for target %d", - dm_setup_args.target_count); + DMERR("failed to allocate memory for target %s<%ld>", + dev->name, i); goto parse_fail; } - dm_setup_args.target_count++; + dev->target_count++; - (*target)->begin = simple_strtoull(str, &next, 10); - if (!next || *next != DM_FIELD_SEP) { - DMERR("failed to parse starting sector for target %d", - dm_setup_args.target_count - 1); + if (!get_dm_option(&opt, DM_FIELD_SEP)) { + DMERR("failed to parse starting sector" + " for target %s<%ld>", dev->name, i); goto parse_fail; } - str = skip_spaces(next + 1); + (*target)->begin = simple_strtoull(opt.start, NULL, 10); - (*target)->length = simple_strtoull(str, &next, 10); - if (!next || *next != DM_FIELD_SEP) { - DMERR("failed to parse length for target %d", - dm_setup_args.target_count - 1); + if (!get_dm_option(&opt, DM_FIELD_SEP)) { + DMERR("failed to parse length for target %s<%ld>", + dev->name, i); goto parse_fail; } - str = skip_spaces(next + 1); - - len = get_dm_option(str, &next, DM_FIELD_SEP); - if (!len || - !((*target)->type = kstrndup(str, len, GFP_KERNEL))) { - DMERR("failed to parse type for target %d", - dm_setup_args.target_count - 1); + (*target)->length = simple_strtoull(opt.start, NULL, 10); + + if (get_dm_option(&opt, DM_FIELD_SEP)) + (*target)->type = kstrndup(opt.start, opt.len, + GFP_KERNEL); + if (!((*target)->type)) { + DMERR("failed to parse type for target %s<%ld>", + dev->name, i); goto parse_fail; } - str = skip_spaces(next); - - len = get_dm_option(str, &next, DM_LINE_SEP); - if (!len || - !((*target)->params = kstrndup(str, len, GFP_KERNEL))) { - DMERR("failed to parse params for target %d", - dm_setup_args.target_count - 1); + if (get_dm_option(&opt, DM_LINE_SEP)) + (*target)->params = kstrndup(opt.start, opt.len, + GFP_KERNEL); + if (!((*target)->params)) { + DMERR("failed to parse params for target %s<%ld>", + dev->name, i); goto parse_fail; } - str = skip_spaces(next); - - /* Before moving on, walk through the copied target and - * attempt to replace all /dev/xxx with the major:minor number. - * It may not be possible to resolve them traditionally at - * boot-time. */ - dm_substitute_devices((*target)->params, len); - target = &((*target)->next); } - DMDEBUG("parsed %d targets", dm_setup_args.target_count); + DMDEBUG("parsed %d targets", dev->target_count); - return 0; + return opt.next; parse_fail: - return 1; + return NULL; +} + +static struct dm_device * __init dm_parse_args(void) +{ + struct dm_device *devices = NULL; + struct dm_device **tail = &devices; + struct dm_device *dev; + char *str = dm_setup_args.str; + unsigned long num_devices = dm_setup_args.num_devices; + unsigned long i; + + if (!str) + return NULL; + for (i = 0; i < num_devices; i++) { + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) { + DMERR("failed to allocated memory for dev"); + goto error; + } + *tail = dev; + tail = &dev->next; + /* + * devices are given minor numbers 0 - n-1 + * in the order they are found in the arg + * string. + */ + dev->minor = i; + str = dm_parse_device(dev, str); + if (!str) /* NULL indicates error in parsing, bail */ + goto error; + + str = dm_parse_targets(dev, str); + if (!str) + goto error; + } + return devices; +error: + dm_setup_cleanup(devices); + return NULL; } /* * Parse the command-line parameters given our kernel, but do not * actually try to invoke the DM device now; that is handled by - * dm_setup_drive after the low-level disk drivers have initialised. - * dm format is as follows: - * dm="name uuid fmode,[table line 1],[table line 2],..." - * May be used with root=/dev/dm-0 as it always uses the first dm minor. + * dm_setup_drives after the low-level disk drivers have initialised. + * dm format is described at the top of the file. + * + * Because dm minor numbers are assigned in assending order starting with 0, + * You can assume the first device is /dev/dm-0, the next device is /dev/dm-1, + * and so forth. */ - static int __init dm_setup(char *str) { - dm_setup_args_init(); + struct dm_option opt; + unsigned long num_devices; - str = dm_setup_parse_device_args(str); if (!str) { DMDEBUG("str is NULL"); goto parse_fail; } - - /* Target parsing is delayed until we have dynamic memory */ - dm_setup_args.targets = str; - - printk(KERN_INFO "dm: will configure '%s' on dm-%d\n", - dm_setup_args.name, dm_setup_args.minor); - + opt.next = str; + if (!get_dm_option(&opt, DM_FIELD_SEP)) + goto parse_fail; + if (isdigit(opt.start[0])) { /* XXX: Optional number field */ + num_devices = simple_strtoul(opt.start, NULL, 10); + str = opt.next; + } else { + num_devices = 1; + /* Don't advance str */ + } + if (num_devices > DM_MAX_DEVICES) { + DMDEBUG("too many devices %lu > %d", + num_devices, DM_MAX_DEVICES); + } + dm_setup_args.str = str; + dm_setup_args.num_devices = num_devices; + DMINFO("will configure %lu devices", num_devices); dm_early_setup = 1; return 1; parse_fail: - printk(KERN_WARNING "dm: Invalid arguments supplied to dm=.\n"); + DMWARN("Invalid arguments supplied to dm=."); return 0; } - -static void __init dm_setup_drive(void) +static void __init dm_setup_drives(void) { struct mapped_device *md = NULL; struct dm_table *table = NULL; struct dm_setup_target *target; - char *uuid = dm_setup_args.uuid; + struct dm_device *dev; + char *uuid; fmode_t fmode = FMODE_READ; + struct dm_device *devices; - /* Finish parsing the targets. */ - if (dm_setup_parse_targets(dm_setup_args.targets)) - goto parse_fail; - - if (dm_create(dm_setup_args.minor, &md)) { - DMDEBUG("failed to create the device"); - goto dm_create_fail; - } - DMDEBUG("created device '%s'", dm_device_name(md)); - - /* In addition to flagging the table below, the disk must be - * set explicitly ro/rw. */ - set_disk_ro(dm_disk(md), dm_setup_args.ro); + devices = dm_parse_args(); - if (!dm_setup_args.ro) - fmode |= FMODE_WRITE; - if (dm_table_create(&table, fmode, dm_setup_args.target_count, md)) { - DMDEBUG("failed to create the table"); - goto dm_table_create_fail; - } + for (dev = devices; dev; dev = dev->next) { + if (dm_create(dev->minor, &md)) { + DMDEBUG("failed to create the device"); + goto dm_create_fail; + } + DMDEBUG("created device '%s'", dm_device_name(md)); + + /* + * In addition to flagging the table below, the disk must be + * set explicitly ro/rw. + */ + set_disk_ro(dm_disk(md), dev->ro); + + if (!dev->ro) + fmode |= FMODE_WRITE; + if (dm_table_create(&table, fmode, dev->target_count, md)) { + DMDEBUG("failed to create the table"); + goto dm_table_create_fail; + } - dm_lock_md_type(md); - target = dm_setup_args.target; - while (target) { - DMINFO("adding target '%llu %llu %s %s'", - (unsigned long long) target->begin, - (unsigned long long) target->length, target->type, - target->params); - if (dm_table_add_target(table, target->type, target->begin, - target->length, target->params)) { - DMDEBUG("failed to add the target to the table"); - goto add_target_fail; + dm_lock_md_type(md); + + for (target = dev->target; target; target = target->next) { + DMINFO("adding target '%llu %llu %s %s'", + (unsigned long long) target->begin, + (unsigned long long) target->length, + target->type, target->params); + if (dm_table_add_target(table, target->type, + target->begin, + target->length, + target->params)) { + DMDEBUG("failed to add the target" + " to the table"); + goto add_target_fail; + } + } + if (dm_table_complete(table)) { + DMDEBUG("failed to complete the table"); + goto table_complete_fail; } - target = target->next; - } - if (dm_table_complete(table)) { - DMDEBUG("failed to complete the table"); - goto table_complete_fail; - } + /* Suspend the device so that we can bind it to the table. */ + if (dm_suspend(md, 0)) { + DMDEBUG("failed to suspend the device pre-bind"); + goto suspend_fail; + } - if (dm_get_md_type(md) == DM_TYPE_NONE) { + /* Initial table load: acquire type of table. */ dm_set_md_type(md, dm_table_get_type(table)); + + /* Setup md->queue to reflect md's type. */ if (dm_setup_md_queue(md)) { DMWARN("unable to set up device queue for new table."); goto setup_md_queue_fail; } - } else if (dm_get_md_type(md) != dm_table_get_type(table)) { - DMWARN("can't change device type after initial table load."); - goto setup_md_queue_fail; - } - - /* Suspend the device so that we can bind it to the table. */ - if (dm_suspend(md, 0)) { - DMDEBUG("failed to suspend the device pre-bind"); - goto suspend_fail; - } - /* Bind the table to the device. This is the only way to associate - * md->map with the table and set the disk capacity directly. */ - if (dm_swap_table(md, table)) { /* should return NULL. */ - DMDEBUG("failed to bind the device to the table"); - goto table_bind_fail; - } + /* + * Bind the table to the device. This is the only way + * to associate md->map with the table and set the disk + * capacity directly. + */ + if (dm_swap_table(md, table)) { /* should return NULL. */ + DMDEBUG("failed to bind the device to the table"); + goto table_bind_fail; + } - /* Finally, resume and the device should be ready. */ - if (dm_resume(md)) { - DMDEBUG("failed to resume the device"); - goto resume_fail; - } + /* Finally, resume and the device should be ready. */ + if (dm_resume(md)) { + DMDEBUG("failed to resume the device"); + goto resume_fail; + } - /* Export the dm device via the ioctl interface */ - if (!strcmp(DM_NO_UUID, dm_setup_args.uuid)) - uuid = NULL; - if (dm_ioctl_export(md, dm_setup_args.name, uuid)) { - DMDEBUG("failed to export device with given name and uuid"); - goto export_fail; - } - printk(KERN_INFO "dm: dm-%d is ready\n", dm_setup_args.minor); + /* Export the dm device via the ioctl interface */ + if (!strcmp(DM_NO_UUID, dev->uuid)) + uuid = NULL; + if (dm_ioctl_export(md, dev->name, uuid)) { + DMDEBUG("failed to export device with given" + " name and uuid"); + goto export_fail; + } - dm_unlock_md_type(md); - dm_setup_cleanup(); + dm_unlock_md_type(md); + + DMINFO("dm-%d is ready", dev->minor); + } + dm_setup_cleanup(devices); return; export_fail: resume_fail: table_bind_fail: -suspend_fail: setup_md_queue_fail: +suspend_fail: table_complete_fail: add_target_fail: dm_unlock_md_type(md); dm_table_create_fail: dm_put(md); dm_create_fail: - dm_setup_cleanup(); -parse_fail: - printk(KERN_WARNING "dm: starting dm-%d (%s) failed\n", - dm_setup_args.minor, dm_setup_args.name); + DMWARN("starting dm-%d (%s) failed", + dev->minor, dev->name); + dm_setup_cleanup(devices); } __setup("dm=", dm_setup); @@ -421,6 +465,6 @@ void __init dm_run_setup(void) { if (!dm_early_setup) return; - printk(KERN_INFO "dm: attempting early device configuration.\n"); - dm_setup_drive(); + DMINFO("attempting early device configuration."); + dm_setup_drives(); } diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 161a1807e6ef..46436543ad28 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -747,7 +747,7 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir, } mode &= ~current_umask(); - ret = vfs_create(dir, path->dentry, mode, true); + ret = vfs_create2(path->mnt, dir, path->dentry, mode, true); path->dentry->d_fsdata = NULL; if (ret) return ERR_PTR(ret); @@ -763,7 +763,7 @@ static struct file *do_open(struct path *path, int oflag) if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) return ERR_PTR(-EINVAL); acc = oflag2acc[oflag & O_ACCMODE]; - if (inode_permission(d_inode(path->dentry), acc)) + if (inode_permission2(path->mnt, d_inode(path->dentry), acc)) return ERR_PTR(-EACCES); return dentry_open(path, oflag, current_cred()); } @@ -796,7 +796,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, ro = mnt_want_write(mnt); /* we'll drop it in any case */ error = 0; mutex_lock(&d_inode(root)->i_mutex); - path.dentry = lookup_one_len(name->name, root, strlen(name->name)); + path.dentry = lookup_one_len2(name->name, mnt, root, strlen(name->name)); if (IS_ERR(path.dentry)) { error = PTR_ERR(path.dentry); goto out_putfd; @@ -867,7 +867,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) if (err) goto out_name; mutex_lock_nested(&d_inode(mnt->mnt_root)->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name->name, mnt->mnt_root, + dentry = lookup_one_len2(name->name, mnt, mnt->mnt_root, strlen(name->name)); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); @@ -879,7 +879,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) err = -ENOENT; } else { ihold(inode); - err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL); + err = vfs_unlink2(mnt, d_inode(dentry->d_parent), dentry, NULL); } dput(dentry); @@ -1251,8 +1251,10 @@ retry: timeo = MAX_SCHEDULE_TIMEOUT; ret = netlink_attachskb(sock, nc, &timeo, NULL); - if (ret == 1) + if (ret == 1) { + sock = NULL; goto retry; + } if (ret) { sock = NULL; nc = NULL; diff --git a/ipc/shm.c b/ipc/shm.c index 3174634ca4e5..4982a4e7f009 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1083,8 +1083,8 @@ out_unlock1: * "raddr" thing points to kernel space, and there has to be a wrapper around * this. */ -long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, - unsigned long shmlba) +long do_shmat(int shmid, char __user *shmaddr, int shmflg, + ulong *raddr, unsigned long shmlba) { struct shmid_kernel *shp; unsigned long addr; @@ -1105,8 +1105,13 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, goto out; else if ((addr = (ulong)shmaddr)) { if (addr & (shmlba - 1)) { - if (shmflg & SHM_RND) - addr &= ~(shmlba - 1); /* round down */ + /* + * Round down to the nearest multiple of shmlba. + * For sane do_mmap_pgoff() parameters, avoid + * round downs that trigger nil-page and MAP_FIXED. + */ + if ((shmflg & SHM_RND) && addr >= shmlba) + addr &= ~(shmlba - 1); else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 939945a5649c..a162661c9d60 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -457,13 +457,15 @@ void audit_remove_watch_rule(struct audit_krule *krule) list_del(&krule->rlist); if (list_empty(&watch->rules)) { + /* + * audit_remove_watch() drops our reference to 'parent' which + * can get freed. Grab our own reference to be safe. + */ + audit_get_parent(parent); audit_remove_watch(watch); - - if (list_empty(&parent->watches)) { - audit_get_parent(parent); + if (list_empty(&parent->watches)) fsnotify_destroy_mark(&parent->mark, audit_watch_group); - audit_put_parent(parent); - } + audit_put_parent(parent); } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2cbfba78d3db..863e24f1e62e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -754,6 +754,11 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) if (err) return err; + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d leaks addr into mem\n", insn->src_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 03a1b3f754d6..16d5b7a46850 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2751,11 +2751,12 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, tsk = tsk->group_leader; /* - * Workqueue threads may acquire PF_NO_SETAFFINITY and become - * trapped in a cpuset, or RT worker may be born in a cgroup - * with no rt_runtime allocated. Just say no. + * kthreads may acquire PF_NO_SETAFFINITY during initialization. + * If userland migrates such a kthread to a non-root cgroup, it can + * become trapped in a cpuset, or RT kthread may be born in a + * cgroup with no rt_runtime allocated. Just say no. */ - if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { + if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; goto out_unlock_rcu; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3f9db31c5d04..f93a9f9b4b97 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -60,6 +60,7 @@ #include <linux/cgroup.h> #include <linux/wait.h> +struct static_key cpusets_pre_enable_key __read_mostly = STATIC_KEY_INIT_FALSE; struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE; /* See "Frequency meter" comments, below. */ @@ -174,9 +175,9 @@ typedef enum { } cpuset_flagbits_t; /* convenient tests for these bits */ -static inline bool is_cpuset_online(const struct cpuset *cs) +static inline bool is_cpuset_online(struct cpuset *cs) { - return test_bit(CS_ONLINE, &cs->flags); + return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) diff --git a/kernel/events/core.c b/kernel/events/core.c index f4fdaff76f6d..3421b1271970 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5823,7 +5823,7 @@ static int __perf_pmu_output_stop(void *info) { struct perf_event *event = info; struct pmu *pmu = event->pmu; - struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); struct remote_output ro = { .rb = event->rb, }; @@ -6169,6 +6169,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) char *buf = NULL; char *name; + if (vma->vm_flags & VM_READ) + prot |= PROT_READ; + if (vma->vm_flags & VM_WRITE) + prot |= PROT_WRITE; + if (vma->vm_flags & VM_EXEC) + prot |= PROT_EXEC; + + if (vma->vm_flags & VM_MAYSHARE) + flags = MAP_SHARED; + else + flags = MAP_PRIVATE; + + if (vma->vm_flags & VM_DENYWRITE) + flags |= MAP_DENYWRITE; + if (vma->vm_flags & VM_MAYEXEC) + flags |= MAP_EXECUTABLE; + if (vma->vm_flags & VM_LOCKED) + flags |= MAP_LOCKED; + if (vma->vm_flags & VM_HUGETLB) + flags |= MAP_HUGETLB; + if (file) { struct inode *inode; dev_t dev; @@ -6195,27 +6216,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) maj = MAJOR(dev); min = MINOR(dev); - if (vma->vm_flags & VM_READ) - prot |= PROT_READ; - if (vma->vm_flags & VM_WRITE) - prot |= PROT_WRITE; - if (vma->vm_flags & VM_EXEC) - prot |= PROT_EXEC; - - if (vma->vm_flags & VM_MAYSHARE) - flags = MAP_SHARED; - else - flags = MAP_PRIVATE; - - if (vma->vm_flags & VM_DENYWRITE) - flags |= MAP_DENYWRITE; - if (vma->vm_flags & VM_MAYEXEC) - flags |= MAP_EXECUTABLE; - if (vma->vm_flags & VM_LOCKED) - flags |= MAP_LOCKED; - if (vma->vm_flags & VM_HUGETLB) - flags |= MAP_HUGETLB; - goto got_name; } else { if (vma->vm_ops && vma->vm_ops->name) { @@ -8390,6 +8390,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) return 0; } +/* + * Variation on perf_event_ctx_lock_nested(), except we take two context + * mutexes. + */ +static struct perf_event_context * +__perf_event_ctx_lock_double(struct perf_event *group_leader, + struct perf_event_context *ctx) +{ + struct perf_event_context *gctx; + +again: + rcu_read_lock(); + gctx = READ_ONCE(group_leader->ctx); + if (!atomic_inc_not_zero(&gctx->refcount)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + mutex_lock_double(&gctx->mutex, &ctx->mutex); + + if (group_leader->ctx != gctx) { + mutex_unlock(&ctx->mutex); + mutex_unlock(&gctx->mutex); + put_ctx(gctx); + goto again; + } + + return gctx; +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -8630,8 +8661,26 @@ SYSCALL_DEFINE5(perf_event_open, } if (move_group) { - gctx = group_leader->ctx; - mutex_lock_double(&gctx->mutex, &ctx->mutex); + gctx = __perf_event_ctx_lock_double(group_leader, ctx); + + /* + * Check if we raced against another sys_perf_event_open() call + * moving the software group underneath us. + */ + if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) { + /* + * If someone moved the group out from under us, check + * if this new event wound up on the same ctx, if so + * its the regular !move_group case, otherwise fail. + */ + if (gctx != ctx) { + err = -EINVAL; + goto err_locked; + } else { + perf_event_ctx_unlock(group_leader, gctx); + move_group = 0; + } + } } else { mutex_lock(&ctx->mutex); } @@ -8726,7 +8775,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_unpin_context(ctx); if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); if (task) { @@ -8754,7 +8803,7 @@ SYSCALL_DEFINE5(perf_event_open, err_locked: if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); /* err_file: */ fput(event_file); @@ -9374,7 +9423,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } /* @@ -9390,7 +9439,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } raw_spin_lock_irqsave(&parent_ctx->lock, flags); @@ -9418,6 +9467,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) } raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); +out_unlock: mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); diff --git a/kernel/extable.c b/kernel/extable.c index e820ccee9846..4f06fc34313f 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -66,7 +66,7 @@ static inline int init_kernel_text(unsigned long addr) return 0; } -int core_kernel_text(unsigned long addr) +int notrace core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && addr < (unsigned long)_etext) diff --git a/kernel/fork.c b/kernel/fork.c index c85efa77e825..968917653c2c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -331,13 +331,14 @@ void set_task_stack_end_magic(struct task_struct *tsk) *stackend = STACK_END_MAGIC; /* for overflow detection */ } -static struct task_struct *dup_task_struct(struct task_struct *orig) +static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; struct thread_info *ti; - int node = tsk_fork_get_node(orig); int err; + if (node == NUMA_NO_NODE) + node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; @@ -367,7 +368,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) set_task_stack_end_magic(tsk); #ifdef CONFIG_CC_STACKPROTECTOR - tsk->stack_canary = get_random_int(); + tsk->stack_canary = get_random_long(); #endif /* @@ -1271,7 +1272,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, int __user *child_tidptr, struct pid *pid, int trace, - unsigned long tls) + unsigned long tls, + int node) { int retval; struct task_struct *p; @@ -1324,7 +1326,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto fork_out; retval = -ENOMEM; - p = dup_task_struct(current); + p = dup_task_struct(current, node); if (!p) goto fork_out; @@ -1589,11 +1591,13 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ recalc_sigpending(); if (signal_pending(current)) { - spin_unlock(¤t->sighand->siglock); - write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; goto bad_fork_cancel_cgroup; } + if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) { + retval = -ENOMEM; + goto bad_fork_cancel_cgroup; + } if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); @@ -1644,6 +1648,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, return p; bad_fork_cancel_cgroup: + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p, cgrp_ss_priv); bad_fork_free_pid: threadgroup_change_end(current); @@ -1700,7 +1706,8 @@ static inline void init_idle_pids(struct pid_link *links) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0); + task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0, + cpu_to_node(cpu)); if (!IS_ERR(task)) { init_idle_pids(task->pids); init_idle(task, cpu); @@ -1745,7 +1752,7 @@ long _do_fork(unsigned long clone_flags, } p = copy_process(clone_flags, stack_start, stack_size, - child_tidptr, NULL, trace, tls); + child_tidptr, NULL, trace, tls, NUMA_NO_NODE); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. diff --git a/kernel/futex.c b/kernel/futex.c index e8af73cc51a7..af29863f3349 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2690,7 +2690,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, { struct hrtimer_sleeper timeout, *to = NULL; struct rt_mutex_waiter rt_waiter; - struct rt_mutex *pi_mutex = NULL; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; @@ -2774,6 +2773,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) + rt_mutex_unlock(&q.pi_state->pi_mutex); /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. @@ -2782,6 +2783,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, spin_unlock(q.lock_ptr); } } else { + struct rt_mutex *pi_mutex; + /* * We have been woken up by futex_unlock_pi(), a timeout, or a * signal. futex_unlock_pi() will not destroy the lock_ptr nor @@ -2805,18 +2808,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0; + /* + * If fixup_pi_state_owner() faulted and was unable to handle + * the fault, unlock the rt_mutex and return the fault to + * userspace. + */ + if (ret && rt_mutex_owner(pi_mutex) == current) + rt_mutex_unlock(pi_mutex); + /* Unqueue and drop the lock. */ unqueue_me_pi(&q); } - /* - * If fixup_pi_state_owner() faulted and was unable to handle the - * fault, unlock the rt_mutex and return the fault to userspace. - */ - if (ret == -EFAULT) { - if (pi_mutex && rt_mutex_owner(pi_mutex) == current) - rt_mutex_unlock(pi_mutex); - } else if (ret == -EINTR) { + if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling * futex_lock_pi() directly. We could restart this syscall, but @@ -3199,4 +3203,4 @@ static int __init futex_init(void) return 0; } -__initcall(futex_init); +core_initcall(futex_init); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 15206453b12a..e4453d9f788c 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -810,8 +810,8 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, if (!desc) return; - __irq_do_set_handler(desc, handle, 1, NULL); desc->irq_common_data.handler_data = data; + __irq_do_set_handler(desc, handle, 1, NULL); irq_put_desc_busunlock(desc, flags); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 6ead200370da..a079ed14f230 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1287,8 +1287,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) ret = __irq_set_trigger(desc, new->flags & IRQF_TRIGGER_MASK); - if (ret) + if (ret) { + irq_release_resources(desc); goto out_mask; + } } desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d10ab6b9b5e0..695763516908 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -563,7 +563,7 @@ static void kprobe_optimizer(struct work_struct *work) } /* Wait for completing optimization and unoptimization */ -static void wait_for_kprobe_optimizer(void) +void wait_for_kprobe_optimizer(void) { mutex_lock(&kprobe_mutex); diff --git a/kernel/kthread.c b/kernel/kthread.c index 9ff173dca1ae..850b255649a2 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -18,6 +18,7 @@ #include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/uaccess.h> +#include <linux/cgroup.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); @@ -205,6 +206,7 @@ static int kthread(void *_create) ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) { + cgroup_kthread_ready(); __kthread_parkme(&self); ret = threadfn(data); } @@ -510,6 +512,7 @@ int kthreadd(void *unused) set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; + cgroup_init_kthreadd(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/membarrier.c b/kernel/membarrier.c index 536c727a56e9..9f9284f37f8d 100644 --- a/kernel/membarrier.c +++ b/kernel/membarrier.c @@ -16,6 +16,7 @@ #include <linux/syscalls.h> #include <linux/membarrier.h> +#include <linux/tick.h> /* * Bitmask made from a "or" of all commands within enum membarrier_cmd, @@ -51,6 +52,9 @@ */ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) { + /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */ + if (tick_nohz_full_enabled()) + return -ENOSYS; if (unlikely(flags)) return -EINVAL; switch (cmd) { diff --git a/kernel/padata.c b/kernel/padata.c index b38bea9c466a..ecc7b3f452c7 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -189,19 +189,20 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd) reorder = &next_queue->reorder; + spin_lock(&reorder->lock); if (!list_empty(&reorder->list)) { padata = list_entry(reorder->list.next, struct padata_priv, list); - spin_lock(&reorder->lock); list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); - spin_unlock(&reorder->lock); pd->processed++; + spin_unlock(&reorder->lock); goto out; } + spin_unlock(&reorder->lock); if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) { padata = ERR_PTR(-ENODATA); @@ -356,7 +357,7 @@ static int padata_setup_cpumasks(struct parallel_data *pd, cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask); if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) { - free_cpumask_var(pd->cpumask.cbcpu); + free_cpumask_var(pd->cpumask.pcpu); return -ENOMEM; } diff --git a/kernel/panic.c b/kernel/panic.c index 41e2b54f36b5..1d07cf9af849 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -167,7 +167,7 @@ void panic(const char *fmt, ...) * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ - pr_emerg("Rebooting in %d seconds..", panic_timeout); + pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); diff --git a/kernel/pid.c b/kernel/pid.c index 78b3d9f80d44..b17263be9082 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -526,8 +526,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, if (!ns) ns = task_active_pid_ns(current); if (likely(pid_alive(task))) { - if (type != PIDTYPE_PID) + if (type != PIDTYPE_PID) { + if (type == __PIDTYPE_TGID) + type = PIDTYPE_PID; task = task->group_leader; + } nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns); } rcu_read_unlock(); @@ -536,12 +539,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, } EXPORT_SYMBOL(__task_pid_nr_ns); -pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return pid_nr_ns(task_tgid(tsk), ns); -} -EXPORT_SYMBOL(task_tgid_nr_ns); - struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index a65ba137fd15..567ecc826bc8 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -255,7 +255,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) * if reparented. */ for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->nr_hashed == init_pids) break; schedule(); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 3124cebaec31..797f19e2aaa9 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -647,7 +647,7 @@ static void power_down(void) */ int hibernate(void) { - int error; + int error, nr_calls = 0; if (!hibernation_available()) { pr_debug("PM: Hibernation not available.\n"); @@ -662,9 +662,11 @@ int hibernate(void) } pm_prepare_console(); - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Exit; + } printk(KERN_INFO "PM: Syncing filesystems ... "); sys_sync(); @@ -714,7 +716,7 @@ int hibernate(void) /* Don't bother checking whether freezer_test_done is true */ freezer_test_done = false; Exit: - pm_notifier_call_chain(PM_POST_HIBERNATION); + __pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL); pm_restore_console(); atomic_inc(&snapshot_device_available); Unlock: @@ -740,7 +742,7 @@ int hibernate(void) */ static int software_resume(void) { - int error; + int error, nr_calls = 0; unsigned int flags; /* @@ -827,9 +829,11 @@ static int software_resume(void) } pm_prepare_console(); - error = pm_notifier_call_chain(PM_RESTORE_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Close_Finish; + } pr_debug("PM: Preparing processes for restore.\n"); error = freeze_processes(); @@ -855,7 +859,7 @@ static int software_resume(void) unlock_device_hotplug(); thaw_processes(); Finish: - pm_notifier_call_chain(PM_POST_RESTORE); + __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); pm_restore_console(); atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ diff --git a/kernel/power/main.c b/kernel/power/main.c index 27946975eff0..5ea50b1b7595 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -38,12 +38,19 @@ int unregister_pm_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_pm_notifier); -int pm_notifier_call_chain(unsigned long val) +int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls) { - int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL); + int ret; + + ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL, + nr_to_call, nr_calls); return notifier_to_errno(ret); } +int pm_notifier_call_chain(unsigned long val) +{ + return __pm_notifier_call_chain(val, -1, NULL); +} /* If set, devices may be suspended and resumed asynchronously. */ int pm_async_enabled = 1; diff --git a/kernel/power/power.h b/kernel/power/power.h index efe1b3b17c88..51f02ecaf125 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -200,6 +200,8 @@ static inline void suspend_test_finish(const char *label) {} #ifdef CONFIG_PM_SLEEP /* kernel/power/main.c */ +extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call, + int *nr_calls); extern int pm_notifier_call_chain(unsigned long val); #endif diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 024411816ccf..58209d8bfc56 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -268,16 +268,18 @@ static int suspend_test(int level) */ static int suspend_prepare(suspend_state_t state) { - int error; + int error, nr_calls = 0; if (!sleep_state_supported(state)) return -EPERM; pm_prepare_console(); - error = pm_notifier_call_chain(PM_SUSPEND_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Finish; + } trace_suspend_resume(TPS("freeze_processes"), 0, true); error = suspend_freeze_processes(); @@ -288,7 +290,7 @@ static int suspend_prepare(suspend_state_t state) suspend_stats.failed_freeze++; dpm_save_failed_step(SUSPEND_FREEZE); Finish: - pm_notifier_call_chain(PM_POST_SUSPEND); + __pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL); pm_restore_console(); return error; } diff --git a/kernel/power/user.c b/kernel/power/user.c index 526e8911460a..35310b627388 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -47,7 +47,7 @@ atomic_t snapshot_device_available = ATOMIC_INIT(1); static int snapshot_open(struct inode *inode, struct file *filp) { struct snapshot_data *data; - int error; + int error, nr_calls = 0; if (!hibernation_available()) return -EPERM; @@ -74,9 +74,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) swap_type_of(swsusp_resume_device, 0, NULL) : -1; data->mode = O_RDONLY; data->free_bitmaps = false; - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); + error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); if (error) - pm_notifier_call_chain(PM_POST_HIBERNATION); + __pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL); } else { /* * Resuming. We may need to wait for the image device to @@ -86,13 +86,15 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->swap = -1; data->mode = O_WRONLY; - error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls); if (!error) { error = create_basic_memory_bitmaps(); data->free_bitmaps = !error; - } + } else + nr_calls--; + if (error) - pm_notifier_call_chain(PM_POST_RESTORE); + __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); } if (error) atomic_inc(&snapshot_device_available); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index e7e586bb2022..1a698158face 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1440,7 +1440,7 @@ static void call_console_drivers(int level, { struct console *con; - trace_console(text, len); + trace_console_rcuidle(text, len); if (level >= console_loglevel && !ignore_loglevel) return; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index a46c40bfb5f6..5e2cd1030702 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -28,19 +28,25 @@ #include <linux/compat.h> +void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, + const struct cred *ptracer_cred) +{ + BUG_ON(!list_empty(&child->ptrace_entry)); + list_add(&child->ptrace_entry, &new_parent->ptraced); + child->parent = new_parent; + child->ptracer_cred = get_cred(ptracer_cred); +} + /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ -void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) +static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { - BUG_ON(!list_empty(&child->ptrace_entry)); - list_add(&child->ptrace_entry, &new_parent->ptraced); - child->parent = new_parent; rcu_read_lock(); - child->ptracer_cred = get_cred(__task_cred(new_parent)); + __ptrace_link(child, new_parent, __task_cred(new_parent)); rcu_read_unlock(); } @@ -151,11 +157,17 @@ static void ptrace_unfreeze_traced(struct task_struct *task) WARN_ON(!task->ptrace || task->parent != current); + /* + * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely. + * Recheck state under the lock to close this race. + */ spin_lock_irq(&task->sighand->siglock); - if (__fatal_signal_pending(task)) - wake_up_state(task, __TASK_TRACED); - else - task->state = TASK_TRACED; + if (task->state == __TASK_TRACED) { + if (__fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + else + task->state = TASK_TRACED; + } spin_unlock_irq(&task->sighand->siglock); } @@ -347,7 +359,7 @@ static int ptrace_attach(struct task_struct *task, long request, flags |= PT_SEIZED; task->ptrace = flags; - __ptrace_link(task, current); + ptrace_link(task, current); /* SEIZE doesn't trap tracee on attach */ if (!seize) @@ -414,7 +426,7 @@ static int ptrace_traceme(void) */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; - __ptrace_link(current, current->real_parent); + ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); diff --git a/kernel/resource.c b/kernel/resource.c index 249b1eb1e6e1..a4a94e700fb9 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -105,16 +105,25 @@ static int r_show(struct seq_file *m, void *v) { struct resource *root = m->private; struct resource *r = v, *p; + unsigned long long start, end; int width = root->end < 0x10000 ? 4 : 8; int depth; for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent) if (p->parent == root) break; + + if (file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) { + start = r->start; + end = r->end; + } else { + start = end = 0; + } + seq_printf(m, "%*s%0*llx-%0*llx : %s\n", depth * 2, "", - width, (unsigned long long) r->start, - width, (unsigned long long) r->end, + width, start, + width, end, r->name ? r->name : "<BAD>"); return 0; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1df6da0094f0..c2ef34d5d9f1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5786,7 +5786,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) walt_set_window_start(rq); raw_spin_unlock_irqrestore(&rq->lock, flags); rq->calc_load_update = calc_load_update; - account_reset_rq(rq); break; case CPU_ONLINE: @@ -6374,6 +6373,9 @@ enum s_alloc { * Build an iteration mask that can exclude certain CPUs from the upwards * domain traversal. * + * Only CPUs that can arrive at this group should be considered to continue + * balancing. + * * Asymmetric node setups can result in situations where the domain tree is of * unequal depth, make sure to skip domains that already cover the entire * range. @@ -6385,18 +6387,31 @@ enum s_alloc { */ static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) { - const struct cpumask *span = sched_domain_span(sd); + const struct cpumask *sg_span = sched_group_cpus(sg); struct sd_data *sdd = sd->private; struct sched_domain *sibling; int i; - for_each_cpu(i, span) { + for_each_cpu(i, sg_span) { sibling = *per_cpu_ptr(sdd->sd, i); - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + + /* + * Can happen in the asymmetric case, where these siblings are + * unused. The mask will not be empty because those CPUs that + * do have the top domain _should_ span the domain. + */ + if (!sibling->child) + continue; + + /* If we would not end up here, we can't continue from here */ + if (!cpumask_equal(sg_span, sched_domain_span(sibling->child))) continue; cpumask_set_cpu(i, sched_group_mask(sg)); } + + /* We must not have empty masks here */ + WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg))); } /* @@ -8572,11 +8587,20 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); - sched_online_group(tg, parent); - return &tg->css; } +/* Expose task group only after completing cgroup initialization */ +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css->parent); + + if (parent) + sched_online_group(tg, parent); + return 0; +} + static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); @@ -8951,6 +8975,7 @@ static struct cftype cpu_files[] = { struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, + .css_online = cpu_cgroup_css_online, .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, .fork = cpu_cgroup_fork, diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 9d9eb50d4059..f10b1cb255b2 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1800,12 +1800,11 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) queue_push_tasks(rq); -#else +#endif if (dl_task(rq->curr)) check_preempt_curr_dl(rq, p, 0); else resched_curr(rq); -#endif } } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 30d76a18ae1a..6f353de3f390 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2757,6 +2757,10 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) cfs_rq->load_last_update_time_copy = sa->last_update_time; #endif + /* Trace CPU load, unless cfs_rq belongs to a non-root task_group */ + if (cfs_rq == &rq_of(cfs_rq)->cfs) + trace_sched_load_avg_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq); + return decayed || removed; } @@ -2780,7 +2784,6 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) if (entity_is_task(se)) trace_sched_load_avg_task(task_of(se), &se->avg); - trace_sched_load_avg_cpu(cpu, cfs_rq); } static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -3958,6 +3961,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) if (!cfs_bandwidth_used()) return; + /* Synchronize hierarchical throttle counter: */ + if (unlikely(!cfs_rq->throttle_uptodate)) { + struct rq *rq = rq_of(cfs_rq); + struct cfs_rq *pcfs_rq; + struct task_group *tg; + + cfs_rq->throttle_uptodate = 1; + + /* Get closest up-to-date node, because leaves go first: */ + for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) { + pcfs_rq = tg->cfs_rq[cpu_of(rq)]; + if (pcfs_rq->throttle_uptodate) + break; + } + if (tg) { + cfs_rq->throttle_count = pcfs_rq->throttle_count; + cfs_rq->throttled_clock_task = rq_clock_task(rq); + } + } + /* an active group must be handled by the update_curr()->put() path */ if (!cfs_rq->runtime_enabled || cfs_rq->curr) return; @@ -4343,15 +4366,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { + /* Avoid re-evaluating load for this entity: */ + se = parent_entity(se); /* * Bias pick_next to pick a task from this cfs_rq, as * p is sleeping when it is within its sched_slice. */ - if (task_sleep && parent_entity(se)) - set_next_buddy(parent_entity(se)); - - /* avoid re-evaluating load for this entity */ - se = parent_entity(se); + if (task_sleep && se && !throttled_hierarchy(cfs_rq)) + set_next_buddy(se); break; } flags |= DEQUEUE_SLEEP; @@ -4916,7 +4938,7 @@ long group_norm_util(struct energy_env *eenv, struct sched_group *sg) } static int find_new_capacity(struct energy_env *eenv, - const struct sched_group_energy const *sge) + const struct sched_group_energy * const sge) { int idx; unsigned long util = group_max_util(eenv); diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index b0b93fd33af9..f8e8d68ed3fd 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -201,8 +201,9 @@ void calc_load_exit_idle(void) struct rq *this_rq = this_rq(); /* - * If we're still before the sample window, we're done. + * If we're still before the pending sample window, we're done. */ + this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update)) return; @@ -211,7 +212,6 @@ void calc_load_exit_idle(void) * accounted through the nohz accounting, so skip the entire deal and * sync up for the next window. */ - this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update + 10)) this_rq->calc_load_update += LOAD_FREQ; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8a16cba968c4..541b8494450e 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2235,10 +2235,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) queue_push_tasks(rq); -#else +#endif /* CONFIG_SMP */ if (p->prio < rq->curr->prio) resched_curr(rq); -#endif /* CONFIG_SMP */ } } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2f2b959ad244..0f18bcc49025 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -421,7 +421,7 @@ struct cfs_rq { u64 throttled_clock, throttled_clock_task; u64 throttled_clock_task_time; - int throttled, throttle_count; + int throttled, throttle_count, throttle_uptodate; struct list_head throttled_list; #endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -915,7 +915,7 @@ struct sched_group { unsigned int group_weight; struct sched_group_capacity *sgc; - const struct sched_group_energy const *sge; + const struct sched_group_energy *sge; /* * The CPUs this group covers. @@ -2025,16 +2025,3 @@ static inline u64 irq_time_read(int cpu) } #endif /* CONFIG_64BIT */ #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ - -static inline void account_reset_rq(struct rq *rq) -{ -#ifdef CONFIG_IRQ_TIME_ACCOUNTING - rq->prev_irq_time = 0; -#endif -#ifdef CONFIG_PARAVIRT - rq->prev_steal_time = 0; -#endif -#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING - rq->prev_steal_time_rq = 0; -#endif -} diff --git a/kernel/signal.c b/kernel/signal.c index f3f1f7a972fd..5d50ea899b6d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -346,7 +346,7 @@ static bool task_participate_group_stop(struct task_struct *task) * fresh group stop. Read comment in do_signal_stop() for details. */ if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { - sig->flags = SIGNAL_STOP_STOPPED; + signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED); return true; } return false; @@ -503,7 +503,8 @@ int unhandled_signal(struct task_struct *tsk, int sig) return !tsk->ptrace; } -static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) +static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, + bool *resched_timer) { struct sigqueue *q, *first = NULL; @@ -525,6 +526,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); + + *resched_timer = + (first->flags & SIGQUEUE_PREALLOC) && + (info->si_code == SI_TIMER) && + (info->si_sys_private); + __sigqueue_free(first); } else { /* @@ -541,12 +548,12 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - siginfo_t *info) + siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); if (sig) - collect_signal(sig, pending, info); + collect_signal(sig, pending, info, resched_timer); return sig; } @@ -558,15 +565,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, */ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { + bool resched_timer = false; int signr; /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ - signr = __dequeue_signal(&tsk->pending, mask, info); + signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { signr = __dequeue_signal(&tsk->signal->shared_pending, - mask, info); + mask, info, &resched_timer); /* * itimer signal ? * @@ -611,7 +619,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) */ current->jobctl |= JOBCTL_STOP_DEQUEUED; } - if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { + if (resched_timer) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave @@ -837,7 +845,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) * will take ->siglock, notice SIGNAL_CLD_MASK, and * notify its parent. See get_signal_to_deliver(). */ - signal->flags = why | SIGNAL_STOP_CONTINUED; + signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED); signal->group_stop_count = 0; signal->group_exit_code = 0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index abb795e8a6f1..a098831020f4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -65,6 +65,7 @@ #include <linux/sched/sysctl.h> #include <linux/kexec.h> #include <linux/bpf.h> +#include <linux/mount.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -174,7 +175,7 @@ extern int no_unaligned_warning; #define SYSCTL_WRITES_WARN 0 #define SYSCTL_WRITES_STRICT 1 -static int sysctl_writes_strict = SYSCTL_WRITES_WARN; +static int sysctl_writes_strict = SYSCTL_WRITES_STRICT; static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -1853,6 +1854,14 @@ static struct ctl_table fs_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, + { + .procname = "mount-max", + .data = &sysctl_mount_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, { } }; @@ -2162,9 +2171,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, if (write) { if (*negp) return -EINVAL; + if (*lvalp > UINT_MAX) + return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; + *negp = false; *lvalp = (unsigned long)val; } return 0; @@ -2518,6 +2530,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int break; if (neg) continue; + val = convmul * val / convdiv; if ((min && val < *min) || (max && val > *max)) continue; *i = val; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 7fbba635a549..6fcc367ad531 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -339,7 +339,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; - start = ktime_add(start, base->gettime()); + start = ktime_add_safe(start, base->gettime()); alarm_start(alarm, start); } EXPORT_SYMBOL_GPL(alarm_start_relative); @@ -425,7 +425,7 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) overrun++; } - alarm->node.expires = ktime_add(alarm->node.expires, interval); + alarm->node.expires = ktime_add_safe(alarm->node.expires, interval); return overrun; } EXPORT_SYMBOL_GPL(alarm_forward); @@ -611,13 +611,22 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, /* start the timer */ timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval); + + /* + * Rate limit to the tick as a hot fix to prevent DOS. Will be + * mopped up later. + */ + if (timr->it.alarm.interval.tv64 && + ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC) + timr->it.alarm.interval = ktime_set(0, TICK_NSEC); + exp = timespec_to_ktime(new_setting->it_value); /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { ktime_t now; now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime(); - exp = ktime_add(now, exp); + exp = ktime_add_safe(now, exp); } alarm_start(&timr->it.alarm.alarmtimer, exp); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5fa544f3f560..738f3467d169 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -116,6 +116,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) tk->offs_boot = ktime_add(tk->offs_boot, delta); } +/* + * tk_clock_read - atomic clocksource read() helper + * + * This helper is necessary to use in the read paths because, while the + * seqlock ensures we don't return a bad value while structures are updated, + * it doesn't protect from potential crashes. There is the possibility that + * the tkr's clocksource may change between the read reference, and the + * clock reference passed to the read function. This can cause crashes if + * the wrong clocksource is passed to the wrong read function. + * This isn't necessary to use when holding the timekeeper_lock or doing + * a read of the fast-timekeeper tkrs (which is protected by its own locking + * and update logic). + */ +static inline u64 tk_clock_read(struct tk_read_base *tkr) +{ + struct clocksource *clock = READ_ONCE(tkr->clock); + + return clock->read(clock); +} + #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ @@ -173,7 +193,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) */ do { seq = read_seqcount_begin(&tk_core.seq); - now = tkr->read(tkr->clock); + now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; @@ -207,7 +227,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) cycle_t cycle_now, delta; /* read clocksource */ - cycle_now = tkr->read(tkr->clock); + cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); @@ -235,12 +255,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; - tk->tkr_mono.read = clock->read; tk->tkr_mono.mask = clock->mask; - tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; - tk->tkr_raw.read = clock->read; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; @@ -404,7 +422,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) now += timekeeping_delta_to_ns(tkr, clocksource_delta( - tkr->read(tkr->clock), + tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_retry(&tkf->seq, seq)); @@ -461,6 +479,10 @@ static cycle_t dummy_clock_read(struct clocksource *cs) return cycles_at_suspend; } +static struct clocksource dummy_clock = { + .read = dummy_clock_read, +}; + /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. @@ -477,13 +499,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk) struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - cycles_at_suspend = tkr->read(tkr->clock); - tkr_dummy.read = dummy_clock_read; + cycles_at_suspend = tk_clock_read(tkr); + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - tkr_dummy.read = dummy_clock_read; + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } @@ -647,11 +669,10 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr_mono.clock; cycle_t cycle_now, delta; s64 nsec; - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -1434,7 +1455,7 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && cycle_now > tk->tkr_mono.cycle_last) { u64 num, max = ULLONG_MAX; @@ -1829,7 +1850,7 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3f743b147247..eba904bae48c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3535,7 +3535,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod) int exclude_mod = 0; int found = 0; int ret; - int clear_filter; + int clear_filter = 0; if (func) { func_g.type = filter_parse_regex(func, len, &func_g.search, @@ -3677,23 +3677,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash) ftrace_probe_registered = 1; } -static void __disable_ftrace_function_probe(void) +static bool __disable_ftrace_function_probe(void) { int i; if (!ftrace_probe_registered) - return; + return false; for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { struct hlist_head *hhd = &ftrace_func_hash[i]; if (hhd->first) - return; + return false; } /* no more funcs left */ ftrace_shutdown(&trace_probe_ops, 0); ftrace_probe_registered = 0; + return true; } @@ -3820,6 +3821,7 @@ static void __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data, int flags) { + struct ftrace_ops_hash old_hash_ops; struct ftrace_func_entry *rec_entry; struct ftrace_func_probe *entry; struct ftrace_func_probe *p; @@ -3831,6 +3833,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, struct hlist_node *tmp; char str[KSYM_SYMBOL_LEN]; int i, ret; + bool disabled; if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) func_g.search = NULL; @@ -3849,6 +3852,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_lock(&trace_probe_ops.func_hash->regex_lock); + old_hash_ops.filter_hash = old_hash; + /* Probes only have filters */ + old_hash_ops.notrace_hash = NULL; + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); if (!hash) /* Hmm, should report this somehow */ @@ -3886,12 +3893,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, } } mutex_lock(&ftrace_lock); - __disable_ftrace_function_probe(); + disabled = __disable_ftrace_function_probe(); /* * Remove after the disable is called. Otherwise, if the last * probe is removed, a null hash means *all enabled*. */ ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + + /* still need to update the function call sites */ + if (ftrace_enabled && !disabled) + ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS, + &old_hash_ops); synchronize_sched(); if (!ret) free_ftrace_hash_rcu(old_hash); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index acbb0e73d3a2..1275175b0946 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3440,11 +3440,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + struct buffer_page *head_page; + struct buffer_page *commit_page; + unsigned commit; cpu_buffer = iter->cpu_buffer; - return iter->head_page == cpu_buffer->commit_page && - iter->head == rb_commit_index(cpu_buffer); + /* Remember, trace recording is off when iterator is in use */ + reader = cpu_buffer->reader_page; + head_page = cpu_buffer->head_page; + commit_page = cpu_buffer->commit_page; + commit = rb_page_commit(commit_page); + + return ((iter->head_page == commit_page && iter->head == commit) || + (iter->head_page == reader && commit_page == head_page && + head_page->read == commit && + iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); @@ -4875,9 +4887,9 @@ static __init int test_ringbuffer(void) rb_data[cpu].cnt = cpu; rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], "rbtester/%d", cpu); - if (WARN_ON(!rb_threads[cpu])) { + if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_threads[cpu]); goto out_free; } @@ -4887,9 +4899,9 @@ static __init int test_ringbuffer(void) /* Now create the rb hammer! */ rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); - if (WARN_ON(!rb_hammer)) { + if (WARN_ON(IS_ERR(rb_hammer))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_hammer); goto out_free; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 293af3346c8c..70f519e8489e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1681,7 +1681,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, TRACE_FLAG_IRQS_NOSUPPORT | #endif ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | - ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | + ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); } @@ -6150,11 +6150,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, return ret; out_reg: - ret = register_ftrace_function_probe(glob, ops, count); + ret = alloc_snapshot(&global_trace); + if (ret < 0) + goto out; - if (ret >= 0) - alloc_snapshot(&global_trace); + ret = register_ftrace_function_probe(glob, ops, count); + out: return ret < 0 ? ret : 0; } @@ -6825,6 +6827,7 @@ static int instance_rmdir(const char *name) } kfree(tr->topts); + free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c9956440d0e6..e9092a0247bf 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -659,30 +659,25 @@ static int create_trace_kprobe(int argc, char **argv) pr_info("Probe point is not specified.\n"); return -EINVAL; } - if (isdigit(argv[1][0])) { - if (is_return) { - pr_info("Return probe point must be a symbol.\n"); - return -EINVAL; - } - /* an address specified */ - ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); - if (ret) { - pr_info("Failed to parse address.\n"); - return ret; - } - } else { + + /* try to parse an address. if that fails, try to read the + * input as a symbol. */ + if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { /* a symbol specified */ symbol = argv[1]; /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret) { - pr_info("Failed to parse symbol.\n"); + pr_info("Failed to parse either an address or a symbol.\n"); return ret; } if (offset && is_return) { pr_info("Return probe must be used without offset.\n"); return -EINVAL; } + } else if (is_return) { + pr_info("Return probe point must be a symbol.\n"); + return -EINVAL; } argc -= 2; argv += 2; @@ -1471,6 +1466,11 @@ static __init int kprobe_trace_self_tests_init(void) end: release_all_trace_kprobes(); + /* + * Wait for the optimizer work to finish. Otherwise it might fiddle + * with probes in already freed __init text. + */ + wait_for_kprobe_optimizer(); if (warn) pr_cont("NG: Some tests are failed. Please check them.\n"); else diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2c2f971f3e75..23231237f2e2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3647,8 +3647,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, return -EINVAL; /* creating multiple pwqs breaks ordering guarantee */ - if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) - return -EINVAL; + if (!list_empty(&wq->pwqs)) { + if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) + return -EINVAL; + + wq->flags &= ~__WQ_ORDERED; + } ctx = apply_wqattrs_prepare(wq, attrs); @@ -3834,6 +3838,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, struct workqueue_struct *wq; struct pool_workqueue *pwq; + /* + * Unbound && max_active == 1 used to imply ordered, which is no + * longer the case on NUMA machines due to per-node pools. While + * alloc_ordered_workqueue() is the right way to create an ordered + * workqueue, keep the previous behavior to avoid subtle breakages + * on NUMA. + */ + if ((flags & WQ_UNBOUND) && max_active == 1) + flags |= __WQ_ORDERED; + /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; @@ -4022,13 +4036,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) struct pool_workqueue *pwq; /* disallow meddling with max_active for ordered workqueues */ - if (WARN_ON(wq->flags & __WQ_ORDERED)) + if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); + wq->flags &= ~__WQ_ORDERED; wq->saved_max_active = max_active; for_each_pwq(pwq, wq) @@ -5154,7 +5169,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) * attributes breaks ordering guarantee. Disallow exposing ordered * workqueues. */ - if (WARN_ON(wq->flags & __WQ_ORDERED)) + if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 63d14d9b51d8..c879d72bf9f7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -145,7 +145,7 @@ config DEBUG_INFO_REDUCED config DEBUG_INFO_SPLIT bool "Produce split debuginfo in .dwo files" - depends on DEBUG_INFO + depends on DEBUG_INFO && !FRV help Generate debug info into separate .dwo files. This significantly reduces the build directory size for builds with DEBUG_INFO, diff --git a/lib/cmdline.c b/lib/cmdline.c index 8f13cf73c2ec..79069d7938ea 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -22,14 +22,14 @@ * the values[M, M+1, ..., N] into the ints array in get_options. */ -static int get_range(char **str, int *pint) +static int get_range(char **str, int *pint, int n) { int x, inc_counter, upper_range; (*str)++; upper_range = simple_strtol((*str), NULL, 0); inc_counter = upper_range - *pint; - for (x = *pint; x < upper_range; x++) + for (x = *pint; n && x < upper_range; x++, n--) *pint++ = x; return inc_counter; } @@ -96,7 +96,7 @@ char *get_options(const char *str, int nints, int *ints) break; if (res == 3) { int range_nums; - range_nums = get_range((char **)&str, ints + i); + range_nums = get_range((char **)&str, ints + i, nints - i); if (range_nums < 0) break; /* diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 76f29ecba8f4..771234d050c7 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -452,11 +452,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); /* - * For mappings greater than a page, we limit the stride (and - * hence alignment) to a page size. + * For mappings greater than or equal to a page, we limit the stride + * (and hence alignment) to a page size. */ nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - if (size > PAGE_SIZE) + if (size >= PAGE_SIZE) stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); else stride = 1; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 10cd1860e5b0..7e26aea3e404 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -4315,6 +4315,51 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + { + /* Mainly testing JIT + imm64 here. */ + "JMP_JGE_X: ldimm64 test 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JGE, R1, R2, 2), + BPF_LD_IMM64(R0, 0xffffffffffffffffUL), + BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xeeeeeeeeU } }, + }, + { + "JMP_JGE_X: ldimm64 test 2", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JGE, R1, R2, 0), + BPF_LD_IMM64(R0, 0xffffffffffffffffUL), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffffU } }, + }, + { + "JMP_JGE_X: ldimm64 test 3", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JGE, R1, R2, 4), + BPF_LD_IMM64(R0, 0xffffffffffffffffUL), + BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JNE | BPF_X */ { "JMP_JNE_X: if (3 != 2) return 1", diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c index 0ecef3e4690e..5e6db6b1e3bd 100644 --- a/lib/test_user_copy.c +++ b/lib/test_user_copy.c @@ -58,7 +58,9 @@ static int __init test_user_copy_init(void) usermem = (char __user *)user_addr; bad_usermem = (char *)user_addr; - /* Legitimate usage: none of these should fail. */ + /* + * Legitimate usage: none of these copies should fail. + */ ret |= test(copy_from_user(kmem, usermem, PAGE_SIZE), "legitimate copy_from_user failed"); ret |= test(copy_to_user(usermem, kmem, PAGE_SIZE), @@ -68,19 +70,33 @@ static int __init test_user_copy_init(void) ret |= test(put_user(value, (unsigned long __user *)usermem), "legitimate put_user failed"); - /* Invalid usage: none of these should succeed. */ + /* + * Invalid usage: none of these copies should succeed. + */ + + /* Reject kernel-to-kernel copies through copy_from_user(). */ ret |= test(!copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE), PAGE_SIZE), "illegal all-kernel copy_from_user passed"); + +#if 0 + /* + * When running with SMAP/PAN/etc, this will Oops the kernel + * due to the zeroing of userspace memory on failure. This needs + * to be tested in LKDTM instead, since this test module does not + * expect to explode. + */ ret |= test(!copy_from_user(bad_usermem, (char __user *)kmem, PAGE_SIZE), "illegal reversed copy_from_user passed"); +#endif ret |= test(!copy_to_user((char __user *)kmem, kmem + PAGE_SIZE, PAGE_SIZE), "illegal all-kernel copy_to_user passed"); ret |= test(!copy_to_user((char __user *)kmem, bad_usermem, PAGE_SIZE), "illegal reversed copy_to_user passed"); + ret |= test(!get_user(value, (unsigned long __user *)kmem), "illegal get_user passed"); ret |= test(!put_user(value, (unsigned long __user *)kmem), diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 9ef80bf441b3..a988d4ef39da 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -757,15 +757,20 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) if (!bdi->wb_congested) return -ENOMEM; + atomic_set(&bdi->wb_congested->refcnt, 1); + err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (err) { - kfree(bdi->wb_congested); + wb_congested_put(bdi->wb_congested); return err; } return 0; } -static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } +static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +{ + wb_congested_put(bdi->wb_congested); +} #endif /* CONFIG_CGROUP_WRITEBACK */ diff --git a/mm/filemap.c b/mm/filemap.c index c588d1222b2a..69f75c77c098 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -865,9 +865,12 @@ void page_endio(struct page *page, int rw, int err) unlock_page(page); } else { /* rw == WRITE */ if (err) { + struct address_space *mapping; + SetPageError(page); - if (page->mapping) - mapping_set_error(page->mapping, err); + mapping = page_mapping(page); + if (mapping) + mapping_set_error(mapping, err); } end_page_writeback(page); } @@ -1559,6 +1562,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, cond_resched(); find_page: + if (fatal_signal_pending(current)) { + error = -EINTR; + goto out; + } + page = find_get_page(mapping, index); if (!page) { page_cache_sync_readahead(mapping, @@ -312,11 +312,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, /* mlock all present pages, but do not fault in new pages */ if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK) return -ENOENT; - /* For mm_populate(), just skip the stack guard page. */ - if ((*flags & FOLL_POPULATE) && - (stack_guard_page_start(vma, address) || - stack_guard_page_end(vma, address + PAGE_SIZE))) - return -ENOENT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (nonblocking) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 530e6427f823..6c6f5ccfcda1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1269,6 +1269,16 @@ out_unlock: return ret; } +/* + * FOLL_FORCE can write to even unwritable pmd's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +{ + return pmd_write(pmd) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); +} + struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, @@ -1279,7 +1289,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !pmd_write(*pmd)) + if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) goto out; /* Avoid dumping huge zero page */ @@ -1353,8 +1363,11 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if (unlikely(pmd_trans_migrating(*pmdp))) { page = pmd_page(*pmdp); + if (!get_page_unless_zero(page)) + goto out_unlock; spin_unlock(ptl); wait_on_page_locked(page); + put_page(page); goto out; } @@ -1386,8 +1399,11 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { + if (!get_page_unless_zero(page)) + goto out_unlock; spin_unlock(ptl); wait_on_page_locked(page); + put_page(page); page_nid = -1; goto out; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea11123a9249..7294301d8495 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4362,6 +4362,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { struct page *page = NULL; spinlock_t *ptl; + pte_t pte; retry: ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); @@ -4371,12 +4372,13 @@ retry: */ if (!pmd_huge(*pmd)) goto out; - if (pmd_present(*pmd)) { + pte = huge_ptep_get((pte_t *)pmd); + if (pte_present(pte)) { page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); if (flags & FOLL_GET) get_page(page); } else { - if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) { + if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); __migration_entry_wait(mm, (pte_t *)pmd, ptl); goto retry; diff --git a/mm/internal.h b/mm/internal.h index 6979b2bd3227..f63f4393d633 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -453,6 +453,7 @@ struct tlbflush_unmap_batch; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); +void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { @@ -460,6 +461,8 @@ static inline void try_to_unmap_flush(void) static inline void try_to_unmap_flush_dirty(void) { } - +static inline void flush_tlb_batched_pending(struct mm_struct *mm) +{ +} #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ #endif /* __MM_INTERNAL_H */ diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 12f222d0224b..b4e31f78ae69 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -13,6 +13,7 @@ * */ +#include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/printk.h> @@ -251,6 +252,8 @@ void kasan_report(unsigned long addr, size_t size, if (likely(!kasan_report_enabled())) return; + disable_trace_on_warning(); + info.access_addr = (void *)addr; info.access_size = size; info.is_write = is_write; diff --git a/mm/list_lru.c b/mm/list_lru.c index 5d8dffd5b57c..786176b1a0ee 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -117,6 +117,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item) l = list_lru_from_kmem(nlru, item); list_add_tail(item, &l->list); l->nr_items++; + nlru->nr_items++; spin_unlock(&nlru->lock); return true; } @@ -136,6 +137,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item) l = list_lru_from_kmem(nlru, item); list_del_init(item); l->nr_items--; + nlru->nr_items--; spin_unlock(&nlru->lock); return true; } @@ -183,15 +185,10 @@ EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { - long count = 0; - int memcg_idx; + struct list_lru_node *nlru; - count += __list_lru_count_one(lru, nid, -1); - if (list_lru_memcg_aware(lru)) { - for_each_memcg_cache_index(memcg_idx) - count += __list_lru_count_one(lru, nid, memcg_idx); - } - return count; + nlru = &lru->node[nid]; + return nlru->nr_items; } EXPORT_SYMBOL_GPL(list_lru_count_node); @@ -226,6 +223,7 @@ restart: assert_spin_locked(&nlru->lock); case LRU_REMOVED: isolated++; + nlru->nr_items--; /* * If the lru lock has been dropped, our list * traversal is now invalid and so we have to diff --git a/mm/memblock.c b/mm/memblock.c index c3b7ebcc22a6..007b6fc1da9b 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -835,6 +835,18 @@ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) } /** + * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return 0 on success, -errno on failure. + */ +int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP); +} + +/** * __next_reserved_mem_region - next function for for_each_reserved_region() * @idx: pointer to u64 loop variable * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL @@ -1486,15 +1498,16 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void) return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } -void __init memblock_enforce_memory_limit(phys_addr_t limit) +static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; struct memblock_region *r; - if (!limit) - return; - - /* find out max address */ + /* + * translate the memory @limit size into the max address within one of + * the memory memblock regions, if the @limit exceeds the total size + * of those regions, max_addr will keep original value ULLONG_MAX + */ for_each_memblock(memory, r) { if (limit <= r->size) { max_addr = r->base + limit; @@ -1503,6 +1516,22 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) limit -= r->size; } + return max_addr; +} + +void __init memblock_enforce_memory_limit(phys_addr_t limit) +{ + phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == (phys_addr_t)ULLONG_MAX) + return; + /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX); @@ -1510,6 +1539,50 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) (phys_addr_t)ULLONG_MAX); } +void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) +{ + int start_rgn, end_rgn; + int i, ret; + + if (!size) + return; + + ret = memblock_isolate_range(&memblock.memory, base, size, + &start_rgn, &end_rgn); + if (ret) + return; + + /* remove all the MAP regions */ + for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) + if (!memblock_is_nomap(&memblock.memory.regions[i])) + memblock_remove_region(&memblock.memory, i); + + for (i = start_rgn - 1; i >= 0; i--) + if (!memblock_is_nomap(&memblock.memory.regions[i])) + memblock_remove_region(&memblock.memory, i); + + /* truncate the reserved regions */ + memblock_remove_range(&memblock.reserved, 0, base); + memblock_remove_range(&memblock.reserved, + base + size, (phys_addr_t)ULLONG_MAX); +} + +void __init memblock_mem_limit_remove_map(phys_addr_t limit) +{ + phys_addr_t max_addr; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == (phys_addr_t)ULLONG_MAX) + return; + + memblock_cap_memory_range(0, max_addr); +} + static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; @@ -1528,12 +1601,12 @@ static int __init_memblock memblock_search(struct memblock_type *type, phys_addr return -1; } -int __init memblock_is_reserved(phys_addr_t addr) +bool __init memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } -int __init_memblock memblock_is_memory(phys_addr_t addr) +bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } @@ -1662,6 +1735,30 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name } } +extern unsigned long __init_memblock +memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr) +{ + struct memblock_type *type = &memblock.reserved; + unsigned long size = 0; + int idx; + + for (idx = 0; idx < type->cnt; idx++) { + struct memblock_region *rgn = &type->regions[idx]; + phys_addr_t start, end; + + if (rgn->base + rgn->size < start_addr) + continue; + if (rgn->base > end_addr) + continue; + + start = rgn->base; + end = start + rgn->size; + size += end - start; + } + + return size; +} + void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 17dfe70f3309..484bedd8d811 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4150,24 +4150,6 @@ static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) atomic_add(n, &memcg->id.ref); } -static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) -{ - while (!atomic_inc_not_zero(&memcg->id.ref)) { - /* - * The root cgroup cannot be destroyed, so it's refcount must - * always be >= 1. - */ - if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { - VM_BUG_ON(1); - break; - } - memcg = parent_mem_cgroup(memcg); - if (!memcg) - memcg = root_mem_cgroup; - } - return memcg; -} - static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { if (atomic_sub_and_test(n, &memcg->id.ref)) { @@ -4496,9 +4478,9 @@ static int mem_cgroup_do_precharge(unsigned long count) return ret; } - /* Try charges one by one with reclaim */ + /* Try charges one by one with reclaim, but do not retry */ while (count--) { - ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1); + ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1); if (ret) return ret; mc.precharge++; @@ -5752,6 +5734,24 @@ static int __init mem_cgroup_init(void) subsys_initcall(mem_cgroup_init); #ifdef CONFIG_MEMCG_SWAP +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) +{ + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + /** * mem_cgroup_swapout - transfer a memsw charge to swap * @page: page whose memsw charge to transfer diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 750b7893ee3a..091fe9b06663 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1208,7 +1208,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * page_remove_rmap() in try_to_unmap_one(). So to determine page status * correctly, we save a copy of the page flags at this time. */ - page_flags = p->flags; + if (PageHuge(p)) + page_flags = hpage->flags; + else + page_flags = p->flags; /* * unpoison always clear PG_hwpoison inside page lock @@ -1619,12 +1622,8 @@ static int soft_offline_huge_page(struct page *page, int flags) if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); - /* - * We know that soft_offline_huge_page() tries to migrate - * only one hugepage pointed to by hpage, so we need not - * run through the pagelist here. - */ - putback_active_hugepage(hpage); + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); if (ret > 0) ret = -EIO; } else { diff --git a/mm/memory.c b/mm/memory.c index 76dcee317714..9ac55172aa7b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1127,6 +1127,7 @@ again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; @@ -2662,40 +2663,6 @@ out_release: } /* - * This is like a special single-page "expand_{down|up}wards()", - * except we must first make sure that 'address{-|+}PAGE_SIZE' - * doesn't hit another vma. - */ -static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address) -{ - address &= PAGE_MASK; - if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) { - struct vm_area_struct *prev = vma->vm_prev; - - /* - * Is there a mapping abutting this one below? - * - * That's only ok if it's the same stack mapping - * that has gotten split.. - */ - if (prev && prev->vm_end == address) - return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - - return expand_downwards(vma, address - PAGE_SIZE); - } - if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { - struct vm_area_struct *next = vma->vm_next; - - /* As VM_GROWSDOWN but s/below/above/ */ - if (next && next->vm_start == address + PAGE_SIZE) - return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - - return expand_upwards(vma, address + PAGE_SIZE); - } - return 0; -} - -/* * We enter with non-exclusive mmap_sem (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. @@ -2715,10 +2682,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; - /* Check if we need to add a guard page to the stack */ - if (check_stack_guard_page(vma, address) < 0) - return VM_FAULT_SIGSEGV; - /* Use the zero-page for reads */ if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(address), diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a042a9d537bb..a18923e4359d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1371,17 +1371,20 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) } /* - * Confirm all pages in a range [start, end) is belongs to the same zone. + * Confirm all pages in a range [start, end) belong to the same zone. + * When true, return its valid [start, end). */ -int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) +int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, + unsigned long *valid_start, unsigned long *valid_end) { unsigned long pfn, sec_end_pfn; + unsigned long start, end; struct zone *zone = NULL; struct page *page; int i; - for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn); + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1); pfn < end_pfn; - pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) { + pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) { /* Make sure the memory section is present first */ if (!present_section_nr(pfn_to_section_nr(pfn))) continue; @@ -1397,10 +1400,20 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; + if (!zone) + start = pfn + i; zone = page_zone(page); + end = pfn + MAX_ORDER_NR_PAGES; } } - return 1; + + if (zone) { + *valid_start = start; + *valid_end = end; + return 1; + } else { + return 0; + } } /* @@ -1718,6 +1731,7 @@ static int __ref __offline_pages(unsigned long start_pfn, long offlined_pages; int ret, drain, retry_max, node; unsigned long flags; + unsigned long valid_start, valid_end; struct zone *zone; struct memory_notify arg; @@ -1728,10 +1742,10 @@ static int __ref __offline_pages(unsigned long start_pfn, return -EINVAL; /* This makes hotplug much easier...and readable. we assume this for now. .*/ - if (!test_pages_in_a_zone(start_pfn, end_pfn)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) return -EINVAL; - zone = page_zone(pfn_to_page(start_pfn)); + zone = page_zone(pfn_to_page(valid_start)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f20eb4e8c4cc..177668a9c267 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -895,11 +895,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, *policy |= (pol->flags & MPOL_MODE_FLAGS); } - if (vma) { - up_read(¤t->mm->mmap_sem); - vma = NULL; - } - err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { @@ -1493,7 +1488,6 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); @@ -1502,14 +1496,13 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(bm, nmask, nr_bits); + if (compat_get_bitmap(bm, nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, bm, alloc_size); + if (copy_to_user(nm, bm, alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_set_mempolicy(mode, nm, nr_bits+1); } @@ -1517,7 +1510,6 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; nodemask_t bm; @@ -1526,14 +1518,13 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits); + if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, nodes_addr(bm), alloc_size); + if (copy_to_user(nm, nodes_addr(bm), alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_mbind(start, len, mode, nm, nr_bits+1, flags); } @@ -2007,8 +1998,8 @@ retry_cpuset: nmask = policy_nodemask(gfp, pol); zl = policy_zonelist(gfp, pol, node); - mpol_cond_put(pol); page = __alloc_pages_nodemask(gfp, order, zl, nmask); + mpol_cond_put(pol); out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; diff --git a/mm/mempool.c b/mm/mempool.c index 004d42b1dfaf..7924f4f58a6d 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -135,8 +135,8 @@ static void *remove_element(mempool_t *pool) void *element = pool->elements[--pool->curr_nr]; BUG_ON(pool->curr_nr < 0); - check_element(pool, element); kasan_unpoison_element(pool, element); + check_element(pool, element); return element; } diff --git a/mm/migrate.c b/mm/migrate.c index 72c09dea6526..afedcfab60e2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -38,6 +38,7 @@ #include <linux/balloon_compaction.h> #include <linux/mmu_notifier.h> #include <linux/page_idle.h> +#include <linux/ptrace.h> #include <asm/tlbflush.h> @@ -1483,7 +1484,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, const int __user *, nodes, int __user *, status, int, flags) { - const struct cred *cred = current_cred(), *tcred; struct task_struct *task; struct mm_struct *mm; int err; @@ -1507,14 +1507,9 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, /* * Check if this process has the right to modify the specified - * process. The right exists if the process has administrative - * capabilities, superuser privileges or the same - * userid as the target process. + * process. Use the regular "ptrace_may_access()" checks. */ - tcred = __task_cred(task); - if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) && - !capable(CAP_SYS_NICE)) { + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out; diff --git a/mm/mlock.c b/mm/mlock.c index d843bc9d32dd..206e86b98a03 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -277,7 +277,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) { int i; int nr = pagevec_count(pvec); - int delta_munlocked; + int delta_munlocked = -nr; struct pagevec pvec_putback; int pgrescued = 0; @@ -297,6 +297,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) continue; else __munlock_isolation_failed(page); + } else { + delta_munlocked++; } /* @@ -308,7 +310,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) pagevec_add(&pvec_putback, pvec->pages[i]); pvec->pages[i] = NULL; } - delta_munlocked = -nr + pagevec_count(&pvec_putback); __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); spin_unlock_irq(&zone->lru_lock); diff --git a/mm/mmap.c b/mm/mmap.c index a089cca8d79a..19823fc3dcfa 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -300,6 +300,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; + struct vm_area_struct *next; unsigned long min_brk; bool populate; @@ -344,7 +345,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) } /* Check against existing mmap mappings. */ - if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE)) + next = find_vma(mm, oldbrk); + if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; /* Ok, looks good - let it rip. */ @@ -367,10 +369,22 @@ out: static long vma_compute_subtree_gap(struct vm_area_struct *vma) { - unsigned long max, subtree_gap; - max = vma->vm_start; - if (vma->vm_prev) - max -= vma->vm_prev->vm_end; + unsigned long max, prev_end, subtree_gap; + + /* + * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we + * allow two stack_guard_gaps between them here, and when choosing + * an unmapped area; whereas when expanding we only require one. + * That's a little inconsistent, but keeps the code here simpler. + */ + max = vm_start_gap(vma); + if (vma->vm_prev) { + prev_end = vm_end_gap(vma->vm_prev); + if (max > prev_end) + max -= prev_end; + else + max = 0; + } if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; @@ -463,7 +477,7 @@ static void validate_mm(struct mm_struct *mm) anon_vma_unlock_read(anon_vma); } - highest_address = vma->vm_end; + highest_address = vm_end_gap(vma); vma = vma->vm_next; i++; } @@ -632,7 +646,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_next) vma_gap_update(vma->vm_next); else - mm->highest_vm_end = vma->vm_end; + mm->highest_vm_end = vm_end_gap(vma); /* * vma->vm_prev wasn't known when we followed the rbtree to find the @@ -878,7 +892,7 @@ again: remove_next = 1 + (end > next->vm_end); vma_gap_update(vma); if (end_changed) { if (!next) - mm->highest_vm_end = end; + mm->highest_vm_end = vm_end_gap(vma); else if (!adjust_next) vma_gap_update(next); } @@ -921,7 +935,7 @@ again: remove_next = 1 + (end > next->vm_end); else if (next) vma_gap_update(next); else - mm->highest_vm_end = end; + VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); } if (insert && file) uprobe_mmap(insert); @@ -1762,7 +1776,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) while (true) { /* Visit left subtree if it looks promising */ - gap_end = vma->vm_start; + gap_end = vm_start_gap(vma); if (gap_end >= low_limit && vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, @@ -1773,12 +1787,13 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) } } - gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) return -ENOMEM; - if (gap_end >= low_limit && gap_end - gap_start >= length) + if (gap_end >= low_limit && + gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit right subtree if it looks promising */ @@ -1800,8 +1815,8 @@ check_current: vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_left) { - gap_start = vma->vm_prev->vm_end; - gap_end = vma->vm_start; + gap_start = vm_end_gap(vma->vm_prev); + gap_end = vm_start_gap(vma); goto check_current; } } @@ -1865,7 +1880,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) while (true) { /* Visit right subtree if it looks promising */ - gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; if (gap_start <= high_limit && vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, @@ -1878,10 +1893,11 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) check_current: /* Check if current node has a suitable gap */ - gap_end = vma->vm_start; + gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; - if (gap_start <= high_limit && gap_end - gap_start >= length) + if (gap_start <= high_limit && + gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit left subtree if it looks promising */ @@ -1904,7 +1920,7 @@ check_current: struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_right) { gap_start = vma->vm_prev ? - vma->vm_prev->vm_end : 0; + vm_end_gap(vma->vm_prev) : 0; goto check_current; } } @@ -1942,7 +1958,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; if (len > TASK_SIZE - mmap_min_addr) @@ -1953,9 +1969,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (addr) { addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } @@ -1978,7 +1995,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info; @@ -1993,9 +2010,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } @@ -2120,21 +2138,19 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr, * update accounting. This is shared with both the * grow-up and grow-down cases. */ -static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) +static int acct_stack_growth(struct vm_area_struct *vma, + unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; - unsigned long new_start, actual_size; + unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, grow)) return -ENOMEM; /* Stack limit test */ - actual_size = size; - if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) - actual_size -= PAGE_SIZE; - if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2172,16 +2188,32 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *next; + unsigned long gap_addr; int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* Guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else + /* Guard against exceeding limits of the address space. */ + address &= PAGE_MASK; + if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; + address += PAGE_SIZE; + + /* Enforce stack_guard_gap */ + gap_addr = address + stack_guard_gap; + + /* Guard against overflow */ + if (gap_addr < address || gap_addr > TASK_SIZE) + gap_addr = TASK_SIZE; + + next = vma->vm_next; + if (next && next->vm_start < gap_addr) { + if (!(next->vm_flags & VM_GROWSUP)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) @@ -2227,7 +2259,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (vma->vm_next) vma_gap_update(vma->vm_next); else - mm->highest_vm_end = address; + mm->highest_vm_end = vm_end_gap(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); @@ -2248,6 +2280,8 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *prev; + unsigned long gap_addr; int error; address &= PAGE_MASK; @@ -2255,6 +2289,17 @@ int expand_downwards(struct vm_area_struct *vma, if (error) return error; + /* Enforce stack_guard_gap */ + gap_addr = address - stack_guard_gap; + if (gap_addr > address) + return -ENOMEM; + prev = vma->vm_prev; + if (prev && prev->vm_end > gap_addr) { + if (!(prev->vm_flags & VM_GROWSDOWN)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; @@ -2310,28 +2355,25 @@ int expand_downwards(struct vm_area_struct *vma, return error; } -/* - * Note how expand_stack() refuses to expand the stack all the way to - * abut the next virtual mapping, *unless* that mapping itself is also - * a stack mapping. We want to leave room for a guard page, after all - * (the guard page itself is not added here, that is done by the - * actual page faulting logic) - * - * This matches the behavior of the guard page logic (see mm/memory.c: - * check_stack_guard_page()), which only allows the guard page to be - * removed under these circumstances. - */ +/* enforced gap between the expanding stack and other mappings. */ +unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; + +static int __init cmdline_parse_stack_guard_gap(char *p) +{ + unsigned long val; + char *endptr; + + val = simple_strtoul(p, &endptr, 10); + if (!*endptr) + stack_guard_gap = val << PAGE_SHIFT; + + return 0; +} +__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); + #ifdef CONFIG_STACK_GROWSUP int expand_stack(struct vm_area_struct *vma, unsigned long address) { - struct vm_area_struct *next; - - address &= PAGE_MASK; - next = vma->vm_next; - if (next && next->vm_start == address + PAGE_SIZE) { - if (!(next->vm_flags & VM_GROWSUP)) - return -ENOMEM; - } return expand_upwards(vma, address); } @@ -2353,14 +2395,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) #else int expand_stack(struct vm_area_struct *vma, unsigned long address) { - struct vm_area_struct *prev; - - address &= PAGE_MASK; - prev = vma->vm_prev; - if (prev && prev->vm_end == address) { - if (!(prev->vm_flags & VM_GROWSDOWN)) - return -ENOMEM; - } return expand_downwards(vma, address); } @@ -2458,7 +2492,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, vma->vm_prev = prev; vma_gap_update(vma); } else - mm->highest_vm_end = prev ? prev->vm_end : 0; + mm->highest_vm_end = prev ? vm_end_gap(prev) : 0; tail_vma->vm_next = NULL; /* Kill the cache */ diff --git a/mm/mprotect.c b/mm/mprotect.c index bddb2c75492d..b8849a3930a0 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -72,6 +72,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (!pte) return 0; + flush_tlb_batched_pending(vma->vm_mm); arch_enter_lazy_mmu_mode(); do { oldpte = *pte; diff --git a/mm/mremap.c b/mm/mremap.c index c25bc6268e46..fe7b7f65f4f4 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -135,6 +135,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_ptl = pte_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + flush_tlb_batched_pending(vma->vm_mm); arch_enter_lazy_mmu_mode(); for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 45e79be95e8d..4ae77db917f2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -274,6 +274,26 @@ int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT static inline void reset_deferred_meminit(pg_data_t *pgdat) { + unsigned long max_initialise; + unsigned long reserved_lowmem; + + /* + * Initialise at least 2G of a node but also take into account that + * two large system hashes that can take up 1GB for 0.25TB/node. + */ + max_initialise = max(2UL << (30 - PAGE_SHIFT), + (pgdat->node_spanned_pages >> 8)); + + /* + * Compensate the all the memblock reservations (e.g. crash kernel) + * from the initial estimation to make sure we will initialize enough + * memory to boot. + */ + reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn, + pgdat->node_start_pfn + max_initialise); + max_initialise += reserved_lowmem; + + pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages); pgdat->first_deferred_pfn = ULONG_MAX; } @@ -307,10 +327,9 @@ static inline bool update_defer_init(pg_data_t *pgdat, /* Always populate low zones for address-contrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; - /* Initialise at least 2G of the highest zone */ (*nr_initialised)++; - if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) && + if ((*nr_initialised > pgdat->static_init_size) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { pgdat->first_deferred_pfn = pfn; return false; @@ -1513,14 +1532,14 @@ int move_freepages(struct zone *zone, #endif for (page = start_page; page <= end_page;) { - /* Make sure we are not inadvertently changing nodes */ - VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); - if (!pfn_valid_within(page_to_pfn(page))) { page++; continue; } + /* Make sure we are not inadvertently changing nodes */ + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); + if (!PageBuddy(page)) { page++; continue; @@ -2472,7 +2491,7 @@ static bool zone_local(struct zone *local_zone, struct zone *zone) static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { - return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) < + return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= RECLAIM_DISTANCE; } #else /* CONFIG_NUMA */ @@ -5348,7 +5367,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* pg_data_t should be reset to zero when it's allocated */ WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); - reset_deferred_meminit(pgdat); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -5367,6 +5385,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, (unsigned long)pgdat->node_mem_map); #endif + reset_deferred_meminit(pgdat); free_area_init_core(pgdat); } @@ -5833,8 +5852,8 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s) } if (pages && s) - pr_info("Freeing %s memory: %ldK (%p - %p)\n", - s, pages << (PAGE_SHIFT - 10), start, end); + pr_info("Freeing %s memory: %ldK\n", + s, pages << (PAGE_SHIFT - 10)); return pages; } @@ -6788,7 +6807,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, /* Make sure the range is really isolated. */ if (test_pages_isolated(outer_start, end, false)) { - pr_info("%s: [%lx, %lx) PFNs busy\n", + pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n", __func__, outer_start, end); ret = -EBUSY; goto done; diff --git a/mm/percpu.c b/mm/percpu.c index 1f376bce413c..ef6353f0adbd 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1012,8 +1012,11 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (chunk != pcpu_reserved_chunk) + if (chunk != pcpu_reserved_chunk) { + spin_lock_irqsave(&pcpu_lock, flags); pcpu_nr_empty_pop_pages -= occ_pages; + spin_unlock_irqrestore(&pcpu_lock, flags); + } if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); diff --git a/mm/rmap.c b/mm/rmap.c index b577fbb98d4b..ede183c32f45 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -649,6 +649,13 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, tlb_ubc->flush_required = true; /* + * Ensure compiler does not re-order the setting of tlb_flush_batched + * before the PTE is cleared. + */ + barrier(); + mm->tlb_flush_batched = true; + + /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. @@ -675,6 +682,35 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) return should_defer; } + +/* + * Reclaim unmaps pages under the PTL but do not flush the TLB prior to + * releasing the PTL if TLB flushes are batched. It's possible for a parallel + * operation such as mprotect or munmap to race between reclaim unmapping + * the page and flushing the page. If this race occurs, it potentially allows + * access to data via a stale TLB entry. Tracking all mm's that have TLB + * batching in flight would be expensive during reclaim so instead track + * whether TLB batching occurred in the past and if so then do a flush here + * if required. This will cost one additional flush per reclaim cycle paid + * by the first operation at risk such as mprotect and mumap. + * + * This must be called under the PTL so that an access to tlb_flush_batched + * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise + * via the PTL. + */ +void flush_tlb_batched_pending(struct mm_struct *mm) +{ + if (mm->tlb_flush_batched) { + flush_tlb_mm(mm); + + /* + * Do not allow the compiler to re-order the clearing of + * tlb_flush_batched before the tlb is flushed. + */ + barrier(); + mm->tlb_flush_batched = false; + } +} #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, struct page *page, bool writable) diff --git a/mm/slab.c b/mm/slab.c index 24a615d42d74..462938fc7cb9 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1670,6 +1670,14 @@ static void kmem_rcu_free(struct rcu_head *head) } #if DEBUG +static bool is_debug_pagealloc_cache(struct kmem_cache *cachep) +{ + if (debug_pagealloc_enabled() && OFF_SLAB(cachep) && + (cachep->size % PAGE_SIZE) == 0) + return true; + + return false; +} #ifdef CONFIG_DEBUG_PAGEALLOC static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, @@ -1703,6 +1711,23 @@ static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, } *addr++ = 0x87654321; } + +static void slab_kernel_map(struct kmem_cache *cachep, void *objp, + int map, unsigned long caller) +{ + if (!is_debug_pagealloc_cache(cachep)) + return; + + if (caller) + store_stackinfo(cachep, objp, caller); + + kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map); +} + +#else +static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp, + int map, unsigned long caller) {} + #endif static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) @@ -1781,6 +1806,9 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) int size, i; int lines = 0; + if (is_debug_pagealloc_cache(cachep)) + return; + realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; @@ -1846,16 +1874,8 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, void *objp = index_to_obj(cachep, page, i); if (cachep->flags & SLAB_POISON) { -#ifdef CONFIG_DEBUG_PAGEALLOC - if (cachep->size % PAGE_SIZE == 0 && - OFF_SLAB(cachep)) - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 1); - else - check_poison_obj(cachep, objp); -#else check_poison_obj(cachep, objp); -#endif + slab_kernel_map(cachep, objp, 1, 0); } if (cachep->flags & SLAB_RED_ZONE) { if (*dbg_redzone1(cachep, objp) != RED_INACTIVE) @@ -2179,7 +2199,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) else size += BYTES_PER_WORD; } -#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) /* * To activate debug pagealloc, off-slab management is necessary * requirement. In early phase of initialization, small sized slab @@ -2187,14 +2206,14 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) * to check size >= 256. It guarantees that all necessary small * sized slab is initialized in current slab initialization sequence. */ - if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) && + if (debug_pagealloc_enabled() && (flags & SLAB_POISON) && + !slab_early_init && size >= kmalloc_size(INDEX_NODE) && size >= 256 && cachep->object_size > cache_line_size() && ALIGN(size, cachep->align) < PAGE_SIZE) { cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align); size = PAGE_SIZE; } #endif -#endif /* * Determine if the slab management is 'on' or 'off' slab. @@ -2237,15 +2256,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) if (flags & CFLGS_OFF_SLAB) { /* really off slab. No need for manual alignment */ freelist_size = calculate_freelist_size(cachep->num, 0); - -#ifdef CONFIG_PAGE_POISONING - /* If we're going to use the generic kernel_map_pages() - * poisoning, then it's going to smash the contents of - * the redzone and userword anyhow, so switch them off. - */ - if (size % PAGE_SIZE == 0 && flags & SLAB_POISON) - flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); -#endif } cachep->colour_off = cache_line_size(); @@ -2261,7 +2271,19 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) cachep->size = size; cachep->reciprocal_buffer_size = reciprocal_value(size); - if (flags & CFLGS_OFF_SLAB) { +#if DEBUG + /* + * If we're going to use the generic kernel_map_pages() + * poisoning, then it's going to smash the contents of + * the redzone and userword anyhow, so switch them off. + */ + if (IS_ENABLED(CONFIG_PAGE_POISONING) && + (cachep->flags & SLAB_POISON) && + is_debug_pagealloc_cache(cachep)) + cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); +#endif + + if (OFF_SLAB(cachep)) { cachep->freelist_cache = kmalloc_slab(freelist_size, 0u); /* * This is a possibility for one of the kmalloc_{dma,}_caches. @@ -2488,9 +2510,6 @@ static void cache_init_objs(struct kmem_cache *cachep, for (i = 0; i < cachep->num; i++) { void *objp = index_to_obj(cachep, page, i); #if DEBUG - /* need to poison the objs? */ - if (cachep->flags & SLAB_POISON) - poison_obj(cachep, objp, POISON_FREE); if (cachep->flags & SLAB_STORE_USER) *dbg_userword(cachep, objp) = NULL; @@ -2514,10 +2533,11 @@ static void cache_init_objs(struct kmem_cache *cachep, slab_error(cachep, "constructor overwrote the" " start of an object"); } - if ((cachep->size % PAGE_SIZE) == 0 && - OFF_SLAB(cachep) && cachep->flags & SLAB_POISON) - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 0); + /* need to poison the objs? */ + if (cachep->flags & SLAB_POISON) { + poison_obj(cachep, objp, POISON_FREE); + slab_kernel_map(cachep, objp, 0, 0); + } #else if (cachep->ctor) cachep->ctor(objp); @@ -2736,17 +2756,8 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, set_obj_status(page, objnr, OBJECT_FREE); if (cachep->flags & SLAB_POISON) { -#ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { - store_stackinfo(cachep, objp, caller); - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 0); - } else { - poison_obj(cachep, objp, POISON_FREE); - } -#else poison_obj(cachep, objp, POISON_FREE); -#endif + slab_kernel_map(cachep, objp, 0, caller); } return objp; } @@ -2873,15 +2884,8 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, if (!objp) return objp; if (cachep->flags & SLAB_POISON) { -#ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 1); - else - check_poison_obj(cachep, objp); -#else check_poison_obj(cachep, objp); -#endif + slab_kernel_map(cachep, objp, 1, 0); poison_obj(cachep, objp, POISON_INUSE); } if (cachep->flags & SLAB_STORE_USER) diff --git a/mm/slub.c b/mm/slub.c index 41f7cae64a49..d6fe997c0577 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5343,6 +5343,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) char mbuf[64]; char *buf; struct slab_attribute *attr = to_slab_attr(slab_attrs[i]); + ssize_t len; if (!attr || !attr->store || !attr->show) continue; @@ -5367,8 +5368,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) buf = buffer; } - attr->show(root_cache, buf); - attr->store(s, buf, strlen(buf)); + len = attr->show(root_cache, buf); + if (len > 0) + attr->store(s, buf, len); } if (buffer) diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index b5f7f24b8dd1..09f733b0424a 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -48,6 +48,9 @@ static int swap_cgroup_prepare(int type) if (!page) goto not_enough_page; ctrl->map[idx] = page; + + if (!(idx % SWAP_CLUSTER_MAX)) + cond_resched(); } return 0; not_enough_page: @@ -202,6 +205,8 @@ void swap_cgroup_swapoff(int type) struct page *page = map[i]; if (page) __free_page(page); + if (!(i % SWAP_CLUSTER_MAX)) + cond_resched(); } vfree(map); } diff --git a/mm/truncate.c b/mm/truncate.c index 76e35ad97102..f4c8270f7b84 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -732,7 +732,7 @@ EXPORT_SYMBOL(truncate_setsize); */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { - int bsize = 1 << inode->i_blkbits; + int bsize = i_blocksize(inode); loff_t rounded_from; struct page *page; pgoff_t index; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index c5afd573d7da..3fb15c25af87 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -112,9 +112,16 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long reclaimed) { unsigned long scale = scanned + reclaimed; - unsigned long pressure; + unsigned long pressure = 0; /* + * reclaimed can be greater than scanned in cases + * like THP, where the scanned is 1 and reclaimed + * could be 512 + */ + if (reclaimed >= scanned) + goto out; + /* * We calculate the ratio (in percents) of how many pages were * scanned vs. reclaimed in a given time frame (window). Note that * time is in VM reclaimer's "ticks", i.e. number of pages @@ -124,6 +131,7 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, pressure = scale - (reclaimed * scale / scanned); pressure = pressure * 100 / scale; +out: pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, scanned, reclaimed); diff --git a/mm/vmscan.c b/mm/vmscan.c index bfc5050cbd01..440c2df9be82 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2529,7 +2529,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) if (!populated_zone(zone)) continue; - classzone_idx = requested_highidx; + classzone_idx = gfp_zone(sc->gfp_mask); while (!populated_zone(zone->zone_pgdat->node_zones + classzone_idx)) classzone_idx--; diff --git a/mm/zswap.c b/mm/zswap.c index 340261946fda..45476f429789 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -78,7 +78,13 @@ static u64 zswap_duplicate_entry; /* Enable/disable zswap (disabled by default) */ static bool zswap_enabled; -module_param_named(enabled, zswap_enabled, bool, 0644); +static int zswap_enabled_param_set(const char *, + const struct kernel_param *); +static struct kernel_param_ops zswap_enabled_param_ops = { + .set = zswap_enabled_param_set, + .get = param_get_bool, +}; +module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644); /* Crypto compressor to use */ #define ZSWAP_COMPRESSOR_DEFAULT "lzo" @@ -176,6 +182,9 @@ static atomic_t zswap_pools_count = ATOMIC_INIT(0); /* used by param callback function */ static bool zswap_init_started; +/* fatal error during init */ +static bool zswap_init_failed; + /********************************* * helpers and fwd declarations **********************************/ @@ -702,6 +711,11 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, char *s = strstrip((char *)val); int ret; + if (zswap_init_failed) { + pr_err("can't set param, initialization failed\n"); + return -ENODEV; + } + /* no change required */ if (!strcmp(s, *(char **)kp->arg)) return 0; @@ -781,6 +795,17 @@ static int zswap_zpool_param_set(const char *val, return __zswap_param_set(val, kp, NULL, zswap_compressor); } +static int zswap_enabled_param_set(const char *val, + const struct kernel_param *kp) +{ + if (zswap_init_failed) { + pr_err("can't enable, initialization failed\n"); + return -ENODEV; + } + + return param_set_bool(val, kp); +} + /********************************* * writeback code **********************************/ @@ -1267,6 +1292,9 @@ pool_fail: dstmem_fail: zswap_entry_cache_destroy(); cache_fail: + /* if built-in, we aren't unloaded on failure; don't allow use */ + zswap_init_failed = true; + zswap_enabled = false; return -ENOMEM; } /* must be late so crypto has time to come up */ diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index ad8d6e6b87ca..5e4199d5a388 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -278,7 +278,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) return 0; out_free_newdev: - free_netdev(new_dev); + if (new_dev->reg_state == NETREG_UNINITIALIZED) + free_netdev(new_dev); return err; } @@ -291,6 +292,10 @@ static void vlan_sync_address(struct net_device *dev, if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; + /* vlan continues to inherit address of lower device */ + if (vlan_dev_inherit_address(vlandev, dev)) + goto out; + /* vlan address was different from the old address and is equal to * the new address */ if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && @@ -303,6 +308,7 @@ static void vlan_sync_address(struct net_device *dev, !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); +out: ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 9d010a09ab98..cc1557978066 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -109,6 +109,8 @@ int vlan_check_real_dev(struct net_device *real_dev, void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); +bool vlan_dev_inherit_address(struct net_device *dev, + struct net_device *real_dev); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index fded86508117..ca4dc9031073 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -244,6 +244,17 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result) strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23); } +bool vlan_dev_inherit_address(struct net_device *dev, + struct net_device *real_dev) +{ + if (dev->addr_assign_type != NET_ADDR_STOLEN) + return false; + + ether_addr_copy(dev->dev_addr, real_dev->dev_addr); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return true; +} + static int vlan_dev_open(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); @@ -254,7 +265,8 @@ static int vlan_dev_open(struct net_device *dev) !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; - if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) { + if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) && + !vlan_dev_inherit_address(dev, real_dev)) { err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) goto out; @@ -558,8 +570,10 @@ static int vlan_dev_init(struct net_device *dev) /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; - if (is_zero_ether_addr(dev->dev_addr)) - eth_hw_addr_inherit(dev, real_dev); + if (is_zero_ether_addr(dev->dev_addr)) { + ether_addr_copy(dev->dev_addr, real_dev->dev_addr); + dev->addr_assign_type = NET_ADDR_STOLEN; + } if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); diff --git a/net/9p/client.c b/net/9p/client.c index ea79ee9a7348..f5feac4ff4ec 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -2101,6 +2101,10 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } + if (rsize < count) { + pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize); + count = rsize; + } p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index 655a7d4c96e1..983f0b5e14f1 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -264,7 +264,7 @@ void ax25_disconnect(ax25_cb *ax25, int reason) { ax25_clear_queues(ax25); - if (!sock_flag(ax25->sk, SOCK_DESTROY)) + if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY)) ax25_stop_heartbeat(ax25); ax25_stop_t1timer(ax25); ax25_stop_t2timer(ax25); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index b1eb8c09a660..c842f40c1173 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1164,7 +1164,8 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_NOSIGNAL|MSG_ERRQUEUE)) + if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_NOSIGNAL|MSG_ERRQUEUE| + MSG_CMSG_COMPAT)) return -EINVAL; if (len < 4 || len > HCI_MAX_FRAME_SIZE) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 4b175df35184..906f88550cd8 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -23,6 +23,7 @@ #include <linux/debugfs.h> #include <linux/crypto.h> #include <linux/scatterlist.h> +#include <crypto/algapi.h> #include <crypto/b128ops.h> #include <net/bluetooth/bluetooth.h> @@ -524,7 +525,7 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16], if (err) return false; - return !memcmp(bdaddr->b, hash, 3); + return !crypto_memneq(bdaddr->b, hash, 3); } int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa) @@ -577,7 +578,7 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) /* This is unlikely, but we need to check that * we didn't accidentially generate a debug key. */ - if (memcmp(smp->local_sk, debug_sk, 32)) + if (crypto_memneq(smp->local_sk, debug_sk, 32)) break; } smp->debug_key = false; @@ -991,7 +992,7 @@ static u8 smp_random(struct smp_chan *smp) if (ret) return SMP_UNSPECIFIED; - if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) { + if (crypto_memneq(smp->pcnf, confirm, sizeof(smp->pcnf))) { BT_ERR("Pairing failed (confirmation values mismatch)"); return SMP_CONFIRM_FAILED; } @@ -1491,7 +1492,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) smp->rrnd, r, cfm)) return SMP_UNSPECIFIED; - if (memcmp(smp->pcnf, cfm, 16)) + if (crypto_memneq(smp->pcnf, cfm, 16)) return SMP_CONFIRM_FAILED; smp->passkey_round++; @@ -1875,7 +1876,7 @@ static u8 sc_send_public_key(struct smp_chan *smp) /* This is unlikely, but we need to check that * we didn't accidentially generate a debug key. */ - if (memcmp(smp->local_sk, debug_sk, 32)) + if (crypto_memneq(smp->local_sk, debug_sk, 32)) break; } } @@ -2140,7 +2141,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (err) return SMP_UNSPECIFIED; - if (memcmp(smp->pcnf, cfm, 16)) + if (crypto_memneq(smp->pcnf, cfm, 16)) return SMP_CONFIRM_FAILED; } else { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), @@ -2621,7 +2622,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) if (err) return SMP_UNSPECIFIED; - if (memcmp(cfm.confirm_val, smp->pcnf, 16)) + if (crypto_memneq(cfm.confirm_val, smp->pcnf, 16)) return SMP_CONFIRM_FAILED; } @@ -2654,7 +2655,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) else hcon->pending_sec_level = BT_SECURITY_FIPS; - if (!memcmp(debug_pk, smp->remote_pk, 64)) + if (!crypto_memneq(debug_pk, smp->remote_pk, 64)) set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags); if (smp->method == DSP_PASSKEY) { @@ -2753,7 +2754,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (err) return SMP_UNSPECIFIED; - if (memcmp(check->e, e, 16)) + if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED; if (!hcon->out) { @@ -3463,7 +3464,7 @@ static int __init test_ah(struct crypto_blkcipher *tfm_aes) if (err) return err; - if (memcmp(res, exp, 3)) + if (crypto_memneq(res, exp, 3)) return -EINVAL; return 0; @@ -3493,7 +3494,7 @@ static int __init test_c1(struct crypto_blkcipher *tfm_aes) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3518,7 +3519,7 @@ static int __init test_s1(struct crypto_blkcipher *tfm_aes) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3550,7 +3551,7 @@ static int __init test_f4(struct crypto_hash *tfm_cmac) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3584,10 +3585,10 @@ static int __init test_f5(struct crypto_hash *tfm_cmac) if (err) return err; - if (memcmp(mackey, exp_mackey, 16)) + if (crypto_memneq(mackey, exp_mackey, 16)) return -EINVAL; - if (memcmp(ltk, exp_ltk, 16)) + if (crypto_memneq(ltk, exp_ltk, 16)) return -EINVAL; return 0; @@ -3620,7 +3621,7 @@ static int __init test_f6(struct crypto_hash *tfm_cmac) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; @@ -3674,7 +3675,7 @@ static int __init test_h6(struct crypto_hash *tfm_cmac) if (err) return err; - if (memcmp(res, exp, 16)) + if (crypto_memneq(res, exp, 16)) return -EINVAL; return 0; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f7fba74108a9..e24754a0e052 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -29,6 +29,7 @@ EXPORT_SYMBOL(br_should_route_hook); static int br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { + br_drop_fake_rtable(skb); return netif_receive_skb(skb); } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 7ddbe7ec81d6..97fc19f001bf 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -516,21 +516,6 @@ static unsigned int br_nf_pre_routing(void *priv, } -/* PF_BRIDGE/LOCAL_IN ************************************************/ -/* The packet is locally destined, which requires a real - * dst_entry, so detach the fake one. On the way up, the - * packet would pass through PRE_ROUTING again (which already - * took place when the packet entered the bridge), but we - * register an IPv4 PRE_ROUTING 'sabotage' hook that will - * prevent this from happening. */ -static unsigned int br_nf_local_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - br_drop_fake_rtable(skb); - return NF_ACCEPT; -} - /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -901,12 +886,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { .priority = NF_BR_PRI_BRNF, }, { - .hook = br_nf_local_in, - .pf = NFPROTO_BRIDGE, - .hooknum = NF_BR_LOCAL_IN, - .priority = NF_BR_PRI_BRNF, - }, - { .hook = br_nf_forward_ip, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 40197ff8918a..ff8bb41d713f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -768,23 +768,16 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return -EPROTONOSUPPORT; } } -#endif - return 0; -} - -static int br_dev_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) -{ - struct net_bridge *br = netdev_priv(dev); + if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { + __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); - if (tb[IFLA_ADDRESS]) { - spin_lock_bh(&br->lock); - br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); - spin_unlock_bh(&br->lock); + if (defpvid >= VLAN_VID_MASK) + return -EINVAL; } +#endif - return register_netdevice(dev); + return 0; } static int br_port_slave_changelink(struct net_device *brdev, @@ -1068,6 +1061,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return 0; } +static int br_dev_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_bridge *br = netdev_priv(dev); + int err; + + if (tb[IFLA_ADDRESS]) { + spin_lock_bh(&br->lock); + br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); + spin_unlock_bh(&br->lock); + } + + err = br_changelink(dev, tb, data); + if (err) + return err; + + return register_netdevice(dev); +} + static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 8a7ada8bb947..bcb4559e735d 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -166,6 +166,8 @@ static void br_stp_start(struct net_bridge *br) br_debug(br, "using kernel STP\n"); /* To start timers on any ports left in blocking */ + if (br->dev->flags & IFF_UP) + mod_timer(&br->hello_timer, jiffies + br->hello_time); br_port_state_selection(br); } diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 5f0f5af0ec35..7dbe6a5c31eb 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -40,7 +40,7 @@ static void br_hello_timer_expired(unsigned long arg) if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); - if (br->stp_enabled != BR_USER_STP) + if (br->stp_enabled == BR_KERNEL_STP) mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time)); } diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index 59ce1fcc220c..71b6ab240dea 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -81,11 +81,7 @@ static struct cfpkt *cfpkt_create_pfx(u16 len, u16 pfx) { struct sk_buff *skb; - if (likely(in_interrupt())) - skb = alloc_skb(len + pfx, GFP_ATOMIC); - else - skb = alloc_skb(len + pfx, GFP_KERNEL); - + skb = alloc_skb(len + pfx, GFP_ATOMIC); if (unlikely(skb == NULL)) return NULL; diff --git a/net/can/af_can.c b/net/can/af_can.c index 166d436196c1..928f58064098 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -445,6 +445,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, * @func: callback function on filter match * @data: returned parameter for callback function * @ident: string for calling module identification + * @sk: socket pointer (might be NULL) * * Description: * Invokes the callback function with the received sk_buff and the given @@ -468,7 +469,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, */ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, void (*func)(struct sk_buff *, void *), void *data, - char *ident) + char *ident, struct sock *sk) { struct receiver *r; struct hlist_head *rl; @@ -496,6 +497,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, r->func = func; r->data = data; r->ident = ident; + r->sk = sk; hlist_add_head_rcu(&r->list, rl); d->entries++; @@ -520,8 +522,11 @@ EXPORT_SYMBOL(can_rx_register); static void can_rx_delete_receiver(struct rcu_head *rp) { struct receiver *r = container_of(rp, struct receiver, rcu); + struct sock *sk = r->sk; kmem_cache_free(rcv_cache, r); + if (sk) + sock_put(sk); } /** @@ -596,8 +601,11 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, spin_unlock(&can_rcvlists_lock); /* schedule the receiver item for deletion */ - if (r) + if (r) { + if (r->sk) + sock_hold(r->sk); call_rcu(&r->rcu, can_rx_delete_receiver); + } } EXPORT_SYMBOL(can_rx_unregister); diff --git a/net/can/af_can.h b/net/can/af_can.h index fca0fe9fc45a..b86f5129e838 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -50,13 +50,14 @@ struct receiver { struct hlist_node list; - struct rcu_head rcu; canid_t can_id; canid_t mask; unsigned long matches; void (*func)(struct sk_buff *, void *); void *data; char *ident; + struct sock *sk; + struct rcu_head rcu; }; #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) diff --git a/net/can/bcm.c b/net/can/bcm.c index 8ef1afacad82..4ccfd356baed 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -710,14 +710,23 @@ static struct bcm_op *bcm_find_op(struct list_head *ops, canid_t can_id, static void bcm_remove_op(struct bcm_op *op) { - hrtimer_cancel(&op->timer); - hrtimer_cancel(&op->thrtimer); - - if (op->tsklet.func) - tasklet_kill(&op->tsklet); + if (op->tsklet.func) { + while (test_bit(TASKLET_STATE_SCHED, &op->tsklet.state) || + test_bit(TASKLET_STATE_RUN, &op->tsklet.state) || + hrtimer_active(&op->timer)) { + hrtimer_cancel(&op->timer); + tasklet_kill(&op->tsklet); + } + } - if (op->thrtsklet.func) - tasklet_kill(&op->thrtsklet); + if (op->thrtsklet.func) { + while (test_bit(TASKLET_STATE_SCHED, &op->thrtsklet.state) || + test_bit(TASKLET_STATE_RUN, &op->thrtsklet.state) || + hrtimer_active(&op->thrtimer)) { + hrtimer_cancel(&op->thrtimer); + tasklet_kill(&op->thrtsklet); + } + } if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); @@ -1170,7 +1179,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = can_rx_register(dev, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, - "bcm"); + "bcm", sk); op->rx_reg_dev = dev; dev_put(dev); @@ -1179,7 +1188,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } else err = can_rx_register(NULL, op->can_id, REGMASK(op->can_id), - bcm_rx_handler, op, "bcm"); + bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ list_del(&op->list); diff --git a/net/can/gw.c b/net/can/gw.c index 455168718c2e..77c8af4047ef 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -442,7 +442,7 @@ static inline int cgw_register_filter(struct cgw_job *gwj) { return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, - gwj, "gw"); + gwj, "gw", NULL); } static inline void cgw_unregister_filter(struct cgw_job *gwj) diff --git a/net/can/raw.c b/net/can/raw.c index 56af689ca999..e9403a26a1d5 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -190,7 +190,7 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk, for (i = 0; i < count; i++) { err = can_rx_register(dev, filter[i].can_id, filter[i].can_mask, - raw_rcv, sk, "raw"); + raw_rcv, sk, "raw", sk); if (err) { /* clean up successfully registered filters */ while (--i >= 0) @@ -211,7 +211,7 @@ static int raw_enable_errfilter(struct net_device *dev, struct sock *sk, if (err_mask) err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG, - raw_rcv, sk, "raw"); + raw_rcv, sk, "raw", sk); return err; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b8d927c56494..a6b2f2138c9d 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -7,6 +7,7 @@ #include <linux/kthread.h> #include <linux/net.h> #include <linux/nsproxy.h> +#include <linux/sched.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/string.h> @@ -478,11 +479,16 @@ static int ceph_tcp_connect(struct ceph_connection *con) { struct sockaddr_storage *paddr = &con->peer_addr.in_addr; struct socket *sock; + unsigned int noio_flag; int ret; BUG_ON(con->sock); + + /* sock_create_kern() allocates with GFP_KERNEL */ + noio_flag = memalloc_noio_save(); ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); + memalloc_noio_restore(noio_flag); if (ret) return ret; sock->sk->sk_allocation = GFP_NOFS; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index ddc3573894b0..bc95e48d5cfb 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1265,7 +1265,6 @@ static int decode_new_up_state_weight(void **p, void *end, if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && (xorstate & CEPH_OSD_EXISTS)) { pr_info("osd%d does not exist\n", osd); - map->osd_weight[osd] = CEPH_OSD_IN; ret = set_primary_affinity(map, osd, CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); if (ret) diff --git a/net/core/dev.c b/net/core/dev.c index 6f203c7fb166..24d243084aab 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -182,7 +182,7 @@ EXPORT_SYMBOL(dev_base_lock); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); -static unsigned int napi_gen_id; +static unsigned int napi_gen_id = NR_CPUS; static DEFINE_HASHTABLE(napi_hash, 8); static seqcount_t devnet_rename_seq; @@ -1246,8 +1246,9 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) if (!new_ifalias) return -ENOMEM; dev->ifalias = new_ifalias; + memcpy(dev->ifalias, alias, len); + dev->ifalias[len] = 0; - strlcpy(dev->ifalias, alias, len+1); return len; } @@ -1676,37 +1677,59 @@ EXPORT_SYMBOL_GPL(net_dec_ingress_queue); static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL -/* We are not allowed to call static_key_slow_dec() from irq context - * If net_disable_timestamp() is called from irq context, defer the - * static_key_slow_dec() calls. - */ static atomic_t netstamp_needed_deferred; +static atomic_t netstamp_wanted; +static void netstamp_clear(struct work_struct *work) +{ + int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + int wanted; + + wanted = atomic_add_return(deferred, &netstamp_wanted); + if (wanted > 0) + static_key_enable(&netstamp_needed); + else + static_key_disable(&netstamp_needed); +} +static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + int wanted; - if (deferred) { - while (--deferred) - static_key_slow_dec(&netstamp_needed); - return; + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 0) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted) + return; } -#endif + atomic_inc(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_inc(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - if (in_interrupt()) { - atomic_inc(&netstamp_needed_deferred); - return; + int wanted; + + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 1) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted) + return; } -#endif + atomic_dec(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_dec(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_disable_timestamp); @@ -2527,9 +2550,10 @@ EXPORT_SYMBOL(skb_mac_gso_segment); static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL; - else - return skb->ip_summed == CHECKSUM_NONE; + return skb->ip_summed != CHECKSUM_PARTIAL && + skb->ip_summed != CHECKSUM_UNNECESSARY; + + return skb->ip_summed == CHECKSUM_NONE; } /** @@ -2548,11 +2572,12 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) { + struct sk_buff *segs; + if (unlikely(skb_needs_check(skb, tx_path))) { int err; - skb_warn_bad_offload(skb); - + /* We're going to init ->check field in TCP or UDP header */ err = skb_cow_head(skb, 0); if (err < 0) return ERR_PTR(err); @@ -2567,7 +2592,12 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, skb_reset_mac_header(skb); skb_reset_mac_len(skb); - return skb_mac_gso_segment(skb, features); + segs = skb_mac_gso_segment(skb, features); + + if (unlikely(skb_needs_check(skb, tx_path))) + skb_warn_bad_offload(skb); + + return segs; } EXPORT_SYMBOL(__skb_gso_segment); @@ -2650,9 +2680,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { - features &= ~NETIF_F_SG; } + if (illegal_highdma(skb->dev, skb)) + features &= ~NETIF_F_SG; return features; } @@ -3027,7 +3057,9 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, int queue_index = 0; #ifdef CONFIG_XPS - if (skb->sender_cpu == 0) + u32 sender_cpu = skb->sender_cpu - 1; + + if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif @@ -4350,6 +4382,12 @@ struct packet_offload *gro_find_complete_by_type(__be16 type) } EXPORT_SYMBOL(gro_find_complete_by_type); +static void napi_skb_free_stolen_head(struct sk_buff *skb) +{ + skb_dst_drop(skb); + kmem_cache_free(skbuff_head_cache, skb); +} + static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { @@ -4363,12 +4401,10 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { - skb_dst_drop(skb); - kmem_cache_free(skbuff_head_cache, skb); - } else { + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else __kfree_skb(skb); - } break; case GRO_HELD: @@ -4434,10 +4470,16 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, break; case GRO_DROP: - case GRO_MERGED_FREE: napi_reuse_skb(napi, skb); break; + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else + napi_reuse_skb(napi, skb); + break; + case GRO_MERGED: break; } @@ -4704,25 +4746,22 @@ EXPORT_SYMBOL_GPL(napi_by_id); void napi_hash_add(struct napi_struct *napi) { - if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) { + if (test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) + return; - spin_lock(&napi_hash_lock); + spin_lock(&napi_hash_lock); - /* 0 is not a valid id, we also skip an id that is taken - * we expect both events to be extremely rare - */ - napi->napi_id = 0; - while (!napi->napi_id) { - napi->napi_id = ++napi_gen_id; - if (napi_by_id(napi->napi_id)) - napi->napi_id = 0; - } + /* 0..NR_CPUS+1 range is reserved for sender_cpu use */ + do { + if (unlikely(++napi_gen_id < NR_CPUS + 1)) + napi_gen_id = NR_CPUS + 1; + } while (napi_by_id(napi_gen_id)); + napi->napi_id = napi_gen_id; - hlist_add_head_rcu(&napi->napi_hash_node, - &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); + hlist_add_head_rcu(&napi->napi_hash_node, + &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); - spin_unlock(&napi_hash_lock); - } + spin_unlock(&napi_hash_lock); } EXPORT_SYMBOL_GPL(napi_hash_add); @@ -7030,8 +7069,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } else { netdev_stats_to_stats64(storage, &dev->stats); } - storage->rx_dropped += atomic_long_read(&dev->rx_dropped); - storage->tx_dropped += atomic_long_read(&dev->tx_dropped); + storage->rx_dropped += (unsigned long)atomic_long_read(&dev->rx_dropped); + storage->tx_dropped += (unsigned long)atomic_long_read(&dev->tx_dropped); return storage; } EXPORT_SYMBOL(dev_get_stats); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 183ef95db502..2bded3ecf03d 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; + ifr.ifr_name[IFNAMSIZ-1] = 0; error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex); if (error) diff --git a/net/core/dst.c b/net/core/dst.c index a1656e3b8d72..e72d706f8d0c 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard_out); -const u32 dst_default_metrics[RTAX_MAX + 1] = { +const struct dst_metrics dst_default_metrics = { /* This initializer is needed to force linker to place this variable * into const section. Otherwise it might end into bss section. * We really want to avoid false sharing on this variable, and catch * any writes on it. */ - [RTAX_MAX] = 0xdeadbeef, + .refcnt = ATOMIC_INIT(1), }; void dst_init(struct dst_entry *dst, struct dst_ops *ops, @@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, if (dev) dev_hold(dev); dst->ops = ops; - dst_init_metrics(dst, dst_default_metrics, true); + dst_init_metrics(dst, dst_default_metrics.metrics, true); dst->expires = 0UL; dst->path = dst; dst->from = NULL; @@ -315,25 +315,30 @@ EXPORT_SYMBOL(dst_release); u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) { - u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); + struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC); if (p) { - u32 *old_p = __DST_METRICS_PTR(old); + struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); unsigned long prev, new; - memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + atomic_set(&p->refcnt, 1); + memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); new = (unsigned long) p; prev = cmpxchg(&dst->_metrics, old, new); if (prev != old) { kfree(p); - p = __DST_METRICS_PTR(prev); + p = (struct dst_metrics *)__DST_METRICS_PTR(prev); if (prev & DST_METRICS_READ_ONLY) p = NULL; + } else if (prev & DST_METRICS_REFCOUNTED) { + if (atomic_dec_and_test(&old_p->refcnt)) + kfree(old_p); } } - return p; + BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0); + return (u32 *)p; } EXPORT_SYMBOL(dst_cow_metrics_generic); @@ -342,7 +347,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) { unsigned long prev, new; - new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY; + new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY; prev = cmpxchg(&dst->_metrics, old, new); if (prev == old) kfree(__DST_METRICS_PTR(old)); @@ -457,6 +462,20 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, spin_lock_bh(&dst_garbage.lock); dst = dst_garbage.list; dst_garbage.list = NULL; + /* The code in dst_ifdown places a hold on the loopback device. + * If the gc entry processing is set to expire after a lengthy + * interval, this hold can cause netdev_wait_allrefs() to hang + * out and wait for a long time -- until the the loopback + * interface is released. If we're really unlucky, it'll emit + * pr_emerg messages to console too. Reset the interval here, + * so dst cleanups occur in a more timely fashion. + */ + if (dst_garbage.timer_inc > DST_GC_INC) { + dst_garbage.timer_inc = DST_GC_INC; + dst_garbage.timer_expires = DST_GC_MIN; + mod_delayed_work(system_wq, &dst_gc_work, + dst_garbage.timer_expires); + } spin_unlock_bh(&dst_garbage.lock); if (last) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 29edf74846fc..b6bca625b0d2 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -886,9 +886,12 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = vzalloc(reglen); - if (reglen && !regbuf) - return -ENOMEM; + regbuf = NULL; + if (reglen) { + regbuf = vzalloc(reglen); + if (!regbuf) + return -ENOMEM; + } ops->get_regs(dev, ®s, regbuf); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 769cece9b00b..ae92131c4f89 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -859,7 +859,8 @@ static void neigh_probe(struct neighbour *neigh) if (skb) skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); - neigh->ops->solicit(neigh, skb); + if (neigh->ops->solicit) + neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); kfree_skb(skb); } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 94acfc89ad97..440aa9f6e0a8 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work) while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; struct netdev_queue *txq; + unsigned int q_index; if (!netif_device_present(dev) || !netif_running(dev)) { kfree_skb(skb); continue; } - txq = skb_get_tx_queue(dev, skb); - local_irq_save(flags); + /* check if skb->queue_mapping is still valid */ + q_index = skb_get_queue_mapping(skb); + if (unlikely(q_index >= dev->real_num_tx_queues)) { + q_index = q_index % dev->real_num_tx_queues; + skb_set_queue_mapping(skb, q_index); + } + txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b94e165a4f79..5b3d611d8b5f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -897,6 +897,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ + nla_total_size(4) /* IFLA_LINK_NETNSID */ + + nla_total_size(4) /* IFLA_GROUP */ + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ @@ -1018,7 +1019,7 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) return err; } - if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name)) + if (nla_put_string(skb, IFLA_PHYS_PORT_NAME, name)) return -EMSGSIZE; return 0; @@ -1089,6 +1090,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, struct ifla_vf_mac vf_mac; struct ifla_vf_info ivi; + memset(&ivi, 0, sizeof(ivi)); + /* Not all SR-IOV capable drivers support the * spoofcheck and "RSS query enable" query. Preset to * -1 so the user space tool can detect that the driver @@ -1097,7 +1100,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, ivi.spoofchk = -1; ivi.rss_query_en = -1; ivi.trusted = -1; - memset(ivi.mac, 0, sizeof(ivi.mac)); /* The default value for VF link state is "auto" * IFLA_VF_LINK_STATE_AUTO which equals zero */ @@ -1370,6 +1372,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, + [IFLA_GROUP] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1458,13 +1461,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, 0, NLM_F_MULTI, ext_filter_mask); - /* If we ran out of room on the first message, - * we're in trouble - */ - WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); - if (err < 0) - goto out; + if (err < 0) { + if (likely(skb->len)) + goto out; + + goto out_err; + } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: @@ -1472,10 +1475,12 @@ cont: } } out: + err = skb->len; +out_err: cb->args[1] = idx; cb->args[0] = h; - return skb->len; + return err; } int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len) @@ -1737,7 +1742,8 @@ static int do_setlink(const struct sk_buff *skb, struct sockaddr *sa; int len; - len = sizeof(sa_family_t) + dev->addr_len; + len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len, + sizeof(*sa)); sa = kmalloc(len, GFP_KERNEL); if (!sa) { err = -ENOMEM; @@ -3127,8 +3133,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) err = br_dev->netdev_ops->ndo_bridge_getlink( skb, portid, seq, dev, filter_mask, NLM_F_MULTI); - if (err < 0 && err != -EOPNOTSUPP) - break; + if (err < 0 && err != -EOPNOTSUPP) { + if (likely(skb->len)) + break; + + goto out_err; + } } idx++; } @@ -3139,16 +3149,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) seq, dev, filter_mask, NLM_F_MULTI); - if (err < 0 && err != -EOPNOTSUPP) - break; + if (err < 0 && err != -EOPNOTSUPP) { + if (likely(skb->len)) + break; + + goto out_err; + } } idx++; } } + err = skb->len; +out_err: rcu_read_unlock(); cb->args[0] = idx; - return skb->len; + return err; } static inline size_t bridge_nlmsg_size(void) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4968b5ddea69..73dfd7729bc9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3678,13 +3678,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, if (!skb_may_tx_timestamp(sk, false)) return; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - *skb_hwtstamps(skb) = *hwtstamps; - __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); - - sock_put(sk); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + *skb_hwtstamps(skb) = *hwtstamps; + __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); + sock_put(sk); + } } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); @@ -3735,7 +3736,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; - int err; + int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; @@ -3745,14 +3746,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - err = sock_queue_err_skb(sk, skb); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + err = sock_queue_err_skb(sk, skb); + sock_put(sk); + } if (err) kfree_skb(skb); - - sock_put(sk); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); diff --git a/net/core/sock.c b/net/core/sock.c index f367df38c264..2871364e4420 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1459,6 +1459,11 @@ void sk_destruct(struct sock *sk) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + } + if (sk->sk_peer_cred) put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); @@ -1552,6 +1557,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) is_charged = sk_filter_charge(newsk, filter); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { + /* We need to make sure that we don't uncharge the new + * socket if we couldn't charge it in the first place + * as otherwise we uncharge the parent's filter. + */ + if (!is_charged) + RCU_INIT_POINTER(newsk->sk_filter, NULL); /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; @@ -1679,17 +1690,17 @@ EXPORT_SYMBOL(skb_set_owner_w); void skb_orphan_partial(struct sk_buff *skb) { - /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, - * so we do not completely orphan skb, but transfert all - * accounted bytes but one, to avoid unexpected reorders. - */ if (skb->destructor == sock_wfree #ifdef CONFIG_INET || skb->destructor == tcp_wfree #endif ) { - atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); - skb->truesize = 1; + struct sock *sk = skb->sk; + + if (atomic_inc_not_zero(&sk->sk_refcnt)) { + atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + skb->destructor = sock_efree; + } } else { skb_orphan(skb); } @@ -2694,11 +2705,6 @@ void sk_common_release(struct sock *sk) sk_refcnt_debug_release(sk); - if (sk->sk_frag.page) { - put_page(sk->sk_frag.page); - sk->sk_frag.page = NULL; - } - sock_put(sk); } EXPORT_SYMBOL(sk_common_release); diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index f053198e730c..5e3a7302f774 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk) for (i = 0; i < hc->tx_seqbufc; i++) kfree(hc->tx_seqbuf[i]); hc->tx_seqbufc = 0; + dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 1704948e6a12..f227f002c73d 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -1471,9 +1471,12 @@ int dccp_feat_init(struct sock *sk) * singleton values (which always leads to failure). * These settings can still (later) be overridden via sockopts. */ - if (ccid_get_builtin_ccids(&tx.val, &tx.len) || - ccid_get_builtin_ccids(&rx.val, &rx.len)) + if (ccid_get_builtin_ccids(&tx.val, &tx.len)) return -ENOBUFS; + if (ccid_get_builtin_ccids(&rx.val, &rx.len)) { + kfree(tx.val); + return -ENOBUFS; + } if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) || !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len)) diff --git a/net/dccp/input.c b/net/dccp/input.c index 3bd14e885396..dbe2573f6ba1 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -606,7 +606,8 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) < 0) return 1; - goto discard; + consume_skb(skb); + return 0; } if (dh->dccph_type == DCCP_PKT_RESET) goto discard; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 0759f5b9180e..e217f17997a4 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) switch (type) { case ICMP_REDIRECT: - dccp_do_redirect(skb, sk); + if (!sock_owned_by_user(sk)) + dccp_do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ @@ -634,6 +635,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); + reqsk_put(req); return 0; drop_and_free: diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 27c4e81efa24..09a9ab65f4e1 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } @@ -374,6 +376,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); + reqsk_put(req); return 0; drop_and_free: @@ -420,6 +423,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, newsk->sk_backlog_rcv = dccp_v4_do_rcv; newnp->pktoptions = NULL; newnp->opt = NULL; + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; @@ -484,6 +490,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 1994f8af646b..68eed344b471 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; + bh_unlock_sock(newsk); sk_free(newsk); return NULL; } @@ -145,6 +146,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, struct dccp_request_sock *dreq = dccp_rsk(req); bool own_req; + /* TCP/DCCP listeners became lockless. + * DCCP stores complex state in its request_sock, so we need + * a protection for them, now this code runs without being protected + * by the parent (listener) lock. + */ + spin_lock_bh(&dreq->dreq_lock); + /* Check for retransmitted REQUEST */ if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) { @@ -159,7 +167,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, inet_rtx_syn_ack(sk, req); } /* Network Duplicate, discard packet */ - return NULL; + goto out; } DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR; @@ -185,20 +193,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, req, &own_req); - if (!child) - goto listen_overflow; - - return inet_csk_complete_hashdance(sk, child, req, own_req); + if (child) { + child = inet_csk_complete_hashdance(sk, child, req, own_req); + goto out; + } -listen_overflow: - dccp_pr_debug("listen_overflow!\n"); DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); inet_csk_reqsk_queue_drop(sk, req); - return NULL; +out: + spin_unlock_bh(&dreq->dreq_lock); + return child; } EXPORT_SYMBOL_GPL(dccp_check_req); @@ -249,6 +257,7 @@ int dccp_reqsk_init(struct request_sock *req, { struct dccp_request_sock *dreq = dccp_rsk(req); + spin_lock_init(&dreq->dreq_lock); inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport; inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport); inet_rsk(req)->acked = 0; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index b1dc096d22f8..403593bd2b83 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -188,12 +188,6 @@ static inline void dnrt_free(struct dn_route *rt) call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); } -static inline void dnrt_drop(struct dn_route *rt) -{ - dst_release(&rt->dst); - call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); -} - static void dn_dst_check_expire(unsigned long dummy) { int i; @@ -248,7 +242,7 @@ static int dn_dst_gc(struct dst_ops *ops) } *rtp = rt->dst.dn_next; rt->dst.dn_next = NULL; - dnrt_drop(rt); + dnrt_free(rt); break; } spin_unlock_bh(&dn_rt_hash_table[i].lock); @@ -350,7 +344,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou dst_use(&rth->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); - dnrt_drop(rt); + dst_free(&rt->dst); *rp = rth; return 0; } @@ -380,7 +374,7 @@ static void dn_run_flush(unsigned long dummy) for(; rt; rt = next) { next = rcu_dereference_raw(rt->dst.dn_next); RCU_INIT_POINTER(rt->dst.dn_next, NULL); - dst_free((struct dst_entry *)rt); + dnrt_free(rt); } nothing_to_declare: @@ -1187,7 +1181,7 @@ make_route: if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST); + rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, DST_HOST); if (rt == NULL) goto e_nobufs; diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 85f2fdc360c2..29246bc9a7b4 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -102,7 +102,9 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) + if (skb->len < sizeof(*nlh) || + nlh->nlmsg_len < sizeof(*nlh) || + skb->len < nlh->nlmsg_len) return; if (!netlink_capable(skb, CAP_NET_ADMIN)) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7bc787b095c8..554c2a961ad5 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1006,10 +1006,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p, /* Use already configured phy mode */ if (p->phy_interface == PHY_INTERFACE_MODE_NA) p->phy_interface = p->phy->interface; - phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, - p->phy_interface); - - return 0; + return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, + p->phy_interface); } static int dsa_slave_phy_setup(struct dsa_slave_priv *p, @@ -1101,6 +1099,8 @@ int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); + netif_device_detach(slave_dev); + if (p->phy) { phy_stop(p->phy); p->old_pause = -1; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index de85d4e1cf43..52dcd414c2af 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -353,6 +353,7 @@ void ether_setup(struct net_device *dev) dev->header_ops = ð_header_ops; dev->type = ARPHRD_ETHER; dev->hard_header_len = ETH_HLEN; + dev->min_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->addr_len = ETH_ALEN; dev->tx_queue_len = 1000; /* Ethernet wants good queues */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 68bf7bdf7fdb..b25a1b1ee657 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1029,7 +1029,7 @@ static struct inet_protosw inetsw_array[] = .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, - .ops = &inet_dgram_ops, + .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 59b3e0e8fd51..711b4dfa17c3 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1250,7 +1250,7 @@ void __init arp_init(void) /* * ax25 -> ASCII conversion */ -static char *ax2asc2(ax25_address *a, char *buf) +static void ax2asc2(ax25_address *a, char *buf) { char c, *s; int n; @@ -1272,10 +1272,10 @@ static char *ax2asc2(ax25_address *a, char *buf) *s++ = n + '0'; *s++ = '\0'; - if (*buf == '\0' || *buf == '-') - return "*"; - - return buf; + if (*buf == '\0' || *buf == '-') { + buf[0] = '*'; + buf[1] = '\0'; + } } #endif /* CONFIG_AX25 */ @@ -1309,7 +1309,7 @@ static void arp_format_neigh_entry(struct seq_file *seq, } #endif sprintf(tbuf, "%pI4", n->primary_key); - seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n", + seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n", tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name); read_unlock(&n->lock); } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index bdb2a07ec363..6cc3e1d602fb 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1657,6 +1657,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) goto validate_return_locked; } + if (opt_iter + 1 == opt_len) { + err_offset = opt_iter; + goto validate_return_locked; + } tag_len = tag[1]; if (tag_len > (opt_len - opt_iter)) { err_offset = opt_iter + 1; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7e30c7b50a28..ee94bd32d6dc 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -758,7 +758,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; - int dumped = 0; + int dumped = 0, err; if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) @@ -778,20 +778,27 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); - if (fib_table_dump(tb, skb, cb) < 0) - goto out; + err = fib_table_dump(tb, skb, cb); + if (err < 0) { + if (likely(skb->len)) + goto out; + + goto out_err; + } dumped = 1; next: e++; } } out: + err = skb->len; +out_err: rcu_read_unlock(); cb->args[1] = e; cb->args[0] = h; - return skb->len; + return err; } /* Prepare and feed intra-kernel routing request. @@ -1081,7 +1088,8 @@ static void nl_fib_input(struct sk_buff *skb) net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); - if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len || + if (skb->len < nlmsg_total_size(sizeof(*frn)) || + skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(*frn)) return; @@ -1312,13 +1320,14 @@ static struct pernet_operations fib_net_ops = { void __init ip_fib_init(void) { - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); + fib_trie_init(); register_pernet_subsys(&fib_net_ops); + register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); - fib_trie_init(); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 840b450aab46..b2504712259f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -204,6 +204,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); + struct dst_metrics *m; change_nexthops(fi) { if (nexthop_nh->nh_dev) @@ -214,8 +215,9 @@ static void free_fib_info_rcu(struct rcu_head *head) rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); - if (fi->fib_metrics != (u32 *) dst_default_metrics) - kfree(fi->fib_metrics); + m = fi->fib_metrics; + if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt)) + kfree(m); kfree(fi); } @@ -982,11 +984,11 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) val = 255; if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) return -EINVAL; - fi->fib_metrics[type - 1] = val; + fi->fib_metrics->metrics[type - 1] = val; } if (ecn_ca) - fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; + fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; return 0; } @@ -1044,11 +1046,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; fib_info_cnt++; if (cfg->fc_mx) { - fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); + fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL); if (!fi->fib_metrics) goto failure; + atomic_set(&fi->fib_metrics->refcnt, 1); } else - fi->fib_metrics = (u32 *) dst_default_metrics; + fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; @@ -1251,7 +1254,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, if (fi->fib_priority && nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) goto nla_put_failure; - if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) + if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0) goto nla_put_failure; if (fi->fib_prefsrc && @@ -1277,8 +1280,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif - if (fi->fib_nh->nh_lwtstate) - lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); + if (fi->fib_nh->nh_lwtstate && + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0) + goto nla_put_failure; } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1314,8 +1318,10 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif - if (nh->nh_lwtstate) - lwtunnel_fill_encap(skb, nh->nh_lwtstate); + if (nh->nh_lwtstate && + lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 7c52afb98c42..5c598f99a500 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1906,6 +1906,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + int err; + if (i < s_i) { i++; continue; @@ -1916,17 +1918,14 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, continue; } - if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->tb_id, - fa->fa_type, - xkey, - KEYLENGTH - fa->fa_slen, - fa->fa_tos, - fa->fa_info, NLM_F_MULTI) < 0) { + err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE, + tb->tb_id, fa->fa_type, + xkey, KEYLENGTH - fa->fa_slen, + fa->fa_tos, fa->fa_info, NLM_F_MULTI); + if (err < 0) { cb->args[4] = i; - return -1; + return err; } i++; } @@ -1948,10 +1947,13 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, t_key key = cb->args[3]; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) { + int err; + + err = fn_trie_dump_leaf(l, tb, skb, cb); + if (err < 0) { cb->args[3] = key; cb->args[2] = count; - return -1; + return err; } ++count; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 17adfdaf5795..3809d523d012 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1102,6 +1102,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); if (!pmc) return; + spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); @@ -2026,21 +2027,26 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, static void ip_mc_clear_src(struct ip_mc_list *pmc) { - struct ip_sf_list *psf, *nextpsf; + struct ip_sf_list *psf, *nextpsf, *tomb, *sources; - for (psf = pmc->tomb; psf; psf = nextpsf) { + spin_lock_bh(&pmc->lock); + tomb = pmc->tomb; + pmc->tomb = NULL; + sources = pmc->sources; + pmc->sources = NULL; + pmc->sfmode = MCAST_EXCLUDE; + pmc->sfcount[MCAST_INCLUDE] = 0; + pmc->sfcount[MCAST_EXCLUDE] = 1; + spin_unlock_bh(&pmc->lock); + + for (psf = tomb; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } - pmc->tomb = NULL; - for (psf = pmc->sources; psf; psf = nextpsf) { + for (psf = sources; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } - pmc->sources = NULL; - pmc->sfmode = MCAST_EXCLUDE; - pmc->sfcount[MCAST_INCLUDE] = 0; - pmc->sfcount[MCAST_EXCLUDE] = 1; } /* Join a multicast group diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c97a2108cd61..a7e7aa1f6a47 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -669,6 +669,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); newsk->sk_write_space = sk_stream_write_space; + inet_sk(newsk)->mc_list = NULL; + newsk->sk_mark = inet_rsk(req)->ir_mark; atomic64_set(&newsk->sk_cookie, atomic64_read(&inet_rsk(req)->ir_cookie)); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 661bda968594..62e41d38da78 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -922,10 +922,12 @@ static int __ip_append_data(struct sock *sk, csummode = CHECKSUM_PARTIAL; cork->length += length; - if (((length > mtu) || (skb && skb_is_gso(skb))) && + if ((skb && skb_is_gso(skb)) || + (((length + (skb ? skb->len : fragheaderlen)) > mtu) && + (skb_queue_len(queue) <= 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && - (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { + (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx)) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1241,6 +1243,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, return -EINVAL; if ((size + skb->len > mtu) && + (skb_queue_len(&sk->sk_write_queue) == 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { if (skb->ip_summed != CHECKSUM_PARTIAL) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 9ce202549e7a..f300d1cbfa91 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -105,10 +105,10 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_COMPLETE) return; - if (offset != 0) - csum = csum_sub(csum, - csum_partial(skb->data + tlen, - offset, 0)); + if (offset != 0) { + int tend_off = skb_transport_offset(skb) + tlen; + csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0)); + } put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum); } @@ -1192,7 +1192,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } - skb_dst_drop(skb); + /* We need to keep the dst for __ip_options_echo() + * We could restrict the test to opt.ts_needtime || opt.srr, + * but the following is good enough as IP options are not often used. + */ + if (unlikely(IPCB(skb)->opt.optlen)) + skb_dst_force(skb); + else + skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 495fefe6a898..a989aba861e0 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -154,17 +154,18 @@ void ping_hash(struct sock *sk) void ping_unhash(struct sock *sk) { struct inet_sock *isk = inet_sk(sk); + pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); + write_lock_bh(&ping_table.lock); if (sk_hashed(sk)) { - write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - write_unlock_bh(&ping_table.lock); } + write_unlock_bh(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_unhash); @@ -645,6 +646,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, { struct sk_buff *skb = skb_peek(&sk->sk_write_queue); + if (!skb) + return 0; pfh->wcheck = csum_partial((char *)&pfh->icmph, sizeof(struct icmphdr), pfh->wcheck); pfh->icmph.checksum = csum_fold(pfh->wcheck); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6287418c1dfe..ca1031411aa7 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -354,6 +354,9 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, rt->dst.dev->mtu); return -EMSGSIZE; } + if (length < sizeof(struct iphdr)) + return -EINVAL; + if (flags&MSG_PROBE) goto out; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3708ff083211..fd15e55b28d1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -792,6 +792,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf struct rtable *rt; struct flowi4 fl4; const struct iphdr *iph = (const struct iphdr *) skb->data; + struct net *net = dev_net(skb->dev); int oif = skb->dev->ifindex; u8 tos = RT_TOS(iph->tos); u8 prot = iph->protocol; @@ -799,7 +800,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf rt = (struct rtable *) dst; - __build_flow_key(sock_net(sk), &fl4, sk, iph, oif, tos, prot, mark, 0); + __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } @@ -1361,8 +1362,12 @@ static void rt_add_uncached_list(struct rtable *rt) static void ipv4_dst_destroy(struct dst_entry *dst) { + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rtable *rt = (struct rtable *) dst; + if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt)) + kfree(p); + if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1414,7 +1419,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, rt->rt_gateway = nh->nh_gw; rt->rt_uses_gateway = 1; } - dst_init_metrics(&rt->dst, fi->fib_metrics, true); + dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true); + if (fi->fib_metrics != &dst_default_metrics) { + rt->dst._metrics |= DST_METRICS_REFCOUNTED; + atomic_inc(&fi->fib_metrics->refcnt); + } #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif @@ -1963,6 +1972,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, { int res; + tos &= IPTOS_RT_MASK; rcu_read_lock(); /* Multicast recognition logic is moved from route cache to here. @@ -2435,7 +2445,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4->flowi4_tos; - r->rtm_table = table_id; + r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; @@ -2569,7 +2579,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) skb_reset_network_header(skb); /* Bugfix: need to give ip_route_input enough of an IP header to not gag. */ - ip_hdr(skb)->protocol = IPPROTO_ICMP; + ip_hdr(skb)->protocol = IPPROTO_UDP; skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2dc982b15df8..a2e1142145df 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -337,6 +337,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq = tcp_rsk(req); treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; + treq->txhash = net_tx_rndhash(); req->mss = mss; ireq->ir_num = ntohs(th->dest); ireq->ir_rmt_port = th->source; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index dc173e0d2184..48e6509426b0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -783,6 +783,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } + /* if __tcp_splice_read() got nothing while we have + * an skb in receive queue, we do not want to loop. + * This might happen with URG data. + */ + if (!skb_queue_empty(&sk->sk_receive_queue)) + break; sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); @@ -1065,9 +1071,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); + struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) + if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && + uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ @@ -1080,7 +1089,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; - err = __inet_stream_connect(sk->sk_socket, msg->msg_name, + err = __inet_stream_connect(sk->sk_socket, uaddr, msg->msg_namelen, flags); *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); @@ -2254,6 +2263,9 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); + dst_release(sk->sk_rx_dst); + sk->sk_rx_dst = NULL; + tcp_saved_syn_free(tp); WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 882caa4e72bc..aafe68134763 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -183,6 +183,7 @@ void tcp_init_congestion_control(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + tcp_sk(sk)->prior_ssthresh = 0; if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); if (tcp_ca_needs_ecn(sk)) diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 55be6ac70cff..fca618272a01 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -112,7 +112,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, struct tcp_fastopen_cookie tmp; if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { - struct in6_addr *buf = (struct in6_addr *) tmp.val; + struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) @@ -161,6 +161,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, * scaled. So correct it appropriately. */ tp->snd_wnd = ntohs(tcp_hdr(skb)->window); + tp->max_window = tp->snd_wnd; /* Activate the retrans timer so that SYNACK can be retransmitted. * The request socket is not added to the ehash diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 35e97ff3054a..b6d99c308bef 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1135,13 +1135,14 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, */ if (pkt_len > mss) { unsigned int new_len = (pkt_len / mss) * mss; - if (!in_sack && new_len < pkt_len) { + if (!in_sack && new_len < pkt_len) new_len += mss; - if (new_len >= skb->len) - return 0; - } pkt_len = new_len; } + + if (pkt_len >= skb->len && !in_sack) + return 0; + err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; @@ -2165,8 +2166,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt; - int err; + int cnt, oldcnt, lost; unsigned int mss; /* Use SACK to deduce losses of new sequences sent during recovery */ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; @@ -2206,9 +2206,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; mss = tcp_skb_mss(skb); - err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, - mss, GFP_ATOMIC); - if (err < 0) + /* If needed, chop off the prefix to mark as lost. */ + lost = (packets - oldcnt) * mss; + if (lost < skb->len && + tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2503,8 +2504,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || - (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { + if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH && + (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) { tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_time_stamp; } @@ -3220,7 +3221,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, int delta; /* Non-retransmitted hole got filled? That's reordering */ - if (reord < prior_fackets) + if (reord < prior_fackets && reord <= tp->fackets_out) tcp_update_reordering(sk, tp->fackets_out - reord, 0); delta = tcp_is_fack(tp) ? pkts_acked : @@ -5436,6 +5437,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); + icsk->icsk_ack.lrcvtime = tcp_time_stamp; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); @@ -5648,7 +5650,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * to stand against the temptation 8) --ANK */ inet_csk_schedule_ack(sk); - icsk->icsk_ack.lrcvtime = tcp_time_stamp; tcp_enter_quickack_mode(sk); inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 25309b137c43..a84f74af22f7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -271,10 +271,13 @@ EXPORT_SYMBOL(tcp_v4_connect); */ void tcp_v4_mtu_reduced(struct sock *sk) { - struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); - u32 mtu = tcp_sk(sk)->mtu_info; + struct dst_entry *dst; + u32 mtu; + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + mtu = tcp_sk(sk)->mtu_info; dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -420,7 +423,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) switch (type) { case ICMP_REDIRECT: - do_redirect(icmp_skb, sk); + if (!sock_owned_by_user(sk)) + do_redirect(icmp_skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 1e70fa8fa793..3861dedd5365 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -264,13 +264,15 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); + u32 delta; if (rtt_us > 0) tcp_lp_rtt_sample(sk, rtt_us); /* calc inference */ - if (tcp_time_stamp > tp->rx_opt.rcv_tsecr) - lp->inference = 3 * (tcp_time_stamp - tp->rx_opt.rcv_tsecr); + delta = tcp_time_stamp - tp->rx_opt.rcv_tsecr; + if ((s32)delta > 0) + lp->inference = 3 * delta; /* test if within inference */ if (lp->last_drop && (tcp_time_stamp - lp->last_drop < lp->inference)) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 9475a2748a9a..4c1c94fa8f08 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -472,6 +472,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); newtp->rtt_min[0].rtt = ~0U; newicsk->icsk_rto = TCP_TIMEOUT_INIT; + newicsk->icsk_ack.lrcvtime = tcp_time_stamp; newtp->packets_out = 0; newtp->retrans_out = 0; @@ -546,6 +547,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); + newtp->fastopen_req = NULL; newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; newtp->rack.mstamp.v64 = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ca3731721d81..4e88f93f71c8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1221,7 +1221,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, * eventually). The difference is that pulled data not copied, but * immediately discarded. */ -static void __pskb_trim_head(struct sk_buff *skb, int len) +static int __pskb_trim_head(struct sk_buff *skb, int len) { struct skb_shared_info *shinfo; int i, k, eat; @@ -1231,7 +1231,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) __skb_pull(skb, eat); len -= eat; if (!len) - return; + return 0; } eat = len; k = 0; @@ -1257,23 +1257,28 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) skb_reset_tail_pointer(skb); skb->data_len -= len; skb->len = skb->data_len; + return len; } /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { + u32 delta_truesize; + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; - __pskb_trim_head(skb, len); + delta_truesize = __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; skb->ip_summed = CHECKSUM_PARTIAL; - skb->truesize -= len; - sk->sk_wmem_queued -= len; - sk_mem_uncharge(sk, len); - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); + if (delta_truesize) { + skb->truesize -= delta_truesize; + sk->sk_wmem_queued -= delta_truesize; + sk_mem_uncharge(sk, delta_truesize); + sock_set_flag(sk, SOCK_QUEUE_SHRUNK); + } /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) @@ -2383,9 +2388,11 @@ u32 __tcp_select_window(struct sock *sk) int full_space = min_t(int, tp->window_clamp, allowed_space); int window; - if (mss > full_space) + if (unlikely(mss > full_space)) { mss = full_space; - + if (mss <= 0) + return 0; + } if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; @@ -3249,6 +3256,9 @@ int tcp_connect(struct sock *sk) struct sk_buff *buff; int err; + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) + return -EHOSTUNREACH; /* Routing failure or similar. */ + tcp_connect_init(sk); if (unlikely(tp->repair)) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 193ba1fa8a9a..1ec12a4f327e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -223,7 +223,8 @@ void tcp_delack_timer_handler(struct sock *sk) sk_mem_reclaim_partial(sk); - if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) goto out; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -504,7 +505,8 @@ void tcp_write_timer_handler(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); int event; - if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !icsk->icsk_pending) goto out; if (time_after(icsk->icsk_timeout, jiffies)) { @@ -604,7 +606,8 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) + if (!sock_flag(sk, SOCK_KEEPOPEN) || + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT))) goto out; elapsed = keepalive_time_when(tp); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ad3d1534c524..9ee5087b9b5e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -819,7 +819,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); - else if (sk->sk_no_check_tx) { /* UDP csum disabled */ + else if (sk->sk_no_check_tx && !skb_is_gso(skb)) { /* UDP csum off */ skb->ip_summed = CHECKSUM_NONE; goto send; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6396f1c80ae9..6dfc3daf7c21 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -231,7 +231,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (uh->check == 0) uh->check = CSUM_MANGLED_0; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = CHECKSUM_UNNECESSARY; /* Fragment the skb. IP headers of the fragments are updated in * inet_gso_segment() diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1e541578a66d..2d2241006d35 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -112,6 +112,27 @@ static inline u32 cstamp_delta(unsigned long cstamp) return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } +static inline s32 rfc3315_s14_backoff_init(s32 irt) +{ + /* multiply 'initial retransmission time' by 0.9 .. 1.1 */ + u64 tmp = (900000 + prandom_u32() % 200001) * (u64)irt; + do_div(tmp, 1000000); + return (s32)tmp; +} + +static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt) +{ + /* multiply 'retransmission timeout' by 1.9 .. 2.1 */ + u64 tmp = (1900000 + prandom_u32() % 200001) * (u64)rt; + do_div(tmp, 1000000); + if ((s32)tmp > mrt) { + /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */ + tmp = (900000 + prandom_u32() % 200001) * (u64)mrt; + do_div(tmp, 1000000); + } + return (s32)tmp; +} + #ifdef CONFIG_SYSCTL static int addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); @@ -187,6 +208,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, + .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, @@ -202,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif @@ -232,6 +255,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, + .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, @@ -247,6 +271,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif @@ -293,9 +318,9 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev, static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, unsigned long delay) { - if (!delayed_work_pending(&ifp->dad_work)) - in6_ifa_hold(ifp); - mod_delayed_work(addrconf_wq, &ifp->dad_work, delay); + in6_ifa_hold(ifp); + if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay)) + in6_ifa_put(ifp); } static int snmp6_alloc_dev(struct inet6_dev *idev) @@ -1774,17 +1799,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { - if (ifp->flags&IFA_F_PERMANENT) { - spin_lock_bh(&ifp->lock); - addrconf_del_dad_work(ifp); - ifp->flags |= IFA_F_TENTATIVE; - if (dad_failed) - ifp->flags |= IFA_F_DADFAILED; - spin_unlock_bh(&ifp->lock); - if (dad_failed) - ipv6_ifa_notify(0, ifp); - in6_ifa_put(ifp); - } else if (ifp->flags&IFA_F_TEMPORARY) { + if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); ifpub = ifp->ifpub; @@ -1797,6 +1812,16 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); + } else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) { + spin_lock_bh(&ifp->lock); + addrconf_del_dad_work(ifp); + ifp->flags |= IFA_F_TENTATIVE; + if (dad_failed) + ifp->flags |= IFA_F_DADFAILED; + spin_unlock_bh(&ifp->lock); + if (dad_failed) + ipv6_ifa_notify(0, ifp); + in6_ifa_put(ifp); } else { ipv6_del_addr(ifp); } @@ -3170,6 +3195,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); + struct net *net = dev_net(dev); int run_pending = 0; int err; @@ -3185,7 +3211,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, case NETDEV_CHANGEMTU: /* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) { - addrconf_ifdown(dev, 1); + addrconf_ifdown(dev, dev != net->loopback_dev); break; } @@ -3238,9 +3264,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } if (idev) { - if (idev->if_flags & IF_READY) - /* device is already configured. */ + if (idev->if_flags & IF_READY) { + /* device is already configured - + * but resend MLD reports, we might + * have roamed and need to update + * multicast snooping switches + */ + ipv6_mc_up(idev); break; + } idev->if_flags |= IF_READY; } @@ -3292,7 +3324,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, * IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) - addrconf_ifdown(dev, 1); + addrconf_ifdown(dev, dev != net->loopback_dev); } break; @@ -3333,6 +3365,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, */ static struct notifier_block ipv6_dev_notf = { .notifier_call = addrconf_notify, + .priority = ADDRCONF_NOTIFY_PRIORITY, }; static void addrconf_type_change(struct net_device *dev, unsigned long event) @@ -3485,7 +3518,7 @@ static void addrconf_rs_timer(unsigned long data) if (idev->if_flags & IF_RA_RCVD) goto out; - if (idev->rs_probes++ < idev->cnf.rtr_solicits) { + if (idev->rs_probes++ < idev->cnf.rtr_solicits || idev->cnf.rtr_solicits < 0) { write_unlock(&idev->lock); if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) ndisc_send_rs(dev, &lladdr, @@ -3494,11 +3527,13 @@ static void addrconf_rs_timer(unsigned long data) goto put; write_lock(&idev->lock); + idev->rs_interval = rfc3315_s14_backoff_update( + idev->rs_interval, idev->cnf.rtr_solicit_max_interval); /* The wait after the last probe can be shorter */ addrconf_mod_rs_timer(idev, (idev->rs_probes == idev->cnf.rtr_solicits) ? idev->cnf.rtr_solicit_delay : - idev->cnf.rtr_solicit_interval); + idev->rs_interval); } else { /* * Note: we do not support deprecated "all on-link" @@ -3726,7 +3761,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp); send_rs = send_mld && ipv6_accept_ra(ifp->idev) && - ifp->idev->cnf.rtr_solicits > 0 && + ifp->idev->cnf.rtr_solicits != 0 && (dev->flags&IFF_LOOPBACK) == 0; read_unlock_bh(&ifp->idev->lock); @@ -3748,10 +3783,11 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) write_lock_bh(&ifp->idev->lock); spin_lock(&ifp->lock); + ifp->idev->rs_interval = rfc3315_s14_backoff_init( + ifp->idev->cnf.rtr_solicit_interval); ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; - addrconf_mod_rs_timer(ifp->idev, - ifp->idev->cnf.rtr_solicit_interval); + addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval); spin_unlock(&ifp->lock); write_unlock_bh(&ifp->idev->lock); } @@ -4668,6 +4704,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits; array[DEVCONF_RTR_SOLICIT_INTERVAL] = jiffies_to_msecs(cnf->rtr_solicit_interval); + array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] = + jiffies_to_msecs(cnf->rtr_solicit_max_interval); array[DEVCONF_RTR_SOLICIT_DELAY] = jiffies_to_msecs(cnf->rtr_solicit_delay); array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version; @@ -4689,6 +4727,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_RTR_PROBE_INTERVAL] = jiffies_to_msecs(cnf->rtr_probe_interval); #ifdef CONFIG_IPV6_ROUTE_INFO + array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen; array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; #endif #endif @@ -4876,7 +4915,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) return -EINVAL; if (!ipv6_accept_ra(idev)) return -EINVAL; - if (idev->cnf.rtr_solicits <= 0) + if (idev->cnf.rtr_solicits == 0) return -EINVAL; write_lock_bh(&idev->lock); @@ -4901,8 +4940,10 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) if (update_rs) { idev->if_flags |= IF_RS_SENT; + idev->rs_interval = rfc3315_s14_backoff_init( + idev->cnf.rtr_solicit_interval); idev->rs_probes = 1; - addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval); + addrconf_mod_rs_timer(idev, idev->rs_interval); } /* Well, that's kinda nasty ... */ @@ -5272,8 +5313,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); @@ -5282,7 +5322,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf) dev_disable_change(idev); } } - rcu_read_unlock(); } static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) @@ -5542,6 +5581,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec_jiffies, }, { + .procname = "router_solicitation_max_interval", + .data = &ipv6_devconf.rtr_solicit_max_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { .procname = "router_solicitation_delay", .data = &ipv6_devconf.rtr_solicit_delay, .maxlen = sizeof(int), @@ -5651,6 +5697,13 @@ static struct addrconf_sysctl_table }, #ifdef CONFIG_IPV6_ROUTE_INFO { + .procname = "accept_ra_rt_info_min_plen", + .data = &ipv6_devconf.accept_ra_rt_info_min_plen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "accept_ra_rt_info_max_plen", .data = &ipv6_devconf.accept_ra_rt_info_max_plen, .maxlen = sizeof(int), @@ -5977,6 +6030,8 @@ int __init addrconf_init(void) goto errlo; } + ip6_route_init_special_entries(); + for (i = 0; i < IN6_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&inet6_addr_lst[i]); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index cf2dfb222230..56528e9f3e01 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -76,18 +76,22 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a } } - addr_type = ipv6_addr_type(&usin->sin6_addr); - - if (addr_type == IPV6_ADDR_ANY) { + if (ipv6_addr_any(&usin->sin6_addr)) { /* * connect to self */ - usin->sin6_addr.s6_addr[15] = 0x01; + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), + &usin->sin6_addr); + else + usin->sin6_addr = in6addr_loopback; } + addr_type = ipv6_addr_type(&usin->sin6_addr); + daddr = &usin->sin6_addr; - if (addr_type == IPV6_ADDR_MAPPED) { + if (addr_type & IPV6_ADDR_MAPPED) { struct sockaddr_in sin; if (__ipv6_only_sock(sk)) { diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index ed33abf57abd..9ac4f0cef27d 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -32,7 +32,6 @@ struct fib6_rule { struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { - struct rt6_info *rt; struct fib_lookup_arg arg = { .lookup_ptr = lookup, .flags = FIB_LOOKUP_NOREF, @@ -41,21 +40,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); - rt = arg.result; + if (arg.result) + return arg.result; - if (!rt) { - dst_hold(&net->ipv6.ip6_null_entry->dst); - return &net->ipv6.ip6_null_entry->dst; - } - - if (rt->rt6i_flags & RTF_REJECT && - rt->dst.error == -EAGAIN) { - ip6_rt_put(rt); - rt = net->ipv6.ip6_null_entry; - dst_hold(&rt->dst); - } - - return &rt->dst; + dst_hold(&net->ipv6.ip6_null_entry->dst); + return &net->ipv6.ip6_null_entry->dst; } static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, @@ -116,7 +105,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, flp6->saddr = saddr; } err = rt->dst.error; - goto out; + if (err != -EAGAIN) + goto out; } again: ip6_rt_put(rt); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 34cf46d74554..f60e8caea767 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -290,8 +290,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, struct rt6_info *rt; rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); - if (rt->rt6i_flags & RTF_REJECT && - rt->dst.error == -EAGAIN) { + if (rt->dst.error == -EAGAIN) { ip6_rt_put(rt); rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); @@ -768,10 +767,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, goto next_iter; } - if (iter->dst.dev == rt->dst.dev && - iter->rt6i_idev == rt->rt6i_idev && - ipv6_addr_equal(&iter->rt6i_gateway, - &rt->rt6i_gateway)) { + if (rt6_duplicate_nexthop(iter, rt)) { if (rt->rt6i_nsiblings) rt->rt6i_nsiblings = 0; if (!(iter->rt6i_flags & RTF_EXPIRES)) @@ -903,6 +899,8 @@ add: ins = &rt->dst.rt6_next; iter = *ins; while (iter) { + if (iter->rt6i_metric > rt->rt6i_metric) + break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->dst.rt6_next; fib6_purge_rt(iter, fn, info->nl_net); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index eba61b42cd42..ab0efaca4a78 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -55,6 +55,7 @@ #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ip6_tunnel.h> +#include <net/gre.h> static bool log_ecn_error = true; @@ -367,35 +368,37 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { - const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; - __be16 *p = (__be16 *)(skb->data + offset); - int grehlen = offset + 4; + const struct gre_base_hdr *greh; + const struct ipv6hdr *ipv6h; + int grehlen = sizeof(*greh); struct ip6_tnl *t; + int key_off = 0; __be16 flags; + __be32 key; - flags = p[0]; - if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) { - if (flags&(GRE_VERSION|GRE_ROUTING)) - return; - if (flags&GRE_KEY) { - grehlen += 4; - if (flags&GRE_CSUM) - grehlen += 4; - } + if (!pskb_may_pull(skb, offset + grehlen)) + return; + greh = (const struct gre_base_hdr *)(skb->data + offset); + flags = greh->flags; + if (flags & (GRE_VERSION | GRE_ROUTING)) + return; + if (flags & GRE_CSUM) + grehlen += 4; + if (flags & GRE_KEY) { + key_off = grehlen + offset; + grehlen += 4; } - /* If only 8 bytes returned, keyed message will be dropped here */ - if (!pskb_may_pull(skb, grehlen)) + if (!pskb_may_pull(skb, offset + grehlen)) return; ipv6h = (const struct ipv6hdr *)skb->data; - p = (__be16 *)(skb->data + offset); + greh = (const struct gre_base_hdr *)(skb->data + offset); + key = key_off ? *(__be32 *)(skb->data + key_off) : 0; t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, - flags & GRE_KEY ? - *(((__be32 *)p) + (grehlen / 4) - 1) : 0, - p[1]); + key, greh->protocol); if (!t) return; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 225f5f7f26ba..9e2ea4ae840d 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -62,7 +62,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, const struct net_offload *ops; int proto; struct frag_hdr *fptr; - unsigned int unfrag_ip6hlen; u8 *prevhdr; int offset = 0; bool encap, udpfrag; @@ -121,8 +120,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, skb->network_header = (u8 *)ipv6h - skb->head; if (udpfrag) { - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); + int err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) { + kfree_skb_list(segs); + return ERR_PTR(err); + } + fptr = (struct frag_hdr *)((u8 *)ipv6h + err); fptr->frag_off = htons(offset); if (skb->next) fptr->frag_off |= htons(IP6_MF); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 58900c21e4e4..e22339fad10b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -571,7 +571,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; - hlen = ip6_find_1stfragopt(skb, &prevhdr); + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + goto fail; + hlen = err; nexthdr = *prevhdr; mtu = ip6_skb_dst_mtu(skb); @@ -644,8 +647,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, *prevhdr = NEXTHDR_FRAGMENT; tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } @@ -742,13 +743,14 @@ slow_path: * Fragment the datagram. */ - *prevhdr = NEXTHDR_FRAGMENT; troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. */ while (left > 0) { + u8 *fragnexthdr_offset; + len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) @@ -763,8 +765,6 @@ slow_path: frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) + hroom + troom, GFP_ATOMIC); if (!frag) { - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } @@ -793,6 +793,10 @@ slow_path: */ skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); + fragnexthdr_offset = skb_network_header(frag); + fragnexthdr_offset += prevhdr - skb_network_header(skb); + *fragnexthdr_offset = NEXTHDR_FRAGMENT; + /* * Build fragment header. */ @@ -996,6 +1000,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, } } #endif + if (ipv6_addr_v4mapped(&fl6->saddr) && + !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) { + err = -EAFNOSUPPORT; + goto out_err_release; + } return 0; @@ -1348,11 +1357,12 @@ emsgsize: */ cork->length += length; - if (((length > mtu) || - (skb && skb_is_gso(skb))) && + if ((skb && skb_is_gso(skb)) || + (((length + (skb ? skb->len : headersize)) > mtu) && + (skb_queue_len(queue) <= 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && - (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { + (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk))) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, transhdrlen, mtu, flags, fl6); @@ -1424,6 +1434,11 @@ alloc_new_skb: */ alloclen += sizeof(struct frag_hdr); + copy = datalen - transhdrlen - fraggap; + if (copy < 0) { + err = -EINVAL; + goto error; + } if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len, @@ -1473,13 +1488,9 @@ alloc_new_skb: data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } - copy = datalen - transhdrlen - fraggap; - - if (copy < 0) { - err = -EINVAL; - kfree_skb(skb); - goto error; - } else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { + if (copy > 0 && + getfrag(from, data + transhdrlen, offset, + copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c9bd1ee1f145..600975c5eacf 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -479,18 +479,19 @@ ip6_tnl_dev_uninit(struct net_device *dev) __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { - const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw; - __u8 nexthdr = ipv6h->nexthdr; - __u16 off = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; + unsigned int nhoff = raw - skb->data; + unsigned int off = nhoff + sizeof(*ipv6h); + u8 next, nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { - __u16 optlen = 0; struct ipv6_opt_hdr *hdr; - if (raw + off + sizeof(*hdr) > skb->data && - !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr))) + u16 optlen; + + if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; - hdr = (struct ipv6_opt_hdr *) (raw + off); + hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr; if (frag_hdr->frag_off) @@ -501,20 +502,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) } else { optlen = ipv6_optlen(hdr); } + /* cache hdr->nexthdr, since pskb_may_pull() might + * invalidate hdr + */ + next = hdr->nexthdr; if (nexthdr == NEXTHDR_DEST) { - __u16 i = off + 2; + u16 i = 2; + + /* Remember : hdr is no longer valid at this point. */ + if (!pskb_may_pull(skb, off + optlen)) + break; + while (1) { struct ipv6_tlv_tnl_enc_lim *tel; /* No more room for encapsulation limit */ - if (i + sizeof (*tel) > off + optlen) + if (i + sizeof(*tel) > optlen) break; - tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i]; + tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i); /* return index of option if found and valid */ if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT && tel->length == 1) - return i; + return i + off - nhoff; /* else jump to next option */ if (tel->type) i += tel->length + 2; @@ -522,7 +532,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) i++; } } - nexthdr = hdr->nexthdr; + nexthdr = next; off += optlen; } return 0; @@ -1039,7 +1049,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct net_device_stats *stats = &t->dev->stats; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; @@ -1051,26 +1061,28 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { - struct in6_addr *addr6; - struct neighbour *neigh; - int addr_type; + if (skb->protocol == htons(ETH_P_IPV6)) { + struct in6_addr *addr6; + struct neighbour *neigh; + int addr_type; - if (!skb_dst(skb)) - goto tx_err_link_failure; + if (!skb_dst(skb)) + goto tx_err_link_failure; - neigh = dst_neigh_lookup(skb_dst(skb), - &ipv6_hdr(skb)->daddr); - if (!neigh) - goto tx_err_link_failure; + neigh = dst_neigh_lookup(skb_dst(skb), + &ipv6_hdr(skb)->daddr); + if (!neigh) + goto tx_err_link_failure; - addr6 = (struct in6_addr *)&neigh->primary_key; - addr_type = ipv6_addr_type(addr6); + addr6 = (struct in6_addr *)&neigh->primary_key; + addr_type = ipv6_addr_type(addr6); - if (addr_type == IPV6_ADDR_ANY) - addr6 = &ipv6_hdr(skb)->daddr; + if (addr_type == IPV6_ADDR_ANY) + addr6 = &ipv6_hdr(skb)->daddr; - memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); - neigh_release(neigh); + memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); + neigh_release(neigh); + } } else if (!(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { /* enable the cache only only if the routing decision does diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 24fb9c0efd00..5b7433887eda 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -681,6 +681,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) u->link = p->link; u->i_key = p->i_key; u->o_key = p->o_key; + if (u->i_key) + u->i_flags |= GRE_KEY; + if (u->o_key) + u->o_flags |= GRE_KEY; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index d9843e5a667f..8361d73ab653 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -774,7 +774,8 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) +static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, + struct list_head *head) { struct mif_device *v; struct net_device *dev; @@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) dev->ifindex, &in6_dev->cnf); } - if (v->flags & MIFF_REGISTER) + if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); dev_put(dev); @@ -1330,7 +1331,6 @@ static int ip6mr_device_event(struct notifier_block *this, struct mr6_table *mrt; struct mif_device *v; int ct; - LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -1339,10 +1339,9 @@ static int ip6mr_device_event(struct notifier_block *this, v = &mrt->vif6_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(mrt, ct, &list); + mif6_delete(mrt, ct, 1, NULL); } } - unregister_netdevice_many(&list); return NOTIFY_DONE; } @@ -1551,7 +1550,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all) for (i = 0; i < mrt->maxvif; i++) { if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC)) continue; - mif6_delete(mrt, i, &list); + mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); @@ -1704,7 +1703,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(mrt, mifi, NULL); + ret = mif6_delete(mrt, mifi, 0, NULL); rtnl_unlock(); return ret; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 84afb9a77278..3452f9037ad4 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1358,6 +1358,8 @@ skip_linkparms: if (ri->prefix_len == 0 && !in6_dev->cnf.accept_ra_defrtr) continue; + if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) + continue; if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 1d184322a7b1..f9f02581c4ca 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -78,15 +78,15 @@ EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; - while (offset + 1 <= packet_len) { + while (offset <= packet_len) { + struct ipv6_opt_hdr *exthdr; + unsigned int len; switch (**nexthdr) { @@ -107,13 +107,19 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; + if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) + return -EINVAL; + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); + len = ipv6_optlen(exthdr); + if (len + offset >= IPV6_MAXPLEN) + return -EINVAL; + offset += len; + *nexthdr = &exthdr->nexthdr; } - return offset; + return -EINVAL; } EXPORT_SYMBOL(ip6_find_1stfragopt); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 1737fc0f2988..4c753f4a3712 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -50,7 +50,7 @@ static struct inet_protosw pingv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, - .ops = &inet6_dgram_ops, + .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d503b7f373a3..0ef8e114c8ab 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -630,6 +630,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } + if (length < sizeof(struct ipv6hdr)) + return -EINVAL; if (flags&MSG_PROBE) goto out; @@ -1145,8 +1147,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) - amount = skb_tail_pointer(skb) - - skb_transport_header(skb); + amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } @@ -1303,7 +1304,7 @@ void raw6_proc_exit(void) #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ -static const struct proto_ops inet6_sockraw_ops = { +const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3c5d6bb3b850..d3f87ceb3408 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1759,6 +1759,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) int addr_type; int err = -EINVAL; + /* RTF_PCPU is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_PCPU) + goto out; + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) goto out; #ifndef CONFIG_IPV6_SUBTREES @@ -2085,6 +2089,8 @@ static int ip6_route_del(struct fib6_config *cfg) continue; if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) continue; + if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) + continue; dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); @@ -2819,17 +2825,11 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list, struct rt6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; - struct rt6_info *rtnh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { /* check if rt6_info already exists */ - rtnh = nh->rt6_info; - - if (rtnh->dst.dev == rt->dst.dev && - rtnh->rt6i_idev == rt->rt6i_idev && - ipv6_addr_equal(&rtnh->rt6i_gateway, - &rt->rt6i_gateway)) + if (rt6_duplicate_nexthop(nh->rt6_info, rt)) return err; } @@ -3188,7 +3188,8 @@ static int rt6_fill_node(struct net *net, if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) goto nla_put_failure; - lwtunnel_fill_encap(skb, rt->dst.lwtstate); + if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -3354,7 +3355,10 @@ static int ip6_route_dev_notify(struct notifier_block *this, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); - if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { + if (!(dev->flags & IFF_LOOPBACK)) + return NOTIFY_OK; + + if (event == NETDEV_REGISTER) { net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -3363,6 +3367,12 @@ static int ip6_route_dev_notify(struct notifier_block *this, net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif + } else if (event == NETDEV_UNREGISTER) { + in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev); + in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev); +#endif } return NOTIFY_OK; @@ -3669,9 +3679,24 @@ static struct pernet_operations ip6_route_net_late_ops = { static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, - .priority = 0, + .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; +void __init ip6_route_init_special_entries(void) +{ + /* Registering of the loopback is done before this portion of code, + * the loopback reference in rt6_info will not be taken, do it + * manually for init_net */ + init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES + init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #endif +} + int __init ip6_route_init(void) { int ret; @@ -3698,17 +3723,6 @@ int __init ip6_route_init(void) ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; - /* Registering of the loopback is done before this portion of code, - * the loopback reference in rt6_info will not be taken, do it - * manually for init_net */ - init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; - init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); - #ifdef CONFIG_IPV6_MULTIPLE_TABLES - init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; - init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); - init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; - init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); - #endif ret = fib6_init(); if (ret) goto out_register_subsys; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3da2b16356eb..184f0fe35dc6 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1389,6 +1389,7 @@ static int ipip6_tunnel_init(struct net_device *dev) tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); + dev->tstats = NULL; return -ENOMEM; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 336843ca4e6b..7f3667635431 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -210,6 +210,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) treq->snt_synack.v64 = 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; + treq->txhash = net_tx_rndhash(); /* * We need to lookup the dst_entry to get the correct window size. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8ed00c8a128a..4618f52a4abe 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -149,8 +149,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, * connect() to INADDR_ANY means loopback (BSD'ism). */ - if (ipv6_addr_any(&usin->sin6_addr)) - usin->sin6_addr.s6_addr[15] = 0x1; + if (ipv6_addr_any(&usin->sin6_addr)) { + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), + &usin->sin6_addr); + else + usin->sin6_addr = in6addr_loopback; + } addr_type = ipv6_addr_type(&usin->sin6_addr); @@ -189,7 +194,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, * TCP over IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED) { + if (addr_type & IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; @@ -377,10 +382,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } @@ -976,6 +983,16 @@ drop: return 0; /* don't send reset */ } +static void tcp_v6_restore_cb(struct sk_buff *skb) +{ + /* We need to move header back to the beginning if xfrm6_policy_check() + * and tcp_v6_fill_cb() are going to be called again. + * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. + */ + memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, + sizeof(struct inet6_skb_parm)); +} + static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, @@ -1023,6 +1040,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; @@ -1092,6 +1110,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * First: no IPv4 options. */ newinet->inet_opt = NULL; + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; @@ -1165,8 +1184,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * sk_gfp_atomic(sk, GFP_ATOMIC)); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) + if (newnp->pktoptions) { + tcp_v6_restore_cb(newnp->pktoptions); skb_set_owner_r(newnp->pktoptions, newsk); + } } } @@ -1181,16 +1202,6 @@ out: return NULL; } -static void tcp_v6_restore_cb(struct sk_buff *skb) -{ - /* We need to move header back to the beginning if xfrm6_policy_check() - * and tcp_v6_fill_cb() are going to be called again. - * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. - */ - memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, - sizeof(struct inet6_skb_parm)); -} - /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 156a13c7ada8..cedced59ce15 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1136,6 +1136,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; daddr = &sin6->sin6_addr; + if (ipv6_addr_any(daddr) && + ipv6_addr_v4mapped(&np->saddr)) + ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), + daddr); break; case AF_INET: goto do_udp_sendmsg; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 7441e1e63893..2e3c12eeca07 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; + int err; mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) @@ -85,7 +86,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (uh->check == 0) uh->check = CSUM_MANGLED_0; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = CHECKSUM_UNNECESSARY; /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); @@ -97,7 +98,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + return ERR_PTR(err); + unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c index 0e015906f9ca..07d36573f50b 100644 --- a/net/ipv6/xfrm6_mode_ro.c +++ b/net/ipv6/xfrm6_mode_ro.c @@ -47,6 +47,8 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + if (hdr_len < 0) + return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c index 4e344105b3fd..1d3bbe6e1183 100644 --- a/net/ipv6/xfrm6_mode_transport.c +++ b/net/ipv6/xfrm6_mode_transport.c @@ -28,6 +28,8 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + if (hdr_len < 0) + return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 48d0dc89b58d..e735f781e4f3 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1168,11 +1168,10 @@ static int ipxitf_ioctl(unsigned int cmd, void __user *arg) sipx->sipx_network = ipxif->if_netnum; memcpy(sipx->sipx_node, ipxif->if_node, sizeof(sipx->sipx_node)); - rc = -EFAULT; + rc = 0; if (copy_to_user(arg, &ifr, sizeof(ifr))) - break; + rc = -EFAULT; ipxitf_put(ipxif); - rc = 0; break; } case SIOCAIPXITFCRT: diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c index acbe61c7e683..160dc89335e2 100644 --- a/net/irda/irqueue.c +++ b/net/irda/irqueue.c @@ -383,9 +383,6 @@ EXPORT_SYMBOL(hashbin_new); * for deallocating this structure if it's complex. If not the user can * just supply kfree, which should take care of the job. */ -#ifdef CONFIG_LOCKDEP -static int hashbin_lock_depth = 0; -#endif int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func) { irda_queue_t* queue; @@ -396,22 +393,27 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func) IRDA_ASSERT(hashbin->magic == HB_MAGIC, return -1;); /* Synchronize */ - if ( hashbin->hb_type & HB_LOCK ) { - spin_lock_irqsave_nested(&hashbin->hb_spinlock, flags, - hashbin_lock_depth++); - } + if (hashbin->hb_type & HB_LOCK) + spin_lock_irqsave(&hashbin->hb_spinlock, flags); /* * Free the entries in the hashbin, TODO: use hashbin_clear when * it has been shown to work */ for (i = 0; i < HASHBIN_SIZE; i ++ ) { - queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]); - while (queue ) { - if (free_func) - (*free_func)(queue); - queue = dequeue_first( - (irda_queue_t**) &hashbin->hb_queue[i]); + while (1) { + queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]); + + if (!queue) + break; + + if (free_func) { + if (hashbin->hb_type & HB_LOCK) + spin_unlock_irqrestore(&hashbin->hb_spinlock, flags); + free_func(queue); + if (hashbin->hb_type & HB_LOCK) + spin_lock_irqsave(&hashbin->hb_spinlock, flags); + } } } @@ -420,12 +422,8 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func) hashbin->magic = ~HB_MAGIC; /* Release lock */ - if ( hashbin->hb_type & HB_LOCK) { + if (hashbin->hb_type & HB_LOCK) spin_unlock_irqrestore(&hashbin->hb_spinlock, flags); -#ifdef CONFIG_LOCKDEP - hashbin_lock_depth--; -#endif - } /* * Free the hashbin structure diff --git a/net/key/af_key.c b/net/key/af_key.c index f9c9ecb0cdd3..2e1050ec2cf0 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -63,8 +63,13 @@ struct pfkey_sock { } u; struct sk_buff *skb; } dump; + struct mutex dump_lock; }; +static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, + xfrm_address_t *saddr, xfrm_address_t *daddr, + u16 *family); + static inline struct pfkey_sock *pfkey_sk(struct sock *sk) { return (struct pfkey_sock *)sk; @@ -139,6 +144,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; + struct pfkey_sock *pfk; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -153,6 +159,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, if (sk == NULL) goto out; + pfk = pfkey_sk(sk); + mutex_init(&pfk->dump_lock); + sock->ops = &pfkey_ops; sock_init_data(sock, sk); @@ -281,13 +290,23 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) struct sadb_msg *hdr; int rc; + mutex_lock(&pfk->dump_lock); + if (!pfk->dump.dump) { + rc = 0; + goto out; + } + rc = pfk->dump.dump(pfk); - if (rc == -ENOBUFS) - return 0; + if (rc == -ENOBUFS) { + rc = 0; + goto out; + } if (pfk->dump.skb) { - if (!pfkey_can_dump(&pfk->sk)) - return 0; + if (!pfkey_can_dump(&pfk->sk)) { + rc = 0; + goto out; + } hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; @@ -298,6 +317,9 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) } pfkey_terminate_dump(pfk); + +out: + mutex_unlock(&pfk->dump_lock); return rc; } @@ -1135,6 +1157,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, goto out; } + err = -ENOBUFS; key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (sa->sadb_sa_auth) { int keysize = 0; @@ -1146,8 +1169,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, if (key) keysize = (key->sadb_key_bits + 7) / 8; x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL); - if (!x->aalg) + if (!x->aalg) { + err = -ENOMEM; goto out; + } strcpy(x->aalg->alg_name, a->name); x->aalg->alg_key_len = 0; if (key) { @@ -1166,8 +1191,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, goto out; } x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL); - if (!x->calg) + if (!x->calg) { + err = -ENOMEM; goto out; + } strcpy(x->calg->alg_name, a->name); x->props.calgo = sa->sadb_sa_encrypt; } else { @@ -1181,8 +1208,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, if (key) keysize = (key->sadb_key_bits + 7) / 8; x->ealg = kmalloc(sizeof(*x->ealg) + keysize, GFP_KERNEL); - if (!x->ealg) + if (!x->ealg) { + err = -ENOMEM; goto out; + } strcpy(x->ealg->alg_name, a->name); x->ealg->alg_key_len = 0; if (key) { @@ -1227,8 +1256,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, struct xfrm_encap_tmpl *natt; x->encap = kmalloc(sizeof(*x->encap), GFP_KERNEL); - if (!x->encap) + if (!x->encap) { + err = -ENOMEM; goto out; + } natt = x->encap; n_type = ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]; @@ -1793,19 +1824,26 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms struct xfrm_address_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); - if (pfk->dump.dump != NULL) + mutex_lock(&pfk->dump_lock); + if (pfk->dump.dump != NULL) { + mutex_unlock(&pfk->dump_lock); return -EBUSY; + } proto = pfkey_satype2proto(hdr->sadb_msg_satype); - if (proto == 0) + if (proto == 0) { + mutex_unlock(&pfk->dump_lock); return -EINVAL; + } if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; filter = kmalloc(sizeof(*filter), GFP_KERNEL); - if (filter == NULL) + if (filter == NULL) { + mutex_unlock(&pfk->dump_lock); return -ENOMEM; + } memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, sizeof(xfrm_address_t)); @@ -1821,6 +1859,7 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); + mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } @@ -1913,19 +1952,14 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) /* addresses present only in tunnel mode */ if (t->mode == XFRM_MODE_TUNNEL) { - u8 *sa = (u8 *) (rq + 1); - int family, socklen; - - family = pfkey_sockaddr_extract((struct sockaddr *)sa, - &t->saddr); - if (!family) - return -EINVAL; + int err; - socklen = pfkey_sockaddr_len(family); - if (pfkey_sockaddr_extract((struct sockaddr *)(sa + socklen), - &t->id.daddr) != family) - return -EINVAL; - t->encap_family = family; + err = parse_sockaddr_pair( + (struct sockaddr *)(rq + 1), + rq->sadb_x_ipsecrequest_len - sizeof(*rq), + &t->saddr, &t->id.daddr, &t->encap_family); + if (err) + return err; } else t->encap_family = xp->family; @@ -1945,7 +1979,11 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy)) return -EINVAL; - while (len >= sizeof(struct sadb_x_ipsecrequest)) { + while (len >= sizeof(*rq)) { + if (len < rq->sadb_x_ipsecrequest_len || + rq->sadb_x_ipsecrequest_len < sizeof(*rq)) + return -EINVAL; + if ((err = parse_ipsecrequest(xp, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; @@ -2408,7 +2446,6 @@ out: return err; } -#ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_sockaddr_pair_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2); @@ -2420,7 +2457,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, { int af, socklen; - if (ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) + if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) return -EINVAL; af = pfkey_sockaddr_extract(sa, saddr); @@ -2436,6 +2473,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, return 0; } +#ifdef CONFIG_NET_KEY_MIGRATE static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct xfrm_migrate *m) { @@ -2443,13 +2481,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct sadb_x_ipsecrequest *rq2; int mode; - if (len <= sizeof(struct sadb_x_ipsecrequest) || - len < rq1->sadb_x_ipsecrequest_len) + if (len < sizeof(*rq1) || + len < rq1->sadb_x_ipsecrequest_len || + rq1->sadb_x_ipsecrequest_len < sizeof(*rq1)) return -EINVAL; /* old endoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1), - rq1->sadb_x_ipsecrequest_len, + rq1->sadb_x_ipsecrequest_len - sizeof(*rq1), &m->old_saddr, &m->old_daddr, &m->old_family); if (err) @@ -2458,13 +2497,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len); len -= rq1->sadb_x_ipsecrequest_len; - if (len <= sizeof(struct sadb_x_ipsecrequest) || - len < rq2->sadb_x_ipsecrequest_len) + if (len <= sizeof(*rq2) || + len < rq2->sadb_x_ipsecrequest_len || + rq2->sadb_x_ipsecrequest_len < sizeof(*rq2)) return -EINVAL; /* new endpoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1), - rq2->sadb_x_ipsecrequest_len, + rq2->sadb_x_ipsecrequest_len - sizeof(*rq2), &m->new_saddr, &m->new_daddr, &m->new_family); if (err) @@ -2679,14 +2719,18 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb { struct pfkey_sock *pfk = pfkey_sk(sk); - if (pfk->dump.dump != NULL) + mutex_lock(&pfk->dump_lock); + if (pfk->dump.dump != NULL) { + mutex_unlock(&pfk->dump_lock); return -EBUSY; + } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sp; pfk->dump.done = pfkey_dump_sp_done; xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN); + mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ec17cbe8a02b..d3dec414fd44 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -278,7 +278,8 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn } EXPORT_SYMBOL_GPL(l2tp_session_find); -struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, + bool do_ref) { int hash; struct l2tp_session *session; @@ -288,6 +289,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) { if (++count > nth) { + l2tp_session_inc_refcount(session); + if (do_ref && session->ref) + session->ref(session); read_unlock_bh(&tunnel->hlist_lock); return session; } @@ -298,7 +302,7 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) return NULL; } -EXPORT_SYMBOL_GPL(l2tp_session_find_nth); +EXPORT_SYMBOL_GPL(l2tp_session_get_nth); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 5871537af387..555d962a62d2 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -243,7 +243,8 @@ out: struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); -struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth); +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, + bool do_ref); struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname); struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth); @@ -273,6 +274,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops); void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); +int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); /* Session reference counts. Incremented when code obtains a reference * to a session. diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 2d6760a2ae34..d100aed3d06f 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { - pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); pd->session_idx++; if (pd->session == NULL) { @@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v) } /* Show the tunnel or session context */ - if (pd->session == NULL) + if (!pd->session) { l2tp_dfs_seq_tunnel_show(m, pd->tunnel); - else + } else { l2tp_dfs_seq_session_show(m, pd->session); + if (pd->session->deref) + pd->session->deref(pd->session); + l2tp_session_dec_refcount(pd->session); + } out: return 0; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index d0e906d39642..48ab93842322 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <asm/ioctls.h> #include <linux/icmp.h> #include <linux/module.h> #include <linux/skbuff.h> @@ -382,7 +383,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) drop: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); - return -1; + return 0; } /* Userspace will call sendmsg() on the tunnel socket to send L2TP @@ -555,6 +556,30 @@ out: return err ? err : copied; } +int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg) +{ + struct sk_buff *skb; + int amount; + + switch (cmd) { + case SIOCOUTQ: + amount = sk_wmem_alloc_get(sk); + break; + case SIOCINQ: + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + amount = skb ? skb->len : 0; + spin_unlock_bh(&sk->sk_receive_queue.lock); + break; + + default: + return -ENOIOCTLCMD; + } + + return put_user(amount, (int __user *)arg); +} +EXPORT_SYMBOL(l2tp_ioctl); + static struct proto l2tp_ip_prot = { .name = "L2TP/IP", .owner = THIS_MODULE, @@ -563,7 +588,7 @@ static struct proto l2tp_ip_prot = { .bind = l2tp_ip_bind, .connect = l2tp_ip_connect, .disconnect = l2tp_ip_disconnect, - .ioctl = udp_ioctl, + .ioctl = l2tp_ioctl, .destroy = l2tp_ip_destroy_sock, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 0289208b0346..c8f483cd2ca9 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -715,7 +715,7 @@ static struct proto l2tp_ip6_prot = { .bind = l2tp_ip6_bind, .connect = l2tp_ip6_connect, .disconnect = l2tp_ip6_disconnect, - .ioctl = udp_ioctl, + .ioctl = l2tp_ioctl, .destroy = l2tp_ip6_destroy_sock, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 2caaa84ce92d..665cc74df5c5 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -827,7 +827,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback goto out; } - session = l2tp_session_find_nth(tunnel, si); + session = l2tp_session_get_nth(tunnel, si, false); if (session == NULL) { ti++; tunnel = NULL; @@ -837,8 +837,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - session, L2TP_CMD_SESSION_GET) < 0) + session, L2TP_CMD_SESSION_GET) < 0) { + l2tp_session_dec_refcount(session); break; + } + l2tp_session_dec_refcount(session); si++; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1ad18c55064c..8ab9c5d74416 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -467,6 +467,10 @@ static void pppol2tp_session_close(struct l2tp_session *session) static void pppol2tp_session_destruct(struct sock *sk) { struct l2tp_session *session = sk->sk_user_data; + + skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge(&sk->sk_write_queue); + if (session) { sk->sk_user_data = NULL; BUG_ON(session->magic != L2TP_SESSION_MAGIC); @@ -505,9 +509,6 @@ static int pppol2tp_release(struct socket *sock) l2tp_session_queue_purge(session); sock_put(sk); } - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); - release_sock(sk); /* This will delete the session context via @@ -1574,7 +1575,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { - pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); pd->session_idx++; if (pd->session == NULL) { @@ -1701,10 +1702,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v) /* Show the tunnel or session context. */ - if (pd->session == NULL) + if (!pd->session) { pppol2tp_seq_tunnel_show(m, pd->tunnel); - else + } else { pppol2tp_seq_session_show(m, pd->session); + if (pd->session->deref) + pd->session->deref(pd->session); + l2tp_session_dec_refcount(pd->session); + } out: return 0; @@ -1863,4 +1868,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP"); MODULE_LICENSE("GPL"); MODULE_VERSION(PPPOL2TP_DRV_VERSION); MODULE_ALIAS("pppox-proto-" __stringify(PX_PROTO_OL2TP)); -MODULE_ALIAS_L2TP_PWTYPE(11); +MODULE_ALIAS_L2TP_PWTYPE(7); diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 3e821daf9dd4..8bc5a1bd2d45 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -821,7 +821,10 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) * another trick required to cope with how the PROCOM state * machine works. -acme */ + skb_orphan(skb); + sock_hold(sk); skb->sk = sk; + skb->destructor = sock_efree; } if (!sock_owned_by_user(sk)) llc_conn_rcv(sk, skb); diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index d0e1e804ebd7..5404d0d195cc 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -290,7 +290,10 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, ev->type = LLC_SAP_EV_TYPE_PDU; ev->reason = 0; + skb_orphan(skb); + sock_hold(sk); skb->sk = sk; + skb->destructor = sock_efree; llc_sap_state_process(sap, skb); } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index bd06799e2e69..3bbbcaf1ec0b 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -7,6 +7,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation + * Copyright(c) 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -61,6 +62,14 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, { struct ieee80211_local *local = sta->local; struct tid_ampdu_rx *tid_rx; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_RX_STOP, + .tid = tid, + .amsdu = false, + .timeout = 0, + .ssn = 0, + }; lockdep_assert_held(&sta->ampdu_mlme.mtx); @@ -78,8 +87,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, initiator == WLAN_BACK_RECIPIENT ? "recipient" : "inititator", (int)reason); - if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP, - &sta->sta, tid, NULL, 0, false)) + if (drv_ampdu_action(local, sta->sdata, ¶ms)) sdata_info(sta->sdata, "HW problem - can not stop rx aggregation for %pM tid %d\n", sta->sta.addr, tid); @@ -259,6 +267,15 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, { struct ieee80211_local *local = sta->sdata->local; struct tid_ampdu_rx *tid_agg_rx; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_RX_START, + .tid = tid, + .amsdu = false, + .timeout = timeout, + .ssn = start_seq_num, + }; + int i, ret = -EOPNOTSUPP; u16 status = WLAN_STATUS_REQUEST_DECLINED; @@ -301,7 +318,10 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, if (buf_size > sta->sta.max_rx_aggregation_subframes) buf_size = sta->sta.max_rx_aggregation_subframes; - ht_dbg(sta->sdata, "AddBA Req buf_size=%d\n", buf_size); + params.buf_size = buf_size; + + ht_dbg(sta->sdata, "AddBA Req buf_size=%d for %pM\n", + buf_size, sta->sta.addr); if (sta->ampdu_mlme.tid_rx[tid]) { ht_dbg_ratelimited(sta->sdata, @@ -346,8 +366,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, for (i = 0; i < buf_size; i++) __skb_queue_head_init(&tid_agg_rx->reorder_buf[i]); - ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, - &sta->sta, tid, &start_seq_num, 0, false); + ret = drv_ampdu_action(local, sta->sdata, ¶ms); ht_dbg(sta->sdata, "Rx A-MPDU request on %pM tid %d result %d\n", sta->sta.addr, tid, ret); if (ret) { diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index ff757181b0a8..4932e9f243a2 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -7,6 +7,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation + * Copyright(c) 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -295,7 +296,14 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, { struct ieee80211_local *local = sta->local; struct tid_ampdu_tx *tid_tx; - enum ieee80211_ampdu_mlme_action action; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .tid = tid, + .buf_size = 0, + .amsdu = false, + .timeout = 0, + .ssn = 0, + }; int ret; lockdep_assert_held(&sta->ampdu_mlme.mtx); @@ -304,10 +312,10 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, case AGG_STOP_DECLINED: case AGG_STOP_LOCAL_REQUEST: case AGG_STOP_PEER_REQUEST: - action = IEEE80211_AMPDU_TX_STOP_CONT; + params.action = IEEE80211_AMPDU_TX_STOP_CONT; break; case AGG_STOP_DESTROY_STA: - action = IEEE80211_AMPDU_TX_STOP_FLUSH; + params.action = IEEE80211_AMPDU_TX_STOP_FLUSH; break; default: WARN_ON_ONCE(1); @@ -330,9 +338,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, spin_unlock_bh(&sta->lock); if (reason != AGG_STOP_DESTROY_STA) return -EALREADY; - ret = drv_ampdu_action(local, sta->sdata, - IEEE80211_AMPDU_TX_STOP_FLUSH_CONT, - &sta->sta, tid, NULL, 0, false); + params.action = IEEE80211_AMPDU_TX_STOP_FLUSH_CONT; + ret = drv_ampdu_action(local, sta->sdata, ¶ms); WARN_ON_ONCE(ret); return 0; } @@ -381,8 +388,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, WLAN_BACK_INITIATOR; tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST; - ret = drv_ampdu_action(local, sta->sdata, action, - &sta->sta, tid, NULL, 0, false); + ret = drv_ampdu_action(local, sta->sdata, ¶ms); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { @@ -445,7 +451,14 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - u16 start_seq_num; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_TX_START, + .tid = tid, + .buf_size = 0, + .amsdu = false, + .timeout = 0, + }; int ret; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); @@ -467,10 +480,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ synchronize_net(); - start_seq_num = sta->tid_seq[tid] >> 4; - - ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START, - &sta->sta, tid, &start_seq_num, 0, false); + params.ssn = sta->tid_seq[tid] >> 4; + ret = drv_ampdu_action(local, sdata, ¶ms); if (ret) { ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", @@ -499,7 +510,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, - tid_tx->dialog_token, start_seq_num, + tid_tx->dialog_token, params.ssn, IEEE80211_MAX_AMPDU_BUF, tid_tx->timeout); } @@ -684,18 +695,24 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, struct sta_info *sta, u16 tid) { struct tid_ampdu_tx *tid_tx; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_TX_OPERATIONAL, + .tid = tid, + .timeout = 0, + .ssn = 0, + }; lockdep_assert_held(&sta->ampdu_mlme.mtx); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); + params.buf_size = tid_tx->buf_size; + params.amsdu = tid_tx->amsdu; ht_dbg(sta->sdata, "Aggregation is on for %pM tid %d\n", sta->sta.addr, tid); - drv_ampdu_action(local, sta->sdata, - IEEE80211_AMPDU_TX_OPERATIONAL, - &sta->sta, tid, NULL, tid_tx->buf_size, - tid_tx->amsdu); + drv_ampdu_action(local, sta->sdata, ¶ms); /* * synchronize with TX path, while splicing the TX path diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index ca1fe5576103..c258f1041d33 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -284,9 +284,7 @@ int drv_switch_vif_chanctx(struct ieee80211_local *local, int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { int ret = -EOPNOTSUPP; @@ -296,12 +294,10 @@ int drv_ampdu_action(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - trace_drv_ampdu_action(local, sdata, action, sta, tid, - ssn, buf_size, amsdu); + trace_drv_ampdu_action(local, sdata, params); if (local->ops->ampdu_action) - ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action, - sta, tid, ssn, buf_size, amsdu); + ret = local->ops->ampdu_action(&local->hw, &sdata->vif, params); trace_drv_return_int(local, ret); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 154ce4b13406..18b0d65baff0 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -585,9 +585,7 @@ static inline int drv_tx_last_beacon(struct ieee80211_local *local) int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); static inline int drv_get_survey(struct ieee80211_local *local, int idx, struct survey_info *survey) diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 980e9e9b6684..24ba31601fc9 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -66,6 +66,8 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, 2 + (IEEE80211_MAX_SUPP_RATES - 8) + 2 + sizeof(struct ieee80211_ht_cap) + 2 + sizeof(struct ieee80211_ht_operation) + + 2 + sizeof(struct ieee80211_vht_cap) + + 2 + sizeof(struct ieee80211_vht_operation) + ifibss->ie_len; presp = kzalloc(sizeof(*presp) + frame_len, GFP_KERNEL); if (!presp) @@ -486,14 +488,14 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, struct beacon_data *presp, *old_presp; struct cfg80211_bss *cbss; const struct cfg80211_bss_ies *ies; - u16 capability = 0; + u16 capability = WLAN_CAPABILITY_IBSS; u64 tsf; int ret = 0; sdata_assert_lock(sdata); if (ifibss->privacy) - capability = WLAN_CAPABILITY_PRIVACY; + capability |= WLAN_CAPABILITY_PRIVACY; cbss = cfg80211_get_bss(sdata->local->hw.wiphy, ifibss->chandef.chan, ifibss->bssid, ifibss->ssid, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 175ffcf7fb06..2ee53dc1ddf7 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -891,12 +891,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; - if (sband->ht_cap.ht_supported) - local->rx_chains = - max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs), - local->rx_chains); + if (!sband->ht_cap.ht_supported) + continue; /* TODO: consider VHT for RX chains, hopefully it's the same */ + local->rx_chains = + max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs), + local->rx_chains); + + /* no need to mask, SM_PS_DISABLED has all bits set */ + sband->ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED << + IEEE80211_HT_CAP_SM_PS_SHIFT; } /* if low-level driver supports AP, we also support VLAN */ diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index f7bb6829b415..9063e8e736ad 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -355,7 +355,7 @@ int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata, /* fast-forward to vendor IEs */ offset = ieee80211_ie_split_vendor(ifmsh->ie, ifmsh->ie_len, 0); - if (offset) { + if (offset < ifmsh->ie_len) { len = ifmsh->ie_len - offset; data = ifmsh->ie + offset; if (skb_tailroom(skb) < len) diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 00a43a70e1fc..0402fa45b343 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -168,6 +168,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) break; } + flush_delayed_work(&sdata->dec_tailroom_needed_wk); drv_remove_interface(local, sdata); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 2b528389409f..3bcabc2ba4a6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1455,12 +1455,16 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) */ if (!ieee80211_hw_check(&sta->local->hw, AP_LINK_PS) && !ieee80211_has_morefrags(hdr->frame_control) && + !ieee80211_is_back_req(hdr->frame_control) && !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && (rx->sdata->vif.type == NL80211_IFTYPE_AP || rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && - /* PM bit is only checked in frames where it isn't reserved, + /* + * PM bit is only checked in frames where it isn't reserved, * in AP mode it's reserved in non-bufferable management frames * (cf. IEEE 802.11-2012 8.2.4.1.7 Power Management field) + * BAR frames should be ignored as specified in + * IEEE 802.11-2012 10.2.1.2. */ (!ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_bufferable_mmpdu(hdr->frame_control))) { @@ -3396,6 +3400,27 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) !ether_addr_equal(bssid, hdr->addr1)) return false; } + + /* + * 802.11-2016 Table 9-26 says that for data frames, A1 must be + * the BSSID - we've checked that already but may have accepted + * the wildcard (ff:ff:ff:ff:ff:ff). + * + * It also says: + * The BSSID of the Data frame is determined as follows: + * a) If the STA is contained within an AP or is associated + * with an AP, the BSSID is the address currently in use + * by the STA contained in the AP. + * + * So we should not accept data frames with an address that's + * multicast. + * + * Accepting it also opens a security problem because stations + * could encrypt it with the GTK and inject traffic that way. + */ + if (ieee80211_is_data(hdr->frame_control) && multicast) + return false; + return true; case NL80211_IFTYPE_WDS: if (bssid || !ieee80211_is_data(hdr->frame_control)) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 56c6d6cfa5a1..913e959b03cf 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -80,7 +80,23 @@ #define KEY_PR_FMT " cipher:0x%x, flags=%#x, keyidx=%d, hw_key_idx=%d" #define KEY_PR_ARG __entry->cipher, __entry->flags, __entry->keyidx, __entry->hw_key_idx - +#define AMPDU_ACTION_ENTRY __field(enum ieee80211_ampdu_mlme_action, \ + ieee80211_ampdu_mlme_action) \ + STA_ENTRY \ + __field(u16, tid) \ + __field(u16, ssn) \ + __field(u8, buf_size) \ + __field(bool, amsdu) \ + __field(u16, timeout) +#define AMPDU_ACTION_ASSIGN STA_NAMED_ASSIGN(params->sta); \ + __entry->tid = params->tid; \ + __entry->ssn = params->ssn; \ + __entry->buf_size = params->buf_size; \ + __entry->amsdu = params->amsdu; \ + __entry->timeout = params->timeout; +#define AMPDU_ACTION_PR_FMT STA_PR_FMT " tid %d, ssn %d, buf_size %u, amsdu %d, timeout %d" +#define AMPDU_ACTION_PR_ARG STA_PR_ARG, __entry->tid, __entry->ssn, \ + __entry->buf_size, __entry->amsdu, __entry->timeout /* * Tracing for driver callbacks. @@ -970,38 +986,25 @@ DEFINE_EVENT(local_only_evt, drv_tx_last_beacon, TRACE_EVENT(drv_ampdu_action, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu), + struct ieee80211_ampdu_params *params), - TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size, amsdu), + TP_ARGS(local, sdata, params), TP_STRUCT__entry( LOCAL_ENTRY - STA_ENTRY - __field(u32, action) - __field(u16, tid) - __field(u16, ssn) - __field(u8, buf_size) - __field(bool, amsdu) VIF_ENTRY + AMPDU_ACTION_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; - STA_ASSIGN; - __entry->action = action; - __entry->tid = tid; - __entry->ssn = ssn ? *ssn : 0; - __entry->buf_size = buf_size; - __entry->amsdu = amsdu; + AMPDU_ACTION_ASSIGN; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d amsdu:%d", - LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, - __entry->tid, __entry->buf_size, __entry->amsdu + LOCAL_PR_FMT VIF_PR_FMT AMPDU_ACTION_PR_FMT, + LOCAL_PR_ARG, VIF_PR_ARG, AMPDU_ACTION_PR_ARG ) ); diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index d824c38971ed..e19ea1c53afa 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -16,6 +16,7 @@ #include <asm/unaligned.h> #include <net/mac80211.h> #include <crypto/aes.h> +#include <crypto/algapi.h> #include "ieee80211_i.h" #include "michael.h" @@ -152,7 +153,7 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) data_len = skb->len - hdrlen - MICHAEL_MIC_LEN; key = &rx->key->conf.key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY]; michael_mic(key, hdr, data, data_len, mic); - if (memcmp(mic, data + data_len, MICHAEL_MIC_LEN) != 0) + if (crypto_memneq(mic, data + data_len, MICHAEL_MIC_LEN)) goto mic_fail; /* remove Michael MIC from payload */ @@ -1044,7 +1045,7 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx) bip_aad(skb, aad); ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad, skb->data + 24, skb->len - 24, mic); - if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) { + if (crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) { key->u.aes_cmac.icverrors++; return RX_DROP_UNUSABLE; } @@ -1094,7 +1095,7 @@ ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx) bip_aad(skb, aad); ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad, skb->data + 24, skb->len - 24, mic); - if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) { + if (crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) { key->u.aes_cmac.icverrors++; return RX_DROP_UNUSABLE; } @@ -1198,7 +1199,7 @@ ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx) if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce, skb->data + 24, skb->len - 24, mic) < 0 || - memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) { + crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) { key->u.aes_gmac.icverrors++; return RX_DROP_UNUSABLE; } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 881bc2072809..52cfc4478511 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1567,6 +1567,7 @@ static void mpls_net_exit(struct net *net) for (index = 0; index < platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); RCU_INIT_POINTER(platform_label[index], NULL); + mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } rtnl_unlock(); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4da560005b0e..dd1649caa2b2 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -845,10 +845,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, { unsigned int verdict = NF_DROP; - if (IP_VS_FWD_METHOD(cp) != 0) { - pr_err("shouldn't reach here, because the box is on the " - "half connection in the tun/dr module.\n"); - } + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) + goto ignore_cp; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { @@ -882,6 +880,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); + +ignore_cp: verdict = NF_ACCEPT; out: @@ -1242,8 +1242,11 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in */ cp = pp->conn_out_get(ipvs, af, skb, &iph); - if (likely(cp)) + if (likely(cp)) { + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) + goto ignore_cp; return handle_response(af, skb, pd, cp, &iph, hooknum); + } if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || @@ -1285,9 +1288,15 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in } } } + +out: IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; + +ignore_cp: + __ip_vs_conn_put(cp); + goto out; } /* diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 1a9545965c0d..531ca55f1af6 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -53,7 +53,11 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, rcu_read_lock(); t = rcu_dereference(nf_ct_ext_types[id]); - BUG_ON(t == NULL); + if (!t) { + rcu_read_unlock(); + return NULL; + } + off = ALIGN(sizeof(struct nf_ct_ext), t->align); len = off + t->len + var_alloc_len; alloc_size = t->alloc_size + var_alloc_len; @@ -88,7 +92,10 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, rcu_read_lock(); t = rcu_dereference(nf_ct_ext_types[id]); - BUG_ON(t == NULL); + if (!t) { + rcu_read_unlock(); + return NULL; + } newoff = ALIGN(old->len, t->align); newlen = newoff + t->len + var_alloc_len; @@ -186,6 +193,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type) RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL); update_alloc_size(type); mutex_unlock(&nf_ct_ext_type_mutex); - rcu_barrier(); /* Wait for completion of call_rcu()'s */ + synchronize_rcu(); } EXPORT_SYMBOL_GPL(nf_ct_extend_unregister); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9f5272968abb..e565b2becb14 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -45,6 +45,8 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_labels.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/nf_conntrack_synproxy.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_l4proto.h> @@ -1798,6 +1800,8 @@ ctnetlink_create_conntrack(struct net *net, nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); nf_ct_labels_ext_add(ct); + nfct_seqadj_ext_add(ct); + nfct_synproxy_ext_add(ct); /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 0975c993a94e..f11aa28b96ce 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -49,6 +49,7 @@ #include <linux/notifier.h> #include <net/net_namespace.h> #include <net/sock.h> +#include <net/inet_sock.h> struct idletimer_tg_attr { struct attribute attr; @@ -355,7 +356,7 @@ static void reset_timer(const struct idletimer_tg_info *info, /* Stores the uid resposible for waking up the radio */ if (skb && (skb->sk)) { timer->uid = from_kuid_munged(current_user_ns(), - sock_i_uid(skb->sk)); + sock_i_uid(skb_to_full_sk(skb))); } /* checks if there is a pending inactive notification*/ @@ -456,6 +457,7 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) del_timer_sync(&info->timer->timer); sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); unregister_pm_notifier(&info->timer->pm_nb); + cancel_work_sync(&info->timer->work); kfree(info->timer->attr.attr.name); kfree(info->timer); } else { diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index b7c43def0dc6..00f798b20b20 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -104,7 +104,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); tcp_hdrlen = tcph->doff * 4; - if (len < tcp_hdrlen) + if (len < tcp_hdrlen || tcp_hdrlen < sizeof(struct tcphdr)) return -1; if (info->mss == XT_TCPMSS_CLAMP_PMTU) { @@ -156,6 +156,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (len > tcp_hdrlen) return 0; + /* tcph->doff has 4 bits, do not wrap it to 0 */ + if (tcp_hdrlen >= 15 * 4) + return 0; + /* * MSS Option not found ?! add it.. */ diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c index 3bf0c59dab2f..0f5628a59917 100644 --- a/net/netfilter/xt_qtaguid.c +++ b/net/netfilter/xt_qtaguid.c @@ -1814,8 +1814,11 @@ ret_res: } #ifdef DDEBUG -/* This function is not in xt_qtaguid_print.c because of locks visibility */ -static void prdebug_full_state(int indent_level, const char *fmt, ...) +/* + * This function is not in xt_qtaguid_print.c because of locks visibility. + * The lock of sock_tag_list must be aquired before calling this function + */ +static void prdebug_full_state_locked(int indent_level, const char *fmt, ...) { va_list args; char *fmt_buff; @@ -1836,16 +1839,12 @@ static void prdebug_full_state(int indent_level, const char *fmt, ...) kfree(buff); va_end(args); - spin_lock_bh(&sock_tag_list_lock); prdebug_sock_tag_tree(indent_level, &sock_tag_tree); - spin_unlock_bh(&sock_tag_list_lock); - spin_lock_bh(&sock_tag_list_lock); spin_lock_bh(&uid_tag_data_tree_lock); prdebug_uid_tag_data_tree(indent_level, &uid_tag_data_tree); prdebug_proc_qtu_data_tree(indent_level, &proc_qtu_data_tree); spin_unlock_bh(&uid_tag_data_tree_lock); - spin_unlock_bh(&sock_tag_list_lock); spin_lock_bh(&iface_stat_list_lock); prdebug_iface_stat_list(indent_level, &iface_stat_list); @@ -1854,7 +1853,7 @@ static void prdebug_full_state(int indent_level, const char *fmt, ...) pr_debug("qtaguid: %s(): }\n", __func__); } #else -static void prdebug_full_state(int indent_level, const char *fmt, ...) {} +static void prdebug_full_state_locked(int indent_level, const char *fmt, ...) {} #endif struct proc_ctrl_print_info { @@ -1977,8 +1976,11 @@ static int qtaguid_ctrl_proc_show(struct seq_file *m, void *v) (u64)atomic64_read(&qtu_events.match_no_sk), (u64)atomic64_read(&qtu_events.match_no_sk_file)); - /* Count the following as part of the last item_index */ - prdebug_full_state(0, "proc ctrl"); + /* Count the following as part of the last item_index. No need + * to lock the sock_tag_list here since it is already locked when + * starting the seq_file operation + */ + prdebug_full_state_locked(0, "proc ctrl"); } return 0; @@ -2887,8 +2889,10 @@ static int qtudev_release(struct inode *inode, struct file *file) sock_tag_tree_erase(&st_to_free_tree); - prdebug_full_state(0, "%s(): pid=%u tgid=%u", __func__, + spin_lock_bh(&sock_tag_list_lock); + prdebug_full_state_locked(0, "%s(): pid=%u tgid=%u", __func__, current->pid, current->tgid); + spin_unlock_bh(&sock_tag_list_lock); return 0; } diff --git a/net/netlink/Kconfig b/net/netlink/Kconfig index 2c5e95e9bfbd..5d6e8c05b3d4 100644 --- a/net/netlink/Kconfig +++ b/net/netlink/Kconfig @@ -2,15 +2,6 @@ # Netlink Sockets # -config NETLINK_MMAP - bool "NETLINK: mmaped IO" - ---help--- - This option enables support for memory mapped netlink IO. This - reduces overhead by avoiding copying data between kernel- and - userspace. - - If unsure, say N. - config NETLINK_DIAG tristate "NETLINK: socket monitoring interface" default n diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 360700a2f46c..acfb16fdcd55 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -225,7 +225,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, dev_hold(dev); - if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head)) + if (is_vmalloc_addr(skb->head)) nskb = netlink_to_full_skb(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); @@ -300,610 +300,8 @@ static void netlink_rcv_wake(struct sock *sk) wake_up_interruptible(&nlk->wait); } -#ifdef CONFIG_NETLINK_MMAP -static bool netlink_rx_is_mmaped(struct sock *sk) -{ - return nlk_sk(sk)->rx_ring.pg_vec != NULL; -} - -static bool netlink_tx_is_mmaped(struct sock *sk) -{ - return nlk_sk(sk)->tx_ring.pg_vec != NULL; -} - -static __pure struct page *pgvec_to_page(const void *addr) -{ - if (is_vmalloc_addr(addr)) - return vmalloc_to_page(addr); - else - return virt_to_page(addr); -} - -static void free_pg_vec(void **pg_vec, unsigned int order, unsigned int len) -{ - unsigned int i; - - for (i = 0; i < len; i++) { - if (pg_vec[i] != NULL) { - if (is_vmalloc_addr(pg_vec[i])) - vfree(pg_vec[i]); - else - free_pages((unsigned long)pg_vec[i], order); - } - } - kfree(pg_vec); -} - -static void *alloc_one_pg_vec_page(unsigned long order) -{ - void *buffer; - gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | - __GFP_NOWARN | __GFP_NORETRY; - - buffer = (void *)__get_free_pages(gfp_flags, order); - if (buffer != NULL) - return buffer; - - buffer = vzalloc((1 << order) * PAGE_SIZE); - if (buffer != NULL) - return buffer; - - gfp_flags &= ~__GFP_NORETRY; - return (void *)__get_free_pages(gfp_flags, order); -} - -static void **alloc_pg_vec(struct netlink_sock *nlk, - struct nl_mmap_req *req, unsigned int order) -{ - unsigned int block_nr = req->nm_block_nr; - unsigned int i; - void **pg_vec; - - pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL); - if (pg_vec == NULL) - return NULL; - - for (i = 0; i < block_nr; i++) { - pg_vec[i] = alloc_one_pg_vec_page(order); - if (pg_vec[i] == NULL) - goto err1; - } - - return pg_vec; -err1: - free_pg_vec(pg_vec, order, block_nr); - return NULL; -} - - -static void -__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec, - unsigned int order) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct sk_buff_head *queue; - struct netlink_ring *ring; - - queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; - ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring; - - spin_lock_bh(&queue->lock); - - ring->frame_max = req->nm_frame_nr - 1; - ring->head = 0; - ring->frame_size = req->nm_frame_size; - ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE; - - swap(ring->pg_vec_len, req->nm_block_nr); - swap(ring->pg_vec_order, order); - swap(ring->pg_vec, pg_vec); - - __skb_queue_purge(queue); - spin_unlock_bh(&queue->lock); - - WARN_ON(atomic_read(&nlk->mapped)); - - if (pg_vec) - free_pg_vec(pg_vec, order, req->nm_block_nr); -} - -static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, - bool tx_ring) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring; - void **pg_vec = NULL; - unsigned int order = 0; - - ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring; - - if (atomic_read(&nlk->mapped)) - return -EBUSY; - if (atomic_read(&ring->pending)) - return -EBUSY; - - if (req->nm_block_nr) { - if (ring->pg_vec != NULL) - return -EBUSY; - - if ((int)req->nm_block_size <= 0) - return -EINVAL; - if (!PAGE_ALIGNED(req->nm_block_size)) - return -EINVAL; - if (req->nm_frame_size < NL_MMAP_HDRLEN) - return -EINVAL; - if (!IS_ALIGNED(req->nm_frame_size, NL_MMAP_MSG_ALIGNMENT)) - return -EINVAL; - - ring->frames_per_block = req->nm_block_size / - req->nm_frame_size; - if (ring->frames_per_block == 0) - return -EINVAL; - if (ring->frames_per_block * req->nm_block_nr != - req->nm_frame_nr) - return -EINVAL; - - order = get_order(req->nm_block_size); - pg_vec = alloc_pg_vec(nlk, req, order); - if (pg_vec == NULL) - return -ENOMEM; - } else { - if (req->nm_frame_nr) - return -EINVAL; - } - - mutex_lock(&nlk->pg_vec_lock); - if (atomic_read(&nlk->mapped) == 0) { - __netlink_set_ring(sk, req, tx_ring, pg_vec, order); - mutex_unlock(&nlk->pg_vec_lock); - return 0; - } - - mutex_unlock(&nlk->pg_vec_lock); - - if (pg_vec) - free_pg_vec(pg_vec, order, req->nm_block_nr); - - return -EBUSY; -} - -static void netlink_mm_open(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - struct socket *sock = file->private_data; - struct sock *sk = sock->sk; - - if (sk) - atomic_inc(&nlk_sk(sk)->mapped); -} - -static void netlink_mm_close(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - struct socket *sock = file->private_data; - struct sock *sk = sock->sk; - - if (sk) - atomic_dec(&nlk_sk(sk)->mapped); -} - -static const struct vm_operations_struct netlink_mmap_ops = { - .open = netlink_mm_open, - .close = netlink_mm_close, -}; - -static int netlink_mmap(struct file *file, struct socket *sock, - struct vm_area_struct *vma) -{ - struct sock *sk = sock->sk; - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring; - unsigned long start, size, expected; - unsigned int i; - int err = -EINVAL; - - if (vma->vm_pgoff) - return -EINVAL; - - mutex_lock(&nlk->pg_vec_lock); - - expected = 0; - for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) { - if (ring->pg_vec == NULL) - continue; - expected += ring->pg_vec_len * ring->pg_vec_pages * PAGE_SIZE; - } - - if (expected == 0) - goto out; - - size = vma->vm_end - vma->vm_start; - if (size != expected) - goto out; - - start = vma->vm_start; - for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) { - if (ring->pg_vec == NULL) - continue; - - for (i = 0; i < ring->pg_vec_len; i++) { - struct page *page; - void *kaddr = ring->pg_vec[i]; - unsigned int pg_num; - - for (pg_num = 0; pg_num < ring->pg_vec_pages; pg_num++) { - page = pgvec_to_page(kaddr); - err = vm_insert_page(vma, start, page); - if (err < 0) - goto out; - start += PAGE_SIZE; - kaddr += PAGE_SIZE; - } - } - } - - atomic_inc(&nlk->mapped); - vma->vm_ops = &netlink_mmap_ops; - err = 0; -out: - mutex_unlock(&nlk->pg_vec_lock); - return err; -} - -static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len) -{ -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 - struct page *p_start, *p_end; - - /* First page is flushed through netlink_{get,set}_status */ - p_start = pgvec_to_page(hdr + PAGE_SIZE); - p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1); - while (p_start <= p_end) { - flush_dcache_page(p_start); - p_start++; - } -#endif -} - -static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr) -{ - smp_rmb(); - flush_dcache_page(pgvec_to_page(hdr)); - return hdr->nm_status; -} - -static void netlink_set_status(struct nl_mmap_hdr *hdr, - enum nl_mmap_status status) -{ - smp_mb(); - hdr->nm_status = status; - flush_dcache_page(pgvec_to_page(hdr)); -} - -static struct nl_mmap_hdr * -__netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos) -{ - unsigned int pg_vec_pos, frame_off; - - pg_vec_pos = pos / ring->frames_per_block; - frame_off = pos % ring->frames_per_block; - - return ring->pg_vec[pg_vec_pos] + (frame_off * ring->frame_size); -} - -static struct nl_mmap_hdr * -netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos, - enum nl_mmap_status status) -{ - struct nl_mmap_hdr *hdr; - - hdr = __netlink_lookup_frame(ring, pos); - if (netlink_get_status(hdr) != status) - return NULL; - - return hdr; -} - -static struct nl_mmap_hdr * -netlink_current_frame(const struct netlink_ring *ring, - enum nl_mmap_status status) -{ - return netlink_lookup_frame(ring, ring->head, status); -} - -static void netlink_increment_head(struct netlink_ring *ring) -{ - ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0; -} - -static void netlink_forward_ring(struct netlink_ring *ring) -{ - unsigned int head = ring->head; - const struct nl_mmap_hdr *hdr; - - do { - hdr = __netlink_lookup_frame(ring, ring->head); - if (hdr->nm_status == NL_MMAP_STATUS_UNUSED) - break; - if (hdr->nm_status != NL_MMAP_STATUS_SKIP) - break; - netlink_increment_head(ring); - } while (ring->head != head); -} - -static bool netlink_has_valid_frame(struct netlink_ring *ring) -{ - unsigned int head = ring->head, pos = head; - const struct nl_mmap_hdr *hdr; - - do { - hdr = __netlink_lookup_frame(ring, pos); - if (hdr->nm_status == NL_MMAP_STATUS_VALID) - return true; - pos = pos != 0 ? pos - 1 : ring->frame_max; - } while (pos != head); - - return false; -} - -static bool netlink_dump_space(struct netlink_sock *nlk) -{ - struct netlink_ring *ring = &nlk->rx_ring; - struct nl_mmap_hdr *hdr; - unsigned int n; - - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); - if (hdr == NULL) - return false; - - n = ring->head + ring->frame_max / 2; - if (n > ring->frame_max) - n -= ring->frame_max; - - hdr = __netlink_lookup_frame(ring, n); - - return hdr->nm_status == NL_MMAP_STATUS_UNUSED; -} - -static unsigned int netlink_poll(struct file *file, struct socket *sock, - poll_table *wait) -{ - struct sock *sk = sock->sk; - struct netlink_sock *nlk = nlk_sk(sk); - unsigned int mask; - int err; - - if (nlk->rx_ring.pg_vec != NULL) { - /* Memory mapped sockets don't call recvmsg(), so flow control - * for dumps is performed here. A dump is allowed to continue - * if at least half the ring is unused. - */ - while (nlk->cb_running && netlink_dump_space(nlk)) { - err = netlink_dump(sk); - if (err < 0) { - sk->sk_err = -err; - sk->sk_error_report(sk); - break; - } - } - netlink_rcv_wake(sk); - } - - mask = datagram_poll(file, sock, wait); - - /* We could already have received frames in the normal receive - * queue, that will show up as NL_MMAP_STATUS_COPY in the ring, - * so if mask contains pollin/etc already, there's no point - * walking the ring. - */ - if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) { - spin_lock_bh(&sk->sk_receive_queue.lock); - if (nlk->rx_ring.pg_vec) { - if (netlink_has_valid_frame(&nlk->rx_ring)) - mask |= POLLIN | POLLRDNORM; - } - spin_unlock_bh(&sk->sk_receive_queue.lock); - } - - spin_lock_bh(&sk->sk_write_queue.lock); - if (nlk->tx_ring.pg_vec) { - if (netlink_current_frame(&nlk->tx_ring, NL_MMAP_STATUS_UNUSED)) - mask |= POLLOUT | POLLWRNORM; - } - spin_unlock_bh(&sk->sk_write_queue.lock); - - return mask; -} - -static struct nl_mmap_hdr *netlink_mmap_hdr(struct sk_buff *skb) -{ - return (struct nl_mmap_hdr *)(skb->head - NL_MMAP_HDRLEN); -} - -static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk, - struct netlink_ring *ring, - struct nl_mmap_hdr *hdr) -{ - unsigned int size; - void *data; - - size = ring->frame_size - NL_MMAP_HDRLEN; - data = (void *)hdr + NL_MMAP_HDRLEN; - - skb->head = data; - skb->data = data; - skb_reset_tail_pointer(skb); - skb->end = skb->tail + size; - skb->len = 0; - - skb->destructor = netlink_skb_destructor; - NETLINK_CB(skb).flags |= NETLINK_SKB_MMAPED; - NETLINK_CB(skb).sk = sk; -} - -static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, - u32 dst_portid, u32 dst_group, - struct scm_cookie *scm) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring; - struct nl_mmap_hdr *hdr; - struct sk_buff *skb; - unsigned int maxlen; - int err = 0, len = 0; - - mutex_lock(&nlk->pg_vec_lock); - - ring = &nlk->tx_ring; - maxlen = ring->frame_size - NL_MMAP_HDRLEN; - - do { - unsigned int nm_len; - - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID); - if (hdr == NULL) { - if (!(msg->msg_flags & MSG_DONTWAIT) && - atomic_read(&nlk->tx_ring.pending)) - schedule(); - continue; - } - - nm_len = ACCESS_ONCE(hdr->nm_len); - if (nm_len > maxlen) { - err = -EINVAL; - goto out; - } - - netlink_frame_flush_dcache(hdr, nm_len); - - skb = alloc_skb(nm_len, GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - __skb_put(skb, nm_len); - memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); - - netlink_increment_head(ring); - - NETLINK_CB(skb).portid = nlk->portid; - NETLINK_CB(skb).dst_group = dst_group; - NETLINK_CB(skb).creds = scm->creds; - - err = security_netlink_send(sk, skb); - if (err) { - kfree_skb(skb); - goto out; - } - - if (unlikely(dst_group)) { - atomic_inc(&skb->users); - netlink_broadcast(sk, skb, dst_portid, dst_group, - GFP_KERNEL); - } - err = netlink_unicast(sk, skb, dst_portid, - msg->msg_flags & MSG_DONTWAIT); - if (err < 0) - goto out; - len += err; - - } while (hdr != NULL || - (!(msg->msg_flags & MSG_DONTWAIT) && - atomic_read(&nlk->tx_ring.pending))); - - if (len > 0) - err = len; -out: - mutex_unlock(&nlk->pg_vec_lock); - return err; -} - -static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb) -{ - struct nl_mmap_hdr *hdr; - - hdr = netlink_mmap_hdr(skb); - hdr->nm_len = skb->len; - hdr->nm_group = NETLINK_CB(skb).dst_group; - hdr->nm_pid = NETLINK_CB(skb).creds.pid; - hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); - hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); - netlink_frame_flush_dcache(hdr, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_VALID); - - NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED; - kfree_skb(skb); -} - -static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring = &nlk->rx_ring; - struct nl_mmap_hdr *hdr; - - spin_lock_bh(&sk->sk_receive_queue.lock); - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); - if (hdr == NULL) { - spin_unlock_bh(&sk->sk_receive_queue.lock); - kfree_skb(skb); - netlink_overrun(sk); - return; - } - netlink_increment_head(ring); - __skb_queue_tail(&sk->sk_receive_queue, skb); - spin_unlock_bh(&sk->sk_receive_queue.lock); - - hdr->nm_len = skb->len; - hdr->nm_group = NETLINK_CB(skb).dst_group; - hdr->nm_pid = NETLINK_CB(skb).creds.pid; - hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); - hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); - netlink_set_status(hdr, NL_MMAP_STATUS_COPY); -} - -#else /* CONFIG_NETLINK_MMAP */ -#define netlink_rx_is_mmaped(sk) false -#define netlink_tx_is_mmaped(sk) false -#define netlink_mmap sock_no_mmap -#define netlink_poll datagram_poll -#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm) 0 -#endif /* CONFIG_NETLINK_MMAP */ - static void netlink_skb_destructor(struct sk_buff *skb) { -#ifdef CONFIG_NETLINK_MMAP - struct nl_mmap_hdr *hdr; - struct netlink_ring *ring; - struct sock *sk; - - /* If a packet from the kernel to userspace was freed because of an - * error without being delivered to userspace, the kernel must reset - * the status. In the direction userspace to kernel, the status is - * always reset here after the packet was processed and freed. - */ - if (netlink_skb_is_mmaped(skb)) { - hdr = netlink_mmap_hdr(skb); - sk = NETLINK_CB(skb).sk; - - if (NETLINK_CB(skb).flags & NETLINK_SKB_TX) { - netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); - ring = &nlk_sk(sk)->tx_ring; - } else { - if (!(NETLINK_CB(skb).flags & NETLINK_SKB_DELIVERED)) { - hdr->nm_len = 0; - netlink_set_status(hdr, NL_MMAP_STATUS_VALID); - } - ring = &nlk_sk(sk)->rx_ring; - } - - WARN_ON(atomic_read(&ring->pending) == 0); - atomic_dec(&ring->pending); - sock_put(sk); - - skb->head = NULL; - } -#endif if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) @@ -936,18 +334,6 @@ static void netlink_sock_destruct(struct sock *sk) } skb_queue_purge(&sk->sk_receive_queue); -#ifdef CONFIG_NETLINK_MMAP - if (1) { - struct nl_mmap_req req; - - memset(&req, 0, sizeof(req)); - if (nlk->rx_ring.pg_vec) - __netlink_set_ring(sk, &req, false, NULL, 0); - memset(&req, 0, sizeof(req)); - if (nlk->tx_ring.pg_vec) - __netlink_set_ring(sk, &req, true, NULL, 0); - } -#endif /* CONFIG_NETLINK_MMAP */ if (!sock_flag(sk, SOCK_DEAD)) { printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); @@ -1201,9 +587,6 @@ static int __netlink_create(struct net *net, struct socket *sock, mutex_init(nlk->cb_mutex); } init_waitqueue_head(&nlk->wait); -#ifdef CONFIG_NETLINK_MMAP - mutex_init(&nlk->pg_vec_lock); -#endif sk->sk_destruct = netlink_sock_destruct; sk->sk_protocol = protocol; @@ -1745,8 +1128,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, nlk = nlk_sk(sk); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state)) && - !netlink_skb_is_mmaped(skb)) { + test_bit(NETLINK_S_CONGESTED, &nlk->state))) { DECLARE_WAITQUEUE(wait, current); if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) @@ -1784,14 +1166,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) netlink_deliver_tap(skb); -#ifdef CONFIG_NETLINK_MMAP - if (netlink_skb_is_mmaped(skb)) - netlink_queue_mmaped_skb(sk, skb); - else if (netlink_rx_is_mmaped(sk)) - netlink_ring_set_copied(sk, skb); - else -#endif /* CONFIG_NETLINK_MMAP */ - skb_queue_tail(&sk->sk_receive_queue, skb); + skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); return len; } @@ -1815,9 +1190,6 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) int delta; WARN_ON(skb->sk != NULL); - if (netlink_skb_is_mmaped(skb)) - return skb; - delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) return skb; @@ -1897,71 +1269,6 @@ struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, unsigned int ldiff, u32 dst_portid, gfp_t gfp_mask) { -#ifdef CONFIG_NETLINK_MMAP - unsigned int maxlen, linear_size; - struct sock *sk = NULL; - struct sk_buff *skb; - struct netlink_ring *ring; - struct nl_mmap_hdr *hdr; - - sk = netlink_getsockbyportid(ssk, dst_portid); - if (IS_ERR(sk)) - goto out; - - ring = &nlk_sk(sk)->rx_ring; - /* fast-path without atomic ops for common case: non-mmaped receiver */ - if (ring->pg_vec == NULL) - goto out_put; - - /* We need to account the full linear size needed as a ring - * slot cannot have non-linear parts. - */ - linear_size = size + ldiff; - if (ring->frame_size - NL_MMAP_HDRLEN < linear_size) - goto out_put; - - skb = alloc_skb_head(gfp_mask); - if (skb == NULL) - goto err1; - - spin_lock_bh(&sk->sk_receive_queue.lock); - /* check again under lock */ - if (ring->pg_vec == NULL) - goto out_free; - - /* check again under lock */ - maxlen = ring->frame_size - NL_MMAP_HDRLEN; - if (maxlen < linear_size) - goto out_free; - - netlink_forward_ring(ring); - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); - if (hdr == NULL) - goto err2; - - netlink_ring_setup_skb(skb, sk, ring, hdr); - netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); - atomic_inc(&ring->pending); - netlink_increment_head(ring); - - spin_unlock_bh(&sk->sk_receive_queue.lock); - return skb; - -err2: - kfree_skb(skb); - spin_unlock_bh(&sk->sk_receive_queue.lock); - netlink_overrun(sk); -err1: - sock_put(sk); - return NULL; - -out_free: - kfree_skb(skb); - spin_unlock_bh(&sk->sk_receive_queue.lock); -out_put: - sock_put(sk); -out: -#endif return alloc_skb(size, gfp_mask); } EXPORT_SYMBOL_GPL(__netlink_alloc_skb); @@ -2242,8 +1549,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, if (level != SOL_NETLINK) return -ENOPROTOOPT; - if (optname != NETLINK_RX_RING && optname != NETLINK_TX_RING && - optlen >= sizeof(int) && + if (optlen >= sizeof(int) && get_user(val, (unsigned int __user *)optval)) return -EFAULT; @@ -2296,25 +1602,6 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, } err = 0; break; -#ifdef CONFIG_NETLINK_MMAP - case NETLINK_RX_RING: - case NETLINK_TX_RING: { - struct nl_mmap_req req; - - /* Rings might consume more memory than queue limits, require - * CAP_NET_ADMIN. - */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (optlen < sizeof(req)) - return -EINVAL; - if (copy_from_user(&req, optval, sizeof(req))) - return -EFAULT; - err = netlink_set_ring(sk, &req, - optname == NETLINK_TX_RING); - break; - } -#endif /* CONFIG_NETLINK_MMAP */ case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; @@ -2484,18 +1771,6 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) smp_rmb(); } - /* It's a really convoluted way for userland to ask for mmaped - * sendmsg(), but that's what we've got... - */ - if (netlink_tx_is_mmaped(sk) && - iter_is_iovec(&msg->msg_iter) && - msg->msg_iter.nr_segs == 1 && - msg->msg_iter.iov->iov_base == NULL) { - err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, - &scm); - goto out; - } - err = -EMSGSIZE; if (len > sk->sk_sndbuf - 32) goto out; @@ -2812,8 +2087,7 @@ static int netlink_dump(struct sock *sk) goto errout_skb; } - if (!netlink_rx_is_mmaped(sk) && - atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; /* NLMSG_GOODSIZE is small to avoid high order allocations being @@ -2833,7 +2107,7 @@ static int netlink_dump(struct sock *sk) if (!skb) { alloc_size = alloc_min_size; skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, - (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM)); + GFP_KERNEL); } if (!skb) goto errout_skb; @@ -2902,16 +2176,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, struct netlink_sock *nlk; int ret; - /* Memory mapped dump requests need to be copied to avoid looping - * on the pending state in netlink_mmap_sendmsg() while the CB hold - * a reference to the skb. - */ - if (netlink_skb_is_mmaped(skb)) { - skb = skb_copy(skb, GFP_KERNEL); - if (skb == NULL) - return -ENOBUFS; - } else - atomic_inc(&skb->users); + atomic_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { @@ -3255,7 +2520,7 @@ static const struct proto_ops netlink_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = netlink_getname, - .poll = netlink_poll, + .poll = datagram_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, @@ -3263,7 +2528,7 @@ static const struct proto_ops netlink_ops = { .getsockopt = netlink_getsockopt, .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, - .mmap = netlink_mmap, + .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index df32cb92d9fc..ea4600aea6b0 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -45,12 +45,6 @@ struct netlink_sock { int (*netlink_bind)(struct net *net, int group); void (*netlink_unbind)(struct net *net, int group); struct module *module; -#ifdef CONFIG_NETLINK_MMAP - struct mutex pg_vec_lock; - struct netlink_ring rx_ring; - struct netlink_ring tx_ring; - atomic_t mapped; -#endif /* CONFIG_NETLINK_MMAP */ struct rhash_head node; struct rcu_head rcu; @@ -62,15 +56,6 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } -static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb) -{ -#ifdef CONFIG_NETLINK_MMAP - return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; -#else - return false; -#endif /* CONFIG_NETLINK_MMAP */ -} - struct netlink_table { struct rhashtable hash; struct hlist_head mc_list; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 3ee63a3cff30..8dd836a8dd60 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -8,41 +8,6 @@ #include "af_netlink.h" -#ifdef CONFIG_NETLINK_MMAP -static int sk_diag_put_ring(struct netlink_ring *ring, int nl_type, - struct sk_buff *nlskb) -{ - struct netlink_diag_ring ndr; - - ndr.ndr_block_size = ring->pg_vec_pages << PAGE_SHIFT; - ndr.ndr_block_nr = ring->pg_vec_len; - ndr.ndr_frame_size = ring->frame_size; - ndr.ndr_frame_nr = ring->frame_max + 1; - - return nla_put(nlskb, nl_type, sizeof(ndr), &ndr); -} - -static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb) -{ - struct netlink_sock *nlk = nlk_sk(sk); - int ret; - - mutex_lock(&nlk->pg_vec_lock); - ret = sk_diag_put_ring(&nlk->rx_ring, NETLINK_DIAG_RX_RING, nlskb); - if (!ret) - ret = sk_diag_put_ring(&nlk->tx_ring, NETLINK_DIAG_TX_RING, - nlskb); - mutex_unlock(&nlk->pg_vec_lock); - - return ret; -} -#else -static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb) -{ - return 0; -} -#endif - static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb) { struct netlink_sock *nlk = nlk_sk(sk); @@ -87,10 +52,6 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO)) goto out_nlmsg_trim; - if ((req->ndiag_show & NDIAG_SHOW_RING_CFG) && - sk_diag_put_rings_cfg(sk, skb)) - goto out_nlmsg_trim; - nlmsg_end(skb, nlh); return 0; diff --git a/net/nfc/core.c b/net/nfc/core.c index 1fe3d3b362c0..c5a2c7e733b3 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -969,6 +969,8 @@ static void nfc_release(struct device *d) kfree(se); } + ida_simple_remove(&nfc_index_ida, dev->idx); + kfree(dev); } @@ -1043,6 +1045,7 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, int tx_headroom, int tx_tailroom) { struct nfc_dev *dev; + int rc; if (!ops->start_poll || !ops->stop_poll || !ops->activate_target || !ops->deactivate_target || !ops->im_transceive) @@ -1055,6 +1058,15 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, if (!dev) return NULL; + rc = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL); + if (rc < 0) + goto err_free_dev; + dev->idx = rc; + + dev->dev.class = &nfc_class; + dev_set_name(&dev->dev, "nfc%d", dev->idx); + device_initialize(&dev->dev); + dev->ops = ops; dev->supported_protocols = supported_protocols; dev->tx_headroom = tx_headroom; @@ -1077,6 +1089,11 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, } return dev; + +err_free_dev: + kfree(dev); + + return ERR_PTR(rc); } EXPORT_SYMBOL(nfc_allocate_device); @@ -1091,14 +1108,6 @@ int nfc_register_device(struct nfc_dev *dev) pr_debug("dev_name=%s\n", dev_name(&dev->dev)); - dev->idx = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL); - if (dev->idx < 0) - return dev->idx; - - dev->dev.class = &nfc_class; - dev_set_name(&dev->dev, "nfc%d", dev->idx); - device_initialize(&dev->dev); - mutex_lock(&nfc_devlist_mutex); nfc_devlist_generation++; rc = device_add(&dev->dev); @@ -1136,12 +1145,10 @@ EXPORT_SYMBOL(nfc_register_device); */ void nfc_unregister_device(struct nfc_dev *dev) { - int rc, id; + int rc; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); - id = dev->idx; - if (dev->rfkill) { rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); @@ -1166,8 +1173,6 @@ void nfc_unregister_device(struct nfc_dev *dev) nfc_devlist_generation++; device_del(&dev->dev); mutex_unlock(&nfc_devlist_mutex); - - ida_simple_remove(&nfc_index_ida, id); } EXPORT_SYMBOL(nfc_unregister_device); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index ecf0a0196f18..9c222a106c7f 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -76,7 +76,8 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) struct sockaddr_nfc_llcp llcp_addr; int len, ret = 0; - if (!addr || addr->sa_family != AF_NFC) + if (!addr || alen < offsetofend(struct sockaddr, sa_family) || + addr->sa_family != AF_NFC) return -EINVAL; pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); @@ -150,7 +151,8 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_nfc_llcp llcp_addr; int len, ret = 0; - if (!addr || addr->sa_family != AF_NFC) + if (!addr || alen < offsetofend(struct sockaddr, sa_family) || + addr->sa_family != AF_NFC) return -EINVAL; pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); @@ -655,8 +657,7 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, pr_debug("sock %p sk %p flags 0x%x\n", sock, sk, flags); - if (!addr || len < sizeof(struct sockaddr_nfc) || - addr->sa_family != AF_NFC) + if (!addr || len < sizeof(*addr) || addr->sa_family != AF_NFC) return -EINVAL; if (addr->service_name_len == 0 && addr->dsap == 0) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 10c99a578421..67583ad7f610 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1084,8 +1084,7 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops, return ndev; free_nfc: - kfree(ndev->nfc_dev); - + nfc_free_device(ndev->nfc_dev); free_nci: kfree(ndev); return NULL; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index f58c1fba1026..12dfb457275d 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -873,7 +873,9 @@ static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info) u32 device_idx, target_idx, protocol; int rc; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + !info->attrs[NFC_ATTR_TARGET_INDEX] || + !info->attrs[NFC_ATTR_PROTOCOLS]) return -EINVAL; device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e004067ec24a..6a2507f24b0f 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -501,7 +501,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, /* The conntrack module expects to be working at L3. */ nh_ofs = skb_network_offset(skb); - skb_pull(skb, nh_ofs); + skb_pull_rcsum(skb, nh_ofs); if (key->ip.frag != OVS_FRAG_TYPE_NONE) { err = handle_fragments(net, key, info->zone.id, skb); @@ -527,6 +527,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, &info->labels.mask); err: skb_push(skb, nh_ofs); + skb_postpush_rcsum(skb, skb->data, nh_ofs); if (err) kfree_skb(skb); return err; @@ -576,8 +577,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, nla_for_each_nested(a, attr, rem) { int type = nla_type(a); - int maxlen = ovs_ct_attr_lens[type].maxlen; - int minlen = ovs_ct_attr_lens[type].minlen; + int maxlen; + int minlen; if (type > OVS_CT_ATTR_MAX) { OVS_NLERR(log, @@ -585,6 +586,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, type, OVS_CT_ATTR_MAX); return -EINVAL; } + + maxlen = ovs_ct_attr_lens[type].maxlen; + minlen = ovs_ct_attr_lens[type].minlen; if (nla_len(a) < minlen || nla_len(a) > maxlen) { OVS_NLERR(log, "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)", diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d1bd4a45ca2d..d26b28def310 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -588,7 +588,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, ipv4 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV6_SRC: - SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src, nla_get_in6_addr(a), is_mask); ipv6 = true; break; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f223d1c80ccf..148ec130d99d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1497,6 +1497,8 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po) f->arr[f->num_members] = sk; smp_wmb(); f->num_members++; + if (f->num_members == 1) + dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } @@ -1513,6 +1515,8 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po) BUG_ON(i >= f->num_members); f->arr[i] = f->arr[f->num_members - 1]; f->num_members--; + if (f->num_members == 0) + __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } @@ -1623,6 +1627,7 @@ static void fanout_release_data(struct packet_fanout *f) static int fanout_add(struct sock *sk, u16 id, u16 type_flags) { + struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f, *match; u8 type = type_flags & 0xff; @@ -1645,23 +1650,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) return -EINVAL; } + mutex_lock(&fanout_mutex); + + err = -EINVAL; if (!po->running) - return -EINVAL; + goto out; + err = -EALREADY; if (po->fanout) - return -EALREADY; + goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { - po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL); - if (!po->rollover) - return -ENOMEM; - atomic_long_set(&po->rollover->num, 0); - atomic_long_set(&po->rollover->num_huge, 0); - atomic_long_set(&po->rollover->num_failed, 0); + err = -ENOMEM; + rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); + if (!rollover) + goto out; + atomic_long_set(&rollover->num, 0); + atomic_long_set(&rollover->num_huge, 0); + atomic_long_set(&rollover->num_failed, 0); + po->rollover = rollover; } - mutex_lock(&fanout_mutex); match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && @@ -1691,7 +1701,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.id_match = match_fanout_group; - dev_add_pack(&match->prot_hook); list_add(&match->list, &fanout_list); } err = -EINVAL; @@ -1708,36 +1717,40 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) } } out: - mutex_unlock(&fanout_mutex); - if (err) { - kfree(po->rollover); + if (err && rollover) { + kfree(rollover); po->rollover = NULL; } + mutex_unlock(&fanout_mutex); return err; } -static void fanout_release(struct sock *sk) +/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes + * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. + * It is the responsibility of the caller to call fanout_release_data() and + * free the returned packet_fanout (after synchronize_net()) + */ +static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; + mutex_lock(&fanout_mutex); f = po->fanout; - if (!f) - return; + if (f) { + po->fanout = NULL; - mutex_lock(&fanout_mutex); - po->fanout = NULL; + if (atomic_dec_and_test(&f->sk_ref)) + list_del(&f->list); + else + f = NULL; - if (atomic_dec_and_test(&f->sk_ref)) { - list_del(&f->list); - dev_remove_pack(&f->prot_hook); - fanout_release_data(f); - kfree(f); + if (po->rollover) + kfree_rcu(po->rollover, rcu); } mutex_unlock(&fanout_mutex); - if (po->rollover) - kfree_rcu(po->rollover, rcu); + return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, @@ -2637,7 +2650,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) int vnet_hdr_len; struct packet_sock *po = pkt_sk(sk); unsigned short gso_type = 0; - int hlen, tlen; + int hlen, tlen, linear; int extra_len = 0; ssize_t n; @@ -2741,8 +2754,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; - skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, - __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len), + linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); + linear = max(linear, min_t(int, len, dev->hard_header_len)); + skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; @@ -2845,6 +2859,7 @@ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; + struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; @@ -2884,9 +2899,14 @@ static int packet_release(struct socket *sock) packet_set_ring(sk, &req_u, 1, 1); } - fanout_release(sk); + f = fanout_release(sk); synchronize_net(); + + if (f) { + fanout_release_data(f); + kfree(f); + } /* * Now the socket is dead. No more input will appear. */ @@ -3001,7 +3021,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[15]; + char name[sizeof(uaddr->sa_data) + 1]; /* * Check legality @@ -3009,7 +3029,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, if (addr_len != sizeof(struct sockaddr)) return -EINVAL; - strlcpy(name, uaddr->sa_data, sizeof(name)); + /* uaddr->sa_data comes from the userspace, it's not guaranteed to be + * zero-terminated. + */ + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); + name[sizeof(uaddr->sa_data)] = 0; return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); } @@ -3598,12 +3622,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_reserve = val; - return 0; + if (val > INT_MAX) + return -EINVAL; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_reserve = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_LOSS: { @@ -3860,7 +3891,6 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - fanout_release(sk); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); @@ -4115,8 +4145,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; if (po->tp_version >= TPACKET_V3 && - (int)(req->tp_block_size - - BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0) + req->tp_block_size <= + BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv)) goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + po->tp_reserve)) @@ -4127,6 +4157,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; + if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; @@ -4198,7 +4230,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, register_prot_hook(sk); } spin_unlock(&po->bind_lock); - if (closing && (po->tp_version > TPACKET_V2)) { + if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); diff --git a/net/rds/cong.c b/net/rds/cong.c index e6144b8246fd..6641bcf7c185 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -299,7 +299,7 @@ void rds_cong_set_bit(struct rds_cong_map *map, __be16 port) i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; - __set_bit_le(off, (void *)map->m_page_addrs[i]); + set_bit_le(off, (void *)map->m_page_addrs[i]); } void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port) @@ -313,7 +313,7 @@ void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port) i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; - __clear_bit_le(off, (void *)map->m_page_addrs[i]); + clear_bit_le(off, (void *)map->m_page_addrs[i]); } static int rds_cong_test_bit(struct rds_cong_map *map, __be16 port) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 0936a4a32b47..e353e3255206 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -78,7 +78,7 @@ int rds_tcp_accept_one(struct socket *sock) struct inet_sock *inet; struct rds_tcp_connection *rs_tcp; - ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family, + ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type, sock->sk->sk_protocol, &new_sock); if (ret) diff --git a/net/rpmsg/rpmsg_proto.c b/net/rpmsg/rpmsg_proto.c index 1c30815556eb..010a9aed6dbf 100644 --- a/net/rpmsg/rpmsg_proto.c +++ b/net/rpmsg/rpmsg_proto.c @@ -543,6 +543,11 @@ static void __rpmsg_proto_cb(struct device *dev, int from_vproc_id, void *data, len, true); #endif + if (!sk) { + dev_warn(dev, "callback for deleted socket (from %d)\n", src); + return; + } + lock_sock(sk); switch (sk->sk_state) { @@ -590,6 +595,15 @@ static void rpmsg_proto_cb(struct rpmsg_channel *rpdev, void *data, int len, { int id = rpmsg_sock_get_proc_id(rpdev); + /* published rpmsg channels from remote side reuse their end-point's + * private field for storing the list of connected sockets, so cannot + * process messages. + */ + if (rpdev->src >= RPMSG_RESERVED_ADDRESSES) { + dev_err(&rpdev->dev, "rpmsg_proto device not designed to receive any messages\n"); + return; + } + __rpmsg_proto_cb(&rpdev->dev, id, data, len, priv, src); } @@ -609,8 +623,11 @@ static int rpmsg_proto_probe(struct rpmsg_channel *rpdev) dev_err(dev, "id %d already associated to different vrp\n", id); - if (dst == RPMSG_ADDR_ANY) + if (dst == RPMSG_ADDR_ANY) { + /* Set announce to false and avoid extra delay when binding. */ + rpdev->announce = false; return 0; + } /* associate id/vrp for later lookup in rpmsg_sock_bind() */ if (!vrp) { diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index da3cc09f683e..91d43ab3a961 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -215,7 +215,7 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned int toklen = *_toklen, n_parts, loop, tmp; + unsigned int toklen = *_toklen, n_parts, loop, tmp, paddedlen; /* there must be at least one name, and at least #names+1 length * words */ @@ -245,16 +245,16 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, toklen -= 4; if (tmp <= 0 || tmp > AFSTOKEN_STRING_MAX) return -EINVAL; - if (tmp > toklen) + paddedlen = (tmp + 3) & ~3; + if (paddedlen > toklen) return -EINVAL; princ->name_parts[loop] = kmalloc(tmp + 1, GFP_KERNEL); if (!princ->name_parts[loop]) return -ENOMEM; memcpy(princ->name_parts[loop], xdr, tmp); princ->name_parts[loop][tmp] = 0; - tmp = (tmp + 3) & ~3; - toklen -= tmp; - xdr += tmp >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; } if (toklen < 4) @@ -263,16 +263,16 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, toklen -= 4; if (tmp <= 0 || tmp > AFSTOKEN_K5_REALM_MAX) return -EINVAL; - if (tmp > toklen) + paddedlen = (tmp + 3) & ~3; + if (paddedlen > toklen) return -EINVAL; princ->realm = kmalloc(tmp + 1, GFP_KERNEL); if (!princ->realm) return -ENOMEM; memcpy(princ->realm, xdr, tmp); princ->realm[tmp] = 0; - tmp = (tmp + 3) & ~3; - toklen -= tmp; - xdr += tmp >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; _debug("%s/...@%s", princ->name_parts[0], princ->realm); @@ -291,7 +291,7 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned int toklen = *_toklen, len; + unsigned int toklen = *_toklen, len, paddedlen; /* there must be at least one tag and one length word */ if (toklen <= 8) @@ -305,15 +305,17 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, toklen -= 8; if (len > max_data_size) return -EINVAL; + paddedlen = (len + 3) & ~3; + if (paddedlen > toklen) + return -EINVAL; td->data_len = len; if (len > 0) { td->data = kmemdup(xdr, len, GFP_KERNEL); if (!td->data) return -ENOMEM; - len = (len + 3) & ~3; - toklen -= len; - xdr += len >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; } _debug("tag %x len %x", td->tag, td->data_len); @@ -385,7 +387,7 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, const __be32 **_xdr, unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned int toklen = *_toklen, len; + unsigned int toklen = *_toklen, len, paddedlen; /* there must be at least one length word */ if (toklen <= 4) @@ -397,6 +399,9 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, toklen -= 4; if (len > AFSTOKEN_K5_TIX_MAX) return -EINVAL; + paddedlen = (len + 3) & ~3; + if (paddedlen > toklen) + return -EINVAL; *_tktlen = len; _debug("ticket len %u", len); @@ -405,9 +410,8 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, *_ticket = kmemdup(xdr, len, GFP_KERNEL); if (!*_ticket) return -ENOMEM; - len = (len + 3) & ~3; - toklen -= len; - xdr += len >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; } *_xdr = xdr; @@ -550,7 +554,7 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep) { const __be32 *xdr = prep->data, *token; const char *cp; - unsigned int len, tmp, loop, ntoken, toklen, sec_ix; + unsigned int len, paddedlen, loop, ntoken, toklen, sec_ix; size_t datalen = prep->datalen; int ret; @@ -576,22 +580,21 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep) if (len < 1 || len > AFSTOKEN_CELL_MAX) goto not_xdr; datalen -= 4; - tmp = (len + 3) & ~3; - if (tmp > datalen) + paddedlen = (len + 3) & ~3; + if (paddedlen > datalen) goto not_xdr; cp = (const char *) xdr; for (loop = 0; loop < len; loop++) if (!isprint(cp[loop])) goto not_xdr; - if (len < tmp) - for (; loop < tmp; loop++) - if (cp[loop]) - goto not_xdr; + for (; loop < paddedlen; loop++) + if (cp[loop]) + goto not_xdr; _debug("cellname: [%u/%u] '%*.*s'", - len, tmp, len, len, (const char *) xdr); - datalen -= tmp; - xdr += tmp >> 2; + len, paddedlen, len, len, (const char *) xdr); + datalen -= paddedlen; + xdr += paddedlen >> 2; /* get the token count */ if (datalen < 12) @@ -612,10 +615,11 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep) sec_ix = ntohl(*xdr); datalen -= 4; _debug("token: [%x/%zx] %x", toklen, datalen, sec_ix); - if (toklen < 20 || toklen > datalen) + paddedlen = (toklen + 3) & ~3; + if (toklen < 20 || toklen > datalen || paddedlen > datalen) goto not_xdr; - datalen -= (toklen + 3) & ~3; - xdr += (toklen + 3) >> 2; + datalen -= paddedlen; + xdr += paddedlen >> 2; } while (--loop > 0); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 06e7c4a37245..694a06f1e0d5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -820,10 +820,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, goto out_module_put; err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a); - if (err < 0) + if (err <= 0) goto out_module_put; - if (err == 0) - goto noflush_out; nla_nest_end(skb, nest); @@ -840,7 +838,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, out_module_put: module_put(a.ops->owner); err_out: -noflush_out: kfree_skb(skb); return err; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index bb41699c6c49..7ecb14f3db54 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -109,6 +109,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, if (ret < 0) return ret; + if (!tb[TCA_CONNMARK_PARMS]) + return -EINVAL; + parm = nla_data(tb[TCA_CONNMARK_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d05869646515..0915d448ba23 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -42,8 +42,8 @@ static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int return PTR_ERR(target); t->u.kernel.target = target; + memset(&par, 0, sizeof(par)); par.table = table; - par.entryinfo = NULL; par.target = target; par.targinfo = t->data; par.hook_mask = hook; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e384d6aefa3a..1090a52c03cd 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -36,14 +36,15 @@ static DEFINE_SPINLOCK(mirred_list_lock); static void tcf_mirred_release(struct tc_action *a, int bind) { struct tcf_mirred *m = to_mirred(a); - struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); + struct net_device *dev; /* We could be called either in a RCU callback or with RTNL lock held. */ spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); - spin_unlock_bh(&mirred_list_lock); + dev = rcu_dereference_protected(m->tcfm_dev, 1); if (dev) dev_put(dev); + spin_unlock_bh(&mirred_list_lock); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 95b560f0b253..6d340cd6e2a7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1004,6 +1004,9 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, return sch; } + /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ + if (ops->destroy) + ops->destroy(sch); err_out3: dev_put(dev); kfree((char *) sch - sch->padded); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 13d6f83ec491..45d4b2f22f62 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -636,7 +636,9 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) q->hhf_arrays[i] = hhf_zalloc(HHF_ARRAYS_LEN * sizeof(u32)); if (!q->hhf_arrays[i]) { - hhf_destroy(sch); + /* Note: hhf_destroy() will be called + * by our caller. + */ return -ENOMEM; } } @@ -647,7 +649,9 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) q->hhf_valid_bits[i] = hhf_zalloc(HHF_ARRAYS_LEN / BITS_PER_BYTE); if (!q->hhf_valid_bits[i]) { - hhf_destroy(sch); + /* Note: hhf_destroy() will be called + * by our caller. + */ return -ENOMEM; } } diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 3e82f047caaf..d9c84328e7eb 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -52,7 +52,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) /* pre-allocate qdiscs, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); - if (priv->qdiscs == NULL) + if (!priv->qdiscs) return -ENOMEM; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { @@ -60,18 +60,14 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops, TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(ntx + 1))); - if (qdisc == NULL) - goto err; + if (!qdisc) + return -ENOMEM; priv->qdiscs[ntx] = qdisc; qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->flags |= TCQ_F_MQROOT; return 0; - -err: - mq_destroy(sch); - return -ENOMEM; } static void mq_attach(struct Qdisc *sch) diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index ad70ecf57ce7..66bccc5ff4ea 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -117,20 +117,17 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) /* pre-allocate qdisc, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); - if (priv->qdiscs == NULL) { - err = -ENOMEM; - goto err; - } + if (!priv->qdiscs) + return -ENOMEM; for (i = 0; i < dev->num_tx_queues; i++) { dev_queue = netdev_get_tx_queue(dev, i); qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops, TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(i + 1))); - if (qdisc == NULL) { - err = -ENOMEM; - goto err; - } + if (!qdisc) + return -ENOMEM; + priv->qdiscs[i] = qdisc; qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } @@ -143,7 +140,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) priv->hw_owned = 1; err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc); if (err) - goto err; + return err; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -157,10 +154,6 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) sch->flags |= TCQ_F_MQROOT; return 0; - -err: - mqprio_destroy(sch); - return err; } static void mqprio_attach(struct Qdisc *sch) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 498f0a2cb47f..4431e2833e45 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -742,9 +742,10 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->ht = sfq_alloc(sizeof(q->ht[0]) * q->divisor); q->slots = sfq_alloc(sizeof(q->slots[0]) * q->maxflows); if (!q->ht || !q->slots) { - sfq_destroy(sch); + /* Note: sfq_destroy() will be called by our caller */ return -ENOMEM; } + for (i = 0; i < q->divisor; i++) q->ht[i] = SFQ_EMPTY_SLOT; diff --git a/net/sctp/input.c b/net/sctp/input.c index b6493b3f11a9..2d7859c03fd2 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -472,15 +472,14 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, struct sctp_association **app, struct sctp_transport **tpp) { + struct sctp_init_chunk *chunkhdr, _chunkhdr; union sctp_addr saddr; union sctp_addr daddr; struct sctp_af *af; struct sock *sk = NULL; struct sctp_association *asoc; struct sctp_transport *transport = NULL; - struct sctp_init_chunk *chunkhdr; __u32 vtag = ntohl(sctphdr->vtag); - int len = skb->len - ((void *)sctphdr - (void *)skb->data); *app = NULL; *tpp = NULL; @@ -515,13 +514,16 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, * discard the packet. */ if (vtag == 0) { - chunkhdr = (void *)sctphdr + sizeof(struct sctphdr); - if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t) - + sizeof(__be32) || + /* chunk header + first 4 octects of init header */ + chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) + + sizeof(struct sctphdr), + sizeof(struct sctp_chunkhdr) + + sizeof(__be32), &_chunkhdr); + if (!chunkhdr || chunkhdr->chunk_hdr.type != SCTP_CID_INIT || - ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) { + ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) goto out; - } + } else if (vtag != asoc->c.peer_vtag) { goto out; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ce46f1c7f133..7527c168e471 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -239,12 +239,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct sctp_bind_addr *bp; struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; - union sctp_addr *baddr = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; struct in6_addr *final_p, final; __u8 matchlen = 0; - __u8 bmatchlen; sctp_scope_t scope; memset(fl6, 0, sizeof(struct flowi6)); @@ -311,23 +309,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid) + struct dst_entry *bdst; + __u8 bmatchlen; + + if (!laddr->valid || + laddr->state != SCTP_ADDR_SRC || + laddr->a.sa.sa_family != AF_INET6 || + scope > sctp_scope(&laddr->a)) continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (laddr->a.sa.sa_family == AF_INET6) && - (scope <= sctp_scope(&laddr->a))) { - bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); - if (!baddr || (matchlen < bmatchlen)) { - baddr = &laddr->a; - matchlen = bmatchlen; - } - } - } - if (baddr) { - fl6->saddr = baddr->v6.sin6_addr; - fl6->fl6_sport = baddr->v6.sin6_port; + + fl6->saddr = laddr->a.v6.sin6_addr; + fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + + if (!IS_ERR(bdst) && + ipv6_chk_addr(dev_net(bdst->dev), + &laddr->a.v6.sin6_addr, bdst->dev, 1)) { + if (!IS_ERR_OR_NULL(dst)) + dst_release(dst); + dst = bdst; + break; + } + + bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); + if (matchlen > bmatchlen) + continue; + + if (!IS_ERR_OR_NULL(dst)) + dst_release(dst); + dst = bdst; + matchlen = bmatchlen; } rcu_read_unlock(); @@ -662,6 +674,9 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; rcu_read_lock(); opt = rcu_dereference(np->opt); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b5fd4ab56156..3ebf3b652d60 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -235,8 +235,12 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, sctp_assoc_t id) { struct sctp_association *addr_asoc = NULL, *id_asoc = NULL; - struct sctp_transport *transport; + struct sctp_af *af = sctp_get_af_specific(addr->ss_family); union sctp_addr *laddr = (union sctp_addr *)addr; + struct sctp_transport *transport; + + if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len)) + return NULL; addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep, laddr, @@ -4422,6 +4426,12 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) if (!asoc) return -EINVAL; + /* If there is a thread waiting on more sndbuf space for + * sending on this asoc, it cannot be peeled. + */ + if (waitqueue_active(&asoc->wait)) + return -EBUSY; + /* An association cannot be branched off from an already peeled-off * socket, nor is this supported for tcp style sockets. */ @@ -6388,6 +6398,9 @@ int sctp_inet_listen(struct socket *sock, int backlog) if (sock->state != SS_UNCONNECTED) goto out; + if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED)) + goto out; + /* If backlog is zero, disable listening. */ if (!backlog) { if (sctp_sstate(sk, CLOSED)) @@ -6960,7 +6973,6 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, */ release_sock(sk); current_timeo = schedule_timeout(current_timeo); - BUG_ON(sk != asoc->base.sk); lock_sock(sk); *timeo_p = current_timeo; diff --git a/net/socket.c b/net/socket.c index 66d984ac2991..18aff3d804ec 100644 --- a/net/socket.c +++ b/net/socket.c @@ -520,11 +520,11 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, return used; } -int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) +static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) { int err = simple_setattr(dentry, iattr); - if (!err) { + if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); sock->sk->sk_uid = iattr->ia_uid; @@ -2199,8 +2199,10 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, return err; err = sock_error(sock->sk); - if (err) + if (err) { + datagrams = err; goto out_put; + } entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 06095cc8815e..1f0687d8e3d7 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -541,9 +541,13 @@ gss_setup_upcall(struct gss_auth *gss_auth, struct rpc_cred *cred) return gss_new; gss_msg = gss_add_msg(gss_new); if (gss_msg == gss_new) { - int res = rpc_queue_upcall(gss_new->pipe, &gss_new->msg); + int res; + atomic_inc(&gss_msg->count); + res = rpc_queue_upcall(gss_new->pipe, &gss_new->msg); if (res) { gss_unhash_msg(gss_new); + atomic_dec(&gss_msg->count); + gss_release_msg(gss_new); gss_msg = ERR_PTR(res); } } else @@ -836,6 +840,7 @@ gss_pipe_destroy_msg(struct rpc_pipe_msg *msg) warn_gssd(); gss_release_msg(gss_msg); } + gss_release_msg(gss_msg); } static void gss_pipe_dentry_destroy(struct dentry *dir, diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index eeeba5adee6d..2410d557ae39 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -260,7 +260,7 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, if (!oa->data) return -ENOMEM; - creds = kmalloc(sizeof(struct svc_cred), GFP_KERNEL); + creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL); if (!creds) { kfree(oa->data); return -ENOMEM; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 7a93922457ff..f28aeb2cfd32 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -337,6 +337,11 @@ out: static DEFINE_IDA(rpc_clids); +void rpc_cleanup_clids(void) +{ + ida_destroy(&rpc_clids); +} + static int rpc_alloc_clid(struct rpc_clnt *clnt) { int clid; diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index ee5d3d253102..3142f38d1104 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -119,6 +119,7 @@ out: static void __exit cleanup_sunrpc(void) { + rpc_cleanup_clids(); rpcauth_remove_module(); cleanup_socket_xprt(); svc_cleanup_xprt_sock(); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 648f2a67f314..cb1381513c82 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -381,6 +381,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev = dev_get_by_name(net, driver_name); if (!dev) return -ENODEV; + if (tipc_mtu_bad(dev, 0)) { + dev_put(dev); + return -EINVAL; + } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); @@ -570,14 +574,19 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, if (!b_ptr) return NOTIFY_DONE; - b_ptr->mtu = dev->mtu; - switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev)) break; case NETDEV_GOING_DOWN: + tipc_reset_bearer(net, b_ptr); + break; case NETDEV_CHANGEMTU: + if (tipc_mtu_bad(dev, 0)) { + bearer_disable(net, b_ptr); + break; + } + b_ptr->mtu = dev->mtu; tipc_reset_bearer(net, b_ptr); break; case NETDEV_CHANGEADDR: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 552185bc4773..5f11e18b1fa1 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -39,6 +39,7 @@ #include "netlink.h" #include "core.h" +#include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 @@ -61,6 +62,9 @@ #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 +/* minimum bearer MTU */ +#define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) + /** * struct tipc_node_map - set of node identifiers * @count: # of nodes in set @@ -226,4 +230,13 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +/* check if device MTU is too low for tipc headers */ +static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) +{ + if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) + return false; + netdev_warn(dev, "MTU too low for tipc bearer\n"); + return true; +} + #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.c b/net/tipc/core.c index 03a842870c52..e2bdb07a49a2 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -69,6 +69,7 @@ static int __net_init tipc_init_net(struct net *net) if (err) goto out_nametbl; + INIT_LIST_HEAD(&tn->dist_queue); err = tipc_topsrv_start(net); if (err) goto out_subscr; diff --git a/net/tipc/core.h b/net/tipc/core.h index 18e95a8020cd..fe3b89e9cde4 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -103,6 +103,9 @@ struct tipc_net { spinlock_t nametbl_lock; struct name_table *nametbl; + /* Name dist queue */ + struct list_head dist_queue; + /* Topology subscription server */ struct tipc_server *topsrv; atomic_t subscription_count; diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index f51c8bdbea1c..c4c151bc000c 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -40,11 +40,6 @@ int sysctl_tipc_named_timeout __read_mostly = 2000; -/** - * struct tipc_dist_queue - queue holding deferred name table updates - */ -static struct list_head tipc_dist_queue = LIST_HEAD_INIT(tipc_dist_queue); - struct distr_queue_item { struct distr_item i; u32 dtype; @@ -67,6 +62,8 @@ static void publ_to_item(struct distr_item *i, struct publication *p) /** * named_prepare_buf - allocate & initialize a publication message + * + * The buffer returned is of size INT_H_SIZE + payload size */ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, u32 dest) @@ -171,9 +168,9 @@ static void named_distribute(struct net *net, struct sk_buff_head *list, struct publication *publ; struct sk_buff *skb = NULL; struct distr_item *item = NULL; - uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) * - ITEM_SIZE; - uint msg_rem = msg_dsz; + u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) / + ITEM_SIZE) * ITEM_SIZE; + u32 msg_rem = msg_dsz; list_for_each_entry(publ, pls, local_list) { /* Prepare next buffer: */ @@ -340,9 +337,11 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i, * tipc_named_add_backlog - add a failed name table update to the backlog * */ -static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node) +static void tipc_named_add_backlog(struct net *net, struct distr_item *i, + u32 type, u32 node) { struct distr_queue_item *e; + struct tipc_net *tn = net_generic(net, tipc_net_id); unsigned long now = get_jiffies_64(); e = kzalloc(sizeof(*e), GFP_ATOMIC); @@ -352,7 +351,7 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node) e->node = node; e->expires = now + msecs_to_jiffies(sysctl_tipc_named_timeout); memcpy(e, i, sizeof(*i)); - list_add_tail(&e->next, &tipc_dist_queue); + list_add_tail(&e->next, &tn->dist_queue); } /** @@ -362,10 +361,11 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node) void tipc_named_process_backlog(struct net *net) { struct distr_queue_item *e, *tmp; + struct tipc_net *tn = net_generic(net, tipc_net_id); char addr[16]; unsigned long now = get_jiffies_64(); - list_for_each_entry_safe(e, tmp, &tipc_dist_queue, next) { + list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) { if (time_after(e->expires, now)) { if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype)) continue; @@ -405,7 +405,7 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq) node = msg_orignode(msg); while (count--) { if (!tipc_update_nametbl(net, item, node, mtype)) - tipc_named_add_backlog(item, mtype, node); + tipc_named_add_backlog(net, item, mtype, node); item++; } kfree_skb(skb); diff --git a/net/tipc/node.c b/net/tipc/node.c index 3926b561f873..2df0b98d4a32 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -102,9 +102,10 @@ static unsigned int tipc_hashfn(u32 addr) static void tipc_node_kref_release(struct kref *kref) { - struct tipc_node *node = container_of(kref, struct tipc_node, kref); + struct tipc_node *n = container_of(kref, struct tipc_node, kref); - tipc_node_delete(node); + kfree(n->bc_entry.link); + kfree_rcu(n, rcu); } void tipc_node_put(struct tipc_node *node) @@ -216,21 +217,20 @@ static void tipc_node_delete(struct tipc_node *node) { list_del_rcu(&node->list); hlist_del_rcu(&node->hash); - kfree(node->bc_entry.link); - kfree_rcu(node, rcu); + tipc_node_put(node); + + del_timer_sync(&node->timer); + tipc_node_put(node); } void tipc_node_stop(struct net *net) { - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_net *tn = tipc_net(net); struct tipc_node *node, *t_node; spin_lock_bh(&tn->node_list_lock); - list_for_each_entry_safe(node, t_node, &tn->node_list, list) { - if (del_timer(&node->timer)) - tipc_node_put(node); - tipc_node_put(node); - } + list_for_each_entry_safe(node, t_node, &tn->node_list, list) + tipc_node_delete(node); spin_unlock_bh(&tn->node_list_lock); } @@ -313,9 +313,7 @@ static void tipc_node_timeout(unsigned long data) if (rc & TIPC_LINK_DOWN_EVT) tipc_node_link_down(n, bearer_id, false); } - if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) - tipc_node_get(n); - tipc_node_put(n); + mod_timer(&n->timer, jiffies + n->keepalive_intv); } /** @@ -730,7 +728,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt) state = SELF_UP_PEER_UP; break; case SELF_LOST_CONTACT_EVT: - state = SELF_DOWN_PEER_LEAVING; + state = SELF_DOWN_PEER_DOWN; break; case SELF_ESTABL_CONTACT_EVT: case PEER_LOST_CONTACT_EVT: @@ -749,7 +747,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt) state = SELF_UP_PEER_UP; break; case PEER_LOST_CONTACT_EVT: - state = SELF_LEAVING_PEER_DOWN; + state = SELF_DOWN_PEER_DOWN; break; case SELF_LOST_CONTACT_EVT: case PEER_ESTABL_CONTACT_EVT: diff --git a/net/tipc/server.c b/net/tipc/server.c index 922e04a43396..50f5b0ca7b3c 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -452,6 +452,11 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid, if (!con) return -EINVAL; + if (!test_bit(CF_CONNECTED, &con->flags)) { + conn_put(con); + return 0; + } + e = tipc_alloc_entry(data, len); if (!e) { conn_put(con); @@ -465,12 +470,8 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid, list_add_tail(&e->list, &con->outqueue); spin_unlock_bh(&con->outqueue_lock); - if (test_bit(CF_CONNECTED, &con->flags)) { - if (!queue_work(s->send_wq, &con->swork)) - conn_put(con); - } else { + if (!queue_work(s->send_wq, &con->swork)) conn_put(con); - } return 0; } @@ -494,7 +495,7 @@ static void tipc_send_to_sock(struct tipc_conn *con) int ret; spin_lock_bh(&con->outqueue_lock); - while (1) { + while (test_bit(CF_CONNECTED, &con->flags)) { e = list_entry(con->outqueue.next, struct outqueue_entry, list); if ((struct list_head *) e == &con->outqueue) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b26b7a127773..65171f8e8c45 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -777,9 +777,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, * @tsk: receiving socket * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) +static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct sock *sk = &tsk->sk; + u32 onode = tsk_own_node(tsk); struct tipc_msg *hdr = buf_msg(skb); int mtyp = msg_type(hdr); int conn_cong; @@ -792,7 +794,8 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) if (mtyp == CONN_PROBE) { msg_set_type(hdr, CONN_PROBE_REPLY); - tipc_sk_respond(sk, skb, TIPC_OK); + if (tipc_msg_reverse(onode, &skb, TIPC_OK)) + __skb_queue_tail(xmitq, skb); return; } else if (mtyp == CONN_ACK) { conn_cong = tsk_conn_cong(tsk); @@ -1647,7 +1650,8 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) * * Returns true if message was added to socket receive queue, otherwise false */ -static bool filter_rcv(struct sock *sk, struct sk_buff *skb) +static bool filter_rcv(struct sock *sk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct socket *sock = sk->sk_socket; struct tipc_sock *tsk = tipc_sk(sk); @@ -1657,7 +1661,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb) int usr = msg_user(hdr); if (unlikely(msg_user(hdr) == CONN_MANAGER)) { - tipc_sk_proto_rcv(tsk, skb); + tipc_sk_proto_rcv(tsk, skb, xmitq); return false; } @@ -1700,7 +1704,8 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb) return true; reject: - tipc_sk_respond(sk, skb, err); + if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err)) + __skb_queue_tail(xmitq, skb); return false; } @@ -1716,9 +1721,24 @@ reject: static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { unsigned int truesize = skb->truesize; + struct sk_buff_head xmitq; + u32 dnode, selector; - if (likely(filter_rcv(sk, skb))) + __skb_queue_head_init(&xmitq); + + if (likely(filter_rcv(sk, skb, &xmitq))) { atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); + return 0; + } + + if (skb_queue_empty(&xmitq)) + return 0; + + /* Send response/rejected message */ + skb = __skb_dequeue(&xmitq); + dnode = msg_destnode(buf_msg(skb)); + selector = msg_origport(buf_msg(skb)); + tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); return 0; } @@ -1732,12 +1752,13 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) * Caller must hold socket lock */ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, - u32 dport) + u32 dport, struct sk_buff_head *xmitq) { + unsigned long time_limit = jiffies + 2; + struct sk_buff *skb; unsigned int lim; atomic_t *dcnt; - struct sk_buff *skb; - unsigned long time_limit = jiffies + 2; + u32 onode; while (skb_queue_len(inputq)) { if (unlikely(time_after_eq(jiffies, time_limit))) @@ -1749,20 +1770,22 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - filter_rcv(sk, skb); + filter_rcv(sk, skb, xmitq); continue; } /* Try backlog, compensating for double-counted bytes */ dcnt = &tipc_sk(sk)->dupl_rcvcnt; - if (sk->sk_backlog.len) + if (!sk->sk_backlog.len) atomic_set(dcnt, 0); lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt); if (likely(!sk_add_backlog(sk, skb, lim))) continue; /* Overload => reject message back to sender */ - tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD); + onode = tipc_own_addr(sock_net(sk)); + if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD)) + __skb_queue_tail(xmitq, skb); break; } } @@ -1775,12 +1798,14 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, */ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { + struct sk_buff_head xmitq; u32 dnode, dport = 0; int err; struct tipc_sock *tsk; struct sock *sk; struct sk_buff *skb; + __skb_queue_head_init(&xmitq); while (skb_queue_len(inputq)) { dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); @@ -1788,9 +1813,14 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) if (likely(tsk)) { sk = &tsk->sk; if (likely(spin_trylock_bh(&sk->sk_lock.slock))) { - tipc_sk_enqueue(inputq, sk, dport); + tipc_sk_enqueue(inputq, sk, dport, &xmitq); spin_unlock_bh(&sk->sk_lock.slock); } + /* Send pending response/rejected messages, if any */ + while ((skb = __skb_dequeue(&xmitq))) { + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, dport); + } sock_put(sk); continue; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 6af78c6276b4..78d6b78de29d 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -52,7 +52,7 @@ /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 -#define UDP_MIN_HEADROOM 28 +#define UDP_MIN_HEADROOM 48 static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, @@ -376,6 +376,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; + if (tipc_mtu_bad(dev, sizeof(struct iphdr) + + sizeof(struct udphdr))) { + err = -EINVAL; + goto err; + } b->mtu = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 73f75258ce46..e05ec54ac53f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -994,9 +994,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) unsigned int hash; struct unix_address *addr; struct hlist_head *list; + struct path path = { NULL, NULL }; err = -EINVAL; - if (sunaddr->sun_family != AF_UNIX) + if (addr_len < offsetofend(struct sockaddr_un, sun_family) || + sunaddr->sun_family != AF_UNIX) goto out; if (addr_len == sizeof(short)) { @@ -1009,9 +1011,20 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; + if (sun_path[0]) { + umode_t mode = S_IFSOCK | + (SOCK_INODE(sock)->i_mode & ~current_umask()); + err = unix_mknod(sun_path, mode, &path); + if (err) { + if (err == -EEXIST) + err = -EADDRINUSE; + goto out; + } + } + err = mutex_lock_interruptible(&u->bindlock); if (err) - goto out; + goto out_put; err = -EINVAL; if (u->addr) @@ -1028,16 +1041,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) atomic_set(&addr->refcnt, 1); if (sun_path[0]) { - struct path path; - umode_t mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); - if (err) { - if (err == -EEXIST) - err = -EADDRINUSE; - unix_release_addr(addr); - goto out_up; - } addr->hash = UNIX_HASH_SIZE; hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); @@ -1064,6 +1067,9 @@ out_unlock: spin_unlock(&unix_table_lock); out_up: mutex_unlock(&u->bindlock); +out_put: + if (err) + path_put(&path); out: return err; } @@ -1103,6 +1109,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, unsigned int hash; int err; + err = -EINVAL; + if (alen < offsetofend(struct sockaddr, sa_family)) + goto out; + if (addr->sa_family != AF_UNSPEC) { err = unix_mkname(sunaddr, alen, &hash); if (err < 0) diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 6a0d48525fcf..c36757e72844 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); + BUG_ON(!atomic_long_read(&u->inflight)); BUG_ON(list_empty(&u->link)); if (atomic_long_dec_and_test(&u->inflight)) @@ -341,6 +342,14 @@ void unix_gc(void) } list_del(&cursor); + /* Now gc_candidates contains only garbage. Restore original + * inflight counters for these as well, and remove the skbuffs + * which are creating the cycle(s). + */ + skb_queue_head_init(&hitlist); + list_for_each_entry(u, &gc_candidates, link) + scan_children(&u->sk, inc_inflight, &hitlist); + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ @@ -350,14 +359,6 @@ void unix_gc(void) list_move_tail(&u->link, &gc_inflight_list); } - /* Now gc_candidates contains only garbage. Restore original - * inflight counters for these as well, and remove the skbuffs - * which are creating the cycle(s). - */ - skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) - scan_children(&u->sk, inc_inflight, &hitlist); - spin_unlock(&unix_gc_lock); /* Here we are. Hitlist is filled. Die. */ diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 0a369bb440e7..662bdd20a748 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -842,7 +842,7 @@ static void vmci_transport_peer_detach_cb(u32 sub_id, * qp_handle. */ if (vmci_handle_is_invalid(e_payload->handle) || - vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) + !vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) return; /* We don't ask for delayed CBs when we subscribe to this event (we @@ -2154,7 +2154,7 @@ module_exit(vmci_transport_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMCI transport for Virtual Sockets"); -MODULE_VERSION("1.0.2.0-k"); +MODULE_VERSION("1.0.3.0-k"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("vmware_vsock"); MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1f0de6d74daa..de10e3c0e2a4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -302,8 +302,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, [NL80211_ATTR_PID] = { .type = NLA_U32 }, [NL80211_ATTR_4ADDR] = { .type = NLA_U8 }, - [NL80211_ATTR_PMKID] = { .type = NLA_BINARY, - .len = WLAN_PMKID_LEN }, + [NL80211_ATTR_PMKID] = { .len = WLAN_PMKID_LEN }, [NL80211_ATTR_DURATION] = { .type = NLA_U32 }, [NL80211_ATTR_COOKIE] = { .type = NLA_U64 }, [NL80211_ATTR_TX_RATES] = { .type = NLA_NESTED }, @@ -359,6 +358,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 }, [NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 }, [NL80211_ATTR_P2P_OPPPS] = { .type = NLA_U8 }, + [NL80211_ATTR_LOCAL_MESH_POWER_MODE] = {. type = NLA_U32 }, [NL80211_ATTR_ACL_POLICY] = {. type = NLA_U32 }, [NL80211_ATTR_MAC_ADDRS] = { .type = NLA_NESTED }, [NL80211_ATTR_STA_CAPABILITY] = { .type = NLA_U16 }, @@ -492,21 +492,17 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb, { int err; - rtnl_lock(); - if (!cb->args[0]) { err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, nl80211_fam.attrbuf, nl80211_fam.maxattr, nl80211_policy); if (err) - goto out_unlock; + return err; *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), nl80211_fam.attrbuf); - if (IS_ERR(*wdev)) { - err = PTR_ERR(*wdev); - goto out_unlock; - } + if (IS_ERR(*wdev)) + return PTR_ERR(*wdev); *rdev = wiphy_to_rdev((*wdev)->wiphy); /* 0 is the first index - add 1 to parse only once */ cb->args[0] = (*rdev)->wiphy_idx + 1; @@ -516,10 +512,8 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); struct wireless_dev *tmp; - if (!wiphy) { - err = -ENODEV; - goto out_unlock; - } + if (!wiphy) + return -ENODEV; *rdev = wiphy_to_rdev(wiphy); *wdev = NULL; @@ -530,21 +524,11 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb, } } - if (!*wdev) { - err = -ENODEV; - goto out_unlock; - } + if (!*wdev) + return -ENODEV; } return 0; - out_unlock: - rtnl_unlock(); - return err; -} - -static void nl80211_finish_wdev_dump(struct cfg80211_registered_device *rdev) -{ - rtnl_unlock(); } /* IE validation */ @@ -3884,9 +3868,10 @@ static int nl80211_dump_station(struct sk_buff *skb, int sta_idx = cb->args[2]; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out_err; if (!wdev->netdev) { err = -EINVAL; @@ -3922,7 +3907,7 @@ static int nl80211_dump_station(struct sk_buff *skb, cb->args[2] = sta_idx; err = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return err; } @@ -4639,9 +4624,10 @@ static int nl80211_dump_mpath(struct sk_buff *skb, int path_idx = cb->args[2]; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out_err; if (!rdev->ops->dump_mpath) { err = -EOPNOTSUPP; @@ -4675,7 +4661,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, cb->args[2] = path_idx; err = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return err; } @@ -4835,9 +4821,10 @@ static int nl80211_dump_mpp(struct sk_buff *skb, int path_idx = cb->args[2]; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out_err; if (!rdev->ops->dump_mpp) { err = -EOPNOTSUPP; @@ -4870,7 +4857,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb, cb->args[2] = path_idx; err = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return err; } @@ -5718,6 +5705,10 @@ static int validate_scan_freqs(struct nlattr *freqs) struct nlattr *attr1, *attr2; int n_channels = 0, tmp1, tmp2; + nla_for_each_nested(attr1, freqs, tmp1) + if (nla_len(attr1) != sizeof(u32)) + return 0; + nla_for_each_nested(attr1, freqs, tmp1) { n_channels++; /* @@ -6806,9 +6797,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) int start = cb->args[2], idx = 0; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); - if (err) + if (err) { + rtnl_unlock(); return err; + } wdev_lock(wdev); spin_lock_bh(&rdev->bss_lock); @@ -6831,7 +6825,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) wdev_unlock(wdev); cb->args[2] = idx; - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return skb->len; } @@ -6915,9 +6909,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) int res; bool radio_stats; + rtnl_lock(); res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (res) - return res; + goto out_err; /* prepare_wdev_dump parsed the attributes */ radio_stats = nl80211_fam.attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS]; @@ -6958,7 +6953,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) cb->args[2] = survey_idx; res = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return res; } @@ -10158,17 +10153,13 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, void *data = NULL; unsigned int data_len = 0; - rtnl_lock(); - if (cb->args[0]) { /* subtract the 1 again here */ struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); struct wireless_dev *tmp; - if (!wiphy) { - err = -ENODEV; - goto out_unlock; - } + if (!wiphy) + return -ENODEV; *rdev = wiphy_to_rdev(wiphy); *wdev = NULL; @@ -10189,13 +10180,11 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, nl80211_fam.attrbuf, nl80211_fam.maxattr, nl80211_policy); if (err) - goto out_unlock; + return err; if (!nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID] || - !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) { - err = -EINVAL; - goto out_unlock; - } + !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) + return -EINVAL; *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), nl80211_fam.attrbuf); @@ -10204,10 +10193,8 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, *rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), nl80211_fam.attrbuf); - if (IS_ERR(*rdev)) { - err = PTR_ERR(*rdev); - goto out_unlock; - } + if (IS_ERR(*rdev)) + return PTR_ERR(*rdev); vid = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID]); subcmd = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]); @@ -10220,19 +10207,15 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd) continue; - if (!vcmd->dumpit) { - err = -EOPNOTSUPP; - goto out_unlock; - } + if (!vcmd->dumpit) + return -EOPNOTSUPP; vcmd_idx = i; break; } - if (vcmd_idx < 0) { - err = -EOPNOTSUPP; - goto out_unlock; - } + if (vcmd_idx < 0) + return -EOPNOTSUPP; if (nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]); @@ -10249,9 +10232,6 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, /* keep rtnl locked in successful case */ return 0; - out_unlock: - rtnl_unlock(); - return err; } static int nl80211_vendor_cmd_dump(struct sk_buff *skb, @@ -10266,9 +10246,10 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb, int err; struct nlattr *vendor_data; + rtnl_lock(); err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out; vcmd_idx = cb->args[2]; data = (void *)cb->args[3]; @@ -10277,18 +10258,26 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb, if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_NETDEV)) { - if (!wdev) - return -EINVAL; + if (!wdev) { + err = -EINVAL; + goto out; + } if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV && - !wdev->netdev) - return -EINVAL; + !wdev->netdev) { + err = -EINVAL; + goto out; + } if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) { if (wdev->netdev && - !netif_running(wdev->netdev)) - return -ENETDOWN; - if (!wdev->netdev && !wdev->p2p_started) - return -ENETDOWN; + !netif_running(wdev->netdev)) { + err = -ENETDOWN; + goto out; + } + if (!wdev->netdev && !wdev->p2p_started) { + err = -ENETDOWN; + goto out; + } } } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b5e665b3cfb0..77055a362041 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1216,7 +1216,7 @@ static inline int policy_to_flow_dir(int dir) } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, - const struct flowi *fl) + const struct flowi *fl, u16 family) { struct xfrm_policy *pol; struct net *net = sock_net(sk); @@ -1225,8 +1225,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, read_lock_bh(&net->xfrm.xfrm_policy_lock); pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { - bool match = xfrm_selector_match(&pol->selector, fl, - sk->sk_family); + bool match = xfrm_selector_match(&pol->selector, fl, family); int err = 0; if (match) { @@ -1776,43 +1775,6 @@ free_dst: goto out; } -#ifdef CONFIG_XFRM_SUB_POLICY -static int xfrm_dst_alloc_copy(void **target, const void *src, int size) -{ - if (!*target) { - *target = kmalloc(size, GFP_ATOMIC); - if (!*target) - return -ENOMEM; - } - - memcpy(*target, src, size); - return 0; -} -#endif - -static int xfrm_dst_update_parent(struct dst_entry *dst, - const struct xfrm_selector *sel) -{ -#ifdef CONFIG_XFRM_SUB_POLICY - struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - return xfrm_dst_alloc_copy((void **)&(xdst->partner), - sel, sizeof(*sel)); -#else - return 0; -#endif -} - -static int xfrm_dst_update_origin(struct dst_entry *dst, - const struct flowi *fl) -{ -#ifdef CONFIG_XFRM_SUB_POLICY - struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - return xfrm_dst_alloc_copy((void **)&(xdst->origin), fl, sizeof(*fl)); -#else - return 0; -#endif -} - static int xfrm_expand_policies(const struct flowi *fl, u16 family, struct xfrm_policy **pols, int *num_pols, int *num_xfrms) @@ -1884,16 +1846,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, xdst = (struct xfrm_dst *)dst; xdst->num_xfrms = err; - if (num_pols > 1) - err = xfrm_dst_update_parent(dst, &pols[1]->selector); - else - err = xfrm_dst_update_origin(dst, fl); - if (unlikely(err)) { - dst_free(dst); - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); - return ERR_PTR(err); - } - xdst->num_pols = num_pols; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); @@ -2221,7 +2173,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; - pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); + pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2500,7 +2452,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { - pol = xfrm_sk_policy_lookup(sk, dir, &fl); + pol = xfrm_sk_policy_lookup(sk, dir, &fl, family); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; @@ -3030,6 +2982,11 @@ static int __net_init xfrm_net_init(struct net *net) { int rv; + /* Initialize the per-net locks here */ + spin_lock_init(&net->xfrm.xfrm_state_lock); + rwlock_init(&net->xfrm.xfrm_policy_lock); + mutex_init(&net->xfrm.xfrm_cfg_mutex); + rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; @@ -3046,11 +3003,6 @@ static int __net_init xfrm_net_init(struct net *net) if (rv < 0) goto out; - /* Initialize the per-net locks here */ - spin_lock_init(&net->xfrm.xfrm_state_lock); - rwlock_init(&net->xfrm.xfrm_policy_lock); - mutex_init(&net->xfrm.xfrm_cfg_mutex); - return 0; out: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 805681a7d356..7a5a64e70b4d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -412,7 +412,14 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es up = nla_data(rp); ulen = xfrm_replay_state_esn_len(up); - if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen) + /* Check the overall length and the internal bitmap length to avoid + * potential overflow. */ + if (nla_len(rp) < ulen || + xfrm_replay_state_esn_len(replay_esn) != ulen || + replay_esn->bmp_len != up->bmp_len) + return -EINVAL; + + if (up->replay_window > up->bmp_len * sizeof(__u32) * 8) return -EINVAL; return 0; diff --git a/Documentation/mic/mpssd/.gitignore b/samples/mic/mpssd/.gitignore index 8b7c72f07c92..8b7c72f07c92 100644 --- a/Documentation/mic/mpssd/.gitignore +++ b/samples/mic/mpssd/.gitignore diff --git a/samples/mic/mpssd/Makefile b/samples/mic/mpssd/Makefile new file mode 100644 index 000000000000..3e3ef91fed6b --- /dev/null +++ b/samples/mic/mpssd/Makefile @@ -0,0 +1,27 @@ +ifndef CROSS_COMPILE +uname_M := $(shell uname -m 2>/dev/null || echo not) +ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) + +ifeq ($(ARCH),x86) + +PROGS := mpssd +CC = $(CROSS_COMPILE)gcc +CFLAGS := -I../../../usr/include -I../../../tools/include + +ifdef DEBUG +CFLAGS += -DDEBUG=$(DEBUG) +endif + +all: $(PROGS) +mpssd: mpssd.c sysfs.c + $(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread + +install: + install mpssd /usr/sbin/mpssd + install micctrl /usr/sbin/micctrl + +clean: + rm -fr $(PROGS) + +endif +endif diff --git a/Documentation/mic/mpssd/micctrl b/samples/mic/mpssd/micctrl index 8f2629b41c5f..8f2629b41c5f 100755..100644 --- a/Documentation/mic/mpssd/micctrl +++ b/samples/mic/mpssd/micctrl diff --git a/Documentation/mic/mpssd/mpss b/samples/mic/mpssd/mpss index 09ea90931649..09ea90931649 100755..100644 --- a/Documentation/mic/mpssd/mpss +++ b/samples/mic/mpssd/mpss diff --git a/Documentation/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c index c99a75968c01..c99a75968c01 100644 --- a/Documentation/mic/mpssd/mpssd.c +++ b/samples/mic/mpssd/mpssd.c diff --git a/Documentation/mic/mpssd/mpssd.h b/samples/mic/mpssd/mpssd.h index 8bd64944aacc..8bd64944aacc 100644 --- a/Documentation/mic/mpssd/mpssd.h +++ b/samples/mic/mpssd/mpssd.h diff --git a/Documentation/mic/mpssd/sysfs.c b/samples/mic/mpssd/sysfs.c index 8dd326936083..8dd326936083 100644 --- a/Documentation/mic/mpssd/sysfs.c +++ b/samples/mic/mpssd/sysfs.c diff --git a/samples/seccomp/bpf-helper.h b/samples/seccomp/bpf-helper.h index 38ee70f3cd5b..1d8de9edd858 100644 --- a/samples/seccomp/bpf-helper.h +++ b/samples/seccomp/bpf-helper.h @@ -138,7 +138,7 @@ union arg64 { #define ARG_32(idx) \ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx)) -/* Loads hi into A and lo in X */ +/* Loads lo into M[0] and hi into M[1] and A */ #define ARG_64(idx) \ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx)), \ BPF_STMT(BPF_ST, 0), /* lo -> M[0] */ \ @@ -153,88 +153,107 @@ union arg64 { BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 1, 0), \ jt -/* Checks the lo, then swaps to check the hi. A=lo,X=hi */ +#define JA32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \ + jt + +#define JGE32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \ + jt + +#define JGT32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 0, 1), \ + jt + +#define JLE32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 1, 0), \ + jt + +#define JLT32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \ + jt + +/* + * All the JXX64 checks assume lo is saved in M[0] and hi is saved in both + * A and M[1]. This invariant is kept by restoring A if necessary. + */ #define JEQ64(lo, hi, jt) \ + /* if (hi != arg.hi) goto NOMATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ + /* if (lo != arg.lo) goto NOMATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 0, 2), \ - BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ jt, \ - BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */ + BPF_STMT(BPF_LD+BPF_MEM, 1) #define JNE64(lo, hi, jt) \ - BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 5, 0), \ - BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ + /* if (hi != arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo != arg.lo) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 2, 0), \ - BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ jt, \ - BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */ - -#define JA32(value, jt) \ - BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \ - jt + BPF_STMT(BPF_LD+BPF_MEM, 1) #define JA64(lo, hi, jt) \ + /* if (hi & arg.hi) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (hi), 3, 0), \ - BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo & arg.lo) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (lo), 0, 2), \ - BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ jt, \ - BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */ + BPF_STMT(BPF_LD+BPF_MEM, 1) -#define JGE32(value, jt) \ - BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \ - jt - -#define JLT32(value, jt) \ - BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \ - jt - -/* Shortcut checking if hi > arg.hi. */ #define JGE64(lo, hi, jt) \ + /* if (hi > arg.hi) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ - BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo >= arg.lo) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 0, 2), \ - BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \ - jt, \ - BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */ - -#define JLT64(lo, hi, jt) \ - BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \ - BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ - BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ - BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \ - BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ jt, \ - BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */ + BPF_STMT(BPF_LD+BPF_MEM, 1) -#define JGT32(value, jt) \ - BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 0, 1), \ - jt - -#define JLE32(value, jt) \ - BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 1, 0), \ - jt - -/* Check hi > args.hi first, then do the GE checking */ #define JGT64(lo, hi, jt) \ + /* if (hi > arg.hi) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ - BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo > arg.lo) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 0, 2), \ - BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ jt, \ - BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */ + BPF_STMT(BPF_LD+BPF_MEM, 1) #define JLE64(lo, hi, jt) \ - BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 6, 0), \ - BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \ - BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ + /* if (hi < arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo <= arg.lo) goto MATCH; */ \ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \ - BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define JLT64(lo, hi, jt) \ + /* if (hi < arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo < arg.lo) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 2, 0), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ jt, \ - BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */ + BPF_STMT(BPF_LD+BPF_MEM, 1) #define LOAD_SYSCALL_NR \ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, \ diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 2b3c22808c3b..fabdf0e5c28c 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -2348,6 +2348,7 @@ sub process { # Check for git id commit length and improperly formed commit descriptions if ($in_commit_log && !$commit_log_possible_stack_dump && + $line !~ /^This reverts commit [0-9a-f]{7,40}/ && ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i || ($line =~ /\b[0-9a-f]{12,40}\b/i && $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i && @@ -3252,7 +3253,7 @@ sub process { $fixedline =~ s/\s*=\s*$/ = {/; fix_insert_line($fixlinenr, $fixedline); $fixedline = $line; - $fixedline =~ s/^(.\s*){\s*/$1/; + $fixedline =~ s/^(.\s*)\{\s*/$1/; fix_insert_line($fixlinenr, $fixedline); } } @@ -3602,7 +3603,7 @@ sub process { my $fixedline = rtrim($prevrawline) . " {"; fix_insert_line($fixlinenr, $fixedline); $fixedline = $rawline; - $fixedline =~ s/^(.\s*){\s*/$1\t/; + $fixedline =~ s/^(.\s*)\{\s*/$1\t/; if ($fixedline !~ /^\+\s*$/) { fix_insert_line($fixlinenr, $fixedline); } @@ -4091,7 +4092,7 @@ sub process { if (ERROR("SPACING", "space required before the open brace '{'\n" . $herecurr) && $fix) { - $fixed[$fixlinenr] =~ s/^(\+.*(?:do|\))){/$1 {/; + $fixed[$fixlinenr] =~ s/^(\+.*(?:do|\)))\{/$1 {/; } } diff --git a/security/inode.c b/security/inode.c index 16622aef9bde..0f1a041bf6cb 100644 --- a/security/inode.c +++ b/security/inode.c @@ -100,7 +100,7 @@ struct dentry *securityfs_create_file(const char *name, umode_t mode, dir = d_inode(parent); mutex_lock(&dir->i_mutex); - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_one_len2(name, mount, parent, strlen(name)); if (IS_ERR(dentry)) goto out; diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index ed5a9c110b3a..9ce9d5003dcc 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -203,10 +203,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint, cause = "missing-hash"; status = INTEGRITY_NOLABEL; - if (opened & FILE_CREATED) { + if (opened & FILE_CREATED) iint->flags |= IMA_NEW_FILE; + if ((iint->flags & IMA_NEW_FILE) && + !(iint->flags & IMA_DIGSIG_REQUIRED)) status = INTEGRITY_PASS; - } goto out; } diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index 696ccfa08d10..31898856682e 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -428,7 +428,7 @@ static int init_blkcipher_desc(struct blkcipher_desc *desc, const u8 *key, static struct key *request_master_key(struct encrypted_key_payload *epayload, const u8 **master_key, size_t *master_keylen) { - struct key *mkey = NULL; + struct key *mkey = ERR_PTR(-EINVAL); if (!strncmp(epayload->master_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) { diff --git a/security/keys/gc.c b/security/keys/gc.c index addf060399e0..9cb4fe4478a1 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -46,7 +46,7 @@ static unsigned long key_gc_flags; * immediately unlinked. */ struct key_type key_type_dead = { - .name = "dead", + .name = ".dead", }; /* diff --git a/security/keys/key.c b/security/keys/key.c index 534808915371..09c10b181881 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -934,12 +934,11 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen) /* the key must be writable */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) - goto error; + return ret; /* attempt to update it if supported */ - ret = -EOPNOTSUPP; if (!key->type->update) - goto error; + return -EOPNOTSUPP; memset(&prep, 0, sizeof(prep)); prep.data = payload; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 1c3872aeed14..671709d8610d 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -97,7 +97,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type, /* pull the payload in if one was supplied */ payload = NULL; - if (_payload) { + if (plen) { ret = -ENOMEM; payload = kmalloc(plen, GFP_KERNEL | __GFP_NOWARN); if (!payload) { @@ -271,7 +271,8 @@ error: * Create and join an anonymous session keyring or join a named session * keyring, creating it if necessary. A named session keyring must have Search * permission for it to be joined. Session keyrings without this permit will - * be skipped over. + * be skipped over. It is not permitted for userspace to create or join + * keyrings whose name begin with a dot. * * If successful, the ID of the joined session keyring will be returned. */ @@ -288,12 +289,16 @@ long keyctl_join_session_keyring(const char __user *_name) ret = PTR_ERR(name); goto error; } + + ret = -EPERM; + if (name[0] == '.') + goto error_name; } /* join the session */ ret = join_session_keyring(name); +error_name: kfree(name); - error: return ret; } @@ -322,7 +327,7 @@ long keyctl_update_key(key_serial_t id, /* pull the payload in if one was supplied */ payload = NULL; - if (_payload) { + if (plen) { ret = -ENOMEM; payload = kmalloc(plen, GFP_KERNEL); if (!payload) @@ -1223,8 +1228,8 @@ error: * Read or set the default keyring in which request_key() will cache keys and * return the old setting. * - * If a process keyring is specified then this will be created if it doesn't - * yet exist. The old setting will be returned if successful. + * If a thread or process keyring is specified then it will be created if it + * doesn't yet exist. The old setting will be returned if successful. */ long keyctl_set_reqkey_keyring(int reqkey_defl) { @@ -1249,11 +1254,8 @@ long keyctl_set_reqkey_keyring(int reqkey_defl) case KEY_REQKEY_DEFL_PROCESS_KEYRING: ret = install_process_keyring_to_cred(new); - if (ret < 0) { - if (ret != -EEXIST) - goto error; - ret = 0; - } + if (ret < 0) + goto error; goto set; case KEY_REQKEY_DEFL_DEFAULT: diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index e6d50172872f..4ed909142956 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -125,13 +125,18 @@ error: } /* - * Install a fresh thread keyring directly to new credentials. This keyring is - * allowed to overrun the quota. + * Install a thread keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ int install_thread_keyring_to_cred(struct cred *new) { struct key *keyring; + if (new->thread_keyring) + return 0; + keyring = keyring_alloc("_tid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, KEY_ALLOC_QUOTA_OVERRUN, NULL); @@ -143,7 +148,9 @@ int install_thread_keyring_to_cred(struct cred *new) } /* - * Install a fresh thread keyring, discarding the old one. + * Install a thread keyring to the current task if it didn't have one already. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ static int install_thread_keyring(void) { @@ -154,8 +161,6 @@ static int install_thread_keyring(void) if (!new) return -ENOMEM; - BUG_ON(new->thread_keyring); - ret = install_thread_keyring_to_cred(new); if (ret < 0) { abort_creds(new); @@ -166,17 +171,17 @@ static int install_thread_keyring(void) } /* - * Install a process keyring directly to a credentials struct. + * Install a process keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. * - * Returns -EEXIST if there was already a process keyring, 0 if one installed, - * and other value on any other error + * Return: 0 if a process keyring is now present; -errno on failure. */ int install_process_keyring_to_cred(struct cred *new) { struct key *keyring; if (new->process_keyring) - return -EEXIST; + return 0; keyring = keyring_alloc("_pid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, @@ -189,11 +194,9 @@ int install_process_keyring_to_cred(struct cred *new) } /* - * Make sure a process keyring is installed for the current process. The - * existing process keyring is not replaced. + * Install a process keyring to the current task if it didn't have one already. * - * Returns 0 if there is a process keyring by the end of this function, some - * error otherwise. + * Return: 0 if a process keyring is now present; -errno on failure. */ static int install_process_keyring(void) { @@ -207,14 +210,18 @@ static int install_process_keyring(void) ret = install_process_keyring_to_cred(new); if (ret < 0) { abort_creds(new); - return ret != -EEXIST ? ret : 0; + return ret; } return commit_creds(new); } /* - * Install a session keyring directly to a credentials struct. + * Install the given keyring as the session keyring of the given credentials + * struct, replacing the existing one if any. If the given keyring is NULL, + * then install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) { @@ -249,8 +256,11 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) } /* - * Install a session keyring, discarding the old one. If a keyring is not - * supplied, an empty one is invented. + * Install the given keyring as the session keyring of the current task, + * replacing the existing one if any. If the given keyring is NULL, then + * install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ static int install_session_keyring(struct key *keyring) { diff --git a/security/security.c b/security/security.c index 46f405ce6b0f..ae05ab153c5a 100644 --- a/security/security.c +++ b/security/security.c @@ -498,6 +498,7 @@ int security_path_chown(struct path *path, kuid_t uid, kgid_t gid) return 0; return call_int_hook(path_chown, 0, path, uid, gid); } +EXPORT_SYMBOL(security_path_chown); int security_path_chroot(struct path *path) { diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 94a0bfc748d1..2bc8b555bca9 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5673,7 +5673,7 @@ static int selinux_setprocattr(struct task_struct *p, return error; /* Obtain a SID for the context, if one was specified. */ - if (size && str[1] && str[1] != '\n') { + if (size && str[0] && str[0] != '\n') { if (str[size-1] == '\n') { str[size-1] = 0; size--; diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 58e79e02f217..e326c1d80416 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1530,19 +1530,14 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, void __user *arg) { struct snd_seq_queue_info info; - int result; struct snd_seq_queue *q; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; - result = snd_seq_queue_alloc(client->number, info.locked, info.flags); - if (result < 0) - return result; - - q = queueptr(result); - if (q == NULL) - return -EINVAL; + q = snd_seq_queue_alloc(client->number, info.locked, info.flags); + if (IS_ERR(q)) + return PTR_ERR(q); info.queue = q->queue; info.locked = q->locked; @@ -1552,7 +1547,7 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, if (! info.name[0]) snprintf(info.name, sizeof(info.name), "Queue-%d", q->queue); strlcpy(q->name, info.name, sizeof(q->name)); - queuefree(q); + snd_use_lock_free(&q->use_lock); if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; @@ -1921,6 +1916,7 @@ static int snd_seq_ioctl_set_client_pool(struct snd_seq_client *client, info.output_pool != client->pool->size)) { if (snd_seq_write_pool_allocated(client)) { /* remove all existing cells */ + snd_seq_pool_mark_closing(client->pool); snd_seq_queue_client_leave_cells(client->number); snd_seq_pool_done(client->pool); } diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c index 1d5acbe0c08b..3490d21ab9e7 100644 --- a/sound/core/seq/seq_fifo.c +++ b/sound/core/seq/seq_fifo.c @@ -70,6 +70,9 @@ void snd_seq_fifo_delete(struct snd_seq_fifo **fifo) return; *fifo = NULL; + if (f->pool) + snd_seq_pool_mark_closing(f->pool); + snd_seq_fifo_clear(f); /* wake up clients if any */ @@ -135,6 +138,7 @@ int snd_seq_fifo_event_in(struct snd_seq_fifo *f, f->tail = cell; if (f->head == NULL) f->head = cell; + cell->next = NULL; f->cells++; spin_unlock_irqrestore(&f->lock, flags); @@ -214,6 +218,8 @@ void snd_seq_fifo_cell_putback(struct snd_seq_fifo *f, spin_lock_irqsave(&f->lock, flags); cell->next = f->head; f->head = cell; + if (!f->tail) + f->tail = cell; f->cells++; spin_unlock_irqrestore(&f->lock, flags); } @@ -259,6 +265,10 @@ int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize) /* NOTE: overflow flag is not cleared */ spin_unlock_irqrestore(&f->lock, flags); + /* close the old pool and wait until all users are gone */ + snd_seq_pool_mark_closing(oldpool); + snd_use_lock_sync(&f->use_lock); + /* release cells in old pool */ for (cell = oldhead; cell; cell = next) { next = cell->next; diff --git a/sound/core/seq/seq_lock.c b/sound/core/seq/seq_lock.c index 3b693e924db7..12ba83367b1b 100644 --- a/sound/core/seq/seq_lock.c +++ b/sound/core/seq/seq_lock.c @@ -28,19 +28,16 @@ /* wait until all locks are released */ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) { - int max_count = 5 * HZ; + int warn_count = 5 * HZ; if (atomic_read(lockp) < 0) { pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line); return; } while (atomic_read(lockp) > 0) { - if (max_count == 0) { - pr_warn("ALSA: seq_lock: timeout [%d left] in %s:%d\n", atomic_read(lockp), file, line); - break; - } + if (warn_count-- == 0) + pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line); schedule_timeout_uninterruptible(1); - max_count--; } } diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index c850345c43b5..5847c4475bf3 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -414,32 +414,33 @@ int snd_seq_pool_init(struct snd_seq_pool *pool) return 0; } +/* refuse the further insertion to the pool */ +void snd_seq_pool_mark_closing(struct snd_seq_pool *pool) +{ + unsigned long flags; + + if (snd_BUG_ON(!pool)) + return; + spin_lock_irqsave(&pool->lock, flags); + pool->closing = 1; + spin_unlock_irqrestore(&pool->lock, flags); +} + /* remove events */ int snd_seq_pool_done(struct snd_seq_pool *pool) { unsigned long flags; struct snd_seq_event_cell *ptr; - int max_count = 5 * HZ; if (snd_BUG_ON(!pool)) return -EINVAL; /* wait for closing all threads */ - spin_lock_irqsave(&pool->lock, flags); - pool->closing = 1; - spin_unlock_irqrestore(&pool->lock, flags); - if (waitqueue_active(&pool->output_sleep)) wake_up(&pool->output_sleep); - while (atomic_read(&pool->counter) > 0) { - if (max_count == 0) { - pr_warn("ALSA: snd_seq_pool_done timeout: %d cells remain\n", atomic_read(&pool->counter)); - break; - } + while (atomic_read(&pool->counter) > 0) schedule_timeout_uninterruptible(1); - max_count--; - } /* release all resources */ spin_lock_irqsave(&pool->lock, flags); @@ -491,6 +492,7 @@ int snd_seq_pool_delete(struct snd_seq_pool **ppool) *ppool = NULL; if (pool == NULL) return 0; + snd_seq_pool_mark_closing(pool); snd_seq_pool_done(pool); kfree(pool); return 0; diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h index 4a2ec779b8a7..32f959c17786 100644 --- a/sound/core/seq/seq_memory.h +++ b/sound/core/seq/seq_memory.h @@ -84,6 +84,7 @@ static inline int snd_seq_total_cells(struct snd_seq_pool *pool) int snd_seq_pool_init(struct snd_seq_pool *pool); /* done pool - free events */ +void snd_seq_pool_mark_closing(struct snd_seq_pool *pool); int snd_seq_pool_done(struct snd_seq_pool *pool); /* create pool */ diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index 0bec02e89d51..79e0c5604ef8 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -181,23 +181,29 @@ void __exit snd_seq_queues_delete(void) } } +static void queue_use(struct snd_seq_queue *queue, int client, int use); + /* allocate a new queue - - * return queue index value or negative value for error + * return pointer to new queue or ERR_PTR(-errno) for error + * The new queue's use_lock is set to 1. It is the caller's responsibility to + * call snd_use_lock_free(&q->use_lock). */ -int snd_seq_queue_alloc(int client, int locked, unsigned int info_flags) +struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int info_flags) { struct snd_seq_queue *q; q = queue_new(client, locked); if (q == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); q->info_flags = info_flags; + queue_use(q, client, 1); + snd_use_lock_use(&q->use_lock); if (queue_list_add(q) < 0) { + snd_use_lock_free(&q->use_lock); queue_delete(q); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } - snd_seq_queue_use(q->queue, client, 1); /* use this queue */ - return q->queue; + return q; } /* delete a queue - queue must be owned by the client */ @@ -502,19 +508,9 @@ int snd_seq_queue_timer_set_tempo(int queueid, int client, return result; } - -/* use or unuse this queue - - * if it is the first client, starts the timer. - * if it is not longer used by any clients, stop the timer. - */ -int snd_seq_queue_use(int queueid, int client, int use) +/* use or unuse this queue */ +static void queue_use(struct snd_seq_queue *queue, int client, int use) { - struct snd_seq_queue *queue; - - queue = queueptr(queueid); - if (queue == NULL) - return -EINVAL; - mutex_lock(&queue->timer_mutex); if (use) { if (!test_and_set_bit(client, queue->clients_bitmap)) queue->clients++; @@ -529,6 +525,21 @@ int snd_seq_queue_use(int queueid, int client, int use) } else { snd_seq_timer_close(queue); } +} + +/* use or unuse this queue - + * if it is the first client, starts the timer. + * if it is not longer used by any clients, stop the timer. + */ +int snd_seq_queue_use(int queueid, int client, int use) +{ + struct snd_seq_queue *queue; + + queue = queueptr(queueid); + if (queue == NULL) + return -EINVAL; + mutex_lock(&queue->timer_mutex); + queue_use(queue, client, use); mutex_unlock(&queue->timer_mutex); queuefree(queue); return 0; diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h index 30c8111477f6..719093489a2c 100644 --- a/sound/core/seq/seq_queue.h +++ b/sound/core/seq/seq_queue.h @@ -71,7 +71,7 @@ void snd_seq_queues_delete(void); /* create new queue (constructor) */ -int snd_seq_queue_alloc(int client, int locked, unsigned int flags); +struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int flags); /* delete queue (destructor) */ int snd_seq_queue_delete(int client, int queueid); diff --git a/sound/core/timer.c b/sound/core/timer.c index ae4ea2e2e7fe..48eaccba82a3 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1621,6 +1621,7 @@ static int snd_timer_user_tselect(struct file *file, if (err < 0) goto __err; + tu->qhead = tu->qtail = tu->qused = 0; kfree(tu->queue); tu->queue = NULL; kfree(tu->tqueue); @@ -1700,9 +1701,21 @@ static int snd_timer_user_params(struct file *file, return -EBADFD; if (copy_from_user(¶ms, _params, sizeof(params))) return -EFAULT; - if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE) && params.ticks < 1) { - err = -EINVAL; - goto _end; + if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) { + u64 resolution; + + if (params.ticks < 1) { + err = -EINVAL; + goto _end; + } + + /* Don't allow resolution less than 1ms */ + resolution = snd_timer_resolution(tu->timeri); + resolution *= params.ticks; + if (resolution < 1000000) { + err = -EINVAL; + goto _end; + } } if (params.queue_size > 0 && (params.queue_size < 32 || params.queue_size > 1024)) { @@ -1946,6 +1959,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, tu = file->private_data; unit = tu->tread ? sizeof(struct snd_timer_tread) : sizeof(struct snd_timer_read); + mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); while ((long)count - result >= unit) { while (!tu->qused) { @@ -1961,7 +1975,9 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, add_wait_queue(&tu->qchange_sleep, &wait); spin_unlock_irq(&tu->qlock); + mutex_unlock(&tu->ioctl_lock); schedule(); + mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); remove_wait_queue(&tu->qchange_sleep, &wait); @@ -1981,7 +1997,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, tu->qused--; spin_unlock_irq(&tu->qlock); - mutex_lock(&tu->ioctl_lock); if (tu->tread) { if (copy_to_user(buffer, &tu->tqueue[qhead], sizeof(struct snd_timer_tread))) @@ -1991,7 +2006,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, sizeof(struct snd_timer_read))) err = -EFAULT; } - mutex_unlock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); if (err < 0) @@ -2001,6 +2015,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, } _error: spin_unlock_irq(&tu->qlock); + mutex_unlock(&tu->ioctl_lock); return result > 0 ? result : err; } diff --git a/sound/firewire/lib.h b/sound/firewire/lib.h index f3f6f84c48d6..bb5f8cdea3e2 100644 --- a/sound/firewire/lib.h +++ b/sound/firewire/lib.h @@ -42,7 +42,7 @@ struct snd_fw_async_midi_port { struct snd_rawmidi_substream *substream; snd_fw_async_midi_port_fill fill; - unsigned int consume_bytes; + int consume_bytes; }; int snd_fw_async_midi_port_init(struct snd_fw_async_midi_port *port, diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c index 9667cbfb0ca2..79edd88d5cd0 100644 --- a/sound/pci/ctxfi/cthw20k1.c +++ b/sound/pci/ctxfi/cthw20k1.c @@ -27,12 +27,6 @@ #include "cthw20k1.h" #include "ct20k1reg.h" -#if BITS_PER_LONG == 32 -#define CT_XFI_DMA_MASK DMA_BIT_MASK(32) /* 32 bit PTE */ -#else -#define CT_XFI_DMA_MASK DMA_BIT_MASK(64) /* 64 bit PTE */ -#endif - struct hw20k1 { struct hw hw; spinlock_t reg_20k1_lock; @@ -1904,19 +1898,18 @@ static int hw_card_start(struct hw *hw) { int err; struct pci_dev *pci = hw->pci; + const unsigned int dma_bits = BITS_PER_LONG; err = pci_enable_device(pci); if (err < 0) return err; /* Set DMA transfer mask */ - if (dma_set_mask(&pci->dev, CT_XFI_DMA_MASK) < 0 || - dma_set_coherent_mask(&pci->dev, CT_XFI_DMA_MASK) < 0) { - dev_err(hw->card->dev, - "architecture does not support PCI busmaster DMA with mask 0x%llx\n", - CT_XFI_DMA_MASK); - err = -ENXIO; - goto error1; + if (!dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) { + dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(dma_bits)); + } else { + dma_set_mask(&pci->dev, DMA_BIT_MASK(32)); + dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(32)); } if (!hw->io_base) { diff --git a/sound/pci/ctxfi/cthw20k2.c b/sound/pci/ctxfi/cthw20k2.c index 9dc2950e1ab7..d86678c2a957 100644 --- a/sound/pci/ctxfi/cthw20k2.c +++ b/sound/pci/ctxfi/cthw20k2.c @@ -26,12 +26,6 @@ #include "cthw20k2.h" #include "ct20k2reg.h" -#if BITS_PER_LONG == 32 -#define CT_XFI_DMA_MASK DMA_BIT_MASK(32) /* 32 bit PTE */ -#else -#define CT_XFI_DMA_MASK DMA_BIT_MASK(64) /* 64 bit PTE */ -#endif - struct hw20k2 { struct hw hw; /* for i2c */ @@ -2029,19 +2023,18 @@ static int hw_card_start(struct hw *hw) int err = 0; struct pci_dev *pci = hw->pci; unsigned int gctl; + const unsigned int dma_bits = BITS_PER_LONG; err = pci_enable_device(pci); if (err < 0) return err; /* Set DMA transfer mask */ - if (dma_set_mask(&pci->dev, CT_XFI_DMA_MASK) < 0 || - dma_set_coherent_mask(&pci->dev, CT_XFI_DMA_MASK) < 0) { - dev_err(hw->card->dev, - "architecture does not support PCI busmaster DMA with mask 0x%llx\n", - CT_XFI_DMA_MASK); - err = -ENXIO; - goto error1; + if (!dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) { + dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(dma_bits)); + } else { + dma_set_mask(&pci->dev, DMA_BIT_MASK(32)); + dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(32)); } if (!hw->io_base) { diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h index 373fcad840ea..776dffa88aee 100644 --- a/sound/pci/hda/hda_codec.h +++ b/sound/pci/hda/hda_codec.h @@ -294,6 +294,8 @@ struct hda_codec { #define list_for_each_codec(c, bus) \ list_for_each_entry(c, &(bus)->core.codec_list, core.list) +#define list_for_each_codec_safe(c, n, bus) \ + list_for_each_entry_safe(c, n, &(bus)->core.codec_list, core.list) /* snd_hda_codec_read/write optional flags */ #define HDA_RW_NO_RESPONSE_FALLBACK (1 << 0) diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 5baf8b56b6e7..9c6e10fb479f 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1128,8 +1128,12 @@ EXPORT_SYMBOL_GPL(azx_probe_codecs); /* configure each codec instance */ int azx_codec_configure(struct azx *chip) { - struct hda_codec *codec; - list_for_each_codec(codec, &chip->bus) { + struct hda_codec *codec, *next; + + /* use _safe version here since snd_hda_codec_configure() deregisters + * the device upon error and deletes itself from the bus list. + */ + list_for_each_codec_safe(codec, next, &chip->bus) { snd_hda_codec_configure(codec); } return 0; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index dc2fa576d60d..689df78f640a 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3190,6 +3190,7 @@ static int check_dyn_adc_switch(struct hda_codec *codec) spec->input_paths[i][nums]); spec->input_paths[i][nums] = spec->input_paths[i][n]; + spec->input_paths[i][n] = 0; } } nums++; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index ad4a1e9a3ae1..e6de496bffbe 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2166,7 +2166,20 @@ static void azx_remove(struct pci_dev *pci) /* cancel the pending probing work */ chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); + /* FIXME: below is an ugly workaround. + * Both device_release_driver() and driver_probe_device() + * take *both* the device's and its parent's lock before + * calling the remove() and probe() callbacks. The codec + * probe takes the locks of both the codec itself and its + * parent, i.e. the PCI controller dev. Meanwhile, when + * the PCI controller is unbound, it takes its lock, too + * ==> ouch, a deadlock! + * As a workaround, we unlock temporarily here the controller + * device during cancel_work_sync() call. + */ + device_unlock(&pci->dev); cancel_work_sync(&hda->probe_work); + device_lock(&pci->dev); snd_card_free(card); } @@ -2208,9 +2221,9 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, /* Lewisburg */ { PCI_DEVICE(0x8086, 0xa1f0), - .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE }, { PCI_DEVICE(0x8086, 0xa270), - .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE }, /* Lynx Point-LP */ { PCI_DEVICE(0x8086, 0x9c20), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 00c50d58f108..5cab24f52825 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2233,6 +2233,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x8691, "ASUS ROG Ranger VIII", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT), SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP), + SND_PCI_QUIRK(0x104d, 0x9060, "Sony Vaio VPCL14M1R", ALC882_FIXUP_NO_PRIMARY_HP), SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP), SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP), @@ -4831,6 +4832,7 @@ enum { ALC292_FIXUP_DISABLE_AAMIX, ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK, ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, ALC275_FIXUP_DELL_XPS, ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, ALC293_FIXUP_LENOVO_SPK_NOISE, @@ -5429,6 +5431,15 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE }, + [ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x18, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE + }, [ALC275_FIXUP_DELL_XPS] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -5501,7 +5512,7 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc298_fixup_speaker_volume, .chained = true, - .chain_id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, + .chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, @@ -5560,6 +5571,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), + SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -5674,6 +5686,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), + SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), @@ -6038,6 +6051,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { ALC295_STANDARD_PINS, {0x17, 0x21014040}, {0x18, 0x21a19050}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC295_STANDARD_PINS), SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, ALC298_STANDARD_PINS, {0x17, 0x90170110}), @@ -6047,6 +6062,12 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, ALC298_STANDARD_PINS, {0x17, 0x90170150}), + SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_SPK_VOLUME, + {0x12, 0xb7a60140}, + {0x13, 0xb7a60150}, + {0x17, 0x90170110}, + {0x1a, 0x03011020}, + {0x21, 0x03211030}), {} }; diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 37b70f8e878f..0abab7926dca 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1537,6 +1537,8 @@ static const struct snd_pci_quirk stac9200_fixup_tbl[] = { "Dell Inspiron 1501", STAC_9200_DELL_M26), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x01f6, "unknown Dell", STAC_9200_DELL_M26), + SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0201, + "Dell Latitude D430", STAC_9200_DELL_M22), /* Panasonic */ SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-74", STAC_9200_PANASONIC), /* Gateway machines needs EAPD to be set on resume */ diff --git a/sound/ppc/awacs.c b/sound/ppc/awacs.c index 09da7b52bc2e..1468e4b7bf93 100644 --- a/sound/ppc/awacs.c +++ b/sound/ppc/awacs.c @@ -991,6 +991,7 @@ snd_pmac_awacs_init(struct snd_pmac *chip) if (err < 0) return err; } + master_vol = NULL; if (pm7500) err = build_mixers(chip, ARRAY_SIZE(snd_pmac_awacs_mixers_pmac7500), diff --git a/sound/soc/atmel/atmel-classd.c b/sound/soc/atmel/atmel-classd.c index 8276675730ef..78a985629607 100644 --- a/sound/soc/atmel/atmel-classd.c +++ b/sound/soc/atmel/atmel-classd.c @@ -343,7 +343,7 @@ static int atmel_classd_codec_dai_digital_mute(struct snd_soc_dai *codec_dai, } #define CLASSD_ACLK_RATE_11M2896_MPY_8 (112896 * 100 * 8) -#define CLASSD_ACLK_RATE_12M288_MPY_8 (12228 * 1000 * 8) +#define CLASSD_ACLK_RATE_12M288_MPY_8 (12288 * 1000 * 8) static struct { int rate; diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index c1b87c5800b1..b3fddba4c084 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -936,7 +936,8 @@ static void nau8825_fll_apply(struct nau8825 *nau8825, NAU8825_FLL_INTEGER_MASK, fll_param->fll_int); /* FLL pre-scaler */ regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL4, - NAU8825_FLL_REF_DIV_MASK, fll_param->clk_ref_div); + NAU8825_FLL_REF_DIV_MASK, + fll_param->clk_ref_div << NAU8825_FLL_REF_DIV_SFT); /* select divided VCO input */ regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL5, NAU8825_FLL_FILTER_SW_MASK, 0x0000); diff --git a/sound/soc/codecs/nau8825.h b/sound/soc/codecs/nau8825.h index dff8edb83bfd..a0b220726a63 100644 --- a/sound/soc/codecs/nau8825.h +++ b/sound/soc/codecs/nau8825.h @@ -114,7 +114,8 @@ #define NAU8825_FLL_INTEGER_MASK (0x3ff << 0) /* FLL4 (0x07) */ -#define NAU8825_FLL_REF_DIV_MASK (0x3 << 10) +#define NAU8825_FLL_REF_DIV_SFT 10 +#define NAU8825_FLL_REF_DIV_MASK (0x3 << NAU8825_FLL_REF_DIV_SFT) /* FLL5 (0x08) */ #define NAU8825_FLL_FILTER_SW_MASK (0x1 << 14) diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index a564759845f9..5a3f544bb3a8 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -126,6 +126,16 @@ static const struct reg_default aic3x_reg[] = { { 108, 0x00 }, { 109, 0x00 }, }; +static bool aic3x_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case AIC3X_RESET: + return true; + default: + return false; + } +} + static const struct regmap_config aic3x_regmap = { .reg_bits = 8, .val_bits = 8, @@ -133,6 +143,9 @@ static const struct regmap_config aic3x_regmap = { .max_register = DAC_ICC_ADJ, .reg_defaults = aic3x_reg, .num_reg_defaults = ARRAY_SIZE(aic3x_reg), + + .volatile_reg = aic3x_volatile_reg, + .cache_type = REGCACHE_RBTREE, }; diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 7a5c9a36c1db..daba8c56b43b 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -139,7 +139,7 @@ static struct snd_soc_dai_link byt_dailink[] = { .codec_dai_name = "snd-soc-dummy-dai", .codec_name = "snd-soc-dummy", .platform_name = "sst-mfld-platform", - .ignore_suspend = 1, + .nonatomic = true, .dynamic = 1, .dpcm_playback = 1, .dpcm_capture = 1, @@ -166,6 +166,7 @@ static struct snd_soc_dai_link byt_dailink[] = { | SND_SOC_DAIFMT_CBS_CFS, .be_hw_params_fixup = byt_codec_fixup, .ignore_suspend = 1, + .nonatomic = true, .dpcm_playback = 1, .dpcm_capture = 1, .ops = &byt_be_ssp2_ops, diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index bb82bb966000..c1addf49c4f2 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -68,7 +68,8 @@ out: static int soc_compr_open_fe(struct snd_compr_stream *cstream) { struct snd_soc_pcm_runtime *fe = cstream->private_data; - struct snd_pcm_substream *fe_substream = fe->pcm->streams[0].substream; + struct snd_pcm_substream *fe_substream = + fe->pcm->streams[cstream->direction].substream; struct snd_soc_platform *platform = fe->platform; struct snd_soc_dpcm *dpcm; struct snd_soc_dapm_widget_list *list; @@ -412,7 +413,8 @@ static int soc_compr_set_params_fe(struct snd_compr_stream *cstream, struct snd_compr_params *params) { struct snd_soc_pcm_runtime *fe = cstream->private_data; - struct snd_pcm_substream *fe_substream = fe->pcm->streams[0].substream; + struct snd_pcm_substream *fe_substream = + fe->pcm->streams[cstream->direction].substream; struct snd_soc_platform *platform = fe->platform; int ret = 0, stream; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 06a91d88689a..0124eedcaaa3 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1793,6 +1793,9 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) for (i = 0; i < card->num_aux_devs; i++) soc_remove_aux_dev(card, i); + /* free the ALSA card at first; this syncs with pending operations */ + snd_card_free(card->snd_card); + /* remove and free each DAI */ soc_remove_dai_links(card); @@ -1804,9 +1807,7 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) snd_soc_dapm_free(&card->dapm); - snd_card_free(card->snd_card); return 0; - } /* removes a socdev */ diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 65b936e251ea..977066ba1769 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -181,6 +181,10 @@ int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir, dev_dbg(be->dev, "ASoC: BE %s event %d dir %d\n", be->dai_link->name, event, dir); + if ((event == SND_SOC_DAPM_STREAM_STOP) && + (be->dpcm[dir].users >= 1)) + continue; + snd_soc_dapm_stream_event(be, dir, event); } @@ -2073,9 +2077,11 @@ static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd) break; case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - case SNDRV_PCM_TRIGGER_PAUSE_PUSH: fe->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP; break; + case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PAUSED; + break; } out: diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index be1f511e4f54..ae2981460cd8 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -384,6 +384,9 @@ static void snd_complete_urb(struct urb *urb) if (unlikely(atomic_read(&ep->chip->shutdown))) goto exit_clear; + if (unlikely(!test_bit(EP_FLAG_RUNNING, &ep->flags))) + goto exit_clear; + if (usb_pipeout(ep->pipe)) { retire_outbound_urb(ep, ctx); /* can be stopped during retire callback */ diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 499b03c8281d..696de5ac69be 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -541,6 +541,8 @@ int snd_usb_mixer_vol_tlv(struct snd_kcontrol *kcontrol, int op_flag, if (size < sizeof(scale)) return -ENOMEM; + if (cval->min_mute) + scale[0] = SNDRV_CTL_TLVT_DB_MINMAX_MUTE; scale[2] = cval->dBmin; scale[3] = cval->dBmax; if (copy_to_user(_tlv, scale, sizeof(scale))) diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index 3417ef347e40..2b4b067646ab 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -64,6 +64,7 @@ struct usb_mixer_elem_info { int cached; int cache_val[MAX_CHANNELS]; u8 initialized; + u8 min_mute; void *private_data; }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 04991b009132..5d2fc5f58bfe 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -1873,6 +1873,12 @@ void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer, if (unitid == 7 && cval->control == UAC_FU_VOLUME) snd_dragonfly_quirk_db_scale(mixer, cval, kctl); break; + /* lowest playback value is muted on C-Media devices */ + case USB_ID(0x0d8c, 0x000c): + case USB_ID(0x0d8c, 0x0014): + if (strstr(kctl->id.name, "Playback")) + cval->min_mute = 1; + break; } } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 29f38e2b4ca9..1cc20d138dae 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1143,6 +1143,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ + case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */ case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */ case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */ case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ diff --git a/ti_config_fragments/android_omap.cfg b/ti_config_fragments/android_omap.cfg index 8774acf1aaf3..55ccf7851202 100644 --- a/ti_config_fragments/android_omap.cfg +++ b/ti_config_fragments/android_omap.cfg @@ -68,8 +68,6 @@ CONFIG_WLCORE=y CONFIG_WLCORE_SPI=y CONFIG_WLCORE_SDIO=y -CONFIG_VT=y - # Disable /proc/config.gz CONFIG_IKCONFIG_PROC=n diff --git a/ti_config_fragments/baseport.cfg b/ti_config_fragments/baseport.cfg index 810239d07d75..60329ab13a0e 100644 --- a/ti_config_fragments/baseport.cfg +++ b/ti_config_fragments/baseport.cfg @@ -378,6 +378,7 @@ CONFIG_TWL6040_CORE=y CONFIG_MFD_WL1273_CORE=n CONFIG_MFD_LM3533=n CONFIG_MFD_TI_LP873X=y +CONFIG_MFD_TI_LP87565=y CONFIG_MFD_TC3589X=n CONFIG_MFD_TMIO=n CONFIG_MFD_T7L66XB=n @@ -417,6 +418,7 @@ CONFIG_REGULATOR_LP3972=n CONFIG_REGULATOR_LP872X=n CONFIG_REGULATOR_LP8755=n CONFIG_REGULATOR_LP873X=y +CONFIG_REGULATOR_LP87565=y CONFIG_REGULATOR_LTC3589=n CONFIG_REGULATOR_MAX14577=n CONFIG_REGULATOR_MAX1586=n @@ -567,7 +569,6 @@ CONFIG_GPIO_XILINX=n CONFIG_GPIO_TPS6586X=n # Enable options to facilitate testing -CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=n CONFIG_CRYPTO_TEST=m CONFIG_RTC_DEBUG=y CONFIG_THERMAL_EMULATION=y diff --git a/ti_config_fragments/debug_options.cfg b/ti_config_fragments/debug_options.cfg index 3de9ba4afa1f..c48c3d61cb61 100644 --- a/ti_config_fragments/debug_options.cfg +++ b/ti_config_fragments/debug_options.cfg @@ -89,3 +89,6 @@ CONFIG_IRQ_DOMAIN_DEBUG=y # Debug HighMem CONFIG_DEBUG_HIGHMEM=y + +# Crypto self-tests +CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=n diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 0d9f48ec42bb..bc7adb84e679 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -1433,7 +1433,7 @@ int main(int argc, char *argv[]) openlog("KVP", 0, LOG_USER); syslog(LOG_INFO, "KVP starting; pid is:%d", getpid()); - kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR); + kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC); if (kvp_fd < 0) { syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s", diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index fa7208a32d76..8a679b21f0c4 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -115,4 +115,13 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define WRITE_ONCE(x, val) \ ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) + +#ifndef __fallthrough +# if defined(__GNUC__) && __GNUC__ >= 7 +# define __fallthrough __attribute__ ((fallthrough)) +# else +# define __fallthrough +# endif +#endif + #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h index 41446668ccce..d5677d39c1e4 100644 --- a/tools/include/linux/log2.h +++ b/tools/include/linux/log2.h @@ -13,12 +13,6 @@ #define _TOOLS_LINUX_LOG2_H /* - * deal with unrepresentable constant logarithms - */ -extern __attribute__((const, noreturn)) -int ____ilog2_NaN(void); - -/* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() @@ -78,7 +72,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n) < 1 ? ____ilog2_NaN() : \ + (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ @@ -141,10 +135,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - (n) & (1ULL << 1) ? 1 : \ - (n) & (1ULL << 0) ? 0 : \ - ____ilog2_NaN() \ - ) : \ + 1 ) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ diff --git a/tools/lib/lockdep/uinclude/linux/lockdep.h b/tools/lib/lockdep/uinclude/linux/lockdep.h index c808c7d02d21..e69118b2077e 100644 --- a/tools/lib/lockdep/uinclude/linux/lockdep.h +++ b/tools/lib/lockdep/uinclude/linux/lockdep.h @@ -8,7 +8,7 @@ #include <linux/utsname.h> #include <linux/compiler.h> -#define MAX_LOCK_DEPTH 2000UL +#define MAX_LOCK_DEPTH 255UL #define asmlinkage #define __visible diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c index f1ce60065258..ec30c2fcbac0 100644 --- a/tools/lib/traceevent/plugin_sched_switch.c +++ b/tools/lib/traceevent/plugin_sched_switch.c @@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s, trace_seq_printf(s, "%lld ", val); if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0) - trace_seq_printf(s, "[%lld] ", val); + trace_seq_printf(s, "[%d] ", (int) val); if (pevent_get_field_val(s, event, "prev_state", record, &val, 0) == 0) write_state(s, val); @@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s, trace_seq_printf(s, "%lld", val); if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0) - trace_seq_printf(s, " [%lld]", val); + trace_seq_printf(s, " [%d]", (int) val); return 0; } diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 74c265e0ffa0..fb1c9ddc3478 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -566,9 +566,9 @@ install-tests: all install-gtk $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' -install-bin: install-tools install-tests +install-bin: install-tools install-tests install-traceevent-plugins -install: install-bin try-install-man install-traceevent-plugins +install: install-bin try-install-man install-python_ext: $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index d28c1b6a3b54..fa5d17af88b7 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -17,7 +17,7 @@ static pid_t spawn(void) if (pid) return pid; - while(1); + while(1) sleep(5); return 0; } diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c index 9223c164e545..1f86ee8fb831 100644 --- a/tools/perf/arch/x86/util/dwarf-regs.c +++ b/tools/perf/arch/x86/util/dwarf-regs.c @@ -63,6 +63,8 @@ struct pt_regs_offset { # define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)} #endif +/* TODO: switching by dwarf address size */ +#ifndef __x86_64__ static const struct pt_regs_offset x86_32_regoffset_table[] = { REG_OFFSET_NAME_32("%ax", eax), REG_OFFSET_NAME_32("%cx", ecx), @@ -75,6 +77,8 @@ static const struct pt_regs_offset x86_32_regoffset_table[] = { REG_OFFSET_END, }; +#define regoffset_table x86_32_regoffset_table +#else static const struct pt_regs_offset x86_64_regoffset_table[] = { REG_OFFSET_NAME_64("%ax", rax), REG_OFFSET_NAME_64("%dx", rdx), @@ -95,11 +99,7 @@ static const struct pt_regs_offset x86_64_regoffset_table[] = { REG_OFFSET_END, }; -/* TODO: switching by dwarf address size */ -#ifdef __x86_64__ #define regoffset_table x86_64_regoffset_table -#else -#define regoffset_table x86_32_regoffset_table #endif /* Minus 1 for the ending REG_OFFSET_END */ diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 492df2752a2d..b4eb5b679081 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -1570,13 +1570,13 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed"); if (g->p.show_details >= 2) { - char tname[32]; + char tname[14 + 2 * 10 + 1]; struct thread_data *td; for (p = 0; p < g->p.nr_proc; p++) { for (t = 0; t < g->p.nr_threads; t++) { - memset(tname, 0, 32); + memset(tname, 0, sizeof(tname)); td = g->threads + p*g->p.nr_threads + t; - snprintf(tname, 32, "process%d:thread%d", p, t); + snprintf(tname, sizeof(tname), "process%d:thread%d", p, t); print_res(tname, td->speed_gbs, "GB/sec", "thread-speed", "GB/sec/thread speed"); print_res(tname, td->system_time_ns / 1e9, diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 368d1e1561f7..48840556bf2d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1253,21 +1253,19 @@ static int is_directory(const char *base_path, const struct dirent *dent) return S_ISDIR(st.st_mode); } -#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\ - while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) && \ - lang_next) \ - if ((lang_dirent.d_type == DT_DIR || \ - (lang_dirent.d_type == DT_UNKNOWN && \ - is_directory(scripts_path, &lang_dirent))) && \ - (strcmp(lang_dirent.d_name, ".")) && \ - (strcmp(lang_dirent.d_name, ".."))) - -#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\ - while (!readdir_r(lang_dir, &script_dirent, &script_next) && \ - script_next) \ - if (script_dirent.d_type != DT_DIR && \ - (script_dirent.d_type != DT_UNKNOWN || \ - !is_directory(lang_path, &script_dirent))) +#define for_each_lang(scripts_path, scripts_dir, lang_dirent) \ + while ((lang_dirent = readdir(scripts_dir)) != NULL) \ + if ((lang_dirent->d_type == DT_DIR || \ + (lang_dirent->d_type == DT_UNKNOWN && \ + is_directory(scripts_path, lang_dirent))) && \ + (strcmp(lang_dirent->d_name, ".")) && \ + (strcmp(lang_dirent->d_name, ".."))) + +#define for_each_script(lang_path, lang_dir, script_dirent) \ + while ((script_dirent = readdir(lang_dir)) != NULL) \ + if (script_dirent->d_type != DT_DIR && \ + (script_dirent->d_type != DT_UNKNOWN || \ + !is_directory(lang_path, script_dirent))) #define RECORD_SUFFIX "-record" @@ -1413,7 +1411,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset __maybe_unused) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; char script_path[MAXPATHLEN]; @@ -1428,19 +1426,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused, if (!scripts_dir) return -1; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - script_root = get_script_root(&script_dirent, REPORT_SUFFIX); + for_each_script(lang_path, lang_dir, script_dirent) { + script_root = get_script_root(script_dirent, REPORT_SUFFIX); if (script_root) { desc = script_desc__findnew(script_root); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); read_script_info(desc, script_path); free(script_root); } @@ -1528,7 +1526,7 @@ static int check_ev_match(char *dir_name, char *scriptname, */ int find_scripts(char **scripts_array, char **scripts_path_array) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; struct perf_session *session; @@ -1551,9 +1549,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array) return -1; } - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); #ifdef NO_LIBPERL if (strstr(lang_path, "perl")) continue; @@ -1567,16 +1565,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array) if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { + for_each_script(lang_path, lang_dir, script_dirent) { /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent.d_name, "top.")) + if (strstr(script_dirent->d_name, "top.")) continue; sprintf(scripts_path_array[i], "%s/%s", lang_path, - script_dirent.d_name); - temp = strchr(script_dirent.d_name, '.'); + script_dirent->d_name); + temp = strchr(script_dirent->d_name, '.'); snprintf(scripts_array[i], - (temp - script_dirent.d_name) + 1, - "%s", script_dirent.d_name); + (temp - script_dirent->d_name) + 1, + "%s", script_dirent->d_name); if (check_ev_match(lang_path, scripts_array[i], session)) @@ -1594,7 +1592,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array) static char *get_script_path(const char *script_root, const char *suffix) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; char script_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; @@ -1607,21 +1605,21 @@ static char *get_script_path(const char *script_root, const char *suffix) if (!scripts_dir) return NULL; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - __script_root = get_script_root(&script_dirent, suffix); + for_each_script(lang_path, lang_dir, script_dirent) { + __script_root = get_script_root(script_dirent, suffix); if (__script_root && !strcmp(script_root, __script_root)) { free(__script_root); closedir(lang_dir); closedir(scripts_dir); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); return strdup(script_path); } free(__script_root); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7e2e72e6d9d1..4a8a02c302d2 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -636,7 +636,7 @@ repeat: case -1: if (errno == EINTR) continue; - /* Fall trhu */ + __fallthrough; default: c = getc(stdin); tcsetattr(0, TCSAFLUSH, &save); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index c783d8fd3a80..ebe7115c751a 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1617,6 +1617,7 @@ static int trace__process_event(struct trace *trace, struct machine *machine, color_fprintf(trace->output, PERF_COLOR_RED, "LOST %" PRIu64 " events!\n", event->lost.lost); ret = machine__process_lost_event(machine, event, sample); + break; default: ret = machine__process_event(machine, event, sample); break; diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 636d7b42d844..54af2f2e2ee4 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1727,15 +1727,14 @@ static int test_pmu_events(void) } while (!ret && (ent = readdir(dir))) { -#define MAX_NAME 100 struct evlist_test e; - char name[MAX_NAME]; + char name[2 * NAME_MAX + 1 + 12 + 3]; if (!strcmp(ent->d_name, ".") || !strcmp(ent->d_name, "..")) continue; - snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name); + snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name); e.name = name; e.check = test__checkevent_pmu_events; @@ -1743,11 +1742,10 @@ static int test_pmu_events(void) ret = test_event(&e); if (ret) break; - snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); + snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); e.name = name; e.check = test__checkevent_pmu_events_mix; ret = test_event(&e); -#undef MAX_NAME } closedir(dir); diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index e9703c0829f1..07b5f5951b25 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -702,7 +702,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, ui_browser__gotorc(browser, row, column + 1); SLsmg_draw_hline(2); - if (row++ == 0) + if (++row == 0) goto out; } else row = 0; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index d4d7cc27252f..718bd46d47fa 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -755,11 +755,11 @@ static int annotate_browser__run(struct annotate_browser *browser, nd = browser->curr_hot; break; case K_UNTAB: - if (nd != NULL) + if (nd != NULL) { nd = rb_next(nd); if (nd == NULL) nd = rb_first(&browser->entries); - else + } else nd = browser->curr_hot; break; case K_F1: diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 956187bf1a85..26cba64345e3 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -416,7 +416,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, { char filename[PATH_MAX]; DIR *tasks; - struct dirent dirent, *next; + struct dirent *dirent; pid_t tgid, ppid; int rc = 0; @@ -445,11 +445,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, return 0; } - while (!readdir_r(tasks, &dirent, &next) && next) { + while ((dirent = readdir(tasks)) != NULL) { char *end; pid_t _pid; - _pid = strtol(dirent.d_name, &end, 10); + _pid = strtol(dirent->d_name, &end, 10); if (*end) continue; @@ -558,7 +558,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, { DIR *proc; char proc_path[PATH_MAX]; - struct dirent dirent, *next; + struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event; int err = -1; @@ -583,9 +583,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (proc == NULL) goto out_free_fork; - while (!readdir_r(proc, &dirent, &next) && next) { + while ((dirent = readdir(proc)) != NULL) { char *end; - pid_t pid = strtol(dirent.d_name, &end, 10); + pid_t pid = strtol(dirent->d_name, &end, 10); if (*end) /* only interested in proper numerical dirents */ continue; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 71df7acf8643..eeeae0629ad3 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -22,6 +22,7 @@ #include <errno.h> #include <stdint.h> #include <inttypes.h> +#include <linux/compiler.h> #include "../cache.h" #include "../util.h" @@ -63,6 +64,25 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_FUP_NO_TIP, }; +static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) +{ + switch (pkt_state) { + case INTEL_PT_STATE_NO_PSB: + case INTEL_PT_STATE_NO_IP: + case INTEL_PT_STATE_ERR_RESYNC: + case INTEL_PT_STATE_IN_SYNC: + case INTEL_PT_STATE_TNT: + return true; + case INTEL_PT_STATE_TIP: + case INTEL_PT_STATE_TIP_PGD: + case INTEL_PT_STATE_FUP: + case INTEL_PT_STATE_FUP_NO_TIP: + return false; + default: + return true; + }; +} + #ifdef INTEL_PT_STRICT #define INTEL_PT_STATE_ERR1 INTEL_PT_STATE_NO_PSB #define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_PSB @@ -90,6 +110,7 @@ struct intel_pt_decoder { bool have_tma; bool have_cyc; bool fixup_last_mtc; + bool have_last_ip; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -97,6 +118,7 @@ struct intel_pt_decoder { uint64_t timestamp; uint64_t tsc_timestamp; uint64_t ref_timestamp; + uint64_t sample_timestamp; uint64_t ret_addr; uint64_t ctc_timestamp; uint64_t ctc_delta; @@ -124,8 +146,6 @@ struct intel_pt_decoder { bool have_calc_cyc_to_tsc; int exec_mode; unsigned int insn_bytes; - uint64_t sign_bit; - uint64_t sign_bits; uint64_t period; enum intel_pt_period_type period_type; uint64_t tot_insn_cnt; @@ -139,6 +159,7 @@ struct intel_pt_decoder { unsigned int fup_tx_flags; unsigned int tx_flags; uint64_t timestamp_insn_cnt; + uint64_t sample_insn_cnt; uint64_t stuck_ip; int no_progress; int stuck_ip_prd; @@ -192,9 +213,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->data = params->data; decoder->return_compression = params->return_compression; - decoder->sign_bit = (uint64_t)1 << 47; - decoder->sign_bits = ~(((uint64_t)1 << 48) - 1); - decoder->period = params->period; decoder->period_type = params->period_type; @@ -363,21 +381,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen) return 0; } -static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, - const struct intel_pt_pkt *packet, +static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, uint64_t last_ip) { uint64_t ip; switch (packet->count) { - case 2: + case 1: ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) | packet->payload; break; - case 4: + case 2: ip = (last_ip & (uint64_t)0xffffffff00000000ULL) | packet->payload; break; + case 3: + ip = packet->payload; + /* Sign-extend 6-byte ip */ + if (ip & (uint64_t)0x800000000000ULL) + ip |= (uint64_t)0xffff000000000000ULL; + break; + case 4: + ip = (last_ip & (uint64_t)0xffff000000000000ULL) | + packet->payload; + break; case 6: ip = packet->payload; break; @@ -385,16 +412,13 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, return 0; } - if (ip & decoder->sign_bit) - return ip | decoder->sign_bits; - return ip; } static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { - decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet, - decoder->last_ip); + decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); + decoder->have_last_ip = true; } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -895,6 +919,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder, decoder->tot_insn_cnt += insn_cnt; decoder->timestamp_insn_cnt += insn_cnt; + decoder->sample_insn_cnt += insn_cnt; decoder->period_insn_cnt += insn_cnt; if (err) { @@ -1413,7 +1438,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - intel_pt_set_last_ip(decoder); + if (decoder->packet.count) + intel_pt_set_last_ip(decoder); break; case INTEL_PT_MODE_TSX: @@ -1617,6 +1643,8 @@ next: break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psbend(decoder); if (err == -EAGAIN) @@ -1695,6 +1723,13 @@ next: } } +static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) +{ + return decoder->packet.count && + (decoder->have_last_ip || decoder->packet.count == 3 || + decoder->packet.count == 6); +} + /* Walk PSB+ packets to get in sync. */ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) { @@ -1708,6 +1743,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: intel_pt_log("ERROR: Unexpected packet\n"); @@ -1715,8 +1751,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) { + if (intel_pt_have_ip(decoder)) { uint64_t current_ip = decoder->ip; intel_pt_set_ip(decoder); @@ -1762,6 +1797,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; intel_pt_clear_tx_flags(decoder); + __fallthrough; + case INTEL_PT_TNT: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); @@ -1802,27 +1839,21 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) + if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); if (decoder->ip) return 0; break; case INTEL_PT_FUP: - if (decoder->overflow) { - if (decoder->last_ip || - decoder->packet.count == 6 || - decoder->packet.count == 0) - intel_pt_set_ip(decoder); - if (decoder->ip) - return 0; - } - if (decoder->packet.count) - intel_pt_set_last_ip(decoder); + if (intel_pt_have_ip(decoder)) + intel_pt_set_ip(decoder); + if (decoder->ip) + return 0; break; case INTEL_PT_MTC: @@ -1871,6 +1902,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; + intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psb(decoder); if (err) return err; @@ -1896,6 +1930,8 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) { int err; + decoder->set_fup_tx_flags = false; + intel_pt_log("Scanning for full IP\n"); err = intel_pt_walk_to_ip(decoder); if (err) @@ -2004,6 +2040,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; + decoder->have_last_ip = false; decoder->last_ip = 0; decoder->ip = 0; intel_pt_clear_stack(&decoder->stack); @@ -2012,6 +2049,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) if (err) return err; + decoder->have_last_ip = true; decoder->pkt_state = INTEL_PT_STATE_NO_IP; err = intel_pt_walk_psb(decoder); @@ -2030,7 +2068,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) { - uint64_t est = decoder->timestamp_insn_cnt << 1; + uint64_t est = decoder->sample_insn_cnt << 1; if (!decoder->cbr || !decoder->max_non_turbo_ratio) goto out; @@ -2038,7 +2076,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) est *= decoder->max_non_turbo_ratio; est /= decoder->cbr; out: - return decoder->timestamp + est; + return decoder->sample_timestamp + est; } const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) @@ -2054,7 +2092,9 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_sync(decoder); break; case INTEL_PT_STATE_NO_IP: + decoder->have_last_ip = false; decoder->last_ip = 0; + decoder->ip = 0; /* Fall through */ case INTEL_PT_STATE_ERR_RESYNC: err = intel_pt_sync_ip(decoder); @@ -2091,15 +2131,24 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) } } while (err == -ENOLINK); - decoder->state.err = err ? intel_pt_ext_err(err) : 0; - decoder->state.timestamp = decoder->timestamp; + if (err) { + decoder->state.err = intel_pt_ext_err(err); + decoder->state.from_ip = decoder->ip; + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } else { + decoder->state.err = 0; + if (intel_pt_sample_time(decoder->pkt_state)) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } + } + + decoder->state.timestamp = decoder->sample_timestamp; decoder->state.est_timestamp = intel_pt_est_timestamp(decoder); decoder->state.cr3 = decoder->cr3; decoder->state.tot_insn_cnt = decoder->tot_insn_cnt; - if (err) - decoder->state.from_ip = decoder->ip; - return &decoder->state; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index b1257c816310..7528ae4f7e28 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -17,6 +17,7 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/compiler.h> #include "intel-pt-pkt-decoder.h" @@ -292,36 +293,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte, const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { - switch (byte >> 5) { + int ip_len; + + packet->count = byte >> 5; + + switch (packet->count) { case 0: - packet->count = 0; + ip_len = 0; break; case 1: if (len < 3) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 2; + ip_len = 2; packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1)); break; case 2: if (len < 5) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 4; + ip_len = 4; packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1)); break; case 3: - case 6: + case 4: if (len < 7) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 6; + ip_len = 6; memcpy_le64(&packet->payload, buf + 1, 6); break; + case 6: + if (len < 9) + return INTEL_PT_NEED_MORE_BYTES; + ip_len = 8; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1)); + break; default: return INTEL_PT_BAD_PACKET; } packet->type = type; - return packet->count + 1; + return ip_len + 1; } static int intel_pt_get_mode(const unsigned char *buf, size_t len, @@ -488,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, case INTEL_PT_FUP: if (!(packet->count)) return snprintf(buf, buf_len, "%s no ip", name); + __fallthrough; case INTEL_PT_CYC: case INTEL_PT_VMCS: case INTEL_PT_MTC: diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 854dd2105bd5..881bbb5e7912 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -138,11 +138,11 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { #define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) -#define for_each_subsystem(sys_dir, sys_dirent, sys_next) \ - while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next) \ - if (sys_dirent.d_type == DT_DIR && \ - (strcmp(sys_dirent.d_name, ".")) && \ - (strcmp(sys_dirent.d_name, ".."))) +#define for_each_subsystem(sys_dir, sys_dirent) \ + while ((sys_dirent = readdir(sys_dir)) != NULL) \ + if (sys_dirent->d_type == DT_DIR && \ + (strcmp(sys_dirent->d_name, ".")) && \ + (strcmp(sys_dirent->d_name, ".."))) static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) { @@ -159,12 +159,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) return 0; } -#define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) \ - while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next) \ - if (evt_dirent.d_type == DT_DIR && \ - (strcmp(evt_dirent.d_name, ".")) && \ - (strcmp(evt_dirent.d_name, "..")) && \ - (!tp_event_has_id(&sys_dirent, &evt_dirent))) +#define for_each_event(sys_dirent, evt_dir, evt_dirent) \ + while ((evt_dirent = readdir(evt_dir)) != NULL) \ + if (evt_dirent->d_type == DT_DIR && \ + (strcmp(evt_dirent->d_name, ".")) && \ + (strcmp(evt_dirent->d_name, "..")) && \ + (!tp_event_has_id(sys_dirent, evt_dirent))) #define MAX_EVENT_LENGTH 512 @@ -173,7 +173,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) { struct tracepoint_path *path = NULL; DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char id_buf[24]; int fd; u64 id; @@ -184,18 +184,18 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) if (!sys_dir) return NULL; - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, - evt_dirent.d_name); + evt_dirent->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) continue; @@ -220,9 +220,9 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) free(path); return NULL; } - strncpy(path->system, sys_dirent.d_name, + strncpy(path->system, sys_dirent->d_name, MAX_EVENT_LENGTH); - strncpy(path->name, evt_dirent.d_name, + strncpy(path->name, evt_dirent->d_name, MAX_EVENT_LENGTH); return path; } @@ -1662,7 +1662,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only) { DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; char **evt_list = NULL; @@ -1680,20 +1680,20 @@ restart: goto out_close_sys_dir; } - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { if (subsys_glob != NULL && - !strglobmatch(sys_dirent.d_name, subsys_glob)) + !strglobmatch(sys_dirent->d_name, subsys_glob)) continue; snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { if (event_glob != NULL && - !strglobmatch(evt_dirent.d_name, event_glob)) + !strglobmatch(evt_dirent->d_name, event_glob)) continue; if (!evt_num_known) { @@ -1702,7 +1702,7 @@ restart: } snprintf(evt_path, MAXPATHLEN, "%s:%s", - sys_dirent.d_name, evt_dirent.d_name); + sys_dirent->d_name, evt_dirent->d_name); evt_list[evt_i] = strdup(evt_path); if (evt_list[evt_i] == NULL) @@ -1755,7 +1755,7 @@ out_close_sys_dir: int is_valid_tracepoint(const char *event_string) { DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; @@ -1763,17 +1763,17 @@ int is_valid_tracepoint(const char *event_string) if (!sys_dir) return 0; - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s:%s", - sys_dirent.d_name, evt_dirent.d_name); + sys_dirent->d_name, evt_dirent->d_name); if (!strcmp(evt_path, event_string)) { closedir(evt_dir); closedir(sys_dir); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 6f2a0279476c..593066c68e3d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -153,7 +153,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n if (fd == -1) return -1; - sret = read(fd, alias->unit, UNIT_MAX_LEN); + sret = read(fd, alias->unit, UNIT_MAX_LEN); if (sret < 0) goto error; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 05012bb178d7..fdd87c7e3e91 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1460,16 +1460,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, Dwarf_Addr _addr = 0, baseaddr = 0; const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; - bool reloc = false; -retry: + /* We always need to relocate the address for aranges */ + if (debuginfo__get_text_offset(dbg, &baseaddr) == 0) + addr += baseaddr; /* Find cu die */ if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { - if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) { - addr += baseaddr; - reloc = true; - goto retry; - } pr_warning("Failed to find debug information for address %lx\n", addr); ret = -EINVAL; diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index 6516e220c247..82d28c67e0f3 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -1,6 +1,6 @@ libperf-$(CONFIG_LIBPERL) += trace-event-perl.o libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o -CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default +CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index bcae659b6546..efb53772e0ec 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -269,6 +269,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf) len = strfilter_node__sprint_pt(node->l, buf); if (len < 0) return len; + __fallthrough; case '!': if (buf) { *(buf + len++) = *node->p; diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index fc8781de62db..accb7ece1d3c 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -21,6 +21,8 @@ s64 perf_atoll(const char *str) case 'b': case 'B': if (*p) goto out_err; + + __fallthrough; case '\0': return length; default: diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 27ae382feb2d..7c97ecaeae48 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -488,6 +488,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) break; } else { int n = namesz + descsz; + + if (n > (int)sizeof(bf)) { + n = sizeof(bf); + pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n", + __func__, filename, nhdr.n_namesz, nhdr.n_descsz); + } if (read(fd, bf, n) != n) break; } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0a9ae8014729..829508a21448 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -227,7 +227,7 @@ void thread__find_cpumode_addr_location(struct thread *thread, struct addr_location *al) { size_t i; - const u8 const cpumodes[] = { + const u8 cpumodes[] = { PERF_RECORD_MISC_USER, PERF_RECORD_MISC_KERNEL, PERF_RECORD_MISC_GUEST_USER, diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 6ec3c5ca438f..4e666b95b87e 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -92,8 +92,8 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) { DIR *proc; int max_threads = 32, items, i; - char path[256]; - struct dirent dirent, *next, **namelist = NULL; + char path[NAME_MAX + 1 + 6]; + struct dirent *dirent, **namelist = NULL; struct thread_map *threads = thread_map__alloc(max_threads); if (threads == NULL) @@ -106,16 +106,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) threads->nr = 0; atomic_set(&threads->refcnt, 1); - while (!readdir_r(proc, &dirent, &next) && next) { + while ((dirent = readdir(proc)) != NULL) { char *end; bool grow = false; struct stat st; - pid_t pid = strtol(dirent.d_name, &end, 10); + pid_t pid = strtol(dirent->d_name, &end, 10); if (*end) /* only interested in proper numerical dirents */ continue; - snprintf(path, sizeof(path), "/proc/%s", dirent.d_name); + snprintf(path, sizeof(path), "/proc/%s", dirent->d_name); if (stat(path, &st) != 0) continue; diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 93b0aa74ca03..39c2c7d067bb 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -156,6 +156,7 @@ out: */ case 0x2C: /* Westmere EP - Gulftown */ cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO; + break; case 0x2A: /* SNB */ case 0x2D: /* SNB Xeon */ case 0x3A: /* IVB */ diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index d08e214ec6e7..223d88e25e05 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -2629,7 +2629,7 @@ sub do_run_test { } waitpid $child_pid, 0; - $child_exit = $?; + $child_exit = $? >> 8; my $end_time = time; $test_time = $end_time - $start_time; diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c index 10a21a958aaf..763f37fecfb8 100644 --- a/tools/testing/selftests/capabilities/test_execve.c +++ b/tools/testing/selftests/capabilities/test_execve.c @@ -138,9 +138,6 @@ static void chdir_to_tmpfs(void) if (chdir(cwd) != 0) err(1, "chdir to private tmpfs"); - - if (umount2(".", MNT_DETACH) != 0) - err(1, "detach private tmpfs"); } static void copy_fromat_to(int fromfd, const char *fromname, const char *toname) @@ -248,7 +245,7 @@ static int do_tests(int uid, const char *our_path) err(1, "chown"); if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0) err(1, "chmod"); -} + } capng_get_caps_process(); @@ -384,7 +381,7 @@ static int do_tests(int uid, const char *our_path) } else { printf("[RUN]\tNon-root +ia, sgidnonroot => i\n"); exec_other_validate_cap("./validate_cap_sgidnonroot", - false, false, true, false); + false, false, true, false); if (fork_wait()) { printf("[RUN]\tNon-root +ia, sgidroot => i\n"); diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 31a3035cd4eb..923e59eb82c7 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -394,6 +394,51 @@ static void *threadproc(void *ctx) } } +#ifdef __i386__ + +#ifndef SA_RESTORE +#define SA_RESTORER 0x04000000 +#endif + +/* + * The UAPI header calls this 'struct sigaction', which conflicts with + * glibc. Sigh. + */ +struct fake_ksigaction { + void *handler; /* the real type is nasty */ + unsigned long sa_flags; + void (*sa_restorer)(void); + unsigned char sigset[8]; +}; + +static void fix_sa_restorer(int sig) +{ + struct fake_ksigaction ksa; + + if (syscall(SYS_rt_sigaction, sig, NULL, &ksa, 8) == 0) { + /* + * glibc has a nasty bug: it sometimes writes garbage to + * sa_restorer. This interacts quite badly with anything + * that fiddles with SS because it can trigger legacy + * stack switching. Patch it up. See: + * + * https://sourceware.org/bugzilla/show_bug.cgi?id=21269 + */ + if (!(ksa.sa_flags & SA_RESTORER) && ksa.sa_restorer) { + ksa.sa_restorer = NULL; + if (syscall(SYS_rt_sigaction, sig, &ksa, NULL, + sizeof(ksa.sigset)) != 0) + err(1, "rt_sigaction"); + } + } +} +#else +static void fix_sa_restorer(int sig) +{ + /* 64-bit glibc works fine. */ +} +#endif + static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags) { @@ -405,6 +450,7 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), if (sigaction(sig, &sa, 0)) err(1, "sigaction"); + fix_sa_restorer(sig); } static jmp_buf jmpbuf; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 46dbc0a7dfc1..49001fa84ead 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -868,7 +868,8 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx, continue; kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); - kvm->buses[bus_idx]->ioeventfd_count--; + if (kvm->buses[bus_idx]) + kvm->buses[bus_idx]->ioeventfd_count--; ioeventfd_release(p); ret = 0; break; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 336ed267c407..cb092bd9965b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -654,8 +654,11 @@ static void kvm_destroy_vm(struct kvm *kvm) list_del(&kvm->vm_list); spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); - for (i = 0; i < KVM_NR_BUSES; i++) - kvm_io_bus_destroy(kvm->buses[i]); + for (i = 0; i < KVM_NR_BUSES; i++) { + if (kvm->buses[i]) + kvm_io_bus_destroy(kvm->buses[i]); + kvm->buses[i] = NULL; + } kvm_coalesced_mmio_free(kvm); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); @@ -3271,6 +3274,8 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + if (!bus) + return -ENOMEM; r = __kvm_io_bus_write(vcpu, bus, &range, val); return r < 0 ? r : 0; } @@ -3288,6 +3293,8 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + if (!bus) + return -ENOMEM; /* First try the device referenced by cookie. */ if ((cookie >= 0) && (cookie < bus->dev_count) && @@ -3338,6 +3345,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); + if (!bus) + return -ENOMEM; r = __kvm_io_bus_read(vcpu, bus, &range, val); return r < 0 ? r : 0; } @@ -3350,6 +3359,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, struct kvm_io_bus *new_bus, *bus; bus = kvm->buses[bus_idx]; + if (!bus) + return -ENOMEM; + /* exclude ioeventfd which is limited by maximum fd */ if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; @@ -3369,37 +3381,41 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, } /* Caller must hold slots_lock. */ -int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev) +void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev) { - int i, r; + int i; struct kvm_io_bus *new_bus, *bus; bus = kvm->buses[bus_idx]; - r = -ENOENT; + if (!bus) + return; + for (i = 0; i < bus->dev_count; i++) if (bus->range[i].dev == dev) { - r = 0; break; } - if (r) - return r; + if (i == bus->dev_count) + return; new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) * sizeof(struct kvm_io_range)), GFP_KERNEL); - if (!new_bus) - return -ENOMEM; + if (!new_bus) { + pr_err("kvm: failed to shrink bus, removing it completely\n"); + goto broken; + } memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); new_bus->dev_count--; memcpy(new_bus->range + i, bus->range + i + 1, (new_bus->dev_count - i) * sizeof(struct kvm_io_range)); +broken: rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); - return r; + return; } static struct notifier_block kvm_cpu_notifier = { diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 1dd087da6f31..111e09c3f4bf 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -47,6 +47,22 @@ static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep) return vfio_group; } +static bool kvm_vfio_external_group_match_file(struct vfio_group *group, + struct file *filep) +{ + bool ret, (*fn)(struct vfio_group *, struct file *); + + fn = symbol_get(vfio_external_group_match_file); + if (!fn) + return false; + + ret = fn(group, filep); + + symbol_put(vfio_external_group_match_file); + + return ret; +} + static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group) { void (*fn)(struct vfio_group *); @@ -171,18 +187,13 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) if (!f.file) return -EBADF; - vfio_group = kvm_vfio_group_get_external_user(f.file); - fdput(f); - - if (IS_ERR(vfio_group)) - return PTR_ERR(vfio_group); - ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvg, &kv->group_list, node) { - if (kvg->vfio_group != vfio_group) + if (!kvm_vfio_external_group_match_file(kvg->vfio_group, + f.file)) continue; list_del(&kvg->node); @@ -196,7 +207,7 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) mutex_unlock(&kv->lock); - kvm_vfio_group_put_external_user(vfio_group); + fdput(f); kvm_vfio_update_coherency(dev); |