diff options
1802 files changed, 22877 insertions, 10261 deletions
diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy index f1c5cc9d17a8..4c3efe434806 100644 --- a/Documentation/ABI/testing/ima_policy +++ b/Documentation/ABI/testing/ima_policy @@ -23,7 +23,7 @@ Description: [fowner]] lsm: [[subj_user=] [subj_role=] [subj_type=] [obj_user=] [obj_role=] [obj_type=]] - option: [[appraise_type=]] + option: [[appraise_type=]] [permit_directio] base: func:= [BPRM_CHECK][MMAP_CHECK][FILE_CHECK][MODULE_CHECK] mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC] diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile index f9fd615427fb..1d27f0a1abd1 100644 --- a/Documentation/DocBook/media/Makefile +++ b/Documentation/DocBook/media/Makefile @@ -195,7 +195,7 @@ DVB_DOCUMENTED = \ # install_media_images = \ - $(Q)cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api + $(Q)-cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64 $(Q)base64 -d $< >$@ diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 26b1e31d5a13..1ec219a14904 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -119,6 +119,20 @@ Example: platform_set_drvdata(), but left the variable "dev" unused, delete it. +If your patch fixes a bug in a specific commit, e.g. you found an issue using +git-bisect, please use the 'Fixes:' tag with the first 12 characters of the +SHA-1 ID, and the one line summary. +Example: + + Fixes: e21d2170f366 ("video: remove unnecessary platform_set_drvdata()") + +The following git-config settings can be used to add a pretty format for +outputting the above style in the git log or git show commands + + [core] + abbrev = 12 + [pretty] + fixes = Fixes: %h (\"%s\") 3) Separate your changes. @@ -430,7 +444,7 @@ person it names. This tag documents that potentially interested parties have been included in the discussion -14) Using Reported-by:, Tested-by:, Reviewed-by: and Suggested-by: +14) Using Reported-by:, Tested-by:, Reviewed-by:, Suggested-by: and Fixes: If this patch fixes a problem reported by somebody else, consider adding a Reported-by: tag to credit the reporter for their contribution. Please @@ -485,6 +499,12 @@ idea was not posted in a public forum. That said, if we diligently credit our idea reporters, they will, hopefully, be inspired to help us again in the future. +A Fixes: tag indicates that the patch fixes an issue in a previous commit. It +is used to make it easy to determine where a bug originated, which can help +review a bug fix. This tag also assists the stable kernel team in determining +which stable kernel versions should receive your fix. This is the preferred +method for indicating a bug fixed by the patch. See #2 above for more details. + 15) The canonical patch format diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt index e742d21dbd96..a69ffe1d54d5 100644 --- a/Documentation/cpu-freq/intel-pstate.txt +++ b/Documentation/cpu-freq/intel-pstate.txt @@ -15,10 +15,13 @@ New sysfs files for controlling P state selection have been added to /sys/devices/system/cpu/intel_pstate/ max_perf_pct: limits the maximum P state that will be requested by - the driver stated as a percentage of the available performance. + the driver stated as a percentage of the available performance. The + available (P states) performance may be reduced by the no_turbo + setting described below. min_perf_pct: limits the minimum P state that will be requested by - the driver stated as a percentage of the available performance. + the driver stated as a percentage of the max (non-turbo) + performance level. no_turbo: limits the driver to selecting P states below the turbo frequency range. diff --git a/Documentation/debugging-via-ohci1394.txt b/Documentation/debugging-via-ohci1394.txt index fa0151a712f9..5c9a567b3fac 100644 --- a/Documentation/debugging-via-ohci1394.txt +++ b/Documentation/debugging-via-ohci1394.txt @@ -25,9 +25,11 @@ using data transfer rates in the order of 10MB/s or more. With most FireWire controllers, memory access is limited to the low 4 GB of physical address space. This can be a problem on IA64 machines where memory is located mostly above that limit, but it is rarely a problem on -more common hardware such as x86, x86-64 and PowerPC. However, at least -Agere/LSI FW643e and FW643e2 controllers are known to support access to -physical addresses above 4 GB. +more common hardware such as x86, x86-64 and PowerPC. + +At least LSI FW643e and FW643e2 controllers are known to support access to +physical addresses above 4 GB, but this feature is currently not enabled by +Linux. Together with a early initialization of the OHCI-1394 controller for debugging, this facility proved most useful for examining long debugs logs in the printk @@ -101,8 +103,9 @@ Step-by-step instructions for using firescope with early OHCI initialization: compliant, they are based on TI PCILynx chips and require drivers for Win- dows operating systems. - The mentioned kernel log message contains ">4 GB phys DMA" in case of - OHCI-1394 controllers which support accesses above this limit. + The mentioned kernel log message contains the string "physUB" if the + controller implements a writable Physical Upper Bound register. This is + required for physical DMA above 4 GB (but not utilized by Linux yet). 2) Establish a working FireWire cable connection: diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt index 05a27e9442bd..2f5173500bd9 100644 --- a/Documentation/device-mapper/thin-provisioning.txt +++ b/Documentation/device-mapper/thin-provisioning.txt @@ -309,7 +309,10 @@ ii) Status error_if_no_space|queue_if_no_space If the pool runs out of data or metadata space, the pool will either queue or error the IO destined to the data device. The - default is to queue the IO until more space is added. + default is to queue the IO until more space is added or the + 'no_space_timeout' expires. The 'no_space_timeout' dm-thin-pool + module parameter can be used to change this timeout -- it + defaults to 60 seconds but may be disabled using a value of 0. iii) Messages diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt index 9fbbdb783a72..68ff2137bae7 100644 --- a/Documentation/devicetree/bindings/dma/ti-edma.txt +++ b/Documentation/devicetree/bindings/dma/ti-edma.txt @@ -29,6 +29,6 @@ edma: edma@49000000 { dma-channels = <64>; ti,edma-regions = <4>; ti,edma-slots = <256>; - ti,edma-xbar-event-map = <1 12 - 2 13>; + ti,edma-xbar-event-map = /bits/ 16 <1 12 + 2 13>; }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt index 1486497a24c1..ce6a1a072028 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt @@ -4,11 +4,13 @@ Specifying interrupt information for devices 1) Interrupt client nodes ------------------------- -Nodes that describe devices which generate interrupts must contain an either an -"interrupts" property or an "interrupts-extended" property. These properties -contain a list of interrupt specifiers, one per output interrupt. The format of -the interrupt specifier is determined by the interrupt controller to which the -interrupts are routed; see section 2 below for details. +Nodes that describe devices which generate interrupts must contain an +"interrupts" property, an "interrupts-extended" property, or both. If both are +present, the latter should take precedence; the former may be provided simply +for compatibility with software that does not recognize the latter. These +properties contain a list of interrupt specifiers, one per output interrupt. The +format of the interrupt specifier is determined by the interrupt controller to +which the interrupts are routed; see section 2 below for details. Example: interrupt-parent = <&intc1>; diff --git a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt index 46f344965313..4eb7997674a0 100644 --- a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt +++ b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt @@ -1,7 +1,7 @@ ADI AXI-SPDIF controller Required properties: - - compatible : Must be "adi,axi-spdif-1.00.a" + - compatible : Must be "adi,axi-spdif-tx-1.00.a" - reg : Must contain SPDIF core's registers location and length - clocks : Pairs of phandle and specifier referencing the controller's clocks. The controller expects two clocks, the clock used for the AXI interface and diff --git a/Documentation/devicetree/bindings/spi/efm32-spi.txt b/Documentation/devicetree/bindings/spi/efm32-spi.txt index a590ca51be75..f762e11bfe11 100644 --- a/Documentation/devicetree/bindings/spi/efm32-spi.txt +++ b/Documentation/devicetree/bindings/spi/efm32-spi.txt @@ -3,7 +3,7 @@ Required properties: - #address-cells: see spi-bus.txt - #size-cells: see spi-bus.txt -- compatible: should be "efm32,spi" +- compatible: should be "energymicro,efm32-spi" - reg: Offset and length of the register set for the controller - interrupts: pair specifying rx and tx irq - clocks: phandle to the spi clock @@ -15,7 +15,7 @@ Example: spi1: spi@0x4000c400 { /* USART1 */ #address-cells = <1>; #size-cells = <0>; - compatible = "efm32,spi"; + compatible = "energymicro,efm32-spi"; reg = <0x4000c400 0x400>; interrupts = <15 16>; clocks = <&cmu 20>; diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801 index aaaf069306a3..adf5e33e8312 100644 --- a/Documentation/i2c/busses/i2c-i801 +++ b/Documentation/i2c/busses/i2c-i801 @@ -26,6 +26,7 @@ Supported adapters: * Intel Wellsburg (PCH) * Intel Coleto Creek (PCH) * Intel Wildcat Point-LP (PCH) + * Intel BayTrail (SOC) Datasheets: Publicly available at the Intel website On Intel Patsburg and later chipsets, both the normal host SMBus controller diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt index 5602eb71ad5d..e1ae127ed099 100644 --- a/Documentation/input/elantech.txt +++ b/Documentation/input/elantech.txt @@ -504,9 +504,12 @@ byte 5: * reg_10 bit 7 6 5 4 3 2 1 0 - 0 0 0 0 0 0 0 A + 0 0 0 0 R F T A A: 1 = enable absolute tracking + T: 1 = enable two finger mode auto correct + F: 1 = disable ABS Position Filter + R: 1 = enable real hardware resolution 6.2 Native absolute mode 6 byte packet format ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO index 0091a8215ac1..b61885c35ce1 100644 --- a/Documentation/ja_JP/HOWTO +++ b/Documentation/ja_JP/HOWTO @@ -315,7 +315,7 @@ Andrew Morton ㌠Linux-kernel メーリングリストã«ã‚«ãƒ¼ãƒãƒ«ãƒªãƒªãƒ¼ã ã‚‚ã—ã€3.x.y カーãƒãƒ«ãŒå˜åœ¨ã—ãªã„å ´åˆã«ã¯ã€ç•ªå·ãŒä¸€ç•ªå¤§ãã„ 3.x ㌠最新ã®å®‰å®šç‰ˆã‚«ãƒ¼ãƒãƒ«ã§ã™ã€‚ -3.x.y 㯠"stable" ãƒãƒ¼ãƒ <stable@kernel.org> ã§ãƒ¡ãƒ³ãƒ†ã•ã‚Œã¦ãŠã‚Šã€å¿… +3.x.y 㯠"stable" ãƒãƒ¼ãƒ <stable@vger.kernel.org> ã§ãƒ¡ãƒ³ãƒ†ã•ã‚Œã¦ãŠã‚Šã€å¿… è¦ã«å¿œã˜ã¦ãƒªãƒªãƒ¼ã‚¹ã•ã‚Œã¾ã™ã€‚通常ã®ãƒªãƒªãƒ¼ã‚¹æœŸé–“㯠2週間毎ã§ã™ãŒã€å·®ã—迫㣠ãŸå•é¡ŒãŒãªã‘ã‚Œã°ã‚‚ã†å°‘ã—é•·ããªã‚‹ã“ã¨ã‚‚ã‚ã‚Šã¾ã™ã€‚ã‚»ã‚ュリティ関連ã®å•é¡Œ ã®å ´åˆã¯ã“ã‚Œã«å¯¾ã—ã¦ã ã„ãŸã„ã®å ´åˆã€ã™ãã«ãƒªãƒªãƒ¼ã‚¹ãŒã•ã‚Œã¾ã™ã€‚ diff --git a/Documentation/ja_JP/stable_kernel_rules.txt b/Documentation/ja_JP/stable_kernel_rules.txt index 14265837c4ce..9dbda9b5d21e 100644 --- a/Documentation/ja_JP/stable_kernel_rules.txt +++ b/Documentation/ja_JP/stable_kernel_rules.txt @@ -50,16 +50,16 @@ linux-2.6.29/Documentation/stable_kernel_rules.txt -stable ツリーã«ãƒ‘ッãƒã‚’é€ä»˜ã™ã‚‹æ‰‹ç¶šã- - - 上記ã®è¦å‰‡ã«å¾“ã£ã¦ã„ã‚‹ã‹ã‚’確èªã—ãŸå¾Œã«ã€stable@kernel.org ã«ãƒ‘ッム+ - 上記ã®è¦å‰‡ã«å¾“ã£ã¦ã„ã‚‹ã‹ã‚’確èªã—ãŸå¾Œã«ã€stable@vger.kernel.org ã«ãƒ‘ッムをé€ã‚‹ã€‚ - é€ä¿¡è€…ã¯ãƒ‘ッãƒãŒã‚ューã«å—ã‘付ã‘られãŸéš›ã«ã¯ ACK ã‚’ã€å´ä¸‹ã•ã‚ŒãŸå ´åˆ ã«ã¯ NAK ã‚’å—ã‘å–る。ã“ã®åå¿œã¯é–‹ç™ºè€…ãŸã¡ã®ã‚¹ã‚±ã‚¸ãƒ¥ãƒ¼ãƒ«ã«ã‚ˆã£ã¦ã€æ•° æ—¥ã‹ã‹ã‚‹å ´åˆãŒã‚る。 - ã‚‚ã—å—ã‘å–られãŸã‚‰ã€ãƒ‘ッãƒã¯ä»–ã®é–‹ç™ºè€…ãŸã¡ã¨é–¢é€£ã™ã‚‹ã‚µãƒ–システム㮠メンテナーã«ã‚ˆã‚‹ãƒ¬ãƒ“ューã®ãŸã‚ã« -stable ã‚ューã«è¿½åŠ ã•ã‚Œã‚‹ã€‚ - - パッãƒã« stable@kernel.org ã®ã‚¢ãƒ‰ãƒ¬ã‚¹ãŒä»˜åŠ ã•ã‚Œã¦ã„ã‚‹ã¨ãã«ã¯ã€ãã‚Œ + - パッãƒã« stable@vger.kernel.org ã®ã‚¢ãƒ‰ãƒ¬ã‚¹ãŒä»˜åŠ ã•ã‚Œã¦ã„ã‚‹ã¨ãã«ã¯ã€ãã‚Œ ㌠Linus ã®ãƒ„リーã«å…¥ã‚‹æ™‚ã«è‡ªå‹•çš„ã« stable ãƒãƒ¼ãƒ ã« email ã•ã‚Œã‚‹ã€‚ - - ã‚»ã‚ュリティパッãƒã¯ã“ã®ã‚¨ã‚¤ãƒªã‚¢ã‚¹ (stable@kernel.org) ã«é€ã‚‰ã‚Œã‚‹ã¹ + - ã‚»ã‚ュリティパッãƒã¯ã“ã®ã‚¨ã‚¤ãƒªã‚¢ã‚¹ (stable@vger.kernel.org) ã«é€ã‚‰ã‚Œã‚‹ã¹ ãã§ã¯ãªãã€ä»£ã‚ã‚Šã« security@kernel.org ã®ã‚¢ãƒ‰ãƒ¬ã‚¹ã«é€ã‚‰ã‚Œã‚‹ã€‚ レビューサイクル- diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt new file mode 100644 index 000000000000..ea45dd3901e3 --- /dev/null +++ b/Documentation/lzo.txt @@ -0,0 +1,164 @@ + +LZO stream format as understood by Linux's LZO decompressor +=========================================================== + +Introduction + + This is not a specification. No specification seems to be publicly available + for the LZO stream format. This document describes what input format the LZO + decompressor as implemented in the Linux kernel understands. The file subject + of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on + the compressor nor on any other implementations though it seems likely that + the format matches the standard one. The purpose of this document is to + better understand what the code does in order to propose more efficient fixes + for future bug reports. + +Description + + The stream is composed of a series of instructions, operands, and data. The + instructions consist in a few bits representing an opcode, and bits forming + the operands for the instruction, whose size and position depend on the + opcode and on the number of literals copied by previous instruction. The + operands are used to indicate : + + - a distance when copying data from the dictionary (past output buffer) + - a length (number of bytes to copy from dictionary) + - the number of literals to copy, which is retained in variable "state" + as a piece of information for next instructions. + + Optionally depending on the opcode and operands, extra data may follow. These + extra data can be a complement for the operand (eg: a length or a distance + encoded on larger values), or a literal to be copied to the output buffer. + + The first byte of the block follows a different encoding from other bytes, it + seems to be optimized for literal use only, since there is no dictionary yet + prior to that byte. + + Lengths are always encoded on a variable size starting with a small number + of bits in the operand. If the number of bits isn't enough to represent the + length, up to 255 may be added in increments by consuming more bytes with a + rate of at most 255 per extra byte (thus the compression ratio cannot exceed + around 255:1). The variable length encoding using #bits is always the same : + + length = byte & ((1 << #bits) - 1) + if (!length) { + length = ((1 << #bits) - 1) + length += 255*(number of zero bytes) + length += first-non-zero-byte + } + length += constant (generally 2 or 3) + + For references to the dictionary, distances are relative to the output + pointer. Distances are encoded using very few bits belonging to certain + ranges, resulting in multiple copy instructions using different encodings. + Certain encodings involve one extra byte, others involve two extra bytes + forming a little-endian 16-bit quantity (marked LE16 below). + + After any instruction except the large literal copy, 0, 1, 2 or 3 literals + are copied before starting the next instruction. The number of literals that + were copied may change the meaning and behaviour of the next instruction. In + practice, only one instruction needs to know whether 0, less than 4, or more + literals were copied. This is the information stored in the <state> variable + in this implementation. This number of immediate literals to be copied is + generally encoded in the last two bits of the instruction but may also be + taken from the last two bits of an extra operand (eg: distance). + + End of stream is declared when a block copy of distance 0 is seen. Only one + instruction may encode this distance (0001HLLL), it takes one LE16 operand + for the distance, thus requiring 3 bytes. + + IMPORTANT NOTE : in the code some length checks are missing because certain + instructions are called under the assumption that a certain number of bytes + follow because it has already been garanteed before parsing the instructions. + They just have to "refill" this credit if they consume extra bytes. This is + an implementation design choice independant on the algorithm or encoding. + +Byte sequences + + First byte encoding : + + 0..17 : follow regular instruction encoding, see below. It is worth + noting that codes 16 and 17 will represent a block copy from + the dictionary which is empty, and that they will always be + invalid at this place. + + 18..21 : copy 0..3 literals + state = (byte - 17) = 0..3 [ copy <state> literals ] + skip byte + + 22..255 : copy literal string + length = (byte - 17) = 4..238 + state = 4 [ don't copy extra literals ] + skip byte + + Instruction encoding : + + 0 0 0 0 X X X X (0..15) + Depends on the number of literals copied by the last instruction. + If last instruction did not copy any literal (state == 0), this + encoding will be a copy of 4 or more literal, and must be interpreted + like this : + + 0 0 0 0 L L L L (0..15) : copy long literal string + length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte) + state = 4 (no extra literals are copied) + + If last instruction used to copy between 1 to 3 literals (encoded in + the instruction's opcode or distance), the instruction is a copy of a + 2-byte block from the dictionary within a 1kB distance. It is worth + noting that this instruction provides little savings since it uses 2 + bytes to encode a copy of 2 other bytes but it encodes the number of + following literals for free. It must be interpreted like this : + + 0 0 0 0 D D S S (0..15) : copy 2 bytes from <= 1kB distance + length = 2 + state = S (copy S literals after this block) + Always followed by exactly one byte : H H H H H H H H + distance = (H << 2) + D + 1 + + If last instruction used to copy 4 or more literals (as detected by + state == 4), the instruction becomes a copy of a 3-byte block from the + dictionary from a 2..3kB distance, and must be interpreted like this : + + 0 0 0 0 D D S S (0..15) : copy 3 bytes from 2..3 kB distance + length = 3 + state = S (copy S literals after this block) + Always followed by exactly one byte : H H H H H H H H + distance = (H << 2) + D + 2049 + + 0 0 0 1 H L L L (16..31) + Copy of a block within 16..48kB distance (preferably less than 10B) + length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte) + Always followed by exactly one LE16 : D D D D D D D D : D D D D D D S S + distance = 16384 + (H << 14) + D + state = S (copy S literals after this block) + End of stream is reached if distance == 16384 + + 0 0 1 L L L L L (32..63) + Copy of small block within 16kB distance (preferably less than 34B) + length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte) + Always followed by exactly one LE16 : D D D D D D D D : D D D D D D S S + distance = D + 1 + state = S (copy S literals after this block) + + 0 1 L D D D S S (64..127) + Copy 3-4 bytes from block within 2kB distance + state = S (copy S literals after this block) + length = 3 + L + Always followed by exactly one byte : H H H H H H H H + distance = (H << 3) + D + 1 + + 1 L L D D D S S (128..255) + Copy 5-8 bytes from block within 2kB distance + state = S (copy S literals after this block) + length = 5 + L + Always followed by exactly one byte : H H H H H H H H + distance = (H << 3) + D + 1 + +Authors + + This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an + analysis of the decompression code available in Linux 3.16-rc5. The code is + tricky, it is possible that this document contains mistakes or that a few + corner cases were overlooked. In any case, please report any doubt, fix, or + proposed updates to the author(s) so that the document can be updated. diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt index b8dd0df76952..0fd40b15e2d5 100644 --- a/Documentation/sound/alsa/ALSA-Configuration.txt +++ b/Documentation/sound/alsa/ALSA-Configuration.txt @@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. ------------------- Module for sound cards based on the Asus AV66/AV100/AV200 chips, - i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX, - HDAV1.3 (Deluxe), and HDAV1.3 Slim. + i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe), + Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim. This module supports autoprobe and multiple cards. diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt index b0714d8f678a..8dfb6a5f427d 100644 --- a/Documentation/stable_kernel_rules.txt +++ b/Documentation/stable_kernel_rules.txt @@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the Procedure for submitting patches to the -stable tree: + - If the patch covers files in net/ or drivers/net please follow netdev stable + submission guidelines as described in + Documentation/networking/netdev-FAQ.txt - Send the patch, after verifying that it follows the above rules, to stable@vger.kernel.org. You must note the upstream commit ID in the changelog of your submission, as well as the kernel version you wish diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index e55124e7c40c..855d9b37bf76 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -317,6 +317,7 @@ for more than this value report a warning. This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. 0: means infinite timeout - no checking done. +Possible values to set are in range {0..LONG_MAX/HZ}. ============================================================== diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index d614a9b6a280..b602784b289f 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -681,7 +681,8 @@ The batch value of each per cpu pagelist is also updated as a result. It is set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8) The initial value is zero. Kernel does not use this value at boot time to set -the high water marks for each per cpu page list. +the high water marks for each per cpu page list. If the user writes '0' to this +sysctl, it will revert to this default behavior. ============================================================== diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt index 1e6b6531bbcc..d2ba80bb7af5 100644 --- a/Documentation/video4linux/gspca.txt +++ b/Documentation/video4linux/gspca.txt @@ -55,6 +55,7 @@ zc3xx 0458:700f Genius VideoCam Web V2 sonixj 0458:7025 Genius Eye 311Q sn9c20x 0458:7029 Genius Look 320s sonixj 0458:702e Genius Slim 310 NB +sn9c20x 0458:7045 Genius Look 1320 V2 sn9c20x 0458:704a Genius Slim 1320 sn9c20x 0458:704c Genius i-Look 1321 sn9c20x 045e:00f4 LifeCam VX-6000 (SN9C20x + OV9650) diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index 290894176142..53838d9c6295 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -425,6 +425,20 @@ fault through the slow path. Since only 19 bits are used to store generation-number on mmio spte, all pages are zapped when there is an overflow. +Unfortunately, a single memory access might access kvm_memslots(kvm) multiple +times, the last one happening when the generation number is retrieved and +stored into the MMIO spte. Thus, the MMIO spte might be created based on +out-of-date information, but with an up-to-date generation number. + +To avoid this, the generation number is incremented again after synchronize_srcu +returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a +memslot update, while some SRCU readers might be using the old copy. We do not +want to use an MMIO sptes created with an odd generation number, and we can do +this without losing a bit in the MMIO spte. The low bit of the generation +is not stored in MMIO spte, and presumed zero when it is extracted out of the +spte. If KVM is unlucky and creates an MMIO spte while the low bit is 1, +the next access to the spte will always be a cache miss. + Further reading =============== diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt index 550068466605..6ae89a9edf2a 100644 --- a/Documentation/vm/hwpoison.txt +++ b/Documentation/vm/hwpoison.txt @@ -84,6 +84,11 @@ PR_MCE_KILL PR_MCE_KILL_EARLY: Early kill PR_MCE_KILL_LATE: Late kill PR_MCE_KILL_DEFAULT: Use system global default + Note that if you want to have a dedicated thread which handles + the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should + call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise, + the SIGBUS is sent to the main thread. + PR_MCE_KILL_GET return current mode diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index c584a51add15..afe68ddbe6a4 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) ... unused hole ... +ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks +... unused hole ... ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls diff --git a/Documentation/zh_CN/HOWTO b/Documentation/zh_CN/HOWTO index 6c914aa87e71..54ea24ff63c7 100644 --- a/Documentation/zh_CN/HOWTO +++ b/Documentation/zh_CN/HOWTO @@ -237,7 +237,7 @@ kernel.org网站的pub/linux/kernel/v2.6/目录下找到它。它的开å‘éµå¾ª 如果没有2.6.x.yç‰ˆæœ¬å†…æ ¸å˜åœ¨ï¼Œé‚£ä¹ˆæœ€æ–°çš„2.6.xç‰ˆæœ¬å†…æ ¸å°±ç›¸å½“äºŽæ˜¯å½“å‰çš„稳定 ç‰ˆå†…æ ¸ã€‚ -2.6.x.y版本由“稳定版â€å°ç»„(邮件地å€<stable@kernel.org>ï¼‰ç»´æŠ¤ï¼Œä¸€èˆ¬éš”å‘¨å‘ +2.6.x.y版本由“稳定版â€å°ç»„(邮件地å€<stable@vger.kernel.org>ï¼‰ç»´æŠ¤ï¼Œä¸€èˆ¬éš”å‘¨å‘ å¸ƒæ–°ç‰ˆæœ¬ã€‚ å†…æ ¸æºç ä¸çš„Documentation/stable_kernel_rules.txt文件具体æ述了å¯è¢«ç¨³å®š diff --git a/Documentation/zh_CN/stable_kernel_rules.txt b/Documentation/zh_CN/stable_kernel_rules.txt index b5b9b0ab02fd..26ea5ed7cd9c 100644 --- a/Documentation/zh_CN/stable_kernel_rules.txt +++ b/Documentation/zh_CN/stable_kernel_rules.txt @@ -42,7 +42,7 @@ Documentation/stable_kernel_rules.txt çš„ä¸æ–‡ç¿»è¯‘ å‘稳定版代ç æ ‘æ交补ä¸çš„过程: - - 在确认了补ä¸ç¬¦åˆä»¥ä¸Šçš„规则åŽï¼Œå°†è¡¥ä¸å‘é€åˆ°stable@kernel.org。 + - 在确认了补ä¸ç¬¦åˆä»¥ä¸Šçš„规则åŽï¼Œå°†è¡¥ä¸å‘é€åˆ°stable@vger.kernel.org。 - 如果补ä¸è¢«æŽ¥å—到队列里,å‘é€è€…会收到一个ACK回å¤ï¼Œå¦‚果没有被接å—,收 到的是NAK回å¤ã€‚回å¤éœ€è¦å‡ 天的时间,这å–决于开å‘者的时间安排。 - 被接å—çš„è¡¥ä¸ä¼šè¢«åŠ 到稳定版本队列里,ç‰å¾…其他开å‘者的审查。 @@ -1,8 +1,8 @@ VERSION = 3 PATCHLEVEL = 14 -SUBLEVEL = 0 +SUBLEVEL = 24 EXTRAVERSION = -NAME = Shuffling Zombie Juror +NAME = Remembering Coco # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -639,6 +639,8 @@ KBUILD_CFLAGS += -fomit-frame-pointer endif endif +KBUILD_CFLAGS += $(call cc-option, -fno-var-tracking-assignments) + ifdef CONFIG_DEBUG_INFO KBUILD_CFLAGS += -g KBUILD_AFLAGS += -Wa,--gdwarf-2 diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index ea16d782af58..398064cef746 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -11,13 +11,16 @@ / { compatible = "snps,nsimosci"; - clock-frequency = <80000000>; /* 80 MHZ */ + clock-frequency = <20000000>; /* 20 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&intc>; chosen { - bootargs = "console=tty0 consoleblank=0"; + /* this is for console on PGU */ + /* bootargs = "console=tty0 consoleblank=0"; */ + /* this is for console on serial */ + bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug"; }; aliases { @@ -44,15 +47,14 @@ }; uart0: serial@c0000000 { - compatible = "snps,dw-apb-uart"; + compatible = "ns8250"; reg = <0xc0000000 0x2000>; interrupts = <11>; - #clock-frequency = <80000000>; clock-frequency = <3686400>; baud = <115200>; reg-shift = <2>; reg-io-width = <4>; - status = "okay"; + no-loopback-test = <1>; }; pgu0: pgu@c9000000 { diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 451af30914f6..c01ba35a4eff 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -54,6 +54,7 @@ CONFIG_SERIO_ARC_PS2=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 2fd3162ec4df..c1d3d2da1191 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -55,4 +55,31 @@ extern void read_decode_cache_bcr(void); #endif /* !__ASSEMBLY__ */ +/* Instruction cache related Auxiliary registers */ +#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ +#define ARC_REG_IC_IVIC 0x10 +#define ARC_REG_IC_CTRL 0x11 +#define ARC_REG_IC_IVIL 0x19 +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_IC_PTAG 0x1E +#endif + +/* Bit val in IC_CTRL */ +#define IC_CTRL_CACHE_DISABLE 0x1 + +/* Data cache related Auxiliary registers */ +#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ +#define ARC_REG_DC_IVDC 0x47 +#define ARC_REG_DC_CTRL 0x48 +#define ARC_REG_DC_IVDL 0x4A +#define ARC_REG_DC_FLSH 0x4B +#define ARC_REG_DC_FLDL 0x4C +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_DC_PTAG 0x5C +#endif + +/* Bit val in DC_CTRL */ +#define DC_CTRL_INV_MODE_FLUSH 0x40 +#define DC_CTRL_FLUSH_STATUS 0x100 + #endif /* _ASM_CACHE_H */ diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h index b65fca7ffeb5..fea931634136 100644 --- a/arch/arc/include/asm/kgdb.h +++ b/arch/arc/include/asm/kgdb.h @@ -19,7 +19,7 @@ * register API yet */ #undef DBG_MAX_REG_NUM -#define GDB_MAX_REGS 39 +#define GDB_MAX_REGS 87 #define BREAK_INSTR_SIZE 2 #define CACHE_FLUSH_IS_SAFE 1 @@ -33,23 +33,27 @@ static inline void arch_kgdb_breakpoint(void) extern void kgdb_trap(struct pt_regs *regs); -enum arc700_linux_regnums { +/* This is the numbering of registers according to the GDB. See GDB's + * arc-tdep.h for details. + * + * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */ +enum arc_linux_regnums { _R0 = 0, _R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13, _R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24, _R25, _R26, - _BTA = 27, - _LP_START = 28, - _LP_END = 29, - _LP_COUNT = 30, - _STATUS32 = 31, - _BLINK = 32, - _FP = 33, - __SP = 34, - _EFA = 35, - _RET = 36, - _ORIG_R8 = 37, - _STOP_PC = 38 + _FP = 27, + __SP = 28, + _R30 = 30, + _BLINK = 31, + _LP_COUNT = 60, + _STOP_PC = 64, + _RET = 64, + _LP_START = 65, + _LP_END = 66, + _STATUS32 = 67, + _ECR = 76, + _BTA = 82, }; #else diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h index 2618cc13ba75..76a7739aab1c 100644 --- a/arch/arc/include/uapi/asm/ptrace.h +++ b/arch/arc/include/uapi/asm/ptrace.h @@ -11,6 +11,7 @@ #ifndef _UAPI__ASM_ARC_PTRACE_H #define _UAPI__ASM_ARC_PTRACE_H +#define PTRACE_GET_THREAD_AREA 25 #ifndef __ASSEMBLY__ /* diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 47d09d07f093..6e8f83a32522 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -614,11 +614,13 @@ resume_user_mode_begin: resume_kernel_mode: -#ifdef CONFIG_PREEMPT - - ; This is a must for preempt_schedule_irq() + ; Disable Interrupts from this point on + ; CONFIG_PREEMPT: This is a must for preempt_schedule_irq() + ; !CONFIG_PREEMPT: To ensure restore_regs is intr safe IRQ_DISABLE r9 +#ifdef CONFIG_PREEMPT + ; Can't preempt if preemption disabled GET_CURR_THR_INFO_FROM_SP r10 ld r8, [r10, THREAD_INFO_PREEMPT_COUNT] diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 991997269d02..07a58f2d3077 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -12,10 +12,42 @@ * to skip certain things during boot on simulator */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/entry.h> -#include <linux/linkage.h> #include <asm/arcregs.h> +#include <asm/cache.h> + +.macro CPU_EARLY_SETUP + + ; Setting up Vectror Table (in case exception happens in early boot + sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + + ; Disable I-cache/D-cache if kernel so configured + lr r5, [ARC_REG_IC_BCR] + breq r5, 0, 1f ; I$ doesn't exist + lr r5, [ARC_REG_IC_CTRL] +#ifdef CONFIG_ARC_HAS_ICACHE + bclr r5, r5, 0 ; 0 - Enable, 1 is Disable +#else + bset r5, r5, 0 ; I$ exists, but is not used +#endif + sr r5, [ARC_REG_IC_CTRL] + +1: + lr r5, [ARC_REG_DC_BCR] + breq r5, 0, 1f ; D$ doesn't exist + lr r5, [ARC_REG_DC_CTRL] + bclr r5, r5, 6 ; Invalidate (discard w/o wback) +#ifdef CONFIG_ARC_HAS_DCACHE + bclr r5, r5, 0 ; Enable (+Inv) +#else + bset r5, r5, 0 ; Disable (+Inv) +#endif + sr r5, [ARC_REG_DC_CTRL] + +1: +.endm .cpu A7 @@ -24,13 +56,13 @@ .globl stext stext: ;------------------------------------------------------------------- - ; Don't clobber r0-r4 yet. It might have bootloader provided info + ; Don't clobber r0-r2 yet. It might have bootloader provided info ;------------------------------------------------------------------- - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP #ifdef CONFIG_SMP - ; Only Boot (Master) proceeds. Others wait in platform dependent way + ; Ensure Boot (Master) proceeds. Others wait in platform dependent way ; IDENTITY Reg [ 3 2 1 0 ] ; (cpu-id) ^^^ => Zero for UP ARC700 ; => #Core-ID if SMP (Master 0) @@ -39,7 +71,8 @@ stext: ; need to make sure only boot cpu takes this path. GET_CPU_ID r5 cmp r5, 0 - jnz arc_platform_smp_wait_to_boot + mov.ne r0, r5 + jne arc_platform_smp_wait_to_boot #endif ; Clear BSS before updating any globals ; XXX: use ZOL here @@ -89,7 +122,7 @@ stext: first_lines_of_secondary: - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP ; setup per-cpu idle task as "current" on this CPU ld r0, [@secondary_idle_tsk] diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c index 5d76706139dd..13b3ffb27a38 100644 --- a/arch/arc/kernel/ptrace.c +++ b/arch/arc/kernel/ptrace.c @@ -146,6 +146,10 @@ long arch_ptrace(struct task_struct *child, long request, pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data); switch (request) { + case PTRACE_GET_THREAD_AREA: + ret = put_user(task_thread_info(child)->thr_ptr, + (unsigned long __user *)data); + break; default: ret = ptrace_request(child, request, addr, data); break; diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 400c663b21c2..1f676c4794e0 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -73,37 +73,9 @@ #include <asm/cachectl.h> #include <asm/setup.h> -/* Instruction cache related Auxiliary registers */ -#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ -#define ARC_REG_IC_IVIC 0x10 -#define ARC_REG_IC_CTRL 0x11 -#define ARC_REG_IC_IVIL 0x19 -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_IC_PTAG 0x1E -#endif - -/* Bit val in IC_CTRL */ -#define IC_CTRL_CACHE_DISABLE 0x1 - -/* Data cache related Auxiliary registers */ -#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ -#define ARC_REG_DC_IVDC 0x47 -#define ARC_REG_DC_CTRL 0x48 -#define ARC_REG_DC_IVDL 0x4A -#define ARC_REG_DC_FLSH 0x4B -#define ARC_REG_DC_FLDL 0x4C -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_DC_PTAG 0x5C -#endif - -/* Bit val in DC_CTRL */ -#define DC_CTRL_INV_MODE_FLUSH 0x40 -#define DC_CTRL_FLUSH_STATUS 0x100 - -char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) +char *arc_cache_mumbojumbo(int c, char *buf, int len) { int n = 0; - unsigned int c = smp_processor_id(); #define PR_CACHE(p, enb, str) \ { \ @@ -169,72 +141,43 @@ void read_decode_cache_bcr(void) */ void arc_cache_init(void) { - unsigned int cpu = smp_processor_id(); - struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; - struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; - unsigned int dcache_does_alias, temp; + unsigned int __maybe_unused cpu = smp_processor_id(); + struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc; char str[256]; printk(arc_cache_mumbojumbo(0, str, sizeof(str))); - if (!ic->ver) - goto chk_dc; - -#ifdef CONFIG_ARC_HAS_ICACHE - /* 1. Confirm some of I-cache params which Linux assumes */ - if (ic->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); - - if (ic->ver != CONFIG_ARC_MMU_VER) - panic("Cache ver doesn't match MMU ver\n"); -#endif - - /* Enable/disable I-Cache */ - temp = read_aux_reg(ARC_REG_IC_CTRL); - #ifdef CONFIG_ARC_HAS_ICACHE - temp &= ~IC_CTRL_CACHE_DISABLE; -#else - temp |= IC_CTRL_CACHE_DISABLE; + ic = &cpuinfo_arc700[cpu].icache; + if (ic->ver) { + if (ic->line_len != L1_CACHE_BYTES) + panic("ICache line [%d] != kernel Config [%d]", + ic->line_len, L1_CACHE_BYTES); + + if (ic->ver != CONFIG_ARC_MMU_VER) + panic("Cache ver [%d] doesn't match MMU ver [%d]\n", + ic->ver, CONFIG_ARC_MMU_VER); + } #endif - write_aux_reg(ARC_REG_IC_CTRL, temp); - -chk_dc: - if (!dc->ver) - return; - #ifdef CONFIG_ARC_HAS_DCACHE - if (dc->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); + dc = &cpuinfo_arc700[cpu].dcache; + if (dc->ver) { + unsigned int dcache_does_alias; - /* check for D-Cache aliasing */ - dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; + if (dc->line_len != L1_CACHE_BYTES) + panic("DCache line [%d] != kernel Config [%d]", + dc->line_len, L1_CACHE_BYTES); - if (dcache_does_alias && !cache_is_vipt_aliasing()) - panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - else if (!dcache_does_alias && cache_is_vipt_aliasing()) - panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); -#endif - - /* Set the default Invalidate Mode to "simpy discard dirty lines" - * as this is more frequent then flush before invalidate - * Ofcourse we toggle this default behviour when desired - */ - temp = read_aux_reg(ARC_REG_DC_CTRL); - temp &= ~DC_CTRL_INV_MODE_FLUSH; + /* check for D-Cache aliasing */ + dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; -#ifdef CONFIG_ARC_HAS_DCACHE - /* Enable D-Cache: Clear Bit 0 */ - write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE); -#else - /* Flush D cache */ - write_aux_reg(ARC_REG_DC_FLSH, 0x1); - /* Disable D cache */ - write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE); + if (dcache_does_alias && !cache_is_vipt_aliasing()) + panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + else if (!dcache_does_alias && cache_is_vipt_aliasing()) + panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + } #endif - - return; } #define OP_INV 0x1 @@ -254,12 +197,16 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, if (cacheop == OP_INV_IC) { aux_cmd = ARC_REG_IC_IVIL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_IC_PTAG; +#endif } else { /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_DC_PTAG; +#endif } /* Ensure we properly floor/ceil the non-line aligned/sized requests diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig index 295cefeb25d3..33058aa40e77 100644 --- a/arch/arc/plat-arcfpga/Kconfig +++ b/arch/arc/plat-arcfpga/Kconfig @@ -33,7 +33,6 @@ config ISS_SMP_EXTN bool "ARC SMP Extensions (ISS Models only)" default n depends on SMP - select ARC_HAS_COH_RTSC help SMP Extensions to ARC700, in a "simulation only" Model, supported in ARC ISS (Instruction Set Simulator). diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 15949459611f..4733d327cfb1 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -6,6 +6,7 @@ config ARM select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION @@ -898,7 +899,7 @@ config ARCH_MULTI_V5 bool "ARMv5 based platforms (ARM926T, XSCALE, PJ1, ...)" depends on !ARCH_MULTI_V6_V7 select ARCH_MULTI_V4_V5 - select CPU_ARM926T if (!CPU_ARM946E || CPU_ARM1020 || \ + select CPU_ARM926T if !(CPU_ARM946E || CPU_ARM1020 || \ CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \ CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_FEROCEON) diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index e3f27ec31718..2e7d932887b5 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -183,7 +183,7 @@ &usb { status = "okay"; - control@44e10000 { + control@44e10620 { status = "okay"; }; @@ -204,7 +204,7 @@ dr_mode = "host"; }; - dma-controller@07402000 { + dma-controller@47402000 { status = "okay"; }; }; diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index 7e6c64ed966d..801055a42998 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -325,7 +325,7 @@ &usb { status = "okay"; - control@44e10000 { + control@44e10620 { status = "okay"; }; @@ -346,7 +346,7 @@ dr_mode = "host"; }; - dma-controller@07402000 { + dma-controller@47402000 { status = "okay"; }; }; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 486880b74831..dd142bc677ca 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -334,7 +334,7 @@ &usb { status = "okay"; - control@44e10000 { + control@44e10620 { status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-igep0033.dtsi b/arch/arm/boot/dts/am335x-igep0033.dtsi index 7063311a58d9..5942e7dab94f 100644 --- a/arch/arm/boot/dts/am335x-igep0033.dtsi +++ b/arch/arm/boot/dts/am335x-igep0033.dtsi @@ -202,7 +202,7 @@ &usb { status = "okay"; - control@44e10000 { + control@44e10620 { status = "okay"; }; @@ -223,7 +223,7 @@ dr_mode = "host"; }; - dma-controller@07402000 { + dma-controller@47402000 { status = "okay"; }; }; diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 6d95d3df33c7..ab01d0f98d1a 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -140,7 +140,7 @@ compatible = "ti,edma3"; ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2"; reg = <0x49000000 0x10000>, - <0x44e10f90 0x10>; + <0x44e10f90 0x40>; interrupts = <12 13 14>; #dma-cells = <1>; dma-channels = <64>; @@ -448,7 +448,7 @@ ti,hwmods = "usb_otg_hs"; status = "disabled"; - usb_ctrl_mod: control@44e10000 { + usb_ctrl_mod: control@44e10620 { compatible = "ti,am335x-usb-ctrl-module"; reg = <0x44e10620 0x10 0x44e10648 0x4>; @@ -551,7 +551,7 @@ "tx14", "tx15"; }; - cppi41dma: dma-controller@07402000 { + cppi41dma: dma-controller@47402000 { compatible = "ti,am3359-cppi41"; reg = <0x47400000 0x1000 0x47402000 0x1000 diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index c6bd4d986c29..8775681df7ed 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -161,9 +161,6 @@ ti,hwmods = "mailbox"; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <8>; - ti,mbox-names = "wkup_m3"; - ti,mbox-data = <0 0 0 0>; - status = "disabled"; }; timer1: timer@44e31000 { diff --git a/arch/arm/boot/dts/armada-370-netgear-rn102.dts b/arch/arm/boot/dts/armada-370-netgear-rn102.dts index 651aeb5ef439..f3188e953de4 100644 --- a/arch/arm/boot/dts/armada-370-netgear-rn102.dts +++ b/arch/arm/boot/dts/armada-370-netgear-rn102.dts @@ -144,6 +144,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-370-netgear-rn104.dts b/arch/arm/boot/dts/armada-370-netgear-rn104.dts index 4e27587667bf..da406c1c726a 100644 --- a/arch/arm/boot/dts/armada-370-netgear-rn104.dts +++ b/arch/arm/boot/dts/armada-370-netgear-rn104.dts @@ -146,6 +146,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi index 74b5964430ac..e5d4902c630f 100644 --- a/arch/arm/boot/dts/armada-370-xp.dtsi +++ b/arch/arm/boot/dts/armada-370-xp.dtsi @@ -226,6 +226,7 @@ #size-cells = <0>; compatible = "marvell,orion-mdio"; reg = <0x72004 0x4>; + clocks = <&gateclk 4>; }; eth1: ethernet@74000 { diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index bcf6d79a57ec..8c2fe44e4dfe 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -40,7 +40,7 @@ /* Device Bus parameters are required */ /* Read parameters */ - devbus,bus-width = <8>; + devbus,bus-width = <16>; devbus,turn-off-ps = <60000>; devbus,badr-skew-ps = <0>; devbus,acc-first-ps = <124000>; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 274e2ad5f51c..df5c34284dbd 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -49,7 +49,7 @@ /* Device Bus parameters are required */ /* Read parameters */ - devbus,bus-width = <8>; + devbus,bus-width = <16>; devbus,turn-off-ps = <60000>; devbus,badr-skew-ps = <0>; devbus,acc-first-ps = <124000>; diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index ff049ee862eb..b4aba09de911 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -224,6 +224,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index 99bcf76e6953..1c6bd83bde5e 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -23,7 +23,7 @@ memory { device_type = "memory"; - reg = <0 0x00000000 0 0xC0000000>; /* 3 GB */ + reg = <0 0x00000000 0 0x40000000>; /* 1 GB soldered on */ }; soc { @@ -37,7 +37,7 @@ /* Device Bus parameters are required */ /* Read parameters */ - devbus,bus-width = <8>; + devbus,bus-width = <16>; devbus,turn-off-ps = <60000>; devbus,badr-skew-ps = <0>; devbus,acc-first-ps = <124000>; diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index fece8665fb63..b8f234bf7de8 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -535,6 +535,7 @@ compatible = "atmel,hsmci"; reg = <0xfff80000 0x600>; interrupts = <10 IRQ_TYPE_LEVEL_HIGH 0>; + pinctrl-names = "default"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -544,6 +545,7 @@ compatible = "atmel,hsmci"; reg = <0xfff84000 0x600>; interrupts = <11 IRQ_TYPE_LEVEL_HIGH 0>; + pinctrl-names = "default"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index 5babba0a3a75..9381754b35cc 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -50,13 +50,13 @@ mcspi1_pins: pinmux_mcspi1_pins { pinctrl-single,pins = < - 0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */ - 0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */ - 0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */ - 0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */ - 0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */ - 0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */ - 0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */ + 0x3a4 (PIN_INPUT | MUX_MODE0) /* spi1_sclk */ + 0x3a8 (PIN_INPUT | MUX_MODE0) /* spi1_d1 */ + 0x3ac (PIN_INPUT | MUX_MODE0) /* spi1_d0 */ + 0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs0 */ + 0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs1 */ + 0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs2.hdmi1_hpd */ + 0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs3.hdmi1_cec */ >; }; @@ -182,6 +182,7 @@ regulator-name = "ldo3"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; regulator-boot-on; }; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 1fd75aa4639d..767f0e376f4d 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -178,7 +178,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio2: gpio@48055000 { @@ -189,7 +189,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio3: gpio@48057000 { @@ -200,7 +200,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio4: gpio@48059000 { @@ -211,7 +211,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio5: gpio@4805b000 { @@ -222,7 +222,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio6: gpio@4805d000 { @@ -233,7 +233,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio7: gpio@48051000 { @@ -244,7 +244,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio8: gpio@48053000 { @@ -255,7 +255,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; uart1: serial@4806a000 { diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts index b42e658876e5..457112d659ea 100644 --- a/arch/arm/boot/dts/exynos5250-arndale.dts +++ b/arch/arm/boot/dts/exynos5250-arndale.dts @@ -287,6 +287,7 @@ regulator-name = "vdd_g3d"; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <1000000>; + regulator-always-on; regulator-boot-on; op_mode = <1>; }; diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi index 8db792b26f79..15eb8d4e4d3c 100644 --- a/arch/arm/boot/dts/exynos5420.dtsi +++ b/arch/arm/boot/dts/exynos5420.dtsi @@ -323,6 +323,13 @@ #dma-cells = <1>; #dma-channels = <8>; #dma-requests = <1>; + /* + * MDMA1 can support both secure and non-secure + * AXI transactions. When this is enabled in the kernel + * for boards that run in secure mode, we are getting + * imprecise external aborts causing the kernel to oops. + */ + status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/hi3620.dtsi b/arch/arm/boot/dts/hi3620.dtsi index ab1116d086be..83a5b8685bd9 100644 --- a/arch/arm/boot/dts/hi3620.dtsi +++ b/arch/arm/boot/dts/hi3620.dtsi @@ -73,7 +73,7 @@ L2: l2-cache { compatible = "arm,pl310-cache"; - reg = <0xfc10000 0x100000>; + reg = <0x100000 0x100000>; interrupts = <0 15 4>; cache-unified; cache-level = <2>; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index 737ed5da8f71..de1611966d8b 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -30,6 +30,7 @@ spi2 = &spi3; usb0 = &usbotg; usb1 = &usbhost1; + ethernet0 = &fec; }; cpus { diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 826231eb4446..da2eb7f6a5b2 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -30,6 +30,7 @@ spi0 = &cspi1; spi1 = &cspi2; spi2 = &cspi3; + ethernet0 = &fec; }; aitc: aitc-interrupt-controller@e0000000 { diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi index 4bcdd3ad15e5..e1b601595a09 100644 --- a/arch/arm/boot/dts/imx51.dtsi +++ b/arch/arm/boot/dts/imx51.dtsi @@ -27,6 +27,7 @@ spi0 = &ecspi1; spi1 = &ecspi2; spi2 = &cspi; + ethernet0 = &fec; }; tzic: tz-interrupt-controller@e0000000 { diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi index 4307e80b2d2e..50eda500f39a 100644 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@ -33,6 +33,7 @@ spi0 = &ecspi1; spi1 = &ecspi2; spi2 = &cspi; + ethernet0 = &fec; }; cpus { @@ -87,7 +88,7 @@ ipu: ipu@18000000 { #crtc-cells = <1>; compatible = "fsl,imx53-ipu"; - reg = <0x18000000 0x080000000>; + reg = <0x18000000 0x08000000>; interrupts = <11 10>; clocks = <&clks 59>, <&clks 110>, <&clks 61>; clock-names = "bus", "di0", "di1"; diff --git a/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts index dc86429756d7..4651672bda89 100644 --- a/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts +++ b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts @@ -30,6 +30,16 @@ bootargs = "console=ttyS0,115200n8 earlyprintk"; }; + mbus { + pcie-controller { + status = "okay"; + + pcie@1,0 { + status = "okay"; + }; + }; + }; + ocp@f1000000 { pinctrl@10000 { pmx_usb_led: pmx-usb-led { @@ -73,14 +83,6 @@ ehci@50000 { status = "okay"; }; - - pcie-controller { - status = "okay"; - - pcie@1,0 { - status = "okay"; - }; - }; }; gpio-leds { diff --git a/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi index aa78c2d11fe7..e2cc85cc3b87 100644 --- a/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi +++ b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi @@ -4,6 +4,16 @@ / { model = "ZyXEL NSA310"; + mbus { + pcie-controller { + status = "okay"; + + pcie@1,0 { + status = "okay"; + }; + }; + }; + ocp@f1000000 { pinctrl: pinctrl@10000 { @@ -26,14 +36,6 @@ status = "okay"; nr-ports = <2>; }; - - pcie-controller { - status = "okay"; - - pcie@1,0 { - status = "okay"; - }; - }; }; gpio_poweroff { diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index d3f8a6e8ca20..69409f7e05dc 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -275,6 +275,8 @@ gpmc,num-waitpins = <4>; ti,hwmods = "gpmc"; ti,no-idle-on-init; + clocks = <&l3_div_ck>; + clock-names = "fck"; }; uart1: serial@4806a000 { diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index a72813a9663e..7a16647c76f4 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -302,6 +302,8 @@ gpmc,num-cs = <8>; gpmc,num-waitpins = <4>; ti,hwmods = "gpmc"; + clocks = <&l3_iclk_div>; + clock-names = "fck"; }; i2c1: i2c@48070000 { diff --git a/arch/arm/boot/dts/sama5d3_can.dtsi b/arch/arm/boot/dts/sama5d3_can.dtsi index a0775851cce5..eaf41451ad0c 100644 --- a/arch/arm/boot/dts/sama5d3_can.dtsi +++ b/arch/arm/boot/dts/sama5d3_can.dtsi @@ -40,7 +40,7 @@ atmel,clk-output-range = <0 66000000>; }; - can1_clk: can0_clk { + can1_clk: can1_clk { #clock-cells = <0>; reg = <41>; atmel,clk-output-range = <0 66000000>; diff --git a/arch/arm/boot/dts/ste-ccu8540.dts b/arch/arm/boot/dts/ste-ccu8540.dts index 7f3baf51a3a9..32dd55e5f4e6 100644 --- a/arch/arm/boot/dts/ste-ccu8540.dts +++ b/arch/arm/boot/dts/ste-ccu8540.dts @@ -18,6 +18,7 @@ compatible = "st-ericsson,ccu8540", "st-ericsson,u8540"; memory@0 { + device_type = "memory"; reg = <0x20000000 0x1f000000>, <0xc0000000 0x3f000000>; }; diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi index ec0698a8354a..9c2ba74a8b60 100644 --- a/arch/arm/boot/dts/tegra124.dtsi +++ b/arch/arm/boot/dts/tegra124.dtsi @@ -164,19 +164,6 @@ status = "disabled"; }; - serial@70006400 { - compatible = "nvidia,tegra124-uart", "nvidia,tegra20-uart"; - reg = <0x70006400 0x40>; - reg-shift = <2>; - interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA124_CLK_UARTE>; - resets = <&tegra_car 66>; - reset-names = "serial"; - dmas = <&apbdma 20>, <&apbdma 20>; - dma-names = "rx", "tx"; - status = "disabled"; - }; - pwm@7000a000 { compatible = "nvidia,tegra124-pwm", "nvidia,tegra20-pwm"; reg = <0x7000a000 0x100>; diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c index 41bca32409fc..5339009b3c0c 100644 --- a/arch/arm/common/edma.c +++ b/arch/arm/common/edma.c @@ -1423,55 +1423,38 @@ EXPORT_SYMBOL(edma_clear_event); #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_DMADEVICES) -static int edma_of_read_u32_to_s16_array(const struct device_node *np, - const char *propname, s16 *out_values, - size_t sz) +static int edma_xbar_event_map(struct device *dev, struct device_node *node, + struct edma_soc_info *pdata, size_t sz) { - int ret; - - ret = of_property_read_u16_array(np, propname, out_values, sz); - if (ret) - return ret; - - /* Terminate it */ - *out_values++ = -1; - *out_values++ = -1; - - return 0; -} - -static int edma_xbar_event_map(struct device *dev, - struct device_node *node, - struct edma_soc_info *pdata, int len) -{ - int ret, i; + const char pname[] = "ti,edma-xbar-event-map"; struct resource res; void __iomem *xbar; - const s16 (*xbar_chans)[2]; + s16 (*xbar_chans)[2]; + size_t nelm = sz / sizeof(s16); u32 shift, offset, mux; + int ret, i; - xbar_chans = devm_kzalloc(dev, - len/sizeof(s16) + 2*sizeof(s16), - GFP_KERNEL); + xbar_chans = devm_kzalloc(dev, (nelm + 2) * sizeof(s16), GFP_KERNEL); if (!xbar_chans) return -ENOMEM; ret = of_address_to_resource(node, 1, &res); if (ret) - return -EIO; + return -ENOMEM; xbar = devm_ioremap(dev, res.start, resource_size(&res)); if (!xbar) return -ENOMEM; - ret = edma_of_read_u32_to_s16_array(node, - "ti,edma-xbar-event-map", - (s16 *)xbar_chans, - len/sizeof(u32)); + ret = of_property_read_u16_array(node, pname, (u16 *)xbar_chans, nelm); if (ret) return -EIO; - for (i = 0; xbar_chans[i][0] != -1; i++) { + /* Invalidate last entry for the other user of this mess */ + nelm >>= 1; + xbar_chans[nelm][0] = xbar_chans[nelm][1] = -1; + + for (i = 0; i < nelm; i++) { shift = (xbar_chans[i][1] & 0x03) << 3; offset = xbar_chans[i][1] & 0xfffffffc; mux = readl(xbar + offset); @@ -1480,8 +1463,7 @@ static int edma_xbar_event_map(struct device *dev, writel(mux, (xbar + offset)); } - pdata->xbar_chans = xbar_chans; - + pdata->xbar_chans = (const s16 (*)[2]) xbar_chans; return 0; } diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c index 4522366da759..15468fbbdea3 100644 --- a/arch/arm/crypto/aesbs-glue.c +++ b/arch/arm/crypto/aesbs-glue.c @@ -137,7 +137,7 @@ static int aesbs_cbc_encrypt(struct blkcipher_desc *desc, dst += AES_BLOCK_SIZE; } while (--blocks); } - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } @@ -158,7 +158,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc, bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr, walk.nbytes, &ctx->dec, walk.iv); kernel_neon_end(); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } while (walk.nbytes) { u32 blocks = walk.nbytes / AES_BLOCK_SIZE; @@ -182,7 +182,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc, dst += AES_BLOCK_SIZE; src += AES_BLOCK_SIZE; } while (--blocks); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } @@ -268,7 +268,7 @@ static int aesbs_xts_encrypt(struct blkcipher_desc *desc, bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr, walk.nbytes, &ctx->enc, walk.iv); kernel_neon_end(); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } @@ -292,7 +292,7 @@ static int aesbs_xts_decrypt(struct blkcipher_desc *desc, bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr, walk.nbytes, &ctx->dec, walk.iv); kernel_neon_end(); - err = blkcipher_walk_done(desc, &walk, 0); + err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } return err; } diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h index 191ada6e4d2d..662c7bd06108 100644 --- a/arch/arm/include/asm/div64.h +++ b/arch/arm/include/asm/div64.h @@ -156,7 +156,7 @@ /* Select the best insn combination to perform the */ \ /* actual __m * __n / (__p << 64) operation. */ \ if (!__c) { \ - asm ( "umull %Q0, %R0, %1, %Q2\n\t" \ + asm ( "umull %Q0, %R0, %Q1, %Q2\n\t" \ "mov %Q0, #0" \ : "=&r" (__res) \ : "r" (__m), "r" (__n) \ diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index e42cf597f6e6..2aff798fbef4 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -3,11 +3,6 @@ #ifdef __KERNEL__ -#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP) -/* ARM doesn't provide unprivileged exclusive memory accessors */ -#include <asm-generic/futex.h> -#else - #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/errno.h> @@ -164,6 +159,5 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) return ret; } -#endif /* !(CPU_USE_DOMAINS && SMP) */ #endif /* __KERNEL__ */ #endif /* _ASM_ARM_FUTEX_H */ diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index dfff709fda3c..219ac88a9542 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -140,6 +140,7 @@ #define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ #define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ #define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ +#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */ #define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) #ifndef __ASSEMBLY__ diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h index 83259b873333..5f833f7adba1 100644 --- a/arch/arm/include/asm/tls.h +++ b/arch/arm/include/asm/tls.h @@ -1,6 +1,9 @@ #ifndef __ASMARM_TLS_H #define __ASMARM_TLS_H +#include <linux/compiler.h> +#include <asm/thread_info.h> + #ifdef __ASSEMBLY__ #include <asm/asm-offsets.h> .macro switch_tls_none, base, tp, tpuser, tmp1, tmp2 @@ -50,6 +53,49 @@ #endif #ifndef __ASSEMBLY__ + +static inline void set_tls(unsigned long val) +{ + struct thread_info *thread; + + thread = current_thread_info(); + + thread->tp_value[0] = val; + + /* + * This code runs with preemption enabled and therefore must + * be reentrant with respect to switch_tls. + * + * We need to ensure ordering between the shadow state and the + * hardware state, so that we don't corrupt the hardware state + * with a stale shadow state during context switch. + * + * If we're preempted here, switch_tls will load TPIDRURO from + * thread_info upon resuming execution and the following mcr + * is merely redundant. + */ + barrier(); + + if (!tls_emu) { + if (has_tls_reg) { + asm("mcr p15, 0, %0, c13, c0, 3" + : : "r" (val)); + } else { +#ifdef CONFIG_KUSER_HELPERS + /* + * User space must never try to access this + * directly. Expect your app to break + * eventually if you do so. The user helper + * at 0xffff0fe0 must be used instead. (see + * entry-armv.S for details) + */ + *((unsigned int *)0xffff0ff0) = val; +#endif + } + + } +} + static inline unsigned long get_tpuser(void) { unsigned long reg = 0; @@ -59,5 +105,23 @@ static inline unsigned long get_tpuser(void) return reg; } + +static inline void set_tpuser(unsigned long val) +{ + /* Since TPIDRURW is fully context-switched (unlike TPIDRURO), + * we need not update thread_info. + */ + if (has_tls_reg && !tls_emu) { + asm("mcr p15, 0, %0, c13, c0, 2" + : : "r" (val)); + } +} + +static inline void flush_tls(void) +{ + set_tls(0); + set_tpuser(0); +} + #endif #endif /* __ASMARM_TLS_H */ diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 72abdc541f38..7f3f3cc25d7e 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -171,8 +171,9 @@ extern int __put_user_8(void *, unsigned long long); #define __put_user_check(x,p) \ ({ \ unsigned long __limit = current_thread_info()->addr_limit - 1; \ + const typeof(*(p)) __user *__tmp_p = (p); \ register const typeof(*(p)) __r2 asm("r2") = (x); \ - register const typeof(*(p)) __user *__p asm("r0") = (p);\ + register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \ register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ switch (sizeof(*(__p))) { \ diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index acabef1a75df..21ca0cebcab0 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -15,7 +15,17 @@ #include <uapi/asm/unistd.h> +/* + * This may need to be greater than __NR_last_syscall+1 in order to + * account for the padding in the syscall table + */ #define __NR_syscalls (384) + +/* + * *NOTE*: This is a ghost syscall private to the kernel. Only the + * __kuser_cmpxchg code in entry-armv.S should be aware of its + * existence. Don't ever use this from user code. + */ #define __ARM_NR_cmpxchg (__ARM_NR_BASE+0x00fff0) #define __ARCH_WANT_STAT64 @@ -48,6 +58,5 @@ */ #define __IGNORE_fadvise64_64 #define __IGNORE_migrate_pages -#define __IGNORE_kcmp #endif /* __ASM_ARM_UNISTD_H */ diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index fb5584d0cc05..c3776331f407 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -410,11 +410,6 @@ #define __NR_sched_getattr (__NR_SYSCALL_BASE+381) /* - * This may need to be greater than __NR_last_syscall+1 in order to - * account for the padding in the syscall table - */ - -/* * The following SWIs are ARM private. */ #define __ARM_NR_BASE (__NR_SYSCALL_BASE+0x0f0000) @@ -425,12 +420,6 @@ #define __ARM_NR_set_tls (__ARM_NR_BASE+5) /* - * *NOTE*: This is a ghost syscall private to the kernel. Only the - * __kuser_cmpxchg code in entry-armv.S should be aware of its - * existence. Don't ever use this from user code. - */ - -/* * The following syscalls are obsolete and no longer available for EABI. */ #if !defined(__KERNEL__) diff --git a/arch/arm/kernel/crash_dump.c b/arch/arm/kernel/crash_dump.c index 90c50d4b43f7..5d1286d51154 100644 --- a/arch/arm/kernel/crash_dump.c +++ b/arch/arm/kernel/crash_dump.c @@ -39,7 +39,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!csize) return 0; - vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + vaddr = ioremap(__pfn_to_phys(pfn), PAGE_SIZE); if (!vaddr) return -ENOMEM; diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 39f89fbd5111..88c6babeb0b5 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -132,6 +132,10 @@ orrne r5, V7M_xPSR_FRAMEPTRALIGN biceq r5, V7M_xPSR_FRAMEPTRALIGN + @ ensure bit 0 is cleared in the PC, otherwise behaviour is + @ unpredictable + bic r4, #1 + @ write basic exception frame stmdb r2!, {r1, r3-r5} ldmia sp, {r1, r3-r5} diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 9723d17b8f38..1e782bdeee49 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -163,7 +163,7 @@ static bool migrate_one_irq(struct irq_desc *desc) c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index f0d180d8b29f..8cf0996aa1a8 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -184,3 +184,10 @@ void machine_kexec(struct kimage *image) soft_restart(reboot_entry_phys); } + +void arch_crash_save_vmcoreinfo(void) +{ +#ifdef CONFIG_ARM_LPAE + VMCOREINFO_CONFIG(ARM_LPAE); +#endif +} diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 92f7b15dd221..5f6e650ec9ab 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -334,6 +334,8 @@ void flush_thread(void) memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); memset(&thread->fpstate, 0, sizeof(union fp_state)); + flush_tls(); + thread_notify(THREAD_NOTIFY_FLUSH, thread); } diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index af4e8c8a5422..6582c4adc182 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -83,13 +83,16 @@ static int save_trace(struct stackframe *frame, void *d) return trace->nr_entries >= trace->max_entries; } -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +/* This must be noinline to so that our skip calculation works correctly */ +static noinline void __save_stack_trace(struct task_struct *tsk, + struct stack_trace *trace, unsigned int nosched) { struct stack_trace_data data; struct stackframe frame; data.trace = trace; data.skip = trace->skip; + data.no_sched_functions = nosched; if (tsk != current) { #ifdef CONFIG_SMP @@ -102,7 +105,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; return; #else - data.no_sched_functions = 1; frame.fp = thread_saved_fp(tsk); frame.sp = thread_saved_sp(tsk); frame.lr = 0; /* recovered from the stack */ @@ -111,11 +113,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) } else { register unsigned long current_sp asm ("sp"); - data.no_sched_functions = 0; + /* We don't want this function nor the caller */ + data.skip += 2; frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_sp; frame.lr = (unsigned long)__builtin_return_address(0); - frame.pc = (unsigned long)save_stack_trace_tsk; + frame.pc = (unsigned long)__save_stack_trace; } walk_stackframe(&frame, save_trace, &data); @@ -123,9 +126,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; } +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + __save_stack_trace(tsk, trace, 1); +} + void save_stack_trace(struct stack_trace *trace) { - save_stack_trace_tsk(current, trace); + __save_stack_trace(current, trace, 0); } EXPORT_SYMBOL_GPL(save_stack_trace); #endif diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c index 7b8403b76666..80f0d69205e7 100644 --- a/arch/arm/kernel/thumbee.c +++ b/arch/arm/kernel/thumbee.c @@ -45,7 +45,7 @@ static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void switch (cmd) { case THREAD_NOTIFY_FLUSH: - thread->thumbee_state = 0; + teehbr_write(0); break; case THREAD_NOTIFY_SWITCH: current_thread_info()->thumbee_state = teehbr_read(); diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 172ee18ff124..9265b8bb529a 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -578,7 +578,6 @@ do_cache_op(unsigned long start, unsigned long end, int flags) #define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE) asmlinkage int arm_syscall(int no, struct pt_regs *regs) { - struct thread_info *thread = current_thread_info(); siginfo_t info; if ((no >> 16) != (__ARM_NR_BASE>> 16)) @@ -629,21 +628,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) return regs->ARM_r0; case NR(set_tls): - thread->tp_value[0] = regs->ARM_r0; - if (tls_emu) - return 0; - if (has_tls_reg) { - asm ("mcr p15, 0, %0, c13, c0, 3" - : : "r" (regs->ARM_r0)); - } else { - /* - * User space must never try to access this directly. - * Expect your app to break eventually if you do so. - * The user helper at 0xffff0fe0 must be used instead. - * (see entry-armv.S for details) - */ - *((unsigned int *)0xffff0ff0) = regs->ARM_r0; - } + set_tls(regs->ARM_r0); return 0; #ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 0de91fc6de0f..ec4fa868a7ba 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -89,6 +89,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) else kvm_vcpu_block(vcpu); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; } diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S index 1b9844d369cc..ee4f7447a1d3 100644 --- a/arch/arm/kvm/init.S +++ b/arch/arm/kvm/init.S @@ -98,6 +98,10 @@ __do_hyp_init: mrc p15, 0, r0, c10, c2, 1 mcr p15, 4, r0, c10, c2, 1 + @ Invalidate the stale TLBs from Bootloader + mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH + dsb ish + @ Set the HSCTLR to: @ - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel) @ - Endianness: Kernel config diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 7789857d1470..575d7904305b 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -42,6 +42,8 @@ static unsigned long hyp_idmap_start; static unsigned long hyp_idmap_end; static phys_addr_t hyp_idmap_vector; +#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t)) + #define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x)) static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) @@ -199,14 +201,14 @@ void free_boot_hyp_pgd(void) if (boot_hyp_pgd) { unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE); unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE); - kfree(boot_hyp_pgd); + free_pages((unsigned long)boot_hyp_pgd, pgd_order); boot_hyp_pgd = NULL; } if (hyp_pgd) unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE); - kfree(init_bounce_page); + free_page((unsigned long)init_bounce_page); init_bounce_page = NULL; mutex_unlock(&kvm_hyp_pgd_mutex); @@ -236,7 +238,7 @@ void free_hyp_pgds(void) for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE); - kfree(hyp_pgd); + free_pages((unsigned long)hyp_pgd, pgd_order); hyp_pgd = NULL; } @@ -930,7 +932,7 @@ int kvm_mmu_init(void) size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start; phys_addr_t phys_base; - init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL); + init_bounce_page = (void *)__get_free_page(GFP_KERNEL); if (!init_bounce_page) { kvm_err("Couldn't allocate HYP init bounce page\n"); err = -ENOMEM; @@ -956,8 +958,9 @@ int kvm_mmu_init(void) (unsigned long)phys_base); } - hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL); - boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL); + hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order); + boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order); + if (!hyp_pgd || !boot_hyp_pgd) { kvm_err("Hyp mode PGD not allocated\n"); err = -ENOMEM; diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c index 034529d801b2..d66f102c352a 100644 --- a/arch/arm/mach-at91/clock.c +++ b/arch/arm/mach-at91/clock.c @@ -962,6 +962,7 @@ static int __init at91_clock_reset(void) } at91_pmc_write(AT91_PMC_SCDR, scdr); + at91_pmc_write(AT91_PMC_PCDR, pcdr); if (cpu_is_sama5d3()) at91_pmc_write(AT91_PMC_PCDR1, pcdr1); diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c index 2ba694f9626b..f8bc3511a8c8 100644 --- a/arch/arm/mach-at91/sysirq_mask.c +++ b/arch/arm/mach-at91/sysirq_mask.c @@ -25,24 +25,28 @@ #include "generic.h" -#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ -#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ +#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ +#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ +#define AT91_RTC_IRQ_MASK 0x1f /* Available IRQs mask */ void __init at91_sysirq_mask_rtc(u32 rtc_base) { void __iomem *base; - u32 mask; base = ioremap(rtc_base, 64); if (!base) return; - mask = readl_relaxed(base + AT91_RTC_IMR); - if (mask) { - pr_info("AT91: Disabling rtc irq\n"); - writel_relaxed(mask, base + AT91_RTC_IDR); - (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ - } + /* + * sam9x5 SoCs have the following errata: + * "RTC: Interrupt Mask Register cannot be used + * Interrupt Mask Register read always returns 0." + * + * Hence we're not relying on IMR values to disable + * interrupts. + */ + writel_relaxed(AT91_RTC_IRQ_MASK, base + AT91_RTC_IDR); + (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ iounmap(base); } diff --git a/arch/arm/mach-imx/devices/platform-ipu-core.c b/arch/arm/mach-imx/devices/platform-ipu-core.c index fc4dd7cedc11..6bd7c3f37ac0 100644 --- a/arch/arm/mach-imx/devices/platform-ipu-core.c +++ b/arch/arm/mach-imx/devices/platform-ipu-core.c @@ -77,7 +77,7 @@ struct platform_device *__init imx_alloc_mx3_camera( pdev = platform_device_alloc("mx3-camera", 0); if (!pdev) - goto err; + return ERR_PTR(-ENOMEM); pdev->dev.dma_mask = kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL); if (!pdev->dev.dma_mask) diff --git a/arch/arm/mach-mvebu/mvebu-soc-id.c b/arch/arm/mach-mvebu/mvebu-soc-id.c index f3b325f6cbd4..0e1547a186b0 100644 --- a/arch/arm/mach-mvebu/mvebu-soc-id.c +++ b/arch/arm/mach-mvebu/mvebu-soc-id.c @@ -107,7 +107,18 @@ static int __init mvebu_soc_id_init(void) iounmap(pci_base); res_ioremap: - clk_disable_unprepare(clk); + /* + * If the PCIe unit is actually enabled and we have PCI + * support in the kernel, we intentionally do not release the + * reference to the clock. We want to keep it running since + * the bootloader does some PCIe link configuration that the + * kernel is for now unable to do, and gating the clock would + * make us loose this precious configuration. + */ + if (!of_device_is_available(child) || !IS_ENABLED(CONFIG_PCI_MVEBU)) { + clk_disable_unprepare(clk); + clk_put(clk); + } clk_err: of_node_put(child); diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c index fd90cafc2e36..db57072aeed3 100644 --- a/arch/arm/mach-omap1/board-h2.c +++ b/arch/arm/mach-omap1/board-h2.c @@ -343,7 +343,7 @@ static struct omap_usb_config h2_usb_config __initdata = { /* usb1 has a Mini-AB port and external isp1301 transceiver */ .otg = 2, -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ /* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */ #elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c index 816ecd13f81e..bfed4f928663 100644 --- a/arch/arm/mach-omap1/board-h3.c +++ b/arch/arm/mach-omap1/board-h3.c @@ -366,7 +366,7 @@ static struct omap_usb_config h3_usb_config __initdata = { /* usb1 has a Mini-AB port and external isp1301 transceiver */ .otg = 2, -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ #elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) /* NONSTANDARD CABLE NEEDED (B-to-Mini-B) */ diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c index bd5f02e9c354..c49ce83cc1eb 100644 --- a/arch/arm/mach-omap1/board-innovator.c +++ b/arch/arm/mach-omap1/board-innovator.c @@ -312,7 +312,7 @@ static struct omap_usb_config h2_usb_config __initdata = { /* usb1 has a Mini-AB port and external isp1301 transceiver */ .otg = 2, -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ /* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */ #elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c index d68909b095f1..55b10877f4ff 100644 --- a/arch/arm/mach-omap1/board-osk.c +++ b/arch/arm/mach-omap1/board-osk.c @@ -280,7 +280,7 @@ static struct omap_usb_config osk_usb_config __initdata = { * be used, with a NONSTANDARD gender-bending cable/dongle, as * a peripheral. */ -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .register_dev = 1, .hmc_mode = 0, #else diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c index ac82512b9c8c..b6885e42c0a0 100644 --- a/arch/arm/mach-omap2/board-flash.c +++ b/arch/arm/mach-omap2/board-flash.c @@ -142,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs, board_nand_data.nr_parts = nr_parts; board_nand_data.devsize = nand_type; - board_nand_data.ecc_opt = OMAP_ECC_BCH8_CODE_HW; + board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_HW; gpmc_nand_init(&board_nand_data, gpmc_t); } #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */ diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c index 11ed9152e665..793039a9bd26 100644 --- a/arch/arm/mach-omap2/cclock3xxx_data.c +++ b/arch/arm/mach-omap2/cclock3xxx_data.c @@ -456,7 +456,8 @@ static struct clk_hw_omap dpll4_m5x2_ck_hw = { .clkdm_name = "dpll4_clkdm", }; -DEFINE_STRUCT_CLK(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names, dpll4_m5x2_ck_ops); +DEFINE_STRUCT_CLK_FLAGS(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names, + dpll4_m5x2_ck_ops, CLK_SET_RATE_PARENT); static struct clk dpll4_m5x2_ck_3630 = { .name = "dpll4_m5x2_ck", diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c index 44bb4d544dcf..89cde0786d25 100644 --- a/arch/arm/mach-omap2/control.c +++ b/arch/arm/mach-omap2/control.c @@ -314,7 +314,8 @@ void omap3_save_scratchpad_contents(void) scratchpad_contents.public_restore_ptr = virt_to_phys(omap3_restore_3630); else if (omap_rev() != OMAP3430_REV_ES3_0 && - omap_rev() != OMAP3430_REV_ES3_1) + omap_rev() != OMAP3430_REV_ES3_1 && + omap_rev() != OMAP3430_REV_ES3_1_2) scratchpad_contents.public_restore_ptr = virt_to_phys(omap3_restore); else diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index 01fc710c8181..2498ab025fa2 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -14,6 +14,7 @@ #include <linux/cpuidle.h> #include <linux/cpu_pm.h> #include <linux/export.h> +#include <linux/clockchips.h> #include <asm/cpuidle.h> #include <asm/proc-fns.h> @@ -83,6 +84,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, { struct idle_statedata *cx = state_ptr + index; u32 mpuss_can_lose_context = 0; + int cpu_id = smp_processor_id(); /* * CPU0 has to wait and stay ON until CPU1 is OFF state. @@ -110,6 +112,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) && (cx->mpu_logic_state == PWRDM_POWER_OFF); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id); + /* * Call idle CPU PM enter notifier chain so that * VFP and per CPU interrupt context is saved. @@ -165,6 +169,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (dev->cpu == 0 && mpuss_can_lose_context) cpu_cluster_pm_exit(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id); + fail: cpuidle_coupled_parallel_barrier(dev, &abort_barrier); cpu_done[dev->cpu] = false; @@ -172,6 +178,16 @@ fail: return index; } +/* + * For each cpu, setup the broadcast timer because local timers + * stops for the states above C1. + */ +static void omap_setup_broadcast_timer(void *arg) +{ + int cpu = smp_processor_id(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu); +} + static struct cpuidle_driver omap4_idle_driver = { .name = "omap4_idle", .owner = THIS_MODULE, @@ -189,8 +205,7 @@ static struct cpuidle_driver omap4_idle_driver = { /* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */ .exit_latency = 328 + 440, .target_residency = 960, - .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED | - CPUIDLE_FLAG_TIMER_STOP, + .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED, .enter = omap_enter_idle_coupled, .name = "C2", .desc = "CPUx OFF, MPUSS CSWR", @@ -199,8 +214,7 @@ static struct cpuidle_driver omap4_idle_driver = { /* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */ .exit_latency = 460 + 518, .target_residency = 1100, - .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED | - CPUIDLE_FLAG_TIMER_STOP, + .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED, .enter = omap_enter_idle_coupled, .name = "C3", .desc = "CPUx OFF, MPUSS OSWR", @@ -231,5 +245,8 @@ int __init omap4_idle_init(void) if (!cpu_clkdm[0] || !cpu_clkdm[1]) return -ENODEV; + /* Configure the broadcast timer on each cpu */ + on_each_cpu(omap_setup_broadcast_timer, NULL, 1); + return cpuidle_register(&omap4_idle_driver, cpu_online_mask); } diff --git a/arch/arm/mach-omap2/irq.c b/arch/arm/mach-omap2/irq.c index e022a869bff2..6037a9a01ed5 100644 --- a/arch/arm/mach-omap2/irq.c +++ b/arch/arm/mach-omap2/irq.c @@ -222,6 +222,7 @@ void __init ti81xx_init_irq(void) static inline void omap_intc_handle_irq(void __iomem *base_addr, struct pt_regs *regs) { u32 irqnr; + int handled_irq = 0; do { irqnr = readl_relaxed(base_addr + 0x98); @@ -249,8 +250,15 @@ out: if (irqnr) { irqnr = irq_find_mapping(domain, irqnr); handle_IRQ(irqnr, regs); + handled_irq = 1; } } while (irqnr); + + /* If an irq is masked or deasserted while active, we will + * keep ending up here with no irq handled. So remove it from + * the INTC with an ack.*/ + if (!handled_irq) + omap_ack_irq(NULL); } asmlinkage void __exception_irq_entry omap2_intc_handle_irq(struct pt_regs *regs) diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c index 48094b58c88f..b12a4f9fc9d0 100644 --- a/arch/arm/mach-omap2/mux.c +++ b/arch/arm/mach-omap2/mux.c @@ -183,8 +183,10 @@ static int __init _omap_mux_get_by_name(struct omap_mux_partition *partition, m0_entry = mux->muxnames[0]; /* First check for full name in mode0.muxmode format */ - if (mode0_len && strncmp(muxname, m0_entry, mode0_len)) - continue; + if (mode0_len) + if (strncmp(muxname, m0_entry, mode0_len) || + (strlen(m0_entry) != mode0_len)) + continue; /* Then check for muxmode only */ for (i = 0; i < OMAP_MUX_NR_MODES; i++) { diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 1f33f5db10d5..4551efd28f8d 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2185,6 +2185,8 @@ static int _enable(struct omap_hwmod *oh) oh->mux->pads_dynamic))) { omap_hwmod_mux(oh->mux, _HWMOD_STATE_ENABLED); _reconfigure_io_chain(); + } else if (oh->flags & HWMOD_FORCE_MSTANDBY) { + _reconfigure_io_chain(); } _add_initiator_dep(oh, mpu_oh); @@ -2291,6 +2293,8 @@ static int _idle(struct omap_hwmod *oh) if (oh->mux && oh->mux->pads_dynamic) { omap_hwmod_mux(oh->mux, _HWMOD_STATE_IDLE); _reconfigure_io_chain(); + } else if (oh->flags & HWMOD_FORCE_MSTANDBY) { + _reconfigure_io_chain(); } oh->_state = _HWMOD_STATE_IDLE; @@ -2546,11 +2550,12 @@ static int __init _init(struct omap_hwmod *oh, void *data) return -EINVAL; } - if (np) + if (np) { if (of_find_property(np, "ti,no-reset-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -3344,6 +3349,9 @@ int __init omap_hwmod_register_links(struct omap_hwmod_ocp_if **ois) if (!ois) return 0; + if (ois[0] == NULL) /* Empty list */ + return 0; + if (!linkspace) { if (_alloc_linkspace(ois)) { pr_err("omap_hwmod: could not allocate link space\n"); diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index 4c3b1e6df508..ea4643abbe61 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -1968,7 +1968,7 @@ static struct omap_hwmod_irq_info omap3xxx_usb_host_hs_irqs[] = { static struct omap_hwmod omap3xxx_usb_host_hs_hwmod = { .name = "usb_host_hs", .class = &omap3xxx_usb_host_hs_hwmod_class, - .clkdm_name = "l3_init_clkdm", + .clkdm_name = "usbhost_clkdm", .mpu_irqs = omap3xxx_usb_host_hs_irqs, .main_clk = "usbhost_48m_fck", .prcm = { @@ -2053,7 +2053,7 @@ static struct omap_hwmod_irq_info omap3xxx_usb_tll_hs_irqs[] = { static struct omap_hwmod omap3xxx_usb_tll_hs_hwmod = { .name = "usb_tll_hs", .class = &omap3xxx_usb_tll_hs_hwmod_class, - .clkdm_name = "l3_init_clkdm", + .clkdm_name = "core_l4_clkdm", .mpu_irqs = omap3xxx_usb_tll_hs_irqs, .main_clk = "usbtll_fck", .prcm = { diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c index e297d6231c3a..7babf515465c 100644 --- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c @@ -895,7 +895,7 @@ static struct omap_hwmod omap54xx_mcpdm_hwmod = { * current exception. */ - .flags = HWMOD_EXT_OPT_MAIN_CLK, + .flags = HWMOD_EXT_OPT_MAIN_CLK | HWMOD_SWSUP_SIDLE, .main_clk = "pad_clks_ck", .prcm = { .omap4 = { diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index 810c205d668b..2e35ff99f60e 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -35,6 +35,7 @@ #include "i2c.h" #include "mmc.h" #include "wd_timer.h" +#include "soc.h" /* Base offset for all DRA7XX interrupts external to MPUSS */ #define DRA7XX_IRQ_GIC_START 32 @@ -2707,7 +2708,6 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { &dra7xx_l4_per3__usb_otg_ss1, &dra7xx_l4_per3__usb_otg_ss2, &dra7xx_l4_per3__usb_otg_ss3, - &dra7xx_l4_per3__usb_otg_ss4, &dra7xx_l3_main_1__vcp1, &dra7xx_l4_per2__vcp1, &dra7xx_l3_main_1__vcp2, @@ -2716,8 +2716,26 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { NULL, }; +static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = { + &dra7xx_l4_per3__usb_otg_ss4, + NULL, +}; + +static struct omap_hwmod_ocp_if *dra72x_hwmod_ocp_ifs[] __initdata = { + NULL, +}; + int __init dra7xx_hwmod_init(void) { + int ret; + omap_hwmod_init(); - return omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs); + ret = omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs); + + if (!ret && soc_is_dra74x()) + return omap_hwmod_register_links(dra74x_hwmod_ocp_ifs); + else if (!ret && soc_is_dra72x()) + return omap_hwmod_register_links(dra72x_hwmod_ocp_ifs); + + return ret; } diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h index 7bdd22afce69..d4d0fce325c7 100644 --- a/arch/arm/mach-omap2/pm.h +++ b/arch/arm/mach-omap2/pm.h @@ -103,7 +103,7 @@ static inline void enable_omap3630_toggle_l2_on_restore(void) { } #define PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD (1 << 0) -#if defined(CONFIG_ARCH_OMAP4) +#if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP4) extern u16 pm44xx_errata; #define IS_PM44XX_ERRATUM(id) (pm44xx_errata & (id)) #else diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h index 076bd90a6ce0..8a9be09d9f38 100644 --- a/arch/arm/mach-omap2/soc.h +++ b/arch/arm/mach-omap2/soc.h @@ -245,6 +245,8 @@ IS_AM_SUBCLASS(437x, 0x437) #define soc_is_omap54xx() 0 #define soc_is_omap543x() 0 #define soc_is_dra7xx() 0 +#define soc_is_dra74x() 0 +#define soc_is_dra72x() 0 #if defined(MULTI_OMAP2) # if defined(CONFIG_ARCH_OMAP2) @@ -393,7 +395,11 @@ IS_OMAP_TYPE(3430, 0x3430) #if defined(CONFIG_SOC_DRA7XX) #undef soc_is_dra7xx +#undef soc_is_dra74x +#undef soc_is_dra72x #define soc_is_dra7xx() (of_machine_is_compatible("ti,dra7")) +#define soc_is_dra74x() (of_machine_is_compatible("ti,dra74")) +#define soc_is_dra72x() (of_machine_is_compatible("ti,dra72")) #endif /* Various silicon revisions for omap2 */ diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h index f565f9944af2..7548db2bfb8a 100644 --- a/arch/arm/mach-orion5x/common.h +++ b/arch/arm/mach-orion5x/common.h @@ -21,7 +21,7 @@ struct mv_sata_platform_data; #define ORION_MBUS_DEVBUS_BOOT_ATTR 0x0f #define ORION_MBUS_DEVBUS_TARGET(cs) 0x01 #define ORION_MBUS_DEVBUS_ATTR(cs) (~(1 << cs)) -#define ORION_MBUS_SRAM_TARGET 0x00 +#define ORION_MBUS_SRAM_TARGET 0x09 #define ORION_MBUS_SRAM_ATTR 0x00 /* diff --git a/arch/arm/mach-pxa/include/mach/hx4700.h b/arch/arm/mach-pxa/include/mach/hx4700.h index 8bc02913517c..0e1bb46264f9 100644 --- a/arch/arm/mach-pxa/include/mach/hx4700.h +++ b/arch/arm/mach-pxa/include/mach/hx4700.h @@ -14,6 +14,7 @@ #include <linux/gpio.h> #include <linux/mfd/asic3.h> +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */ #define HX4700_ASIC3_GPIO_BASE PXA_NR_BUILTIN_GPIO #define HX4700_EGPIO_BASE (HX4700_ASIC3_GPIO_BASE + ASIC3_NUM_GPIOS) diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 1f8fed94c2a4..ca8ecdee47d8 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -446,7 +446,6 @@ config CPU_32v5 config CPU_32v6 bool - select CPU_USE_DOMAINS if CPU_V6 && MMU select TLS_REG_EMUL if !CPU_32v6K && !MMU config CPU_32v6K @@ -671,7 +670,7 @@ config ARM_VIRT_EXT config SWP_EMULATE bool "Emulate SWP/SWPB instructions" - depends on !CPU_USE_DOMAINS && CPU_V7 + depends on CPU_V7 default y if SMP select HAVE_PROC_CPU if PROC_FS help diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 3815a8262af0..8c48c5c22a33 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -17,12 +17,6 @@ */ .align 5 ENTRY(v6_early_abort) -#ifdef CONFIG_CPU_V6 - sub r1, sp, #4 @ Get unused stack location - strex r0, r1, [r1] @ Clear the exclusive monitor -#elif defined(CONFIG_CPU_32v6K) - clrex -#endif mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR /* diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S index 703375277ba6..4812ad054214 100644 --- a/arch/arm/mm/abort-ev7.S +++ b/arch/arm/mm/abort-ev7.S @@ -13,12 +13,6 @@ */ .align 5 ENTRY(v7_early_abort) - /* - * The effect of data aborts on on the exclusive access monitor are - * UNPREDICTABLE. Do a CLREX to clear the state - */ - clrex - mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 924036473b16..d301662b7b32 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -40,6 +40,7 @@ * This code is not portable to processors with late data abort handling. */ #define CODING_BITS(i) (i & 0x0e000000) +#define COND_BITS(i) (i & 0xf0000000) #define LDST_I_BIT(i) (i & (1 << 26)) /* Immediate constant */ #define LDST_P_BIT(i) (i & (1 << 24)) /* Preindex */ @@ -817,6 +818,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) break; case 0x04000000: /* ldr or str immediate */ + if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */ + goto bad; offset.un = OFFSET_BITS(instr); handler = do_alignment_ldrstr; break; diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 54ee6163c181..66781bf34077 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -56,8 +56,3 @@ int pmd_huge(pmd_t pmd) { return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } - -int pmd_huge_support(void) -{ - return 1; -} diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 8e0e52eb76b5..d7a0ee898d24 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -25,6 +25,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, pr_warning("Failed to allocate identity pmd.\n"); return; } + /* + * Copy the original PMD to ensure that the PMD entries for + * the kernel image are preserved. + */ + if (!pud_none(*pud)) + memcpy(pmd, pmd_offset(pud, 0), + PTRS_PER_PMD * sizeof(pmd_t)); pud_populate(&init_mm, pud, pmd); pmd += pmd_index(addr); } else diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index a623cb3ad012..f15c22e8bcd5 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -516,6 +516,16 @@ static void __init build_mem_type_table(void) s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2; /* + * We don't use domains on ARMv6 (since this causes problems with + * v6/v7 kernels), so we must use a separate memory type for user + * r/o, kernel r/w to map the vectors page. + */ +#ifndef CONFIG_ARM_LPAE + if (cpu_arch == CPU_ARCH_ARMv6) + vecs_pgprot |= L_PTE_MT_VECTORS; +#endif + + /* * ARMv6 and above have extended page tables. */ if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) { @@ -1426,8 +1436,8 @@ void __init early_paging_init(const struct machine_desc *mdesc, return; /* remap kernel code and data */ - map_start = init_mm.start_code; - map_end = init_mm.brk; + map_start = init_mm.start_code & PMD_MASK; + map_end = ALIGN(init_mm.brk, PMD_SIZE); /* get a handle on things... */ pgd0 = pgd_offset_k(0); @@ -1462,7 +1472,7 @@ void __init early_paging_init(const struct machine_desc *mdesc, } /* remap pmds for kernel mapping */ - phys = __pa(map_start) & PMD_MASK; + phys = __pa(map_start); do { *pmdk++ = __pmd(phys | pmdprot); phys += PMD_SIZE; diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index e3c48a3fe063..ee1d80593958 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -112,13 +112,9 @@ * 100x 1 0 1 r/o no acc * 10x0 1 0 1 r/o no acc * 1011 0 0 1 r/w no acc - * 110x 0 1 0 r/w r/o - * 11x0 0 1 0 r/w r/o - * 1111 0 1 1 r/w r/w - * - * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed: * 110x 1 1 1 r/o r/o * 11x0 1 1 1 r/o r/o + * 1111 0 1 1 r/w r/w */ .macro armv6_mt_table pfx \pfx\()_mt_table: @@ -137,7 +133,7 @@ .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED .long 0x00 @ unused .long 0x00 @ unused - .long 0x00 @ unused + .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS .endm .macro armv6_set_pte_ext pfx @@ -158,24 +154,21 @@ tst r1, #L_PTE_USER orrne r3, r3, #PTE_EXT_AP1 -#ifdef CONFIG_CPU_USE_DOMAINS - @ allow kernel read/write access to read-only user pages tstne r3, #PTE_EXT_APX - bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 -#endif + + @ user read-only -> kernel read-only + bicne r3, r3, #PTE_EXT_AP0 tst r1, #L_PTE_XN orrne r3, r3, #PTE_EXT_XN - orr r3, r3, r2 + eor r3, r3, r2 tst r1, #L_PTE_YOUNG tstne r1, #L_PTE_PRESENT moveq r3, #0 -#ifndef CONFIG_CPU_USE_DOMAINS tstne r1, #L_PTE_NONE movne r3, #0 -#endif str r3, [r0] mcr p15, 0, r0, c7, c10, 1 @ flush_pte diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index bdd3be4be77a..1f52915f2b28 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -90,21 +90,14 @@ ENTRY(cpu_v7_set_pte_ext) tst r1, #L_PTE_USER orrne r3, r3, #PTE_EXT_AP1 -#ifdef CONFIG_CPU_USE_DOMAINS - @ allow kernel read/write access to read-only user pages - tstne r3, #PTE_EXT_APX - bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 -#endif tst r1, #L_PTE_XN orrne r3, r3, #PTE_EXT_XN tst r1, #L_PTE_YOUNG tstne r1, #L_PTE_VALID -#ifndef CONFIG_CPU_USE_DOMAINS eorne r1, r1, #L_PTE_NONE tstne r1, #L_PTE_NONE -#endif moveq r3, #0 ARM( str r3, [r0, #2048]! ) diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 01a719e18bb0..22e3ad63500c 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -64,6 +64,14 @@ ENTRY(cpu_v7_switch_mm) mov pc, lr ENDPROC(cpu_v7_switch_mm) +#ifdef __ARMEB__ +#define rl r3 +#define rh r2 +#else +#define rl r2 +#define rh r3 +#endif + /* * cpu_v7_set_pte_ext(ptep, pte) * @@ -73,13 +81,13 @@ ENDPROC(cpu_v7_switch_mm) */ ENTRY(cpu_v7_set_pte_ext) #ifdef CONFIG_MMU - tst r2, #L_PTE_VALID + tst rl, #L_PTE_VALID beq 1f - tst r3, #1 << (57 - 32) @ L_PTE_NONE - bicne r2, #L_PTE_VALID + tst rh, #1 << (57 - 32) @ L_PTE_NONE + bicne rl, #L_PTE_VALID bne 1f - tst r3, #1 << (55 - 32) @ L_PTE_DIRTY - orreq r2, #L_PTE_RDONLY + tst rh, #1 << (55 - 32) @ L_PTE_DIRTY + orreq rl, #L_PTE_RDONLY 1: strd r2, r3, [r0] ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 27bbcfc7202a..65b788410bd9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -2,6 +2,7 @@ config ARM64 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_COMPAT_IPC_PARSE_VERSION diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index fda2704b3f9f..e72289a97367 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -37,8 +37,8 @@ typedef s32 compat_ssize_t; typedef s32 compat_time_t; typedef s32 compat_clock_t; typedef s32 compat_pid_t; -typedef u32 __compat_uid_t; -typedef u32 __compat_gid_t; +typedef u16 __compat_uid_t; +typedef u16 __compat_gid_t; typedef u16 __compat_uid16_t; typedef u16 __compat_gid16_t; typedef u32 __compat_uid32_t; diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index fd0c0c0e447a..064d3525f260 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -26,8 +26,6 @@ #include <xen/xen.h> #include <asm/xen/hypervisor.h> -#define ARCH_HAS_DMA_GET_REQUIRED_MASK - #define DMA_ERROR_CODE (~(dma_addr_t)0) extern struct dma_map_ops *dma_ops; diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index d064047612b1..52b484b6aa1a 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -79,7 +79,6 @@ static inline void decode_ctrl_reg(u32 reg, */ #define ARM_MAX_BRP 16 #define ARM_MAX_WRP 16 -#define ARM_MAX_HBP_SLOTS (ARM_MAX_BRP + ARM_MAX_WRP) /* Virtual debug register bases. */ #define AARCH64_DBG_REG_BVR 0 diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 9dc5dc39fded..11ad59b856c6 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -56,6 +56,8 @@ #define TASK_SIZE_32 UL(0x100000000) #define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) +#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \ + TASK_SIZE_32 : TASK_SIZE_64) #else #define TASK_SIZE TASK_SIZE_64 #endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index aa3917c8b623..acb17e0d5e24 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -199,7 +199,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { if (pte_valid_user(pte)) { - if (pte_exec(pte)) + if (!pte_special(pte) && pte_exec(pte)) __sync_icache_dcache(pte, addr); if (pte_dirty(pte) && pte_write(pte)) pte_val(pte) &= ~PTE_RDONLY; @@ -286,11 +286,11 @@ static inline int has_transparent_hugepage(void) * Mark the prot value as uncacheable and unbufferable. */ #define pgprot_noncached(prot) \ - __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE)) + __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN) #define pgprot_writecombine(prot) \ - __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC)) + __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define pgprot_dmacoherent(prot) \ - __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC)) + __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index bb8eb8a78e67..faa0e1ce59df 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -404,7 +404,7 @@ __SYSCALL(379, sys_finit_module) __SYSCALL(380, sys_sched_setattr) __SYSCALL(381, sys_sched_getattr) -#define __NR_compat_syscalls 379 +#define __NR_compat_syscalls 382 /* * Compat syscall numbers used by the AArch64 kernel. diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 39ac630d83de..a8e4bdbbb4b8 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -275,7 +275,6 @@ el1_sp_pc: * Stack or PC alignment exception handling */ mrs x0, far_el1 - mov x1, x25 mov x2, sp b do_sp_pc_abort el1_undef: diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 473e5dbf8f39..dfa6e3e74fdd 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -105,7 +105,7 @@ static bool migrate_one_irq(struct irq_desc *desc) c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 1c0a9be2ffa8..6e7e579c629d 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -187,9 +187,27 @@ void exit_thread(void) { } +static void tls_thread_flush(void) +{ + asm ("msr tpidr_el0, xzr"); + + if (is_compat_task()) { + current->thread.tp_value = 0; + + /* + * We need to ensure ordering between the shadow state and the + * hardware state, so that we don't corrupt the hardware state + * with a stale shadow state during context switch. + */ + barrier(); + asm ("msr tpidrro_el0, xzr"); + } +} + void flush_thread(void) { fpsimd_flush_thread(); + tls_thread_flush(); flush_ptrace_hw_breakpoint(current); } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6a8928bba03c..b1269dac1289 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -81,7 +81,8 @@ static void ptrace_hbptriggered(struct perf_event *bp, break; } } - for (i = ARM_MAX_BRP; i < ARM_MAX_HBP_SLOTS && !bp; ++i) { + + for (i = 0; i < ARM_MAX_WRP; ++i) { if (current->thread.debug.hbp_watch[i] == bp) { info.si_errno = -((i << 1) + 1); break; @@ -650,11 +651,16 @@ static int compat_gpr_get(struct task_struct *target, reg = task_pt_regs(target)->regs[idx]; } - ret = copy_to_user(ubuf, ®, sizeof(reg)); - if (ret) - break; + if (kbuf) { + memcpy(kbuf, ®, sizeof(reg)); + kbuf += sizeof(reg); + } else { + ret = copy_to_user(ubuf, ®, sizeof(reg)); + if (ret) + break; - ubuf += sizeof(reg); + ubuf += sizeof(reg); + } } return ret; @@ -684,11 +690,16 @@ static int compat_gpr_set(struct task_struct *target, unsigned int idx = start + i; compat_ulong_t reg; - ret = copy_from_user(®, ubuf, sizeof(reg)); - if (ret) - return ret; + if (kbuf) { + memcpy(®, kbuf, sizeof(reg)); + kbuf += sizeof(reg); + } else { + ret = copy_from_user(®, ubuf, sizeof(reg)); + if (ret) + return ret; - ubuf += sizeof(reg); + ubuf += sizeof(reg); + } switch (idx) { case 15: @@ -821,6 +832,7 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t val) { int ret; + mm_segment_t old_fs = get_fs(); if (off & 3 || off >= COMPAT_USER_SZ) return -EIO; @@ -828,10 +840,13 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, if (off >= sizeof(compat_elf_gregset_t)) return 0; + set_fs(KERNEL_DS); ret = copy_regset_from_user(tsk, &user_aarch32_view, REGSET_COMPAT_GPR, off, sizeof(compat_ulong_t), &val); + set_fs(old_fs); + return ret; } diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 26e9c4eeaba8..78039927c807 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -79,6 +79,12 @@ long compat_arm_syscall(struct pt_regs *regs) case __ARM_NR_compat_set_tls: current->thread.tp_value = regs->regs[0]; + + /* + * Protect against register corruption from context switch. + * See comment in tls_thread_flush. + */ + barrier(); asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0])); return 0; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 7bc41eab4c64..fd9aeba99683 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -62,6 +62,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) else kvm_vcpu_block(vcpu); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; } diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 2b0244d65c16..12e26f358c31 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -74,6 +74,10 @@ __do_hyp_init: msr mair_el2, x4 isb + /* Invalidate the stale TLBs from Bootloader */ + tlbi alle2 + dsb sy + mrs x4, sctlr_el2 and x4, x4, #SCTLR_EL2_EE // preserve endianness of EL2 ldr x5, =SCTLR_EL2_FLAGS diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index e4193e3adc7f..0d64089d28b5 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -79,7 +79,8 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) return; if (!test_and_set_bit(PG_dcache_clean, &page->flags)) { - __flush_dcache_area(page_address(page), PAGE_SIZE); + __flush_dcache_area(page_address(page), + PAGE_SIZE << compound_order(page)); __flush_icache_all(); } else if (icache_is_aivivt()) { __flush_icache_all(); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 5e9aec358306..023747bf4dd7 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -51,12 +51,11 @@ int pmd_huge(pmd_t pmd) int pud_huge(pud_t pud) { +#ifndef __PAGETABLE_PMD_FOLDED return !(pud_val(pud) & PUD_TABLE_BIT); -} - -int pmd_huge_support(void) -{ - return 1; +#else + return 0; +#endif } static __init int setup_hugepagesz(char *opt) diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 68232db98baa..76069c18ee42 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -114,11 +114,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index dbdd2231c75d..b2e322939256 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -17,6 +17,7 @@ config M68K select FPU if MMU select ARCH_WANT_IPC_PARSE_VERSION select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE + select HAVE_FUTEX_CMPXCHG if MMU && FUTEX select HAVE_MOD_ARCH_SPECIFIC select MODULES_USE_ELF_REL select MODULES_USE_ELF_RELA diff --git a/arch/m68k/mm/hwtest.c b/arch/m68k/mm/hwtest.c index 2c7dde3c6430..2a5259fd23eb 100644 --- a/arch/m68k/mm/hwtest.c +++ b/arch/m68k/mm/hwtest.c @@ -28,9 +28,11 @@ int hwreg_present( volatile void *regp ) { int ret = 0; + unsigned long flags; long save_sp, save_vbr; long tmp_vectors[3]; + local_irq_save(flags); __asm__ __volatile__ ( "movec %/vbr,%2\n\t" "movel #Lberr1,%4@(8)\n\t" @@ -46,6 +48,7 @@ int hwreg_present( volatile void *regp ) : "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr) : "a" (regp), "a" (tmp_vectors) ); + local_irq_restore(flags); return( ret ); } @@ -58,9 +61,11 @@ EXPORT_SYMBOL(hwreg_present); int hwreg_write( volatile void *regp, unsigned short val ) { int ret; + unsigned long flags; long save_sp, save_vbr; long tmp_vectors[3]; + local_irq_save(flags); __asm__ __volatile__ ( "movec %/vbr,%2\n\t" "movel #Lberr2,%4@(8)\n\t" @@ -78,6 +83,7 @@ int hwreg_write( volatile void *regp, unsigned short val ) : "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr) : "a" (regp), "a" (tmp_vectors), "g" (val) ); + local_irq_restore(flags); return( ret ); } diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h index 5d6b4b407dda..2d6f0de77325 100644 --- a/arch/metag/include/asm/barrier.h +++ b/arch/metag/include/asm/barrier.h @@ -15,6 +15,7 @@ static inline void wr_fence(void) volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_FENCE; barrier(); *flushptr = 0; + barrier(); } #else /* CONFIG_METAG_META21 */ @@ -35,6 +36,7 @@ static inline void wr_fence(void) *flushptr = 0; *flushptr = 0; *flushptr = 0; + barrier(); } #endif /* !CONFIG_METAG_META21 */ @@ -68,6 +70,7 @@ static inline void fence(void) volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_ATOMIC_UNLOCK; barrier(); *flushptr = 0; + barrier(); } #define smp_mb() fence() #define smp_rmb() fence() diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index f16477d1f571..a8a37477c66e 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -22,6 +22,8 @@ /* Add an extra page of padding at the top of the stack for the guard page. */ #define STACK_TOP (TASK_SIZE - PAGE_SIZE) #define STACK_TOP_MAX STACK_TOP +/* Maximum virtual space for stack */ +#define STACK_SIZE_MAX (CONFIG_MAX_STACK_SIZE_MB*1024*1024) /* This decides where the kernel will search for a free chunk of vm * space during mmap's. diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c index 042431509b56..3c52fa6d0f8e 100644 --- a/arch/metag/mm/hugetlbpage.c +++ b/arch/metag/mm/hugetlbpage.c @@ -110,11 +110,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c00c4ddf4514..5244cecf1e45 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/string.h> #include <asm/addrspace.h> diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index c2bb4f896ce7..3aa5b46b2d40 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -635,7 +635,7 @@ static void octeon_irq_cpu_offline_ciu(struct irq_data *data) cpumask_clear(&new_affinity); cpumask_set_cpu(cpumask_first(cpu_online_mask), &new_affinity); } - __irq_set_affinity_locked(data, &new_affinity); + irq_set_affinity_locked(data, &new_affinity, false); } static int octeon_irq_ciu_set_affinity(struct irq_data *data, diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 331b837cec57..270cb3c6c498 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -458,6 +458,18 @@ static void octeon_halt(void) octeon_kill_core(NULL); } +static char __read_mostly octeon_system_type[80]; + +static int __init init_octeon_system_type(void) +{ + snprintf(octeon_system_type, sizeof(octeon_system_type), "%s (%s)", + cvmx_board_type_to_string(octeon_bootinfo->board_type), + octeon_model_get_string(read_c0_prid())); + + return 0; +} +early_initcall(init_octeon_system_type); + /** * Return a string representing the system type * @@ -465,11 +477,7 @@ static void octeon_halt(void) */ const char *octeon_board_type_string(void) { - static char name[80]; - sprintf(name, "%s (%s)", - cvmx_board_type_to_string(octeon_bootinfo->board_type), - octeon_model_get_string(read_c0_prid())); - return name; + return octeon_system_type; } const char *get_system_type(void) diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h index 992aaba603b5..b463f2aa5a61 100644 --- a/arch/mips/include/asm/ftrace.h +++ b/arch/mips/include/asm/ftrace.h @@ -24,7 +24,7 @@ do { \ asm volatile ( \ "1: " load " %[tmp_dst], 0(%[tmp_src])\n" \ " li %[tmp_err], 0\n" \ - "2:\n" \ + "2: .insn\n" \ \ ".section .fixup, \"ax\"\n" \ "3: li %[tmp_err], 1\n" \ @@ -46,7 +46,7 @@ do { \ asm volatile ( \ "1: " store " %[tmp_src], 0(%[tmp_dst])\n"\ " li %[tmp_err], 0\n" \ - "2:\n" \ + "2: .insn\n" \ \ ".section .fixup, \"ax\"\n" \ "3: li %[tmp_err], 1\n" \ diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 7bba9da110af..6d019ca1bead 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -23,7 +23,7 @@ struct pt_regs { #ifdef CONFIG_32BIT /* Pad bytes for argument save space on the stack. */ - unsigned long pad0[6]; + unsigned long pad0[8]; #endif /* Saved main processor registers. */ diff --git a/arch/mips/include/asm/reg.h b/arch/mips/include/asm/reg.h index 910e71a12466..b8343ccbc989 100644 --- a/arch/mips/include/asm/reg.h +++ b/arch/mips/include/asm/reg.h @@ -12,116 +12,194 @@ #ifndef __ASM_MIPS_REG_H #define __ASM_MIPS_REG_H - -#if defined(CONFIG_32BIT) || defined(WANT_COMPAT_REG_H) - -#define EF_R0 6 -#define EF_R1 7 -#define EF_R2 8 -#define EF_R3 9 -#define EF_R4 10 -#define EF_R5 11 -#define EF_R6 12 -#define EF_R7 13 -#define EF_R8 14 -#define EF_R9 15 -#define EF_R10 16 -#define EF_R11 17 -#define EF_R12 18 -#define EF_R13 19 -#define EF_R14 20 -#define EF_R15 21 -#define EF_R16 22 -#define EF_R17 23 -#define EF_R18 24 -#define EF_R19 25 -#define EF_R20 26 -#define EF_R21 27 -#define EF_R22 28 -#define EF_R23 29 -#define EF_R24 30 -#define EF_R25 31 +#define MIPS32_EF_R0 6 +#define MIPS32_EF_R1 7 +#define MIPS32_EF_R2 8 +#define MIPS32_EF_R3 9 +#define MIPS32_EF_R4 10 +#define MIPS32_EF_R5 11 +#define MIPS32_EF_R6 12 +#define MIPS32_EF_R7 13 +#define MIPS32_EF_R8 14 +#define MIPS32_EF_R9 15 +#define MIPS32_EF_R10 16 +#define MIPS32_EF_R11 17 +#define MIPS32_EF_R12 18 +#define MIPS32_EF_R13 19 +#define MIPS32_EF_R14 20 +#define MIPS32_EF_R15 21 +#define MIPS32_EF_R16 22 +#define MIPS32_EF_R17 23 +#define MIPS32_EF_R18 24 +#define MIPS32_EF_R19 25 +#define MIPS32_EF_R20 26 +#define MIPS32_EF_R21 27 +#define MIPS32_EF_R22 28 +#define MIPS32_EF_R23 29 +#define MIPS32_EF_R24 30 +#define MIPS32_EF_R25 31 /* * k0/k1 unsaved */ -#define EF_R26 32 -#define EF_R27 33 +#define MIPS32_EF_R26 32 +#define MIPS32_EF_R27 33 -#define EF_R28 34 -#define EF_R29 35 -#define EF_R30 36 -#define EF_R31 37 +#define MIPS32_EF_R28 34 +#define MIPS32_EF_R29 35 +#define MIPS32_EF_R30 36 +#define MIPS32_EF_R31 37 /* * Saved special registers */ -#define EF_LO 38 -#define EF_HI 39 - -#define EF_CP0_EPC 40 -#define EF_CP0_BADVADDR 41 -#define EF_CP0_STATUS 42 -#define EF_CP0_CAUSE 43 -#define EF_UNUSED0 44 - -#define EF_SIZE 180 - -#endif - -#if defined(CONFIG_64BIT) && !defined(WANT_COMPAT_REG_H) - -#define EF_R0 0 -#define EF_R1 1 -#define EF_R2 2 -#define EF_R3 3 -#define EF_R4 4 -#define EF_R5 5 -#define EF_R6 6 -#define EF_R7 7 -#define EF_R8 8 -#define EF_R9 9 -#define EF_R10 10 -#define EF_R11 11 -#define EF_R12 12 -#define EF_R13 13 -#define EF_R14 14 -#define EF_R15 15 -#define EF_R16 16 -#define EF_R17 17 -#define EF_R18 18 -#define EF_R19 19 -#define EF_R20 20 -#define EF_R21 21 -#define EF_R22 22 -#define EF_R23 23 -#define EF_R24 24 -#define EF_R25 25 +#define MIPS32_EF_LO 38 +#define MIPS32_EF_HI 39 + +#define MIPS32_EF_CP0_EPC 40 +#define MIPS32_EF_CP0_BADVADDR 41 +#define MIPS32_EF_CP0_STATUS 42 +#define MIPS32_EF_CP0_CAUSE 43 +#define MIPS32_EF_UNUSED0 44 + +#define MIPS32_EF_SIZE 180 + +#define MIPS64_EF_R0 0 +#define MIPS64_EF_R1 1 +#define MIPS64_EF_R2 2 +#define MIPS64_EF_R3 3 +#define MIPS64_EF_R4 4 +#define MIPS64_EF_R5 5 +#define MIPS64_EF_R6 6 +#define MIPS64_EF_R7 7 +#define MIPS64_EF_R8 8 +#define MIPS64_EF_R9 9 +#define MIPS64_EF_R10 10 +#define MIPS64_EF_R11 11 +#define MIPS64_EF_R12 12 +#define MIPS64_EF_R13 13 +#define MIPS64_EF_R14 14 +#define MIPS64_EF_R15 15 +#define MIPS64_EF_R16 16 +#define MIPS64_EF_R17 17 +#define MIPS64_EF_R18 18 +#define MIPS64_EF_R19 19 +#define MIPS64_EF_R20 20 +#define MIPS64_EF_R21 21 +#define MIPS64_EF_R22 22 +#define MIPS64_EF_R23 23 +#define MIPS64_EF_R24 24 +#define MIPS64_EF_R25 25 /* * k0/k1 unsaved */ -#define EF_R26 26 -#define EF_R27 27 +#define MIPS64_EF_R26 26 +#define MIPS64_EF_R27 27 -#define EF_R28 28 -#define EF_R29 29 -#define EF_R30 30 -#define EF_R31 31 +#define MIPS64_EF_R28 28 +#define MIPS64_EF_R29 29 +#define MIPS64_EF_R30 30 +#define MIPS64_EF_R31 31 /* * Saved special registers */ -#define EF_LO 32 -#define EF_HI 33 - -#define EF_CP0_EPC 34 -#define EF_CP0_BADVADDR 35 -#define EF_CP0_STATUS 36 -#define EF_CP0_CAUSE 37 - -#define EF_SIZE 304 /* size in bytes */ +#define MIPS64_EF_LO 32 +#define MIPS64_EF_HI 33 + +#define MIPS64_EF_CP0_EPC 34 +#define MIPS64_EF_CP0_BADVADDR 35 +#define MIPS64_EF_CP0_STATUS 36 +#define MIPS64_EF_CP0_CAUSE 37 + +#define MIPS64_EF_SIZE 304 /* size in bytes */ + +#if defined(CONFIG_32BIT) + +#define EF_R0 MIPS32_EF_R0 +#define EF_R1 MIPS32_EF_R1 +#define EF_R2 MIPS32_EF_R2 +#define EF_R3 MIPS32_EF_R3 +#define EF_R4 MIPS32_EF_R4 +#define EF_R5 MIPS32_EF_R5 +#define EF_R6 MIPS32_EF_R6 +#define EF_R7 MIPS32_EF_R7 +#define EF_R8 MIPS32_EF_R8 +#define EF_R9 MIPS32_EF_R9 +#define EF_R10 MIPS32_EF_R10 +#define EF_R11 MIPS32_EF_R11 +#define EF_R12 MIPS32_EF_R12 +#define EF_R13 MIPS32_EF_R13 +#define EF_R14 MIPS32_EF_R14 +#define EF_R15 MIPS32_EF_R15 +#define EF_R16 MIPS32_EF_R16 +#define EF_R17 MIPS32_EF_R17 +#define EF_R18 MIPS32_EF_R18 +#define EF_R19 MIPS32_EF_R19 +#define EF_R20 MIPS32_EF_R20 +#define EF_R21 MIPS32_EF_R21 +#define EF_R22 MIPS32_EF_R22 +#define EF_R23 MIPS32_EF_R23 +#define EF_R24 MIPS32_EF_R24 +#define EF_R25 MIPS32_EF_R25 +#define EF_R26 MIPS32_EF_R26 +#define EF_R27 MIPS32_EF_R27 +#define EF_R28 MIPS32_EF_R28 +#define EF_R29 MIPS32_EF_R29 +#define EF_R30 MIPS32_EF_R30 +#define EF_R31 MIPS32_EF_R31 +#define EF_LO MIPS32_EF_LO +#define EF_HI MIPS32_EF_HI +#define EF_CP0_EPC MIPS32_EF_CP0_EPC +#define EF_CP0_BADVADDR MIPS32_EF_CP0_BADVADDR +#define EF_CP0_STATUS MIPS32_EF_CP0_STATUS +#define EF_CP0_CAUSE MIPS32_EF_CP0_CAUSE +#define EF_UNUSED0 MIPS32_EF_UNUSED0 +#define EF_SIZE MIPS32_EF_SIZE + +#elif defined(CONFIG_64BIT) + +#define EF_R0 MIPS64_EF_R0 +#define EF_R1 MIPS64_EF_R1 +#define EF_R2 MIPS64_EF_R2 +#define EF_R3 MIPS64_EF_R3 +#define EF_R4 MIPS64_EF_R4 +#define EF_R5 MIPS64_EF_R5 +#define EF_R6 MIPS64_EF_R6 +#define EF_R7 MIPS64_EF_R7 +#define EF_R8 MIPS64_EF_R8 +#define EF_R9 MIPS64_EF_R9 +#define EF_R10 MIPS64_EF_R10 +#define EF_R11 MIPS64_EF_R11 +#define EF_R12 MIPS64_EF_R12 +#define EF_R13 MIPS64_EF_R13 +#define EF_R14 MIPS64_EF_R14 +#define EF_R15 MIPS64_EF_R15 +#define EF_R16 MIPS64_EF_R16 +#define EF_R17 MIPS64_EF_R17 +#define EF_R18 MIPS64_EF_R18 +#define EF_R19 MIPS64_EF_R19 +#define EF_R20 MIPS64_EF_R20 +#define EF_R21 MIPS64_EF_R21 +#define EF_R22 MIPS64_EF_R22 +#define EF_R23 MIPS64_EF_R23 +#define EF_R24 MIPS64_EF_R24 +#define EF_R25 MIPS64_EF_R25 +#define EF_R26 MIPS64_EF_R26 +#define EF_R27 MIPS64_EF_R27 +#define EF_R28 MIPS64_EF_R28 +#define EF_R29 MIPS64_EF_R29 +#define EF_R30 MIPS64_EF_R30 +#define EF_R31 MIPS64_EF_R31 +#define EF_LO MIPS64_EF_LO +#define EF_HI MIPS64_EF_HI +#define EF_CP0_EPC MIPS64_EF_CP0_EPC +#define EF_CP0_BADVADDR MIPS64_EF_CP0_BADVADDR +#define EF_CP0_STATUS MIPS64_EF_CP0_STATUS +#define EF_CP0_CAUSE MIPS64_EF_CP0_CAUSE +#define EF_SIZE MIPS64_EF_SIZE #endif /* CONFIG_64BIT */ diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 24846f9053fe..e80ae50cae80 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -136,7 +136,8 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_WORK_SYSCALL_ENTRY (_TIF_NOHZ | _TIF_SYSCALL_TRACE | \ - _TIF_SYSCALL_AUDIT | _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT (_TIF_NOHZ | _TIF_SYSCALL_TRACE | \ diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 7faf5f2bee25..71df942fb77c 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -72,12 +72,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; #include <asm/processor.h> -/* - * When this file is selected, we are definitely running a 64bit kernel. - * So using the right regs define in asm/reg.h - */ -#define WANT_COMPAT_REG_H - /* These MUST be defined before elf.h gets included */ extern void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs); #define ELF_CORE_COPY_REGS(_dest, _regs) elf32_core_copy_regs(_dest, _regs); @@ -149,21 +143,21 @@ void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs) { int i; - for (i = 0; i < EF_R0; i++) + for (i = 0; i < MIPS32_EF_R0; i++) grp[i] = 0; - grp[EF_R0] = 0; + grp[MIPS32_EF_R0] = 0; for (i = 1; i <= 31; i++) - grp[EF_R0 + i] = (elf_greg_t) regs->regs[i]; - grp[EF_R26] = 0; - grp[EF_R27] = 0; - grp[EF_LO] = (elf_greg_t) regs->lo; - grp[EF_HI] = (elf_greg_t) regs->hi; - grp[EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc; - grp[EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr; - grp[EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status; - grp[EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause; -#ifdef EF_UNUSED0 - grp[EF_UNUSED0] = 0; + grp[MIPS32_EF_R0 + i] = (elf_greg_t) regs->regs[i]; + grp[MIPS32_EF_R26] = 0; + grp[MIPS32_EF_R27] = 0; + grp[MIPS32_EF_LO] = (elf_greg_t) regs->lo; + grp[MIPS32_EF_HI] = (elf_greg_t) regs->hi; + grp[MIPS32_EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc; + grp[MIPS32_EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr; + grp[MIPS32_EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status; + grp[MIPS32_EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause; +#ifdef MIPS32_EF_UNUSED0 + grp[MIPS32_EF_UNUSED0] = 0; #endif } diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 5b5ddb231f26..78f18436cdf2 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -255,11 +255,13 @@ static void __init gic_setup_intr(unsigned int intr, unsigned int cpu, /* Setup Intr to Pin mapping */ if (pin & GIC_MAP_TO_NMI_MSK) { + int i; + GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin); /* FIXME: hack to route NMI to all cpu's */ - for (cpu = 0; cpu < NR_CPUS; cpu += 32) { + for (i = 0; i < NR_CPUS; i += 32) { GICWRITE(GIC_REG_ADDR(SHARED, - GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)), + GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)), 0xffffffff); } } else { diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c index fab40f7d2e03..ac9facc08694 100644 --- a/arch/mips/kernel/irq-msc01.c +++ b/arch/mips/kernel/irq-msc01.c @@ -131,7 +131,7 @@ void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqma board_bind_eic_interrupt = &msc_bind_eic_interrupt; - for (; nirq >= 0; nirq--, imp++) { + for (; nirq > 0; nirq--, imp++) { int n = imp->im_irq; switch (imp->im_type) { diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index 539b6294b613..8f89ff4ed524 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -123,7 +123,11 @@ NESTED(_mcount, PT_SIZE, ra) nop #endif b ftrace_stub +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#else nop +#endif static_trace: MCOUNT_SAVE_REGS @@ -133,6 +137,9 @@ static_trace: move a1, AT /* arg2: parent's return address */ MCOUNT_RESTORE_REGS +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#endif .globl ftrace_stub ftrace_stub: RETURN_BACK @@ -177,6 +184,11 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra) jal prepare_ftrace_return nop MCOUNT_RESTORE_REGS +#ifndef CONFIG_DYNAMIC_FTRACE +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#endif +#endif RETURN_BACK END(ftrace_graph_caller) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 7da9b76db4d9..60f48febe762 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -170,6 +170,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) __get_user(fregs[i], i + (__u64 __user *) data); __get_user(child->thread.fpu.fcr31, data + 64); + child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; /* FIR may not be written. */ @@ -265,36 +266,160 @@ int ptrace_set_watch_regs(struct task_struct *child, /* regset get/set implementations */ -static int gpr_get(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) +#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32) + +static int gpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) { struct pt_regs *regs = task_pt_regs(target); + u32 uregs[ELF_NGREG] = {}; + unsigned i; - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - regs, 0, sizeof(*regs)); + for (i = MIPS32_EF_R1; i <= MIPS32_EF_R31; i++) { + /* k0/k1 are copied as zero. */ + if (i == MIPS32_EF_R26 || i == MIPS32_EF_R27) + continue; + + uregs[i] = regs->regs[i - MIPS32_EF_R0]; + } + + uregs[MIPS32_EF_LO] = regs->lo; + uregs[MIPS32_EF_HI] = regs->hi; + uregs[MIPS32_EF_CP0_EPC] = regs->cp0_epc; + uregs[MIPS32_EF_CP0_BADVADDR] = regs->cp0_badvaddr; + uregs[MIPS32_EF_CP0_STATUS] = regs->cp0_status; + uregs[MIPS32_EF_CP0_CAUSE] = regs->cp0_cause; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); } -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) +static int gpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) { - struct pt_regs newregs; - int ret; + struct pt_regs *regs = task_pt_regs(target); + u32 uregs[ELF_NGREG]; + unsigned start, num_regs, i; + int err; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &newregs, - 0, sizeof(newregs)); - if (ret) - return ret; + start = pos / sizeof(u32); + num_regs = count / sizeof(u32); - *task_pt_regs(target) = newregs; + if (start + num_regs > ELF_NGREG) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) { + /* + * Cast all values to signed here so that if this is a 64-bit + * kernel, the supplied 32-bit values will be sign extended. + */ + switch (i) { + case MIPS32_EF_R1 ... MIPS32_EF_R25: + /* k0/k1 are ignored. */ + case MIPS32_EF_R28 ... MIPS32_EF_R31: + regs->regs[i - MIPS32_EF_R0] = (s32)uregs[i]; + break; + case MIPS32_EF_LO: + regs->lo = (s32)uregs[i]; + break; + case MIPS32_EF_HI: + regs->hi = (s32)uregs[i]; + break; + case MIPS32_EF_CP0_EPC: + regs->cp0_epc = (s32)uregs[i]; + break; + } + } return 0; } +#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */ + +#ifdef CONFIG_64BIT + +static int gpr64_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct pt_regs *regs = task_pt_regs(target); + u64 uregs[ELF_NGREG] = {}; + unsigned i; + + for (i = MIPS64_EF_R1; i <= MIPS64_EF_R31; i++) { + /* k0/k1 are copied as zero. */ + if (i == MIPS64_EF_R26 || i == MIPS64_EF_R27) + continue; + + uregs[i] = regs->regs[i - MIPS64_EF_R0]; + } + + uregs[MIPS64_EF_LO] = regs->lo; + uregs[MIPS64_EF_HI] = regs->hi; + uregs[MIPS64_EF_CP0_EPC] = regs->cp0_epc; + uregs[MIPS64_EF_CP0_BADVADDR] = regs->cp0_badvaddr; + uregs[MIPS64_EF_CP0_STATUS] = regs->cp0_status; + uregs[MIPS64_EF_CP0_CAUSE] = regs->cp0_cause; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); +} + +static int gpr64_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct pt_regs *regs = task_pt_regs(target); + u64 uregs[ELF_NGREG]; + unsigned start, num_regs, i; + int err; + + start = pos / sizeof(u64); + num_regs = count / sizeof(u64); + + if (start + num_regs > ELF_NGREG) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0, + sizeof(uregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) { + switch (i) { + case MIPS64_EF_R1 ... MIPS64_EF_R25: + /* k0/k1 are ignored. */ + case MIPS64_EF_R28 ... MIPS64_EF_R31: + regs->regs[i - MIPS64_EF_R0] = uregs[i]; + break; + case MIPS64_EF_LO: + regs->lo = uregs[i]; + break; + case MIPS64_EF_HI: + regs->hi = uregs[i]; + break; + case MIPS64_EF_CP0_EPC: + regs->cp0_epc = uregs[i]; + break; + } + } + + return 0; +} + +#endif /* CONFIG_64BIT */ + static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, @@ -322,14 +447,16 @@ enum mips_regset { REGSET_FPR, }; +#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32) + static const struct user_regset mips_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = ELF_NGREG, .size = sizeof(unsigned int), .align = sizeof(unsigned int), - .get = gpr_get, - .set = gpr_set, + .get = gpr32_get, + .set = gpr32_set, }, [REGSET_FPR] = { .core_note_type = NT_PRFPREG, @@ -349,14 +476,18 @@ static const struct user_regset_view user_mips_view = { .n = ARRAY_SIZE(mips_regsets), }; +#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */ + +#ifdef CONFIG_64BIT + static const struct user_regset mips64_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = ELF_NGREG, .size = sizeof(unsigned long), .align = sizeof(unsigned long), - .get = gpr_get, - .set = gpr_set, + .get = gpr64_get, + .set = gpr64_set, }, [REGSET_FPR] = { .core_note_type = NT_PRFPREG, @@ -369,25 +500,26 @@ static const struct user_regset mips64_regsets[] = { }; static const struct user_regset_view user_mips64_view = { - .name = "mips", + .name = "mips64", .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI, .regsets = mips64_regsets, - .n = ARRAY_SIZE(mips_regsets), + .n = ARRAY_SIZE(mips64_regsets), }; +#endif /* CONFIG_64BIT */ + const struct user_regset_view *task_user_regset_view(struct task_struct *task) { #ifdef CONFIG_32BIT return &user_mips_view; -#endif - +#else #ifdef CONFIG_MIPS32_O32 - if (test_thread_flag(TIF_32BIT_REGS)) - return &user_mips_view; + if (test_tsk_thread_flag(task, TIF_32BIT_REGS)) + return &user_mips_view; #endif - return &user_mips64_view; +#endif } long arch_ptrace(struct task_struct *child, long request, @@ -593,7 +725,7 @@ long arch_ptrace(struct task_struct *child, long request, break; #endif case FPC_CSR: - child->thread.fpu.fcr31 = data; + child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X; break; case DSP_BASE ... DSP_BASE + 5: { dspreg_t *dregs; diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index e0b499694d18..81e6ae0220bc 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1429,7 +1429,7 @@ asmlinkage void cache_parity_error(void) reg_val & (1<<30) ? "secondary" : "primary", reg_val & (1<<31) ? "data" : "insn"); if (cpu_has_mips_r2 && - ((current_cpu_data.processor_id && 0xff0000) == PRID_COMP_MIPS)) { + ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) { pr_err("Error bits: %s%s%s%s%s%s%s%s\n", reg_val & (1<<29) ? "ED " : "", reg_val & (1<<28) ? "ET " : "", @@ -1469,7 +1469,7 @@ asmlinkage void do_ftlb(void) /* For the moment, report the problem and hang. */ if (cpu_has_mips_r2 && - ((current_cpu_data.processor_id && 0xff0000) == PRID_COMP_MIPS)) { + ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) { pr_err("FTLB error exception, cp0_ecc=0x%08x:\n", read_c0_ecc()); pr_err("cp0_errorepc == %0*lx\n", field, read_c0_errorepc()); diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index c369a5d35527..b897dde93e7a 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -605,7 +605,6 @@ static void emulate_load_store_insn(struct pt_regs *regs, case sdc1_op: die_if_kernel("Unaligned FP access in kernel code", regs); BUG_ON(!used_math()); - BUG_ON(!is_fpu_owner()); lose_fpu(1); /* Save FPU state for the emulator. */ res = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index da5186fbd77a..3e0ff8d0fbf9 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -149,9 +149,7 @@ void kvm_mips_free_vcpus(struct kvm *kvm) if (kvm->arch.guest_pmap[i] != KVM_INVALID_PAGE) kvm_mips_release_pfn_clean(kvm->arch.guest_pmap[i]); } - - if (kvm->arch.guest_pmap) - kfree(kvm->arch.guest_pmap); + kfree(kvm->arch.guest_pmap); kvm_for_each_vcpu(i, vcpu, kvm) { kvm_arch_vcpu_free(vcpu); @@ -304,7 +302,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) if (cpu_has_veic || cpu_has_vint) { size = 0x200 + VECTORSPACING * 64; } else { - size = 0x200; + size = 0x4000; } /* Save Linux EBASE */ @@ -389,12 +387,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvm_mips_dump_stats(vcpu); - if (vcpu->arch.guest_ebase) - kfree(vcpu->arch.guest_ebase); - - if (vcpu->arch.kseg0_commpage) - kfree(vcpu->arch.kseg0_commpage); - + kfree(vcpu->arch.guest_ebase); + kfree(vcpu->arch.kseg0_commpage); + kfree(vcpu); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c index 4b6274b47f33..e75ef8219caf 100644 --- a/arch/mips/kvm/kvm_mips_emul.c +++ b/arch/mips/kvm/kvm_mips_emul.c @@ -1571,17 +1571,17 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc, arch->gprs[rt] = kvm_read_c0_guest_userlocal(cop0); #else /* UserLocal not implemented */ - er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu); + er = EMULATE_FAIL; #endif break; default: - printk("RDHWR not supported\n"); + kvm_debug("RDHWR %#x not supported @ %p\n", rd, opc); er = EMULATE_FAIL; break; } } else { - printk("Emulate RI not supported @ %p: %#x\n", opc, inst); + kvm_debug("Emulate RI not supported @ %p: %#x\n", opc, inst); er = EMULATE_FAIL; } @@ -1590,6 +1590,7 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc, */ if (er == EMULATE_FAIL) { vcpu->arch.pc = curr_pc; + er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu); } return er; } diff --git a/arch/mips/lantiq/dts/easy50712.dts b/arch/mips/lantiq/dts/easy50712.dts index fac1f5b178eb..143b8a37b5e4 100644 --- a/arch/mips/lantiq/dts/easy50712.dts +++ b/arch/mips/lantiq/dts/easy50712.dts @@ -8,6 +8,7 @@ }; memory@0 { + device_type = "memory"; reg = <0x0 0x2000000>; }; diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c index aed32b88576c..7d8c9cce3009 100644 --- a/arch/mips/loongson/lemote-2f/clock.c +++ b/arch/mips/loongson/lemote-2f/clock.c @@ -91,6 +91,7 @@ EXPORT_SYMBOL(clk_put); int clk_set_rate(struct clk *clk, unsigned long rate) { + unsigned int rate_khz = rate / 1000; int ret = 0; int regval; int i; @@ -111,10 +112,10 @@ int clk_set_rate(struct clk *clk, unsigned long rate) if (loongson2_clockmod_table[i].frequency == CPUFREQ_ENTRY_INVALID) continue; - if (rate == loongson2_clockmod_table[i].frequency) + if (rate_khz == loongson2_clockmod_table[i].frequency) break; } - if (rate != loongson2_clockmod_table[i].frequency) + if (rate_khz != loongson2_clockmod_table[i].frequency) return -ENOTSUPP; clk->rate = rate; diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c index 77e0ae036e7c..4ec8ee10d371 100644 --- a/arch/mips/mm/hugetlbpage.c +++ b/arch/mips/mm/hugetlbpage.c @@ -84,11 +84,6 @@ int pud_huge(pud_t pud) return (pud_val(pud) & _PAGE_HUGE) != 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index b234b1b5ccad..dd012c599ad1 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1057,6 +1057,7 @@ static void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep) struct mips_huge_tlb_info { int huge_pte; int restore_scratch; + bool need_reload_pte; }; static struct mips_huge_tlb_info @@ -1071,6 +1072,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l, rv.huge_pte = scratch; rv.restore_scratch = 0; + rv.need_reload_pte = false; if (check_for_high_segbits) { UASM_i_MFC0(p, tmp, C0_BADVADDR); @@ -1259,6 +1261,7 @@ static void build_r4000_tlb_refill_handler(void) } else { htlb_info.huge_pte = K0; htlb_info.restore_scratch = 0; + htlb_info.need_reload_pte = true; vmalloc_mode = refill_noscratch; /* * create the plain linear handler @@ -1295,6 +1298,8 @@ static void build_r4000_tlb_refill_handler(void) } #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT uasm_l_tlb_huge_update(&l, p); + if (htlb_info.need_reload_pte) + UASM_i_LW(&p, htlb_info.huge_pte, 0, K1); build_huge_update_entries(&p, htlb_info.huge_pte, K1); build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random, htlb_info.restore_scratch); diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S index 7e0277a1048f..32a7c828f073 100644 --- a/arch/mips/power/hibernate.S +++ b/arch/mips/power/hibernate.S @@ -43,6 +43,7 @@ LEAF(swsusp_arch_resume) bne t1, t3, 1b PTR_L t0, PBE_NEXT(t0) bnez t0, 0b + jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */ PTR_LA t0, saved_regs PTR_L ra, PT_R31(t0) PTR_L sp, PT_R29(t0) diff --git a/arch/mips/ralink/dts/mt7620a_eval.dts b/arch/mips/ralink/dts/mt7620a_eval.dts index 35eb874ab7f1..709f58132f5c 100644 --- a/arch/mips/ralink/dts/mt7620a_eval.dts +++ b/arch/mips/ralink/dts/mt7620a_eval.dts @@ -7,6 +7,7 @@ model = "Ralink MT7620A evaluation board"; memory@0 { + device_type = "memory"; reg = <0x0 0x2000000>; }; diff --git a/arch/mips/ralink/dts/rt2880_eval.dts b/arch/mips/ralink/dts/rt2880_eval.dts index 322d7002595b..0a685db093d4 100644 --- a/arch/mips/ralink/dts/rt2880_eval.dts +++ b/arch/mips/ralink/dts/rt2880_eval.dts @@ -7,6 +7,7 @@ model = "Ralink RT2880 evaluation board"; memory@0 { + device_type = "memory"; reg = <0x8000000 0x2000000>; }; diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/ralink/dts/rt3052_eval.dts index 0ac73ea28198..ec9e9a035541 100644 --- a/arch/mips/ralink/dts/rt3052_eval.dts +++ b/arch/mips/ralink/dts/rt3052_eval.dts @@ -7,6 +7,7 @@ model = "Ralink RT3052 evaluation board"; memory@0 { + device_type = "memory"; reg = <0x0 0x2000000>; }; diff --git a/arch/mips/ralink/dts/rt3883_eval.dts b/arch/mips/ralink/dts/rt3883_eval.dts index 2fa6b330bf4f..e8df21a5d10d 100644 --- a/arch/mips/ralink/dts/rt3883_eval.dts +++ b/arch/mips/ralink/dts/rt3883_eval.dts @@ -7,6 +7,7 @@ model = "Ralink RT3883 evaluation board"; memory@0 { + device_type = "memory"; reg = <0x0 0x2000000>; }; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index bb2a8ec440e7..a8f4a70c0742 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -22,6 +22,7 @@ config PARISC select GENERIC_SMP_IDLE_THREAD select GENERIC_STRNCPY_FROM_USER select SYSCTL_ARCH_UNALIGN_ALLOW + select SYSCTL_EXCEPTION_TRACE select HAVE_MOD_ARCH_SPECIFIC select VIRT_TO_BUS select MODULES_USE_ELF_RELA diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 7187664034c3..5db8882f732c 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -48,7 +48,12 @@ cflags-y := -pipe # These flags should be implied by an hppa-linux configuration, but they # are not in gcc 3.2. -cflags-y += -mno-space-regs -mfast-indirect-calls +cflags-y += -mno-space-regs + +# -mfast-indirect-calls is only relevant for 32-bit kernels. +ifndef CONFIG_64BIT +cflags-y += -mfast-indirect-calls +endif # Currently we save and restore fpregs on all kernel entry/interruption paths. # If that gets optimized, we might need to disable the use of fpregs in the diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 198a86feb574..d951c9681ab3 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -55,6 +55,11 @@ #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX DEFAULT_TASK_SIZE +/* Allow bigger stacks for 64-bit processes */ +#define STACK_SIZE_MAX (USER_WIDE_MODE \ + ? (1 << 30) /* 1 GB */ \ + : (CONFIG_MAX_STACK_SIZE_MB*1024*1024)) + #endif #ifndef __ASSEMBLY__ diff --git a/arch/parisc/include/asm/shmparam.h b/arch/parisc/include/asm/shmparam.h index 628ddc22faa8..afe1300ab667 100644 --- a/arch/parisc/include/asm/shmparam.h +++ b/arch/parisc/include/asm/shmparam.h @@ -1,8 +1,7 @@ #ifndef _ASMPARISC_SHMPARAM_H #define _ASMPARISC_SHMPARAM_H -#define __ARCH_FORCE_SHMLBA 1 - -#define SHMLBA 0x00400000 /* attach addr needs to be 4 Mb aligned */ +#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */ +#define SHM_COLOUR 0x00400000 /* shared mappings colouring */ #endif /* _ASMPARISC_SHMPARAM_H */ diff --git a/arch/parisc/include/uapi/asm/resource.h b/arch/parisc/include/uapi/asm/resource.h index 8b06343b62ed..090483c47dbb 100644 --- a/arch/parisc/include/uapi/asm/resource.h +++ b/arch/parisc/include/uapi/asm/resource.h @@ -1,7 +1,6 @@ #ifndef _ASM_PARISC_RESOURCE_H #define _ASM_PARISC_RESOURCE_H -#define _STK_LIM_MAX 10 * _STK_LIM #include <asm-generic/resource.h> #endif diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h index a2fa297196bc..f5645d6a89f2 100644 --- a/arch/parisc/include/uapi/asm/signal.h +++ b/arch/parisc/include/uapi/asm/signal.h @@ -69,8 +69,6 @@ #define SA_NOMASK SA_NODEFER #define SA_ONESHOT SA_RESETHAND -#define SA_RESTORER 0x04000000 /* obsolete -- ignored */ - #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index a6ffc775a9f8..f6448c7c62b5 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -323,7 +323,8 @@ void flush_dcache_page(struct page *page) * specifically accesses it, of course) */ flush_tlb_page(mpnt, addr); - if (old_addr == 0 || (old_addr & (SHMLBA - 1)) != (addr & (SHMLBA - 1))) { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { __flush_cache_page(mpnt, addr, page_to_phys(page)); if (old_addr) printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? (char *)mpnt->vm_file->f_path.dentry->d_name.name : "(null)"); diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c index 608716f8496b..af3bc359dc70 100644 --- a/arch/parisc/kernel/hardware.c +++ b/arch/parisc/kernel/hardware.c @@ -1210,7 +1210,8 @@ static struct hp_hardware hp_hardware_list[] = { {HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"}, {HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"}, {HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"}, - {HPHW_FIO, 0x076, 0x000AD, 0x00, "Crestone Peak RS-232"}, + {HPHW_FIO, 0x076, 0x000AD, 0x0, "Crestone Peak Core RS-232"}, + {HPHW_FIO, 0x077, 0x000AD, 0x0, "Crestone Peak Fast? Core RS-232"}, {HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"}, {HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"}, {HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"}, diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index b7cadc4a06cd..e1ffea2f9a0b 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -45,7 +45,7 @@ static int get_offset(unsigned int last_mmap) { - return (last_mmap & (SHMLBA-1)) >> PAGE_SHIFT; + return (last_mmap & (SHM_COLOUR-1)) >> PAGE_SHIFT; } static unsigned long shared_align_offset(unsigned int last_mmap, @@ -57,8 +57,8 @@ static unsigned long shared_align_offset(unsigned int last_mmap, static inline unsigned long COLOR_ALIGN(unsigned long addr, unsigned int last_mmap, unsigned long pgoff) { - unsigned long base = (addr+SHMLBA-1) & ~(SHMLBA-1); - unsigned long off = (SHMLBA-1) & + unsigned long base = (addr+SHM_COLOUR-1) & ~(SHM_COLOUR-1); + unsigned long off = (SHM_COLOUR-1) & (shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT); return base + off; @@ -72,10 +72,10 @@ static unsigned long mmap_upper_limit(void) { unsigned long stack_base; - /* Limit stack size to 1GB - see setup_arg_pages() in fs/exec.c */ + /* Limit stack size - see setup_arg_pages() in fs/exec.c */ stack_base = rlimit_max(RLIMIT_STACK); - if (stack_base > (1 << 30)) - stack_base = 1 << 30; + if (stack_base > STACK_SIZE_MAX) + stack_base = STACK_SIZE_MAX; return PAGE_ALIGN(STACK_TOP - stack_base); } @@ -101,7 +101,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, if (flags & MAP_FIXED) { if ((flags & MAP_SHARED) && last_mmap && (addr - shared_align_offset(last_mmap, pgoff)) - & (SHMLBA - 1)) + & (SHM_COLOUR - 1)) return -EINVAL; goto found_addr; } @@ -122,7 +122,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, info.length = len; info.low_limit = mm->mmap_legacy_base; info.high_limit = mmap_upper_limit(); - info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0; + info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; info.align_offset = shared_align_offset(last_mmap, pgoff); addr = vm_unmapped_area(&info); @@ -161,7 +161,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (flags & MAP_FIXED) { if ((flags & MAP_SHARED) && last_mmap && (addr - shared_align_offset(last_mmap, pgoff)) - & (SHMLBA - 1)) + & (SHM_COLOUR - 1)) return -EINVAL; goto found_addr; } @@ -182,7 +182,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; - info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0; + info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; info.align_offset = shared_align_offset(last_mmap, pgoff); addr = vm_unmapped_area(&info); if (!(addr & ~PAGE_MASK)) diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index bb9f3b64de55..ec741fe02ab6 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -4,6 +4,7 @@ * Copyright (C) 2000-2001 Hewlett Packard Company * Copyright (C) 2000 John Marvin * Copyright (C) 2001 Matthew Wilcox + * Copyright (C) 2014 Helge Deller <deller@gmx.de> * * These routines maintain argument size conversion between 32bit and 64bit * environment. Based heavily on sys_ia32.c and sys_sparc32.c. @@ -57,3 +58,12 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23, current->comm, current->pid, r20); return -ENOSYS; } + +asmlinkage long sys32_fanotify_mark(compat_int_t fanotify_fd, compat_uint_t flags, + compat_uint_t mask0, compat_uint_t mask1, compat_int_t dfd, + const char __user * pathname) +{ + return sys_fanotify_mark(fanotify_fd, flags, + ((__u64)mask1 << 32) | mask0, + dfd, pathname); +} diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index a63bb179f79a..7ef22e3387e0 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -74,7 +74,7 @@ ENTRY(linux_gateway_page) /* ADDRESS 0xb0 to 0xb8, lws uses two insns for entry */ /* Light-weight-syscall entry must always be located at 0xb0 */ /* WARNING: Keep this number updated with table size changes */ -#define __NR_lws_entries (2) +#define __NR_lws_entries (3) lws_entry: gate lws_start, %r0 /* increase privilege */ @@ -502,7 +502,7 @@ lws_exit: /*************************************************** - Implementing CAS as an atomic operation: + Implementing 32bit CAS as an atomic operation: %r26 - Address to examine %r25 - Old value to check (old) @@ -589,10 +589,13 @@ cas_nocontend: # endif /* ENABLE_LWS_DEBUG */ + rsm PSW_SM_I, %r0 /* Disable interrupts */ + /* COW breaks can cause contention on UP systems */ LDCW 0(%sr2,%r20), %r28 /* Try to acquire the lock */ cmpb,<>,n %r0, %r28, cas_action /* Did we get it? */ cas_wouldblock: ldo 2(%r0), %r28 /* 2nd case */ + ssm PSW_SM_I, %r0 b lws_exit /* Contended... */ ldo -EAGAIN(%r0), %r21 /* Spin in userspace */ @@ -619,15 +622,17 @@ cas_action: stw %r1, 4(%sr2,%r20) #endif /* The load and store could fail */ -1: ldw 0(%sr3,%r26), %r28 +1: ldw,ma 0(%sr3,%r26), %r28 sub,<> %r28, %r25, %r0 -2: stw %r24, 0(%sr3,%r26) +2: stw,ma %r24, 0(%sr3,%r26) /* Free lock */ - stw %r20, 0(%sr2,%r20) + stw,ma %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG /* Clear thread register indicator */ stw %r0, 4(%sr2,%r20) #endif + /* Enable interrupts */ + ssm PSW_SM_I, %r0 /* Return to userspace, set no error */ b lws_exit copy %r0, %r21 @@ -639,6 +644,7 @@ cas_action: #if ENABLE_LWS_DEBUG stw %r0, 4(%sr2,%r20) #endif + ssm PSW_SM_I, %r0 b lws_exit ldo -EFAULT(%r0),%r21 /* set errno */ nop @@ -653,6 +659,230 @@ cas_action: ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page) + /*************************************************** + New CAS implementation which uses pointers and variable size + information. The value pointed by old and new MUST NOT change + while performing CAS. The lock only protect the value at %r26. + + %r26 - Address to examine + %r25 - Pointer to the value to check (old) + %r24 - Pointer to the value to set (new) + %r23 - Size of the variable (0/1/2/3 for 8/16/32/64 bit) + %r28 - Return non-zero on failure + %r21 - Kernel error code + + %r21 has the following meanings: + + EAGAIN - CAS is busy, ldcw failed, try again. + EFAULT - Read or write failed. + + Scratch: r20, r22, r28, r29, r1, fr4 (32bit for 64bit CAS only) + + ****************************************************/ + + /* ELF32 Process entry path */ +lws_compare_and_swap_2: +#ifdef CONFIG_64BIT + /* Clip the input registers */ + depdi 0, 31, 32, %r26 + depdi 0, 31, 32, %r25 + depdi 0, 31, 32, %r24 + depdi 0, 31, 32, %r23 +#endif + + /* Check the validity of the size pointer */ + subi,>>= 4, %r23, %r0 + b,n lws_exit_nosys + + /* Jump to the functions which will load the old and new values into + registers depending on the their size */ + shlw %r23, 2, %r29 + blr %r29, %r0 + nop + + /* 8bit load */ +4: ldb 0(%sr3,%r25), %r25 + b cas2_lock_start +5: ldb 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 16bit load */ +6: ldh 0(%sr3,%r25), %r25 + b cas2_lock_start +7: ldh 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 32bit load */ +8: ldw 0(%sr3,%r25), %r25 + b cas2_lock_start +9: ldw 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 64bit load */ +#ifdef CONFIG_64BIT +10: ldd 0(%sr3,%r25), %r25 +11: ldd 0(%sr3,%r24), %r24 +#else + /* Load new value into r22/r23 - high/low */ +10: ldw 0(%sr3,%r25), %r22 +11: ldw 4(%sr3,%r25), %r23 + /* Load new value into fr4 for atomic store later */ +12: flddx 0(%sr3,%r24), %fr4 +#endif + +cas2_lock_start: + /* Load start of lock table */ + ldil L%lws_lock_start, %r20 + ldo R%lws_lock_start(%r20), %r28 + + /* Extract four bits from r26 and hash lock (Bits 4-7) */ + extru %r26, 27, 4, %r20 + + /* Find lock to use, the hash is either one of 0 to + 15, multiplied by 16 (keep it 16-byte aligned) + and add to the lock table offset. */ + shlw %r20, 4, %r20 + add %r20, %r28, %r20 + + rsm PSW_SM_I, %r0 /* Disable interrupts */ + /* COW breaks can cause contention on UP systems */ + LDCW 0(%sr2,%r20), %r28 /* Try to acquire the lock */ + cmpb,<>,n %r0, %r28, cas2_action /* Did we get it? */ +cas2_wouldblock: + ldo 2(%r0), %r28 /* 2nd case */ + ssm PSW_SM_I, %r0 + b lws_exit /* Contended... */ + ldo -EAGAIN(%r0), %r21 /* Spin in userspace */ + + /* + prev = *addr; + if ( prev == old ) + *addr = new; + return prev; + */ + + /* NOTES: + This all works becuse intr_do_signal + and schedule both check the return iasq + and see that we are on the kernel page + so this process is never scheduled off + or is ever sent any signal of any sort, + thus it is wholly atomic from usrspaces + perspective + */ +cas2_action: + /* Jump to the correct function */ + blr %r29, %r0 + /* Set %r28 as non-zero for now */ + ldo 1(%r0),%r28 + + /* 8bit CAS */ +13: ldb,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +14: stb,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 16bit CAS */ +15: ldh,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +16: sth,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 32bit CAS */ +17: ldw,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +18: stw,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 64bit CAS */ +#ifdef CONFIG_64BIT +19: ldd,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +20: std,ma %r24, 0(%sr3,%r26) + copy %r0, %r28 +#else + /* Compare first word */ +19: ldw,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r22, %r0 + b,n cas2_end + /* Compare second word */ +20: ldw,ma 4(%sr3,%r26), %r29 + sub,= %r29, %r23, %r0 + b,n cas2_end + /* Perform the store */ +21: fstdx %fr4, 0(%sr3,%r26) + copy %r0, %r28 +#endif + +cas2_end: + /* Free lock */ + stw,ma %r20, 0(%sr2,%r20) + /* Enable interrupts */ + ssm PSW_SM_I, %r0 + /* Return to userspace, set no error */ + b lws_exit + copy %r0, %r21 + +22: + /* Error occurred on load or store */ + /* Free lock */ + stw %r20, 0(%sr2,%r20) + ssm PSW_SM_I, %r0 + ldo 1(%r0),%r28 + b lws_exit + ldo -EFAULT(%r0),%r21 /* set errno */ + nop + nop + nop + + /* Exception table entries, for the load and store, return EFAULT. + Each of the entries must be relocated. */ + ASM_EXCEPTIONTABLE_ENTRY(4b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(5b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(6b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(7b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(8b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(9b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(10b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(11b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(13b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(14b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(15b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(16b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(17b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(18b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(19b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(20b-linux_gateway_page, 22b-linux_gateway_page) +#ifndef CONFIG_64BIT + ASM_EXCEPTIONTABLE_ENTRY(12b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(21b-linux_gateway_page, 22b-linux_gateway_page) +#endif + /* Make sure nothing else is placed on this page */ .align PAGE_SIZE END(linux_gateway_page) @@ -669,8 +899,9 @@ ENTRY(end_linux_gateway_page) /* Light-weight-syscall table */ /* Start of lws table. */ ENTRY(lws_table) - LWS_ENTRY(compare_and_swap32) /* 0 - ELF32 Atomic compare and swap */ - LWS_ENTRY(compare_and_swap64) /* 1 - ELF64 Atomic compare and swap */ + LWS_ENTRY(compare_and_swap32) /* 0 - ELF32 Atomic 32bit CAS */ + LWS_ENTRY(compare_and_swap64) /* 1 - ELF64 Atomic 32bit CAS */ + LWS_ENTRY(compare_and_swap_2) /* 2 - ELF32 Atomic 64bit CAS */ END(lws_table) /* End of lws table */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 80e5dd248934..7dd8a3b22147 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -392,7 +392,7 @@ ENTRY_COMP(vmsplice) ENTRY_COMP(move_pages) /* 295 */ ENTRY_SAME(getcpu) - ENTRY_SAME(epoll_pwait) + ENTRY_COMP(epoll_pwait) ENTRY_COMP(statfs64) ENTRY_COMP(fstatfs64) ENTRY_COMP(kexec_load) /* 300 */ @@ -418,7 +418,7 @@ ENTRY_SAME(accept4) /* 320 */ ENTRY_SAME(prlimit64) ENTRY_SAME(fanotify_init) - ENTRY_COMP(fanotify_mark) + ENTRY_DIFF(fanotify_mark) ENTRY_COMP(clock_adjtime) ENTRY_SAME(name_to_handle_at) /* 325 */ ENTRY_COMP(open_by_handle_at) diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 1cd1d0c83b6d..47ee620d15d2 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -25,6 +25,7 @@ #include <linux/interrupt.h> #include <linux/console.h> #include <linux/bug.h> +#include <linux/ratelimit.h> #include <asm/assembly.h> #include <asm/uaccess.h> @@ -42,9 +43,6 @@ #include "../math-emu/math-emu.h" /* for handle_fpe() */ -#define PRINT_USER_FAULTS /* (turn this on if you want user faults to be */ - /* dumped to the console via printk) */ - #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) DEFINE_SPINLOCK(pa_dbit_lock); #endif @@ -160,6 +158,17 @@ void show_regs(struct pt_regs *regs) } } +static DEFINE_RATELIMIT_STATE(_hppa_rs, + DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); + +#define parisc_printk_ratelimited(critical, regs, fmt, ...) { \ + if ((critical || show_unhandled_signals) && __ratelimit(&_hppa_rs)) { \ + printk(fmt, ##__VA_ARGS__); \ + show_regs(regs); \ + } \ +} + + static void do_show_stack(struct unwind_frame_info *info) { int i = 1; @@ -229,12 +238,10 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) if (err == 0) return; /* STFU */ - printk(KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n", + parisc_printk_ratelimited(1, regs, + KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n", current->comm, task_pid_nr(current), str, err, regs->iaoq[0]); -#ifdef PRINT_USER_FAULTS - /* XXX for debugging only */ - show_regs(regs); -#endif + return; } @@ -321,14 +328,11 @@ static void handle_break(struct pt_regs *regs) (tt == BUG_TRAP_TYPE_NONE) ? 9 : 0); } -#ifdef PRINT_USER_FAULTS - if (unlikely(iir != GDB_BREAK_INSN)) { - printk(KERN_DEBUG "break %d,%d: pid=%d command='%s'\n", + if (unlikely(iir != GDB_BREAK_INSN)) + parisc_printk_ratelimited(0, regs, + KERN_DEBUG "break %d,%d: pid=%d command='%s'\n", iir & 31, (iir>>13) & ((1<<13)-1), task_pid_nr(current), current->comm); - show_regs(regs); - } -#endif /* send standard GDB signal */ handle_gdb_break(regs, TRAP_BRKPT); @@ -758,11 +762,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs) default: if (user_mode(regs)) { -#ifdef PRINT_USER_FAULTS - printk(KERN_DEBUG "\nhandle_interruption() pid=%d command='%s'\n", - task_pid_nr(current), current->comm); - show_regs(regs); -#endif + parisc_printk_ratelimited(0, regs, KERN_DEBUG + "handle_interruption() pid=%d command='%s'\n", + task_pid_nr(current), current->comm); /* SIGBUS, for lack of a better one. */ si.si_signo = SIGBUS; si.si_code = BUS_OBJERR; @@ -779,16 +781,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs) if (user_mode(regs)) { if ((fault_space >> SPACEID_SHIFT) != (regs->sr[7] >> SPACEID_SHIFT)) { -#ifdef PRINT_USER_FAULTS - if (fault_space == 0) - printk(KERN_DEBUG "User Fault on Kernel Space "); - else - printk(KERN_DEBUG "User Fault (long pointer) (fault %d) ", - code); - printk(KERN_CONT "pid=%d command='%s'\n", - task_pid_nr(current), current->comm); - show_regs(regs); -#endif + parisc_printk_ratelimited(0, regs, KERN_DEBUG + "User fault %d on space 0x%08lx, pid=%d command='%s'\n", + code, fault_space, + task_pid_nr(current), current->comm); si.si_signo = SIGSEGV; si.si_errno = 0; si.si_code = SEGV_MAPERR; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 9d08c71a967e..d72197f0ddb8 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -19,10 +19,6 @@ #include <asm/uaccess.h> #include <asm/traps.h> -#define PRINT_USER_FAULTS /* (turn this on if you want user faults to be */ - /* dumped to the console via printk) */ - - /* Various important other fields */ #define bit22set(x) (x & 0x00000200) #define bits23_25set(x) (x & 0x000001c0) @@ -34,6 +30,8 @@ DEFINE_PER_CPU(struct exception_data, exception_data); +int show_unhandled_signals = 1; + /* * parisc_acctyp(unsigned int inst) -- * Given a PA-RISC memory access instruction, determine if the @@ -173,6 +171,32 @@ int fixup_exception(struct pt_regs *regs) return 0; } +/* + * Print out info about fatal segfaults, if the show_unhandled_signals + * sysctl is set: + */ +static inline void +show_signal_msg(struct pt_regs *regs, unsigned long code, + unsigned long address, struct task_struct *tsk, + struct vm_area_struct *vma) +{ + if (!unhandled_signal(tsk, SIGSEGV)) + return; + + if (!printk_ratelimit()) + return; + + pr_warn("\n"); + pr_warn("do_page_fault() command='%s' type=%lu address=0x%08lx", + tsk->comm, code, address); + print_vma_addr(KERN_CONT " in ", regs->iaoq[0]); + if (vma) + pr_warn(" vm_start = 0x%08lx, vm_end = 0x%08lx\n", + vma->vm_start, vma->vm_end); + + show_regs(regs); +} + void do_page_fault(struct pt_regs *regs, unsigned long code, unsigned long address) { @@ -270,16 +294,8 @@ bad_area: if (user_mode(regs)) { struct siginfo si; -#ifdef PRINT_USER_FAULTS - printk(KERN_DEBUG "\n"); - printk(KERN_DEBUG "do_page_fault() pid=%d command='%s' type=%lu address=0x%08lx\n", - task_pid_nr(tsk), tsk->comm, code, address); - if (vma) { - printk(KERN_DEBUG "vm_start = 0x%08lx, vm_end = 0x%08lx\n", - vma->vm_start, vma->vm_end); - } - show_regs(regs); -#endif + show_signal_msg(regs, code, address, tsk, vma); + switch (code) { case 15: /* Data TLB miss fault/Data page fault */ /* send SIGSEGV when outside of vma */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 957bf344c0f5..ee3c6608126a 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -141,6 +141,7 @@ config PPC select HAVE_DEBUG_STACKOVERFLOW select HAVE_IRQ_EXIT_ON_IRQ_STACK select ARCH_USE_CMPXCHG_LOCKREF if PPC64 + select ARCH_SUPPORTS_ATOMIC_RMW config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN @@ -410,7 +411,7 @@ config KEXEC config CRASH_DUMP bool "Build a kdump crash kernel" depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP) - select RELOCATABLE if PPC64 || 44x || FSL_BOOKE + select RELOCATABLE if (PPC64 && !COMPILE_TEST) || 44x || FSL_BOOKE help Build a kernel suitable for use as a kdump capture kernel. The same kernel binary can be used as production kernel and dump @@ -1000,6 +1001,7 @@ endmenu if PPC64 config RELOCATABLE bool "Build a relocatable kernel" + depends on !COMPILE_TEST select NONSTATIC_KERNEL help This builds a kernel image that is capable of running anywhere diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 0f4344e6fbca..8289e2b241a2 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -149,7 +149,9 @@ endif CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell) -KBUILD_CPPFLAGS += -Iarch/$(ARCH) +asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1) + +KBUILD_CPPFLAGS += -Iarch/$(ARCH) $(asinstr) KBUILD_AFLAGS += -Iarch/$(ARCH) KBUILD_CFLAGS += -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y) CPP = $(CC) -E $(KBUILD_CFLAGS) diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index a613d2c82fd9..b142b8e0ed9e 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -8,7 +8,11 @@ #include <linux/sched.h> #define COMPAT_USER_HZ 100 +#ifdef __BIG_ENDIAN__ #define COMPAT_UTS_MACHINE "ppc\0\0" +#else +#define COMPAT_UTS_MACHINE "ppcle\0\0" +#endif typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index ad3025d0880b..f20786825b8f 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -57,10 +57,10 @@ struct machdep_calls { void (*hpte_removebolted)(unsigned long ea, int psize, int ssize); void (*flush_hash_range)(unsigned long number, int local); - void (*hugepage_invalidate)(struct mm_struct *mm, + void (*hugepage_invalidate)(unsigned long vsid, + unsigned long addr, unsigned char *hpte_slot_array, - unsigned long addr, int psize); - + int psize, int ssize); /* special for kexec, to be called in real mode, linear mapping is * destroyed as well */ void (*hpte_clear_all)(void); diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 3fd2f1b6f906..cefc7b4f4fb1 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -60,8 +60,7 @@ struct power_pmu { #define PPMU_SIAR_VALID 0x00000010 /* Processor has SIAR Valid bit */ #define PPMU_HAS_SSLOT 0x00000020 /* Has sampled slot in MMCRA */ #define PPMU_HAS_SIER 0x00000040 /* Has SIER */ -#define PPMU_BHRB 0x00000080 /* has BHRB feature enabled */ -#define PPMU_EBB 0x00000100 /* supports event based branch */ +#define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */ /* * Values for flags to get_alternatives() diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index eb9261024f51..7b3d54fae46f 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -413,7 +413,7 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp) } extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp); + pmd_t *pmdp, unsigned long old_pmd); #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 6586a40a46ce..cded7c1278ef 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -318,11 +318,16 @@ n: addi reg,reg,(name - 0b)@l; #ifdef __powerpc64__ +#ifdef HAVE_AS_ATHIGH +#define __AS_ATHIGH high +#else +#define __AS_ATHIGH h +#endif #define LOAD_REG_IMMEDIATE(reg,expr) \ lis reg,(expr)@highest; \ ori reg,reg,(expr)@higher; \ rldicr reg,reg,32,31; \ - oris reg,reg,(expr)@h; \ + oris reg,reg,(expr)@__AS_ATHIGH; \ ori reg,reg,(expr)@l; #define LOAD_REG_ADDR(reg,name) \ diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h index d836d945068d..9ecede1e124c 100644 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ b/arch/powerpc/include/asm/pte-hash64-64k.h @@ -46,11 +46,31 @@ * in order to deal with 64K made of 4K HW pages. Thus we override the * generic accessors and iterators here */ -#define __real_pte(e,p) ((real_pte_t) { \ - (e), (pte_val(e) & _PAGE_COMBO) ? \ - (pte_val(*((p) + PTRS_PER_PTE))) : 0 }) -#define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \ - (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf)) +#define __real_pte __real_pte +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +{ + real_pte_t rpte; + + rpte.pte = pte; + rpte.hidx = 0; + if (pte_val(pte) & _PAGE_COMBO) { + /* + * Make sure we order the hidx load against the _PAGE_COMBO + * check. The store side ordering is done in __hash_page_4K + */ + smp_rmb(); + rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE)); + } + return rpte; +} + +static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) +{ + if ((pte_val(rpte.pte) & _PAGE_COMBO)) + return (rpte.hidx >> (index<<2)) & 0xf; + return (pte_val(rpte.pte) >> 12) & 0xf; +} + #define __rpte_to_pte(r) ((r).pte) #define __rpte_sub_valid(rpte, index) \ (pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index))) diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 279b80f3bb29..c0c61fa9cd9e 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -47,6 +47,12 @@ STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define STACK_FRAME_MIN_SIZE 32 +#else +#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD +#endif + /* Size of dummy stack frame allocated when calling signal handler. */ #define __SIGNAL_FRAMESIZE 128 #define __SIGNAL_FRAMESIZE32 64 @@ -60,6 +66,7 @@ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD) #define STACK_FRAME_MARKER 2 +#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD /* Size of stack frame allocated when calling signal handler. */ #define __SIGNAL_FRAMESIZE 64 diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 90c06ec6eff5..ce17815b8b55 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -213,6 +213,7 @@ #define SPRN_ACOP 0x1F /* Available Coprocessor Register */ #define SPRN_TFIAR 0x81 /* Transaction Failure Inst Addr */ #define SPRN_TEXASR 0x82 /* Transaction EXception & Summary */ +#define TEXASR_FS __MASK(63-36) /* Transaction Failure Summary */ #define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */ #define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */ #define SPRN_CTRLF 0x088 diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 35aa339410bd..4dbe072eecbe 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -61,6 +61,7 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { + smp_mb(); return !arch_spin_value_unlocked(*lock); } diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 0e83e7d8c73f..b5fad8afe837 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -84,6 +84,8 @@ static inline void clear_task_ebb(struct task_struct *t) { #ifdef CONFIG_PPC_BOOK3S_64 /* EBB perf events are not inherited, so clear all EBB state. */ + t->thread.ebbrr = 0; + t->thread.ebbhr = 0; t->thread.bescr = 0; t->thread.mmcr2 = 0; t->thread.mmcr0 = 0; diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 3ddf70276706..0616916b446a 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -190,7 +190,7 @@ SYSCALL_SPU(getcwd) SYSCALL_SPU(capget) SYSCALL_SPU(capset) COMPAT_SYS(sigaltstack) -COMPAT_SYS_SPU(sendfile) +SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile) SYSCALL(ni_syscall) SYSCALL(ni_syscall) PPC_SYS(vfork) diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 5b7657959faa..de2c0e4ee1aa 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -41,5 +41,6 @@ #define PPC_FEATURE2_EBB 0x10000000 #define PPC_FEATURE2_ISEL 0x08000000 #define PPC_FEATURE2_TAR 0x04000000 +#define PPC_FEATURE2_VEC_CRYPTO 0x02000000 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 6c8dd5da4de5..7ac1eab3ff8a 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -109,7 +109,8 @@ extern void __restore_cpu_e6500(void); PPC_FEATURE_PSERIES_PERFMON_COMPAT) #define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \ - PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR) + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ + PPC_FEATURE2_VEC_CRYPTO) #define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ PPC_FEATURE_TRUE_LE | \ PPC_FEATURE_HAS_ALTIVEC_COMP) diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 40bd7bd4e19a..8a8b722870a1 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -48,6 +48,9 @@ static struct of_device_id legacy_serial_parents[] __initdata = { static unsigned int legacy_serial_count; static int legacy_serial_console = -1; +static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | + UPF_SHARE_IRQ | UPF_FIXED_PORT; + static unsigned int tsi_serial_in(struct uart_port *p, int offset) { unsigned int tmp; @@ -153,8 +156,6 @@ static int __init add_legacy_soc_port(struct device_node *np, { u64 addr; const __be32 *addrp; - upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ - | UPF_FIXED_PORT; struct device_node *tsi = of_get_parent(np); /* We only support ports that have a clock frequency properly @@ -185,9 +186,11 @@ static int __init add_legacy_soc_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ if (tsi && !strcmp(tsi->type, "tsi-bridge")) - return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_TSI, addr, addr, + NO_IRQ, legacy_port_flags, 0); else - return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_MEM, addr, addr, + NO_IRQ, legacy_port_flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, @@ -233,7 +236,7 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Add port, irq will be dealt with later */ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), - taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0); + taddr, NO_IRQ, legacy_port_flags, 0); } @@ -306,7 +309,7 @@ static int __init add_legacy_pci_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, - UPF_BOOT_AUTOCONF, np != pci_dev); + legacy_port_flags, np != pci_dev); } #endif diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 59d229a2a3e0..879b3aacac32 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -237,7 +237,7 @@ static void wake_offline_cpus(void) if (!cpu_online(cpu)) { printk(KERN_INFO "kexec: Waking offline cpu %d.\n", cpu); - cpu_up(cpu); + WARN_ON(cpu_up(cpu)); } } } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index af064d28b365..31d021506d21 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -610,6 +610,31 @@ out_and_saveregs: tm_save_sprs(thr); } +extern void __tm_recheckpoint(struct thread_struct *thread, + unsigned long orig_msr); + +void tm_recheckpoint(struct thread_struct *thread, + unsigned long orig_msr) +{ + unsigned long flags; + + /* We really can't be interrupted here as the TEXASR registers can't + * change and later in the trecheckpoint code, we have a userspace R1. + * So let's hard disable over this region. + */ + local_irq_save(flags); + hard_irq_disable(); + + /* The TM SPRs are restored here, so that TEXASR.FS can be set + * before the trecheckpoint and no explosion occurs. + */ + tm_restore_sprs(thread); + + __tm_recheckpoint(thread, orig_msr); + + local_irq_restore(flags); +} + static inline void tm_recheckpoint_new_task(struct task_struct *new) { unsigned long msr; @@ -628,13 +653,10 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) if (!new->thread.regs) return; - /* The TM SPRs are restored here, so that TEXASR.FS can be set - * before the trecheckpoint and no explosion occurs. - */ - tm_restore_sprs(&new->thread); - - if (!MSR_TM_ACTIVE(new->thread.regs->msr)) + if (!MSR_TM_ACTIVE(new->thread.regs->msr)){ + tm_restore_sprs(&new->thread); return; + } msr = new->thread.tm_orig_msr; /* Recheckpoint to restore original checkpointed register state. */ TM_DEBUG("*** tm_recheckpoint of pid %d " diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index bc76cc6b419c..04aa4d3c7c05 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -456,9 +456,17 @@ void __init smp_setup_cpu_maps(void) } for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { + bool avail; + DBG(" thread %d -> cpu %d (hard id %d)\n", j, cpu, be32_to_cpu(intserv[j])); - set_cpu_present(cpu, true); + + avail = of_device_is_available(dn); + if (!avail) + avail = !of_property_match_string(dn, + "enable-method", "spin-table"); + + set_cpu_present(cpu, avail); set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j])); set_cpu_possible(cpu, true); cpu++; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index a67e00aa3caa..4e47db686b5d 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -881,6 +881,8 @@ static long restore_tm_user_regs(struct pt_regs *regs, * transactional versions should be loaded. */ tm_enable(); + /* Make sure the transaction is marked as failed */ + current->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); /* Get the top half of the MSR */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 8d253c29649b..d501dc4dc3e6 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -527,6 +527,8 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, } #endif tm_enable(); + /* Make sure the transaction is marked as failed */ + current->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index b3dab20acf34..f8b994abb57f 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -511,7 +511,7 @@ void timer_interrupt(struct pt_regs * regs) may_hard_irq_enable(); -#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) +#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) do_IRQ(regs); #endif @@ -805,9 +805,6 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - /* Don't adjust the decrementer if some irq work is pending */ - if (test_irq_work_pending()) - return 0; __get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt; set_dec(evt); diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index ef47bcbd4352..03567c05950a 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -307,7 +307,7 @@ dont_backup_fp: * Call with IRQs off, stacks get all out of sync for * some periods in here! */ -_GLOBAL(tm_recheckpoint) +_GLOBAL(__tm_recheckpoint) mfcr r5 mflr r0 stw r5, 8(r1) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 17fc9496b6ac..7a25d9218a05 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -86,7 +86,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) /* CPU points to the first thread of the core */ if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) { -#ifdef CONFIG_KVM_XICS +#ifdef CONFIG_PPC_ICP_NATIVE int real_cpu = cpu + vcpu->arch.ptid; if (paca[real_cpu].kvm_hstate.xics_phys) xics_wake_cpu(real_cpu); @@ -1360,9 +1360,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) smp_wmb(); #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) if (cpu != smp_processor_id()) { -#ifdef CONFIG_KVM_XICS xics_wake_cpu(cpu); -#endif if (vcpu->arch.ptid) ++vc->n_woken; } diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index 0c9c8d7d0734..170a0346f756 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -70,12 +70,16 @@ void __rw_yield(arch_rwlock_t *rw) void arch_spin_unlock_wait(arch_spinlock_t *lock) { + smp_mb(); + while (lock->slock) { HMT_low(); if (SHARED_PROCESSOR) __spin_yield(lock); } HMT_medium(); + + smp_mb(); } EXPORT_SYMBOL(arch_spin_unlock_wait); diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index c0511c27a733..412dd46dd0b7 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1470,7 +1470,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) regs->gpr[rd] = byterev_4(val); goto ldst_done; -#ifdef CONFIG_PPC_CPU +#ifdef CONFIG_PPC_FPU case 535: /* lfsx */ case 567: /* lfsux */ if (!(regs->msr & MSR_FP)) diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 3ea26c25590b..838de8e17dc5 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -418,18 +418,18 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, local_irq_restore(flags); } -static void native_hugepage_invalidate(struct mm_struct *mm, +static void native_hugepage_invalidate(unsigned long vsid, + unsigned long addr, unsigned char *hpte_slot_array, - unsigned long addr, int psize) + int psize, int ssize) { - int ssize = 0, i; - int lock_tlbie; + int i; struct hash_pte *hptep; int actual_psize = MMU_PAGE_16M; unsigned int max_hpte_count, valid; unsigned long flags, s_addr = addr; unsigned long hpte_v, want_v, shift; - unsigned long hidx, vpn = 0, vsid, hash, slot; + unsigned long hidx, vpn = 0, hash, slot; shift = mmu_psize_defs[psize].shift; max_hpte_count = 1U << (PMD_SHIFT - shift); @@ -443,15 +443,6 @@ static void native_hugepage_invalidate(struct mm_struct *mm, /* get the vpn */ addr = s_addr + (i * (1ul << shift)); - if (!is_kernel_addr(addr)) { - ssize = user_segment_size(addr); - vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); - } else { - vsid = get_kernel_vsid(addr, mmu_kernel_ssize); - ssize = mmu_kernel_ssize; - } - vpn = hpt_vpn(addr, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); if (hidx & _PTEIDX_SECONDARY) @@ -471,22 +462,13 @@ static void native_hugepage_invalidate(struct mm_struct *mm, else /* Invalidate the hpte. NOTE: this also unlocks it */ hptep->v = 0; + /* + * We need to do tlb invalidate for all the address, tlbie + * instruction compares entry_VA in tlb with the VA specified + * here + */ + tlbie(vpn, psize, actual_psize, ssize, 0); } - /* - * Since this is a hugepage, we just need a single tlbie. - * use the last vpn. - */ - lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); - if (lock_tlbie) - raw_spin_lock(&native_tlbie_lock); - - asm volatile("ptesync":::"memory"); - __tlbie(vpn, psize, actual_psize, ssize); - asm volatile("eieio; tlbsync; ptesync":::"memory"); - - if (lock_tlbie) - raw_spin_unlock(&native_tlbie_lock); - local_irq_restore(flags); } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index d766d6ee33fe..6650699eb3b6 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -960,6 +960,22 @@ void hash_failure_debug(unsigned long ea, unsigned long access, trap, vsid, ssize, psize, lpsize, pte); } +static void check_paca_psize(unsigned long ea, struct mm_struct *mm, + int psize, bool user_region) +{ + if (user_region) { + if (psize != get_paca_psize(ea)) { + get_paca()->context = mm->context; + slb_flush_and_rebolt(); + } + } else if (get_paca()->vmalloc_sllp != + mmu_psize_defs[mmu_vmalloc_psize].sllp) { + get_paca()->vmalloc_sllp = + mmu_psize_defs[mmu_vmalloc_psize].sllp; + slb_vmalloc_update(); + } +} + /* Result code is: * 0 - handled * 1 - normal page fault @@ -1081,6 +1097,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) WARN_ON(1); } #endif + check_paca_psize(ea, mm, psize, user_region); + goto bail; } @@ -1121,17 +1139,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) #endif } } - if (user_region) { - if (psize != get_paca_psize(ea)) { - get_paca()->context = mm->context; - slb_flush_and_rebolt(); - } - } else if (get_paca()->vmalloc_sllp != - mmu_psize_defs[mmu_vmalloc_psize].sllp) { - get_paca()->vmalloc_sllp = - mmu_psize_defs[mmu_vmalloc_psize].sllp; - slb_vmalloc_update(); - } + + check_paca_psize(ea, mm, psize, user_region); #endif /* CONFIG_PPC_64K_PAGES */ #ifdef CONFIG_PPC_HAS_HASH_64K diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 826893fcb3a7..5f5e6328c21c 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -18,6 +18,57 @@ #include <linux/mm.h> #include <asm/machdep.h> +static void invalidate_old_hpte(unsigned long vsid, unsigned long addr, + pmd_t *pmdp, unsigned int psize, int ssize) +{ + int i, max_hpte_count, valid; + unsigned long s_addr; + unsigned char *hpte_slot_array; + unsigned long hidx, shift, vpn, hash, slot; + + s_addr = addr & HPAGE_PMD_MASK; + hpte_slot_array = get_hpte_slot_array(pmdp); + /* + * IF we try to do a HUGE PTE update after a withdraw is done. + * we will find the below NULL. This happens when we do + * split_huge_page_pmd + */ + if (!hpte_slot_array) + return; + + if (ppc_md.hugepage_invalidate) + return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array, + psize, ssize); + /* + * No bluk hpte removal support, invalidate each entry + */ + shift = mmu_psize_defs[psize].shift; + max_hpte_count = HPAGE_PMD_SIZE >> shift; + for (i = 0; i < max_hpte_count; i++) { + /* + * 8 bits per each hpte entries + * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit] + */ + valid = hpte_valid(hpte_slot_array, i); + if (!valid) + continue; + hidx = hpte_hash_index(hpte_slot_array, i); + + /* get the vpn */ + addr = s_addr + (i * (1ul << shift)); + vpn = hpt_vpn(addr, vsid, ssize); + hash = hpt_hash(vpn, shift, ssize); + if (hidx & _PTEIDX_SECONDARY) + hash = ~hash; + + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += hidx & _PTEIDX_GROUP_IX; + ppc_md.hpte_invalidate(slot, vpn, psize, + MMU_PAGE_16M, ssize, 0); + } +} + + int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, pmd_t *pmdp, unsigned long trap, int local, int ssize, unsigned int psize) @@ -33,7 +84,9 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * atomically mark the linux large page PMD busy and dirty */ do { - old_pmd = pmd_val(*pmdp); + pmd_t pmd = ACCESS_ONCE(*pmdp); + + old_pmd = pmd_val(pmd); /* If PMD busy, retry the access */ if (unlikely(old_pmd & _PAGE_BUSY)) return 0; @@ -85,6 +138,15 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, vpn = hpt_vpn(ea, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); hpte_slot_array = get_hpte_slot_array(pmdp); + if (psize == MMU_PAGE_4K) { + /* + * invalidate the old hpte entry if we have that mapped via 64K + * base page size. This is because demote_segment won't flush + * hash page table entries. + */ + if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) + invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize); + } valid = hpte_valid(hpte_slot_array, index); if (valid) { @@ -107,11 +169,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * safely update this here. */ valid = 0; - new_pmd &= ~_PAGE_HPTEFLAGS; hpte_slot_array[index] = 0; - } else - /* clear the busy bits and set the hash pte bits */ - new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; + } } if (!valid) { @@ -119,11 +178,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, /* insert new entry */ pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT; -repeat: - hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; - - /* clear the busy bits and set the hash pte bits */ - new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; + new_pmd |= _PAGE_HASHPTE; /* Add in WIMG bits */ rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | @@ -132,6 +187,8 @@ repeat: * enable the memory coherence always */ rflags |= HPTE_R_M; +repeat: + hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, @@ -172,8 +229,17 @@ repeat: mark_hpte_slot_valid(hpte_slot_array, index, slot); } /* - * No need to use ldarx/stdcx here + * Mark the pte with _PAGE_COMBO, if we are trying to hash it with + * base page size 4k. + */ + if (psize == MMU_PAGE_4K) + new_pmd |= _PAGE_COMBO; + /* + * The hpte valid is stored in the pgtable whose address is in the + * second half of the PMD. Order this against clearing of the busy bit in + * huge pmd. */ + smp_wmb(); *pmdp = __pmd(new_pmd & ~_PAGE_BUSY); return 0; } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index eb923654ba80..7e70ae968e5f 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd) */ return ((pgd_val(pgd) & 0x3) != 0x0); } - -int pmd_huge_support(void) -{ - return 1; -} #else int pmd_huge(pmd_t pmd) { @@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd) { return 0; } - -int pmd_huge_support(void) -{ - return 0; -} #endif pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 30a42e24bf14..a5fff173be4f 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -610,8 +610,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action, case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: unmap_cpu_from_node(lcpu); - break; ret = NOTIFY_OK; + break; #endif } return ret; diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 62bf5e8e78da..c64da56d7582 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -538,7 +538,7 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, *pmdp = __pmd((old & ~clr) | set); #endif if (old & _PAGE_HASHPTE) - hpte_do_hugepage_flush(mm, addr, pmdp); + hpte_do_hugepage_flush(mm, addr, pmdp, old); return old; } @@ -645,7 +645,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, if (!(old & _PAGE_SPLITTING)) { /* We need to flush the hpte */ if (old & _PAGE_HASHPTE) - hpte_do_hugepage_flush(vma->vm_mm, address, pmdp); + hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old); } } @@ -718,7 +718,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, * neesd to be flushed. */ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) + pmd_t *pmdp, unsigned long old_pmd) { int ssize, i; unsigned long s_addr; @@ -740,12 +740,29 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, if (!hpte_slot_array) return; - /* get the base page size */ + /* get the base page size,vsid and segment size */ +#ifdef CONFIG_DEBUG_VM psize = get_slice_psize(mm, s_addr); + BUG_ON(psize == MMU_PAGE_16M); +#endif + if (old_pmd & _PAGE_COMBO) + psize = MMU_PAGE_4K; + else + psize = MMU_PAGE_64K; + + if (!is_kernel_addr(s_addr)) { + ssize = user_segment_size(s_addr); + vsid = get_vsid(mm->context.id, s_addr, ssize); + WARN_ON(vsid == 0); + } else { + vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize); + ssize = mmu_kernel_ssize; + } if (ppc_md.hugepage_invalidate) - return ppc_md.hugepage_invalidate(mm, hpte_slot_array, - s_addr, psize); + return ppc_md.hugepage_invalidate(vsid, s_addr, + hpte_slot_array, + psize, ssize); /* * No bluk hpte removal support, invalidate each entry */ @@ -763,15 +780,6 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, /* get the vpn */ addr = s_addr + (i * (1ul << shift)); - if (!is_kernel_addr(addr)) { - ssize = user_segment_size(addr); - vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); - } else { - vsid = get_kernel_vsid(addr, mmu_kernel_ssize); - ssize = mmu_kernel_ssize; - } - vpn = hpt_vpn(addr, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); if (hidx & _PTEIDX_SECONDARY) diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index c99f6510a0b2..9adda5790463 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -216,7 +216,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, if (!(pte & _PAGE_HASHPTE)) continue; if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte))) - hpte_do_hugepage_flush(mm, start, (pmd_t *)pte); + hpte_do_hugepage_flush(mm, start, (pmd_t *)ptep, pte); else hpte_need_flush(mm, start, ptep, pte, 0); } diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 74d1e780748b..2396dda282cd 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -35,7 +35,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp) return 0; /* must be 16-byte aligned */ if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD)) return 0; - if (sp >= prev_sp + STACK_FRAME_OVERHEAD) + if (sp >= prev_sp + STACK_FRAME_MIN_SIZE) return 1; /* * sp could decrease when we jump off an interrupt stack diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 67cf22083f4c..38265dc85318 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -483,7 +483,7 @@ static bool is_ebb_event(struct perf_event *event) * check that the PMU supports EBB, meaning those that don't can still * use bit 63 of the event code for something else if they wish. */ - return (ppmu->flags & PPMU_EBB) && + return (ppmu->flags & PPMU_ARCH_207S) && ((event->attr.config >> PERF_EVENT_CONFIG_EBB_SHIFT) & 1); } @@ -851,7 +851,22 @@ static void power_pmu_read(struct perf_event *event) } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev); local64_add(delta, &event->count); - local64_sub(delta, &event->hw.period_left); + + /* + * A number of places program the PMC with (0x80000000 - period_left). + * We never want period_left to be less than 1 because we will program + * the PMC with a value >= 0x800000000 and an edge detected PMC will + * roll around to 0 before taking an exception. We have seen this + * on POWER8. + * + * To fix this, clamp the minimum value of period_left to 1. + */ + do { + prev = local64_read(&event->hw.period_left); + val = prev - delta; + if (val < 1) + val = 1; + } while (local64_cmpxchg(&event->hw.period_left, prev, val) != prev); } /* @@ -1152,6 +1167,9 @@ static void power_pmu_enable(struct pmu *pmu) write_mmcr0(cpuhw, mmcr0); + if (ppmu->flags & PPMU_ARCH_207S) + mtspr(SPRN_MMCR2, 0); + /* * Enable instruction sampling if necessary */ @@ -1548,7 +1566,7 @@ static int power_pmu_event_init(struct perf_event *event) if (has_branch_stack(event)) { /* PMU has BHRB enabled */ - if (!(ppmu->flags & PPMU_BHRB)) + if (!(ppmu->flags & PPMU_ARCH_207S)) return -EOPNOTSUPP; } diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index 96cee20dcd34..4a06530cbb71 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -751,7 +751,7 @@ static struct power_pmu power8_pmu = { .get_constraint = power8_get_constraint, .get_alternatives = power8_get_alternatives, .disable_pmc = power8_disable_pmc, - .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB, + .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S, .n_generic = ARRAY_SIZE(power8_generic_events), .generic_events = power8_generic_events, .cache_events = &power8_cache_events, diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 253fefe3d1a0..5b51079f3e3b 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -549,7 +549,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) ret = ioda_eeh_phb_reset(hose, option); } else { bus = eeh_pe_bus_get(pe); - if (pci_is_root_bus(bus)) + if (pci_is_root_bus(bus) || + pci_is_root_bus(bus->parent)) ret = ioda_eeh_root_reset(hose, option); else ret = ioda_eeh_bridge_reset(hose, bus->self, option); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3b2b4fb3585b..beedaf0c5e75 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -491,6 +491,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, set_dma_ops(&pdev->dev, &dma_iommu_ops); set_iommu_table_base(&pdev->dev, &pe->tce32_table); } + *pdev->dev.dma_mask = dma_mask; return 0; } diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a8fe5aa3d34f..3b46eed1dcf6 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -380,7 +380,7 @@ static int dlpar_online_cpu(struct device_node *dn) BUG_ON(get_cpu_current_state(cpu) != CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_up(cpu); + rc = device_online(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); @@ -463,7 +463,7 @@ static int dlpar_offline_cpu(struct device_node *dn) if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_down(cpu); + rc = device_offline(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 8a8f0472d98f..83da53fde6b5 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -464,6 +464,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state) } else { result = EEH_STATE_NOT_SUPPORT; } + break; default: result = EEH_STATE_NOT_SUPPORT; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 0ea99e3d4815..2d6fe89ff89d 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -88,13 +88,14 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args args = { - .token = cpu_to_be32(rtas_stop_self_token), + static struct rtas_args args = { .nargs = 0, .nret = 1, .rets = &args.args[0], }; + args.token = cpu_to_be32(rtas_stop_self_token); + local_irq_disable(); BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 9590dbb756f2..b9a82042760f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -160,7 +160,7 @@ static int pseries_remove_memory(struct device_node *np) static inline int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { - return -EOPNOTSUPP; + return 0; } static inline int pseries_remove_memory(struct device_node *np) { diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 33b552ffbe57..de1ec54a2a57 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -329,16 +329,16 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { - __be32 windows_available; - __be32 largest_available_block; - __be32 page_size; - __be32 migration_capable; + u32 windows_available; + u32 largest_available_block; + u32 page_size; + u32 migration_capable; }; struct ddw_create_response { - __be32 liobn; - __be32 addr_hi; - __be32 addr_lo; + u32 liobn; + u32 addr_hi; + u32 addr_lo; }; static LIST_HEAD(direct_window_list); @@ -721,20 +721,22 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static void remove_ddw(struct device_node *np) +static void remove_ddw(struct device_node *np, bool remove_prop) { struct dynamic_dma_window_prop *dwp; struct property *win64; - const u32 *ddw_avail; + u32 ddw_avail[3]; u64 liobn; - int len, ret; + int ret = 0; + + ret = of_property_read_u32_array(np, "ibm,ddw-applicable", + &ddw_avail[0], 3); - ddw_avail = of_get_property(np, "ibm,ddw-applicable", &len); win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); if (!win64) return; - if (!ddw_avail || len < 3 * sizeof(u32) || win64->length < sizeof(*dwp)) + if (ret || win64->length < sizeof(*dwp)) goto delprop; dwp = win64->value; @@ -761,7 +763,8 @@ static void remove_ddw(struct device_node *np) np->full_name, ret, ddw_avail[2], liobn); delprop: - ret = of_remove_property(np, win64); + if (remove_prop) + ret = of_remove_property(np, win64); if (ret) pr_warning("%s: failed to remove direct window property: %d\n", np->full_name, ret); @@ -805,7 +808,7 @@ static int find_existing_ddw_windows(void) window = kzalloc(sizeof(*window), GFP_KERNEL); if (!window || len < sizeof(struct dynamic_dma_window_prop)) { kfree(window); - remove_ddw(pdn); + remove_ddw(pdn, true); continue; } @@ -871,8 +874,9 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ - ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, cfg_addr, - BUID_HI(buid), BUID_LO(buid), page_shift, window_shift); + ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, + cfg_addr, BUID_HI(buid), BUID_LO(buid), + page_shift, window_shift); } while (rtas_busy_delay(ret)); dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " @@ -909,7 +913,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) int page_shift; u64 dma_addr, max_addr; struct device_node *dn; - const u32 *uninitialized_var(ddw_avail); + u32 ddw_avail[3]; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; @@ -941,8 +945,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * for the given node in that order. * the property is actually in the parent, not the PE */ - ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len); - if (!ddw_avail || len < 3 * sizeof(u32)) + ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable", + &ddw_avail[0], 3); + if (ret) goto out_failed; /* @@ -965,11 +970,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_dbg(&dev->dev, "no free dynamic windows"); goto out_failed; } - if (be32_to_cpu(query.page_size) & 4) { + if (query.page_size & 4) { page_shift = 24; /* 16MB */ - } else if (be32_to_cpu(query.page_size) & 2) { + } else if (query.page_size & 2) { page_shift = 16; /* 64kB */ - } else if (be32_to_cpu(query.page_size) & 1) { + } else if (query.page_size & 1) { page_shift = 12; /* 4kB */ } else { dev_dbg(&dev->dev, "no supported direct page size in mask %x", @@ -979,7 +984,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ max_addr = memory_hotplug_max(); - if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) { + if (query.largest_available_block < (max_addr >> page_shift)) { dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); @@ -1005,8 +1010,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (ret != 0) goto out_free_prop; - ddwprop->liobn = create.liobn; - ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2)); + ddwprop->liobn = cpu_to_be32(create.liobn); + ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) | + create.addr_lo); ddwprop->tce_shift = cpu_to_be32(page_shift); ddwprop->window_shift = cpu_to_be32(len); @@ -1038,14 +1044,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) list_add(&window->list, &direct_window_list); spin_unlock(&direct_window_list_lock); - dma_addr = of_read_number(&create.addr_hi, 2); + dma_addr = be64_to_cpu(ddwprop->dma_base); goto out_unlock; out_free_window: kfree(window); out_clear_window: - remove_ddw(pdn); + remove_ddw(pdn, true); out_free_prop: kfree(win64->name); @@ -1255,7 +1261,14 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti switch (action) { case OF_RECONFIG_DETACH_NODE: - remove_ddw(np); + /* + * Removing the property will invoke the reconfig + * notifier again, which causes dead-lock on the + * read-write semaphore of the notifier chain. So + * we have to remove the property when releasing + * the device node. + */ + remove_ddw(np, false); if (pci && pci->iommu_table) iommu_free_table(pci->iommu_table, np->full_name); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index b02af9ef3ff6..ccf6f162f69c 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -430,16 +430,17 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags); } -static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm, - unsigned char *hpte_slot_array, - unsigned long addr, int psize) +static void pSeries_lpar_hugepage_invalidate(unsigned long vsid, + unsigned long addr, + unsigned char *hpte_slot_array, + int psize, int ssize) { - int ssize = 0, i, index = 0; + int i, index = 0; unsigned long s_addr = addr; unsigned int max_hpte_count, valid; unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH]; unsigned long slot_array[PPC64_HUGE_HPTE_BATCH]; - unsigned long shift, hidx, vpn = 0, vsid, hash, slot; + unsigned long shift, hidx, vpn = 0, hash, slot; shift = mmu_psize_defs[psize].shift; max_hpte_count = 1U << (PMD_SHIFT - shift); @@ -452,15 +453,6 @@ static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm, /* get the vpn */ addr = s_addr + (i * (1ul << shift)); - if (!is_kernel_addr(addr)) { - ssize = user_segment_size(addr); - vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); - } else { - vsid = get_kernel_vsid(addr, mmu_kernel_ssize); - ssize = mmu_kernel_ssize; - } - vpn = hpt_vpn(addr, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); if (hidx & _PTEIDX_SECONDARY) diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index efe61374f6ea..e68922b0d4f5 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -118,10 +118,10 @@ int remove_phb_dynamic(struct pci_controller *phb) } } - /* Unregister the bridge device from sysfs and remove the PCI bus */ - device_unregister(b->bridge); + /* Remove the PCI bus and unregister the bridge device from sysfs */ phb->bus = NULL; pci_remove_bus(b); + device_unregister(b->bridge); /* Now release the IO resource */ if (res->flags & IORESOURCE_IO) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 65a07750f4f9..a0a3bed6e4dc 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -93,6 +93,7 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE select ARCH_SAVE_PAGE_KEYS if HIBERNATION + select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT @@ -117,6 +118,7 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index cf3c0089bef2..23223cd63e54 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -820,6 +820,9 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func, else memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE); spin_unlock(&ctrblk_lock); + } else { + if (!nbytes) + memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE); } /* * final block may be < AES_BLOCK_SIZE, copy only nbytes diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 0a5aac8a9412..7acb77f7ef1a 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -429,6 +429,9 @@ static int ctr_desall_crypt(struct blkcipher_desc *desc, long func, else memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE); spin_unlock(&ctrblk_lock); + } else { + if (!nbytes) + memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE); } /* final block may be < DES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index fa9aaf7144b7..1d4706114a45 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -15,23 +15,29 @@ #include <linux/compiler.h> #include <linux/types.h> +#include <asm/barrier.h> #include <asm/cmpxchg.h> #define ATOMIC_INIT(i) { (i) } +#define __ATOMIC_NO_BARRIER "\n" + #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES #define __ATOMIC_OR "lao" #define __ATOMIC_AND "lan" #define __ATOMIC_ADD "laa" +#define __ATOMIC_BARRIER "bcr 14,0\n" -#define __ATOMIC_LOOP(ptr, op_val, op_string) \ +#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \ ({ \ int old_val; \ \ typecheck(atomic_t *, ptr); \ asm volatile( \ + __barrier \ op_string " %0,%2,%1\n" \ + __barrier \ : "=d" (old_val), "+Q" ((ptr)->counter) \ : "d" (op_val) \ : "cc", "memory"); \ @@ -43,8 +49,9 @@ #define __ATOMIC_OR "or" #define __ATOMIC_AND "nr" #define __ATOMIC_ADD "ar" +#define __ATOMIC_BARRIER "\n" -#define __ATOMIC_LOOP(ptr, op_val, op_string) \ +#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \ ({ \ int old_val, new_val; \ \ @@ -82,7 +89,7 @@ static inline void atomic_set(atomic_t *v, int i) static inline int atomic_add_return(int i, atomic_t *v) { - return __ATOMIC_LOOP(v, i, __ATOMIC_ADD) + i; + return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i; } static inline void atomic_add(int i, atomic_t *v) @@ -94,12 +101,10 @@ static inline void atomic_add(int i, atomic_t *v) : "+Q" (v->counter) : "i" (i) : "cc", "memory"); - } else { - atomic_add_return(i, v); + return; } -#else - atomic_add_return(i, v); #endif + __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_NO_BARRIER); } #define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0) @@ -115,12 +120,12 @@ static inline void atomic_add(int i, atomic_t *v) static inline void atomic_clear_mask(unsigned int mask, atomic_t *v) { - __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND); + __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER); } static inline void atomic_set_mask(unsigned int mask, atomic_t *v) { - __ATOMIC_LOOP(v, mask, __ATOMIC_OR); + __ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER); } #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) @@ -157,19 +162,24 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) #ifdef CONFIG_64BIT +#define __ATOMIC64_NO_BARRIER "\n" + #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES #define __ATOMIC64_OR "laog" #define __ATOMIC64_AND "lang" #define __ATOMIC64_ADD "laag" +#define __ATOMIC64_BARRIER "bcr 14,0\n" -#define __ATOMIC64_LOOP(ptr, op_val, op_string) \ +#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \ ({ \ long long old_val; \ \ typecheck(atomic64_t *, ptr); \ asm volatile( \ + __barrier \ op_string " %0,%2,%1\n" \ + __barrier \ : "=d" (old_val), "+Q" ((ptr)->counter) \ : "d" (op_val) \ : "cc", "memory"); \ @@ -181,8 +191,9 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) #define __ATOMIC64_OR "ogr" #define __ATOMIC64_AND "ngr" #define __ATOMIC64_ADD "agr" +#define __ATOMIC64_BARRIER "\n" -#define __ATOMIC64_LOOP(ptr, op_val, op_string) \ +#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \ ({ \ long long old_val, new_val; \ \ @@ -220,17 +231,32 @@ static inline void atomic64_set(atomic64_t *v, long long i) static inline long long atomic64_add_return(long long i, atomic64_t *v) { - return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD) + i; + return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i; +} + +static inline void atomic64_add(long long i, atomic64_t *v) +{ +#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES + if (__builtin_constant_p(i) && (i > -129) && (i < 128)) { + asm volatile( + "agsi %0,%1\n" + : "+Q" (v->counter) + : "i" (i) + : "cc", "memory"); + return; + } +#endif + __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER); } static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v) { - __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND); + __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER); } static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v) { - __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR); + __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER); } #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) @@ -334,25 +360,13 @@ static inline void atomic64_clear_mask(unsigned long long mask, atomic64_t *v) } while (atomic64_cmpxchg(v, old, new) != old); } -#endif /* CONFIG_64BIT */ - static inline void atomic64_add(long long i, atomic64_t *v) { -#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES - if (__builtin_constant_p(i) && (i > -129) && (i < 128)) { - asm volatile( - "agsi %0,%1\n" - : "+Q" (v->counter) - : "i" (i) - : "cc", "memory"); - } else { - atomic64_add_return(i, v); - } -#else atomic64_add_return(i, v); -#endif } +#endif /* CONFIG_64BIT */ + static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u) { long long c, old; diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 6e6ad0680829..4e206123b439 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -47,14 +47,18 @@ #include <linux/typecheck.h> #include <linux/compiler.h> +#include <asm/barrier.h> + +#define __BITOPS_NO_BARRIER "\n" #ifndef CONFIG_64BIT #define __BITOPS_OR "or" #define __BITOPS_AND "nr" #define __BITOPS_XOR "xr" +#define __BITOPS_BARRIER "\n" -#define __BITOPS_LOOP(__addr, __val, __op_string) \ +#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \ ({ \ unsigned long __old, __new; \ \ @@ -67,7 +71,7 @@ " jl 0b" \ : "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\ : "d" (__val) \ - : "cc"); \ + : "cc", "memory"); \ __old; \ }) @@ -78,17 +82,20 @@ #define __BITOPS_OR "laog" #define __BITOPS_AND "lang" #define __BITOPS_XOR "laxg" +#define __BITOPS_BARRIER "bcr 14,0\n" -#define __BITOPS_LOOP(__addr, __val, __op_string) \ +#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \ ({ \ unsigned long __old; \ \ typecheck(unsigned long *, (__addr)); \ asm volatile( \ + __barrier \ __op_string " %0,%2,%1\n" \ + __barrier \ : "=d" (__old), "+Q" (*(__addr)) \ : "d" (__val) \ - : "cc"); \ + : "cc", "memory"); \ __old; \ }) @@ -97,8 +104,9 @@ #define __BITOPS_OR "ogr" #define __BITOPS_AND "ngr" #define __BITOPS_XOR "xgr" +#define __BITOPS_BARRIER "\n" -#define __BITOPS_LOOP(__addr, __val, __op_string) \ +#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \ ({ \ unsigned long __old, __new; \ \ @@ -111,7 +119,7 @@ " jl 0b" \ : "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\ : "d" (__val) \ - : "cc"); \ + : "cc", "memory"); \ __old; \ }) @@ -149,12 +157,12 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr) "oi %0,%b1\n" : "+Q" (*caddr) : "i" (1 << (nr & 7)) - : "cc"); + : "cc", "memory"); return; } #endif mask = 1UL << (nr & (BITS_PER_LONG - 1)); - __BITOPS_LOOP(addr, mask, __BITOPS_OR); + __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_NO_BARRIER); } static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr) @@ -170,12 +178,12 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr) "ni %0,%b1\n" : "+Q" (*caddr) : "i" (~(1 << (nr & 7))) - : "cc"); + : "cc", "memory"); return; } #endif mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); - __BITOPS_LOOP(addr, mask, __BITOPS_AND); + __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_NO_BARRIER); } static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) @@ -191,12 +199,12 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) "xi %0,%b1\n" : "+Q" (*caddr) : "i" (1 << (nr & 7)) - : "cc"); + : "cc", "memory"); return; } #endif mask = 1UL << (nr & (BITS_PER_LONG - 1)); - __BITOPS_LOOP(addr, mask, __BITOPS_XOR); + __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_NO_BARRIER); } static inline int @@ -206,8 +214,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) unsigned long old, mask; mask = 1UL << (nr & (BITS_PER_LONG - 1)); - old = __BITOPS_LOOP(addr, mask, __BITOPS_OR); - barrier(); + old = __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_BARRIER); return (old & mask) != 0; } @@ -218,8 +225,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) unsigned long old, mask; mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); - old = __BITOPS_LOOP(addr, mask, __BITOPS_AND); - barrier(); + old = __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_BARRIER); return (old & ~mask) != 0; } @@ -230,8 +236,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) unsigned long old, mask; mask = 1UL << (nr & (BITS_PER_LONG - 1)); - old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR); - barrier(); + old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_BARRIER); return (old & mask) != 0; } diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index f201af8be580..31b5ca8f8c3d 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -219,7 +219,7 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *); #define to_ccwdev(n) container_of(n, struct ccw_device, dev) #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver) -extern struct ccw_device *ccw_device_probe_console(void); +extern struct ccw_device *ccw_device_probe_console(struct ccw_driver *); extern void ccw_device_wait_idle(struct ccw_device *); extern int ccw_device_force_console(struct ccw_device *); diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index bbf8141408cd..2bed4f02a558 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -142,9 +142,9 @@ struct _lowcore { __u8 pad_0x02fc[0x0300-0x02fc]; /* 0x02fc */ /* Interrupt response block */ - __u8 irb[64]; /* 0x0300 */ + __u8 irb[96]; /* 0x0300 */ - __u8 pad_0x0340[0x0e00-0x0340]; /* 0x0340 */ + __u8 pad_0x0360[0x0e00-0x0360]; /* 0x0360 */ /* * 0xe00 contains the address of the IPL Parameter Information @@ -288,12 +288,13 @@ struct _lowcore { __u8 pad_0x03a0[0x0400-0x03a0]; /* 0x03a0 */ /* Interrupt response block. */ - __u8 irb[64]; /* 0x0400 */ + __u8 irb[96]; /* 0x0400 */ + __u8 pad_0x0460[0x0480-0x0460]; /* 0x0460 */ /* Per cpu primary space access list */ - __u32 paste[16]; /* 0x0440 */ + __u32 paste[16]; /* 0x0480 */ - __u8 pad_0x0480[0x0e00-0x0480]; /* 0x0480 */ + __u8 pad_0x04c0[0x0e00-0x04c0]; /* 0x04c0 */ /* * 0xe00 contains the address of the IPL Parameter Information diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index f6be6087a0e9..184d305af3e7 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -64,7 +64,7 @@ void update_cr_regs(struct task_struct *task) if (task->thread.per_flags & PER_FLAG_NO_TE) cr_new &= ~(1UL << 55); if (cr_new != cr) - __ctl_load(cr, 0, 0); + __ctl_load(cr_new, 0, 0); /* Set or clear transaction execution TDC bits 62 and 63. */ __ctl_store(cr, 2, 2); cr_new = cr & ~3UL; @@ -323,9 +323,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) unsigned long mask = PSW_MASK_USER; mask |= is_ri_task(child) ? PSW_MASK_RI : 0; - if ((data & ~mask) != PSW_USER_BITS) + if ((data ^ PSW_USER_BITS) & ~mask) + /* Invalid psw mask. */ + return -EINVAL; + if ((data & PSW_MASK_ASC) == PSW_ASC_HOME) + /* Invalid address-space-control bits */ return -EINVAL; if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)) + /* Invalid addressing mode bits */ return -EINVAL; } *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; @@ -661,9 +666,12 @@ static int __poke_user_compat(struct task_struct *child, mask |= is_ri_task(child) ? PSW32_MASK_RI : 0; /* Build a 64 bit psw mask from 31 bit mask. */ - if ((tmp & ~mask) != PSW32_USER_BITS) + if ((tmp ^ PSW32_USER_BITS) & ~mask) /* Invalid psw mask. */ return -EINVAL; + if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME) + /* Invalid address-space-control bits */ + return -EINVAL; regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | (regs->psw.mask & PSW_MASK_BA) | (__u64)(tmp & mask) << 32; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index dd95f1631621..a80190be6e83 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -226,7 +226,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtom_clock_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; vdso_data->wtom_clock_nsec = tk->xtime_nsec + - + (tk->wall_to_monotonic.tv_nsec << tk->shift); + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift); nsecps = (u64) NSEC_PER_SEC << tk->shift; while (vdso_data->wtom_clock_nsec >= nsecps) { vdso_data->wtom_clock_nsec -= nsecps; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 5f79d2d79ca7..f1ba119878ec 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -71,6 +71,7 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, return 0; if (vcpu->arch.sie_block->gcr[0] & 0x2000ul) return 1; + return 0; case KVM_S390_INT_EMERGENCY: if (psw_extint_disabled(vcpu)) return 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e0676f390d57..95f4a976c160 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -753,7 +753,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) if (rc == 0) { if (kvm_is_ucontrol(vcpu->kvm)) - rc = -EOPNOTSUPP; + /* Don't exit for host interrupts. */ + rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0; else rc = kvm_handle_sie_intercept(vcpu); } diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index d261c62e40a6..248445f92604 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -223,11 +223,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmdp, int write) { diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 3584ed9b20a1..e309c5c41158 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -810,11 +810,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep; down_read(&mm->mmap_sem); +retry: ptep = get_locked_pte(current->mm, addr, &ptl); if (unlikely(!ptep)) { up_read(&mm->mmap_sem); return -EFAULT; } + if (!(pte_val(*ptep) & _PAGE_INVALID) && + (pte_val(*ptep) & _PAGE_PROTECT)) { + pte_unmap_unlock(*ptep, ptl); + if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) { + up_read(&mm->mmap_sem); + return -EFAULT; + } + goto retry; + } new = old = pgste_get_lock(ptep); pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT | diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 708d60e40066..8e08c6712eb8 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -276,7 +276,6 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter) case BPF_S_LD_W_IND: case BPF_S_LD_H_IND: case BPF_S_LD_B_IND: - case BPF_S_LDX_B_MSH: case BPF_S_LD_IMM: case BPF_S_LD_MEM: case BPF_S_MISC_TXA: @@ -812,7 +811,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int bpfsize, return NULL; memset(header, 0, sz); header->pages = sz / PAGE_SIZE; - hole = sz - (bpfsize + sizeof(*header)); + hole = min(sz - (bpfsize + sizeof(*header)), PAGE_SIZE - sizeof(*header)); /* Insert random number of illegal instructions before BPF code * and make sure the first instruction starts at an even address. */ diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index ff1465c0519c..5acf89c1afc5 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -118,7 +118,7 @@ static struct plat_sci_port scif0_platform_data = { }; static struct resource scif0_resources[] = { - DEFINE_RES_MEM(0xfffffe80, 0x100), + DEFINE_RES_MEM(0xfffffe80, 0x10), DEFINE_RES_IRQ(evt2irq(0x4e0)), }; @@ -143,7 +143,7 @@ static struct plat_sci_port scif1_platform_data = { }; static struct resource scif1_resources[] = { - DEFINE_RES_MEM(0xa4000150, 0x100), + DEFINE_RES_MEM(0xa4000150, 0x10), DEFINE_RES_IRQ(evt2irq(0x900)), }; @@ -169,7 +169,7 @@ static struct plat_sci_port scif2_platform_data = { }; static struct resource scif2_resources[] = { - DEFINE_RES_MEM(0xa4000140, 0x100), + DEFINE_RES_MEM(0xa4000140, 0x10), DEFINE_RES_IRQ(evt2irq(0x880)), }; diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c index b959f5592604..8dfe645bcc4b 100644 --- a/arch/sh/kernel/dumpstack.c +++ b/arch/sh/kernel/dumpstack.c @@ -115,7 +115,7 @@ static int print_trace_stack(void *data, char *name) */ static void print_trace_address(void *data, unsigned long addr, int reliable) { - printk(data); + printk("%s", (char *)data); printk_address(addr, reliable); } diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index 0d676a41081e..d7762349ea48 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -83,11 +83,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 7d8b7e94b93b..a38513c33a62 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -67,6 +67,7 @@ config SPARC64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_CONTEXT_TRACKING select HAVE_DEBUG_KMEMLEAK + select SPARSE_IRQ select RTC_DRV_CMOS select RTC_DRV_BQ4802 select RTC_DRV_SUN4V @@ -77,6 +78,7 @@ config SPARC64 select ARCH_HAVE_NMI_SAFE_CMPXCHG select HAVE_C_RECORDMCOUNT select NO_BOOTMEM + select ARCH_SUPPORTS_ATOMIC_RMW config ARCH_DEFCONFIG string diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index ca121f0fa3ec..17be9d618335 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2944,6 +2944,16 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num, unsigned long reg_val); #endif +#define HV_FAST_T5_GET_PERFREG 0x1a8 +#define HV_FAST_T5_SET_PERFREG 0x1a9 + +#ifndef __ASSEMBLY__ +unsigned long sun4v_t5_get_perfreg(unsigned long reg_num, + unsigned long *reg_val); +unsigned long sun4v_t5_set_perfreg(unsigned long reg_num, + unsigned long reg_val); +#endif + /* Function numbers for HV_CORE_TRAP. */ #define HV_CORE_SET_VER 0x00 #define HV_CORE_PUTCHAR 0x01 @@ -2975,6 +2985,7 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num, #define HV_GRP_VF_CPU 0x0205 #define HV_GRP_KT_CPU 0x0209 #define HV_GRP_VT_CPU 0x020c +#define HV_GRP_T5_CPU 0x0211 #define HV_GRP_DIAG 0x0300 #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index abf6afe82ca8..3deb07ff1e00 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -37,7 +37,7 @@ * * ino_bucket->irq allocation is made during {sun4v_,}build_irq(). */ -#define NR_IRQS 255 +#define NR_IRQS (2048) extern void irq_install_pre_handler(int irq, void (*func)(unsigned int, void *, void *), @@ -57,11 +57,8 @@ extern unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p, unsigned long iclr_base); extern void sun4u_destroy_msi(unsigned int irq); -extern unsigned char irq_alloc(unsigned int dev_handle, - unsigned int dev_ino); -#ifdef CONFIG_PCI_MSI -extern void irq_free(unsigned int irq); -#endif +unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino); +void irq_free(unsigned int irq); extern void __init init_IRQ(void); extern void fixup_irqs(void); diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h index bdb524a7b814..8732ed391aff 100644 --- a/arch/sparc/include/asm/ldc.h +++ b/arch/sparc/include/asm/ldc.h @@ -53,13 +53,14 @@ struct ldc_channel; /* Allocate state for a channel. */ extern struct ldc_channel *ldc_alloc(unsigned long id, const struct ldc_channel_config *cfgp, - void *event_arg); + void *event_arg, + const char *name); /* Shut down and free state for a channel. */ extern void ldc_free(struct ldc_channel *lp); /* Register TX and RX queues of the link with the hypervisor. */ -extern int ldc_bind(struct ldc_channel *lp, const char *name); +extern int ldc_bind(struct ldc_channel *lp); /* For non-RAW protocols we need to complete a handshake before * communication can proceed. ldc_connect() does that, if the diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a12dbe3b7762..e48fdf4e16ff 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -62,7 +62,8 @@ struct linux_mem_p1275 { /* You must call prom_init() before using any of the library services, * preferably as early as possible. Pass it the romvec pointer. */ -extern void prom_init(void *cif_handler, void *cif_stack); +extern void prom_init(void *cif_handler); +extern void prom_init_report(void); /* Boot argument acquisition, returns the boot command line string. */ extern char *prom_getbootargs(void); diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index aac53fcea807..b18e602fcac4 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -57,18 +57,21 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct pag typedef struct { unsigned long pte; } pte_t; typedef struct { unsigned long iopte; } iopte_t; typedef struct { unsigned long pmd; } pmd_t; +typedef struct { unsigned long pud; } pud_t; typedef struct { unsigned long pgd; } pgd_t; typedef struct { unsigned long pgprot; } pgprot_t; #define pte_val(x) ((x).pte) #define iopte_val(x) ((x).iopte) #define pmd_val(x) ((x).pmd) +#define pud_val(x) ((x).pud) #define pgd_val(x) ((x).pgd) #define pgprot_val(x) ((x).pgprot) #define __pte(x) ((pte_t) { (x) } ) #define __iopte(x) ((iopte_t) { (x) } ) #define __pmd(x) ((pmd_t) { (x) } ) +#define __pud(x) ((pud_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) @@ -77,18 +80,21 @@ typedef struct { unsigned long pgprot; } pgprot_t; typedef unsigned long pte_t; typedef unsigned long iopte_t; typedef unsigned long pmd_t; +typedef unsigned long pud_t; typedef unsigned long pgd_t; typedef unsigned long pgprot_t; #define pte_val(x) (x) #define iopte_val(x) (x) #define pmd_val(x) (x) +#define pud_val(x) (x) #define pgd_val(x) (x) #define pgprot_val(x) (x) #define __pte(x) (x) #define __iopte(x) (x) #define __pmd(x) (x) +#define __pud(x) (x) #define __pgd(x) (x) #define __pgprot(x) (x) @@ -96,21 +102,14 @@ typedef unsigned long pgprot_t; typedef pte_t *pgtable_t; -/* These two values define the virtual address space range in which we - * must forbid 64-bit user processes from making mappings. It used to - * represent precisely the virtual address space hole present in most - * early sparc64 chips including UltraSPARC-I. But now it also is - * further constrained by the limits of our page tables, which is - * 43-bits of virtual address. - */ -#define SPARC64_VA_HOLE_TOP _AC(0xfffffc0000000000,UL) -#define SPARC64_VA_HOLE_BOTTOM _AC(0x0000040000000000,UL) +extern unsigned long sparc64_va_hole_top; +extern unsigned long sparc64_va_hole_bottom; /* The next two defines specify the actual exclusion region we * enforce, wherein we use a 4GB red zone on each side of the VA hole. */ -#define VA_EXCLUDE_START (SPARC64_VA_HOLE_BOTTOM - (1UL << 32UL)) -#define VA_EXCLUDE_END (SPARC64_VA_HOLE_TOP + (1UL << 32UL)) +#define VA_EXCLUDE_START (sparc64_va_hole_bottom - (1UL << 32UL)) +#define VA_EXCLUDE_END (sparc64_va_hole_top + (1UL << 32UL)) #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_32BIT) ? \ _AC(0x0000000070000000,UL) : \ @@ -118,20 +117,16 @@ typedef pte_t *pgtable_t; #include <asm-generic/memory_model.h> -#define PAGE_OFFSET_BY_BITS(X) (-(_AC(1,UL) << (X))) extern unsigned long PAGE_OFFSET; #endif /* !(__ASSEMBLY__) */ -/* The maximum number of physical memory address bits we support, this - * is used to size various tables used to manage kernel TLB misses and - * also the sparsemem code. +/* The maximum number of physical memory address bits we support. The + * largest value we can support is whatever "KPGD_SHIFT + KPTE_BITS" + * evaluates to. */ -#define MAX_PHYS_ADDRESS_BITS 47 +#define MAX_PHYS_ADDRESS_BITS 53 -/* These two shift counts are used when indexing sparc64_valid_addr_bitmap - * and kpte_linear_bitmap. - */ #define ILOG2_4MB 22 #define ILOG2_256MB 28 diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index bcfe063bce23..2c8d41fb13a4 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -15,6 +15,13 @@ extern struct kmem_cache *pgtable_cache; +static inline void __pgd_populate(pgd_t *pgd, pud_t *pud) +{ + pgd_set(pgd, pud); +} + +#define pgd_populate(MM, PGD, PUD) __pgd_populate(PGD, PUD) + static inline pgd_t *pgd_alloc(struct mm_struct *mm) { return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); @@ -25,7 +32,23 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(pgtable_cache, pgd); } -#define pud_populate(MM, PUD, PMD) pud_set(PUD, PMD) +static inline void __pud_populate(pud_t *pud, pmd_t *pmd) +{ + pud_set(pud, pmd); +} + +#define pud_populate(MM, PUD, PMD) __pud_populate(PUD, PMD) + +static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return kmem_cache_alloc(pgtable_cache, + GFP_KERNEL|__GFP_REPEAT); +} + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + kmem_cache_free(pgtable_cache, pud); +} static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { @@ -91,4 +114,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pte_t *pte, #define __pmd_free_tlb(tlb, pmd, addr) \ pgtable_free_tlb(tlb, pmd, false) +#define __pud_free_tlb(tlb, pud, addr) \ + pgtable_free_tlb(tlb, pud, false) + #endif /* _SPARC64_PGALLOC_H */ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 0f9e94537eee..e8dfabf156c7 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -20,11 +20,10 @@ #include <asm/page.h> #include <asm/processor.h> -#include <asm-generic/pgtable-nopud.h> - /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB). * The page copy blockops can use 0x6000000 to 0x8000000. - * The TSB is mapped in the 0x8000000 to 0xa000000 range. + * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range. + * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range. * The PROM resides in an area spanning 0xf0000000 to 0x100000000. * The vmalloc area spans 0x100000000 to 0x200000000. * Since modules need to be in the lowest 32-bits of the address space, @@ -33,17 +32,15 @@ * 0x400000000. */ #define TLBTEMP_BASE _AC(0x0000000006000000,UL) -#define TSBMAP_BASE _AC(0x0000000008000000,UL) +#define TSBMAP_8K_BASE _AC(0x0000000008000000,UL) +#define TSBMAP_4M_BASE _AC(0x0000000008400000,UL) #define MODULES_VADDR _AC(0x0000000010000000,UL) #define MODULES_LEN _AC(0x00000000e0000000,UL) #define MODULES_END _AC(0x00000000f0000000,UL) #define LOW_OBP_ADDRESS _AC(0x00000000f0000000,UL) #define HI_OBP_ADDRESS _AC(0x0000000100000000,UL) #define VMALLOC_START _AC(0x0000000100000000,UL) -#define VMALLOC_END _AC(0x0000010000000000,UL) -#define VMEMMAP_BASE _AC(0x0000010000000000,UL) - -#define vmemmap ((struct page *)VMEMMAP_BASE) +#define VMEMMAP_BASE VMALLOC_END /* PMD_SHIFT determines the size of the area a second-level page * table can map @@ -53,13 +50,25 @@ #define PMD_MASK (~(PMD_SIZE-1)) #define PMD_BITS (PAGE_SHIFT - 3) -/* PGDIR_SHIFT determines what a third-level page table entry can map */ -#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-3) + PMD_BITS) +/* PUD_SHIFT determines the size of the area a third-level page + * table can map + */ +#define PUD_SHIFT (PMD_SHIFT + PMD_BITS) +#define PUD_SIZE (_AC(1,UL) << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) +#define PUD_BITS (PAGE_SHIFT - 3) + +/* PGDIR_SHIFT determines what a fourth-level page table entry can map */ +#define PGDIR_SHIFT (PUD_SHIFT + PUD_BITS) #define PGDIR_SIZE (_AC(1,UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) #define PGDIR_BITS (PAGE_SHIFT - 3) -#if (PGDIR_SHIFT + PGDIR_BITS) != 43 +#if (MAX_PHYS_ADDRESS_BITS > PGDIR_SHIFT + PGDIR_BITS) +#error MAX_PHYS_ADDRESS_BITS exceeds what kernel page tables can support +#endif + +#if (PGDIR_SHIFT + PGDIR_BITS) != 53 #error Page table parameters do not cover virtual address space properly. #endif @@ -69,19 +78,32 @@ #ifndef __ASSEMBLY__ +extern unsigned long VMALLOC_END; + +#define vmemmap ((struct page *)VMEMMAP_BASE) + #include <linux/sched.h> +bool kern_addr_valid(unsigned long addr); + /* Entries per page directory level. */ #define PTRS_PER_PTE (1UL << (PAGE_SHIFT-3)) #define PTRS_PER_PMD (1UL << PMD_BITS) +#define PTRS_PER_PUD (1UL << PUD_BITS) #define PTRS_PER_PGD (1UL << PGDIR_BITS) /* Kernel has a separate 44bit address space. */ #define FIRST_USER_ADDRESS 0 -#define pte_ERROR(e) __builtin_trap() -#define pmd_ERROR(e) __builtin_trap() -#define pgd_ERROR(e) __builtin_trap() +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n", \ + __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0)) +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %p(%016lx) seen at (%pS)\n", \ + __FILE__, __LINE__, &(e), pud_val(e), __builtin_return_address(0)) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n", \ + __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0)) #endif /* !(__ASSEMBLY__) */ @@ -90,6 +112,7 @@ #define _PAGE_R _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/ #define _PAGE_SPECIAL _AC(0x0200000000000000,UL) /* Special page */ #define _PAGE_PMD_HUGE _AC(0x0100000000000000,UL) /* Huge page */ +#define _PAGE_PUD_HUGE _PAGE_PMD_HUGE /* Advertise support for _PAGE_SPECIAL */ #define __HAVE_ARCH_PTE_SPECIAL @@ -258,8 +281,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) { unsigned long mask, tmp; - /* SUN4U: 0x600307ffffffecb8 (negated == 0x9ffcf80000001347) - * SUN4V: 0x30ffffffffffee17 (negated == 0xcf000000000011e8) + /* SUN4U: 0x630107ffffffec38 (negated == 0x9cfef800000013c7) + * SUN4V: 0x33ffffffffffee07 (negated == 0xcc000000000011f8) * * Even if we use negation tricks the result is still a 6 * instruction sequence, so don't try to play fancy and just @@ -289,10 +312,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) " .previous\n" : "=r" (mask), "=r" (tmp) : "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U | - _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U | + _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U), "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V | - _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V | + _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V)); return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask)); @@ -633,29 +656,29 @@ static inline unsigned long pmd_large(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return (pte_val(pte) & _PAGE_PMD_HUGE) && pte_present(pte); + return pte_val(pte) & _PAGE_PMD_HUGE; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline unsigned long pmd_young(pmd_t pmd) +static inline unsigned long pmd_pfn(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_young(pte); + return pte_pfn(pte); } -static inline unsigned long pmd_write(pmd_t pmd) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +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_pfn(pmd_t pmd) +static inline unsigned long pmd_write(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_pfn(pte); + return pte_write(pte); } static inline unsigned long pmd_trans_huge(pmd_t pmd) @@ -719,20 +742,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mknotpresent(pmd_t pmd) -{ - unsigned long mask; - - if (tlb_type == hypervisor) - mask = _PAGE_PRESENT_4V; - else - mask = _PAGE_PRESENT_4U; - - pmd_val(pmd) &= ~mask; - - return pmd; -} - static inline pmd_t pmd_mksplitting(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); @@ -757,6 +766,22 @@ static inline int pmd_present(pmd_t pmd) #define pmd_none(pmd) (!pmd_val(pmd)) +/* pmd_bad() is only called on non-trans-huge PMDs. Our encoding is + * very simple, it's just the physical address. PTE tables are of + * size PAGE_SIZE so make sure the sub-PAGE_SIZE bits are clear and + * the top bits outside of the range of any physical address size we + * support are clear as well. We also validate the physical itself. + */ +#define pmd_bad(pmd) (pmd_val(pmd) & ~PAGE_MASK) + +#define pud_none(pud) (!pud_val(pud)) + +#define pud_bad(pud) (pud_val(pud) & ~PAGE_MASK) + +#define pgd_none(pgd) (!pgd_val(pgd)) + +#define pgd_bad(pgd) (pgd_val(pgd) & ~PAGE_MASK) + #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); @@ -790,16 +815,34 @@ static inline unsigned long __pmd_page(pmd_t pmd) #define pud_page_vaddr(pud) \ ((unsigned long) __va(pud_val(pud))) #define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud)) -#define pmd_bad(pmd) (0) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL) -#define pud_none(pud) (!pud_val(pud)) -#define pud_bad(pud) (0) #define pud_present(pud) (pud_val(pud) != 0U) #define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) +#define pgd_page_vaddr(pgd) \ + ((unsigned long) __va(pgd_val(pgd))) +#define pgd_present(pgd) (pgd_val(pgd) != 0U) +#define pgd_clear(pgdp) (pgd_val(*(pgd)) = 0UL) + +static inline unsigned long pud_large(pud_t pud) +{ + pte_t pte = __pte(pud_val(pud)); + + return pte_val(pte) & _PAGE_PMD_HUGE; +} + +static inline unsigned long pud_pfn(pud_t pud) +{ + pte_t pte = __pte(pud_val(pud)); + + return pte_pfn(pte); +} /* Same in both SUN4V and SUN4U. */ #define pte_none(pte) (!pte_val(pte)) +#define pgd_set(pgdp, pudp) \ + (pgd_val(*(pgdp)) = (__pa((unsigned long) (pudp)))) + /* to find an entry in a page-table-directory. */ #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) @@ -807,6 +850,11 @@ static inline unsigned long __pmd_page(pmd_t pmd) /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) +/* Find an entry in the third-level page table.. */ +#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) +#define pud_offset(pgdp, address) \ + ((pud_t *) pgd_page_vaddr(*(pgdp)) + pud_index(address)) + /* Find an entry in the second-level page table.. */ #define pmd_offset(pudp, address) \ ((pmd_t *) pud_page_vaddr(*(pudp)) + \ @@ -879,7 +927,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, #endif extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; -extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD]; extern void paging_init(void); extern unsigned long find_ecache_flush_span(unsigned long size); @@ -893,6 +940,10 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd); +#define __HAVE_ARCH_PMDP_INVALIDATE +extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); + #define __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); @@ -919,18 +970,6 @@ extern unsigned long pte_file(pte_t); extern pte_t pgoff_to_pte(unsigned long); #define PTE_FILE_MAX_BITS (64UL - PAGE_SHIFT - 1UL) -extern unsigned long sparc64_valid_addr_bitmap[]; - -/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */ -static inline bool kern_addr_valid(unsigned long addr) -{ - unsigned long paddr = __pa(addr); - - if ((paddr >> 41UL) != 0UL) - return false; - return test_bit(paddr >> 22, sparc64_valid_addr_bitmap); -} - extern int page_in_phys_avail(unsigned long paddr); /* diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 5e35e0517318..acd614668ec1 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -24,6 +24,10 @@ static inline int con_is_present(void) } #endif +#ifdef CONFIG_SPARC64 +extern void __init start_early_boot(void); +#endif + extern void sun_do_break(void); extern int stop_a_enabled; extern int scons_pwroff; diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index 6b67e50fb9b4..69424d48cbb7 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -45,6 +45,8 @@ #define SUN4V_CHIP_NIAGARA3 0x03 #define SUN4V_CHIP_NIAGARA4 0x04 #define SUN4V_CHIP_NIAGARA5 0x05 +#define SUN4V_CHIP_SPARC_M6 0x06 +#define SUN4V_CHIP_SPARC_M7 0x07 #define SUN4V_CHIP_SPARC64X 0x8a #define SUN4V_CHIP_UNKNOWN 0xff diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index a5f01ac6d0f1..cc6275c931a5 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -63,7 +63,8 @@ struct thread_info { struct pt_regs *kern_una_regs; unsigned int kern_una_insn; - unsigned long fpregs[0] __attribute__ ((aligned(64))); + unsigned long fpregs[(7 * 256) / sizeof(unsigned long)] + __attribute__ ((aligned(64))); }; #endif /* !(__ASSEMBLY__) */ @@ -102,6 +103,7 @@ struct thread_info { #define FAULT_CODE_ITLB 0x04 /* Miss happened in I-TLB */ #define FAULT_CODE_WINFIXUP 0x08 /* Miss happened during spill/fill */ #define FAULT_CODE_BLKCOMMIT 0x10 /* Use blk-commit ASI in copy_page */ +#define FAULT_CODE_BAD_RA 0x20 /* Bad RA for sun4v */ #if PAGE_SHIFT == 13 #define THREAD_SIZE (2*PAGE_SIZE) diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 3c3c89f52643..7f9bab26a499 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -34,6 +34,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, { } +void flush_tlb_kernel_range(unsigned long start, unsigned long end); + #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE extern void flush_tlb_pending(void); @@ -48,11 +50,6 @@ extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP -#define flush_tlb_kernel_range(start,end) \ -do { flush_tsb_kernel_range(start,end); \ - __flush_tlb_kernel_range(start,end); \ -} while (0) - static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); @@ -63,11 +60,6 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); -#define flush_tlb_kernel_range(start, end) \ -do { flush_tsb_kernel_range(start,end); \ - smp_flush_tlb_kernel_range(start, end); \ -} while (0) - #define global_flush_tlb_page(mm, vaddr) \ smp_flush_tlb_page(mm, vaddr) diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index 2230f80d9fe3..ecb49cfa3be9 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -133,9 +133,24 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; sub TSB, 0x8, TSB; \ TSB_STORE(TSB, TAG); - /* Do a kernel page table walk. Leaves physical PTE pointer in - * REG1. Jumps to FAIL_LABEL on early page table walk termination. - * VADDR will not be clobbered, but REG2 will. + /* Do a kernel page table walk. Leaves valid PTE value in + * REG1. Jumps to FAIL_LABEL on early page table walk + * termination. VADDR will not be clobbered, but REG2 will. + * + * There are two masks we must apply to propagate bits from + * the virtual address into the PTE physical address field + * when dealing with huge pages. This is because the page + * table boundaries do not match the huge page size(s) the + * hardware supports. + * + * In these cases we propagate the bits that are below the + * page table level where we saw the huge page mapping, but + * are still within the relevant physical bits for the huge + * page size in question. So for PMD mappings (which fall on + * bit 23, for 8MB per PMD) we must propagate bit 22 for a + * 4MB huge page. For huge PUDs (which fall on bit 33, for + * 8GB per PUD), we have to accomodate 256MB and 2GB huge + * pages. So for those we propagate bits 32 to 28. */ #define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL) \ sethi %hi(swapper_pg_dir), REG1; \ @@ -145,15 +160,40 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andn REG2, 0x7, REG2; \ ldx [REG1 + REG2], REG1; \ brz,pn REG1, FAIL_LABEL; \ - sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ + sllx VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ - sllx VADDR, 64 - PMD_SHIFT, REG2; \ + sethi %uhi(_PAGE_PUD_HUGE), REG2; \ + brz,pn REG1, FAIL_LABEL; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + sethi %hi(0xf8000000), REG2; \ + bne,pt %xcc, 697f; \ + sllx REG2, 1, REG2; \ + sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ - add REG1, REG2, REG1; + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + sethi %uhi(_PAGE_PMD_HUGE), REG2; \ + brz,pn REG1, FAIL_LABEL; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + be,pn %xcc, 698f; \ + sethi %hi(0x400000), REG2; \ +697: brgez,pn REG1, FAIL_LABEL; \ + andn REG1, REG2, REG1; \ + and VADDR, REG2, REG2; \ + ba,pt %xcc, 699f; \ + or REG1, REG2, REG1; \ +698: sllx VADDR, 64 - PMD_SHIFT, REG2; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + brgez,pn REG1, FAIL_LABEL; \ + nop; \ +699: /* PMD has been loaded into REG1, interpret the value, seeing * if it is a HUGE PMD or a normal one. If it is not valid @@ -171,7 +211,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andcc REG1, REG2, %g0; \ be,pt %xcc, 700f; \ sethi %hi(4 * 1024 * 1024), REG2; \ - andn REG1, REG2, REG1; \ + brgez,pn REG1, FAIL_LABEL; \ + andn REG1, REG2, REG1; \ and VADDR, REG2, REG2; \ brlz,pt REG1, PTE_LABEL; \ or REG1, REG2, REG1; \ @@ -197,6 +238,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andn REG2, 0x7, REG2; \ ldxa [PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ + sllx VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + brz,pn REG1, FAIL_LABEL; \ sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ @@ -245,8 +291,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; (KERNEL_TSB_SIZE_BYTES / 16) #define KERNEL_TSB4M_NENTRIES 4096 -#define KTSB_PHYS_SHIFT 15 - /* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL * on TSB hit. REG1, REG2, REG3, and REG4 are used as temporaries * and the found TTE will be left in REG1. REG3 and REG4 must @@ -255,17 +299,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * VADDR and TAG will be preserved and not clobbered by this macro. */ #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ -661: sethi %hi(swapper_tsb), REG1; \ - or REG1, %lo(swapper_tsb), REG1; \ +661: sethi %uhi(swapper_tsb), REG1; \ + sethi %hi(swapper_tsb), REG2; \ + or REG1, %ulo(swapper_tsb), REG1; \ + or REG2, %lo(swapper_tsb), REG2; \ .section .swapper_tsb_phys_patch, "ax"; \ .word 661b; \ .previous; \ -661: nop; \ - .section .tsb_ldquad_phys_patch, "ax"; \ - .word 661b; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - .previous; \ + sllx REG1, 32, REG1; \ + or REG1, REG2, REG1; \ srlx VADDR, PAGE_SHIFT, REG2; \ and REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ @@ -280,17 +322,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * we can make use of that for the index computation. */ #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ -661: sethi %hi(swapper_4m_tsb), REG1; \ - or REG1, %lo(swapper_4m_tsb), REG1; \ +661: sethi %uhi(swapper_4m_tsb), REG1; \ + sethi %hi(swapper_4m_tsb), REG2; \ + or REG1, %ulo(swapper_4m_tsb), REG1; \ + or REG2, %lo(swapper_4m_tsb), REG2; \ .section .swapper_4m_tsb_phys_patch, "ax"; \ .word 661b; \ .previous; \ -661: nop; \ - .section .tsb_ldquad_phys_patch, "ax"; \ - .word 661b; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - .previous; \ + sllx REG1, 32, REG1; \ + or REG1, REG2, REG1; \ and TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ add REG1, REG2, REG2; \ diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h index 39ca301920db..11fdf0ef50bb 100644 --- a/arch/sparc/include/asm/visasm.h +++ b/arch/sparc/include/asm/visasm.h @@ -39,6 +39,14 @@ 297: wr %o5, FPRS_FEF, %fprs; \ 298: +#define VISEntryHalfFast(fail_label) \ + rd %fprs, %o5; \ + andcc %o5, FPRS_FEF, %g0; \ + be,pt %icc, 297f; \ + nop; \ + ba,a,pt %xcc, fail_label; \ +297: wr %o5, FPRS_FEF, %fprs; + #define VISExitHalf \ wr %o5, 0, %fprs; diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index 5c5125895db8..52e10defedc4 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -493,6 +493,18 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "niagara5"; break; + case SUN4V_CHIP_SPARC_M6: + sparc_cpu_type = "SPARC-M6"; + sparc_fpu_type = "SPARC-M6 integrated FPU"; + sparc_pmu_type = "sparc-m6"; + break; + + case SUN4V_CHIP_SPARC_M7: + sparc_cpu_type = "SPARC-M7"; + sparc_fpu_type = "SPARC-M7 integrated FPU"; + sparc_pmu_type = "sparc-m7"; + break; + case SUN4V_CHIP_SPARC64X: sparc_cpu_type = "SPARC64-X"; sparc_fpu_type = "SPARC64-X integrated FPU"; diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index de1c844dfabc..e69ec0e3f155 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -326,6 +326,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) case SUN4V_CHIP_NIAGARA3: case SUN4V_CHIP_NIAGARA4: case SUN4V_CHIP_NIAGARA5: + case SUN4V_CHIP_SPARC_M6: + case SUN4V_CHIP_SPARC_M7: case SUN4V_CHIP_SPARC64X: rover_inc_table = niagara_iterate_method; break; diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index dff60abbea01..f87a55d77094 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -1200,14 +1200,14 @@ static int ds_probe(struct vio_dev *vdev, const struct vio_device_id *id) ds_cfg.tx_irq = vdev->tx_irq; ds_cfg.rx_irq = vdev->rx_irq; - lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp); + lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp, "DS"); if (IS_ERR(lp)) { err = PTR_ERR(lp); goto out_free_ds_states; } dp->lp = lp; - err = ldc_bind(lp, "DS"); + err = ldc_bind(lp); if (err) goto out_free_ldc; diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S index b2c2c5be281c..d668ca149e64 100644 --- a/arch/sparc/kernel/dtlb_prot.S +++ b/arch/sparc/kernel/dtlb_prot.S @@ -24,11 +24,11 @@ mov TLB_TAG_ACCESS, %g4 ! For reload of vaddr /* PROT ** ICACHE line 2: More real fault processing */ + ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5 bgu,pn %xcc, winfix_trampoline ! Yes, perform winfixup - ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5 - ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault mov FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4 - nop + ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault + nop nop nop nop diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index 140966fbd303..c88ffb9ee482 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -66,13 +66,10 @@ struct pause_patch_entry { extern struct pause_patch_entry __pause_3insn_patch, __pause_3insn_patch_end; -extern void __init per_cpu_patch(void); extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *, struct sun4v_1insn_patch_entry *); extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *, struct sun4v_2insn_patch_entry *); -extern void __init sun4v_patch(void); -extern void __init boot_cpu_id_too_large(int cpu); extern unsigned int dcache_parity_tl1_occurred; extern unsigned int icache_parity_tl1_occurred; diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 26b706a1867d..3d61fcae7ee3 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -282,8 +282,8 @@ sun4v_chip_type: stx %l2, [%l4 + 0x0] ldx [%sp + 2047 + 128 + 0x50], %l3 ! physaddr low /* 4MB align */ - srlx %l3, 22, %l3 - sllx %l3, 22, %l3 + srlx %l3, ILOG2_4MB, %l3 + sllx %l3, ILOG2_4MB, %l3 stx %l3, [%l4 + 0x8] /* Leave service as-is, "call-method" */ @@ -427,6 +427,12 @@ sun4v_chip_type: cmp %g2, '5' be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA5, %g4 + cmp %g2, '6' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_M6, %g4 + cmp %g2, '7' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_M7, %g4 ba,pt %xcc, 49f nop @@ -585,6 +591,12 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_NIAGARA5 be,pt %xcc, niagara4_patch nop + cmp %g1, SUN4V_CHIP_SPARC_M6 + be,pt %xcc, niagara4_patch + nop + cmp %g1, SUN4V_CHIP_SPARC_M7 + be,pt %xcc, niagara4_patch + nop call generic_patch_copyops nop @@ -660,14 +672,12 @@ tlb_fixup_done: sethi %hi(init_thread_union), %g6 or %g6, %lo(init_thread_union), %g6 ldx [%g6 + TI_TASK], %g4 - mov %sp, %l6 wr %g0, ASI_P, %asi mov 1, %g1 sllx %g1, THREAD_SHIFT, %g1 sub %g1, (STACKFRAME_SZ + STACK_BIAS), %g1 add %g6, %g1, %sp - mov 0, %fp /* Set per-cpu pointer initially to zero, this makes * the boot-cpu use the in-kernel-image per-cpu areas @@ -694,44 +704,14 @@ tlb_fixup_done: nop #endif - mov %l6, %o1 ! OpenPROM stack call prom_init mov %l7, %o0 ! OpenPROM cif handler - /* Initialize current_thread_info()->cpu as early as possible. - * In order to do that accurately we have to patch up the get_cpuid() - * assembler sequences. And that, in turn, requires that we know - * if we are on a Starfire box or not. While we're here, patch up - * the sun4v sequences as well. + /* To create a one-register-window buffer between the kernel's + * initial stack and the last stack frame we use from the firmware, + * do the rest of the boot from a C helper function. */ - call check_if_starfire - nop - call per_cpu_patch - nop - call sun4v_patch - nop - -#ifdef CONFIG_SMP - call hard_smp_processor_id - nop - cmp %o0, NR_CPUS - blu,pt %xcc, 1f - nop - call boot_cpu_id_too_large - nop - /* Not reached... */ - -1: -#else - mov 0, %o0 -#endif - sth %o0, [%g6 + TI_CPU] - - call prom_init_report - nop - - /* Off we go.... */ - call start_kernel + call start_early_boot nop /* Not reached... */ diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index c0a2de0fd624..5c55145bfbf0 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -46,6 +46,7 @@ static struct api_info api_table[] = { { .group = HV_GRP_VF_CPU, }, { .group = HV_GRP_KT_CPU, }, { .group = HV_GRP_VT_CPU, }, + { .group = HV_GRP_T5_CPU, }, { .group = HV_GRP_DIAG, .flags = FLAG_PRE_API }, }; diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index f3ab509b76a8..caedf8320416 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -821,3 +821,19 @@ ENTRY(sun4v_vt_set_perfreg) retl nop ENDPROC(sun4v_vt_set_perfreg) + +ENTRY(sun4v_t5_get_perfreg) + mov %o1, %o4 + mov HV_FAST_T5_GET_PERFREG, %o5 + ta HV_FAST_TRAP + stx %o1, [%o4] + retl + nop +ENDPROC(sun4v_t5_get_perfreg) + +ENTRY(sun4v_t5_set_perfreg) + mov HV_FAST_T5_SET_PERFREG, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(sun4v_t5_set_perfreg) diff --git a/arch/sparc/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S index b7ddcdd1dea9..cdbfec299f2f 100644 --- a/arch/sparc/kernel/hvtramp.S +++ b/arch/sparc/kernel/hvtramp.S @@ -109,7 +109,6 @@ hv_cpu_startup: sllx %g5, THREAD_SHIFT, %g5 sub %g5, (STACKFRAME_SZ + STACK_BIAS), %g5 add %g6, %g5, %sp - mov 0, %fp call init_irqwork_curcpu nop diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index e7e215dfa866..c2d81ad62e78 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -278,7 +278,8 @@ static void *sbus_alloc_coherent(struct device *dev, size_t len, } order = get_order(len_total); - if ((va = __get_free_pages(GFP_KERNEL|__GFP_COMP, order)) == 0) + va = __get_free_pages(gfp, order); + if (va == 0) goto err_nopages; if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL) @@ -443,7 +444,7 @@ static void *pci32_alloc_coherent(struct device *dev, size_t len, } order = get_order(len_total); - va = (void *) __get_free_pages(GFP_KERNEL, order); + va = (void *) __get_free_pages(gfp, order); if (va == NULL) { printk("pci_alloc_consistent: no %ld pages\n", len_total>>PAGE_SHIFT); goto err_nopages; diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 666193f4e8bb..4033c23bdfa6 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -47,8 +47,6 @@ #include "cpumap.h" #include "kstack.h" -#define NUM_IVECS (IMAP_INR + 1) - struct ino_bucket *ivector_table; unsigned long ivector_table_pa; @@ -107,55 +105,196 @@ static void bucket_set_irq(unsigned long bucket_pa, unsigned int irq) #define irq_work_pa(__cpu) &(trap_block[(__cpu)].irq_worklist_pa) -static struct { - unsigned int dev_handle; - unsigned int dev_ino; - unsigned int in_use; -} irq_table[NR_IRQS]; -static DEFINE_SPINLOCK(irq_alloc_lock); +static unsigned long hvirq_major __initdata; +static int __init early_hvirq_major(char *p) +{ + int rc = kstrtoul(p, 10, &hvirq_major); + + return rc; +} +early_param("hvirq", early_hvirq_major); + +static int hv_irq_version; + +/* Major version 2.0 of HV_GRP_INTR added support for the VIRQ cookie + * based interfaces, but: + * + * 1) Several OSs, Solaris and Linux included, use them even when only + * negotiating version 1.0 (or failing to negotiate at all). So the + * hypervisor has a workaround that provides the VIRQ interfaces even + * when only verion 1.0 of the API is in use. + * + * 2) Second, and more importantly, with major version 2.0 these VIRQ + * interfaces only were actually hooked up for LDC interrupts, even + * though the Hypervisor specification clearly stated: + * + * The new interrupt API functions will be available to a guest + * when it negotiates version 2.0 in the interrupt API group 0x2. When + * a guest negotiates version 2.0, all interrupt sources will only + * support using the cookie interface, and any attempt to use the + * version 1.0 interrupt APIs numbered 0xa0 to 0xa6 will result in the + * ENOTSUPPORTED error being returned. + * + * with an emphasis on "all interrupt sources". + * + * To correct this, major version 3.0 was created which does actually + * support VIRQs for all interrupt sources (not just LDC devices). So + * if we want to move completely over the cookie based VIRQs we must + * negotiate major version 3.0 or later of HV_GRP_INTR. + */ +static bool sun4v_cookie_only_virqs(void) +{ + if (hv_irq_version >= 3) + return true; + return false; +} -unsigned char irq_alloc(unsigned int dev_handle, unsigned int dev_ino) +static void __init irq_init_hv(void) { - unsigned long flags; - unsigned char ent; + unsigned long hv_error, major, minor = 0; + + if (tlb_type != hypervisor) + return; - BUILD_BUG_ON(NR_IRQS >= 256); + if (hvirq_major) + major = hvirq_major; + else + major = 3; - spin_lock_irqsave(&irq_alloc_lock, flags); + hv_error = sun4v_hvapi_register(HV_GRP_INTR, major, &minor); + if (!hv_error) + hv_irq_version = major; + else + hv_irq_version = 1; - for (ent = 1; ent < NR_IRQS; ent++) { - if (!irq_table[ent].in_use) + pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n", + hv_irq_version, + sun4v_cookie_only_virqs() ? "enabled" : "disabled"); +} + +/* This function is for the timer interrupt.*/ +int __init arch_probe_nr_irqs(void) +{ + return 1; +} + +#define DEFAULT_NUM_IVECS (0xfffU) +static unsigned int nr_ivec = DEFAULT_NUM_IVECS; +#define NUM_IVECS (nr_ivec) + +static unsigned int __init size_nr_ivec(void) +{ + if (tlb_type == hypervisor) { + switch (sun4v_chip_type) { + /* Athena's devhandle|devino is large.*/ + case SUN4V_CHIP_SPARC64X: + nr_ivec = 0xffff; break; + } } - if (ent >= NR_IRQS) { - printk(KERN_ERR "IRQ: Out of virtual IRQs.\n"); - ent = 0; - } else { - irq_table[ent].dev_handle = dev_handle; - irq_table[ent].dev_ino = dev_ino; - irq_table[ent].in_use = 1; - } + return nr_ivec; +} + +struct irq_handler_data { + union { + struct { + unsigned int dev_handle; + unsigned int dev_ino; + }; + unsigned long sysino; + }; + struct ino_bucket bucket; + unsigned long iclr; + unsigned long imap; +}; + +static inline unsigned int irq_data_to_handle(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; + + return ihd->dev_handle; +} + +static inline unsigned int irq_data_to_ino(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; - spin_unlock_irqrestore(&irq_alloc_lock, flags); + return ihd->dev_ino; +} + +static inline unsigned long irq_data_to_sysino(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; - return ent; + return ihd->sysino; } -#ifdef CONFIG_PCI_MSI void irq_free(unsigned int irq) { - unsigned long flags; + void *data = irq_get_handler_data(irq); - if (irq >= NR_IRQS) - return; + kfree(data); + irq_set_handler_data(irq, NULL); + irq_free_descs(irq, 1); +} - spin_lock_irqsave(&irq_alloc_lock, flags); +unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino) +{ + int irq; - irq_table[irq].in_use = 0; + irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL); + if (irq <= 0) + goto out; - spin_unlock_irqrestore(&irq_alloc_lock, flags); + return irq; +out: + return 0; +} + +static unsigned int cookie_exists(u32 devhandle, unsigned int devino) +{ + unsigned long hv_err, cookie; + struct ino_bucket *bucket; + unsigned int irq = 0U; + + hv_err = sun4v_vintr_get_cookie(devhandle, devino, &cookie); + if (hv_err) { + pr_err("HV get cookie failed hv_err = %ld\n", hv_err); + goto out; + } + + if (cookie & ((1UL << 63UL))) { + cookie = ~cookie; + bucket = (struct ino_bucket *) __va(cookie); + irq = bucket->__irq; + } +out: + return irq; +} + +static unsigned int sysino_exists(u32 devhandle, unsigned int devino) +{ + unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino); + struct ino_bucket *bucket; + unsigned int irq; + + bucket = &ivector_table[sysino]; + irq = bucket_get_irq(__pa(bucket)); + + return irq; +} + +void ack_bad_irq(unsigned int irq) +{ + pr_crit("BAD IRQ ack %d\n", irq); +} + +void irq_install_pre_handler(int irq, + void (*func)(unsigned int, void *, void *), + void *arg1, void *arg2) +{ + pr_warn("IRQ pre handler NOT supported.\n"); } -#endif /* * /proc/interrupts printing: @@ -206,15 +345,6 @@ static unsigned int sun4u_compute_tid(unsigned long imap, unsigned long cpuid) return tid; } -struct irq_handler_data { - unsigned long iclr; - unsigned long imap; - - void (*pre_handler)(unsigned int, void *, void *); - void *arg1; - void *arg2; -}; - #ifdef CONFIG_SMP static int irq_choose_cpu(unsigned int irq, const struct cpumask *affinity) { @@ -316,8 +446,8 @@ static void sun4u_irq_eoi(struct irq_data *data) static void sun4v_irq_enable(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; unsigned long cpuid = irq_choose_cpu(data->irq, data->affinity); + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_settarget(ino, cpuid); @@ -337,8 +467,8 @@ static void sun4v_irq_enable(struct irq_data *data) static int sun4v_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - unsigned int ino = irq_table[data->irq].dev_ino; unsigned long cpuid = irq_choose_cpu(data->irq, mask); + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_settarget(ino, cpuid); @@ -351,7 +481,7 @@ static int sun4v_set_affinity(struct irq_data *data, static void sun4v_irq_disable(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_setenabled(ino, HV_INTR_DISABLED); @@ -362,7 +492,7 @@ static void sun4v_irq_disable(struct irq_data *data) static void sun4v_irq_eoi(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE); @@ -373,14 +503,13 @@ static void sun4v_irq_eoi(struct irq_data *data) static void sun4v_virq_enable(struct irq_data *data) { - unsigned long cpuid, dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); + unsigned long cpuid; int err; cpuid = irq_choose_cpu(data->irq, data->affinity); - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid); if (err != HV_EOK) printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): " @@ -403,14 +532,13 @@ static void sun4v_virq_enable(struct irq_data *data) static int sun4v_virt_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - unsigned long cpuid, dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); + unsigned long cpuid; int err; cpuid = irq_choose_cpu(data->irq, mask); - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid); if (err != HV_EOK) printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): " @@ -422,11 +550,10 @@ static int sun4v_virt_set_affinity(struct irq_data *data, static void sun4v_virq_disable(struct irq_data *data) { - unsigned long dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); int err; - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; err = sun4v_vintr_set_valid(dev_handle, dev_ino, HV_INTR_DISABLED); @@ -438,12 +565,10 @@ static void sun4v_virq_disable(struct irq_data *data) static void sun4v_virq_eoi(struct irq_data *data) { - unsigned long dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); int err; - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_state(dev_handle, dev_ino, HV_INTR_STATE_IDLE); if (err != HV_EOK) @@ -479,31 +604,10 @@ static struct irq_chip sun4v_virq = { .flags = IRQCHIP_EOI_IF_HANDLED, }; -static void pre_flow_handler(struct irq_data *d) -{ - struct irq_handler_data *handler_data = irq_data_get_irq_handler_data(d); - unsigned int ino = irq_table[d->irq].dev_ino; - - handler_data->pre_handler(ino, handler_data->arg1, handler_data->arg2); -} - -void irq_install_pre_handler(int irq, - void (*func)(unsigned int, void *, void *), - void *arg1, void *arg2) -{ - struct irq_handler_data *handler_data = irq_get_handler_data(irq); - - handler_data->pre_handler = func; - handler_data->arg1 = arg1; - handler_data->arg2 = arg2; - - __irq_set_preflow_handler(irq, pre_flow_handler); -} - unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap) { - struct ino_bucket *bucket; struct irq_handler_data *handler_data; + struct ino_bucket *bucket; unsigned int irq; int ino; @@ -537,119 +641,166 @@ out: return irq; } -static unsigned int sun4v_build_common(unsigned long sysino, - struct irq_chip *chip) +static unsigned int sun4v_build_common(u32 devhandle, unsigned int devino, + void (*handler_data_init)(struct irq_handler_data *data, + u32 devhandle, unsigned int devino), + struct irq_chip *chip) { - struct ino_bucket *bucket; - struct irq_handler_data *handler_data; + struct irq_handler_data *data; unsigned int irq; - BUG_ON(tlb_type != hypervisor); + irq = irq_alloc(devhandle, devino); + if (!irq) + goto out; - bucket = &ivector_table[sysino]; - irq = bucket_get_irq(__pa(bucket)); - if (!irq) { - irq = irq_alloc(0, sysino); - bucket_set_irq(__pa(bucket), irq); - irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, - "IVEC"); + data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); + if (unlikely(!data)) { + pr_err("IRQ handler data allocation failed.\n"); + irq_free(irq); + irq = 0; + goto out; } - handler_data = irq_get_handler_data(irq); - if (unlikely(handler_data)) - goto out; + irq_set_handler_data(irq, data); + handler_data_init(data, devhandle, devino); + irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, "IVEC"); + data->imap = ~0UL; + data->iclr = ~0UL; +out: + return irq; +} - handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); - if (unlikely(!handler_data)) { - prom_printf("IRQ: kzalloc(irq_handler_data) failed.\n"); - prom_halt(); - } - irq_set_handler_data(irq, handler_data); +static unsigned long cookie_assign(unsigned int irq, u32 devhandle, + unsigned int devino) +{ + struct irq_handler_data *ihd = irq_get_handler_data(irq); + unsigned long hv_error, cookie; - /* Catch accidental accesses to these things. IMAP/ICLR handling - * is done by hypervisor calls on sun4v platforms, not by direct - * register accesses. + /* handler_irq needs to find the irq. cookie is seen signed in + * sun4v_dev_mondo and treated as a non ivector_table delivery. */ - handler_data->imap = ~0UL; - handler_data->iclr = ~0UL; + ihd->bucket.__irq = irq; + cookie = ~__pa(&ihd->bucket); -out: - return irq; + hv_error = sun4v_vintr_set_cookie(devhandle, devino, cookie); + if (hv_error) + pr_err("HV vintr set cookie failed = %ld\n", hv_error); + + return hv_error; } -unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino) +static void cookie_handler_data(struct irq_handler_data *data, + u32 devhandle, unsigned int devino) { - unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino); + data->dev_handle = devhandle; + data->dev_ino = devino; +} - return sun4v_build_common(sysino, &sun4v_irq); +static unsigned int cookie_build_irq(u32 devhandle, unsigned int devino, + struct irq_chip *chip) +{ + unsigned long hv_error; + unsigned int irq; + + irq = sun4v_build_common(devhandle, devino, cookie_handler_data, chip); + + hv_error = cookie_assign(irq, devhandle, devino); + if (hv_error) { + irq_free(irq); + irq = 0; + } + + return irq; } -unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) +static unsigned int sun4v_build_cookie(u32 devhandle, unsigned int devino) { - struct irq_handler_data *handler_data; - unsigned long hv_err, cookie; - struct ino_bucket *bucket; unsigned int irq; - bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC); - if (unlikely(!bucket)) - return 0; + irq = cookie_exists(devhandle, devino); + if (irq) + goto out; - /* The only reference we store to the IRQ bucket is - * by physical address which kmemleak can't see, tell - * it that this object explicitly is not a leak and - * should be scanned. - */ - kmemleak_not_leak(bucket); + irq = cookie_build_irq(devhandle, devino, &sun4v_virq); - __flush_dcache_range((unsigned long) bucket, - ((unsigned long) bucket + - sizeof(struct ino_bucket))); +out: + return irq; +} - irq = irq_alloc(devhandle, devino); +static void sysino_set_bucket(unsigned int irq) +{ + struct irq_handler_data *ihd = irq_get_handler_data(irq); + struct ino_bucket *bucket; + unsigned long sysino; + + sysino = sun4v_devino_to_sysino(ihd->dev_handle, ihd->dev_ino); + BUG_ON(sysino >= nr_ivec); + bucket = &ivector_table[sysino]; bucket_set_irq(__pa(bucket), irq); +} - irq_set_chip_and_handler_name(irq, &sun4v_virq, handle_fasteoi_irq, - "IVEC"); +static void sysino_handler_data(struct irq_handler_data *data, + u32 devhandle, unsigned int devino) +{ + unsigned long sysino; - handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); - if (unlikely(!handler_data)) - return 0; + sysino = sun4v_devino_to_sysino(devhandle, devino); + data->sysino = sysino; +} - /* In order to make the LDC channel startup sequence easier, - * especially wrt. locking, we do not let request_irq() enable - * the interrupt. - */ - irq_set_status_flags(irq, IRQ_NOAUTOEN); - irq_set_handler_data(irq, handler_data); +static unsigned int sysino_build_irq(u32 devhandle, unsigned int devino, + struct irq_chip *chip) +{ + unsigned int irq; - /* Catch accidental accesses to these things. IMAP/ICLR handling - * is done by hypervisor calls on sun4v platforms, not by direct - * register accesses. - */ - handler_data->imap = ~0UL; - handler_data->iclr = ~0UL; + irq = sun4v_build_common(devhandle, devino, sysino_handler_data, chip); + if (!irq) + goto out; - cookie = ~__pa(bucket); - hv_err = sun4v_vintr_set_cookie(devhandle, devino, cookie); - if (hv_err) { - prom_printf("IRQ: Fatal, cannot set cookie for [%x:%x] " - "err=%lu\n", devhandle, devino, hv_err); - prom_halt(); - } + sysino_set_bucket(irq); +out: + return irq; +} +static int sun4v_build_sysino(u32 devhandle, unsigned int devino) +{ + int irq; + + irq = sysino_exists(devhandle, devino); + if (irq) + goto out; + + irq = sysino_build_irq(devhandle, devino, &sun4v_irq); +out: return irq; } -void ack_bad_irq(unsigned int irq) +unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino) { - unsigned int ino = irq_table[irq].dev_ino; + unsigned int irq; - if (!ino) - ino = 0xdeadbeef; + if (sun4v_cookie_only_virqs()) + irq = sun4v_build_cookie(devhandle, devino); + else + irq = sun4v_build_sysino(devhandle, devino); - printk(KERN_CRIT "Unexpected IRQ from ino[%x] irq[%u]\n", - ino, irq); + return irq; +} + +unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) +{ + int irq; + + irq = cookie_build_irq(devhandle, devino, &sun4v_virq); + if (!irq) + goto out; + + /* This is borrowed from the original function. + */ + irq_set_status_flags(irq, IRQ_NOAUTOEN); + +out: + return irq; } void *hardirq_stack[NR_CPUS]; @@ -720,9 +871,12 @@ void fixup_irqs(void) for (irq = 0; irq < NR_IRQS; irq++) { struct irq_desc *desc = irq_to_desc(irq); - struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_data *data; unsigned long flags; + if (!desc) + continue; + data = irq_desc_get_irq_data(desc); raw_spin_lock_irqsave(&desc->lock, flags); if (desc->action && !irqd_is_per_cpu(data)) { if (data->chip->irq_set_affinity) @@ -922,16 +1076,22 @@ static struct irqaction timer_irq_action = { .name = "timer", }; -/* Only invoked on boot processor. */ -void __init init_IRQ(void) +static void __init irq_ivector_init(void) { - unsigned long size; + unsigned long size, order; + unsigned int ivecs; - map_prom_timers(); - kill_prom_timer(); + /* If we are doing cookie only VIRQs then we do not need the ivector + * table to process interrupts. + */ + if (sun4v_cookie_only_virqs()) + return; - size = sizeof(struct ino_bucket) * NUM_IVECS; - ivector_table = kzalloc(size, GFP_KERNEL); + ivecs = size_nr_ivec(); + size = sizeof(struct ino_bucket) * ivecs; + order = get_order(size); + ivector_table = (struct ino_bucket *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!ivector_table) { prom_printf("Fatal error, cannot allocate ivector_table\n"); prom_halt(); @@ -940,6 +1100,15 @@ void __init init_IRQ(void) ((unsigned long) ivector_table) + size); ivector_table_pa = __pa(ivector_table); +} + +/* Only invoked on boot processor.*/ +void __init init_IRQ(void) +{ + irq_init_hv(); + irq_ivector_init(); + map_prom_timers(); + kill_prom_timer(); if (tlb_type == hypervisor) sun4v_init_mondo_queues(); diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S index 542e96ac4d39..ef0d8e9e1210 100644 --- a/arch/sparc/kernel/ktlb.S +++ b/arch/sparc/kernel/ktlb.S @@ -47,14 +47,6 @@ kvmap_itlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath) TSB_LOCK_TAG(%g1, %g2, %g7) - - /* Load and check PTE. */ - ldxa [%g5] ASI_PHYS_USE_EC, %g5 - mov 1, %g7 - sllx %g7, TSB_TAG_INVALID_BIT, %g7 - brgez,a,pn %g5, kvmap_itlb_longpath - TSB_STORE(%g1, %g7) - TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -118,6 +110,12 @@ kvmap_dtlb_obp: ba,pt %xcc, kvmap_dtlb_load nop +kvmap_linear_early: + sethi %hi(kern_linear_pte_xor), %g7 + ldx [%g7 + %lo(kern_linear_pte_xor)], %g2 + ba,pt %xcc, kvmap_dtlb_tsb4m_load + xor %g2, %g4, %g5 + .align 32 kvmap_dtlb_tsb4m_load: TSB_LOCK_TAG(%g1, %g2, %g7) @@ -146,105 +144,17 @@ kvmap_dtlb_4v: /* Correct TAG_TARGET is already in %g6, check 4mb TSB. */ KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load) #endif - /* TSB entry address left in %g1, lookup linear PTE. - * Must preserve %g1 and %g6 (TAG). - */ -kvmap_dtlb_tsb4m_miss: - /* Clear the PAGE_OFFSET top virtual bits, shift - * down to get PFN, and make sure PFN is in range. - */ -661: sllx %g4, 0, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - /* Check to see if we know about valid memory at the 4MB - * chunk this physical address will reside within. + /* Linear mapping TSB lookup failed. Fallthrough to kernel + * page table based lookup. */ -661: srlx %g5, MAX_PHYS_ADDRESS_BITS, %g2 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - brnz,pn %g2, kvmap_dtlb_longpath - nop - - /* This unconditional branch and delay-slot nop gets patched - * by the sethi sequence once the bitmap is properly setup. - */ - .globl valid_addr_bitmap_insn -valid_addr_bitmap_insn: - ba,pt %xcc, 2f - nop - .subsection 2 - .globl valid_addr_bitmap_patch -valid_addr_bitmap_patch: - sethi %hi(sparc64_valid_addr_bitmap), %g7 - or %g7, %lo(sparc64_valid_addr_bitmap), %g7 - .previous - -661: srlx %g5, ILOG2_4MB, %g2 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - srlx %g2, 6, %g5 - and %g2, 63, %g2 - sllx %g5, 3, %g5 - ldx [%g7 + %g5], %g5 - mov 1, %g7 - sllx %g7, %g2, %g7 - andcc %g5, %g7, %g0 - be,pn %xcc, kvmap_dtlb_longpath - -2: sethi %hi(kpte_linear_bitmap), %g2 - - /* Get the 256MB physical address index. */ -661: sllx %g4, 0, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - or %g2, %lo(kpte_linear_bitmap), %g2 - -661: srlx %g5, ILOG2_256MB, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - and %g5, (32 - 1), %g7 - - /* Divide by 32 to get the offset into the bitmask. */ - srlx %g5, 5, %g5 - add %g7, %g7, %g7 - sllx %g5, 3, %g5 - - /* kern_linear_pte_xor[(mask >> shift) & 3)] */ - ldx [%g2 + %g5], %g2 - srlx %g2, %g7, %g7 - sethi %hi(kern_linear_pte_xor), %g5 - and %g7, 3, %g7 - or %g5, %lo(kern_linear_pte_xor), %g5 - sllx %g7, 3, %g7 - ldx [%g5 + %g7], %g2 - .globl kvmap_linear_patch kvmap_linear_patch: - ba,pt %xcc, kvmap_dtlb_tsb4m_load - xor %g2, %g4, %g5 + ba,a,pt %xcc, kvmap_linear_early kvmap_dtlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) TSB_LOCK_TAG(%g1, %g2, %g7) - - /* Load and check PTE. */ - ldxa [%g5] ASI_PHYS_USE_EC, %g5 - mov 1, %g7 - sllx %g7, TSB_TAG_INVALID_BIT, %g7 - brgez,a,pn %g5, kvmap_dtlb_longpath - TSB_STORE(%g1, %g7) - TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -276,13 +186,8 @@ kvmap_dtlb_load: #ifdef CONFIG_SPARSEMEM_VMEMMAP kvmap_vmemmap: - sub %g4, %g5, %g5 - srlx %g5, 22, %g5 - sethi %hi(vmemmap_table), %g1 - sllx %g5, 3, %g5 - or %g1, %lo(vmemmap_table), %g1 - ba,pt %xcc, kvmap_dtlb_load - ldx [%g1 + %g5], %g5 + KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) + ba,a,pt %xcc, kvmap_dtlb_load #endif kvmap_dtlb_nonlinear: @@ -294,8 +199,8 @@ kvmap_dtlb_nonlinear: #ifdef CONFIG_SPARSEMEM_VMEMMAP /* Do not use the TSB for vmemmap. */ - mov (VMEMMAP_BASE >> 40), %g5 - sllx %g5, 40, %g5 + sethi %hi(VMEMMAP_BASE), %g5 + ldx [%g5 + %lo(VMEMMAP_BASE)], %g5 cmp %g4,%g5 bgeu,pn %xcc, kvmap_vmemmap nop @@ -307,8 +212,8 @@ kvmap_dtlb_tsbmiss: sethi %hi(MODULES_VADDR), %g5 cmp %g4, %g5 blu,pn %xcc, kvmap_dtlb_longpath - mov (VMALLOC_END >> 40), %g5 - sllx %g5, 40, %g5 + sethi %hi(VMALLOC_END), %g5 + ldx [%g5 + %lo(VMALLOC_END)], %g5 cmp %g4, %g5 bgeu,pn %xcc, kvmap_dtlb_longpath nop diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index e01d75d40329..27bb55485472 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -1078,7 +1078,8 @@ static void ldc_iommu_release(struct ldc_channel *lp) struct ldc_channel *ldc_alloc(unsigned long id, const struct ldc_channel_config *cfgp, - void *event_arg) + void *event_arg, + const char *name) { struct ldc_channel *lp; const struct ldc_mode_ops *mops; @@ -1093,6 +1094,8 @@ struct ldc_channel *ldc_alloc(unsigned long id, err = -EINVAL; if (!cfgp) goto out_err; + if (!name) + goto out_err; switch (cfgp->mode) { case LDC_MODE_RAW: @@ -1185,6 +1188,21 @@ struct ldc_channel *ldc_alloc(unsigned long id, INIT_HLIST_HEAD(&lp->mh_list); + snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name); + snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name); + + err = request_irq(lp->cfg.rx_irq, ldc_rx, 0, + lp->rx_irq_name, lp); + if (err) + goto out_free_txq; + + err = request_irq(lp->cfg.tx_irq, ldc_tx, 0, + lp->tx_irq_name, lp); + if (err) { + free_irq(lp->cfg.rx_irq, lp); + goto out_free_txq; + } + return lp; out_free_txq: @@ -1237,31 +1255,14 @@ EXPORT_SYMBOL(ldc_free); * state. This does not initiate a handshake, ldc_connect() does * that. */ -int ldc_bind(struct ldc_channel *lp, const char *name) +int ldc_bind(struct ldc_channel *lp) { unsigned long hv_err, flags; int err = -EINVAL; - if (!name || - (lp->state != LDC_STATE_INIT)) + if (lp->state != LDC_STATE_INIT) return -EINVAL; - snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name); - snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name); - - err = request_irq(lp->cfg.rx_irq, ldc_rx, 0, - lp->rx_irq_name, lp); - if (err) - return err; - - err = request_irq(lp->cfg.tx_irq, ldc_tx, 0, - lp->tx_irq_name, lp); - if (err) { - free_irq(lp->cfg.rx_irq, lp); - return err; - } - - spin_lock_irqsave(&lp->lock, flags); enable_irq(lp->cfg.rx_irq); @@ -1336,7 +1337,7 @@ int ldc_connect(struct ldc_channel *lp) if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) || !(lp->flags & LDC_FLAG_REGISTERED_QUEUES) || lp->hs_state != LDC_HS_OPEN) - err = -EINVAL; + err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL); else err = start_handshake(lp); diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 6479256fd5a4..fce8ab17bcbb 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -141,7 +141,6 @@ static inline unsigned int get_nmi_count(int cpu) static __init void nmi_cpu_busy(void *data) { - local_irq_enable_in_hardirq(); while (endflag == 0) mb(); } diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 269af58497aa..7e967c8018c8 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -191,12 +191,41 @@ static const struct pcr_ops n4_pcr_ops = { .pcr_nmi_disable = PCR_N4_PICNPT, }; +static u64 n5_pcr_read(unsigned long reg_num) +{ + unsigned long val; + + (void) sun4v_t5_get_perfreg(reg_num, &val); + + return val; +} + +static void n5_pcr_write(unsigned long reg_num, u64 val) +{ + (void) sun4v_t5_set_perfreg(reg_num, val); +} + +static const struct pcr_ops n5_pcr_ops = { + .read_pcr = n5_pcr_read, + .write_pcr = n5_pcr_write, + .read_pic = n4_pic_read, + .write_pic = n4_pic_write, + .nmi_picl_value = n4_picl_value, + .pcr_nmi_enable = (PCR_N4_PICNPT | PCR_N4_STRACE | + PCR_N4_UTRACE | PCR_N4_TOE | + (26 << PCR_N4_SL_SHIFT)), + .pcr_nmi_disable = PCR_N4_PICNPT, +}; + + static unsigned long perf_hsvc_group; static unsigned long perf_hsvc_major; static unsigned long perf_hsvc_minor; static int __init register_perf_hsvc(void) { + unsigned long hverror; + if (tlb_type == hypervisor) { switch (sun4v_chip_type) { case SUN4V_CHIP_NIAGARA1: @@ -215,6 +244,10 @@ static int __init register_perf_hsvc(void) perf_hsvc_group = HV_GRP_VT_CPU; break; + case SUN4V_CHIP_NIAGARA5: + perf_hsvc_group = HV_GRP_T5_CPU; + break; + default: return -ENODEV; } @@ -222,10 +255,12 @@ static int __init register_perf_hsvc(void) perf_hsvc_major = 1; perf_hsvc_minor = 0; - if (sun4v_hvapi_register(perf_hsvc_group, - perf_hsvc_major, - &perf_hsvc_minor)) { - printk("perfmon: Could not register hvapi.\n"); + hverror = sun4v_hvapi_register(perf_hsvc_group, + perf_hsvc_major, + &perf_hsvc_minor); + if (hverror) { + pr_err("perfmon: Could not register hvapi(0x%lx).\n", + hverror); return -ENODEV; } } @@ -254,6 +289,10 @@ static int __init setup_sun4v_pcr_ops(void) pcr_ops = &n4_pcr_ops; break; + case SUN4V_CHIP_NIAGARA5: + pcr_ops = &n5_pcr_ops; + break; + default: ret = -ENODEV; break; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b5c38faa4ead..617b9fe33771 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1662,7 +1662,8 @@ static bool __init supported_pmu(void) sparc_pmu = &niagara2_pmu; return true; } - if (!strcmp(sparc_pmu_type, "niagara4")) { + if (!strcmp(sparc_pmu_type, "niagara4") || + !strcmp(sparc_pmu_type, "niagara5")) { sparc_pmu = &niagara4_pmu; return true; } @@ -1671,9 +1672,12 @@ static bool __init supported_pmu(void) int __init init_hw_perf_events(void) { + int err; + pr_info("Performance events: "); - if (!supported_pmu()) { + err = pcr_arch_init(); + if (err || !supported_pmu()) { pr_cont("No support for PMU type '%s'\n", sparc_pmu_type); return 0; } @@ -1685,7 +1689,7 @@ int __init init_hw_perf_events(void) return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index d7b4967f8fa6..c6f7113b6e2f 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -306,6 +306,9 @@ static void __global_pmu_self(int this_cpu) struct global_pmu_snapshot *pp; int i, num; + if (!pcr_ops) + return; + pp = &global_cpu_snapshot[this_cpu].pmu; num = 1; diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 3fdb455e3318..61a519808cb7 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -30,6 +30,7 @@ #include <linux/cpu.h> #include <linux/initrd.h> #include <linux/module.h> +#include <linux/start_kernel.h> #include <asm/io.h> #include <asm/processor.h> @@ -174,7 +175,7 @@ char reboot_command[COMMAND_LINE_SIZE]; static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 }; -void __init per_cpu_patch(void) +static void __init per_cpu_patch(void) { struct cpuid_patch_entry *p; unsigned long ver; @@ -266,7 +267,7 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start, } } -void __init sun4v_patch(void) +static void __init sun4v_patch(void) { extern void sun4v_hvapi_init(void); @@ -335,14 +336,25 @@ static void __init pause_patch(void) } } -#ifdef CONFIG_SMP -void __init boot_cpu_id_too_large(int cpu) +void __init start_early_boot(void) { - prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n", - cpu, NR_CPUS); - prom_halt(); + int cpu; + + check_if_starfire(); + per_cpu_patch(); + sun4v_patch(); + + cpu = hard_smp_processor_id(); + if (cpu >= NR_CPUS) { + prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n", + cpu, NR_CPUS); + prom_halt(); + } + current_thread_info()->cpu = cpu; + + prom_init_report(); + start_kernel(); } -#endif /* On Ultra, we support all of the v8 capabilities. */ unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR | @@ -500,12 +512,16 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_BLKINIT; if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_N2; } @@ -533,6 +549,8 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | AV_SPARC_ASI_BLK_INIT | @@ -540,6 +558,8 @@ static void __init init_sparc64_elf_hwcap(void) if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | AV_SPARC_FMAF); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index b085311dcd0e..50c3dd03be31 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -151,7 +151,7 @@ void cpu_panic(void) #define NUM_ROUNDS 64 /* magic value */ #define NUM_ITERS 5 /* likewise */ -static DEFINE_SPINLOCK(itc_sync_lock); +static DEFINE_RAW_SPINLOCK(itc_sync_lock); static unsigned long go[SLAVE + 1]; #define DEBUG_TICK_SYNC 0 @@ -259,7 +259,7 @@ static void smp_synchronize_one_tick(int cpu) go[MASTER] = 0; membar_safe("#StoreLoad"); - spin_lock_irqsave(&itc_sync_lock, flags); + raw_spin_lock_irqsave(&itc_sync_lock, flags); { for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) { while (!go[MASTER]) @@ -270,7 +270,7 @@ static void smp_synchronize_one_tick(int cpu) membar_safe("#StoreLoad"); } } - spin_unlock_irqrestore(&itc_sync_lock, flags); + raw_spin_unlock_irqrestore(&itc_sync_lock, flags); } #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU) @@ -1395,7 +1395,6 @@ void __cpu_die(unsigned int cpu) void __init smp_cpus_done(unsigned int max_cpus) { - pcr_arch_init(); } void smp_send_reschedule(int cpu) @@ -1480,6 +1479,13 @@ static void __init pcpu_populate_pte(unsigned long addr) pud_t *pud; pmd_t *pmd; + if (pgd_none(*pgd)) { + pud_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + pgd_populate(&init_mm, pgd, new); + } + pud = pud_offset(pgd, addr); if (pud_none(*pud)) { pmd_t *new; diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S index e0c09bf85610..6179e19bc9b9 100644 --- a/arch/sparc/kernel/sun4v_tlb_miss.S +++ b/arch/sparc/kernel/sun4v_tlb_miss.S @@ -195,6 +195,11 @@ sun4v_tsb_miss_common: ldx [%g2 + TRAP_PER_CPU_PGD_PADDR], %g7 sun4v_itlb_error: + rdpr %tl, %g1 + cmp %g1, 1 + ble,pt %icc, sun4v_bad_ra + or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1 + sethi %hi(sun4v_err_itlb_vaddr), %g1 stx %g4, [%g1 + %lo(sun4v_err_itlb_vaddr)] sethi %hi(sun4v_err_itlb_ctx), %g1 @@ -206,15 +211,10 @@ sun4v_itlb_error: sethi %hi(sun4v_err_itlb_error), %g1 stx %o0, [%g1 + %lo(sun4v_err_itlb_error)] + sethi %hi(1f), %g7 rdpr %tl, %g4 - cmp %g4, 1 - ble,pt %icc, 1f - sethi %hi(2f), %g7 ba,pt %xcc, etraptl1 - or %g7, %lo(2f), %g7 - -1: ba,pt %xcc, etrap -2: or %g7, %lo(2b), %g7 +1: or %g7, %lo(1f), %g7 mov %l4, %o1 call sun4v_itlb_error_report add %sp, PTREGS_OFF, %o0 @@ -222,6 +222,11 @@ sun4v_itlb_error: /* NOTREACHED */ sun4v_dtlb_error: + rdpr %tl, %g1 + cmp %g1, 1 + ble,pt %icc, sun4v_bad_ra + or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1 + sethi %hi(sun4v_err_dtlb_vaddr), %g1 stx %g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)] sethi %hi(sun4v_err_dtlb_ctx), %g1 @@ -233,21 +238,23 @@ sun4v_dtlb_error: sethi %hi(sun4v_err_dtlb_error), %g1 stx %o0, [%g1 + %lo(sun4v_err_dtlb_error)] + sethi %hi(1f), %g7 rdpr %tl, %g4 - cmp %g4, 1 - ble,pt %icc, 1f - sethi %hi(2f), %g7 ba,pt %xcc, etraptl1 - or %g7, %lo(2f), %g7 - -1: ba,pt %xcc, etrap -2: or %g7, %lo(2b), %g7 +1: or %g7, %lo(1f), %g7 mov %l4, %o1 call sun4v_dtlb_error_report add %sp, PTREGS_OFF, %o0 /* NOTREACHED */ +sun4v_bad_ra: + or %g0, %g4, %g5 + ba,pt %xcc, sparc64_realfault_common + or %g1, %g0, %g4 + + /* NOTREACHED */ + /* Instruction Access Exception, tl0. */ sun4v_iacc: ldxa [%g0] ASI_SCRATCHPAD, %g2 diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index f7c72b6efc27..d066eb18650c 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -44,7 +44,7 @@ SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1) SIGN1(sys32_io_submit, compat_sys_io_submit, %o1) SIGN1(sys32_mq_open, compat_sys_mq_open, %o1) SIGN1(sys32_select, compat_sys_select, %o0) -SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5) +SIGN1(sys32_futex, compat_sys_futex, %o1) SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0) SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0) SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0) diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S index 737f8cbc7d56..88ede1d53b4c 100644 --- a/arch/sparc/kernel/trampoline_64.S +++ b/arch/sparc/kernel/trampoline_64.S @@ -109,10 +109,13 @@ startup_continue: brnz,pn %g1, 1b nop - sethi %hi(p1275buf), %g2 - or %g2, %lo(p1275buf), %g2 - ldx [%g2 + 0x10], %l2 - add %l2, -(192 + 128), %sp + /* Get onto temporary stack which will be in the locked + * kernel image. + */ + sethi %hi(tramp_stack), %g1 + or %g1, %lo(tramp_stack), %g1 + add %g1, TRAMP_STACK_SIZE, %g1 + sub %g1, STACKFRAME_SZ + STACK_BIAS + 256, %sp flushw /* Setup the loop variables: @@ -394,7 +397,6 @@ after_lock_tlb: sllx %g5, THREAD_SHIFT, %g5 sub %g5, (STACKFRAME_SZ + STACK_BIAS), %g5 add %g6, %g5, %sp - mov 0, %fp rdpr %pstate, %o1 or %o1, PSTATE_IE, %o1 diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 4ced92f05358..25d0c7ece9cc 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2102,6 +2102,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs) atomic_inc(&sun4v_nonresum_oflow_cnt); } +static void sun4v_tlb_error(struct pt_regs *regs) +{ + die_if_kernel("TLB/TSB error", regs); +} + unsigned long sun4v_err_itlb_vaddr; unsigned long sun4v_err_itlb_ctx; unsigned long sun4v_err_itlb_pte; @@ -2109,8 +2114,7 @@ unsigned long sun4v_err_itlb_error; void sun4v_itlb_error_report(struct pt_regs *regs, int tl) { - if (tl > 1) - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); + dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n", regs->tpc, tl); @@ -2123,7 +2127,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl) sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx, sun4v_err_itlb_pte, sun4v_err_itlb_error); - prom_halt(); + sun4v_tlb_error(regs); } unsigned long sun4v_err_dtlb_vaddr; @@ -2133,8 +2137,7 @@ unsigned long sun4v_err_dtlb_error; void sun4v_dtlb_error_report(struct pt_regs *regs, int tl) { - if (tl > 1) - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); + dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n", regs->tpc, tl); @@ -2147,7 +2150,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl) sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx, sun4v_err_dtlb_pte, sun4v_err_dtlb_error); - prom_halt(); + sun4v_tlb_error(regs); } void hypervisor_tlbop_error(unsigned long err, unsigned long op) diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index 14158d40ba76..be98685c14c6 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -162,10 +162,10 @@ tsb_miss_page_table_walk_sun4v_fastpath: nop .previous - rdpr %tl, %g3 - cmp %g3, 1 + rdpr %tl, %g7 + cmp %g7, 1 bne,pn %xcc, winfix_trampoline - nop + mov %g3, %g4 ba,pt %xcc, etrap rd %pc, %g7 call hugetlb_setup diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index 3c1a7cb31579..35ab8b60d256 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -166,17 +166,23 @@ static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs) unsigned long compute_effective_address(struct pt_regs *regs, unsigned int insn, unsigned int rd) { + int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; unsigned int rs1 = (insn >> 14) & 0x1f; unsigned int rs2 = insn & 0x1f; - int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; + unsigned long addr; if (insn & 0x2000) { maybe_flush_windows(rs1, 0, rd, from_kernel); - return (fetch_reg(rs1, regs) + sign_extend_imm13(insn)); + addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn)); } else { maybe_flush_windows(rs1, rs2, rd, from_kernel); - return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs)); + addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs)); } + + if (!from_kernel && test_thread_flag(TIF_32BIT)) + addr &= 0xffffffff; + + return addr; } /* This is just to make gcc think die_if_kernel does return... */ diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c index f8e7dd53e1c7..9c5fbd0b8a04 100644 --- a/arch/sparc/kernel/viohs.c +++ b/arch/sparc/kernel/viohs.c @@ -714,7 +714,7 @@ int vio_ldc_alloc(struct vio_driver_state *vio, cfg.tx_irq = vio->vdev->tx_irq; cfg.rx_irq = vio->vdev->rx_irq; - lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg); + lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg, vio->name); if (IS_ERR(lp)) return PTR_ERR(lp); @@ -746,7 +746,7 @@ void vio_port_up(struct vio_driver_state *vio) err = 0; if (state == LDC_STATE_INIT) { - err = ldc_bind(vio->lp, vio->name); + err = ldc_bind(vio->lp); if (err) printk(KERN_WARNING "%s: Port %lu bind failed, " "err=%d\n", diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 932ff90fd760..09243057cb0b 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -35,8 +35,9 @@ jiffies = jiffies_64; SECTIONS { - /* swapper_low_pmd_dir is sparc64 only */ - swapper_low_pmd_dir = 0x0000000000402000; +#ifdef CONFIG_SPARC64 + swapper_pg_dir = 0x0000000000402000; +#endif . = INITIAL_ADDRESS; .text TEXTSTART : { @@ -122,11 +123,6 @@ SECTIONS *(.swapper_4m_tsb_phys_patch) __swapper_4m_tsb_phys_patch_end = .; } - .page_offset_shift_patch : { - __page_offset_shift_patch = .; - *(.page_offset_shift_patch) - __page_offset_shift_patch_end = .; - } .popc_3insn_patch : { __popc_3insn_patch = .; *(.popc_3insn_patch) diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index 2c20ad63ddbf..30eee6e8a81b 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -236,6 +236,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ */ VISEntryHalf + membar #Sync alignaddr %o1, %g0, %g0 add %o1, (64 - 1), %o4 diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 9cf2ee01cee3..140527a20e7d 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -41,6 +41,10 @@ #endif #endif +#if !defined(EX_LD) && !defined(EX_ST) +#define NON_USER_COPY +#endif + #ifndef EX_LD #define EX_LD(x) x #endif @@ -197,9 +201,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ mov EX_RETVAL(%o3), %o0 .Llarge_src_unaligned: +#ifdef NON_USER_COPY + VISEntryHalfFast(.Lmedium_vis_entry_fail) +#else + VISEntryHalf +#endif andn %o2, 0x3f, %o4 sub %o2, %o4, %o2 - VISEntryHalf alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 EX_LD(LOAD(ldd, %g1 + 0x00, %f0)) @@ -240,6 +248,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop ba,a,pt %icc, .Lmedium_unaligned +#ifdef NON_USER_COPY +.Lmedium_vis_entry_fail: + or %o0, %o1, %g2 +#endif .Lmedium: LOAD(prefetch, %o1 + 0x40, #n_reads_strong) andcc %g2, 0x7, %g0 diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S index 99c017be8719..f75e6906df14 100644 --- a/arch/sparc/lib/memset.S +++ b/arch/sparc/lib/memset.S @@ -3,8 +3,9 @@ * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) * - * Returns 0, if ok, and number of bytes not yet set if exception - * occurs and we were called as clear_user. + * Calls to memset returns initial %o0. Calls to bzero returns 0, if ok, and + * number of bytes not yet set if exception occurs and we were called as + * clear_user. */ #include <asm/ptrace.h> @@ -65,6 +66,8 @@ __bzero_begin: .globl __memset_start, __memset_end __memset_start: memset: + mov %o0, %g1 + mov 1, %g4 and %o1, 0xff, %g3 sll %g3, 8, %g2 or %g3, %g2, %g3 @@ -89,6 +92,7 @@ memset: sub %o0, %o2, %o0 __bzero: + clr %g4 mov %g0, %g3 1: cmp %o1, 7 @@ -151,8 +155,8 @@ __bzero: bne,a 8f EX(stb %g3, [%o0], and %o1, 1) 8: - retl - clr %o0 + b 0f + nop 7: be 13b orcc %o1, 0, %g0 @@ -164,6 +168,12 @@ __bzero: bne 8b EX(stb %g3, [%o0 - 1], add %o1, 1) 0: + andcc %g4, 1, %g0 + be 5f + nop + retl + mov %g1, %o0 +5: retl clr %o0 __memset_end: diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c index aa4d55b0bdf0..5ce8f2f64604 100644 --- a/arch/sparc/math-emu/math_32.c +++ b/arch/sparc/math-emu/math_32.c @@ -499,7 +499,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) case 0: fsr = *pfsr; if (IR == -1) IR = 2; /* fcc is always fcc0 */ - fsr &= ~0xc00; fsr |= (IR << 10); break; + fsr &= ~0xc00; fsr |= (IR << 10); *pfsr = fsr; break; case 1: rd->s = IR; break; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 69bb818fdd79..45a413e4380a 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -96,38 +96,51 @@ static unsigned int get_user_insn(unsigned long tpc) pte_t *ptep, pte; unsigned long pa; u32 insn = 0; - unsigned long pstate; - if (pgd_none(*pgdp)) - goto outret; + if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) + goto out; pudp = pud_offset(pgdp, tpc); - if (pud_none(*pudp)) - goto outret; - pmdp = pmd_offset(pudp, tpc); - if (pmd_none(*pmdp)) - goto outret; + if (pud_none(*pudp) || unlikely(pud_bad(*pudp))) + goto out; /* This disables preemption for us as well. */ - __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate)); - __asm__ __volatile__("wrpr %0, %1, %%pstate" - : : "r" (pstate), "i" (PSTATE_IE)); - ptep = pte_offset_map(pmdp, tpc); - pte = *ptep; - if (!pte_present(pte)) - goto out; + local_irq_disable(); + + pmdp = pmd_offset(pudp, tpc); + if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp))) + goto out_irq_enable; - pa = (pte_pfn(pte) << PAGE_SHIFT); - pa += (tpc & ~PAGE_MASK); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(*pmdp)) { + if (pmd_trans_splitting(*pmdp)) + goto out_irq_enable; - /* Use phys bypass so we don't pollute dtlb/dcache. */ - __asm__ __volatile__("lduwa [%1] %2, %0" - : "=r" (insn) - : "r" (pa), "i" (ASI_PHYS_USE_EC)); + pa = pmd_pfn(*pmdp) << PAGE_SHIFT; + pa += tpc & ~HPAGE_MASK; + /* Use phys bypass so we don't pollute dtlb/dcache. */ + __asm__ __volatile__("lduwa [%1] %2, %0" + : "=r" (insn) + : "r" (pa), "i" (ASI_PHYS_USE_EC)); + } else +#endif + { + ptep = pte_offset_map(pmdp, tpc); + pte = *ptep; + if (pte_present(pte)) { + pa = (pte_pfn(pte) << PAGE_SHIFT); + pa += (tpc & ~PAGE_MASK); + + /* Use phys bypass so we don't pollute dtlb/dcache. */ + __asm__ __volatile__("lduwa [%1] %2, %0" + : "=r" (insn) + : "r" (pa), "i" (ASI_PHYS_USE_EC)); + } + pte_unmap(ptep); + } +out_irq_enable: + local_irq_enable(); out: - pte_unmap(ptep); - __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate)); -outret: return insn; } @@ -153,7 +166,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, } static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, - unsigned int insn, int fault_code) + unsigned long fault_addr, unsigned int insn, + int fault_code) { unsigned long addr; siginfo_t info; @@ -161,10 +175,18 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, info.si_code = code; info.si_signo = sig; info.si_errno = 0; - if (fault_code & FAULT_CODE_ITLB) + if (fault_code & FAULT_CODE_ITLB) { addr = regs->tpc; - else - addr = compute_effective_address(regs, insn, 0); + } else { + /* If we were able to probe the faulting instruction, use it + * to compute a precise fault address. Otherwise use the fault + * time provided address which may only have page granularity. + */ + if (insn) + addr = compute_effective_address(regs, insn, 0); + else + addr = fault_addr; + } info.si_addr = (void __user *) addr; info.si_trapno = 0; @@ -239,7 +261,7 @@ static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code, /* The si_code was set to make clear whether * this was a SEGV_MAPERR or SEGV_ACCERR fault. */ - do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code); + do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code); return; } @@ -259,18 +281,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs) show_regs(regs); } -static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs, - unsigned long addr) -{ - static int times; - - if (times++ < 10) - printk(KERN_ERR "FAULT[%s:%d]: 32-bit process " - "reports 64-bit fault address [%lx]\n", - current->comm, current->pid, addr); - show_regs(regs); -} - asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); @@ -300,10 +310,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) goto intr_or_no_mm; } } - if (unlikely((address >> 32) != 0)) { - bogus_32bit_fault_address(regs, address); + if (unlikely((address >> 32) != 0)) goto intr_or_no_mm; - } } if (regs->tstate & TSTATE_PRIV) { @@ -340,6 +348,9 @@ retry: down_read(&mm->mmap_sem); } + if (fault_code & FAULT_CODE_BAD_RA) + goto do_sigbus; + vma = find_vma(mm, address); if (!vma) goto bad_area; @@ -525,7 +536,7 @@ do_sigbus: * Send a sigbus, regardless of whether we were in kernel * or user mode. */ - do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code); + do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code); /* Kernel mode? Handle exceptions or die */ if (regs->tstate & TSTATE_PRIV) diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index c4d3da68b800..ae6ce383d4df 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -73,7 +73,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, struct page *head, *page, *tail; int refs; - if (!pmd_large(pmd)) + if (!(pmd_val(pmd) & _PAGE_VALID)) return 0; if (write && !pmd_write(pmd)) @@ -160,6 +160,36 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +int __get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next, flags; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + + local_irq_save(flags); + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + break; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + break; + } while (pgdp++, addr = next, addr != end); + local_irq_restore(flags); + + return nr; +} + int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 9bd9ce80bf77..d329537739c6 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -231,11 +231,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index eafbc65c9c47..34506f292533 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -73,7 +73,6 @@ unsigned long kern_linear_pte_xor[4] __read_mostly; * 'cpu' properties, but we need to have this table setup before the * MDESC is initialized. */ -unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; #ifndef CONFIG_DEBUG_PAGEALLOC /* A special kernel TSB for 4MB, 256MB, 2GB and 16GB linear mappings. @@ -82,10 +81,11 @@ unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; */ extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES]; #endif +extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; static unsigned long cpu_pgsz_mask; -#define MAX_BANKS 32 +#define MAX_BANKS 1024 static struct linux_prom64_registers pavail[MAX_BANKS]; static int pavail_ents; @@ -163,10 +163,6 @@ static void __init read_obp_memory(const char *property, cmp_p64, NULL); } -unsigned long sparc64_valid_addr_bitmap[VALID_ADDR_BITMAP_BYTES / - sizeof(unsigned long)]; -EXPORT_SYMBOL(sparc64_valid_addr_bitmap); - /* Kernel physical address base and size in bytes. */ unsigned long kern_base __read_mostly; unsigned long kern_size __read_mostly; @@ -350,6 +346,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * mm = vma->vm_mm; + /* Don't insert a non-valid PTE into the TSB, we'll deadlock. */ + if (!pte_accessible(mm, pte)) + return; + spin_lock_irqsave(&mm->context.lock, flags); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) @@ -588,7 +588,7 @@ static void __init remap_kernel(void) int i, tlb_ent = sparc64_highest_locked_tlbent(); tte_vaddr = (unsigned long) KERNBASE; - phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL; + phys_page = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB; tte_data = kern_large_tte(phys_page); kern_locked_tte_data = tte_data; @@ -834,7 +834,10 @@ static int find_node(unsigned long addr) if ((addr & p->mask) == p->val) return i; } - return -1; + /* The following condition has been observed on LDOM guests.*/ + WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node" + " rule. Some physical memory will be owned by node 0."); + return 0; } static u64 memblock_nid_range(u64 start, u64 end, int *nid) @@ -1356,9 +1359,144 @@ static unsigned long __init bootmem_init(unsigned long phys_base) static struct linux_prom64_registers pall[MAX_BANKS] __initdata; static int pall_ents __initdata; -#ifdef CONFIG_DEBUG_PAGEALLOC +static unsigned long max_phys_bits = 40; + +bool kern_addr_valid(unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if ((long)addr < 0L) { + unsigned long pa = __pa(addr); + + if ((addr >> max_phys_bits) != 0UL) + return false; + + return pfn_valid(pa >> PAGE_SHIFT); + } + + if (addr >= (unsigned long) KERNBASE && + addr < (unsigned long)&_end) + return true; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + return 0; + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) + return 0; + + if (pud_large(*pud)) + return pfn_valid(pud_pfn(*pud)); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return 0; + + if (pmd_large(*pmd)) + return pfn_valid(pmd_pfn(*pmd)); + + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) + return 0; + + return pfn_valid(pte_pfn(*pte)); +} +EXPORT_SYMBOL(kern_addr_valid); + +static unsigned long __ref kernel_map_hugepud(unsigned long vstart, + unsigned long vend, + pud_t *pud) +{ + const unsigned long mask16gb = (1UL << 34) - 1UL; + u64 pte_val = vstart; + + /* Each PUD is 8GB */ + if ((vstart & mask16gb) || + (vend - vstart <= mask16gb)) { + pte_val ^= kern_linear_pte_xor[2]; + pud_val(*pud) = pte_val | _PAGE_PUD_HUGE; + + return vstart + PUD_SIZE; + } + + pte_val ^= kern_linear_pte_xor[3]; + pte_val |= _PAGE_PUD_HUGE; + + vend = vstart + mask16gb + 1UL; + while (vstart < vend) { + pud_val(*pud) = pte_val; + + pte_val += PUD_SIZE; + vstart += PUD_SIZE; + pud++; + } + return vstart; +} + +static bool kernel_can_map_hugepud(unsigned long vstart, unsigned long vend, + bool guard) +{ + if (guard && !(vstart & ~PUD_MASK) && (vend - vstart) >= PUD_SIZE) + return true; + + return false; +} + +static unsigned long __ref kernel_map_hugepmd(unsigned long vstart, + unsigned long vend, + pmd_t *pmd) +{ + const unsigned long mask256mb = (1UL << 28) - 1UL; + const unsigned long mask2gb = (1UL << 31) - 1UL; + u64 pte_val = vstart; + + /* Each PMD is 8MB */ + if ((vstart & mask256mb) || + (vend - vstart <= mask256mb)) { + pte_val ^= kern_linear_pte_xor[0]; + pmd_val(*pmd) = pte_val | _PAGE_PMD_HUGE; + + return vstart + PMD_SIZE; + } + + if ((vstart & mask2gb) || + (vend - vstart <= mask2gb)) { + pte_val ^= kern_linear_pte_xor[1]; + pte_val |= _PAGE_PMD_HUGE; + vend = vstart + mask256mb + 1UL; + } else { + pte_val ^= kern_linear_pte_xor[2]; + pte_val |= _PAGE_PMD_HUGE; + vend = vstart + mask2gb + 1UL; + } + + while (vstart < vend) { + pmd_val(*pmd) = pte_val; + + pte_val += PMD_SIZE; + vstart += PMD_SIZE; + pmd++; + } + + return vstart; +} + +static bool kernel_can_map_hugepmd(unsigned long vstart, unsigned long vend, + bool guard) +{ + if (guard && !(vstart & ~PMD_MASK) && (vend - vstart) >= PMD_SIZE) + return true; + + return false; +} + static unsigned long __ref kernel_map_range(unsigned long pstart, - unsigned long pend, pgprot_t prot) + unsigned long pend, pgprot_t prot, + bool use_huge) { unsigned long vstart = PAGE_OFFSET + pstart; unsigned long vend = PAGE_OFFSET + pend; @@ -1377,19 +1515,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, pmd_t *pmd; pte_t *pte; + if (pgd_none(*pgd)) { + pud_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + alloc_bytes += PAGE_SIZE; + pgd_populate(&init_mm, pgd, new); + } pud = pud_offset(pgd, vstart); if (pud_none(*pud)) { pmd_t *new; + if (kernel_can_map_hugepud(vstart, vend, use_huge)) { + vstart = kernel_map_hugepud(vstart, vend, pud); + continue; + } new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); alloc_bytes += PAGE_SIZE; pud_populate(&init_mm, pud, new); } pmd = pmd_offset(pud, vstart); - if (!pmd_present(*pmd)) { + if (pmd_none(*pmd)) { pte_t *new; + if (kernel_can_map_hugepmd(vstart, vend, use_huge)) { + vstart = kernel_map_hugepmd(vstart, vend, pmd); + continue; + } new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); alloc_bytes += PAGE_SIZE; pmd_populate_kernel(&init_mm, pmd, new); @@ -1412,100 +1565,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, return alloc_bytes; } -extern unsigned int kvmap_linear_patch[1]; -#endif /* CONFIG_DEBUG_PAGEALLOC */ - -static void __init kpte_set_val(unsigned long index, unsigned long val) -{ - unsigned long *ptr = kpte_linear_bitmap; - - val <<= ((index % (BITS_PER_LONG / 2)) * 2); - ptr += (index / (BITS_PER_LONG / 2)); - - *ptr |= val; -} - -static const unsigned long kpte_shift_min = 28; /* 256MB */ -static const unsigned long kpte_shift_max = 34; /* 16GB */ -static const unsigned long kpte_shift_incr = 3; - -static unsigned long kpte_mark_using_shift(unsigned long start, unsigned long end, - unsigned long shift) +static void __init flush_all_kernel_tsbs(void) { - unsigned long size = (1UL << shift); - unsigned long mask = (size - 1UL); - unsigned long remains = end - start; - unsigned long val; - - if (remains < size || (start & mask)) - return start; - - /* VAL maps: - * - * shift 28 --> kern_linear_pte_xor index 1 - * shift 31 --> kern_linear_pte_xor index 2 - * shift 34 --> kern_linear_pte_xor index 3 - */ - val = ((shift - kpte_shift_min) / kpte_shift_incr) + 1; - - remains &= ~mask; - if (shift != kpte_shift_max) - remains = size; - - while (remains) { - unsigned long index = start >> kpte_shift_min; + int i; - kpte_set_val(index, val); + for (i = 0; i < KERNEL_TSB_NENTRIES; i++) { + struct tsb *ent = &swapper_tsb[i]; - start += 1UL << kpte_shift_min; - remains -= 1UL << kpte_shift_min; + ent->tag = (1UL << TSB_TAG_INVALID_BIT); } +#ifndef CONFIG_DEBUG_PAGEALLOC + for (i = 0; i < KERNEL_TSB4M_NENTRIES; i++) { + struct tsb *ent = &swapper_4m_tsb[i]; - return start; -} - -static void __init mark_kpte_bitmap(unsigned long start, unsigned long end) -{ - unsigned long smallest_size, smallest_mask; - unsigned long s; - - smallest_size = (1UL << kpte_shift_min); - smallest_mask = (smallest_size - 1UL); - - while (start < end) { - unsigned long orig_start = start; - - for (s = kpte_shift_max; s >= kpte_shift_min; s -= kpte_shift_incr) { - start = kpte_mark_using_shift(start, end, s); - - if (start != orig_start) - break; - } - - if (start == orig_start) - start = (start + smallest_size) & ~smallest_mask; + ent->tag = (1UL << TSB_TAG_INVALID_BIT); } +#endif } -static void __init init_kpte_bitmap(void) -{ - unsigned long i; - - for (i = 0; i < pall_ents; i++) { - unsigned long phys_start, phys_end; - - phys_start = pall[i].phys_addr; - phys_end = phys_start + pall[i].reg_size; - - mark_kpte_bitmap(phys_start, phys_end); - } -} +extern unsigned int kvmap_linear_patch[1]; static void __init kernel_physical_mapping_init(void) { -#ifdef CONFIG_DEBUG_PAGEALLOC unsigned long i, mem_alloced = 0UL; + bool use_huge = true; +#ifdef CONFIG_DEBUG_PAGEALLOC + use_huge = false; +#endif for (i = 0; i < pall_ents; i++) { unsigned long phys_start, phys_end; @@ -1513,7 +1600,7 @@ static void __init kernel_physical_mapping_init(void) phys_end = phys_start + pall[i].reg_size; mem_alloced += kernel_map_range(phys_start, phys_end, - PAGE_KERNEL); + PAGE_KERNEL, use_huge); } printk("Allocated %ld bytes for kernel page tables.\n", @@ -1522,8 +1609,9 @@ static void __init kernel_physical_mapping_init(void) kvmap_linear_patch[0] = 0x01000000; /* nop */ flushi(&kvmap_linear_patch[0]); + flush_all_kernel_tsbs(); + __flush_tlb_all(); -#endif } #ifdef CONFIG_DEBUG_PAGEALLOC @@ -1533,7 +1621,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) unsigned long phys_end = phys_start + (numpages * PAGE_SIZE); kernel_map_range(phys_start, phys_end, - (enable ? PAGE_KERNEL : __pgprot(0))); + (enable ? PAGE_KERNEL : __pgprot(0)), false); flush_tsb_kernel_range(PAGE_OFFSET + phys_start, PAGE_OFFSET + phys_end); @@ -1561,76 +1649,56 @@ unsigned long __init find_ecache_flush_span(unsigned long size) unsigned long PAGE_OFFSET; EXPORT_SYMBOL(PAGE_OFFSET); -static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits) -{ - unsigned long final_shift; - unsigned int val = *insn; - unsigned int cnt; - - /* We are patching in ilog2(max_supported_phys_address), and - * we are doing so in a manner similar to a relocation addend. - * That is, we are adding the shift value to whatever value - * is in the shift instruction count field already. - */ - cnt = (val & 0x3f); - val &= ~0x3f; - - /* If we are trying to shift >= 64 bits, clear the destination - * register. This can happen when phys_bits ends up being equal - * to MAX_PHYS_ADDRESS_BITS. - */ - final_shift = (cnt + (64 - phys_bits)); - if (final_shift >= 64) { - unsigned int rd = (val >> 25) & 0x1f; - - val = 0x80100000 | (rd << 25); - } else { - val |= final_shift; - } - *insn = val; - - __asm__ __volatile__("flush %0" - : /* no outputs */ - : "r" (insn)); -} - -static void __init page_offset_shift_patch(unsigned long phys_bits) -{ - extern unsigned int __page_offset_shift_patch; - extern unsigned int __page_offset_shift_patch_end; - unsigned int *p; - - p = &__page_offset_shift_patch; - while (p < &__page_offset_shift_patch_end) { - unsigned int *insn = (unsigned int *)(unsigned long)*p; +unsigned long VMALLOC_END = 0x0000010000000000UL; +EXPORT_SYMBOL(VMALLOC_END); - page_offset_shift_patch_one(insn, phys_bits); - - p++; - } -} +unsigned long sparc64_va_hole_top = 0xfffff80000000000UL; +unsigned long sparc64_va_hole_bottom = 0x0000080000000000UL; static void __init setup_page_offset(void) { - unsigned long max_phys_bits = 40; - if (tlb_type == cheetah || tlb_type == cheetah_plus) { + /* Cheetah/Panther support a full 64-bit virtual + * address, so we can use all that our page tables + * support. + */ + sparc64_va_hole_top = 0xfff0000000000000UL; + sparc64_va_hole_bottom = 0x0010000000000000UL; + max_phys_bits = 42; } else if (tlb_type == hypervisor) { switch (sun4v_chip_type) { case SUN4V_CHIP_NIAGARA1: case SUN4V_CHIP_NIAGARA2: + /* T1 and T2 support 48-bit virtual addresses. */ + sparc64_va_hole_top = 0xffff800000000000UL; + sparc64_va_hole_bottom = 0x0000800000000000UL; + max_phys_bits = 39; break; case SUN4V_CHIP_NIAGARA3: + /* T3 supports 48-bit virtual addresses. */ + sparc64_va_hole_top = 0xffff800000000000UL; + sparc64_va_hole_bottom = 0x0000800000000000UL; + max_phys_bits = 43; break; case SUN4V_CHIP_NIAGARA4: case SUN4V_CHIP_NIAGARA5: case SUN4V_CHIP_SPARC64X: - default: + case SUN4V_CHIP_SPARC_M6: + /* T4 and later support 52-bit virtual addresses. */ + sparc64_va_hole_top = 0xfff8000000000000UL; + sparc64_va_hole_bottom = 0x0008000000000000UL; max_phys_bits = 47; break; + case SUN4V_CHIP_SPARC_M7: + default: + /* M7 and later support 52-bit virtual addresses. */ + sparc64_va_hole_top = 0xfff8000000000000UL; + sparc64_va_hole_bottom = 0x0008000000000000UL; + max_phys_bits = 49; + break; } } @@ -1640,12 +1708,16 @@ static void __init setup_page_offset(void) prom_halt(); } - PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits); + PAGE_OFFSET = sparc64_va_hole_top; + VMALLOC_END = ((sparc64_va_hole_bottom >> 1) + + (sparc64_va_hole_bottom >> 2)); - pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n", + pr_info("MM: PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n", PAGE_OFFSET, max_phys_bits); - - page_offset_shift_patch(max_phys_bits); + pr_info("MM: VMALLOC [0x%016lx --> 0x%016lx]\n", + VMALLOC_START, VMALLOC_END); + pr_info("MM: VMEMMAP [0x%016lx --> 0x%016lx]\n", + VMEMMAP_BASE, VMEMMAP_BASE << 1); } static void __init tsb_phys_patch(void) @@ -1690,21 +1762,42 @@ static void __init tsb_phys_patch(void) #define NUM_KTSB_DESCR 1 #endif static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR]; -extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; + +/* The swapper TSBs are loaded with a base sequence of: + * + * sethi %uhi(SYMBOL), REG1 + * sethi %hi(SYMBOL), REG2 + * or REG1, %ulo(SYMBOL), REG1 + * or REG2, %lo(SYMBOL), REG2 + * sllx REG1, 32, REG1 + * or REG1, REG2, REG1 + * + * When we use physical addressing for the TSB accesses, we patch the + * first four instructions in the above sequence. + */ static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa) { - pa >>= KTSB_PHYS_SHIFT; + unsigned long high_bits, low_bits; + + high_bits = (pa >> 32) & 0xffffffff; + low_bits = (pa >> 0) & 0xffffffff; while (start < end) { unsigned int *ia = (unsigned int *)(unsigned long)*start; - ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10); + ia[0] = (ia[0] & ~0x3fffff) | (high_bits >> 10); __asm__ __volatile__("flush %0" : : "r" (ia)); - ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff); + ia[1] = (ia[1] & ~0x3fffff) | (low_bits >> 10); __asm__ __volatile__("flush %0" : : "r" (ia + 1)); + ia[2] = (ia[2] & ~0x1fff) | (high_bits & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 2)); + + ia[3] = (ia[3] & ~0x1fff) | (low_bits & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 3)); + start++; } } @@ -1843,7 +1936,6 @@ static void __init sun4v_linear_pte_xor_finalize(void) /* paging_init() sets up the page tables */ static unsigned long last_valid_pfn; -pgd_t swapper_pg_dir[PTRS_PER_PGD]; static void sun4u_pgprot_init(void); static void sun4v_pgprot_init(void); @@ -1881,7 +1973,7 @@ void __init paging_init(void) BUILD_BUG_ON(NR_CPUS > 4096); - kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL; + kern_base = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB; kern_size = (unsigned long)&_end - (unsigned long)KERNBASE; /* Invalidate both kernel TSBs. */ @@ -1937,7 +2029,7 @@ void __init paging_init(void) shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE); real_end = (unsigned long)_end; - num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << 22); + num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << ILOG2_4MB); printk("Kernel: Using %d locked TLB entries for main kernel image.\n", num_kernel_image_mappings); @@ -1946,16 +2038,10 @@ void __init paging_init(void) */ init_mm.pgd += ((shift) / (sizeof(pgd_t))); - memset(swapper_low_pmd_dir, 0, sizeof(swapper_low_pmd_dir)); + memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir)); - /* Now can init the kernel/bad page tables. */ - pud_set(pud_offset(&swapper_pg_dir[0], 0), - swapper_low_pmd_dir + (shift / sizeof(pgd_t))); - inherit_prom_mappings(); - init_kpte_bitmap(); - /* Ok, we can use our TLB miss and window trap handlers safely. */ setup_tba(); @@ -2062,70 +2148,6 @@ int page_in_phys_avail(unsigned long paddr) return 0; } -static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata; -static int pavail_rescan_ents __initdata; - -/* Certain OBP calls, such as fetching "available" properties, can - * claim physical memory. So, along with initializing the valid - * address bitmap, what we do here is refetch the physical available - * memory list again, and make sure it provides at least as much - * memory as 'pavail' does. - */ -static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap) -{ - int i; - - read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents); - - for (i = 0; i < pavail_ents; i++) { - unsigned long old_start, old_end; - - old_start = pavail[i].phys_addr; - old_end = old_start + pavail[i].reg_size; - while (old_start < old_end) { - int n; - - for (n = 0; n < pavail_rescan_ents; n++) { - unsigned long new_start, new_end; - - new_start = pavail_rescan[n].phys_addr; - new_end = new_start + - pavail_rescan[n].reg_size; - - if (new_start <= old_start && - new_end >= (old_start + PAGE_SIZE)) { - set_bit(old_start >> 22, bitmap); - goto do_next_page; - } - } - - prom_printf("mem_init: Lost memory in pavail\n"); - prom_printf("mem_init: OLD start[%lx] size[%lx]\n", - pavail[i].phys_addr, - pavail[i].reg_size); - prom_printf("mem_init: NEW start[%lx] size[%lx]\n", - pavail_rescan[i].phys_addr, - pavail_rescan[i].reg_size); - prom_printf("mem_init: Cannot continue, aborting.\n"); - prom_halt(); - - do_next_page: - old_start += PAGE_SIZE; - } - } -} - -static void __init patch_tlb_miss_handler_bitmap(void) -{ - extern unsigned int valid_addr_bitmap_insn[]; - extern unsigned int valid_addr_bitmap_patch[]; - - valid_addr_bitmap_insn[1] = valid_addr_bitmap_patch[1]; - mb(); - valid_addr_bitmap_insn[0] = valid_addr_bitmap_patch[0]; - flushi(&valid_addr_bitmap_insn[0]); -} - static void __init register_page_bootmem_info(void) { #ifdef CONFIG_NEED_MULTIPLE_NODES @@ -2138,18 +2160,6 @@ static void __init register_page_bootmem_info(void) } void __init mem_init(void) { - unsigned long addr, last; - - addr = PAGE_OFFSET + kern_base; - last = PAGE_ALIGN(kern_size) + addr; - while (addr < last) { - set_bit(__pa(addr) >> 22, sparc64_valid_addr_bitmap); - addr += PAGE_SIZE; - } - - setup_valid_addr_bitmap_from_pavail(sparc64_valid_addr_bitmap); - patch_tlb_miss_handler_bitmap(); - high_memory = __va(last_valid_pfn << PAGE_SHIFT); register_page_bootmem_info(); @@ -2239,18 +2249,9 @@ unsigned long _PAGE_CACHE __read_mostly; EXPORT_SYMBOL(_PAGE_CACHE); #ifdef CONFIG_SPARSEMEM_VMEMMAP -unsigned long vmemmap_table[VMEMMAP_SIZE]; - -static long __meminitdata addr_start, addr_end; -static int __meminitdata node_start; - int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, int node) { - unsigned long phys_start = (vstart - VMEMMAP_BASE); - unsigned long phys_end = (vend - VMEMMAP_BASE); - unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK; - unsigned long end = VMEMMAP_ALIGN(phys_end); unsigned long pte_base; pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U | @@ -2261,47 +2262,52 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | _PAGE_W_4V); - for (; addr < end; addr += VMEMMAP_CHUNK) { - unsigned long *vmem_pp = - vmemmap_table + (addr >> VMEMMAP_CHUNK_SHIFT); - void *block; + pte_base |= _PAGE_PMD_HUGE; - if (!(*vmem_pp & _PAGE_VALID)) { - block = vmemmap_alloc_block(1UL << 22, node); - if (!block) + vstart = vstart & PMD_MASK; + vend = ALIGN(vend, PMD_SIZE); + for (; vstart < vend; vstart += PMD_SIZE) { + pgd_t *pgd = pgd_offset_k(vstart); + unsigned long pte; + pud_t *pud; + pmd_t *pmd; + + if (pgd_none(*pgd)) { + pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node); + + if (!new) return -ENOMEM; + pgd_populate(&init_mm, pgd, new); + } - *vmem_pp = pte_base | __pa(block); + pud = pud_offset(pgd, vstart); + if (pud_none(*pud)) { + pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node); - /* check to see if we have contiguous blocks */ - if (addr_end != addr || node_start != node) { - if (addr_start) - printk(KERN_DEBUG " [%lx-%lx] on node %d\n", - addr_start, addr_end-1, node_start); - addr_start = addr; - node_start = node; - } - addr_end = addr + VMEMMAP_CHUNK; + if (!new) + return -ENOMEM; + pud_populate(&init_mm, pud, new); } - } - return 0; -} -void __meminit vmemmap_populate_print_last(void) -{ - if (addr_start) { - printk(KERN_DEBUG " [%lx-%lx] on node %d\n", - addr_start, addr_end-1, node_start); - addr_start = 0; - addr_end = 0; - node_start = 0; + pmd = pmd_offset(pud, vstart); + + pte = pmd_val(*pmd); + if (!(pte & _PAGE_VALID)) { + void *block = vmemmap_alloc_block(PMD_SIZE, node); + + if (!block) + return -ENOMEM; + + pmd_val(*pmd) = pte_base | __pa(block); + } } + + return 0; } void vmemmap_free(unsigned long start, unsigned long end) { } - #endif /* CONFIG_SPARSEMEM_VMEMMAP */ static void prot_init_common(unsigned long page_none, @@ -2614,6 +2620,10 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pte = pmd_val(entry); + /* Don't insert a non-valid PMD into the TSB, we'll deadlock. */ + if (!(pte & _PAGE_VALID)) + return; + /* We are fabricating 8MB pages using 4MB real hw pages. */ pte |= (addr & (1UL << REAL_HPAGE_SHIFT)); @@ -2694,3 +2704,26 @@ void hugetlb_setup(struct pt_regs *regs) } } #endif + +#ifdef CONFIG_SMP +#define do_flush_tlb_kernel_range smp_flush_tlb_kernel_range +#else +#define do_flush_tlb_kernel_range __flush_tlb_kernel_range +#endif + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) { + if (start < LOW_OBP_ADDRESS) { + flush_tsb_kernel_range(start, LOW_OBP_ADDRESS); + do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS); + } + if (end > HI_OBP_ADDRESS) { + flush_tsb_kernel_range(HI_OBP_ADDRESS, end); + do_flush_tlb_kernel_range(HI_OBP_ADDRESS, end); + } + } else { + flush_tsb_kernel_range(start, end); + do_flush_tlb_kernel_range(start, end); + } +} diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h index 5d3782deb403..ac491193cb54 100644 --- a/arch/sparc/mm/init_64.h +++ b/arch/sparc/mm/init_64.h @@ -8,15 +8,8 @@ */ #define MAX_PHYS_ADDRESS (1UL << MAX_PHYS_ADDRESS_BITS) -#define KPTE_BITMAP_CHUNK_SZ (256UL * 1024UL * 1024UL) -#define KPTE_BITMAP_BYTES \ - ((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 4) -#define VALID_ADDR_BITMAP_CHUNK_SZ (4UL * 1024UL * 1024UL) -#define VALID_ADDR_BITMAP_BYTES \ - ((MAX_PHYS_ADDRESS / VALID_ADDR_BITMAP_CHUNK_SZ) / 8) extern unsigned long kern_linear_pte_xor[4]; -extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; extern unsigned int sparc64_highest_unlocked_tlb_ent; extern unsigned long sparc64_kern_pri_context; extern unsigned long sparc64_kern_pri_nuc_bits; @@ -38,15 +31,4 @@ extern unsigned long kern_locked_tte_data; extern void prom_world(int enter); -#ifdef CONFIG_SPARSEMEM_VMEMMAP -#define VMEMMAP_CHUNK_SHIFT 22 -#define VMEMMAP_CHUNK (1UL << VMEMMAP_CHUNK_SHIFT) -#define VMEMMAP_CHUNK_MASK ~(VMEMMAP_CHUNK - 1UL) -#define VMEMMAP_ALIGN(x) (((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK) - -#define VMEMMAP_SIZE ((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \ - sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT) -extern unsigned long vmemmap_table[VMEMMAP_SIZE]; -#endif - #endif /* _SPARC64_MM_INIT_H */ diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index b12cb5e72812..b89aba217e3b 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -134,7 +134,7 @@ no_cache_flush: #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, - pmd_t pmd, bool exec) + pmd_t pmd) { unsigned long end; pte_t *pte; @@ -142,8 +142,11 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, pte = pte_offset_map(&pmd, vaddr); end = vaddr + HPAGE_SIZE; while (vaddr < end) { - if (pte_val(*pte) & _PAGE_VALID) + if (pte_val(*pte) & _PAGE_VALID) { + bool exec = pte_exec(*pte); + tlb_batch_add_one(mm, vaddr, exec); + } pte++; vaddr += PAGE_SIZE; } @@ -177,19 +180,30 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } if (!pmd_none(orig)) { - pte_t orig_pte = __pte(pmd_val(orig)); - bool exec = pte_exec(orig_pte); - addr &= HPAGE_MASK; if (pmd_trans_huge(orig)) { + pte_t orig_pte = __pte(pmd_val(orig)); + bool exec = pte_exec(orig_pte); + tlb_batch_add_one(mm, addr, exec); tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec); } else { - tlb_batch_pmd_scan(mm, addr, orig, exec); + tlb_batch_pmd_scan(mm, addr, orig); } } } +void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t entry = *pmdp; + + pmd_val(entry) &= ~_PAGE_VALID; + + set_pmd_at(vma->vm_mm, address, pmdp, entry); + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); +} + void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index f5d506fdddad..fe19b81acc09 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -133,7 +133,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign mm->context.tsb_block[tsb_idx].tsb_nentries = tsb_bytes / sizeof(struct tsb); - base = TSBMAP_BASE; + switch (tsb_idx) { + case MM_TSB_BASE: + base = TSBMAP_8K_BASE; + break; +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + case MM_TSB_HUGE: + base = TSBMAP_4M_BASE; + break; +#endif + default: + BUG(); + } + tte = pgprot_val(PAGE_KERNEL_LOCKED); tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb); BUG_ON(tsb_paddr & (tsb_bytes - 1UL)); diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 01fe9946d388..44d258da0a1b 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start_, void *end_) #define BNE (F2(0, 2) | CONDNE) #ifdef CONFIG_SPARC64 -#define BNE_PTR (F2(0, 1) | CONDNE | (2 << 20)) +#define BE_PTR (F2(0, 1) | CONDE | (2 << 20)) #else -#define BNE_PTR BNE +#define BE_PTR BE #endif #define SETHI(K, REG) \ @@ -600,7 +600,7 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ANC_IFINDEX: emit_skb_loadptr(dev, r_A); emit_cmpi(r_A, 0); - emit_branch(BNE_PTR, cleanup_addr + 4); + emit_branch(BE_PTR, cleanup_addr + 4); emit_nop(); emit_load32(r_A, struct net_device, ifindex, r_A); break; @@ -613,7 +613,7 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ANC_HATYPE: emit_skb_loadptr(dev, r_A); emit_cmpi(r_A, 0); - emit_branch(BNE_PTR, cleanup_addr + 4); + emit_branch(BE_PTR, cleanup_addr + 4); emit_nop(); emit_load16(r_A, struct net_device, type, r_A); break; diff --git a/arch/sparc/power/hibernate_asm.S b/arch/sparc/power/hibernate_asm.S index 79942166df84..d7d9017dcb15 100644 --- a/arch/sparc/power/hibernate_asm.S +++ b/arch/sparc/power/hibernate_asm.S @@ -54,8 +54,8 @@ ENTRY(swsusp_arch_resume) nop /* Write PAGE_OFFSET to %g7 */ - sethi %uhi(PAGE_OFFSET), %g7 - sllx %g7, 32, %g7 + sethi %hi(PAGE_OFFSET), %g7 + ldx [%g7 + %lo(PAGE_OFFSET)], %g7 setuw (PAGE_SIZE-8), %g3 diff --git a/arch/sparc/prom/bootstr_64.c b/arch/sparc/prom/bootstr_64.c index ab9ccc63b388..7149e77714a4 100644 --- a/arch/sparc/prom/bootstr_64.c +++ b/arch/sparc/prom/bootstr_64.c @@ -14,7 +14,10 @@ * the .bss section or it will break things. */ -#define BARG_LEN 256 +/* We limit BARG_LEN to 1024 because this is the size of the + * 'barg_out' command line buffer in the SILO bootloader. + */ +#define BARG_LEN 1024 struct { int bootstr_len; int bootstr_valid; diff --git a/arch/sparc/prom/cif.S b/arch/sparc/prom/cif.S index 9c86b4b7d429..8050f381f518 100644 --- a/arch/sparc/prom/cif.S +++ b/arch/sparc/prom/cif.S @@ -11,11 +11,10 @@ .text .globl prom_cif_direct prom_cif_direct: + save %sp, -192, %sp sethi %hi(p1275buf), %o1 or %o1, %lo(p1275buf), %o1 - ldx [%o1 + 0x0010], %o2 ! prom_cif_stack - save %o2, -192, %sp - ldx [%i1 + 0x0008], %l2 ! prom_cif_handler + ldx [%o1 + 0x0008], %l2 ! prom_cif_handler mov %g4, %l0 mov %g5, %l1 mov %g6, %l3 diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c index d95db755828f..110b0d78b864 100644 --- a/arch/sparc/prom/init_64.c +++ b/arch/sparc/prom/init_64.c @@ -26,13 +26,13 @@ phandle prom_chosen_node; * It gets passed the pointer to the PROM vector. */ -extern void prom_cif_init(void *, void *); +extern void prom_cif_init(void *); -void __init prom_init(void *cif_handler, void *cif_stack) +void __init prom_init(void *cif_handler) { phandle node; - prom_cif_init(cif_handler, cif_stack); + prom_cif_init(cif_handler); prom_chosen_node = prom_finddevice(prom_chosen_path); if (!prom_chosen_node || (s32)prom_chosen_node == -1) diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index e58b81726319..545d8bb79b65 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -9,6 +9,7 @@ #include <linux/smp.h> #include <linux/string.h> #include <linux/spinlock.h> +#include <linux/irqflags.h> #include <asm/openprom.h> #include <asm/oplib.h> @@ -19,7 +20,6 @@ struct { long prom_callback; /* 0x00 */ void (*prom_cif_handler)(long *); /* 0x08 */ - unsigned long prom_cif_stack; /* 0x10 */ } p1275buf; extern void prom_world(int); @@ -36,8 +36,8 @@ void p1275_cmd_direct(unsigned long *args) { unsigned long flags; - raw_local_save_flags(flags); - raw_local_irq_restore((unsigned long)PIL_NMI); + local_save_flags(flags); + local_irq_restore((unsigned long)PIL_NMI); raw_spin_lock(&prom_entry_lock); prom_world(1); @@ -45,11 +45,10 @@ void p1275_cmd_direct(unsigned long *args) prom_world(0); raw_spin_unlock(&prom_entry_lock); - raw_local_irq_restore(flags); + local_irq_restore(flags); } void prom_cif_init(void *cif_handler, void *cif_stack) { p1275buf.prom_cif_handler = (void (*)(long *))cif_handler; - p1275buf.prom_cif_stack = (unsigned long)cif_stack; } diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index 0cb3bbaa580c..e514899e1100 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -166,11 +166,6 @@ int pud_huge(pud_t pud) return !!(pud_val(pud) & _PAGE_HUGE_PAGE); } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 3716e6952554..e8ab93c3e638 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q) while(1){ struct ubd *dev = q->queuedata; - if(dev->end_sg == 0){ + if(dev->request == NULL){ struct request *req = blk_fetch_request(q); if(req == NULL) return; @@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q) return; } prepare_flush_request(req, io_req); - submit_request(io_req, dev); + if (submit_request(io_req, dev) == false) + return; } while(dev->start_sg < dev->end_sg){ diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index fb5e4c658f7a..ef470a7a3d0f 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -14,6 +14,8 @@ #include <linux/compiler.h> #include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/io.h> #include <asm/cacheflush.h> @@ -73,7 +75,7 @@ do { \ else \ mm->mmap = NULL; \ rb_erase(&high_vma->vm_rb, &mm->mm_rb); \ - mm->mmap_cache = NULL; \ + vmacache_invalidate(mm); \ mm->map_count--; \ remove_vma(high_vma); \ } \ diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c index de7dc5fdd58b..24e836023e6c 100644 --- a/arch/unicore32/mm/alignment.c +++ b/arch/unicore32/mm/alignment.c @@ -21,6 +21,7 @@ #include <linux/sched.h> #include <linux/uaccess.h> +#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/unaligned.h> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0af5250d914f..98aa930230ec 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -127,6 +127,7 @@ config X86 select HAVE_DEBUG_STACKOVERFLOW select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 select HAVE_CC_STACKPROTECTOR + select ARCH_SUPPORTS_ATOMIC_RMW config INSTRUCTION_DECODER def_bool y @@ -965,10 +966,27 @@ config VM86 default y depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run 16-bit legacy - code on X86 processors. It also may be needed by software like - XFree86 to initialize some video cards via BIOS. Disabling this - option saves about 6k. + This option is required by programs like DOSEMU to run + 16-bit real mode legacy code on x86 processors. It also may + be needed by software like XFree86 to initialize some video + cards via BIOS. Disabling this option saves about 6K. + +config X86_16BIT + bool "Enable support for 16-bit segments" if EXPERT + default y + ---help--- + This option is required by programs like Wine to run 16-bit + protected mode legacy code on x86 processors. Disabling + this option saves about 300 bytes on i386, or around 6K text + plus 16K runtime memory on x86-64, + +config X86_ESPFIX32 + def_bool y + depends on X86_16BIT && X86_32 + +config X86_ESPFIX64 + def_bool y + depends on X86_16BIT && X86_64 config TOSHIBA tristate "Toshiba Laptop support" @@ -1579,6 +1597,7 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI + select RELOCATABLE ---help--- This kernel feature allows a bzImage to be loaded directly by EFI firmware without the use of a bootloader. @@ -1909,6 +1928,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK def_bool y depends on X86_64 || X86_PAE +config ARCH_ENABLE_HUGEPAGE_MIGRATION + def_bool y + depends on X86_64 && HUGETLB_PAGE && MIGRATION + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER @@ -2413,12 +2436,9 @@ config X86_DMA_REMAP depends on STA2X11 config IOSF_MBI - bool + tristate + default m depends on PCI - ---help--- - To be selected by modules requiring access to the Intel OnChip System - Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms - enumerable by PCI. source "net/Kconfig" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index eeda43abed6e..0dd99ea1caf1 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -79,6 +79,7 @@ else UTS_MACHINE := x86_64 CHECKFLAGS += -D__x86_64__ -m64 + biarch := -m64 KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 @@ -152,6 +153,7 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI # does binutils support specific instructions? asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1) +asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1) avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 4dbf967da50d..6cfcf2a2eb93 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -183,12 +183,27 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, static bool mem_avoid_overlap(struct mem_vector *img) { int i; + struct setup_data *ptr; for (i = 0; i < MEM_AVOID_MAX; i++) { if (mem_overlaps(img, &mem_avoid[i])) return true; } + /* Avoid all entries in the setup_data linked list. */ + ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data; + while (ptr) { + struct mem_vector avoid; + + avoid.start = (u64)ptr; + avoid.size = sizeof(*ptr) + ptr->len; + + if (mem_overlaps(img, &avoid)) + return true; + + ptr = (struct setup_data *)(unsigned long)ptr->next; + } + return false; } diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index a7677babf946..78cbb2db5a85 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -425,6 +425,9 @@ void setup_graphics(struct boot_params *boot_params) * Because the x86 boot code expects to be passed a boot_params we * need to create one ourselves (usually the bootloader would create * one for us). + * + * The caller is responsible for filling out ->code32_start in the + * returned boot_params. */ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) { @@ -483,8 +486,6 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) hdr->vid_mode = 0xffff; hdr->boot_flag = 0xAA55; - hdr->code32_start = (__u64)(unsigned long)image->image_base; - hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 9116aac232c7..f45ab7a36fb6 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -50,6 +50,13 @@ ENTRY(efi_pe_entry) pushl %eax pushl %esi pushl %ecx + + call reloc +reloc: + popl %ecx + subl reloc, %ecx + movl %ecx, BP_code32_start(%eax) + sub $0x4, %esp ENTRY(efi_stub_entry) @@ -63,12 +70,7 @@ ENTRY(efi_stub_entry) hlt jmp 1b 2: - call 3f -3: - popl %eax - subl $3b, %eax - subl BP_pref_address(%esi), %eax - add BP_code32_start(%esi), %eax + movl BP_code32_start(%esi), %eax leal preferred_addr(%eax), %eax jmp *%eax diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index c5c1ae0997e7..b10fa66a2540 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -217,6 +217,8 @@ ENTRY(efi_pe_entry) cmpq $0,%rax je 1f mov %rax, %rdx + leaq startup_32(%rip), %rax + movl %eax, BP_code32_start(%rdx) popq %rsi popq %rdi @@ -230,12 +232,7 @@ ENTRY(efi_stub_entry) hlt jmp 1b 2: - call 3f -3: - popq %rax - subq $3b, %rax - subq BP_pref_address(%rsi), %rax - add BP_code32_start(%esi), %eax + movl BP_code32_start(%esi), %eax leaq preferred_addr(%rax), %rax jmp *%rax diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index ec3b8ba68096..04da6c2194ba 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -91,10 +91,9 @@ bs_die: .section ".bsdata", "a" bugger_off_msg: - .ascii "Direct floppy boot is not supported. " - .ascii "Use a boot loader program instead.\r\n" + .ascii "Use a boot loader.\r\n" .ascii "\n" - .ascii "Remove disk and press any key to reboot ...\r\n" + .ascii "Remove disk and press any key to reboot...\r\n" .byte 0 #ifdef CONFIG_EFI_STUB @@ -108,7 +107,7 @@ coff_header: #else .word 0x8664 # x86-64 #endif - .word 3 # nr_sections + .word 4 # nr_sections .long 0 # TimeDateStamp .long 0 # PointerToSymbolTable .long 1 # NumberOfSymbols @@ -250,6 +249,25 @@ section_table: .word 0 # NumberOfLineNumbers .long 0x60500020 # Characteristics (section flags) + # + # The offset & size fields are filled in by build.c. + # + .ascii ".bss" + .byte 0 + .byte 0 + .byte 0 + .byte 0 + .long 0 + .long 0x0 + .long 0 # Size of initialized data + # on disk + .long 0x0 + .long 0 # PointerToRelocations + .long 0 # PointerToLineNumbers + .word 0 # NumberOfRelocations + .word 0 # NumberOfLineNumbers + .long 0xc8000080 # Characteristics (section flags) + #endif /* CONFIG_EFI_STUB */ # Kernel attributes; used by setup. This is part 1 of the diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 8e15b22391fc..3dafaeb9f549 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -142,7 +142,7 @@ static void usage(void) #ifdef CONFIG_EFI_STUB -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) { unsigned int pe_header; unsigned short num_sections; @@ -163,10 +163,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz put_unaligned_le32(size, section + 0x8); /* section header vma field */ - put_unaligned_le32(offset, section + 0xc); + put_unaligned_le32(vma, section + 0xc); /* section header 'size of initialised data' field */ - put_unaligned_le32(size, section + 0x10); + put_unaligned_le32(datasz, section + 0x10); /* section header 'file offset' field */ put_unaligned_le32(offset, section + 0x14); @@ -178,6 +178,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz } } +static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +{ + update_pecoff_section_header_fields(section_name, offset, size, size, offset); +} + static void update_pecoff_setup_and_reloc(unsigned int size) { u32 setup_offset = 0x200; @@ -202,9 +207,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) pe_header = get_unaligned_le32(&buf[0x3c]); - /* Size of image */ - put_unaligned_le32(file_sz, &buf[pe_header + 0x50]); - /* * Size of code: Subtract the size of the first sector (512 bytes) * which includes the header. @@ -219,6 +221,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) update_pecoff_section_header(".text", text_start, text_sz); } +static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz) +{ + unsigned int pe_header; + unsigned int bss_sz = init_sz - file_sz; + + pe_header = get_unaligned_le32(&buf[0x3c]); + + /* Size of uninitialized data */ + put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]); + + /* Size of image */ + put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); + + update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0); +} + #endif /* CONFIG_EFI_STUB */ @@ -270,6 +288,9 @@ int main(int argc, char ** argv) int fd; void *kernel; u32 crc = 0xffffffffUL; +#ifdef CONFIG_EFI_STUB + unsigned int init_sz; +#endif /* Defaults for old kernel */ #ifdef CONFIG_X86_32 @@ -343,7 +364,9 @@ int main(int argc, char ** argv) put_unaligned_le32(sys_size, &buf[0x1f4]); #ifdef CONFIG_EFI_STUB - update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz)); + update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); + init_sz = get_unaligned_le32(&buf[0x260]); + update_pecoff_bss(i + (sys_size * 16), init_sz); #ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */ efi_stub_entry -= 0x200; diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 586f41aac361..185fad49d86f 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -24,10 +24,6 @@ .align 16 .Lbswap_mask: .octa 0x000102030405060708090a0b0c0d0e0f -.Lpoly: - .octa 0xc2000000000000000000000000000001 -.Ltwo_one: - .octa 0x00000001000000000000000000000001 #define DATA %xmm0 #define SHASH %xmm1 @@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update) .Lupdate_just_ret: ret ENDPROC(clmul_ghash_update) - -/* - * void clmul_ghash_setkey(be128 *shash, const u8 *key); - * - * Calculate hash_key << 1 mod poly - */ -ENTRY(clmul_ghash_setkey) - movaps .Lbswap_mask, BSWAP - movups (%rsi), %xmm0 - PSHUFB_XMM BSWAP %xmm0 - movaps %xmm0, %xmm1 - psllq $1, %xmm0 - psrlq $63, %xmm1 - movaps %xmm1, %xmm2 - pslldq $8, %xmm1 - psrldq $8, %xmm2 - por %xmm1, %xmm0 - # reduction - pshufd $0b00100100, %xmm2, %xmm1 - pcmpeqd .Ltwo_one, %xmm1 - pand .Lpoly, %xmm1 - pxor %xmm1, %xmm0 - movups %xmm0, (%rdi) - ret -ENDPROC(clmul_ghash_setkey) diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 6759dd1135be..d785cf2c529c 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -30,8 +30,6 @@ void clmul_ghash_mul(char *dst, const be128 *shash); void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, const be128 *shash); -void clmul_ghash_setkey(be128 *shash, const u8 *key); - struct ghash_async_ctx { struct cryptd_ahash *cryptd_tfm; }; @@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct ghash_ctx *ctx = crypto_shash_ctx(tfm); + be128 *x = (be128 *)key; + u64 a, b; if (keylen != GHASH_BLOCK_SIZE) { crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } - clmul_ghash_setkey(&ctx->shash, key); + /* perform multiplication by 'x' in GF(2^128) */ + a = be64_to_cpu(x->a); + b = be64_to_cpu(x->b); + + ctx->shash.a = (__be64)((b << 1) | (a >> 63)); + ctx->shash.b = (__be64)((a << 1) | (b >> 63)); + + if (a >> 63) + ctx->shash.b ^= cpu_to_be64(0xc2); return 0; } diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index f30cd10293f0..8626b03e83b7 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -141,7 +141,7 @@ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out) /* save number of bits */ bits[1] = cpu_to_be64(sctx->count[0] << 3); - bits[0] = cpu_to_be64(sctx->count[1] << 3) | sctx->count[0] >> 61; + bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61); /* Pad out to 112 mod 128 and append length */ index = sctx->count[0] & 0x7f; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 4299eb05023c..92a2e9333620 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target) 1: movl (%rbp),%ebp _ASM_EXTABLE(1b,ia32_badarg) ASM_CLAC + + /* + * Sysenter doesn't filter flags, so we need to clear NT + * ourselves. To save a few cycles, we can check whether + * NT was set instead of doing an unconditional popfq. + */ + testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp) + jnz sysenter_fix_flags +sysenter_flags_fixed: + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE @@ -184,6 +194,8 @@ sysexit_from_sys_call: TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 + CFI_RESTORE_STATE + #ifdef CONFIG_AUDITSYSCALL .macro auditsys_entry_common movl %esi,%r9d /* 6th arg: 4th syscall arg */ @@ -226,7 +238,6 @@ sysexit_from_sys_call: .endm sysenter_auditsys: - CFI_RESTORE_STATE auditsys_entry_common movl %ebp,%r9d /* reload 6th syscall arg */ jmp sysenter_dispatch @@ -235,6 +246,11 @@ sysexit_audit: auditsys_exit sysexit_from_sys_call #endif +sysenter_fix_flags: + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) + popfq_cfi + jmp sysenter_flags_fixed + sysenter_tracesys: #ifdef CONFIG_AUDITSYSCALL testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index e099f9502ace..5f1296872aed 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -217,9 +217,13 @@ #define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */ #define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_MPX (9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_AVX512F (9*32+16) /* AVX-512 Foundation */ #define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512PF (9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER (9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD (9*32+28) /* AVX-512 Conflict Detection */ /* * BUG word(s) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index acd86c850414..f949715e3957 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -130,7 +130,8 @@ extern void efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); -extern void efi_setup_page_tables(void); +extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); +extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages); extern void __init old_map_region(efi_memory_desc_t *md); extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_mkexec(void); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9c999c1674fa..01f15b227d7e 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -155,8 +155,9 @@ do { \ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) -#define compat_elf_check_arch(x) \ - (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64) +#define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || \ + (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) #if __USER32_DS != __USER_DS # error "The following code assumes __USER32_DS == __USER_DS" diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h new file mode 100644 index 000000000000..99efebb2f69d --- /dev/null +++ b/arch/x86/include/asm/espfix.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_ESPFIX_H +#define _ASM_X86_ESPFIX_H + +#ifdef CONFIG_X86_64 + +#include <asm/percpu.h> + +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +extern void init_espfix_bsp(void); +extern void init_espfix_ap(void); + +#endif /* CONFIG_X86_64 */ + +#endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 7252cd339175..6762a55b798a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -123,14 +123,14 @@ enum fixed_addresses { __end_of_permanent_fixed_addresses, /* - * 256 temporary boot-time mappings, used by early_ioremap(), + * 512 temporary boot-time mappings, used by early_ioremap(), * before ioremap() is functional. * - * If necessary we round it up to the next 256 pages boundary so + * If necessary we round it up to the next 512 pages boundary so * that we can have a single pgd entry and a single pte table: */ #define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 +#define FIX_BTMAPS_SLOTS 8 #define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) FIX_BTMAP_END = (__end_of_permanent_fixed_addresses ^ diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index a8091216963b..68c05398bba9 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + ptep_clear_flush(vma, addr, ptep); } static inline int huge_pte_none(pte_t pte) diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 8e71c7941767..57995f0596a6 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -50,6 +50,32 @@ #define BT_MBI_PCIE_READ 0x00 #define BT_MBI_PCIE_WRITE 0x01 +/* Quark available units */ +#define QRK_MBI_UNIT_HBA 0x00 +#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_RMU 0x04 +#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_MMESRAM 0x05 +#define QRK_MBI_UNIT_SOC 0x31 + +/* Quark read/write opcodes */ +#define QRK_MBI_HBA_READ 0x10 +#define QRK_MBI_HBA_WRITE 0x11 +#define QRK_MBI_HB_READ 0x10 +#define QRK_MBI_HB_WRITE 0x11 +#define QRK_MBI_RMU_READ 0x10 +#define QRK_MBI_RMU_WRITE 0x11 +#define QRK_MBI_MM_READ 0x10 +#define QRK_MBI_MM_WRITE 0x11 +#define QRK_MBI_MMESRAM_READ 0x12 +#define QRK_MBI_MMESRAM_WRITE 0x13 +#define QRK_MBI_SOC_READ 0x06 +#define QRK_MBI_SOC_WRITE 0x07 + +#if IS_ENABLED(CONFIG_IOSF_MBI) + +bool iosf_mbi_available(void); + /** * iosf_mbi_read() - MailBox Interface read command * @port: port indicating subunit being accessed @@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); */ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); +#else /* CONFIG_IOSF_MBI is not enabled */ +static inline +bool iosf_mbi_available(void) +{ + return false; +} + +static inline +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} +#endif /* CONFIG_IOSF_MBI */ + #endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index bba3cf88e624..0a8b519226b8 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void) #define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */ -#define INTERRUPT_RETURN iretq +#define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index fdf83afbb7d9..e9dc02968cf8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -462,7 +462,7 @@ struct kvm_vcpu_arch { bool nmi_injected; /* Trying to inject an NMI this entry */ struct mtrr_state_type mtrr_state; - u32 pat; + u64 pat; int switch_db_regs; unsigned long db[KVM_NR_DB_REGS]; @@ -480,6 +480,7 @@ struct kvm_vcpu_arch { u64 mmio_gva; unsigned access; gfn_t mmio_gfn; + u64 mmio_gen; struct kvm_pmu pmu; @@ -983,6 +984,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); } +static inline u64 get_canonical(u64 la) +{ + return ((int64_t)la << 16) >> 16; +} + +static inline bool is_noncanonical_address(u64 la) +{ +#ifdef CONFIG_X86_64 + return get_canonical(la) != la; +#else + return false; +#endif +} + #define TSS_IOPB_BASE_OFFSET 0x66 #define TSS_BASE_SIZE 0x68 #define TSS_IOPB_SIZE (65536 / 8) @@ -1041,7 +1056,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_define_shared_msr(unsigned index, u32 msr); -void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1dbf7feb..d869931bde62 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; +extern pte_t level1_fixmap_pgt[512]; extern pgd_t init_level4_pgt[]; #define swapper_pg_dir init_level4_pgt diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index c883bf726398..7166e25ecb57 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t; #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) #define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) #define EARLY_DYNAMIC_PAGE_TABLES 64 diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 1aa9ccd43223..94e40f1efdfd 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -385,6 +385,8 @@ extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern phys_addr_t slow_virt_to_phys(void *__address); extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, unsigned numpages, unsigned long page_flags); +void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address, + unsigned numpages); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_DEFS_H */ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index c8b051933b1b..b39e194f6c8d 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -5,6 +5,18 @@ #include <asm/percpu.h> #include <linux/thread_info.h> +#ifdef CONFIG_X86_32 +/* + * i386's current_thread_info() depends on ESP and for interrupt/exception + * stacks this doesn't yield the actual task thread_info. + * + * We hard rely on the fact that all the TIF_NEED_RESCHED bits are + * the same, therefore use the slightly more expensive version below. + */ +#undef tif_need_resched +#define tif_need_resched() test_tsk_thread_flag(current, TIF_NEED_RESCHED) +#endif + DECLARE_PER_CPU(int, __preempt_count); /* diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 14fd6fd75a19..6205f0c434db 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -231,6 +231,22 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, #define ARCH_HAS_USER_SINGLE_STEP_INFO +/* + * When hitting ptrace_stop(), we cannot return using SYSRET because + * that does not restore the full CPU state, only a minimal set. The + * ptracer can change arbitrary register values, which is usually okay + * because the usual ptrace stops run off the signal delivery path which + * forces IRET; however, ptrace_event() stops happen in arbitrary places + * in the kernel and don't force IRET path. + * + * So force IRET path after a ptrace stop. + */ +#define arch_ptrace_stop_needed(code, info) \ +({ \ + set_thread_flag(TIF_NOTIFY_RESUME); \ + false; \ +}) + struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index d62c9f809bc5..75b14ca135be 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -65,6 +65,8 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP +#include <asm/espfix.h> + /* * This is set up by the setup-routine at boot-time */ diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 554738963b28..6c1d7411eb00 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -6,11 +6,14 @@ #define XSTATE_CPUID 0x0000000d -#define XSTATE_FP 0x1 -#define XSTATE_SSE 0x2 -#define XSTATE_YMM 0x4 -#define XSTATE_BNDREGS 0x8 -#define XSTATE_BNDCSR 0x10 +#define XSTATE_FP 0x1 +#define XSTATE_SSE 0x2 +#define XSTATE_YMM 0x4 +#define XSTATE_BNDREGS 0x8 +#define XSTATE_BNDCSR 0x10 +#define XSTATE_OPMASK 0x20 +#define XSTATE_ZMM_Hi256 0x40 +#define XSTATE_Hi16_ZMM 0x80 #define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) @@ -23,7 +26,8 @@ #define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) /* Supported features which support lazy state saving */ -#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) +#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ + | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) /* Supported features which require eager state saving */ #define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 0e79420376eb..990a2fe1588d 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -67,6 +67,7 @@ #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 #define EXIT_REASON_PREEMPTION_TIMER 52 +#define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 #define EXIT_REASON_APIC_WRITE 56 @@ -114,6 +115,7 @@ { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \ { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \ { EXIT_REASON_INVD, "INVD" }, \ + { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" } #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index cb648c84b327..56bac868cb91 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7f26c9a70a9e..523f147b2470 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1290,7 +1290,7 @@ void setup_local_APIC(void) unsigned int value, queued; int i, j, acked = 0; unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz; + long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) rdtscll(tsc); @@ -1387,7 +1387,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc) { + if (cpu_has_tsc && cpu_khz) { rdtscll(ntsc); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8e28bf2fc3ef..3f27f5fd0847 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1141,7 +1141,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 5cd9bfabd645..66746a880dec 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -153,6 +153,21 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -368,6 +383,13 @@ static void init_intel(struct cpuinfo_x86 *c) detect_extended_topology(c); l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -482,6 +504,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -709,7 +738,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 9f7ca266864a..832d05a914ba 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -26,6 +26,7 @@ #include <asm/irq_regs.h> #include <asm/i8259.h> #include <asm/apic.h> +#include <asm/timer.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -105,6 +106,11 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); + +#ifdef CONFIG_X86_IO_APIC + no_timer_check = 1; +#endif + } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index aa333d966886..1340ebfcb467 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1383,6 +1383,15 @@ again: intel_pmu_lbr_read(); /* + * CondChgd bit 63 doesn't mean any overflow status. Ignore + * and clear the bit. + */ + if (__test_and_clear_bit(63, (unsigned long *)&status)) { + if (!status) + goto done; + } + + /* * PEBS overflow sets bit 62 in the global status register */ if (__test_and_clear_bit(62, (unsigned long *)&status)) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 5ad35ad94d0f..95700e52061d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -511,6 +511,7 @@ static int rapl_cpu_prepare(int cpu) struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); int phys_id = topology_physical_package_id(cpu); u64 ms; + u64 msr_rapl_power_unit_bits; if (pmu) return 0; @@ -518,6 +519,9 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; + if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + return -1; + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -1; @@ -531,8 +535,7 @@ static int rapl_cpu_prepare(int cpu) * * we cache in local PMU instance */ - rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit); - pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL; + pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; pmu->pmu = &rapl_pmu_class; /* @@ -649,7 +652,9 @@ static int __init rapl_pmu_init(void) get_online_cpus(); for_each_online_cpu(cpu) { - rapl_cpu_prepare(cpu); + ret = rapl_cpu_prepare(cpu); + if (ret) + goto out; rapl_cpu_init(cpu); } @@ -672,6 +677,7 @@ static int __init rapl_pmu_init(void) hweight32(rapl_cntr_mask), ktime_to_ms(pmu->timer_interval)); +out: put_online_cpus(); return 0; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index bc4a088f9023..6d7d5a1260a6 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func) revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID); /* - * Revision 13 of all triggering devices id in this quirk have - * a problem draining interrupts when irq remapping is enabled, - * and should be flagged as broken. Additionally revisions 0x12 - * and 0x22 of device id 0x3405 has this problem. + * Revision <= 13 of all triggering devices id in this quirk + * have a problem draining interrupts when irq remapping is + * enabled, and should be flagged as broken. Additionally + * revision 0x22 of device id 0x3405 has this problem. */ - if (revision == 0x13) + if (revision <= 0x13) set_irq_remapping_broken(); - else if ((device == 0x3405) && - ((revision == 0x12) || - (revision == 0x22))) + else if (device == 0x3405 && revision == 0x22) set_irq_remapping_broken(); - } /* diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index a2a4f4697889..c5a9cb94dee6 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -431,8 +431,9 @@ sysenter_past_esp: jnz sysenter_audit sysenter_do_call: cmpl $(NR_syscalls), %eax - jae syscall_badsys + jae sysenter_badsys call *sys_call_table(,%eax,4) +sysenter_after_call: movl %eax,PT_EAX(%esp) LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) @@ -513,6 +514,7 @@ ENTRY(system_call) jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) +syscall_after_call: movl %eax,PT_EAX(%esp) # store the return value syscall_exit: LOCKDEP_SYS_EXIT @@ -527,6 +529,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -537,6 +540,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -549,13 +553,9 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -597,6 +597,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -687,8 +688,13 @@ syscall_fault: END(syscall_fault) syscall_badsys: - movl $-ENOSYS,PT_EAX(%esp) - jmp resume_userspace + movl $-ENOSYS,%eax + jmp syscall_after_call +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS,%eax + jmp sysenter_after_call END(syscall_badsys) CFI_ENDPROC /* @@ -704,6 +710,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -713,8 +720,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -725,6 +734,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -1355,11 +1365,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1399,6 +1411,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1420,6 +1433,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 1e96c3628bf2..03cd2a8f6009 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -58,6 +58,7 @@ #include <asm/asm.h> #include <asm/context_tracking.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -1041,12 +1042,45 @@ restore_args: irq_return: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) -#ifdef CONFIG_PARAVIRT ENTRY(native_iret) + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz native_irq_return_ldt +#endif + +native_irq_return_iret: iretq - _ASM_EXTABLE(native_iret, bad_iret) + _ASM_EXTABLE(native_irq_return_iret, bad_iret) + +#ifdef CONFIG_X86_ESPFIX64 +native_irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi + SWAPGS + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp native_irq_return_iret #endif .section .fixup,"ax" @@ -1110,9 +1144,40 @@ ENTRY(retint_kernel) call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) + + /* + * If IRET takes a fault on the espfix stack, then we + * end up promoting it to a doublefault. In that case, + * modify the stack to make it look like we just entered + * the #GP handler from user space, similar to bad_iret. + */ +#ifdef CONFIG_X86_ESPFIX64 + ALIGN +__do_double_fault: + XCPT_FRAME 1 RDI+8 + movq RSP(%rdi),%rax /* Trap on the espfix stack? */ + sarq $PGDIR_SHIFT,%rax + cmpl $ESPFIX_PGD_ENTRY,%eax + jne do_double_fault /* No, just deliver the fault */ + cmpl $__KERNEL_CS,CS(%rdi) + jne do_double_fault + movq RIP(%rdi),%rax + cmpq $native_irq_return_iret,%rax + jne do_double_fault /* This shouldn't happen... */ + movq PER_CPU_VAR(kernel_stack),%rax + subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ + movq %rax,RSP(%rdi) + movq $0,(%rax) /* Missing (lost) #GP error code */ + movq $general_protection,RIP(%rdi) + retq + CFI_ENDPROC +END(__do_double_fault) +#else +# define __do_double_fault do_double_fault +#endif + /* * End of kprobes section */ @@ -1314,7 +1379,7 @@ zeroentry overflow do_overflow zeroentry bounds do_bounds zeroentry invalid_op do_invalid_op zeroentry device_not_available do_device_not_available -paranoiderrorentry double_fault do_double_fault +paranoiderrorentry double_fault __do_double_fault zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun errorentry invalid_TSS do_invalid_TSS errorentry segment_not_present do_segment_not_present @@ -1601,7 +1666,7 @@ error_sti: */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) je error_swapgs movl %ecx,%eax /* zero extend */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c new file mode 100644 index 000000000000..94d857fb1033 --- /dev/null +++ b/arch/x86/kernel/espfix_64.c @@ -0,0 +1,208 @@ +/* ----------------------------------------------------------------------- * + * + * Copyright 2014 Intel Corporation; author: H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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. + * + * ----------------------------------------------------------------------- */ + +/* + * The IRET instruction, when returning to a 16-bit segment, only + * restores the bottom 16 bits of the user space stack pointer. This + * causes some 16-bit software to break, but it also leaks kernel state + * to user space. + * + * This works around this by creating percpu "ministacks", each of which + * is mapped 2^16 times 64K apart. When we detect that the return SS is + * on the LDT, we copy the IRET frame to the ministack and use the + * relevant alias to return to userspace. The ministacks are mapped + * readonly, so if the IRET fault we promote #GP to #DF which is an IST + * vector and thus has its own stack; we then do the fixup in the #DF + * handler. + * + * This file sets up the ministacks and the related page tables. The + * actual ministack invocation is in entry_64.S. + */ + +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/gfp.h> +#include <linux/random.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/setup.h> +#include <asm/espfix.h> + +/* + * Note: we only need 6*8 = 48 bytes for the espfix stack, but round + * it up to a cache line to avoid unnecessary sharing. + */ +#define ESPFIX_STACK_SIZE (8*8UL) +#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) + +/* There is address space for how many espfix pages? */ +#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) + +#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) +#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS +# error "Need more than one PGD for the ESPFIX hack" +#endif + +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + +/* This contains the *bottom* address of the espfix stack */ +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +/* Initialization mutex - should this be a spinlock? */ +static DEFINE_MUTEX(espfix_init_mutex); + +/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ +#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) +static void *espfix_pages[ESPFIX_MAX_PAGES]; + +static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] + __aligned(PAGE_SIZE); + +static unsigned int page_random, slot_random; + +/* + * This returns the bottom address of the espfix stack for a specific CPU. + * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case + * we have to account for some amount of padding at the end of each page. + */ +static inline unsigned long espfix_base_addr(unsigned int cpu) +{ + unsigned long page, slot; + unsigned long addr; + + page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; + slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; + addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); + addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); + addr += ESPFIX_BASE_ADDR; + return addr; +} + +#define PTE_STRIDE (65536/PAGE_SIZE) +#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) +#define ESPFIX_PMD_CLONES PTRS_PER_PMD +#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) + +#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) + +static void init_espfix_random(void) +{ + unsigned long rand; + + /* + * This is run before the entropy pools are initialized, + * but this is hopefully better than nothing. + */ + if (!arch_get_random_long(&rand)) { + /* The constant is an arbitrary large prime */ + rdtscll(rand); + rand *= 0xc345c6b72fd16123UL; + } + + slot_random = rand % ESPFIX_STACKS_PER_PAGE; + page_random = (rand / ESPFIX_STACKS_PER_PAGE) + & (ESPFIX_PAGE_SPACE - 1); +} + +void __init init_espfix_bsp(void) +{ + pgd_t *pgd_p; + pteval_t ptemask; + + ptemask = __supported_pte_mask; + + /* Install the espfix pud into the kernel page directory */ + pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + + /* Randomize the locations */ + init_espfix_random(); + + /* The rest is the same as for any other processor */ + init_espfix_ap(); +} + +void init_espfix_ap(void) +{ + unsigned int cpu, page; + unsigned long addr; + pud_t pud, *pud_p; + pmd_t pmd, *pmd_p; + pte_t pte, *pte_p; + int n; + void *stack_page; + pteval_t ptemask; + + /* We only have to do this once... */ + if (likely(this_cpu_read(espfix_stack))) + return; /* Already initialized */ + + cpu = smp_processor_id(); + addr = espfix_base_addr(cpu); + page = cpu/ESPFIX_STACKS_PER_PAGE; + + /* Did another CPU already set this up? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (likely(stack_page)) + goto done; + + mutex_lock(&espfix_init_mutex); + + /* Did we race on the lock? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (stack_page) + goto unlock_done; + + ptemask = __supported_pte_mask; + + pud_p = &espfix_pud_page[pud_index(addr)]; + pud = *pud_p; + if (!pud_present(pud)) { + pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PUD_CLONES; n++) + set_pud(&pud_p[n], pud); + } + + pmd_p = pmd_offset(&pud, addr); + pmd = *pmd_p; + if (!pmd_present(pmd)) { + pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PMD_CLONES; n++) + set_pmd(&pmd_p[n], pmd); + } + + pte_p = pte_offset_kernel(&pmd, addr); + stack_page = (void *)__get_free_page(GFP_KERNEL); + pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + for (n = 0; n < ESPFIX_PTE_CLONES; n++) + set_pte(&pte_p[n*PTE_STRIDE], pte); + + /* Job is done for this CPU and any CPU which shares this page */ + ACCESS_ONCE(espfix_pages[page]) = stack_page; + +unlock_done: + mutex_unlock(&espfix_init_mutex); +done: + this_cpu_write(espfix_stack, addr); + this_cpu_write(espfix_waddr, (unsigned long)stack_page + + (addr & ~PAGE_MASK)); +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index e6253195a301..1ffc32dbe450 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -659,8 +659,8 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code, ret = -EPERM; goto out; } - run_sync(); out: + run_sync(); return ret; fail_update: diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index c3aae6672843..2e97b3cfa6c7 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -25,6 +25,10 @@ #include <asm/iosf_mbi.h> +#define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_BRASWELL 0x2280 +#define PCI_DEVICE_ID_QUARK_X1000 0x0958 + static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -177,6 +181,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) } EXPORT_SYMBOL(iosf_mbi_modify); +bool iosf_mbi_available(void) +{ + /* Mbi isn't hot-pluggable. No remove routine is provided */ + return mbi_pdev; +} +EXPORT_SYMBOL(iosf_mbi_available); + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -193,7 +204,9 @@ static int iosf_mbi_probe(struct pci_dev *pdev, } static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ebc987398923..c37886d759cc 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -229,6 +229,11 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out_unlock; + } + fill_ldt(&ldt, &ldt_info); if (oldmode) ldt.avl = 0; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 3f08f34f93eb..a1da6737ba5b 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); -DEF_NATIVE(pv_cpu_ops, iret, "iretq"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); @@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, iret); PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 2a26819bb6a8..80eab01c1a68 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail) void arch_remove_reservations(struct resource *avail) { - /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ + /* + * Trim out BIOS area (high 2MB) and E820 regions. We do not remove + * the low 1MB unconditionally, as this area is needed for some ISA + * cards requiring a memory range, e.g. the i82365 PCMCIA controller. + */ if (avail->flags & IORESOURCE_MEM) { - if (avail->start < BIOS_END) - avail->start = BIOS_END; resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); remove_e820_regions(avail); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 9e5de6813e1f..b88fc86309bc 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index a32da804252e..682876533ed9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -243,6 +243,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. @@ -1280,6 +1287,9 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, cpu_sibling_mask(cpu)) cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(cpu_sibling_mask(cpu)); cpumask_clear(cpu_core_mask(cpu)); c->phys_proc_id = 0; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cfbe99f88830..de0290605903 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -921,9 +921,9 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); - } - set_cyc2ns_scale(tsc_khz, freq->cpu); + set_cyc2ns_scale(tsc_khz, freq->cpu); + } return 0; } @@ -1173,14 +1173,17 @@ void __init tsc_init(void) x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) + if (!cpu_has_tsc) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 1f96f9347ed9..09ce23ae370c 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, current->comm, task_pid_nr(current), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a4b451c6addf..dd50e26c58f6 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -399,8 +397,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) set_used_math(); } - if (use_eager_fpu()) + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 07ffca0a89e9..38d3751472e4 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -498,11 +498,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc); } -static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) -{ - register_address_increment(ctxt, &ctxt->_eip, rel); -} - static u32 desc_limit_scaled(struct desc_struct *desc) { u32 limit = get_desc_limit(desc); @@ -576,6 +571,38 @@ static int emulate_nm(struct x86_emulate_ctxt *ctxt) return emulate_exception(ctxt, NM_VECTOR, 0, false); } +static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, + int cs_l) +{ + switch (ctxt->op_bytes) { + case 2: + ctxt->_eip = (u16)dst; + break; + case 4: + ctxt->_eip = (u32)dst; + break; + case 8: + if ((cs_l && is_noncanonical_address(dst)) || + (!cs_l && (dst & ~(u32)-1))) + return emulate_gp(ctxt, 0); + ctxt->_eip = dst; + break; + default: + WARN(1, "unsupported eip assignment size\n"); + } + return X86EMUL_CONTINUE; +} + +static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) +{ + return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64); +} + +static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) +{ + return assign_eip_near(ctxt, ctxt->_eip + rel); +} + static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg) { u16 selector; @@ -1958,13 +1985,15 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) case 2: /* call near abs */ { long int old_eip; old_eip = ctxt->_eip; - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); + if (rc != X86EMUL_CONTINUE) + break; ctxt->src.val = old_eip; rc = em_push(ctxt); break; } case 4: /* jmp abs */ - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); break; case 5: /* jmp far */ rc = em_jmp_far(ctxt); @@ -1996,16 +2025,21 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) static int em_ret(struct x86_emulate_ctxt *ctxt) { - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - return em_pop(ctxt); + int rc; + unsigned long eip; + + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + + return assign_eip_near(ctxt, eip); } static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long cs; + int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -2015,6 +2049,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &cs, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; + /* Outer-privilege level return is not implemented */ + if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl) + return X86EMUL_UNHANDLEABLE; rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS); return rc; } @@ -2273,7 +2310,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct cs, ss; - u64 msr_data; + u64 msr_data, rcx, rdx; int usermode; u16 cs_sel = 0, ss_sel = 0; @@ -2289,6 +2326,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) else usermode = X86EMUL_MODE_PROT32; + rcx = reg_read(ctxt, VCPU_REGS_RCX); + rdx = reg_read(ctxt, VCPU_REGS_RDX); + cs.dpl = 3; ss.dpl = 3; ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); @@ -2306,6 +2346,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ss_sel = cs_sel + 8; cs.d = 0; cs.l = 1; + if (is_noncanonical_address(rcx) || + is_noncanonical_address(rdx)) + return emulate_gp(ctxt, 0); break; } cs_sel |= SELECTOR_RPL_MASK; @@ -2314,8 +2357,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); - ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX); - *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX); + ctxt->_eip = rdx; + *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; } @@ -2854,10 +2897,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt) static int em_call(struct x86_emulate_ctxt *ctxt) { + int rc; long rel = ctxt->src.val; ctxt->src.val = (unsigned long)ctxt->_eip; - jmp_rel(ctxt, rel); + rc = jmp_rel(ctxt, rel); + if (rc != X86EMUL_CONTINUE) + return rc; return em_push(ctxt); } @@ -2889,11 +2935,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) { int rc; + unsigned long eip; - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + rc = assign_eip_near(ctxt, eip); if (rc != X86EMUL_CONTINUE) return rc; rsp_increment(ctxt, ctxt->src.val); @@ -3223,20 +3270,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt) static int em_loop(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1); if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) && (ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags))) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_jcxz(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_in(struct x86_emulate_ctxt *ctxt) @@ -4633,7 +4684,7 @@ special_insn: break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x8d: /* lea r16/r32, m */ ctxt->dst.val = ctxt->src.addr.mem.ea; @@ -4662,7 +4713,7 @@ special_insn: break; case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); ctxt->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ @@ -4782,7 +4833,7 @@ twobyte_insn: break; case 0x80 ... 0x8f: /* jnz rel, etc*/ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 518d86471b76..298781d4cfb4 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -262,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) return; timer = &pit->pit_state.timer; + mutex_lock(&pit->pit_state.lock); if (hrtimer_cancel(timer)) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + mutex_unlock(&pit->pit_state.lock); } static void destroy_pit_timer(struct kvm_pit *pit) diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 484bc874688b..3ec38cb56bd5 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) vector = kvm_cpu_get_extint(v); - if (kvm_apic_vid_enabled(v->kvm) || vector != -1) + if (vector != -1) return vector; /* PIC */ return kvm_get_apic_interrupt(v); /* APIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9736529ade08..453e5fbbb7ae 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -352,31 +352,90 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) { - apic->irr_pending = false; + struct kvm_vcpu *vcpu; + + vcpu = apic->vcpu; + apic_clear_vector(vec, apic->regs + APIC_IRR); - if (apic_search_irr(apic) != -1) - apic->irr_pending = true; + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + /* try to update RVI */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + else { + vec = apic_search_irr(apic); + apic->irr_pending = (vec != -1); + } } static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { - if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + + if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * With APIC virtualization enabled, all caching is disabled + * because the processor can modify ISR under the hood. Instead + * just set SVI. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); + else { ++apic->isr_count; - BUG_ON(apic->isr_count > MAX_APIC_VECTOR); + BUG_ON(apic->isr_count > MAX_APIC_VECTOR); + /* + * ISR (in service register) bit is set when injecting an interrupt. + * The highest vector is injected. Thus the latest bit set matches + * the highest bit in ISR. + */ + apic->highest_isr_cache = vec; + } +} + +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + /* - * ISR (in service register) bit is set when injecting an interrupt. - * The highest vector is injected. Thus the latest bit set matches - * the highest bit in ISR. + * Note that isr_count is always 1, and highest_isr_cache + * is always -1, with APIC virtualization enabled. */ - apic->highest_isr_cache = vec; + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; + + result = find_highest_vector(apic->regs + APIC_ISR); + ASSERT(result == -1 || result >= 16); + + return result; } static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { - if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * We do get here for APIC virtualization enabled if the guest + * uses the Hyper-V APIC enlightenment. In this case we may need + * to trigger a new interrupt delivery by writing the SVI field; + * on the other hand isr_count and highest_isr_cache are unused + * and must be left alone. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + apic_find_highest_isr(apic)); + else { --apic->isr_count; - BUG_ON(apic->isr_count < 0); - apic->highest_isr_cache = -1; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; + } } int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) @@ -456,22 +515,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static inline int apic_find_highest_isr(struct kvm_lapic *apic) -{ - int result; - - /* Note that isr_count is always 1 with vid enabled */ - if (!apic->isr_count) - return -1; - if (likely(apic->highest_isr_cache != -1)) - return apic->highest_isr_cache; - - result = find_highest_vector(apic->regs + APIC_ISR); - ASSERT(result == -1 || result >= 16); - - return result; -} - void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1608,6 +1651,13 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) if (vector == -1) return -1; + /* + * We get here even with APIC virtualization enabled, if doing + * nested virtualization and L1 runs with the "acknowledge interrupt + * on exit" mode. Then we cannot inject the interrupt via RVI, + * because the process would deliver it through the IDT. + */ + apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9b531351a587..49088b8a3ee3 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -198,16 +198,20 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); /* - * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number, - * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation - * number. + * the low bit of the generation number is always presumed to be zero. + * This disables mmio caching during memslot updates. The concept is + * similar to a seqcount but instead of retrying the access we just punt + * and ignore the cache. + * + * spte bits 3-11 are used as bits 1-9 of the generation number, + * the bits 52-61 are used as bits 10-19 of the generation number. */ -#define MMIO_SPTE_GEN_LOW_SHIFT 3 +#define MMIO_SPTE_GEN_LOW_SHIFT 2 #define MMIO_SPTE_GEN_HIGH_SHIFT 52 -#define MMIO_GEN_SHIFT 19 -#define MMIO_GEN_LOW_SHIFT 9 -#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 1) +#define MMIO_GEN_SHIFT 20 +#define MMIO_GEN_LOW_SHIFT 10 +#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 2) #define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1) #define MMIO_MAX_GEN ((1 << MMIO_GEN_SHIFT) - 1) @@ -3157,7 +3161,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - vcpu_clear_mmio_info(vcpu, ~0ul); + vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; @@ -4379,7 +4383,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) * The very rare case: if the generation-number is round, * zap all shadow pages. */ - if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) { + if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 2de1bc09a8d4..9643eda60a52 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3213,7 +3213,7 @@ static int wrmsr_interception(struct vcpu_svm *svm) msr.host_initiated = false; svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (svm_set_msr(&svm->vcpu, &msr)) { + if (kvm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); } else { @@ -3495,9 +3495,9 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_code; - return 0; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } return svm_exit_handlers[exit_code](svm); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 392752834751..0c90f4b3f835 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2582,12 +2582,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: msr = find_msr_entry(vmx, msr_index); if (msr) { + u64 old_msr_data = msr->data; msr->data = data; if (msr - vmx->guest_msrs < vmx->save_nmsrs) { preempt_disable(); - kvm_set_shared_msr(msr->index, msr->data, - msr->mask); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); preempt_enable(); + if (ret) + msr->data = old_msr_data; } break; } @@ -5169,7 +5172,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu) msr.data = data; msr.index = ecx; msr.host_initiated = false; - if (vmx_set_msr(vcpu, &msr) != 0) { + if (kvm_set_msr(vcpu, &msr) != 0) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(vcpu, 0); return 1; @@ -6441,6 +6444,12 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; } +static int handle_invvpid(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -6486,6 +6495,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_INVEPT] = handle_invept, + [EXIT_REASON_INVVPID] = handle_invvpid, }; static const int kvm_vmx_max_exit_handlers = @@ -6719,7 +6729,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD: case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE: case EXIT_REASON_VMOFF: case EXIT_REASON_VMON: - case EXIT_REASON_INVEPT: + case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID: /* * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! @@ -6884,10 +6894,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; - vcpu->run->hw.hardware_exit_reason = exit_reason; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } - return 0; } static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2b8578432d5b..51c2851ca243 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -225,20 +225,25 @@ static void kvm_shared_msr_cpu_online(void) shared_msr_update(i, shared_msrs_global.msrs[i]); } -void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) { unsigned int cpu = smp_processor_id(); struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + int err; if (((value ^ smsr->values[slot].curr) & mask) == 0) - return; + return 0; smsr->values[slot].curr = value; - wrmsrl(shared_msrs_global.msrs[slot], value); + err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); + if (err) + return 1; + if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); smsr->registered = true; } + return 0; } EXPORT_SYMBOL_GPL(kvm_set_shared_msr); @@ -946,7 +951,6 @@ void kvm_enable_efer_bits(u64 mask) } EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); - /* * Writes msr value into into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -954,8 +958,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); */ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { + switch (msr->index) { + case MSR_FS_BASE: + case MSR_GS_BASE: + case MSR_KERNEL_GS_BASE: + case MSR_CSTAR: + case MSR_LSTAR: + if (is_noncanonical_address(msr->data)) + return 1; + break; + case MSR_IA32_SYSENTER_EIP: + case MSR_IA32_SYSENTER_ESP: + /* + * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if + * non-canonical address is written on Intel but not on + * AMD (which ignores the top 32-bits, because it does + * not implement 64-bit SYSENTER). + * + * 64-bit code should hence be able to write a non-canonical + * value on AMD. Making the address canonical ensures that + * vmentry does not fail on Intel after writing a non-canonical + * value, and that something deterministic happens if the guest + * invokes 64-bit SYSENTER. + */ + msr->data = get_canonical(msr->data); + } return kvm_x86_ops->set_msr(vcpu, msr); } +EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention @@ -1109,7 +1139,6 @@ static inline u64 get_kernel_ns(void) { struct timespec ts; - WARN_ON(preemptible()); ktime_get_ts(&ts); monotonic_to_bootbased(&ts); return timespec_to_ns(&ts); @@ -1867,7 +1896,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) break; gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - if (kvm_write_guest(kvm, data, + if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, &tsc_ref, sizeof(tsc_ref))) return 1; mark_page_dirty(kvm, gfn); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 8da5823bcde6..21ea4fc91b5b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -78,15 +78,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, vcpu->arch.mmio_gva = gva & PAGE_MASK; vcpu->arch.access = access; vcpu->arch.mmio_gfn = gfn; + vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation; +} + +static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation; } /* - * Clear the mmio cache info for the given gva, - * specially, if gva is ~0ul, we clear all mmio cache info. + * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we + * clear all mmio cache info. */ +#define MMIO_GVA_ANY (~(gva_t)0) + static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) { - if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) + if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) return; vcpu->arch.mmio_gva = 0; @@ -94,7 +102,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) { - if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK)) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva && + vcpu->arch.mmio_gva == (gva & PAGE_MASK)) return true; return false; @@ -102,7 +111,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) { - if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn && + vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) return true; return false; diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c index 3056702e81fb..060cc4415bd9 100644 --- a/arch/x86/lib/hash.c +++ b/arch/x86/lib/hash.c @@ -39,7 +39,11 @@ static inline u32 crc32_u32(u32 crc, u32 val) { +#ifdef CONFIG_AS_CRC32 asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val)); +#else + asm (".byte 0xf2, 0x0f, 0x38, 0xf1, 0xc1" : "+a" (crc) : "c" (val)); +#endif return crc; } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0002a3a33081..3620928631ce 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,11 +30,13 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + unsigned long lines; }; struct addr_marker { unsigned long start_address; const char *name; + unsigned long max_lines; }; /* indices for address_markers; keep sync'd w/ address_markers below */ @@ -45,6 +47,7 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, + ESPFIX_START_NR, HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, @@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, + { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, pgprot_t new_prot, int level) { pgprotval_t prot, cur; - static const char units[] = "KMGTPE"; + static const char units[] = "BKMGTPE"; /* * If we have a "break" in the series, we need to flush the state that @@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; + st->lines = 0; seq_printf(m, "---[ %s ]---\n", st->marker->name); } else if (prot != cur || level != st->level || st->current_address >= st->marker[1].start_address) { @@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - seq_printf(m, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); - - delta = (st->current_address - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; + if (!st->marker->max_lines || + st->lines < st->marker->max_lines) { + seq_printf(m, "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); + + delta = (st->current_address - st->start_address) >> 10; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + seq_printf(m, "%9lu%c ", delta, *unit); + printk_prot(m, st->current_prot, st->level); } - seq_printf(m, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level); + st->lines++; /* * We print markers for special areas of address space, diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8c9f647ff9e1..8b977ebf9388 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { return NULL; } - -int pmd_huge_support(void) -{ - return 0; -} #else struct page * @@ -80,11 +75,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } - -int pmd_huge_support(void) -{ - return 1; -} #endif #ifdef CONFIG_HUGETLB_PAGE diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 799580cabc78..94bd24771812 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, return err; } +static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, + void *arg) +{ + unsigned long i; + + for (i = 0; i < nr_pages; ++i) + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return 1; + + WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); + + return 0; +} + /* * Remap an arbitrary physical address space into the kernel virtual * address space. Needed when the kernel wants to access high addresses @@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ + pfn = phys_addr >> PAGE_SHIFT; last_pfn = last_addr >> PAGE_SHIFT; - for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { - int is_ram = page_is_ram(pfn); - - if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) - return NULL; - WARN_ON_ONCE(is_ram); - } + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) + return NULL; /* * Mappings have to be page-aligned diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index b3b19f46c016..fed892de9baf 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -405,7 +405,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) psize = page_level_size(level); pmask = page_level_mask(level); offset = virt_addr & ~pmask; - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; return (phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); @@ -692,6 +692,18 @@ static bool try_to_free_pmd_page(pmd_t *pmd) return true; } +static bool try_to_free_pud_page(pud_t *pud) +{ + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) + if (!pud_none(pud[i])) + return false; + + free_page((unsigned long)pud); + return true; +} + static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) { pte_t *pte = pte_offset_kernel(pmd, start); @@ -805,6 +817,16 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) */ } +static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end) +{ + pgd_t *pgd_entry = root + pgd_index(addr); + + unmap_pud_range(pgd_entry, addr, end); + + if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry))) + pgd_clear(pgd_entry); +} + static int alloc_pte_page(pmd_t *pmd) { pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); @@ -999,9 +1021,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, static int populate_pgd(struct cpa_data *cpa, unsigned long addr) { pgprot_t pgprot = __pgprot(_KERNPG_TABLE); - bool allocd_pgd = false; - pgd_t *pgd_entry; pud_t *pud = NULL; /* shut up gcc */ + pgd_t *pgd_entry; int ret; pgd_entry = cpa->pgd + pgd_index(addr); @@ -1015,7 +1036,6 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) return -1; set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE)); - allocd_pgd = true; } pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); @@ -1023,19 +1043,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) ret = populate_pud(cpa, addr, pgd_entry, pgprot); if (ret < 0) { - unmap_pud_range(pgd_entry, addr, + unmap_pgd_range(cpa->pgd, addr, addr + (cpa->numpages << PAGE_SHIFT)); - - if (allocd_pgd) { - /* - * If I allocated this PUD page, I can just as well - * free it in this error path. - */ - pgd_clear(pgd_entry); - free_page((unsigned long)pud); - } return ret; } + cpa->numpages = ret; return 0; } @@ -1861,6 +1873,12 @@ out: return retval; } +void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address, + unsigned numpages) +{ + unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT)); +} + /* * The testcases use internal knowledge of the implementation that shouldn't * be exposed to the rest of the kernel. Include these directly here. diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4ed75dd81d05..af2d4317b218 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -171,7 +171,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen, memset(header, 0xcc, sz); /* fill whole space with int3 instructions */ header->pages = sz / PAGE_SIZE; - hole = sz - (proglen + sizeof(*header)); + hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header)); /* insert a random number of int3 instructions before BPF code */ *image_ptr = &header->image[prandom_u32() % hole]; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index db6b1ab43255..96a159afe3c6 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res, return start; if (start & 0x300) start = (start + 0x3ff) & ~0x3ff; + } else if (res->flags & IORESOURCE_MEM) { + /* The low 1MB range is reserved for ISA cards */ + if (start < BIOS_END) + start = BIOS_END; } return start; } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index b97acecf3fd9..abb81b0ad83f 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -939,14 +939,36 @@ static void __init efi_map_regions_fixed(void) } +static void *realloc_pages(void *old_memmap, int old_shift) +{ + void *ret; + + ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1); + if (!ret) + goto out; + + /* + * A first-time allocation doesn't have anything to copy. + */ + if (!old_memmap) + return ret; + + memcpy(ret, old_memmap, PAGE_SIZE << old_shift); + +out: + free_pages((unsigned long)old_memmap, old_shift); + return ret; +} + /* - * Map efi memory ranges for runtime serivce and update new_memmap with virtual - * addresses. + * Map the efi memory ranges of the runtime services and update new_mmap with + * virtual addresses. */ -static void * __init efi_map_regions(int *count) +static void * __init efi_map_regions(int *count, int *pg_shift) { + void *p, *new_memmap = NULL; + unsigned long left = 0; efi_memory_desc_t *md; - void *p, *tmp, *new_memmap = NULL; for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; @@ -961,20 +983,23 @@ static void * __init efi_map_regions(int *count) efi_map_region(md); get_systab_virt_addr(md); - tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size, - GFP_KERNEL); - if (!tmp) - goto out; - new_memmap = tmp; + if (left < memmap.desc_size) { + new_memmap = realloc_pages(new_memmap, *pg_shift); + if (!new_memmap) + return NULL; + + left += PAGE_SIZE << *pg_shift; + (*pg_shift)++; + } + memcpy(new_memmap + (*count * memmap.desc_size), md, memmap.desc_size); + + left -= memmap.desc_size; (*count)++; } return new_memmap; -out: - kfree(new_memmap); - return NULL; } /* @@ -1000,9 +1025,9 @@ out: */ void __init efi_enter_virtual_mode(void) { - efi_status_t status; + int err, count = 0, pg_shift = 0; void *new_memmap = NULL; - int err, count = 0; + efi_status_t status; efi.systab = NULL; @@ -1019,20 +1044,24 @@ void __init efi_enter_virtual_mode(void) efi_map_regions_fixed(); } else { efi_merge_regions(); - new_memmap = efi_map_regions(&count); + new_memmap = efi_map_regions(&count, &pg_shift); if (!new_memmap) { pr_err("Error reallocating memory, EFI runtime non-functional!\n"); return; } - } - err = save_runtime_map(); - if (err) - pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); + err = save_runtime_map(); + if (err) + pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); + } BUG_ON(!efi.systab); - efi_setup_page_tables(); + if (!efi_setup) { + if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) + return; + } + efi_sync_low_kernel_mappings(); if (!efi_setup) { @@ -1072,7 +1101,35 @@ void __init efi_enter_virtual_mode(void) efi_runtime_mkexec(); - kfree(new_memmap); + + /* + * We mapped the descriptor array into the EFI pagetable above but we're + * not unmapping it here. Here's why: + * + * We're copying select PGDs from the kernel page table to the EFI page + * table and when we do so and make changes to those PGDs like unmapping + * stuff from them, those changes appear in the kernel page table and we + * go boom. + * + * From setup_real_mode(): + * + * ... + * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd; + * + * In this particular case, our allocation is in PGD 0 of the EFI page + * table but we've copied that PGD from PGD[272] of the EFI page table: + * + * pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272 + * + * where the direct memory mapping in kernel space is. + * + * new_memmap's VA comes from that direct mapping and thus clearing it, + * it would get cleared in the kernel page table too. + * + * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift); + */ + if (!efi_setup) + free_pages((unsigned long)new_memmap, pg_shift); /* clean DUMMY object */ efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 0b74cdf7f816..9ee3491e31fb 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -40,7 +40,12 @@ static unsigned long efi_rt_eflags; void efi_sync_low_kernel_mappings(void) {} -void efi_setup_page_tables(void) {} +void __init efi_dump_pagetable(void) {} +int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) +{ + return 0; +} +void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {} void __init efi_map_region(efi_memory_desc_t *md) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 0c2a234fef1e..666b74a09092 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -137,12 +137,38 @@ void efi_sync_low_kernel_mappings(void) sizeof(pgd_t) * num_pgds); } -void efi_setup_page_tables(void) +int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { + pgd_t *pgd; + + if (efi_enabled(EFI_OLD_MEMMAP)) + return 0; + efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd; + pgd = __va(efi_scratch.efi_pgt); - if (!efi_enabled(EFI_OLD_MEMMAP)) - efi_scratch.use_pgd = true; + /* + * It can happen that the physical address of new_memmap lands in memory + * which is not mapped in the EFI page table. Therefore we need to go + * and ident-map those pages containing the map before calling + * phys_efi_set_virtual_address_map(). + */ + if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) { + pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap); + return 1; + } + + efi_scratch.use_pgd = true; + + + return 0; +} + +void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) +{ + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); + + kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages); } static void __init __map_region(efi_memory_desc_t *md, u64 va) diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index a12bddc7ccea..7f517ca19d32 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -212,10 +212,10 @@ 203 common sched_setaffinity sys_sched_setaffinity 204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 common io_setup sys_io_setup +206 64 io_setup sys_io_setup 207 common io_destroy sys_io_destroy 208 common io_getevents sys_io_getevents -209 common io_submit sys_io_submit +209 64 io_submit sys_io_submit 210 common io_cancel sys_io_cancel 211 64 get_thread_area 212 common lookup_dcookie sys_lookup_dcookie @@ -358,3 +358,5 @@ 540 x32 process_vm_writev compat_sys_process_vm_writev 541 x32 setsockopt compat_sys_setsockopt 542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index c98583588580..5b406fc45674 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -134,6 +134,7 @@ static int __init xlated_setup_gnttab_pages(void) { struct page **pages; xen_pfn_t *pfns; + void *vaddr; int rc; unsigned int i; unsigned long nr_grant_frames = gnttab_max_grant_frames(); @@ -159,21 +160,20 @@ static int __init xlated_setup_gnttab_pages(void) for (i = 0; i < nr_grant_frames; i++) pfns[i] = page_to_pfn(pages[i]); - rc = arch_gnttab_map_shared(pfns, nr_grant_frames, nr_grant_frames, - &xen_auto_xlat_grant_frames.vaddr); - - if (rc) { + vaddr = vmap(pages, nr_grant_frames, 0, PAGE_KERNEL); + if (!vaddr) { pr_warn("%s Couldn't map %ld pfns rc:%d\n", __func__, nr_grant_frames, rc); free_xenballooned_pages(nr_grant_frames, pages); kfree(pages); kfree(pfns); - return rc; + return -ENOMEM; } kfree(pages); xen_auto_xlat_grant_frames.pfn = pfns; xen_auto_xlat_grant_frames.count = nr_grant_frames; + xen_auto_xlat_grant_frames.vaddr = vaddr; return 0; } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2423ef04ffea..c83da6fb2dee 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, * * We can construct this by grafting the Xen provided pagetable into * head_64.S's preconstructed pagetables. We copy the Xen L2's into - * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This - * means that only the kernel has a physical mapping to start with - - * but that's enough to get __va working. We need to fill in the rest - * of the physical mapping once some sort of allocator has been set - * up. - * NOTE: for PVH, the page tables are native. + * level2_ident_pgt, and level2_kernel_pgt. This means that only the + * kernel has a physical mapping to start with - but that's enough to + * get __va working. We need to fill in the rest of the physical + * mapping once some sort of allocator has been set up. NOTE: for + * PVH, the page tables are native. */ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { @@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_i[0] -> level2_ident_pgt */ convert_pfn_mfn(level3_ident_pgt); /* L3_k[510] -> level2_kernel_pgt - * L3_i[511] -> level2_fixmap_pgt */ + * L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); + + /* L3_k[511][506] -> level1_fixmap_pgt */ + convert_pfn_mfn(level2_fixmap_pgt); } /* We get [511][511] and have Xen's version of level2_kernel_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); @@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][511] have entries that point to the same + * Both L4[272][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you * are OK - which is what cleanup_highmap does) */ copy_page(level2_ident_pgt, l2); - /* Graft it onto L4[511][511] */ + /* Graft it onto L4[511][510] */ copy_page(level2_kernel_pgt, l2); - /* Get [511][510] and graft that in level2_fixmap_pgt */ - l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); - copy_page(level2_fixmap_pgt, l2); - /* Note that we don't do anything with level1_fixmap_pgt which - * we don't need. */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { /* Make pagetable pieces RO */ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); @@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); + set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 0982233b9b84..a6a72ce8630f 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -574,13 +574,7 @@ void xen_enable_syscall(void) } #endif /* CONFIG_X86_64 */ } -void xen_enable_nmi(void) -{ -#ifdef CONFIG_X86_64 - if (register_callback(CALLBACKTYPE_nmi, (char *)nmi)) - BUG(); -#endif -} + void __init xen_pvmmu_arch_setup(void) { HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); @@ -595,7 +589,6 @@ void __init xen_pvmmu_arch_setup(void) xen_enable_sysenter(); xen_enable_syscall(); - xen_enable_nmi(); } /* This function is not called for HVM domains */ diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 581521c843a5..c570feab9fa2 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -274,7 +274,7 @@ void __init xen_init_spinlocks(void) printk(KERN_DEBUG "xen: PV spinlocks disabled\n"); return; } - + printk(KERN_DEBUG "xen: PV spinlocks enabled\n"); pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; } @@ -290,6 +290,9 @@ static __init int xen_init_spinlocks_jump(void) if (!xen_pvspin) return 0; + if (!xen_domain()) + return 0; + static_key_slow_inc(¶virt_ticketlocks_enabled); return 0; } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 7b78f88c1707..5718b0b58b60 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -444,7 +444,7 @@ void xen_setup_timer(int cpu) irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER| - IRQF_FORCE_RESUME, + IRQF_FORCE_RESUME|IRQF_EARLY_RESUME, name, NULL); (void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX); diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 216446295ada..51230ba97bef 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -67,7 +67,12 @@ #define VMALLOC_START 0xC0000000 #define VMALLOC_END 0xC7FEFFFF #define TLBTEMP_BASE_1 0xC7FF0000 -#define TLBTEMP_BASE_2 0xC7FF8000 +#define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) +#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE +#define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) +#else +#define TLBTEMP_SIZE ICACHE_WAY_SIZE +#endif /* * For the Xtensa architecture, the PTE layout is as follows: diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index fd686dc45d1a..c7211e7e182d 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -52,7 +52,12 @@ */ .macro get_fs ad, sp GET_CURRENT(\ad,\sp) +#if THREAD_CURRENT_DS > 1020 + addi \ad, \ad, TASK_THREAD + l32i \ad, \ad, THREAD_CURRENT_DS - TASK_THREAD +#else l32i \ad, \ad, THREAD_CURRENT_DS +#endif .endm /* diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h index b4cb1100c0fb..a47909f0c34b 100644 --- a/arch/xtensa/include/uapi/asm/ioctls.h +++ b/arch/xtensa/include/uapi/asm/ioctls.h @@ -28,17 +28,17 @@ #define TCSETSW 0x5403 #define TCSETSF 0x5404 -#define TCGETA _IOR('t', 23, struct termio) -#define TCSETA _IOW('t', 24, struct termio) -#define TCSETAW _IOW('t', 25, struct termio) -#define TCSETAF _IOW('t', 28, struct termio) +#define TCGETA 0x80127417 /* _IOR('t', 23, struct termio) */ +#define TCSETA 0x40127418 /* _IOW('t', 24, struct termio) */ +#define TCSETAW 0x40127419 /* _IOW('t', 25, struct termio) */ +#define TCSETAF 0x4012741C /* _IOW('t', 28, struct termio) */ #define TCSBRK _IO('t', 29) #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) -#define TIOCSWINSZ _IOW('t', 103, struct winsize) -#define TIOCGWINSZ _IOR('t', 104, struct winsize) +#define TIOCSWINSZ 0x40087467 /* _IOW('t', 103, struct winsize) */ +#define TIOCGWINSZ 0x80087468 /* _IOR('t', 104, struct winsize) */ #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ #define TIOCSTOP _IO('t', 111) /* stop output, like ^S */ #define TIOCOUTQ _IOR('t', 115, int) /* output queue size */ @@ -88,7 +88,6 @@ #define TIOCSETD _IOW('T', 35, int) #define TIOCGETD _IOR('T', 36, int) #define TCSBRKP _IOW('T', 37, int) /* Needed for POSIX tcsendbreak()*/ -#define TIOCTTYGSTRUCT _IOR('T', 38, struct tty_struct) /* For debugging only*/ #define TIOCSBRK _IO('T', 39) /* BSD compatibility */ #define TIOCCBRK _IO('T', 40) /* BSD compatibility */ #define TIOCGSID _IOR('T', 41, pid_t) /* Return the session ID of FD*/ @@ -114,8 +113,10 @@ #define TIOCSERGETLSR _IOR('T', 89, unsigned int) /* Get line status reg. */ /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */ # define TIOCSER_TEMT 0x01 /* Transmitter physically empty */ -#define TIOCSERGETMULTI _IOR('T', 90, struct serial_multiport_struct) /* Get multiport config */ -#define TIOCSERSETMULTI _IOW('T', 91, struct serial_multiport_struct) /* Set multiport config */ +#define TIOCSERGETMULTI 0x80a8545a /* Get multiport config */ + /* _IOR('T', 90, struct serial_multiport_struct) */ +#define TIOCSERSETMULTI 0x40a8545b /* Set multiport config */ + /* _IOW('T', 91, struct serial_multiport_struct) */ #define TIOCMIWAIT _IO('T', 92) /* wait for a change on serial input line(s) */ #define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */ diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index ef7f4990722b..a06b7efaae82 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1001,9 +1001,8 @@ ENTRY(fast_syscall_xtensa) movi a7, 4 # sizeof(unsigned int) access_ok a3, a7, a0, a2, .Leac # a0: scratch reg, a2: sp - addi a6, a6, -1 # assuming SYS_XTENSA_ATOMIC_SET = 1 - _bgeui a6, SYS_XTENSA_COUNT - 1, .Lill - _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP - 1, .Lnswp + _bgeui a6, SYS_XTENSA_COUNT, .Lill + _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP, .Lnswp /* Fall through for ATOMIC_CMP_SWP. */ @@ -1015,27 +1014,26 @@ TRY s32i a5, a3, 0 # different, modify value l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, 1 # and return 1 - addi a6, a6, 1 # restore a6 (really necessary?) rfe 1: l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, 0 # return 0 (note that we cannot set - addi a6, a6, 1 # restore a6 (really necessary?) rfe .Lnswp: /* Atomic set, add, and exg_add. */ TRY l32i a7, a3, 0 # orig + addi a6, a6, -SYS_XTENSA_ATOMIC_SET add a0, a4, a7 # + arg moveqz a0, a4, a6 # set + addi a6, a6, SYS_XTENSA_ATOMIC_SET TRY s32i a0, a3, 0 # write new value mov a0, a2 mov a2, a7 l32i a7, a0, PT_AREG7 # restore a7 l32i a0, a0, PT_AREG0 # restore a0 - addi a6, a6, 1 # restore a6 (really necessary?) rfe CATCH @@ -1044,7 +1042,7 @@ CATCH movi a2, -EFAULT rfe -.Lill: l32i a7, a2, PT_AREG0 # restore a7 +.Lill: l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, -EINVAL rfe @@ -1565,7 +1563,7 @@ ENTRY(fast_second_level_miss) rsr a0, excvaddr bltu a0, a3, 2f - addi a1, a0, -(2 << (DCACHE_ALIAS_ORDER + PAGE_SHIFT)) + addi a1, a0, -TLBTEMP_SIZE bgeu a1, a3, 2f /* Check if we have to restore an ITLB mapping. */ @@ -1820,7 +1818,6 @@ ENTRY(_switch_to) entry a1, 16 - mov a10, a2 # preserve 'prev' (a2) mov a11, a3 # and 'next' (a3) l32i a4, a2, TASK_THREAD_INFO @@ -1828,8 +1825,14 @@ ENTRY(_switch_to) save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER - s32i a0, a10, THREAD_RA # save return address - s32i a1, a10, THREAD_SP # save stack pointer +#if THREAD_RA > 1020 || THREAD_SP > 1020 + addi a10, a2, TASK_THREAD + s32i a0, a10, THREAD_RA - TASK_THREAD # save return address + s32i a1, a10, THREAD_SP - TASK_THREAD # save stack pointer +#else + s32i a0, a2, THREAD_RA # save return address + s32i a1, a2, THREAD_SP # save stack pointer +#endif /* Disable ints while we manipulate the stack pointer. */ @@ -1870,7 +1873,6 @@ ENTRY(_switch_to) load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER wsr a14, ps - mov a2, a10 # return 'prev' rsync retw diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 2d9cc6dbfd78..e8b76b8e4b29 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -49,9 +49,8 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag) /* We currently don't support coherent memory outside KSEG */ - if (ret < XCHAL_KSEG_CACHED_VADDR - || ret >= XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE) - BUG(); + BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR || + ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); if (ret != 0) { @@ -68,10 +67,11 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle) { - long addr=(long)vaddr+XCHAL_KSEG_CACHED_VADDR-XCHAL_KSEG_BYPASS_VADDR; + unsigned long addr = (unsigned long)vaddr + + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; - if (addr < 0 || addr >= XCHAL_KSEG_SIZE) - BUG(); + BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR || + addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); free_pages(addr, get_order(size)); } diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S index f9e1ec346e35..8453e6e39895 100644 --- a/arch/xtensa/kernel/vectors.S +++ b/arch/xtensa/kernel/vectors.S @@ -376,38 +376,42 @@ _DoubleExceptionVector_WindowOverflow: beqz a2, 1f # if at start of vector, don't restore addi a0, a0, -128 - bbsi a0, 8, 1f # don't restore except for overflow 8 and 12 - bbsi a0, 7, 2f + bbsi.l a0, 8, 1f # don't restore except for overflow 8 and 12 + + /* + * This fixup handler is for the extremely unlikely case where the + * overflow handler's reference thru a0 gets a hardware TLB refill + * that bumps out the (distinct, aliasing) TLB entry that mapped its + * prior references thru a9/a13, and where our reference now thru + * a9/a13 gets a 2nd-level miss exception (not hardware TLB refill). + */ + movi a2, window_overflow_restore_a0_fixup + s32i a2, a3, EXC_TABLE_FIXUP + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + + bbsi.l a0, 7, 2f /* * Restore a0 as saved by _WindowOverflow8(). - * - * FIXME: we really need a fixup handler for this L32E, - * for the extremely unlikely case where the overflow handler's - * reference thru a0 gets a hardware TLB refill that bumps out - * the (distinct, aliasing) TLB entry that mapped its prior - * references thru a9, and where our reference now thru a9 - * gets a 2nd-level miss exception (not hardware TLB refill). */ - l32e a2, a9, -16 - wsr a2, depc # replace the saved a0 - j 1f + l32e a0, a9, -16 + wsr a0, depc # replace the saved a0 + j 3f 2: /* * Restore a0 as saved by _WindowOverflow12(). - * - * FIXME: we really need a fixup handler for this L32E, - * for the extremely unlikely case where the overflow handler's - * reference thru a0 gets a hardware TLB refill that bumps out - * the (distinct, aliasing) TLB entry that mapped its prior - * references thru a13, and where our reference now thru a13 - * gets a 2nd-level miss exception (not hardware TLB refill). */ - l32e a2, a13, -16 - wsr a2, depc # replace the saved a0 + l32e a0, a13, -16 + wsr a0, depc # replace the saved a0 +3: + xsr a3, excsave1 + movi a0, 0 + s32i a0, a3, EXC_TABLE_FIXUP + s32i a2, a3, EXC_TABLE_DOUBLE_SAVE 1: /* * Restore WindowBase while leaving all address registers restored. @@ -449,6 +453,7 @@ _DoubleExceptionVector_WindowOverflow: s32i a0, a2, PT_DEPC +_DoubleExceptionVector_handle_exception: addx4 a0, a0, a3 l32i a0, a0, EXC_TABLE_FAST_USER xsr a3, excsave1 @@ -464,11 +469,120 @@ _DoubleExceptionVector_WindowOverflow: rotw -3 j 1b - .end literal_prefix ENDPROC(_DoubleExceptionVector) /* + * Fixup handler for TLB miss in double exception handler for window owerflow. + * We get here with windowbase set to the window that was being spilled and + * a0 trashed. a0 bit 7 determines if this is a call8 (bit clear) or call12 + * (bit set) window. + * + * We do the following here: + * - go to the original window retaining a0 value; + * - set up exception stack to return back to appropriate a0 restore code + * (we'll need to rotate window back and there's no place to save this + * information, use different return address for that); + * - handle the exception; + * - go to the window that was being spilled; + * - set up window_overflow_restore_a0_fixup as a fixup routine; + * - reload a0; + * - restore the original window; + * - reset the default fixup routine; + * - return to user. By the time we get to this fixup handler all information + * about the conditions of the original double exception that happened in + * the window overflow handler is lost, so we just return to userspace to + * retry overflow from start. + * + * a0: value of depc, original value in depc + * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE + * a3: exctable, original value in excsave1 + */ + +ENTRY(window_overflow_restore_a0_fixup) + + rsr a0, ps + extui a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH + rsr a2, windowbase + sub a0, a2, a0 + extui a0, a0, 0, 3 + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + + _beqi a0, 1, .Lhandle_1 + _beqi a0, 3, .Lhandle_3 + + .macro overflow_fixup_handle_exception_pane n + + rsr a0, depc + rotw -\n + + xsr a3, excsave1 + wsr a2, depc + l32i a2, a3, EXC_TABLE_KSTK + s32i a0, a2, PT_AREG0 + + movi a0, .Lrestore_\n + s32i a0, a2, PT_DEPC + rsr a0, exccause + j _DoubleExceptionVector_handle_exception + + .endm + + overflow_fixup_handle_exception_pane 2 +.Lhandle_1: + overflow_fixup_handle_exception_pane 1 +.Lhandle_3: + overflow_fixup_handle_exception_pane 3 + + .macro overflow_fixup_restore_a0_pane n + + rotw \n + /* Need to preserve a0 value here to be able to handle exception + * that may occur on a0 reload from stack. It may occur because + * TLB miss handler may not be atomic and pointer to page table + * may be lost before we get here. There are no free registers, + * so we need to use EXC_TABLE_DOUBLE_SAVE area. + */ + xsr a3, excsave1 + s32i a2, a3, EXC_TABLE_DOUBLE_SAVE + movi a2, window_overflow_restore_a0_fixup + s32i a2, a3, EXC_TABLE_FIXUP + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + bbsi.l a0, 7, 1f + l32e a0, a9, -16 + j 2f +1: + l32e a0, a13, -16 +2: + rotw -\n + + .endm + +.Lrestore_2: + overflow_fixup_restore_a0_pane 2 + +.Lset_default_fixup: + xsr a3, excsave1 + s32i a2, a3, EXC_TABLE_DOUBLE_SAVE + movi a2, 0 + s32i a2, a3, EXC_TABLE_FIXUP + l32i a2, a3, EXC_TABLE_DOUBLE_SAVE + xsr a3, excsave1 + rfe + +.Lrestore_1: + overflow_fixup_restore_a0_pane 1 + j .Lset_default_fixup +.Lrestore_3: + overflow_fixup_restore_a0_pane 3 + j .Lset_default_fixup + +ENDPROC(window_overflow_restore_a0_fixup) + + .end literal_prefix +/* * Debug interrupt vector * * There is not much space here, so simply jump to another handler. diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index ee32c0085dff..d16db6df86f8 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -269,13 +269,13 @@ SECTIONS .UserExceptionVector.literal) SECTION_VECTOR (_DoubleExceptionVector_literal, .DoubleExceptionVector.literal, - DOUBLEEXC_VECTOR_VADDR - 16, + DOUBLEEXC_VECTOR_VADDR - 40, SIZEOF(.UserExceptionVector.text), .UserExceptionVector.text) SECTION_VECTOR (_DoubleExceptionVector_text, .DoubleExceptionVector.text, DOUBLEEXC_VECTOR_VADDR, - 32, + 40, .DoubleExceptionVector.literal) . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4e491d9b5292..d8f80e733cf8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -80,7 +80,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, blkg->q = q; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; - blkg->refcnt = 1; + atomic_set(&blkg->refcnt, 1); /* root blkg uses @q->root_rl, init rl only for !root blkgs */ if (blkcg != &blkcg_root) { @@ -399,11 +399,8 @@ void __blkg_release_rcu(struct rcu_head *rcu_head) /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); - if (blkg->parent) { - spin_lock_irq(blkg->q->queue_lock); + if (blkg->parent) blkg_put(blkg->parent); - spin_unlock_irq(blkg->q->queue_lock); - } blkg_free(blkg); } @@ -862,6 +859,13 @@ void blkcg_drain_queue(struct request_queue *q) { lockdep_assert_held(q->queue_lock); + /* + * @q could be exiting and already have destroyed all blkgs as + * indicated by NULL root_blkg. If so, don't confuse policies. + */ + if (!q->root_blkg) + return; + blk_throtl_drain(q); } diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 86154eab9523..c135f5660702 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -18,6 +18,7 @@ #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> +#include <linux/atomic.h> /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX @@ -104,7 +105,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - int refcnt; + atomic_t refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -253,13 +254,12 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) * blkg_get - get a blkg reference * @blkg: blkg to get * - * The caller should be holding queue_lock and an existing reference. + * The caller should be holding an existing reference. */ static inline void blkg_get(struct blkcg_gq *blkg) { - lockdep_assert_held(blkg->q->queue_lock); - WARN_ON_ONCE(!blkg->refcnt); - blkg->refcnt++; + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); } void __blkg_release_rcu(struct rcu_head *rcu); @@ -267,14 +267,11 @@ void __blkg_release_rcu(struct rcu_head *rcu); /** * blkg_put - put a blkg reference * @blkg: blkg to put - * - * The caller should be holding queue_lock. */ static inline void blkg_put(struct blkcg_gq *blkg) { - lockdep_assert_held(blkg->q->queue_lock); - WARN_ON_ONCE(blkg->refcnt <= 0); - if (!--blkg->refcnt) + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) call_rcu(&blkg->rcu_head, __blkg_release_rcu); } diff --git a/block/blk-core.c b/block/blk-core.c index bfe16d5af9f9..e45b321cf6a0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2353,7 +2353,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) if (!req->bio) return false; - trace_block_rq_complete(req->q, req); + trace_block_rq_complete(req->q, req, nr_bytes); /* * For fs requests, rq is just carrier of independent bio's diff --git a/block/blk-settings.c b/block/blk-settings.c index 5d21239bc859..95138e9d0ad5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -553,7 +553,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, bottom = max(b->physical_block_size, b->io_min) + alignment; /* Verify that top and bottom intervals line up */ - if (max(top, bottom) & (min(top, bottom) - 1)) { + if (max(top, bottom) % min(top, bottom)) { t->misaligned = 1; ret = -1; } @@ -598,7 +598,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, /* Find lowest common alignment_offset */ t->alignment_offset = lcm(t->alignment_offset, alignment) - & (max(t->physical_block_size, t->io_min) - 1); + % max(t->physical_block_size, t->io_min); /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) { diff --git a/block/blk-tag.c b/block/blk-tag.c index 3f33d8672268..a185b86741e5 100644 --- a/block/blk-tag.c +++ b/block/blk-tag.c @@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag) EXPORT_SYMBOL(blk_queue_find_tag); /** - * __blk_free_tags - release a given set of tag maintenance info + * blk_free_tags - release a given set of tag maintenance info * @bqt: the tag map to free * - * Tries to free the specified @bqt. Returns true if it was - * actually freed and false if there are still references using it + * Drop the reference count on @bqt and frees it when the last reference + * is dropped. */ -static int __blk_free_tags(struct blk_queue_tag *bqt) +void blk_free_tags(struct blk_queue_tag *bqt) { - int retval; - - retval = atomic_dec_and_test(&bqt->refcnt); - if (retval) { + if (atomic_dec_and_test(&bqt->refcnt)) { BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) < bqt->max_depth); @@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt) kfree(bqt); } - - return retval; } +EXPORT_SYMBOL(blk_free_tags); /** * __blk_queue_free_tags - release tag maintenance info @@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q) if (!bqt) return; - __blk_free_tags(bqt); + blk_free_tags(bqt); q->queue_tags = NULL; queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q); } /** - * blk_free_tags - release a given set of tag maintenance info - * @bqt: the tag map to free - * - * For externally managed @bqt frees the map. Callers of this - * function must guarantee to have released all the queues that - * might have been using this tag map. - */ -void blk_free_tags(struct blk_queue_tag *bqt) -{ - if (unlikely(!__blk_free_tags(bqt))) - BUG(); -} -EXPORT_SYMBOL(blk_free_tags); - -/** * blk_queue_free_tags - release tag maintenance info * @q: the request queue for the device * diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 744833b630c6..91c25f261c91 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1275,12 +1275,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) static void cfq_update_group_weight(struct cfq_group *cfqg) { - BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); - if (cfqg->new_weight) { cfqg->weight = cfqg->new_weight; cfqg->new_weight = 0; } +} + +static void +cfq_update_group_leaf_weight(struct cfq_group *cfqg) +{ + BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); if (cfqg->new_leaf_weight) { cfqg->leaf_weight = cfqg->new_leaf_weight; @@ -1299,7 +1303,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) /* add to the service tree */ BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); - cfq_update_group_weight(cfqg); + cfq_update_group_leaf_weight(cfqg); __cfq_group_service_tree_add(st, cfqg); /* @@ -1323,6 +1327,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) */ while ((parent = cfqg_parent(pos))) { if (propagate) { + cfq_update_group_weight(pos); propagate = !parent->nr_active++; parent->children_weight += pos->weight; } diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index fbd5a67cb773..a0926a6094b2 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -690,6 +690,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKROSET: case BLKDISCARD: case BLKSECDISCARD: + case BLKZEROOUT: /* * the ones below are implemented in blkdev_locked_ioctl, * but we call blkdev_ioctl, which gets the lock for us diff --git a/block/genhd.c b/block/genhd.c index 791f41943132..e6723bd4d7a1 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -28,10 +28,10 @@ struct kobject *block_depr; /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) -/* For extended devt allocation. ext_devt_mutex prevents look up +/* For extended devt allocation. ext_devt_lock prevents look up * results from going away underneath its user. */ -static DEFINE_MUTEX(ext_devt_mutex); +static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); static struct device_type disk_type; @@ -420,9 +420,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) } /* allocate ext devt */ - mutex_lock(&ext_devt_mutex); - idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL); - mutex_unlock(&ext_devt_mutex); + idr_preload(GFP_KERNEL); + + spin_lock(&ext_devt_lock); + idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT); + spin_unlock(&ext_devt_lock); + + idr_preload_end(); if (idx < 0) return idx == -ENOSPC ? -EBUSY : idx; @@ -441,15 +445,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) */ void blk_free_devt(dev_t devt) { - might_sleep(); - if (devt == MKDEV(0, 0)) return; if (MAJOR(devt) == BLOCK_EXT_MAJOR) { - mutex_lock(&ext_devt_mutex); + spin_lock(&ext_devt_lock); idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); - mutex_unlock(&ext_devt_mutex); + spin_unlock(&ext_devt_lock); } } @@ -665,7 +667,6 @@ void del_gendisk(struct gendisk *disk) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); - blk_free_devt(disk_to_dev(disk)->devt); } EXPORT_SYMBOL(del_gendisk); @@ -690,13 +691,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno) } else { struct hd_struct *part; - mutex_lock(&ext_devt_mutex); + spin_lock(&ext_devt_lock); part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); if (part && get_disk(part_to_disk(part))) { *partno = part->partno; disk = part_to_disk(part); } - mutex_unlock(&ext_devt_mutex); + spin_unlock(&ext_devt_lock); } return disk; @@ -1098,6 +1099,7 @@ static void disk_release(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); + blk_free_devt(dev->devt); disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL); diff --git a/block/partition-generic.c b/block/partition-generic.c index 789cdea05893..0d9e5f97f0a8 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -211,6 +211,7 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { struct hd_struct *p = dev_to_part(dev); + blk_free_devt(dev->devt); free_part_stats(p); free_part_info(p); kfree(p); @@ -253,7 +254,6 @@ void delete_partition(struct gendisk *disk, int partno) rcu_assign_pointer(ptbl->last_lookup, NULL); kobject_put(part->holder_dir); device_del(part_to_dev(part)); - blk_free_devt(part_devt(part)); hd_struct_put(part); } diff --git a/block/partitions/aix.c b/block/partitions/aix.c index 43be471d9b1d..0931f5136ab2 100644 --- a/block/partitions/aix.c +++ b/block/partitions/aix.c @@ -253,7 +253,7 @@ int aix_partition(struct parsed_partitions *state) continue; } lv_ix = be16_to_cpu(p->lv_ix) - 1; - if (lv_ix > state->limit) { + if (lv_ix >= state->limit) { cur_lv_ix = -1; continue; } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 26487972ac54..4044cf789c7a 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -489,7 +489,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) { err = DRIVER_ERROR << 24; - goto out; + goto error; } memset(sense, 0, sizeof(sense)); @@ -499,7 +499,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, blk_execute_rq(q, disk, rq, 0); -out: err = rq->errors & 0xff; /* only 8 bit SCSI status */ if (err) { if (rq->sense_len && rq->sense) { diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 966f893711b3..6a3ad8011585 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/net.h> #include <linux/rwsem.h> +#include <linux/security.h> struct alg_type_list { const struct af_alg_type *type; @@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) sock_init_data(newsock, sk2); sock_graft(sk2, newsock); + security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); if (err) { diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index a19c027b29bd..83187f497c7c 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -49,7 +49,7 @@ struct skcipher_ctx { struct ablkcipher_request req; }; -#define MAX_SGL_ENTS ((PAGE_SIZE - sizeof(struct skcipher_sg_list)) / \ +#define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) static inline int skcipher_sndbuf(struct sock *sk) diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 3c562f5a60bb..e1bce26cd4f9 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -78,8 +78,6 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap, tx = dma->device_prep_dma_xor(chan, dma_dest, src_list, xor_src_cnt, unmap->len, dma_flags); - src_list[0] = tmp; - if (unlikely(!tx)) async_tx_quiesce(&submit->depend_tx); @@ -92,6 +90,7 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap, xor_src_cnt, unmap->len, dma_flags); } + src_list[0] = tmp; dma_set_unmap(tx, unmap); async_tx_submit(chan, tx, submit); diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 1512e41cd93d..43665d0d0905 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -466,7 +466,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) type -= CRYPTO_MSG_BASE; link = &crypto_dispatch[type]; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) && diff --git a/crypto/crypto_wq.c b/crypto/crypto_wq.c index adad92a44ba2..2f1b8d12952a 100644 --- a/crypto/crypto_wq.c +++ b/crypto/crypto_wq.c @@ -33,7 +33,7 @@ static void __exit crypto_wq_exit(void) destroy_workqueue(kcrypto_wq); } -module_init(crypto_wq_init); +subsys_initcall(crypto_wq_init); module_exit(crypto_wq_exit); MODULE_LICENSE("GPL"); diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 4770de5707b9..561bf25ac9f9 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -56,6 +56,23 @@ config ACPI_PROCFS Say N to delete /proc/acpi/ files that have moved to /sys/ +config ACPI_PROCFS_POWER + bool "Deprecated power /proc/acpi directories" + depends on PROC_FS + help + For backwards compatibility, this option allows + deprecated power /proc/acpi/ directories to exist, even when + they have been replaced by functions in /sys. + The deprecated directories (and their replacements) include: + /proc/acpi/battery/* (/sys/class/power_supply/*) + /proc/acpi/ac_adapter/* (sys/class/power_supply/*) + This option has no effect on /proc/acpi/ directories + and functions, which do not yet exist in /sys + This option, together with the proc directories, will be + deleted in 2.6.39. + + Say N to delete power /proc/acpi/ directories that have moved to /sys/ + config ACPI_EC_DEBUGFS tristate "EC read/write access through /sys/kernel/debug/ec" default n diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 0331f91d56e6..bce34afadcd0 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -47,6 +47,7 @@ acpi-y += sysfs.o acpi-$(CONFIG_X86) += acpi_cmos_rtc.o acpi-$(CONFIG_DEBUG_FS) += debugfs.o acpi-$(CONFIG_ACPI_NUMA) += numa.o +acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o ifdef CONFIG_ACPI_VIDEO acpi-y += video_detect.o endif diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index 6f190bc2b8b7..0bebc6905383 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -30,6 +30,10 @@ #include <linux/types.h> #include <linux/dmi.h> #include <linux/delay.h> +#ifdef CONFIG_ACPI_PROCFS_POWER +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#endif #include <linux/platform_device.h> #include <linux/power_supply.h> #include <linux/acpi.h> @@ -51,26 +55,74 @@ MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_DESCRIPTION("ACPI AC Adapter Driver"); MODULE_LICENSE("GPL"); + +static int acpi_ac_add(struct acpi_device *device); +static int acpi_ac_remove(struct acpi_device *device); +static void acpi_ac_notify(struct acpi_device *device, u32 event); + +static const struct acpi_device_id ac_device_ids[] = { + {"ACPI0003", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, ac_device_ids); + +#ifdef CONFIG_PM_SLEEP +static int acpi_ac_resume(struct device *dev); +#endif +static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume); + +#ifdef CONFIG_ACPI_PROCFS_POWER +extern struct proc_dir_entry *acpi_lock_ac_dir(void); +extern void *acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir); +static int acpi_ac_open_fs(struct inode *inode, struct file *file); +#endif + + static int ac_sleep_before_get_state_ms; +static struct acpi_driver acpi_ac_driver = { + .name = "ac", + .class = ACPI_AC_CLASS, + .ids = ac_device_ids, + .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS, + .ops = { + .add = acpi_ac_add, + .remove = acpi_ac_remove, + .notify = acpi_ac_notify, + }, + .drv.pm = &acpi_ac_pm, +}; + struct acpi_ac { struct power_supply charger; - struct platform_device *pdev; + struct acpi_device * device; unsigned long long state; }; #define to_acpi_ac(x) container_of(x, struct acpi_ac, charger) +#ifdef CONFIG_ACPI_PROCFS_POWER +static const struct file_operations acpi_ac_fops = { + .owner = THIS_MODULE, + .open = acpi_ac_open_fs, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + /* -------------------------------------------------------------------------- AC Adapter Management -------------------------------------------------------------------------- */ static int acpi_ac_get_state(struct acpi_ac *ac) { - acpi_status status; - acpi_handle handle = ACPI_HANDLE(&ac->pdev->dev); + acpi_status status = AE_OK; - status = acpi_evaluate_integer(handle, "_PSR", NULL, + if (!ac) + return -EINVAL; + + status = acpi_evaluate_integer(ac->device->handle, "_PSR", NULL, &ac->state); if (ACPI_FAILURE(status)) { ACPI_EXCEPTION((AE_INFO, status, @@ -111,14 +163,90 @@ static enum power_supply_property ac_props[] = { POWER_SUPPLY_PROP_ONLINE, }; +#ifdef CONFIG_ACPI_PROCFS_POWER +/* -------------------------------------------------------------------------- + FS Interface (/proc) + -------------------------------------------------------------------------- */ + +static struct proc_dir_entry *acpi_ac_dir; + +static int acpi_ac_seq_show(struct seq_file *seq, void *offset) +{ + struct acpi_ac *ac = seq->private; + + + if (!ac) + return 0; + + if (acpi_ac_get_state(ac)) { + seq_puts(seq, "ERROR: Unable to read AC Adapter state\n"); + return 0; + } + + seq_puts(seq, "state: "); + switch (ac->state) { + case ACPI_AC_STATUS_OFFLINE: + seq_puts(seq, "off-line\n"); + break; + case ACPI_AC_STATUS_ONLINE: + seq_puts(seq, "on-line\n"); + break; + default: + seq_puts(seq, "unknown\n"); + break; + } + + return 0; +} + +static int acpi_ac_open_fs(struct inode *inode, struct file *file) +{ + return single_open(file, acpi_ac_seq_show, PDE_DATA(inode)); +} + +static int acpi_ac_add_fs(struct acpi_ac *ac) +{ + struct proc_dir_entry *entry = NULL; + + printk(KERN_WARNING PREFIX "Deprecated procfs I/F for AC is loaded," + " please retry with CONFIG_ACPI_PROCFS_POWER cleared\n"); + if (!acpi_device_dir(ac->device)) { + acpi_device_dir(ac->device) = + proc_mkdir(acpi_device_bid(ac->device), acpi_ac_dir); + if (!acpi_device_dir(ac->device)) + return -ENODEV; + } + + /* 'state' [R] */ + entry = proc_create_data(ACPI_AC_FILE_STATE, + S_IRUGO, acpi_device_dir(ac->device), + &acpi_ac_fops, ac); + if (!entry) + return -ENODEV; + return 0; +} + +static int acpi_ac_remove_fs(struct acpi_ac *ac) +{ + + if (acpi_device_dir(ac->device)) { + remove_proc_entry(ACPI_AC_FILE_STATE, + acpi_device_dir(ac->device)); + remove_proc_entry(acpi_device_bid(ac->device), acpi_ac_dir); + acpi_device_dir(ac->device) = NULL; + } + + return 0; +} +#endif + /* -------------------------------------------------------------------------- Driver Model -------------------------------------------------------------------------- */ -static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data) +static void acpi_ac_notify(struct acpi_device *device, u32 event) { - struct acpi_ac *ac = data; - struct acpi_device *adev; + struct acpi_ac *ac = acpi_driver_data(device); if (!ac) return; @@ -141,11 +269,10 @@ static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data) msleep(ac_sleep_before_get_state_ms); acpi_ac_get_state(ac); - adev = ACPI_COMPANION(&ac->pdev->dev); - acpi_bus_generate_netlink_event(adev->pnp.device_class, - dev_name(&ac->pdev->dev), - event, (u32) ac->state); - acpi_notifier_call_chain(adev, event, (u32) ac->state); + acpi_bus_generate_netlink_event(device->pnp.device_class, + dev_name(&device->dev), event, + (u32) ac->state); + acpi_notifier_call_chain(device, event, (u32) ac->state); kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE); } @@ -170,54 +297,53 @@ static struct dmi_system_id ac_dmi_table[] = { {}, }; -static int acpi_ac_probe(struct platform_device *pdev) +static int acpi_ac_add(struct acpi_device *device) { int result = 0; struct acpi_ac *ac = NULL; - struct acpi_device *adev; - if (!pdev) - return -EINVAL; - adev = ACPI_COMPANION(&pdev->dev); - if (!adev) - return -ENODEV; + if (!device) + return -EINVAL; ac = kzalloc(sizeof(struct acpi_ac), GFP_KERNEL); if (!ac) return -ENOMEM; - strcpy(acpi_device_name(adev), ACPI_AC_DEVICE_NAME); - strcpy(acpi_device_class(adev), ACPI_AC_CLASS); - ac->pdev = pdev; - platform_set_drvdata(pdev, ac); + ac->device = device; + strcpy(acpi_device_name(device), ACPI_AC_DEVICE_NAME); + strcpy(acpi_device_class(device), ACPI_AC_CLASS); + device->driver_data = ac; result = acpi_ac_get_state(ac); if (result) goto end; - ac->charger.name = acpi_device_bid(adev); + ac->charger.name = acpi_device_bid(device); +#ifdef CONFIG_ACPI_PROCFS_POWER + result = acpi_ac_add_fs(ac); + if (result) + goto end; +#endif ac->charger.type = POWER_SUPPLY_TYPE_MAINS; ac->charger.properties = ac_props; ac->charger.num_properties = ARRAY_SIZE(ac_props); ac->charger.get_property = get_ac_property; - result = power_supply_register(&pdev->dev, &ac->charger); + result = power_supply_register(&ac->device->dev, &ac->charger); if (result) goto end; - result = acpi_install_notify_handler(ACPI_HANDLE(&pdev->dev), - ACPI_ALL_NOTIFY, acpi_ac_notify_handler, ac); - if (result) { - power_supply_unregister(&ac->charger); - goto end; - } printk(KERN_INFO PREFIX "%s [%s] (%s)\n", - acpi_device_name(adev), acpi_device_bid(adev), + acpi_device_name(device), acpi_device_bid(device), ac->state ? "on-line" : "off-line"); end: - if (result) + if (result) { +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_ac_remove_fs(ac); +#endif kfree(ac); + } dmi_check_system(ac_dmi_table); return result; @@ -232,7 +358,7 @@ static int acpi_ac_resume(struct device *dev) if (!dev) return -EINVAL; - ac = platform_get_drvdata(to_platform_device(dev)); + ac = acpi_driver_data(to_acpi_device(dev)); if (!ac) return -EINVAL; @@ -246,44 +372,29 @@ static int acpi_ac_resume(struct device *dev) #else #define acpi_ac_resume NULL #endif -static SIMPLE_DEV_PM_OPS(acpi_ac_pm_ops, NULL, acpi_ac_resume); -static int acpi_ac_remove(struct platform_device *pdev) +static int acpi_ac_remove(struct acpi_device *device) { - struct acpi_ac *ac; + struct acpi_ac *ac = NULL; + - if (!pdev) + if (!device || !acpi_driver_data(device)) return -EINVAL; - acpi_remove_notify_handler(ACPI_HANDLE(&pdev->dev), - ACPI_ALL_NOTIFY, acpi_ac_notify_handler); + ac = acpi_driver_data(device); - ac = platform_get_drvdata(pdev); if (ac->charger.dev) power_supply_unregister(&ac->charger); +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_ac_remove_fs(ac); +#endif + kfree(ac); return 0; } -static const struct acpi_device_id acpi_ac_match[] = { - { "ACPI0003", 0 }, - { } -}; -MODULE_DEVICE_TABLE(acpi, acpi_ac_match); - -static struct platform_driver acpi_ac_driver = { - .probe = acpi_ac_probe, - .remove = acpi_ac_remove, - .driver = { - .name = "acpi-ac", - .owner = THIS_MODULE, - .pm = &acpi_ac_pm_ops, - .acpi_match_table = ACPI_PTR(acpi_ac_match), - }, -}; - static int __init acpi_ac_init(void) { int result; @@ -291,16 +402,30 @@ static int __init acpi_ac_init(void) if (acpi_disabled) return -ENODEV; - result = platform_driver_register(&acpi_ac_driver); - if (result < 0) +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_ac_dir = acpi_lock_ac_dir(); + if (!acpi_ac_dir) return -ENODEV; +#endif + + + result = acpi_bus_register_driver(&acpi_ac_driver); + if (result < 0) { +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_unlock_ac_dir(acpi_ac_dir); +#endif + return -ENODEV; + } return 0; } static void __exit acpi_ac_exit(void) { - platform_driver_unregister(&acpi_ac_driver); + acpi_bus_unregister_driver(&acpi_ac_driver); +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_unlock_ac_dir(acpi_ac_dir); +#endif } module_init(acpi_ac_init); module_exit(acpi_ac_exit); diff --git a/drivers/acpi/acpi_cmos_rtc.c b/drivers/acpi/acpi_cmos_rtc.c index 84190ed89c04..aff69d9bfcbf 100644 --- a/drivers/acpi/acpi_cmos_rtc.c +++ b/drivers/acpi/acpi_cmos_rtc.c @@ -35,7 +35,7 @@ acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address, void *handler_context, void *region_context) { int i; - u8 *value = (u8 *)&value64; + u8 *value = (u8 *)value64; if (address > 0xff || !value64) return AE_BAD_PARAMETER; diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index dbfe49e5fd63..1d4950388fa1 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -29,7 +29,6 @@ ACPI_MODULE_NAME("platform"); static const struct acpi_device_id acpi_platform_device_ids[] = { { "PNP0D40" }, - { "ACPI0003" }, { "VPC2004" }, { "BCM4752" }, diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index c29c2c3ec0ad..52c81c49cc7d 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -170,6 +170,9 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr) acpi_status status; int ret; + if (pr->apic_id == -1) + return -ENODEV; + status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta); if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT)) return -ENODEV; @@ -260,10 +263,8 @@ static int acpi_processor_get_info(struct acpi_device *device) } apic_id = acpi_get_apicid(pr->handle, device_declaration, pr->acpi_id); - if (apic_id < 0) { + if (apic_id < 0) acpi_handle_debug(pr->handle, "failed to get CPU APIC ID.\n"); - return -ENODEV; - } pr->apic_id = apic_id; cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id); @@ -404,7 +405,6 @@ static int acpi_processor_add(struct acpi_device *device, goto err; pr->dev = dev; - dev->offline = pr->flags.need_hotplug_init; /* Trigger the processor driver's .probe() if present. */ if (device_attach(dev) >= 0) diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 4ed1aa384df2..514f34033f96 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -132,9 +132,9 @@ u8 ACPI_INIT_GLOBAL(acpi_gbl_do_not_use_xsdt, FALSE); * address. Although ACPICA adheres to the ACPI specification which * requires the use of the corresponding 64-bit address if it is non-zero, * some machines have been found to have a corrupted non-zero 64-bit - * address. Default is FALSE, do not favor the 32-bit addresses. + * address. Default is TRUE, favor the 32-bit addresses. */ -u8 ACPI_INIT_GLOBAL(acpi_gbl_use32_bit_fadt_addresses, FALSE); +u8 ACPI_INIT_GLOBAL(acpi_gbl_use32_bit_fadt_addresses, TRUE); /* * Optionally truncate I/O addresses to 16 bits. Provides compatibility diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index d95ca5449ace..e6ab104afe42 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -254,6 +254,7 @@ struct acpi_create_field_info { u32 field_bit_position; u32 field_bit_length; u16 resource_length; + u16 pin_number_index; u8 field_flags; u8 attribute; u8 field_type; diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index cc7ab6dd724e..a47cc78ffd4f 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -263,6 +263,7 @@ struct acpi_object_region_field { ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u16 resource_length; union acpi_operand_object *region_obj; /* Containing op_region object */ u8 *resource_buffer; /* resource_template for serial regions/fields */ + u16 pin_number_index; /* Index relative to previous Connection/Template */ }; struct acpi_object_bank_field { diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index e7a57c554e84..9af55bd6c4d7 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -360,6 +360,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info, */ info->resource_buffer = NULL; info->connection_node = NULL; + info->pin_number_index = 0; /* * A Connection() is either an actual resource descriptor (buffer) @@ -437,6 +438,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info, } info->field_bit_position += info->field_bit_length; + info->pin_number_index++; /* Index relative to previous Connection() */ break; default: diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 144cbb9b73bc..cd4b231ae760 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -142,6 +142,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, union acpi_operand_object *region_obj2; void *region_context = NULL; struct acpi_connection_info *context; + acpi_physical_address address; ACPI_FUNCTION_TRACE(ev_address_space_dispatch); @@ -231,25 +232,23 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, /* We have everything we need, we can invoke the address space handler */ handler = handler_desc->address_space.handler; - - ACPI_DEBUG_PRINT((ACPI_DB_OPREGION, - "Handler %p (@%p) Address %8.8X%8.8X [%s]\n", - ®ion_obj->region.handler->address_space, handler, - ACPI_FORMAT_NATIVE_UINT(region_obj->region.address + - region_offset), - acpi_ut_get_region_name(region_obj->region. - space_id))); + address = (region_obj->region.address + region_offset); /* * Special handling for generic_serial_bus and general_purpose_io: * There are three extra parameters that must be passed to the * handler via the context: - * 1) Connection buffer, a resource template from Connection() op. - * 2) Length of the above buffer. - * 3) Actual access length from the access_as() op. + * 1) Connection buffer, a resource template from Connection() op + * 2) Length of the above buffer + * 3) Actual access length from the access_as() op + * + * In addition, for general_purpose_io, the Address and bit_width fields + * are defined as follows: + * 1) Address is the pin number index of the field (bit offset from + * the previous Connection) + * 2) bit_width is the actual bit length of the field (number of pins) */ - if (((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) || - (region_obj->region.space_id == ACPI_ADR_SPACE_GPIO)) && + if ((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) && context && field_obj) { /* Get the Connection (resource_template) buffer */ @@ -258,6 +257,24 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, context->length = field_obj->field.resource_length; context->access_length = field_obj->field.access_length; } + if ((region_obj->region.space_id == ACPI_ADR_SPACE_GPIO) && + context && field_obj) { + + /* Get the Connection (resource_template) buffer */ + + context->connection = field_obj->field.resource_buffer; + context->length = field_obj->field.resource_length; + context->access_length = field_obj->field.access_length; + address = field_obj->field.pin_number_index; + bit_width = field_obj->field.bit_length; + } + + ACPI_DEBUG_PRINT((ACPI_DB_OPREGION, + "Handler %p (@%p) Address %8.8X%8.8X [%s]\n", + ®ion_obj->region.handler->address_space, handler, + ACPI_FORMAT_NATIVE_UINT(address), + acpi_ut_get_region_name(region_obj->region. + space_id))); if (!(handler_desc->address_space.handler_flags & ACPI_ADDR_HANDLER_DEFAULT_INSTALLED)) { @@ -271,9 +288,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, /* Call the handler */ - status = handler(function, - (region_obj->region.address + region_offset), - bit_width, value, context, + status = handler(function, address, bit_width, value, context, region_obj2->extra.region_context); if (ACPI_FAILURE(status)) { diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index cfd875243421..d36894a228b1 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -178,6 +178,37 @@ acpi_ex_read_data_from_field(struct acpi_walk_state *walk_state, buffer = &buffer_desc->integer.value; } + if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) && + (obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_GPIO)) { + /* + * For GPIO (general_purpose_io), the Address will be the bit offset + * from the previous Connection() operator, making it effectively a + * pin number index. The bit_length is the length of the field, which + * is thus the number of pins. + */ + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, + "GPIO FieldRead [FROM]: Pin %u Bits %u\n", + obj_desc->field.pin_number_index, + obj_desc->field.bit_length)); + + /* Lock entire transaction if requested */ + + acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags); + + /* Perform the write */ + + status = acpi_ex_access_region(obj_desc, 0, + (u64 *)buffer, ACPI_READ); + acpi_ex_release_global_lock(obj_desc->common_field.field_flags); + if (ACPI_FAILURE(status)) { + acpi_ut_remove_reference(buffer_desc); + } else { + *ret_buffer_desc = buffer_desc; + } + return_ACPI_STATUS(status); + } + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, "FieldRead [TO]: Obj %p, Type %X, Buf %p, ByteLen %X\n", obj_desc, obj_desc->common.type, buffer, @@ -325,6 +356,42 @@ acpi_ex_write_data_to_field(union acpi_operand_object *source_desc, *result_desc = buffer_desc; return_ACPI_STATUS(status); + } else if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) && + (obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_GPIO)) { + /* + * For GPIO (general_purpose_io), we will bypass the entire field + * mechanism and handoff the bit address and bit width directly to + * the handler. The Address will be the bit offset + * from the previous Connection() operator, making it effectively a + * pin number index. The bit_length is the length of the field, which + * is thus the number of pins. + */ + if (source_desc->common.type != ACPI_TYPE_INTEGER) { + return_ACPI_STATUS(AE_AML_OPERAND_TYPE); + } + + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, + "GPIO FieldWrite [FROM]: (%s:%X), Val %.8X [TO]: Pin %u Bits %u\n", + acpi_ut_get_type_name(source_desc->common. + type), + source_desc->common.type, + (u32)source_desc->integer.value, + obj_desc->field.pin_number_index, + obj_desc->field.bit_length)); + + buffer = &source_desc->integer.value; + + /* Lock entire transaction if requested */ + + acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags); + + /* Perform the write */ + + status = acpi_ex_access_region(obj_desc, 0, + (u64 *)buffer, ACPI_WRITE); + acpi_ex_release_global_lock(obj_desc->common_field.field_flags); + return_ACPI_STATUS(status); } /* Get a pointer to the data to be written */ diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 5a588611ab48..8c88cfdec441 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -484,6 +484,8 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info) obj_desc->field.resource_length = info->resource_length; } + obj_desc->field.pin_number_index = info->pin_number_index; + /* Allow full data read from EC address space */ if ((obj_desc->field.region_obj->region.space_id == diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c index a05afff50eb9..b6f6863c07f9 100644 --- a/drivers/acpi/acpica/nsrepair.c +++ b/drivers/acpi/acpica/nsrepair.c @@ -207,13 +207,30 @@ acpi_ns_simple_repair(struct acpi_evaluate_info *info, * this predefined name. Either one return value is expected, or none, * for both methods and other objects. * - * Exit now if there is no return object. Warning if one was expected. + * Try to fix if there was no return object. Warning if failed to fix. */ if (!return_object) { if (expected_btypes && (!(expected_btypes & ACPI_RTYPE_NONE))) { - ACPI_WARN_PREDEFINED((AE_INFO, info->full_pathname, - ACPI_WARN_ALWAYS, - "Missing expected return value")); + if (package_index != ACPI_NOT_PACKAGE_ELEMENT) { + ACPI_WARN_PREDEFINED((AE_INFO, + info->full_pathname, + ACPI_WARN_ALWAYS, + "Found unexpected NULL package element")); + + status = + acpi_ns_repair_null_element(info, + expected_btypes, + package_index, + return_object_ptr); + if (ACPI_SUCCESS(status)) { + return (AE_OK); /* Repair was successful */ + } + } else { + ACPI_WARN_PREDEFINED((AE_INFO, + info->full_pathname, + ACPI_WARN_ALWAYS, + "Missing expected return value")); + } return (AE_AML_NO_RETURN_VALUE); } diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 6412d3c301cb..1bc879ec83d4 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -461,6 +461,7 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address) u32 table_count; struct acpi_table_header *table; acpi_physical_address address; + acpi_physical_address rsdt_address; u32 length; u8 *table_entry; acpi_status status; @@ -488,11 +489,14 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address) * as per the ACPI specification. */ address = (acpi_physical_address) rsdp->xsdt_physical_address; + rsdt_address = + (acpi_physical_address) rsdp->rsdt_physical_address; table_entry_size = ACPI_XSDT_ENTRY_SIZE; } else { /* Root table is an RSDT (32-bit physical addresses) */ address = (acpi_physical_address) rsdp->rsdt_physical_address; + rsdt_address = address; table_entry_size = ACPI_RSDT_ENTRY_SIZE; } @@ -515,8 +519,7 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address) /* Fall back to the RSDT */ - address = - (acpi_physical_address) rsdp->rsdt_physical_address; + address = rsdt_address; table_entry_size = ACPI_RSDT_ENTRY_SIZE; } } diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index edff4e653d9a..c66bca17e736 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -1001,5 +1001,11 @@ acpi_ut_copy_iobject_to_iobject(union acpi_operand_object *source_desc, status = acpi_ut_copy_simple_object(source_desc, *dest_desc); } + /* Delete the allocated object if copy failed */ + + if (ACPI_FAILURE(status)) { + acpi_ut_remove_reference(*dest_desc); + } + return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c index 45c0eb26b33d..cd2047af96db 100644 --- a/drivers/acpi/acpica/utstring.c +++ b/drivers/acpi/acpica/utstring.c @@ -353,7 +353,7 @@ void acpi_ut_print_string(char *string, u16 max_length) } acpi_os_printf("\""); - for (i = 0; string[i] && (i < max_length); i++) { + for (i = 0; (i < max_length) && string[i]; i++) { /* Escape sequences */ diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 797a6938d051..0f004159a317 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -34,8 +34,15 @@ #include <linux/dmi.h> #include <linux/slab.h> #include <linux/suspend.h> +#include <linux/delay.h> #include <asm/unaligned.h> +#ifdef CONFIG_ACPI_PROCFS_POWER +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <asm/uaccess.h> +#endif + #include <linux/acpi.h> #include <linux/power_supply.h> @@ -66,6 +73,19 @@ static unsigned int cache_time = 1000; module_param(cache_time, uint, 0644); MODULE_PARM_DESC(cache_time, "cache time in milliseconds"); +#ifdef CONFIG_ACPI_PROCFS_POWER +extern struct proc_dir_entry *acpi_lock_battery_dir(void); +extern void *acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir); + +enum acpi_battery_files { + info_tag = 0, + state_tag, + alarm_tag, + ACPI_BATTERY_NUMFILES, +}; + +#endif + static const struct acpi_device_id battery_device_ids[] = { {"PNP0C0A", 0}, {"", 0}, @@ -301,6 +321,14 @@ static enum power_supply_property energy_battery_props[] = { POWER_SUPPLY_PROP_SERIAL_NUMBER, }; +#ifdef CONFIG_ACPI_PROCFS_POWER +inline char *acpi_battery_units(struct acpi_battery *battery) +{ + return (battery->power_unit == ACPI_BATTERY_POWER_UNIT_MA) ? + "mA" : "mW"; +} +#endif + /* -------------------------------------------------------------------------- Battery Management -------------------------------------------------------------------------- */ @@ -719,6 +747,279 @@ static void acpi_battery_refresh(struct acpi_battery *battery) } /* -------------------------------------------------------------------------- + FS Interface (/proc) + -------------------------------------------------------------------------- */ + +#ifdef CONFIG_ACPI_PROCFS_POWER +static struct proc_dir_entry *acpi_battery_dir; + +static int acpi_battery_print_info(struct seq_file *seq, int result) +{ + struct acpi_battery *battery = seq->private; + + if (result) + goto end; + + seq_printf(seq, "present: %s\n", + acpi_battery_present(battery) ? "yes" : "no"); + if (!acpi_battery_present(battery)) + goto end; + if (battery->design_capacity == ACPI_BATTERY_VALUE_UNKNOWN) + seq_printf(seq, "design capacity: unknown\n"); + else + seq_printf(seq, "design capacity: %d %sh\n", + battery->design_capacity, + acpi_battery_units(battery)); + + if (battery->full_charge_capacity == ACPI_BATTERY_VALUE_UNKNOWN) + seq_printf(seq, "last full capacity: unknown\n"); + else + seq_printf(seq, "last full capacity: %d %sh\n", + battery->full_charge_capacity, + acpi_battery_units(battery)); + + seq_printf(seq, "battery technology: %srechargeable\n", + (!battery->technology)?"non-":""); + + if (battery->design_voltage == ACPI_BATTERY_VALUE_UNKNOWN) + seq_printf(seq, "design voltage: unknown\n"); + else + seq_printf(seq, "design voltage: %d mV\n", + battery->design_voltage); + seq_printf(seq, "design capacity warning: %d %sh\n", + battery->design_capacity_warning, + acpi_battery_units(battery)); + seq_printf(seq, "design capacity low: %d %sh\n", + battery->design_capacity_low, + acpi_battery_units(battery)); + seq_printf(seq, "cycle count: %i\n", battery->cycle_count); + seq_printf(seq, "capacity granularity 1: %d %sh\n", + battery->capacity_granularity_1, + acpi_battery_units(battery)); + seq_printf(seq, "capacity granularity 2: %d %sh\n", + battery->capacity_granularity_2, + acpi_battery_units(battery)); + seq_printf(seq, "model number: %s\n", battery->model_number); + seq_printf(seq, "serial number: %s\n", battery->serial_number); + seq_printf(seq, "battery type: %s\n", battery->type); + seq_printf(seq, "OEM info: %s\n", battery->oem_info); + end: + if (result) + seq_printf(seq, "ERROR: Unable to read battery info\n"); + return result; +} + +static int acpi_battery_print_state(struct seq_file *seq, int result) +{ + struct acpi_battery *battery = seq->private; + + if (result) + goto end; + + seq_printf(seq, "present: %s\n", + acpi_battery_present(battery) ? "yes" : "no"); + if (!acpi_battery_present(battery)) + goto end; + + seq_printf(seq, "capacity state: %s\n", + (battery->state & 0x04) ? "critical" : "ok"); + if ((battery->state & 0x01) && (battery->state & 0x02)) + seq_printf(seq, + "charging state: charging/discharging\n"); + else if (battery->state & 0x01) + seq_printf(seq, "charging state: discharging\n"); + else if (battery->state & 0x02) + seq_printf(seq, "charging state: charging\n"); + else + seq_printf(seq, "charging state: charged\n"); + + if (battery->rate_now == ACPI_BATTERY_VALUE_UNKNOWN) + seq_printf(seq, "present rate: unknown\n"); + else + seq_printf(seq, "present rate: %d %s\n", + battery->rate_now, acpi_battery_units(battery)); + + if (battery->capacity_now == ACPI_BATTERY_VALUE_UNKNOWN) + seq_printf(seq, "remaining capacity: unknown\n"); + else + seq_printf(seq, "remaining capacity: %d %sh\n", + battery->capacity_now, acpi_battery_units(battery)); + if (battery->voltage_now == ACPI_BATTERY_VALUE_UNKNOWN) + seq_printf(seq, "present voltage: unknown\n"); + else + seq_printf(seq, "present voltage: %d mV\n", + battery->voltage_now); + end: + if (result) + seq_printf(seq, "ERROR: Unable to read battery state\n"); + + return result; +} + +static int acpi_battery_print_alarm(struct seq_file *seq, int result) +{ + struct acpi_battery *battery = seq->private; + + if (result) + goto end; + + if (!acpi_battery_present(battery)) { + seq_printf(seq, "present: no\n"); + goto end; + } + seq_printf(seq, "alarm: "); + if (!battery->alarm) + seq_printf(seq, "unsupported\n"); + else + seq_printf(seq, "%u %sh\n", battery->alarm, + acpi_battery_units(battery)); + end: + if (result) + seq_printf(seq, "ERROR: Unable to read battery alarm\n"); + return result; +} + +static ssize_t acpi_battery_write_alarm(struct file *file, + const char __user * buffer, + size_t count, loff_t * ppos) +{ + int result = 0; + char alarm_string[12] = { '\0' }; + struct seq_file *m = file->private_data; + struct acpi_battery *battery = m->private; + + if (!battery || (count > sizeof(alarm_string) - 1)) + return -EINVAL; + if (!acpi_battery_present(battery)) { + result = -ENODEV; + goto end; + } + if (copy_from_user(alarm_string, buffer, count)) { + result = -EFAULT; + goto end; + } + alarm_string[count] = '\0'; + battery->alarm = simple_strtol(alarm_string, NULL, 0); + result = acpi_battery_set_alarm(battery); + end: + if (!result) + return count; + return result; +} + +typedef int(*print_func)(struct seq_file *seq, int result); + +static print_func acpi_print_funcs[ACPI_BATTERY_NUMFILES] = { + acpi_battery_print_info, + acpi_battery_print_state, + acpi_battery_print_alarm, +}; + +static int acpi_battery_read(int fid, struct seq_file *seq) +{ + struct acpi_battery *battery = seq->private; + int result = acpi_battery_update(battery); + return acpi_print_funcs[fid](seq, result); +} + +#define DECLARE_FILE_FUNCTIONS(_name) \ +static int acpi_battery_read_##_name(struct seq_file *seq, void *offset) \ +{ \ + return acpi_battery_read(_name##_tag, seq); \ +} \ +static int acpi_battery_##_name##_open_fs(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, acpi_battery_read_##_name, PDE_DATA(inode)); \ +} + +DECLARE_FILE_FUNCTIONS(info); +DECLARE_FILE_FUNCTIONS(state); +DECLARE_FILE_FUNCTIONS(alarm); + +#undef DECLARE_FILE_FUNCTIONS + +#define FILE_DESCRIPTION_RO(_name) \ + { \ + .name = __stringify(_name), \ + .mode = S_IRUGO, \ + .ops = { \ + .open = acpi_battery_##_name##_open_fs, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ + .owner = THIS_MODULE, \ + }, \ + } + +#define FILE_DESCRIPTION_RW(_name) \ + { \ + .name = __stringify(_name), \ + .mode = S_IFREG | S_IRUGO | S_IWUSR, \ + .ops = { \ + .open = acpi_battery_##_name##_open_fs, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .write = acpi_battery_write_##_name, \ + .release = single_release, \ + .owner = THIS_MODULE, \ + }, \ + } + +static const struct battery_file { + struct file_operations ops; + umode_t mode; + const char *name; +} acpi_battery_file[] = { + FILE_DESCRIPTION_RO(info), + FILE_DESCRIPTION_RO(state), + FILE_DESCRIPTION_RW(alarm), +}; + +#undef FILE_DESCRIPTION_RO +#undef FILE_DESCRIPTION_RW + +static int acpi_battery_add_fs(struct acpi_device *device) +{ + struct proc_dir_entry *entry = NULL; + int i; + + printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded," + " please retry with CONFIG_ACPI_PROCFS_POWER cleared\n"); + if (!acpi_device_dir(device)) { + acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device), + acpi_battery_dir); + if (!acpi_device_dir(device)) + return -ENODEV; + } + + for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i) { + entry = proc_create_data(acpi_battery_file[i].name, + acpi_battery_file[i].mode, + acpi_device_dir(device), + &acpi_battery_file[i].ops, + acpi_driver_data(device)); + if (!entry) + return -ENODEV; + } + return 0; +} + +static void acpi_battery_remove_fs(struct acpi_device *device) +{ + int i; + if (!acpi_device_dir(device)) + return; + for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i) + remove_proc_entry(acpi_battery_file[i].name, + acpi_device_dir(device)); + + remove_proc_entry(acpi_device_bid(device), acpi_battery_dir); + acpi_device_dir(device) = NULL; +} + +#endif + +/* -------------------------------------------------------------------------- Driver Interface -------------------------------------------------------------------------- */ @@ -770,6 +1071,28 @@ static struct dmi_system_id bat_dmi_table[] = { {}, }; +/* + * Some machines'(E,G Lenovo Z480) ECs are not stable + * during boot up and this causes battery driver fails to be + * probed due to failure of getting battery information + * from EC sometimes. After several retries, the operation + * may work. So add retry code here and 20ms sleep between + * every retries. + */ +static int acpi_battery_update_retry(struct acpi_battery *battery) +{ + int retry, ret; + + for (retry = 5; retry; retry--) { + ret = acpi_battery_update(battery); + if (!ret) + break; + + msleep(20); + } + return ret; +} + static int acpi_battery_add(struct acpi_device *device) { int result = 0; @@ -788,10 +1111,21 @@ static int acpi_battery_add(struct acpi_device *device) mutex_init(&battery->sysfs_lock); if (acpi_has_method(battery->device->handle, "_BIX")) set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags); - result = acpi_battery_update(battery); + + result = acpi_battery_update_retry(battery); if (result) goto fail; +#ifdef CONFIG_ACPI_PROCFS_POWER + result = acpi_battery_add_fs(device); +#endif + if (result) { +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_battery_remove_fs(device); +#endif + goto fail; + } + printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n", ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device), device->status.battery_present ? "present" : "absent"); @@ -817,6 +1151,9 @@ static int acpi_battery_remove(struct acpi_device *device) return -EINVAL; battery = acpi_driver_data(device); unregister_pm_notifier(&battery->pm_nb); +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_battery_remove_fs(device); +#endif sysfs_remove_battery(battery); mutex_destroy(&battery->lock); mutex_destroy(&battery->sysfs_lock); @@ -867,7 +1204,19 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie) if (dmi_check_system(bat_dmi_table)) battery_bix_broken_package = 1; - acpi_bus_register_driver(&acpi_battery_driver); + +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_battery_dir = acpi_lock_battery_dir(); + if (!acpi_battery_dir) + return; +#endif + if (acpi_bus_register_driver(&acpi_battery_driver) < 0) { +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_unlock_battery_dir(acpi_battery_dir); +#endif + return; + } + return; } static int __init acpi_battery_init(void) @@ -879,6 +1228,9 @@ static int __init acpi_battery_init(void) static void __exit acpi_battery_exit(void) { acpi_bus_unregister_driver(&acpi_battery_driver); +#ifdef CONFIG_ACPI_PROCFS_POWER + acpi_unlock_battery_dir(acpi_battery_dir); +#endif } module_init(acpi_battery_init); diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c index afec4526c48a..3d8413d02a97 100644 --- a/drivers/acpi/blacklist.c +++ b/drivers/acpi/blacklist.c @@ -314,6 +314,14 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_VERSION, "2349D15"), }, }, + { + .callback = dmi_disable_osi_win8, + .ident = "Dell Inspiron 7737", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7737"), + }, + }, /* * BIOS invocation of _OSI(Linux) is almost always a BIOS bug. @@ -374,6 +382,19 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T500"), }, }, + /* + * Without this this EEEpc exports a non working WMI interface, with + * this it exports a working "good old" eeepc_laptop interface, fixing + * both brightness control, and rfkill not working. + */ + { + .callback = dmi_enable_osi_linux, + .ident = "Asus EEE PC 1015PX", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "1015PX"), + }, + }, {} }; diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index fcb59c21c68d..b48aefab57e8 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -52,6 +52,12 @@ struct proc_dir_entry *acpi_root_dir; EXPORT_SYMBOL(acpi_root_dir); #ifdef CONFIG_X86 +#ifdef CONFIG_ACPI_CUSTOM_DSDT +static inline int set_copy_dsdt(const struct dmi_system_id *id) +{ + return 0; +} +#else static int set_copy_dsdt(const struct dmi_system_id *id) { printk(KERN_NOTICE "%s detected - " @@ -59,6 +65,7 @@ static int set_copy_dsdt(const struct dmi_system_id *id) acpi_gbl_copy_dsdt_locally = 1; return 0; } +#endif static struct dmi_system_id dsdt_dmi_table[] __initdata = { /* diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 714e957a871a..db35594d4df7 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -302,6 +302,10 @@ static void acpi_button_notify(struct acpi_device *device, u32 event) input_sync(input); pm_wakeup_event(&device->dev, 0); + acpi_bus_generate_netlink_event( + device->pnp.device_class, + dev_name(&device->dev), + event, ++button->pushed); } break; default: diff --git a/drivers/acpi/cm_sbs.c b/drivers/acpi/cm_sbs.c new file mode 100644 index 000000000000..6c9ee68e46fb --- /dev/null +++ b/drivers/acpi/cm_sbs.c @@ -0,0 +1,105 @@ +/* + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * 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; either version 2 of the License, or (at + * your option) any later version. + * + * 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. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/acpi.h> +#include <linux/types.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <acpi/acpi_bus.h> +#include <acpi/acpi_drivers.h> + +#define PREFIX "ACPI: " + +ACPI_MODULE_NAME("cm_sbs"); +#define ACPI_AC_CLASS "ac_adapter" +#define ACPI_BATTERY_CLASS "battery" +#define _COMPONENT ACPI_SBS_COMPONENT +static struct proc_dir_entry *acpi_ac_dir; +static struct proc_dir_entry *acpi_battery_dir; + +static DEFINE_MUTEX(cm_sbs_mutex); + +static int lock_ac_dir_cnt; +static int lock_battery_dir_cnt; + +struct proc_dir_entry *acpi_lock_ac_dir(void) +{ + mutex_lock(&cm_sbs_mutex); + if (!acpi_ac_dir) + acpi_ac_dir = proc_mkdir(ACPI_AC_CLASS, acpi_root_dir); + if (acpi_ac_dir) { + lock_ac_dir_cnt++; + } else { + printk(KERN_ERR PREFIX + "Cannot create %s\n", ACPI_AC_CLASS); + } + mutex_unlock(&cm_sbs_mutex); + return acpi_ac_dir; +} +EXPORT_SYMBOL(acpi_lock_ac_dir); + +void acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir_param) +{ + mutex_lock(&cm_sbs_mutex); + if (acpi_ac_dir_param) + lock_ac_dir_cnt--; + if (lock_ac_dir_cnt == 0 && acpi_ac_dir_param && acpi_ac_dir) { + remove_proc_entry(ACPI_AC_CLASS, acpi_root_dir); + acpi_ac_dir = NULL; + } + mutex_unlock(&cm_sbs_mutex); +} +EXPORT_SYMBOL(acpi_unlock_ac_dir); + +struct proc_dir_entry *acpi_lock_battery_dir(void) +{ + mutex_lock(&cm_sbs_mutex); + if (!acpi_battery_dir) { + acpi_battery_dir = + proc_mkdir(ACPI_BATTERY_CLASS, acpi_root_dir); + } + if (acpi_battery_dir) { + lock_battery_dir_cnt++; + } else { + printk(KERN_ERR PREFIX + "Cannot create %s\n", ACPI_BATTERY_CLASS); + } + mutex_unlock(&cm_sbs_mutex); + return acpi_battery_dir; +} +EXPORT_SYMBOL(acpi_lock_battery_dir); + +void acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir_param) +{ + mutex_lock(&cm_sbs_mutex); + if (acpi_battery_dir_param) + lock_battery_dir_cnt--; + if (lock_battery_dir_cnt == 0 && acpi_battery_dir_param + && acpi_battery_dir) { + remove_proc_entry(ACPI_BATTERY_CLASS, acpi_root_dir); + acpi_battery_dir = NULL; + } + mutex_unlock(&cm_sbs_mutex); + return; +} +EXPORT_SYMBOL(acpi_unlock_battery_dir); diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c index 368f9ddb8480..e4a6f78f3bbc 100644 --- a/drivers/acpi/container.c +++ b/drivers/acpi/container.c @@ -96,6 +96,13 @@ static void container_device_detach(struct acpi_device *adev) device_unregister(dev); } +static void container_device_online(struct acpi_device *adev) +{ + struct device *dev = acpi_driver_data(adev); + + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + static struct acpi_scan_handler container_handler = { .ids = container_device_ids, .attach = container_device_attach, @@ -103,6 +110,7 @@ static struct acpi_scan_handler container_handler = { .hotplug = { .enabled = true, .demand_offline = true, + .notify_online = container_device_online, }, }; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index d7d32c28829b..49d89909b4ed 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -78,6 +78,9 @@ enum { EC_FLAGS_BLOCKED, /* Transactions are blocked */ }; +#define ACPI_EC_COMMAND_POLL 0x01 /* Available for command byte */ +#define ACPI_EC_COMMAND_COMPLETE 0x02 /* Completed last byte */ + /* ec.c is compiled in acpi namespace so this shows up as acpi.ec_delay param */ static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY; module_param(ec_delay, uint, 0644); @@ -109,7 +112,7 @@ struct transaction { u8 ri; u8 wlen; u8 rlen; - bool done; + u8 flags; }; struct acpi_ec *boot_ec, *first_ec; @@ -150,69 +153,83 @@ static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data) outb(data, ec->data_addr); } -static int ec_transaction_done(struct acpi_ec *ec) +static int ec_transaction_completed(struct acpi_ec *ec) { unsigned long flags; int ret = 0; spin_lock_irqsave(&ec->lock, flags); - if (!ec->curr || ec->curr->done) + if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE)) ret = 1; spin_unlock_irqrestore(&ec->lock, flags); return ret; } -static void start_transaction(struct acpi_ec *ec) +static bool advance_transaction(struct acpi_ec *ec) { - ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0; - ec->curr->done = false; - acpi_ec_write_cmd(ec, ec->curr->command); -} - -static void advance_transaction(struct acpi_ec *ec, u8 status) -{ - unsigned long flags; struct transaction *t; + u8 status; + bool wakeup = false; - spin_lock_irqsave(&ec->lock, flags); + pr_debug("===== %s =====\n", in_interrupt() ? "IRQ" : "TASK"); + status = acpi_ec_read_status(ec); t = ec->curr; if (!t) - goto unlock; - if (t->wlen > t->wi) { - if ((status & ACPI_EC_FLAG_IBF) == 0) - acpi_ec_write_data(ec, - t->wdata[t->wi++]); - else - goto err; - } else if (t->rlen > t->ri) { - if ((status & ACPI_EC_FLAG_OBF) == 1) { - t->rdata[t->ri++] = acpi_ec_read_data(ec); - if (t->rlen == t->ri) - t->done = true; + goto err; + if (t->flags & ACPI_EC_COMMAND_POLL) { + if (t->wlen > t->wi) { + if ((status & ACPI_EC_FLAG_IBF) == 0) + acpi_ec_write_data(ec, t->wdata[t->wi++]); + else + goto err; + } else if (t->rlen > t->ri) { + if ((status & ACPI_EC_FLAG_OBF) == 1) { + t->rdata[t->ri++] = acpi_ec_read_data(ec); + if (t->rlen == t->ri) { + t->flags |= ACPI_EC_COMMAND_COMPLETE; + wakeup = true; + } + } else + goto err; + } else if (t->wlen == t->wi && + (status & ACPI_EC_FLAG_IBF) == 0) { + t->flags |= ACPI_EC_COMMAND_COMPLETE; + wakeup = true; + } + return wakeup; + } else { + if ((status & ACPI_EC_FLAG_IBF) == 0) { + acpi_ec_write_cmd(ec, t->command); + t->flags |= ACPI_EC_COMMAND_POLL; } else goto err; - } else if (t->wlen == t->wi && - (status & ACPI_EC_FLAG_IBF) == 0) - t->done = true; - goto unlock; + return wakeup; + } err: /* * If SCI bit is set, then don't think it's a false IRQ * otherwise will take a not handled IRQ as a false one. */ - if (in_interrupt() && !(status & ACPI_EC_FLAG_SCI)) - ++t->irq_count; + if (!(status & ACPI_EC_FLAG_SCI)) { + if (in_interrupt() && t) + ++t->irq_count; + } + return wakeup; +} -unlock: - spin_unlock_irqrestore(&ec->lock, flags); +static void start_transaction(struct acpi_ec *ec) +{ + ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0; + ec->curr->flags = 0; + (void)advance_transaction(ec); } -static int acpi_ec_sync_query(struct acpi_ec *ec); +static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data); static int ec_check_sci_sync(struct acpi_ec *ec, u8 state) { if (state & ACPI_EC_FLAG_SCI) { if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) - return acpi_ec_sync_query(ec); + return acpi_ec_sync_query(ec, NULL); } return 0; } @@ -228,15 +245,17 @@ static int ec_poll(struct acpi_ec *ec) /* don't sleep with disabled interrupts */ if (EC_FLAGS_MSI || irqs_disabled()) { udelay(ACPI_EC_MSI_UDELAY); - if (ec_transaction_done(ec)) + if (ec_transaction_completed(ec)) return 0; } else { if (wait_event_timeout(ec->wait, - ec_transaction_done(ec), + ec_transaction_completed(ec), msecs_to_jiffies(1))) return 0; } - advance_transaction(ec, acpi_ec_read_status(ec)); + spin_lock_irqsave(&ec->lock, flags); + (void)advance_transaction(ec); + spin_unlock_irqrestore(&ec->lock, flags); } while (time_before(jiffies, delay)); pr_debug("controller reset, restart transaction\n"); spin_lock_irqsave(&ec->lock, flags); @@ -268,23 +287,6 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec, return ret; } -static int ec_check_ibf0(struct acpi_ec *ec) -{ - u8 status = acpi_ec_read_status(ec); - return (status & ACPI_EC_FLAG_IBF) == 0; -} - -static int ec_wait_ibf0(struct acpi_ec *ec) -{ - unsigned long delay = jiffies + msecs_to_jiffies(ec_delay); - /* interrupt wait manually if GPE mode is not active */ - while (time_before(jiffies, delay)) - if (wait_event_timeout(ec->wait, ec_check_ibf0(ec), - msecs_to_jiffies(1))) - return 0; - return -ETIME; -} - static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) { int status; @@ -305,12 +307,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) goto unlock; } } - if (ec_wait_ibf0(ec)) { - pr_err("input buffer is not empty, " - "aborting transaction\n"); - status = -ETIME; - goto end; - } pr_debug("transaction start (cmd=0x%02x, addr=0x%02x)\n", t->command, t->wdata ? t->wdata[0] : 0); /* disable GPE during transaction if storm is detected */ @@ -334,7 +330,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) set_bit(EC_FLAGS_GPE_STORM, &ec->flags); } pr_debug("transaction end\n"); -end: if (ec->global_lock) acpi_release_global_lock(glk); unlock: @@ -443,10 +438,8 @@ acpi_handle ec_get_handle(void) EXPORT_SYMBOL(ec_get_handle); -static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data); - /* - * Clears stale _Q events that might have accumulated in the EC. + * Process _Q events that might have accumulated in the EC. * Run with locked ec mutex. */ static void acpi_ec_clear(struct acpi_ec *ec) @@ -455,7 +448,7 @@ static void acpi_ec_clear(struct acpi_ec *ec) u8 value = 0; for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) { - status = acpi_ec_query_unlocked(ec, &value); + status = acpi_ec_sync_query(ec, &value); if (status || !value) break; } @@ -582,13 +575,18 @@ static void acpi_ec_run(void *cxt) kfree(handler); } -static int acpi_ec_sync_query(struct acpi_ec *ec) +static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data) { u8 value = 0; int status; struct acpi_ec_query_handler *handler, *copy; - if ((status = acpi_ec_query_unlocked(ec, &value))) + + status = acpi_ec_query_unlocked(ec, &value); + if (data) + *data = value; + if (status) return status; + list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { /* have custom handler for this bit */ @@ -612,7 +610,7 @@ static void acpi_ec_gpe_query(void *ec_cxt) if (!ec) return; mutex_lock(&ec->mutex); - acpi_ec_sync_query(ec); + acpi_ec_sync_query(ec, NULL); mutex_unlock(&ec->mutex); } @@ -631,17 +629,14 @@ static int ec_check_sci(struct acpi_ec *ec, u8 state) static u32 acpi_ec_gpe_handler(acpi_handle gpe_device, u32 gpe_number, void *data) { + unsigned long flags; struct acpi_ec *ec = data; - u8 status = acpi_ec_read_status(ec); - pr_debug("~~~> interrupt, status:0x%02x\n", status); - - advance_transaction(ec, status); - if (ec_transaction_done(ec) && - (acpi_ec_read_status(ec) & ACPI_EC_FLAG_IBF) == 0) { + spin_lock_irqsave(&ec->lock, flags); + if (advance_transaction(ec)) wake_up(&ec->wait); - ec_check_sci(ec, acpi_ec_read_status(ec)); - } + spin_unlock_irqrestore(&ec->lock, flags); + ec_check_sci(ec, acpi_ec_read_status(ec)); return ACPI_INTERRUPT_HANDLED | ACPI_REENABLE_GPE; } diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 3dca36d4ad26..17f9ec501972 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -1071,9 +1071,9 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) if (pr->id == 0 && cpuidle_get_driver() == &acpi_idle_driver) { - cpuidle_pause_and_lock(); /* Protect against cpu-hotplug */ get_online_cpus(); + cpuidle_pause_and_lock(); /* Disable all cpuidle devices */ for_each_online_cpu(cpu) { @@ -1100,8 +1100,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) cpuidle_enable_device(dev); } } - put_online_cpus(); cpuidle_resume_and_unlock(); + put_online_cpus(); } return 0; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 0bdacc5e26a3..2ba8f02ced36 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -77,7 +77,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res) switch (ares->type) { case ACPI_RESOURCE_TYPE_MEMORY24: memory24 = &ares->data.memory24; - if (!memory24->address_length) + if (!memory24->minimum && !memory24->address_length) return false; acpi_dev_get_memresource(res, memory24->minimum, memory24->address_length, @@ -85,7 +85,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res) break; case ACPI_RESOURCE_TYPE_MEMORY32: memory32 = &ares->data.memory32; - if (!memory32->address_length) + if (!memory32->minimum && !memory32->address_length) return false; acpi_dev_get_memresource(res, memory32->minimum, memory32->address_length, @@ -93,7 +93,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res) break; case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: fixed_memory32 = &ares->data.fixed_memory32; - if (!fixed_memory32->address_length) + if (!fixed_memory32->address && !fixed_memory32->address_length) return false; acpi_dev_get_memresource(res, fixed_memory32->address, fixed_memory32->address_length, @@ -150,7 +150,7 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res) switch (ares->type) { case ACPI_RESOURCE_TYPE_IO: io = &ares->data.io; - if (!io->address_length) + if (!io->minimum && !io->address_length) return false; acpi_dev_get_ioresource(res, io->minimum, io->address_length, @@ -158,7 +158,7 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res) break; case ACPI_RESOURCE_TYPE_FIXED_IO: fixed_io = &ares->data.fixed_io; - if (!fixed_io->address_length) + if (!fixed_io->address && !fixed_io->address_length) return false; acpi_dev_get_ioresource(res, fixed_io->address, fixed_io->address_length, diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 57b053f424d1..493a342efa44 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -106,7 +106,7 @@ static int create_modalias(struct acpi_device *acpi_dev, char *modalias, list_for_each_entry(id, &acpi_dev->pnp.ids, list) { count = snprintf(&modalias[len], size, "%s:", id->id); if (count < 0) - return EINVAL; + return -EINVAL; if (count >= size) return -ENOMEM; len += count; @@ -329,7 +329,8 @@ static int acpi_scan_hot_remove(struct acpi_device *device) unsigned long long sta; acpi_status status; - if (device->handler->hotplug.demand_offline && !acpi_force_hot_remove) { + if (device->handler && device->handler->hotplug.demand_offline + && !acpi_force_hot_remove) { if (!acpi_scan_is_offline(device, true)) return -EBUSY; } else { @@ -660,8 +661,14 @@ static ssize_t acpi_device_sun_show(struct device *dev, struct device_attribute *attr, char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); + acpi_status status; + unsigned long long sun; + + status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun); + if (ACPI_FAILURE(status)) + return -ENODEV; - return sprintf(buf, "%lu\n", acpi_dev->pnp.sun); + return sprintf(buf, "%llu\n", sun); } static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL); @@ -683,7 +690,6 @@ static int acpi_device_setup_files(struct acpi_device *dev) { struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; acpi_status status; - unsigned long long sun; int result = 0; /* @@ -724,14 +730,10 @@ static int acpi_device_setup_files(struct acpi_device *dev) if (dev->pnp.unique_id) result = device_create_file(&dev->dev, &dev_attr_uid); - status = acpi_evaluate_integer(dev->handle, "_SUN", NULL, &sun); - if (ACPI_SUCCESS(status)) { - dev->pnp.sun = (unsigned long)sun; + if (acpi_has_method(dev->handle, "_SUN")) { result = device_create_file(&dev->dev, &dev_attr_sun); if (result) goto end; - } else { - dev->pnp.sun = (unsigned long)-1; } if (acpi_has_method(dev->handle, "_STA")) { @@ -915,12 +917,17 @@ static void acpi_device_notify(acpi_handle handle, u32 event, void *data) device->driver->ops.notify(device, event); } -static acpi_status acpi_device_notify_fixed(void *data) +static void acpi_device_notify_fixed(void *data) { struct acpi_device *device = data; /* Fixed hardware devices have no handles */ acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device); +} + +static acpi_status acpi_device_fixed_event(void *data) +{ + acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data); return AE_OK; } @@ -931,12 +938,12 @@ static int acpi_device_install_notify_handler(struct acpi_device *device) if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON) status = acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON, - acpi_device_notify_fixed, + acpi_device_fixed_event, device); else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON) status = acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON, - acpi_device_notify_fixed, + acpi_device_fixed_event, device); else status = acpi_install_notify_handler(device->handle, @@ -953,10 +960,10 @@ static void acpi_device_remove_notify_handler(struct acpi_device *device) { if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON) acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON, - acpi_device_notify_fixed); + acpi_device_fixed_event); else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON) acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON, - acpi_device_notify_fixed); + acpi_device_fixed_event); else acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY, acpi_device_notify); @@ -2061,6 +2068,9 @@ static void acpi_bus_attach(struct acpi_device *device) ok: list_for_each_entry(child, &device->children, node) acpi_bus_attach(child); + + if (device->handler && device->handler->hotplug.notify_online) + device->handler->hotplug.notify_online(device); } /** diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 85e3b612bdc0..81a756c765dc 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -30,6 +30,7 @@ #include <linux/types.h> #include <linux/hardirq.h> #include <linux/acpi.h> +#include <linux/dynamic_debug.h> #include "internal.h" @@ -464,6 +465,24 @@ acpi_evaluate_hotplug_ost(acpi_handle handle, u32 source_event, EXPORT_SYMBOL(acpi_evaluate_hotplug_ost); /** + * acpi_handle_path: Return the object path of handle + * + * Caller must free the returned buffer + */ +static char *acpi_handle_path(acpi_handle handle) +{ + struct acpi_buffer buffer = { + .length = ACPI_ALLOCATE_BUFFER, + .pointer = NULL + }; + + if (in_interrupt() || + acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer) != AE_OK) + return NULL; + return buffer.pointer; +} + +/** * acpi_handle_printk: Print message with ACPI prefix and object path * * This function is called through acpi_handle_<level> macros and prints @@ -476,29 +495,50 @@ acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...) { struct va_format vaf; va_list args; - struct acpi_buffer buffer = { - .length = ACPI_ALLOCATE_BUFFER, - .pointer = NULL - }; const char *path; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - if (in_interrupt() || - acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer) != AE_OK) - path = "<n/a>"; - else - path = buffer.pointer; - - printk("%sACPI: %s: %pV", level, path, &vaf); + path = acpi_handle_path(handle); + printk("%sACPI: %s: %pV", level, path ? path : "<n/a>" , &vaf); va_end(args); - kfree(buffer.pointer); + kfree(path); } EXPORT_SYMBOL(acpi_handle_printk); +#if defined(CONFIG_DYNAMIC_DEBUG) +/** + * __acpi_handle_debug: pr_debug with ACPI prefix and object path + * + * This function is called through acpi_handle_debug macro and debug + * prints a message with ACPI prefix and object path. This function + * acquires the global namespace mutex to obtain an object path. In + * interrupt context, it shows the object path as <n/a>. + */ +void +__acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + const char *path; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + path = acpi_handle_path(handle); + __dynamic_pr_debug(descriptor, "ACPI: %s: %pV", path ? path : "<n/a>", &vaf); + + va_end(args); + kfree(path); +} +EXPORT_SYMBOL(__acpi_handle_debug); +#endif + /** * acpi_has_method: Check whether @handle has a method named @name * @handle: ACPI device handle diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index b6ba88ed31ae..bb0b90461a6b 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -459,10 +459,10 @@ static struct dmi_system_id video_dmi_table[] __initdata = { }, { .callback = video_set_use_native_backlight, - .ident = "ThinkPad T430s", + .ident = "ThinkPad T430 and T430s", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430"), }, }, { @@ -474,7 +474,7 @@ static struct dmi_system_id video_dmi_table[] __initdata = { }, }, { - .callback = video_set_use_native_backlight, + .callback = video_set_use_native_backlight, .ident = "ThinkPad X1 Carbon", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), @@ -494,7 +494,7 @@ static struct dmi_system_id video_dmi_table[] __initdata = { .ident = "Dell Inspiron 7520", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_VERSION, "Inspiron 7520"), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"), }, }, { @@ -507,6 +507,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = { }, { .callback = video_set_use_native_backlight, + .ident = "Acer Aspire 5742G", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5742G"), + }, + }, + { + .callback = video_set_use_native_backlight, .ident = "Acer Aspire V5-431", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index c81d809c111b..00663d60f6d4 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -306,6 +306,14 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x9c85), board_ahci }, /* Wildcat Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */ + { PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */ + { PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -443,16 +451,23 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a), .driver_data = board_ahci_yes_fbs }, /* 88se9172 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172), + .driver_data = board_ahci_yes_fbs }, /* 88se9182 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9182), .driver_data = board_ahci_yes_fbs }, /* 88se9172 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192), .driver_data = board_ahci_yes_fbs }, /* 88se9172 on some Gigabyte */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0), + .driver_data = board_ahci_yes_fbs }, { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a3), .driver_data = board_ahci_yes_fbs }, { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230), .driver_data = board_ahci_yes_fbs }, + { PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642), + .driver_data = board_ahci_yes_fbs }, /* Promise */ { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ + { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ /* Asmedia */ { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ @@ -1163,7 +1178,7 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host) #endif static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports, - struct ahci_host_priv *hpriv) + struct ahci_host_priv *hpriv) { int rc, nvec; @@ -1189,6 +1204,13 @@ static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports, else if (rc > 0) goto single_msi; + /* fallback to single MSI mode if the controller enforced MRSM mode */ + if (readl(hpriv->mmio + HOST_CTL) & HOST_MRSM) { + pci_disable_msi(pdev); + printk(KERN_INFO "ahci: MRSM is on, fallback to single MSI\n"); + goto single_msi; + } + return nvec; single_msi: @@ -1233,18 +1255,18 @@ int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis) return rc; for (i = 0; i < host->n_ports; i++) { - const char* desc; struct ahci_port_priv *pp = host->ports[i]->private_data; - /* pp is NULL for dummy ports */ - if (pp) - desc = pp->irq_desc; - else - desc = dev_driver_string(host->dev); + /* Do not receive interrupts sent by dummy ports */ + if (!pp) { + disable_irq(irq + i); + continue; + } - rc = devm_request_threaded_irq(host->dev, - irq + i, ahci_hw_interrupt, ahci_thread_fn, IRQF_SHARED, - desc, host->ports[i]); + rc = devm_request_threaded_irq(host->dev, irq + i, + ahci_hw_interrupt, + ahci_thread_fn, IRQF_SHARED, + pp->irq_desc, host->ports[i]); if (rc) goto out_free_irqs; } diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 2289efdf8203..ad36faf31dbd 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -91,6 +91,7 @@ enum { /* HOST_CTL bits */ HOST_RESET = (1 << 0), /* reset controller; self-clear */ HOST_IRQ_EN = (1 << 1), /* global IRQ enable */ + HOST_MRSM = (1 << 2), /* MSI Revert to Single Message */ HOST_AHCI_EN = (1 << 31), /* AHCI enabled */ /* HOST_CAP bits */ diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 6334c8d7c3f1..39f76b987c75 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -340,6 +340,14 @@ static const struct pci_device_id piix_pci_tbl[] = { { 0x8086, 0x0F21, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_byt }, /* SATA Controller IDE (Coleto Creek) */ { 0x8086, 0x23a6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c88, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c89, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c80, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c81, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, { } /* terminate list */ }; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8cb2522d592a..538574f98e22 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4226,6 +4226,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* devices that don't properly handle queued TRIM commands */ { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, { "Crucial_CT???M500SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Micron_M550*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Crucial_CT*M550SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link @@ -4785,6 +4787,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) * ata_qc_new - Request an available ATA command, for queueing * @ap: target port * + * Some ATA host controllers may implement a queue depth which is less + * than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond + * the hardware limitation. + * * LOCKING: * None. */ @@ -4792,21 +4798,27 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap) { struct ata_queued_cmd *qc = NULL; - unsigned int i; + unsigned int max_queue = ap->host->n_tags; + unsigned int i, tag; /* no command while frozen */ if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) return NULL; - /* the last tag is reserved for internal command. */ - for (i = 0; i < ATA_MAX_QUEUE - 1; i++) - if (!test_and_set_bit(i, &ap->qc_allocated)) { - qc = __ata_qc_from_tag(ap, i); + for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) { + tag = tag < max_queue ? tag : 0; + + /* the last tag is reserved for internal command. */ + if (tag == ATA_TAG_INTERNAL) + continue; + + if (!test_and_set_bit(tag, &ap->qc_allocated)) { + qc = __ata_qc_from_tag(ap, tag); + qc->tag = tag; + ap->last_tag = tag; break; } - - if (qc) - qc->tag = i; + } return qc; } @@ -6096,6 +6108,7 @@ void ata_host_init(struct ata_host *host, struct device *dev, { spin_lock_init(&host->lock); mutex_init(&host->eh_mutex); + host->n_tags = ATA_MAX_QUEUE - 1; host->dev = dev; host->ops = ops; } @@ -6177,6 +6190,8 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) { int i, rc; + host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1); + /* host must have been started */ if (!(host->flags & ATA_HOST_STARTED)) { dev_err(host->dev, "BUG: trying to register unstarted host\n"); @@ -6322,6 +6337,8 @@ int ata_host_activate(struct ata_host *host, int irq, static void ata_port_detach(struct ata_port *ap) { unsigned long flags; + struct ata_link *link; + struct ata_device *dev; if (!ap->ops->error_handler) goto skip_eh; @@ -6341,6 +6358,13 @@ static void ata_port_detach(struct ata_port *ap) cancel_delayed_work_sync(&ap->hotplug_task); skip_eh: + /* clean up zpodd on port removal */ + ata_for_each_link(link, ap, HOST_FIRST) { + ata_for_each_dev(dev, link, ALL) { + if (zpodd_dev_enabled(dev)) + zpodd_exit(dev); + } + } if (ap->pmp_link) { int i; for (i = 0; i < SATA_PMP_MAX_PORTS; i++) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b603720b877d..37acda6fa7e4 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -2008,13 +2008,15 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask, DPRINTK("ata%u: bus reset via SRST\n", ap->print_id); - /* software reset. causes dev0 to be selected */ - iowrite8(ap->ctl, ioaddr->ctl_addr); - udelay(20); /* FIXME: flush */ - iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr); - udelay(20); /* FIXME: flush */ - iowrite8(ap->ctl, ioaddr->ctl_addr); - ap->last_ctl = ap->ctl; + if (ap->ioaddr.ctl_addr) { + /* software reset. causes dev0 to be selected */ + iowrite8(ap->ctl, ioaddr->ctl_addr); + udelay(20); /* FIXME: flush */ + iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr); + udelay(20); /* FIXME: flush */ + iowrite8(ap->ctl, ioaddr->ctl_addr); + ap->last_ctl = ap->ctl; + } /* wait the port to become ready */ return ata_sff_wait_after_reset(&ap->link, devmask, deadline); @@ -2215,10 +2217,6 @@ void ata_sff_error_handler(struct ata_port *ap) spin_unlock_irqrestore(ap->lock, flags); - /* ignore ata_sff_softreset if ctl isn't accessible */ - if (softreset == ata_sff_softreset && !ap->ioaddr.ctl_addr) - softreset = NULL; - /* ignore built-in hardresets if SCR access is not available */ if ((hardreset == sata_std_hardreset || hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link)) diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c index d63ee8f41a4f..e3a49df958a3 100644 --- a/drivers/ata/pata_at91.c +++ b/drivers/ata/pata_at91.c @@ -408,12 +408,13 @@ static int pata_at91_probe(struct platform_device *pdev) host->private_data = info; - return ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0, - gpio_is_valid(irq) ? ata_sff_interrupt : NULL, - irq_flags, &pata_at91_sht); + ret = ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0, + gpio_is_valid(irq) ? ata_sff_interrupt : NULL, + irq_flags, &pata_at91_sht); + if (ret) + goto err_put; - if (!ret) - return 0; + return 0; err_put: clk_put(info->mck); diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c index f35f15f4d83e..f7badaa39eb6 100644 --- a/drivers/ata/pata_scc.c +++ b/drivers/ata/pata_scc.c @@ -586,7 +586,7 @@ static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask, * Note: Original code is ata_bus_softreset(). */ -static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, +static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, unsigned long deadline) { struct ata_ioports *ioaddr = &ap->ioaddr; @@ -600,9 +600,7 @@ static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, udelay(20); out_be32(ioaddr->ctl_addr, ap->ctl); - scc_wait_after_reset(&ap->link, devmask, deadline); - - return 0; + return scc_wait_after_reset(&ap->link, devmask, deadline); } /** @@ -619,7 +617,8 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, { struct ata_port *ap = link->ap; unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS; - unsigned int devmask = 0, err_mask; + unsigned int devmask = 0; + int rc; u8 err; DPRINTK("ENTER\n"); @@ -635,9 +634,9 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, /* issue bus reset */ DPRINTK("about to softreset, devmask=%x\n", devmask); - err_mask = scc_bus_softreset(ap, devmask, deadline); - if (err_mask) { - ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", err_mask); + rc = scc_bus_softreset(ap, devmask, deadline); + if (rc) { + ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc); return -EIO; } diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c index 96c6a79ef606..79dedbae282c 100644 --- a/drivers/ata/pata_serverworks.c +++ b/drivers/ata/pata_serverworks.c @@ -252,12 +252,18 @@ static void serverworks_set_dmamode(struct ata_port *ap, struct ata_device *adev pci_write_config_byte(pdev, 0x54, ultra_cfg); } -static struct scsi_host_template serverworks_sht = { +static struct scsi_host_template serverworks_osb4_sht = { + ATA_BMDMA_SHT(DRV_NAME), + .sg_tablesize = LIBATA_DUMB_MAX_PRD, +}; + +static struct scsi_host_template serverworks_csb_sht = { ATA_BMDMA_SHT(DRV_NAME), }; static struct ata_port_operations serverworks_osb4_port_ops = { .inherits = &ata_bmdma_port_ops, + .qc_prep = ata_bmdma_dumb_qc_prep, .cable_detect = serverworks_cable_detect, .mode_filter = serverworks_osb4_filter, .set_piomode = serverworks_set_piomode, @@ -266,6 +272,7 @@ static struct ata_port_operations serverworks_osb4_port_ops = { static struct ata_port_operations serverworks_csb_port_ops = { .inherits = &serverworks_osb4_port_ops, + .qc_prep = ata_bmdma_qc_prep, .mode_filter = serverworks_csb_filter, }; @@ -405,6 +412,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id } }; const struct ata_port_info *ppi[] = { &info[id->driver_data], NULL }; + struct scsi_host_template *sht = &serverworks_csb_sht; int rc; rc = pcim_enable_device(pdev); @@ -418,6 +426,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id /* Select non UDMA capable OSB4 if we can't do fixups */ if (rc < 0) ppi[0] = &info[1]; + sht = &serverworks_osb4_sht; } /* setup CSB5/CSB6 : South Bridge and IDE option RAID */ else if ((pdev->device == PCI_DEVICE_ID_SERVERWORKS_CSB5IDE) || @@ -434,7 +443,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id ppi[1] = &ata_dummy_port_info; } - return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0); + return ata_pci_bmdma_init_one(pdev, ppi, sht, NULL, 0); } #ifdef CONFIG_PM diff --git a/drivers/base/core.c b/drivers/base/core.c index 2b567177ef78..6a8955e78610 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -741,12 +741,12 @@ class_dir_create_and_add(struct class *class, struct kobject *parent_kobj) return &dir->kobj; } +static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { if (dev->class) { - static DEFINE_MUTEX(gdp_mutex); struct kobject *kobj = NULL; struct kobject *parent_kobj; struct kobject *k; @@ -810,7 +810,9 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) glue_dir->kset != &dev->class->p->glue_dirs) return; + mutex_lock(&gdp_mutex); kobject_put(glue_dir); + mutex_unlock(&gdp_mutex); } static void cleanup_device_parent(struct device *dev) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 06051767393f..8a8d611f2021 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -52,6 +52,7 @@ static DEFINE_MUTEX(deferred_probe_mutex); static LIST_HEAD(deferred_probe_pending_list); static LIST_HEAD(deferred_probe_active_list); static struct workqueue_struct *deferred_wq; +static atomic_t deferred_trigger_count = ATOMIC_INIT(0); /** * deferred_probe_work_func() - Retry probing devices in the active list. @@ -135,6 +136,17 @@ static bool driver_deferred_probe_enable = false; * This functions moves all devices from the pending list to the active * list and schedules the deferred probe workqueue to process them. It * should be called anytime a driver is successfully bound to a device. + * + * Note, there is a race condition in multi-threaded probe. In the case where + * more than one device is probing at the same time, it is possible for one + * probe to complete successfully while another is about to defer. If the second + * depends on the first, then it will get put on the pending list after the + * trigger event has already occured and will be stuck there. + * + * The atomic 'deferred_trigger_count' is used to determine if a successful + * trigger has occurred in the midst of probing a driver. If the trigger count + * changes in the midst of a probe, then deferred processing should be triggered + * again. */ static void driver_deferred_probe_trigger(void) { @@ -147,6 +159,7 @@ static void driver_deferred_probe_trigger(void) * into the active list so they can be retried by the workqueue */ mutex_lock(&deferred_probe_mutex); + atomic_inc(&deferred_trigger_count); list_splice_tail_init(&deferred_probe_pending_list, &deferred_probe_active_list); mutex_unlock(&deferred_probe_mutex); @@ -265,6 +278,7 @@ static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); static int really_probe(struct device *dev, struct device_driver *drv) { int ret = 0; + int local_trigger_count = atomic_read(&deferred_trigger_count); atomic_inc(&probe_count); pr_debug("bus: '%s': %s: probing driver %s with device %s\n", @@ -310,6 +324,9 @@ probe_failed: /* Driver requested deferred probing */ dev_info(dev, "Driver %s requests probe deferral\n", drv->name); driver_deferred_probe_add(dev); + /* Did a trigger occur while probing? Need to re-trigger if yes */ + if (local_trigger_count != atomic_read(&deferred_trigger_count)) + driver_deferred_probe_trigger(); } else if (ret != -ENODEV && ret != -ENXIO) { /* driver matched but the probe failed */ printk(KERN_WARNING diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c index 165c2c299e57..d3bffa478eca 100644 --- a/drivers/base/dma-contiguous.c +++ b/drivers/base/dma-contiguous.c @@ -155,13 +155,23 @@ static int __init cma_activate_area(struct cma *cma) base_pfn = pfn; for (j = pageblock_nr_pages; j; --j, pfn++) { WARN_ON_ONCE(!pfn_valid(pfn)); + /* + * alloc_contig_range requires the pfn range + * specified to be in the same zone. Make this + * simple by forcing the entire CMA resv range + * to be in the same zone. + */ if (page_zone(pfn_to_page(pfn)) != zone) - return -EINVAL; + goto err; } init_cma_reserved_pageblock(pfn_to_page(base_pfn)); } while (--i); return 0; + +err: + kfree(cma->bitmap); + return -EINVAL; } static struct cma cma_areas[MAX_CMA_AREAS]; diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index c30df50e4440..2495ee577a64 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -1081,6 +1081,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name, if (!firmware_p) return -EINVAL; + if (!name || name[0] == '\0') + return -EINVAL; + ret = _request_firmware_prepare(&fw, name, device); if (ret <= 0) /* error or already assigned */ goto out; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index bc78848dd59a..9dbf4ef2b2a3 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -13,6 +13,7 @@ #include <linux/string.h> #include <linux/platform_device.h> #include <linux/of_device.h> +#include <linux/of_irq.h> #include <linux/module.h> #include <linux/init.h> #include <linux/dma-mapping.h> @@ -87,7 +88,16 @@ int platform_get_irq(struct platform_device *dev, unsigned int num) return -ENXIO; return dev->archdata.irqs[num]; #else - struct resource *r = platform_get_resource(dev, IORESOURCE_IRQ, num); + struct resource *r; + if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) { + int ret; + + ret = of_irq_get(dev->dev.of_node, num); + if (ret >= 0 || ret == -EPROBE_DEFER) + return ret; + } + + r = platform_get_resource(dev, IORESOURCE_IRQ, num); return r ? r->start : -ENXIO; #endif diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index fa4187418440..08d99ef60b70 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -735,11 +735,9 @@ int of_init_opp_table(struct device *dev) unsigned long freq = be32_to_cpup(val++) * 1000; unsigned long volt = be32_to_cpup(val++); - if (dev_pm_opp_add(dev, freq, volt)) { + if (dev_pm_opp_add(dev, freq, volt)) dev_warn(dev, "%s: Failed to add OPP %ld\n", __func__, freq); - continue; - } nr -= 2; } diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index d4dd77134814..154e7a8c0a04 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -701,7 +701,7 @@ int regcache_sync_block(struct regmap *map, void *block, unsigned int block_base, unsigned int start, unsigned int end) { - if (regmap_can_raw_write(map)) + if (regmap_can_raw_write(map) && !map->use_single_rw) return regcache_sync_block_raw(map, block, cache_present, block_base, start, end); else diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index c5471cd6ebb7..d39fd610aa3b 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -473,6 +473,7 @@ void regmap_debugfs_init(struct regmap *map, const char *name) { struct rb_node *next; struct regmap_range_node *range_node; + const char *devname = "dummy"; /* If we don't have the debugfs root yet, postpone init */ if (!regmap_debugfs_root) { @@ -491,12 +492,15 @@ void regmap_debugfs_init(struct regmap *map, const char *name) INIT_LIST_HEAD(&map->debugfs_off_cache); mutex_init(&map->cache_lock); + if (map->dev) + devname = dev_name(map->dev); + if (name) { map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s", - dev_name(map->dev), name); + devname, name); name = map->debugfs_name; } else { - name = dev_name(map->dev); + name = devname; } map->debugfs = debugfs_create_dir(name, regmap_debugfs_root); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 6a19515f8a45..f6cff3be0ed7 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -105,7 +105,7 @@ bool regmap_readable(struct regmap *map, unsigned int reg) bool regmap_volatile(struct regmap *map, unsigned int reg) { - if (!regmap_readable(map, reg)) + if (!map->format.format_write && !regmap_readable(map, reg)) return false; if (map->volatile_reg) @@ -1308,7 +1308,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, } #ifdef LOG_DEVICE - if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0) dev_info(map->dev, "%x <= %x\n", reg, val); #endif @@ -1557,6 +1557,9 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, } else { void *wval; + if (!val_count) + return -EINVAL; + wval = kmemdup(val, val_count * val_bytes, GFP_KERNEL); if (!wval) { ret = -ENOMEM; @@ -1739,7 +1742,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg, ret = map->reg_read(context, reg, val); if (ret == 0) { #ifdef LOG_DEVICE - if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0) dev_info(map->dev, "%x => %x\n", reg, *val); #endif diff --git a/drivers/base/topology.c b/drivers/base/topology.c index 94ffee378f10..37a5661ca5f9 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -40,8 +40,7 @@ static ssize_t show_##name(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ - unsigned int cpu = dev->id; \ - return sprintf(buf, "%d\n", topology_##name(cpu)); \ + return sprintf(buf, "%d\n", topology_##name(dev->id)); \ } #if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \ diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c index 89c497c630b4..04a14e0f8878 100644 --- a/drivers/block/drbd/drbd_interval.c +++ b/drivers/block/drbd/drbd_interval.c @@ -79,6 +79,7 @@ bool drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) { struct rb_node **new = &root->rb_node, *parent = NULL; + sector_t this_end = this->sector + (this->size >> 9); BUG_ON(!IS_ALIGNED(this->size, 512)); @@ -87,6 +88,8 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) rb_entry(*new, struct drbd_interval, rb); parent = *new; + if (here->end < this_end) + here->end = this_end; if (this->sector < here->sector) new = &(*new)->rb_left; else if (this->sector > here->sector) @@ -99,6 +102,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) return false; } + this->end = this_end; rb_link_node(&this->rb, parent, new); rb_insert_augmented(&this->rb, root, &augment_callbacks); return true; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index c706d50a8b06..8c16c2f97026 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -525,6 +525,12 @@ void conn_try_outdate_peer_async(struct drbd_tconn *tconn) struct task_struct *opa; kref_get(&tconn->kref); + /* We may just have force_sig()'ed this thread + * to get it out of some blocking network function. + * Clear signals; otherwise kthread_run(), which internally uses + * wait_on_completion_killable(), will mistake our pending signal + * for a new fatal signal and fail. */ + flush_signals(current); opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h"); if (IS_ERR(opa)) { conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n"); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 2023043ce7c0..dab515cd77bf 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3053,7 +3053,10 @@ static int raw_cmd_copyout(int cmd, void __user *param, int ret; while (ptr) { - ret = copy_to_user(param, ptr, sizeof(*ptr)); + struct floppy_raw_cmd cmd = *ptr; + cmd.next = NULL; + cmd.kernel_data = NULL; + ret = copy_to_user(param, &cmd, sizeof(cmd)); if (ret) return -EFAULT; param += sizeof(struct floppy_raw_cmd); @@ -3107,10 +3110,11 @@ loop: return -ENOMEM; *rcmd = ptr; ret = copy_from_user(ptr, param, sizeof(*ptr)); - if (ret) - return -EFAULT; ptr->next = NULL; ptr->buffer_length = 0; + ptr->kernel_data = NULL; + if (ret) + return -EFAULT; param += sizeof(struct floppy_raw_cmd); if (ptr->cmd_count > 33) /* the command may now also take up the space @@ -3126,7 +3130,6 @@ loop: for (i = 0; i < 16; i++) ptr->reply[i] = 0; ptr->resultcode = 0; - ptr->kernel_data = NULL; if (ptr->flags & (FD_RAW_READ | FD_RAW_WRITE)) { if (ptr->length <= 0) diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index d777bb7cea93..4e763b0dbbfc 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -252,38 +252,45 @@ static void mtip_async_complete(struct mtip_port *port, void *data, int status) { - struct mtip_cmd *command; + struct mtip_cmd *cmd; struct driver_data *dd = data; - int cb_status = status ? -EIO : 0; + int unaligned, cb_status = status ? -EIO : 0; + void (*func)(void *, int); if (unlikely(!dd) || unlikely(!port)) return; - command = &port->commands[tag]; + cmd = &port->commands[tag]; if (unlikely(status == PORT_IRQ_TF_ERR)) { dev_warn(&port->dd->pdev->dev, "Command tag %d failed due to TFE\n", tag); } + /* Clear the active flag */ + atomic_set(&port->commands[tag].active, 0); + /* Upper layer callback */ - if (likely(command->async_callback)) - command->async_callback(command->async_data, cb_status); + func = cmd->async_callback; + if (likely(func && cmpxchg(&cmd->async_callback, func, 0) == func)) { - command->async_callback = NULL; - command->comp_func = NULL; + /* Unmap the DMA scatter list entries */ + dma_unmap_sg(&dd->pdev->dev, + cmd->sg, + cmd->scatter_ents, + cmd->direction); - /* Unmap the DMA scatter list entries */ - dma_unmap_sg(&dd->pdev->dev, - command->sg, - command->scatter_ents, - command->direction); + func(cmd->async_data, cb_status); + unaligned = cmd->unaligned; - /* Clear the allocated and active bits for the command */ - atomic_set(&port->commands[tag].active, 0); - release_slot(port, tag); + /* Clear the allocated bit for the command */ + release_slot(port, tag); - up(&port->cmd_slot); + if (unlikely(unaligned)) + up(&port->cmd_slot_unal); + else + up(&port->cmd_slot); + } } /* @@ -660,11 +667,12 @@ static void mtip_timeout_function(unsigned long int data) { struct mtip_port *port = (struct mtip_port *) data; struct host_to_dev_fis *fis; - struct mtip_cmd *command; - int tag, cmdto_cnt = 0; + struct mtip_cmd *cmd; + int unaligned, tag, cmdto_cnt = 0; unsigned int bit, group; unsigned int num_command_slots; unsigned long to, tagaccum[SLOTBITS_IN_LONGS]; + void (*func)(void *, int); if (unlikely(!port)) return; @@ -694,8 +702,8 @@ static void mtip_timeout_function(unsigned long int data) group = tag >> 5; bit = tag & 0x1F; - command = &port->commands[tag]; - fis = (struct host_to_dev_fis *) command->command; + cmd = &port->commands[tag]; + fis = (struct host_to_dev_fis *) cmd->command; set_bit(tag, tagaccum); cmdto_cnt++; @@ -709,27 +717,30 @@ static void mtip_timeout_function(unsigned long int data) */ writel(1 << bit, port->completed[group]); - /* Call the async completion callback. */ - if (likely(command->async_callback)) - command->async_callback(command->async_data, - -EIO); - command->async_callback = NULL; - command->comp_func = NULL; + /* Clear the active flag for the command */ + atomic_set(&port->commands[tag].active, 0); - /* Unmap the DMA scatter list entries */ - dma_unmap_sg(&port->dd->pdev->dev, - command->sg, - command->scatter_ents, - command->direction); + func = cmd->async_callback; + if (func && + cmpxchg(&cmd->async_callback, func, 0) == func) { - /* - * Clear the allocated bit and active tag for the - * command. - */ - atomic_set(&port->commands[tag].active, 0); - release_slot(port, tag); + /* Unmap the DMA scatter list entries */ + dma_unmap_sg(&port->dd->pdev->dev, + cmd->sg, + cmd->scatter_ents, + cmd->direction); - up(&port->cmd_slot); + func(cmd->async_data, -EIO); + unaligned = cmd->unaligned; + + /* Clear the allocated bit for the command. */ + release_slot(port, tag); + + if (unaligned) + up(&port->cmd_slot_unal); + else + up(&port->cmd_slot); + } } } @@ -1518,6 +1529,37 @@ static inline void ata_swap_string(u16 *buf, unsigned int len) be16_to_cpus(&buf[i]); } +static void mtip_set_timeout(struct driver_data *dd, + struct host_to_dev_fis *fis, + unsigned int *timeout, u8 erasemode) +{ + switch (fis->command) { + case ATA_CMD_DOWNLOAD_MICRO: + *timeout = 120000; /* 2 minutes */ + break; + case ATA_CMD_SEC_ERASE_UNIT: + case 0xFC: + if (erasemode) + *timeout = ((*(dd->port->identify + 90) * 2) * 60000); + else + *timeout = ((*(dd->port->identify + 89) * 2) * 60000); + break; + case ATA_CMD_STANDBYNOW1: + *timeout = 120000; /* 2 minutes */ + break; + case 0xF7: + case 0xFA: + *timeout = 60000; /* 60 seconds */ + break; + case ATA_CMD_SMART: + *timeout = 15000; /* 15 seconds */ + break; + default: + *timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS; + break; + } +} + /* * Request the device identity information. * @@ -1633,6 +1675,7 @@ static int mtip_standby_immediate(struct mtip_port *port) int rv; struct host_to_dev_fis fis; unsigned long start; + unsigned int timeout; /* Build the FIS. */ memset(&fis, 0, sizeof(struct host_to_dev_fis)); @@ -1640,6 +1683,8 @@ static int mtip_standby_immediate(struct mtip_port *port) fis.opts = 1 << 7; fis.command = ATA_CMD_STANDBYNOW1; + mtip_set_timeout(port->dd, &fis, &timeout, 0); + start = jiffies; rv = mtip_exec_internal_command(port, &fis, @@ -1648,7 +1693,7 @@ static int mtip_standby_immediate(struct mtip_port *port) 0, 0, GFP_ATOMIC, - 15000); + timeout); dbg_printk(MTIP_DRV_NAME "Time taken to complete standby cmd: %d ms\n", jiffies_to_msecs(jiffies - start)); if (rv) @@ -2191,36 +2236,6 @@ static unsigned int implicit_sector(unsigned char command, } return rv; } -static void mtip_set_timeout(struct driver_data *dd, - struct host_to_dev_fis *fis, - unsigned int *timeout, u8 erasemode) -{ - switch (fis->command) { - case ATA_CMD_DOWNLOAD_MICRO: - *timeout = 120000; /* 2 minutes */ - break; - case ATA_CMD_SEC_ERASE_UNIT: - case 0xFC: - if (erasemode) - *timeout = ((*(dd->port->identify + 90) * 2) * 60000); - else - *timeout = ((*(dd->port->identify + 89) * 2) * 60000); - break; - case ATA_CMD_STANDBYNOW1: - *timeout = 120000; /* 2 minutes */ - break; - case 0xF7: - case 0xFA: - *timeout = 60000; /* 60 seconds */ - break; - case ATA_CMD_SMART: - *timeout = 15000; /* 15 seconds */ - break; - default: - *timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS; - break; - } -} /* * Executes a taskfile @@ -4213,6 +4228,7 @@ skip_create_disk: blk_queue_max_hw_sectors(dd->queue, 0xffff); blk_queue_max_segment_size(dd->queue, 0x400000); blk_queue_io_min(dd->queue, 4096); + blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask); /* * write back cache is not supported in the device. FUA depends on @@ -4467,6 +4483,57 @@ static DEFINE_HANDLER(5); static DEFINE_HANDLER(6); static DEFINE_HANDLER(7); +static void mtip_disable_link_opts(struct driver_data *dd, struct pci_dev *pdev) +{ + int pos; + unsigned short pcie_dev_ctrl; + + pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); + if (pos) { + pci_read_config_word(pdev, + pos + PCI_EXP_DEVCTL, + &pcie_dev_ctrl); + if (pcie_dev_ctrl & (1 << 11) || + pcie_dev_ctrl & (1 << 4)) { + dev_info(&dd->pdev->dev, + "Disabling ERO/No-Snoop on bridge device %04x:%04x\n", + pdev->vendor, pdev->device); + pcie_dev_ctrl &= ~(PCI_EXP_DEVCTL_NOSNOOP_EN | + PCI_EXP_DEVCTL_RELAX_EN); + pci_write_config_word(pdev, + pos + PCI_EXP_DEVCTL, + pcie_dev_ctrl); + } + } +} + +static void mtip_fix_ero_nosnoop(struct driver_data *dd, struct pci_dev *pdev) +{ + /* + * This workaround is specific to AMD/ATI chipset with a PCI upstream + * device with device id 0x5aXX + */ + if (pdev->bus && pdev->bus->self) { + if (pdev->bus->self->vendor == PCI_VENDOR_ID_ATI && + ((pdev->bus->self->device & 0xff00) == 0x5a00)) { + mtip_disable_link_opts(dd, pdev->bus->self); + } else { + /* Check further up the topology */ + struct pci_dev *parent_dev = pdev->bus->self; + if (parent_dev->bus && + parent_dev->bus->parent && + parent_dev->bus->parent->self && + parent_dev->bus->parent->self->vendor == + PCI_VENDOR_ID_ATI && + (parent_dev->bus->parent->self->device & + 0xff00) == 0x5a00) { + mtip_disable_link_opts(dd, + parent_dev->bus->parent->self); + } + } + } +} + /* * Called for each supported PCI device detected. * @@ -4618,6 +4685,8 @@ static int mtip_pci_probe(struct pci_dev *pdev, goto block_initialize_err; } + mtip_fix_ero_nosnoop(dd, pdev); + /* Initialize the block layer. */ rv = mtip_block_initialize(dd); if (rv < 0) { @@ -4921,13 +4990,13 @@ static int __init mtip_init(void) */ static void __exit mtip_exit(void) { - debugfs_remove_recursive(dfs_parent); - /* Release the allocated major block device number. */ unregister_blkdev(mtip_major, MTIP_DRV_NAME); /* Unregister the PCI driver. */ pci_unregister_driver(&mtip_pci_driver); + + debugfs_remove_recursive(dfs_parent); } MODULE_AUTHOR("Micron Technology, Inc"); diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index 54174cb32feb..ffb955e7ccb9 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -92,7 +92,7 @@ /* Driver name and version strings */ #define MTIP_DRV_NAME "mtip32xx" -#define MTIP_DRV_VERSION "1.3.0" +#define MTIP_DRV_VERSION "1.3.1" /* Maximum number of minor device numbers per device. */ #define MTIP_MAX_MINORS 16 diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 34898d53395b..255ca232ecc7 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1366,6 +1366,14 @@ static bool obj_request_exists_test(struct rbd_obj_request *obj_request) return test_bit(OBJ_REQ_EXISTS, &obj_request->flags) != 0; } +static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request) +{ + struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev; + + return obj_request->img_offset < + round_up(rbd_dev->parent_overlap, rbd_obj_bytes(&rbd_dev->header)); +} + static void rbd_obj_request_get(struct rbd_obj_request *obj_request) { dout("%s: obj %p (was %d)\n", __func__, obj_request, @@ -1382,6 +1390,13 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request) kref_put(&obj_request->kref, rbd_obj_request_destroy); } +static void rbd_img_request_get(struct rbd_img_request *img_request) +{ + dout("%s: img %p (was %d)\n", __func__, img_request, + atomic_read(&img_request->kref.refcount)); + kref_get(&img_request->kref); +} + static bool img_request_child_test(struct rbd_img_request *img_request); static void rbd_parent_request_destroy(struct kref *kref); static void rbd_img_request_destroy(struct kref *kref); @@ -2128,6 +2143,7 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request) img_request->next_completion = which; out: spin_unlock_irq(&img_request->completion_lock); + rbd_img_request_put(img_request); if (!more) rbd_img_request_complete(img_request); @@ -2225,6 +2241,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request, goto out_partial; obj_request->osd_req = osd_req; obj_request->callback = rbd_img_obj_callback; + rbd_img_request_get(img_request); osd_req_op_extent_init(osd_req, 0, opcode, offset, length, 0, 0); @@ -2253,7 +2270,7 @@ out_partial: rbd_obj_request_put(obj_request); out_unwind: for_each_obj_request_safe(img_request, obj_request, next_obj_request) - rbd_obj_request_put(obj_request); + rbd_img_obj_request_del(img_request, obj_request); return -ENOMEM; } @@ -2647,7 +2664,7 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request) */ if (!img_request_write_test(img_request) || !img_request_layered_test(img_request) || - rbd_dev->parent_overlap <= obj_request->img_offset || + !obj_request_overlaps_parent(obj_request) || ((known = obj_request_known_test(obj_request)) && obj_request_exists_test(obj_request))) { @@ -3200,7 +3217,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev, page_count = (u32) calc_pages_for(offset, length); pages = ceph_alloc_page_vector(page_count, GFP_KERNEL); if (IS_ERR(pages)) - ret = PTR_ERR(pages); + return PTR_ERR(pages); ret = -ENOMEM; obj_request = rbd_obj_request_create(object_name, offset, length, diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index b1cb3f4c4db4..6c911c86fb5a 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -144,11 +144,11 @@ static void virtblk_done(struct virtqueue *vq) if (unlikely(virtqueue_is_broken(vq))) break; } while (!virtqueue_enable_cb(vq)); - spin_unlock_irqrestore(&vblk->vq_lock, flags); /* In case queue is stopped waiting for more buffers. */ if (req_done) blk_mq_start_stopped_hw_queues(vblk->disk->queue); + spin_unlock_irqrestore(&vblk->vq_lock, flags); } static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req) @@ -200,8 +200,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req) spin_lock_irqsave(&vblk->vq_lock, flags); if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) { virtqueue_kick(vblk->vq); - spin_unlock_irqrestore(&vblk->vq_lock, flags); blk_mq_stop_hw_queue(hctx); + spin_unlock_irqrestore(&vblk->vq_lock, flags); return BLK_MQ_RQ_QUEUE_BUSY; } diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 64c60edcdfbc..63fc7f06a014 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -763,6 +763,7 @@ again: BUG_ON(new_map_idx >= segs_to_map); if (unlikely(map[new_map_idx].status != 0)) { pr_debug(DRV_PFX "invalid buffer -- could not remap it\n"); + put_free_pages(blkif, &pages[seg_idx]->page, 1); pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE; ret |= 1; goto next; diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 106d1d8e16ad..b11949c5b029 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -82,6 +82,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x04CA, 0x3004) }, { USB_DEVICE(0x04CA, 0x3005) }, { USB_DEVICE(0x04CA, 0x3006) }, + { USB_DEVICE(0x04CA, 0x3007) }, { USB_DEVICE(0x04CA, 0x3008) }, { USB_DEVICE(0x04CA, 0x300b) }, { USB_DEVICE(0x13d3, 0x3362) }, @@ -127,6 +128,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h index 7399303d7d99..9e81a3d01d2b 100644 --- a/drivers/bluetooth/btmrvl_drv.h +++ b/drivers/bluetooth/btmrvl_drv.h @@ -66,6 +66,7 @@ struct btmrvl_adapter { u8 hs_state; u8 wakeup_tries; wait_queue_head_t cmd_wait_q; + wait_queue_head_t event_hs_wait_q; u8 cmd_complete; bool is_suspended; }; diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 1e0320af00c6..49d20989b45a 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -112,6 +112,7 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb) adapter->hs_state = HS_ACTIVATED; if (adapter->psmode) adapter->ps_state = PS_SLEEP; + wake_up_interruptible(&adapter->event_hs_wait_q); BT_DBG("HS ACTIVATED!"); } else { BT_DBG("HS Enable failed"); @@ -251,11 +252,31 @@ EXPORT_SYMBOL_GPL(btmrvl_enable_ps); int btmrvl_enable_hs(struct btmrvl_private *priv) { + struct btmrvl_adapter *adapter = priv->adapter; int ret; ret = btmrvl_send_sync_cmd(priv, BT_CMD_HOST_SLEEP_ENABLE, NULL, 0); - if (ret) + if (ret) { BT_ERR("Host sleep enable command failed\n"); + return ret; + } + + ret = wait_event_interruptible_timeout(adapter->event_hs_wait_q, + adapter->hs_state, + msecs_to_jiffies(WAIT_UNTIL_HS_STATE_CHANGED)); + if (ret < 0) { + BT_ERR("event_hs_wait_q terminated (%d): %d,%d,%d", + ret, adapter->hs_state, adapter->ps_state, + adapter->wakeup_tries); + } else if (!ret) { + BT_ERR("hs_enable timeout: %d,%d,%d", adapter->hs_state, + adapter->ps_state, adapter->wakeup_tries); + ret = -ETIMEDOUT; + } else { + BT_DBG("host sleep enabled: %d,%d,%d", adapter->hs_state, + adapter->ps_state, adapter->wakeup_tries); + ret = 0; + } return ret; } @@ -341,6 +362,7 @@ static void btmrvl_init_adapter(struct btmrvl_private *priv) priv->adapter->ps_state = PS_AWAKE; init_waitqueue_head(&priv->adapter->cmd_wait_q); + init_waitqueue_head(&priv->adapter->event_hs_wait_q); } static void btmrvl_free_adapter(struct btmrvl_private *priv) @@ -648,6 +670,7 @@ int btmrvl_remove_card(struct btmrvl_private *priv) hdev = priv->btmrvl_dev.hcidev; wake_up_interruptible(&priv->adapter->cmd_wait_q); + wake_up_interruptible(&priv->adapter->event_hs_wait_q); kthread_stop(priv->main_thread.task); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index baeaaed299e4..e00c3f84a4cf 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -149,6 +149,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, @@ -308,6 +309,9 @@ static void btusb_intr_complete(struct urb *urb) BT_ERR("%s corrupted event packet", hdev->name); hdev->stat.err_rx++; } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_INTR_RUNNING, &data->flags)) @@ -396,6 +400,9 @@ static void btusb_bulk_complete(struct urb *urb) BT_ERR("%s corrupted ACL packet", hdev->name); hdev->stat.err_rx++; } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_BULK_RUNNING, &data->flags)) @@ -490,6 +497,9 @@ static void btusb_isoc_complete(struct urb *urb) hdev->stat.err_rx++; } } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_ISOC_RUNNING, &data->flags)) @@ -1478,10 +1488,8 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_BCM92035) hdev->setup = btusb_setup_bcm92035; - if (id->driver_info & BTUSB_INTEL) { - usb_enable_autosuspend(data->udev); + if (id->driver_info & BTUSB_INTEL) hdev->setup = btusb_setup_intel; - } /* Interface numbers are hardcoded in the specification */ data->isoc = usb_ifnum_to_if(data->udev, 1); diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index f6f497450560..56519927479f 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -237,7 +237,7 @@ static void h5_pkt_cull(struct h5 *h5) break; to_remove--; - seq = (seq - 1) % 8; + seq = (seq - 1) & 0x07; } if (seq != h5->rx_ack) @@ -406,6 +406,7 @@ static int h5_rx_3wire_hdr(struct hci_uart *hu, unsigned char c) H5_HDR_PKT_TYPE(hdr) != HCI_3WIRE_LINK_PKT) { BT_ERR("Non-link packet received in non-active state"); h5_reset_rx(h5); + return 0; } h5->rx_func = h5_rx_payload; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 6e06f6f69152..77af52f0e3b1 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -118,10 +118,6 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu) int hci_uart_tx_wakeup(struct hci_uart *hu) { - struct tty_struct *tty = hu->tty; - struct hci_dev *hdev = hu->hdev; - struct sk_buff *skb; - if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) { set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state); return 0; @@ -129,6 +125,22 @@ int hci_uart_tx_wakeup(struct hci_uart *hu) BT_DBG(""); + schedule_work(&hu->write_work); + + return 0; +} + +static void hci_uart_write_work(struct work_struct *work) +{ + struct hci_uart *hu = container_of(work, struct hci_uart, write_work); + struct tty_struct *tty = hu->tty; + struct hci_dev *hdev = hu->hdev; + struct sk_buff *skb; + + /* REVISIT: should we cope with bad skbs or ->write() returning + * and error value ? + */ + restart: clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state); @@ -153,7 +165,6 @@ restart: goto restart; clear_bit(HCI_UART_SENDING, &hu->tx_state); - return 0; } static void hci_uart_init_work(struct work_struct *work) @@ -281,6 +292,7 @@ static int hci_uart_tty_open(struct tty_struct *tty) tty->receive_room = 65536; INIT_WORK(&hu->init_ready, hci_uart_init_work); + INIT_WORK(&hu->write_work, hci_uart_write_work); spin_lock_init(&hu->rx_lock); @@ -318,6 +330,8 @@ static void hci_uart_tty_close(struct tty_struct *tty) if (hdev) hci_uart_close(hdev); + cancel_work_sync(&hu->write_work); + if (test_and_clear_bit(HCI_UART_PROTO_SET, &hu->flags)) { if (hdev) { if (test_bit(HCI_UART_REGISTERED, &hu->flags)) diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index fffa61ff5cb1..12df101ca942 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -68,6 +68,7 @@ struct hci_uart { unsigned long hdev_flags; struct work_struct init_ready; + struct work_struct write_work; struct hci_uart_proto *proto; void *priv; diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index 725c46162bbd..372ae72cce34 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -222,12 +222,6 @@ static int mvebu_mbus_window_conflicts(struct mvebu_mbus_state *mbus, */ if ((u64)base < wend && end > wbase) return 0; - - /* - * Check if target/attribute conflicts - */ - if (target == wtarget && attr == wattr) - return 0; } return 1; diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index 974321a2508d..14790304b84b 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -345,7 +345,6 @@ out: free_irq(apbs[i].irq, &dummy); iounmap(apbs[i].RamIO); } - pci_disable_device(dev); return ret; } diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c index d915707d2ba1..93dcad0c1cbe 100644 --- a/drivers/char/i8k.c +++ b/drivers/char/i8k.c @@ -138,7 +138,9 @@ static int i8k_smm(struct smm_regs *regs) if (!alloc_cpumask_var(&old_mask, GFP_KERNEL)) return -ENOMEM; cpumask_copy(old_mask, ¤t->cpus_allowed); - set_cpus_allowed_ptr(current, cpumask_of(0)); + rc = set_cpus_allowed_ptr(current, cpumask_of(0)); + if (rc) + goto out; if (smp_processor_id() != 0) { rc = -EBUSY; goto out; diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c index f5e4cd7617f6..61e71616689b 100644 --- a/drivers/char/ipmi/ipmi_bt_sm.c +++ b/drivers/char/ipmi/ipmi_bt_sm.c @@ -352,7 +352,7 @@ static inline void write_all_bytes(struct si_sm_data *bt) static inline int read_all_bytes(struct si_sm_data *bt) { - unsigned char i; + unsigned int i; /* * length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode. diff --git a/drivers/char/ipmi/ipmi_kcs_sm.c b/drivers/char/ipmi/ipmi_kcs_sm.c index 6a4bdc18955a..8c25f596808a 100644 --- a/drivers/char/ipmi/ipmi_kcs_sm.c +++ b/drivers/char/ipmi/ipmi_kcs_sm.c @@ -251,8 +251,9 @@ static inline int check_obf(struct si_sm_data *kcs, unsigned char status, if (!GET_STATUS_OBF(status)) { kcs->obf_timeout -= time; if (kcs->obf_timeout < 0) { - start_error_recovery(kcs, "OBF not ready in time"); - return 1; + kcs->obf_timeout = OBF_RETRY_TIMEOUT; + start_error_recovery(kcs, "OBF not ready in time"); + return 1; } return 0; } diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 03f41896d090..8b4fa2c4e661 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -249,6 +249,9 @@ struct smi_info { /* The timer for this si. */ struct timer_list si_timer; + /* This flag is set, if the timer is running (timer_pending() isn't enough) */ + bool timer_running; + /* The time (in jiffies) the last timeout occurred at. */ unsigned long last_timeout_jiffies; @@ -435,6 +438,13 @@ static void start_clear_flags(struct smi_info *smi_info) smi_info->si_state = SI_CLEARING_FLAGS; } +static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val) +{ + smi_info->last_timeout_jiffies = jiffies; + mod_timer(&smi_info->si_timer, new_val); + smi_info->timer_running = true; +} + /* * When we have a situtaion where we run out of memory and cannot * allocate messages, we just leave them in the BMC and run the system @@ -447,8 +457,7 @@ static inline void disable_si_irq(struct smi_info *smi_info) start_disable_irq(smi_info); smi_info->interrupt_disabled = 1; if (!atomic_read(&smi_info->stop_operation)) - mod_timer(&smi_info->si_timer, - jiffies + SI_TIMEOUT_JIFFIES); + smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES); } } @@ -908,15 +917,7 @@ static void sender(void *send_info, list_add_tail(&msg->link, &smi_info->xmit_msgs); if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL) { - /* - * last_timeout_jiffies is updated here to avoid - * smi_timeout() handler passing very large time_diff - * value to smi_event_handler() that causes - * the send command to abort. - */ - smi_info->last_timeout_jiffies = jiffies; - - mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES); + smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES); if (smi_info->thread) wake_up_process(smi_info->thread); @@ -1005,6 +1006,17 @@ static int ipmi_thread(void *data) spin_lock_irqsave(&(smi_info->si_lock), flags); smi_result = smi_event_handler(smi_info, 0); + + /* + * If the driver is doing something, there is a possible + * race with the timer. If the timer handler see idle, + * and the thread here sees something else, the timer + * handler won't restart the timer even though it is + * required. So start it here if necessary. + */ + if (smi_result != SI_SM_IDLE && !smi_info->timer_running) + smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES); + spin_unlock_irqrestore(&(smi_info->si_lock), flags); busy_wait = ipmi_thread_busy_wait(smi_result, smi_info, &busy_until); @@ -1074,10 +1086,6 @@ static void smi_timeout(unsigned long data) * SI_USEC_PER_JIFFY); smi_result = smi_event_handler(smi_info, time_diff); - spin_unlock_irqrestore(&(smi_info->si_lock), flags); - - smi_info->last_timeout_jiffies = jiffies_now; - if ((smi_info->irq) && (!smi_info->interrupt_disabled)) { /* Running with interrupts, only do long timeouts. */ timeout = jiffies + SI_TIMEOUT_JIFFIES; @@ -1099,7 +1107,10 @@ static void smi_timeout(unsigned long data) do_mod_timer: if (smi_result != SI_SM_IDLE) - mod_timer(&(smi_info->si_timer), timeout); + smi_mod_timer(smi_info, timeout); + else + smi_info->timer_running = false; + spin_unlock_irqrestore(&(smi_info->si_lock), flags); } static irqreturn_t si_irq_handler(int irq, void *data) @@ -1147,8 +1158,7 @@ static int smi_start_processing(void *send_info, /* Set up the timer that drives the interface. */ setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi); - new_smi->last_timeout_jiffies = jiffies; - mod_timer(&new_smi->si_timer, jiffies + SI_TIMEOUT_JIFFIES); + smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES); /* * Check if the user forcefully enabled the daemon. diff --git a/drivers/char/random.c b/drivers/char/random.c index 429b75bb60e8..8a64dbeae7b1 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1063,8 +1063,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out) * pool while mixing, and hash one final time. */ sha_transform(hash.w, extract, workspace); - memset(extract, 0, sizeof(extract)); - memset(workspace, 0, sizeof(workspace)); + memzero_explicit(extract, sizeof(extract)); + memzero_explicit(workspace, sizeof(workspace)); /* * In case the hash function has some recognizable output @@ -1076,7 +1076,7 @@ static void extract_buf(struct entropy_store *r, __u8 *out) hash.w[2] ^= rol32(hash.w[2], 16); memcpy(out, &hash, EXTRACT_SIZE); - memset(&hash, 0, sizeof(hash)); + memzero_explicit(&hash, sizeof(hash)); } static ssize_t extract_entropy(struct entropy_store *r, void *buf, @@ -1124,7 +1124,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf, } /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); + memzero_explicit(tmp, sizeof(tmp)); return ret; } @@ -1162,7 +1162,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, } /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); + memzero_explicit(tmp, sizeof(tmp)); return ret; } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 62e10fd1e1cb..6af17002a115 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -491,11 +491,10 @@ static int tpm_startup(struct tpm_chip *chip, __be16 startup_type) int tpm_get_timeouts(struct tpm_chip *chip) { struct tpm_cmd_t tpm_cmd; - struct timeout_t *timeout_cap; + unsigned long new_timeout[4]; + unsigned long old_timeout[4]; struct duration_t *duration_cap; ssize_t rc; - u32 timeout; - unsigned int scale = 1; tpm_cmd.header.in = tpm_getcap_header; tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP; @@ -529,25 +528,46 @@ int tpm_get_timeouts(struct tpm_chip *chip) != sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32)) return -EINVAL; - timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout; - /* Don't overwrite default if value is 0 */ - timeout = be32_to_cpu(timeout_cap->a); - if (timeout && timeout < 1000) { - /* timeouts in msec rather usec */ - scale = 1000; - chip->vendor.timeout_adjusted = true; + old_timeout[0] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.a); + old_timeout[1] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.b); + old_timeout[2] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.c); + old_timeout[3] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.d); + memcpy(new_timeout, old_timeout, sizeof(new_timeout)); + + /* + * Provide ability for vendor overrides of timeout values in case + * of misreporting. + */ + if (chip->ops->update_timeouts != NULL) + chip->vendor.timeout_adjusted = + chip->ops->update_timeouts(chip, new_timeout); + + if (!chip->vendor.timeout_adjusted) { + /* Don't overwrite default if value is 0 */ + if (new_timeout[0] != 0 && new_timeout[0] < 1000) { + int i; + + /* timeouts in msec rather usec */ + for (i = 0; i != ARRAY_SIZE(new_timeout); i++) + new_timeout[i] *= 1000; + chip->vendor.timeout_adjusted = true; + } + } + + /* Report adjusted timeouts */ + if (chip->vendor.timeout_adjusted) { + 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], + old_timeout[2], new_timeout[2], + old_timeout[3], new_timeout[3]); } - if (timeout) - chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale); - timeout = be32_to_cpu(timeout_cap->b); - if (timeout) - chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale); - timeout = be32_to_cpu(timeout_cap->c); - if (timeout) - chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale); - timeout = be32_to_cpu(timeout_cap->d); - if (timeout) - chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale); + + chip->vendor.timeout_a = usecs_to_jiffies(new_timeout[0]); + chip->vendor.timeout_b = usecs_to_jiffies(new_timeout[1]); + chip->vendor.timeout_c = usecs_to_jiffies(new_timeout[2]); + chip->vendor.timeout_d = usecs_to_jiffies(new_timeout[3]); duration: tpm_cmd.header.in = tpm_getcap_header; @@ -991,13 +1011,13 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max) int err, total = 0, retries = 5; u8 *dest = out; + if (!out || !num_bytes || max > TPM_MAX_RNG_DATA) + return -EINVAL; + chip = tpm_chip_find_get(chip_num); if (chip == NULL) return -ENODEV; - if (!out || !num_bytes || max > TPM_MAX_RNG_DATA) - return -EINVAL; - do { tpm_cmd.header.in = tpm_getrandom_header; tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes); @@ -1016,6 +1036,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max) num_bytes -= recd; } while (retries-- && total < max); + tpm_chip_put(chip); return total ? total : -EIO; } EXPORT_SYMBOL_GPL(tpm_get_random); @@ -1095,7 +1116,7 @@ struct tpm_chip *tpm_register_hardware(struct device *dev, goto del_misc; if (tpm_add_ppi(&dev->kobj)) - goto del_misc; + goto del_sysfs; chip->bios_dir = tpm_bios_log_setup(chip->devname); @@ -1106,6 +1127,8 @@ struct tpm_chip *tpm_register_hardware(struct device *dev, return chip; +del_sysfs: + tpm_sysfs_del_device(chip); del_misc: tpm_dev_del_device(chip); put_device: diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c index 5b0dd8ef74c0..be9af2e6ca5a 100644 --- a/drivers/char/tpm/tpm_i2c_stm_st33.c +++ b/drivers/char/tpm/tpm_i2c_stm_st33.c @@ -715,6 +715,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) } tpm_get_timeouts(chip); + tpm_do_selftest(chip); dev_info(chip->dev, "TPM I2C Initialized\n"); return 0; diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c index b3ea223585bd..61dcc8011ec7 100644 --- a/drivers/char/tpm/tpm_ppi.c +++ b/drivers/char/tpm/tpm_ppi.c @@ -328,13 +328,11 @@ int tpm_add_ppi(struct kobject *parent) /* Cache TPM ACPI handle and version string */ acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX, ppi_callback, NULL, NULL, &tpm_ppi_handle); - if (tpm_ppi_handle == NULL) - return -ENODEV; - - return sysfs_create_group(parent, &ppi_attr_grp); + return tpm_ppi_handle ? sysfs_create_group(parent, &ppi_attr_grp) : 0; } void tpm_remove_ppi(struct kobject *parent) { - sysfs_remove_group(parent, &ppi_attr_grp); + if (tpm_ppi_handle) + sysfs_remove_group(parent, &ppi_attr_grp); } diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index a9ed2270c25d..2c46734b266d 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -373,6 +373,36 @@ out_err: return rc; } +struct tis_vendor_timeout_override { + u32 did_vid; + unsigned long timeout_us[4]; +}; + +static const struct tis_vendor_timeout_override vendor_timeout_overrides[] = { + /* Atmel 3204 */ + { 0x32041114, { (TIS_SHORT_TIMEOUT*1000), (TIS_LONG_TIMEOUT*1000), + (TIS_SHORT_TIMEOUT*1000), (TIS_SHORT_TIMEOUT*1000) } }, +}; + +static bool tpm_tis_update_timeouts(struct tpm_chip *chip, + unsigned long *timeout_cap) +{ + int i; + u32 did_vid; + + did_vid = ioread32(chip->vendor.iobase + TPM_DID_VID(0)); + + for (i = 0; i != ARRAY_SIZE(vendor_timeout_overrides); i++) { + if (vendor_timeout_overrides[i].did_vid != did_vid) + continue; + memcpy(timeout_cap, vendor_timeout_overrides[i].timeout_us, + sizeof(vendor_timeout_overrides[i].timeout_us)); + return true; + } + + return false; +} + /* * Early probing for iTPM with STS_DATA_EXPECT flaw. * Try sending command without itpm flag set and if that @@ -437,6 +467,7 @@ static const struct tpm_class_ops tpm_tis = { .recv = tpm_tis_recv, .send = tpm_tis_send, .cancel = tpm_tis_ready, + .update_timeouts = tpm_tis_update_timeouts, .req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_canceled = tpm_tis_req_canceled, diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c index 00a3abe103a5..611b936ecffe 100644 --- a/drivers/clk/clk-s2mps11.c +++ b/drivers/clk/clk-s2mps11.c @@ -130,7 +130,7 @@ static struct device_node *s2mps11_clk_parse_dt(struct platform_device *pdev) int i; if (!iodev->dev->of_node) - return NULL; + return ERR_PTR(-EINVAL); clk_np = of_find_node_by_name(iodev->dev->of_node, "clocks"); if (!clk_np) { @@ -190,16 +190,13 @@ static int s2mps11_clk_probe(struct platform_device *pdev) goto err_reg; } - s2mps11_clk->lookup = devm_kzalloc(&pdev->dev, - sizeof(struct clk_lookup), GFP_KERNEL); + s2mps11_clk->lookup = clkdev_alloc(s2mps11_clk->clk, + s2mps11_name(s2mps11_clk), NULL); if (!s2mps11_clk->lookup) { ret = -ENOMEM; goto err_lup; } - s2mps11_clk->lookup->con_id = s2mps11_name(s2mps11_clk); - s2mps11_clk->lookup->clk = s2mps11_clk->clk; - clkdev_add(s2mps11_clk->lookup); } diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index c42e608af6bb..f9c4632d4dd3 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1487,6 +1487,7 @@ static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long even static void clk_change_rate(struct clk *clk) { struct clk *child; + struct hlist_node *tmp; unsigned long old_rate; unsigned long best_parent_rate = 0; bool skip_set_rate = false; @@ -1525,7 +1526,11 @@ static void clk_change_rate(struct clk *clk) if (clk->notifier_count && old_rate != clk->rate) __clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate); - hlist_for_each_entry(child, &clk->children, child_node) { + /* + * Use safe iteration, as change_rate can actually swap parents + * for certain clock types. + */ + hlist_for_each_entry_safe(child, tmp, &clk->children, child_node) { /* Skip children who will be reparented to another clock */ if (child->new_parent && child->new_parent != clk) continue; @@ -1977,9 +1982,28 @@ struct clk *__clk_register(struct device *dev, struct clk_hw *hw) } EXPORT_SYMBOL_GPL(__clk_register); -static int _clk_register(struct device *dev, struct clk_hw *hw, struct clk *clk) +/** + * clk_register - allocate a new clock, register it and return an opaque cookie + * @dev: device that is registering this clock + * @hw: link to hardware-specific clock data + * + * clk_register is the primary interface for populating the clock tree with new + * clock nodes. It returns a pointer to the newly allocated struct clk which + * cannot be dereferenced by driver code but may be used in conjuction with the + * rest of the clock API. In the event of an error clk_register will return an + * error code; drivers must test for an error code after calling clk_register. + */ +struct clk *clk_register(struct device *dev, struct clk_hw *hw) { int i, ret; + struct clk *clk; + + clk = kzalloc(sizeof(*clk), GFP_KERNEL); + if (!clk) { + pr_err("%s: could not allocate clk\n", __func__); + ret = -ENOMEM; + goto fail_out; + } clk->name = kstrdup(hw->init->name, GFP_KERNEL); if (!clk->name) { @@ -2019,7 +2043,7 @@ static int _clk_register(struct device *dev, struct clk_hw *hw, struct clk *clk) ret = __clk_init(dev, clk); if (!ret) - return 0; + return clk; fail_parent_names_copy: while (--i >= 0) @@ -2028,36 +2052,6 @@ fail_parent_names_copy: fail_parent_names: kfree(clk->name); fail_name: - return ret; -} - -/** - * clk_register - allocate a new clock, register it and return an opaque cookie - * @dev: device that is registering this clock - * @hw: link to hardware-specific clock data - * - * clk_register is the primary interface for populating the clock tree with new - * clock nodes. It returns a pointer to the newly allocated struct clk which - * cannot be dereferenced by driver code but may be used in conjuction with the - * rest of the clock API. In the event of an error clk_register will return an - * error code; drivers must test for an error code after calling clk_register. - */ -struct clk *clk_register(struct device *dev, struct clk_hw *hw) -{ - int ret; - struct clk *clk; - - clk = kzalloc(sizeof(*clk), GFP_KERNEL); - if (!clk) { - pr_err("%s: could not allocate clk\n", __func__); - ret = -ENOMEM; - goto fail_out; - } - - ret = _clk_register(dev, hw, clk); - if (!ret) - return clk; - kfree(clk); fail_out: return ERR_PTR(ret); @@ -2144,9 +2138,10 @@ void clk_unregister(struct clk *clk) if (!hlist_empty(&clk->children)) { struct clk *child; + struct hlist_node *t; /* Reparent all children to the orphan list. */ - hlist_for_each_entry(child, &clk->children, child_node) + hlist_for_each_entry_safe(child, t, &clk->children, child_node) clk_set_parent(child, NULL); } @@ -2166,7 +2161,7 @@ EXPORT_SYMBOL_GPL(clk_unregister); static void devm_clk_release(struct device *dev, void *res) { - clk_unregister(res); + clk_unregister(*(struct clk **)res); } /** @@ -2181,18 +2176,18 @@ static void devm_clk_release(struct device *dev, void *res) struct clk *devm_clk_register(struct device *dev, struct clk_hw *hw) { struct clk *clk; - int ret; + struct clk **clkp; - clk = devres_alloc(devm_clk_release, sizeof(*clk), GFP_KERNEL); - if (!clk) + clkp = devres_alloc(devm_clk_release, sizeof(*clkp), GFP_KERNEL); + if (!clkp) return ERR_PTR(-ENOMEM); - ret = _clk_register(dev, hw, clk); - if (!ret) { - devres_add(dev, clk); + clk = clk_register(dev, hw); + if (!IS_ERR(clk)) { + *clkp = clk; + devres_add(dev, clkp); } else { - devres_free(clk); - clk = ERR_PTR(ret); + devres_free(clkp); } return clk; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index 00f878a04d3f..0996a3a39855 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -55,7 +55,7 @@ static int clk_rcg2_is_enabled(struct clk_hw *hw) if (ret) return ret; - return (cmd & CMD_ROOT_OFF) != 0; + return (cmd & CMD_ROOT_OFF) == 0; } static u8 clk_rcg2_get_parent(struct clk_hw *hw) diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c index f9b59c7e48e9..f3c95d648a53 100644 --- a/drivers/clk/qcom/mmcc-msm8960.c +++ b/drivers/clk/qcom/mmcc-msm8960.c @@ -37,6 +37,8 @@ #define P_PLL2 2 #define P_PLL3 3 +#define F_MN(f, s, _m, _n) { .freq = f, .src = s, .m = _m, .n = _n } + static u8 mmcc_pxo_pll8_pll2_map[] = { [P_PXO] = 0, [P_PLL8] = 2, @@ -58,8 +60,8 @@ static u8 mmcc_pxo_pll8_pll2_pll3_map[] = { static const char *mmcc_pxo_pll8_pll2_pll3[] = { "pxo", - "pll2", "pll8_vote", + "pll2", "pll3", }; @@ -709,18 +711,18 @@ static struct clk_branch csiphy2_timer_clk = { }; static struct freq_tbl clk_tbl_gfx2d[] = { - { 27000000, P_PXO, 1, 0 }, - { 48000000, P_PLL8, 1, 8 }, - { 54857000, P_PLL8, 1, 7 }, - { 64000000, P_PLL8, 1, 6 }, - { 76800000, P_PLL8, 1, 5 }, - { 96000000, P_PLL8, 1, 4 }, - { 128000000, P_PLL8, 1, 3 }, - { 145455000, P_PLL2, 2, 11 }, - { 160000000, P_PLL2, 1, 5 }, - { 177778000, P_PLL2, 2, 9 }, - { 200000000, P_PLL2, 1, 4 }, - { 228571000, P_PLL2, 2, 7 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54857000, P_PLL8, 1, 7), + F_MN( 64000000, P_PLL8, 1, 6), + F_MN( 76800000, P_PLL8, 1, 5), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(128000000, P_PLL8, 1, 3), + F_MN(145455000, P_PLL2, 2, 11), + F_MN(160000000, P_PLL2, 1, 5), + F_MN(177778000, P_PLL2, 2, 9), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228571000, P_PLL2, 2, 7), { } }; @@ -841,22 +843,22 @@ static struct clk_branch gfx2d1_clk = { }; static struct freq_tbl clk_tbl_gfx3d[] = { - { 27000000, P_PXO, 1, 0 }, - { 48000000, P_PLL8, 1, 8 }, - { 54857000, P_PLL8, 1, 7 }, - { 64000000, P_PLL8, 1, 6 }, - { 76800000, P_PLL8, 1, 5 }, - { 96000000, P_PLL8, 1, 4 }, - { 128000000, P_PLL8, 1, 3 }, - { 145455000, P_PLL2, 2, 11 }, - { 160000000, P_PLL2, 1, 5 }, - { 177778000, P_PLL2, 2, 9 }, - { 200000000, P_PLL2, 1, 4 }, - { 228571000, P_PLL2, 2, 7 }, - { 266667000, P_PLL2, 1, 3 }, - { 300000000, P_PLL3, 1, 4 }, - { 320000000, P_PLL2, 2, 5 }, - { 400000000, P_PLL2, 1, 2 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54857000, P_PLL8, 1, 7), + F_MN( 64000000, P_PLL8, 1, 6), + F_MN( 76800000, P_PLL8, 1, 5), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(128000000, P_PLL8, 1, 3), + F_MN(145455000, P_PLL2, 2, 11), + F_MN(160000000, P_PLL2, 1, 5), + F_MN(177778000, P_PLL2, 2, 9), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228571000, P_PLL2, 2, 7), + F_MN(266667000, P_PLL2, 1, 3), + F_MN(300000000, P_PLL3, 1, 4), + F_MN(320000000, P_PLL2, 2, 5), + F_MN(400000000, P_PLL2, 1, 2), { } }; @@ -896,7 +898,7 @@ static struct clk_dyn_rcg gfx3d_src = { .hw.init = &(struct clk_init_data){ .name = "gfx3d_src", .parent_names = mmcc_pxo_pll8_pll2_pll3, - .num_parents = 3, + .num_parents = 4, .ops = &clk_dyn_rcg_ops, }, }, @@ -994,7 +996,7 @@ static struct clk_rcg jpegd_src = { .ns_reg = 0x00ac, .p = { .pre_div_shift = 12, - .pre_div_width = 2, + .pre_div_width = 4, }, .s = { .src_sel_shift = 0, @@ -1114,7 +1116,7 @@ static struct clk_branch mdp_lut_clk = { .enable_reg = 0x016c, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .parent_names = (const char *[]){ "mdp_clk" }, + .parent_names = (const char *[]){ "mdp_src" }, .num_parents = 1, .name = "mdp_lut_clk", .ops = &clk_branch_ops, @@ -1208,7 +1210,7 @@ static struct clk_branch rot_clk = { static u8 mmcc_pxo_hdmi_map[] = { [P_PXO] = 0, - [P_HDMI_PLL] = 2, + [P_HDMI_PLL] = 3, }; static const char *mmcc_pxo_hdmi[] = { @@ -1341,15 +1343,15 @@ static struct clk_branch hdmi_app_clk = { }; static struct freq_tbl clk_tbl_vcodec[] = { - { 27000000, P_PXO, 1, 0 }, - { 32000000, P_PLL8, 1, 12 }, - { 48000000, P_PLL8, 1, 8 }, - { 54860000, P_PLL8, 1, 7 }, - { 96000000, P_PLL8, 1, 4 }, - { 133330000, P_PLL2, 1, 6 }, - { 200000000, P_PLL2, 1, 4 }, - { 228570000, P_PLL2, 2, 7 }, - { 266670000, P_PLL2, 1, 3 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 32000000, P_PLL8, 1, 12), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54860000, P_PLL8, 1, 7), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(133330000, P_PLL2, 1, 6), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228570000, P_PLL2, 2, 7), + F_MN(266670000, P_PLL2, 1, 3), { } }; diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c index c95774514b81..6a0ae77d1939 100644 --- a/drivers/clk/qcom/mmcc-msm8974.c +++ b/drivers/clk/qcom/mmcc-msm8974.c @@ -169,6 +169,7 @@ static struct clk_pll mmpll0 = { .config_reg = 0x0014, .mode_reg = 0x0000, .status_reg = 0x001c, + .status_bit = 17, .clkr.hw.init = &(struct clk_init_data){ .name = "mmpll0", .parent_names = (const char *[]){ "xo" }, @@ -192,9 +193,10 @@ static struct clk_pll mmpll1 = { .l_reg = 0x0044, .m_reg = 0x0048, .n_reg = 0x004c, - .config_reg = 0x0054, + .config_reg = 0x0050, .mode_reg = 0x0040, .status_reg = 0x005c, + .status_bit = 17, .clkr.hw.init = &(struct clk_init_data){ .name = "mmpll1", .parent_names = (const char *[]){ "xo" }, @@ -218,7 +220,7 @@ static struct clk_pll mmpll2 = { .l_reg = 0x4104, .m_reg = 0x4108, .n_reg = 0x410c, - .config_reg = 0x4114, + .config_reg = 0x4110, .mode_reg = 0x4100, .status_reg = 0x411c, .clkr.hw.init = &(struct clk_init_data){ @@ -233,9 +235,10 @@ static struct clk_pll mmpll3 = { .l_reg = 0x0084, .m_reg = 0x0088, .n_reg = 0x008c, - .config_reg = 0x0094, + .config_reg = 0x0090, .mode_reg = 0x0080, .status_reg = 0x009c, + .status_bit = 17, .clkr.hw.init = &(struct clk_init_data){ .name = "mmpll3", .parent_names = (const char *[]){ "xo" }, @@ -2318,7 +2321,7 @@ static const struct pll_config mmpll1_config = { .vco_val = 0x0, .vco_mask = 0x3 << 20, .pre_div_val = 0x0, - .pre_div_mask = 0x3 << 12, + .pre_div_mask = 0x7 << 12, .post_div_val = 0x0, .post_div_mask = 0x3 << 8, .mn_ena_mask = BIT(24), @@ -2332,7 +2335,7 @@ static struct pll_config mmpll3_config = { .vco_val = 0x0, .vco_mask = 0x3 << 20, .pre_div_val = 0x0, - .pre_div_mask = 0x3 << 12, + .pre_div_mask = 0x7 << 12, .post_div_val = 0x0, .post_div_mask = 0x3 << 8, .mn_ena_mask = BIT(24), diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c index c2d204315546..125eba86c844 100644 --- a/drivers/clk/spear/spear3xx_clock.c +++ b/drivers/clk/spear/spear3xx_clock.c @@ -211,7 +211,7 @@ static inline void spear310_clk_init(void) { } /* array of all spear 320 clock lookups */ #ifdef CONFIG_MACH_SPEAR320 -#define SPEAR320_CONTROL_REG (soc_config_base + 0x0000) +#define SPEAR320_CONTROL_REG (soc_config_base + 0x0010) #define SPEAR320_EXT_CTRL_REG (soc_config_base + 0x0018) #define SPEAR320_UARTX_PCLK_MASK 0x1 diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c index 0d20241e0770..e1769addf435 100644 --- a/drivers/clk/tegra/clk-pll.c +++ b/drivers/clk/tegra/clk-pll.c @@ -1718,7 +1718,7 @@ struct clk *tegra_clk_register_plle_tegra114(const char *name, "pll_re_vco"); } else { val_aux &= ~(PLLE_AUX_PLLRE_SEL | PLLE_AUX_PLLP_SEL); - pll_writel(val, pll_params->aux_reg, pll); + pll_writel(val_aux, pll_params->aux_reg, pll); } clk = _tegra_clk_register_pll(pll, name, parent_name, flags, diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c index 166e02f16c8a..cc37c342c4cb 100644 --- a/drivers/clk/tegra/clk-tegra124.c +++ b/drivers/clk/tegra/clk-tegra124.c @@ -764,7 +764,6 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_sdmmc2_8] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true }, [tegra_clk_i2s1] = { .dt_id = TEGRA124_CLK_I2S1, .present = true }, [tegra_clk_i2c1] = { .dt_id = TEGRA124_CLK_I2C1, .present = true }, - [tegra_clk_ndflash] = { .dt_id = TEGRA124_CLK_NDFLASH, .present = true }, [tegra_clk_sdmmc1_8] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true }, [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true }, [tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true }, @@ -809,7 +808,6 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_trace] = { .dt_id = TEGRA124_CLK_TRACE, .present = true }, [tegra_clk_soc_therm] = { .dt_id = TEGRA124_CLK_SOC_THERM, .present = true }, [tegra_clk_dtv] = { .dt_id = TEGRA124_CLK_DTV, .present = true }, - [tegra_clk_ndspeed] = { .dt_id = TEGRA124_CLK_NDSPEED, .present = true }, [tegra_clk_i2cslow] = { .dt_id = TEGRA124_CLK_I2CSLOW, .present = true }, [tegra_clk_dsib] = { .dt_id = TEGRA124_CLK_DSIB, .present = true }, [tegra_clk_tsec] = { .dt_id = TEGRA124_CLK_TSEC, .present = true }, @@ -952,7 +950,6 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_clk_out_3_mux] = { .dt_id = TEGRA124_CLK_CLK_OUT_3_MUX, .present = true }, [tegra_clk_dsia_mux] = { .dt_id = TEGRA124_CLK_DSIA_MUX, .present = true }, [tegra_clk_dsib_mux] = { .dt_id = TEGRA124_CLK_DSIB_MUX, .present = true }, - [tegra_clk_uarte] = { .dt_id = TEGRA124_CLK_UARTE, .present = true }, }; static struct tegra_devclk devclks[] __initdata = { diff --git a/drivers/clk/ti/clk-44xx.c b/drivers/clk/ti/clk-44xx.c index ae00218b5da3..02517a8206bd 100644 --- a/drivers/clk/ti/clk-44xx.c +++ b/drivers/clk/ti/clk-44xx.c @@ -222,7 +222,6 @@ static struct ti_dt_clk omap44xx_clks[] = { DT_CLK(NULL, "auxclk5_src_ck", "auxclk5_src_ck"), DT_CLK(NULL, "auxclk5_ck", "auxclk5_ck"), DT_CLK(NULL, "auxclkreq5_ck", "auxclkreq5_ck"), - DT_CLK("50000000.gpmc", "fck", "dummy_ck"), DT_CLK("omap_i2c.1", "ick", "dummy_ck"), DT_CLK("omap_i2c.2", "ick", "dummy_ck"), DT_CLK("omap_i2c.3", "ick", "dummy_ck"), diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c index 0ef9f581286b..08f3d1b915b3 100644 --- a/drivers/clk/ti/clk-54xx.c +++ b/drivers/clk/ti/clk-54xx.c @@ -182,7 +182,6 @@ static struct ti_dt_clk omap54xx_clks[] = { DT_CLK(NULL, "auxclk3_src_ck", "auxclk3_src_ck"), DT_CLK(NULL, "auxclk3_ck", "auxclk3_ck"), DT_CLK(NULL, "auxclkreq3_ck", "auxclkreq3_ck"), - DT_CLK(NULL, "gpmc_ck", "dummy_ck"), DT_CLK("omap_i2c.1", "ick", "dummy_ck"), DT_CLK("omap_i2c.2", "ick", "dummy_ck"), DT_CLK("omap_i2c.3", "ick", "dummy_ck"), diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c index 9977653f2d63..f7e40734c819 100644 --- a/drivers/clk/ti/clk-7xx.c +++ b/drivers/clk/ti/clk-7xx.c @@ -262,7 +262,6 @@ static struct ti_dt_clk dra7xx_clks[] = { DT_CLK(NULL, "vip1_gclk_mux", "vip1_gclk_mux"), DT_CLK(NULL, "vip2_gclk_mux", "vip2_gclk_mux"), DT_CLK(NULL, "vip3_gclk_mux", "vip3_gclk_mux"), - DT_CLK(NULL, "gpmc_ck", "dummy_ck"), DT_CLK("omap_i2c.1", "ick", "dummy_ck"), DT_CLK("omap_i2c.2", "ick", "dummy_ck"), DT_CLK("omap_i2c.3", "ick", "dummy_ck"), diff --git a/drivers/clk/versatile/clk-vexpress-osc.c b/drivers/clk/versatile/clk-vexpress-osc.c index 2dc8b41a339d..a535c7bf8574 100644 --- a/drivers/clk/versatile/clk-vexpress-osc.c +++ b/drivers/clk/versatile/clk-vexpress-osc.c @@ -102,7 +102,7 @@ void __init vexpress_osc_of_setup(struct device_node *node) osc = kzalloc(sizeof(*osc), GFP_KERNEL); if (!osc) - goto error; + return; osc->func = vexpress_config_func_get_by_node(node); if (!osc->func) { diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index 48f76bc05da0..e252939b9ee1 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -418,8 +418,6 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt) evt->set_mode = exynos4_tick_set_mode; evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; evt->rating = 450; - clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1), - 0xf, 0x7fffffff); exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET); @@ -432,9 +430,12 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt) evt->irq); return -EIO; } + irq_force_affinity(mct_irqs[MCT_L0_IRQ + cpu], cpumask_of(cpu)); } else { enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0); } + clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1), + 0xf, 0x7fffffff); return 0; } @@ -452,7 +453,6 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { struct mct_clock_event_device *mevt; - unsigned int cpu; /* * Grab cpu pointer in each case to avoid spurious @@ -463,12 +463,6 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self, mevt = this_cpu_ptr(&percpu_mct_tick); exynos4_local_timer_setup(&mevt->evt); break; - case CPU_ONLINE: - cpu = (unsigned long)hcpu; - if (mct_int_type == MCT_INT_SPI) - irq_set_affinity(mct_irqs[MCT_L0_IRQ + cpu], - cpumask_of(cpu)); - break; case CPU_DYING: mevt = this_cpu_ptr(&percpu_mct_tick); exynos4_local_timer_stop(&mevt->evt); diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 18c5b9b16645..3165811e2407 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -369,7 +369,7 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg, return; /* Can only change if privileged. */ - if (!capable(CAP_NET_ADMIN)) { + if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) { err = EPERM; goto out; } diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 74945652dd7a..dac58f67307a 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -47,7 +47,7 @@ obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ) += arm_big_little.o # LITTLE drivers, so that it is probed last. obj-$(CONFIG_ARM_DT_BL_CPUFREQ) += arm_big_little_dt.o -obj-$(CONFIG_ARCH_DAVINCI_DA850) += davinci-cpufreq.o +obj-$(CONFIG_ARCH_DAVINCI) += davinci-cpufreq.o obj-$(CONFIG_UX500_SOC_DB8500) += dbx500-cpufreq.o obj-$(CONFIG_ARM_EXYNOS_CPUFREQ) += exynos-cpufreq.o obj-$(CONFIG_ARM_EXYNOS4210_CPUFREQ) += exynos4210-cpufreq.o diff --git a/drivers/cpufreq/at32ap-cpufreq.c b/drivers/cpufreq/at32ap-cpufreq.c index a1c79f549edb..7b612c8bb09e 100644 --- a/drivers/cpufreq/at32ap-cpufreq.c +++ b/drivers/cpufreq/at32ap-cpufreq.c @@ -52,7 +52,7 @@ static int at32_set_target(struct cpufreq_policy *policy, unsigned int index) static int at32_cpufreq_driver_init(struct cpufreq_policy *policy) { unsigned int frequency, rate, min_freq; - static struct clk *cpuclk; + struct clk *cpuclk; int retval, steps, i; if (policy->cpu != 0) diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c index 0c12ffc0ebcb..51322856f908 100644 --- a/drivers/cpufreq/cpufreq-cpu0.c +++ b/drivers/cpufreq/cpufreq-cpu0.c @@ -131,7 +131,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev) return -ENOENT; } - cpu_reg = devm_regulator_get_optional(cpu_dev, "cpu0"); + cpu_reg = regulator_get_optional(cpu_dev, "cpu0"); if (IS_ERR(cpu_reg)) { /* * If cpu0 regulator supply node is present, but regulator is @@ -146,23 +146,23 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev) PTR_ERR(cpu_reg)); } - cpu_clk = devm_clk_get(cpu_dev, NULL); + cpu_clk = clk_get(cpu_dev, NULL); if (IS_ERR(cpu_clk)) { ret = PTR_ERR(cpu_clk); pr_err("failed to get cpu0 clock: %d\n", ret); - goto out_put_node; + goto out_put_reg; } ret = of_init_opp_table(cpu_dev); if (ret) { pr_err("failed to init OPP table: %d\n", ret); - goto out_put_node; + goto out_put_clk; } ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { pr_err("failed to init cpufreq table: %d\n", ret); - goto out_put_node; + goto out_put_clk; } of_property_read_u32(np, "voltage-tolerance", &voltage_tolerance); @@ -217,6 +217,12 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev) out_free_table: dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table); +out_put_clk: + if (!IS_ERR(cpu_clk)) + clk_put(cpu_clk); +out_put_reg: + if (!IS_ERR(cpu_reg)) + regulator_put(cpu_reg); out_put_node: of_node_put(np); return ret; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 199b52b7c3e1..4854f81d038b 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -460,7 +460,18 @@ show_one(cpuinfo_max_freq, cpuinfo.max_freq); show_one(cpuinfo_transition_latency, cpuinfo.transition_latency); show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); -show_one(scaling_cur_freq, cur); + +static ssize_t show_scaling_cur_freq( + struct cpufreq_policy *policy, char *buf) +{ + ssize_t ret; + + if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) + ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); + else + ret = sprintf(buf, "%u\n", policy->cur); + return ret; +} static int cpufreq_set_policy(struct cpufreq_policy *policy, struct cpufreq_policy *new_policy); @@ -854,11 +865,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy, if (ret) goto err_out_kobj_put; } - if (has_target()) { - ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); - if (ret) - goto err_out_kobj_put; - } + + ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); + if (ret) + goto err_out_kobj_put; + if (cpufreq_driver->bios_limit) { ret = sysfs_create_file(&policy->kobj, &bios_limit.attr); if (ret) @@ -1089,10 +1100,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, * the creation of a brand new one. So we need to perform this update * by invoking update_policy_cpu(). */ - if (frozen && cpu != policy->cpu) + if (frozen && cpu != policy->cpu) { update_policy_cpu(policy, cpu); - else + WARN_ON(kobject_move(&policy->kobj, &dev->kobj)); + } else { policy->cpu = cpu; + } policy->governor = CPUFREQ_DEFAULT_GOVERNOR; cpumask_copy(policy->cpus, cpumask_of(cpu)); @@ -1223,6 +1236,8 @@ err_get_freq: per_cpu(cpufreq_cpu_data, j) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); + up_write(&policy->rwsem); + if (cpufreq_driver->exit) cpufreq_driver->exit(policy); err_set_policy_cpu: diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index ba43991ba98a..e1c6433b16e0 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -366,6 +366,11 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy, break; case CPUFREQ_GOV_LIMITS: + mutex_lock(&dbs_data->mutex); + if (!cpu_cdbs->cur_policy) { + mutex_unlock(&dbs_data->mutex); + break; + } mutex_lock(&cpu_cdbs->timer_mutex); if (policy->max < cpu_cdbs->cur_policy->cur) __cpufreq_driver_target(cpu_cdbs->cur_policy, @@ -375,6 +380,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy, policy->min, CPUFREQ_RELATION_L); dbs_check_cpu(dbs_data, cpu); mutex_unlock(&cpu_cdbs->timer_mutex); + mutex_unlock(&dbs_data->mutex); break; } return 0; diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c index 0e27844e8c2d..8089dd2cd9d8 100644 --- a/drivers/cpufreq/integrator-cpufreq.c +++ b/drivers/cpufreq/integrator-cpufreq.c @@ -213,9 +213,9 @@ static int __init integrator_cpufreq_probe(struct platform_device *pdev) return cpufreq_register_driver(&integrator_driver); } -static void __exit integrator_cpufreq_remove(struct platform_device *pdev) +static int __exit integrator_cpufreq_remove(struct platform_device *pdev) { - cpufreq_unregister_driver(&integrator_driver); + return cpufreq_unregister_driver(&integrator_driver); } static const struct of_device_id integrator_cpufreq_match[] = { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 2cd36b9297f3..533a509439ca 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -37,12 +37,13 @@ #define BYT_RATIOS 0x66a #define BYT_VIDS 0x66b #define BYT_TURBO_RATIOS 0x66c +#define BYT_TURBO_VIDS 0x66d -#define FRAC_BITS 6 +#define FRAC_BITS 8 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) #define fp_toint(X) ((X) >> FRAC_BITS) -#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS) + static inline int32_t mul_fp(int32_t x, int32_t y) { @@ -54,24 +55,37 @@ static inline int32_t div_fp(int32_t x, int32_t y) return div_s64((int64_t)x << FRAC_BITS, (int64_t)y); } +static inline int ceiling_fp(int32_t x) +{ + int mask, ret; + + ret = fp_toint(x); + mask = (1 << FRAC_BITS) - 1; + if (x & mask) + ret += 1; + return ret; +} + struct sample { int32_t core_pct_busy; u64 aperf; u64 mperf; - unsigned long long tsc; int freq; + ktime_t time; }; struct pstate_data { int current_pstate; int min_pstate; int max_pstate; + int scaling; int turbo_pstate; }; struct vid_data { - int32_t min; - int32_t max; + int min; + int max; + int turbo; int32_t ratio; }; @@ -96,11 +110,10 @@ struct cpudata { struct vid_data vid; struct _pid pid; + ktime_t last_sample_time; u64 prev_aperf; u64 prev_mperf; - unsigned long long prev_tsc; - int sample_ptr; - struct sample samples[SAMPLE_COUNT]; + struct sample sample; }; static struct cpudata **all_cpu_data; @@ -117,6 +130,7 @@ struct pstate_funcs { int (*get_max)(void); int (*get_min)(void); int (*get_turbo)(void); + int (*get_scaling)(void); void (*set)(struct cpudata*, int pstate); void (*get_vid)(struct cpudata *); }; @@ -131,6 +145,7 @@ static struct pstate_funcs pstate_funcs; struct perf_limits { int no_turbo; + int turbo_disabled; int max_perf_pct; int min_perf_pct; int32_t max_perf; @@ -199,7 +214,7 @@ static signed int pid_calc(struct _pid *pid, int32_t busy) pid->last_err = fp_error; result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm; - + result = result + (1 << (FRAC_BITS-1)); return (signed int)fp_toint(result); } @@ -290,7 +305,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; limits.no_turbo = clamp_t(int, input, 0 , 1); - + if (limits.turbo_disabled) { + pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); + limits.no_turbo = limits.turbo_disabled; + } return count; } @@ -360,21 +378,21 @@ static int byt_get_min_pstate(void) { u64 value; rdmsrl(BYT_RATIOS, value); - return (value >> 8) & 0xFF; + return (value >> 8) & 0x7F; } static int byt_get_max_pstate(void) { u64 value; rdmsrl(BYT_RATIOS, value); - return (value >> 16) & 0xFF; + return (value >> 16) & 0x7F; } static int byt_get_turbo_pstate(void) { u64 value; rdmsrl(BYT_TURBO_RATIOS, value); - return value & 0x3F; + return value & 0x7F; } static void byt_set_pstate(struct cpudata *cpudata, int pstate) @@ -384,7 +402,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) u32 vid; val = pstate << 8; - if (limits.no_turbo) + if (limits.no_turbo && !limits.turbo_disabled) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -392,17 +410,37 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) cpudata->vid.ratio); vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max); - vid = fp_toint(vid_fp); + vid = ceiling_fp(vid_fp); + + if (pstate > cpudata->pstate.max_pstate) + vid = cpudata->vid.turbo; val |= vid; wrmsrl(MSR_IA32_PERF_CTL, val); } +#define BYT_BCLK_FREQS 5 +static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800}; + +static int byt_get_scaling(void) +{ + u64 value; + int i; + + rdmsrl(MSR_FSB_FREQ, value); + i = value & 0x3; + + BUG_ON(i > BYT_BCLK_FREQS); + + return byt_freq_table[i] * 100; +} + static void byt_get_vid(struct cpudata *cpudata) { u64 value; + rdmsrl(BYT_VIDS, value); cpudata->vid.min = int_tofp((value >> 8) & 0x7f); cpudata->vid.max = int_tofp((value >> 16) & 0x7f); @@ -410,6 +448,9 @@ static void byt_get_vid(struct cpudata *cpudata) cpudata->vid.max - cpudata->vid.min, int_tofp(cpudata->pstate.max_pstate - cpudata->pstate.min_pstate)); + + rdmsrl(BYT_TURBO_VIDS, value); + cpudata->vid.turbo = value & 0x7f; } @@ -439,12 +480,17 @@ static int core_get_turbo_pstate(void) return ret; } +static inline int core_get_scaling(void) +{ + return 100000; +} + static void core_set_pstate(struct cpudata *cpudata, int pstate) { u64 val; val = pstate << 8; - if (limits.no_turbo) + if (limits.no_turbo && !limits.turbo_disabled) val |= (u64)1 << 32; wrmsrl(MSR_IA32_PERF_CTL, val); @@ -463,6 +509,7 @@ static struct cpu_defaults core_params = { .get_max = core_get_max_pstate, .get_min = core_get_min_pstate, .get_turbo = core_get_turbo_pstate, + .get_scaling = core_get_scaling, .set = core_set_pstate, }, }; @@ -481,6 +528,7 @@ static struct cpu_defaults byt_params = { .get_min = byt_get_min_pstate, .get_turbo = byt_get_turbo_pstate, .set = byt_set_pstate, + .get_scaling = byt_get_scaling, .get_vid = byt_get_vid, }, }; @@ -514,7 +562,7 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) if (pstate == cpu->pstate.current_pstate) return; - trace_cpu_frequency(pstate * 100000, cpu->cpu); + trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu); cpu->pstate.current_pstate = pstate; @@ -543,62 +591,54 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.min_pstate = pstate_funcs.get_min(); cpu->pstate.max_pstate = pstate_funcs.get_max(); cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); + cpu->pstate.scaling = pstate_funcs.get_scaling(); if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); - - /* - * goto max pstate so we don't slow up boot if we are built-in if we are - * a module we will take care of it during normal operation - */ - intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate); + intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate); } static inline void intel_pstate_calc_busy(struct cpudata *cpu, struct sample *sample) { - int32_t core_pct; - int32_t c0_pct; + int64_t core_pct; + int32_t rem; - core_pct = div_fp(int_tofp((sample->aperf)), - int_tofp((sample->mperf))); - core_pct = mul_fp(core_pct, int_tofp(100)); - FP_ROUNDUP(core_pct); + core_pct = int_tofp(sample->aperf) * int_tofp(100); + core_pct = div_u64_rem(core_pct, int_tofp(sample->mperf), &rem); - c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc)); + if ((rem << 1) >= int_tofp(sample->mperf)) + core_pct += 1; sample->freq = fp_toint( - mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); + mul_fp(int_tofp( + cpu->pstate.max_pstate * cpu->pstate.scaling / 100), + core_pct)); - sample->core_pct_busy = mul_fp(core_pct, c0_pct); + sample->core_pct_busy = (int32_t)core_pct; } static inline void intel_pstate_sample(struct cpudata *cpu) { u64 aperf, mperf; - unsigned long long tsc; rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); - tsc = native_read_tsc(); aperf = aperf >> FRAC_BITS; mperf = mperf >> FRAC_BITS; - tsc = tsc >> FRAC_BITS; - cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT; - cpu->samples[cpu->sample_ptr].aperf = aperf; - cpu->samples[cpu->sample_ptr].mperf = mperf; - cpu->samples[cpu->sample_ptr].tsc = tsc; - cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf; - cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf; - cpu->samples[cpu->sample_ptr].tsc -= cpu->prev_tsc; + cpu->last_sample_time = cpu->sample.time; + cpu->sample.time = ktime_get(); + cpu->sample.aperf = aperf; + cpu->sample.mperf = mperf; + cpu->sample.aperf -= cpu->prev_aperf; + cpu->sample.mperf -= cpu->prev_mperf; - intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]); + intel_pstate_calc_busy(cpu, &cpu->sample); cpu->prev_aperf = aperf; cpu->prev_mperf = mperf; - cpu->prev_tsc = tsc; } static inline void intel_pstate_set_sample_time(struct cpudata *cpu) @@ -612,13 +652,25 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu) static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) { - int32_t core_busy, max_pstate, current_pstate; + int32_t core_busy, max_pstate, current_pstate, sample_ratio; + u32 duration_us; + u32 sample_time; - core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; + core_busy = cpu->sample.core_pct_busy; max_pstate = int_tofp(cpu->pstate.max_pstate); current_pstate = int_tofp(cpu->pstate.current_pstate); core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); - return FP_ROUNDUP(core_busy); + + sample_time = (pid_params.sample_rate_ms * USEC_PER_MSEC); + duration_us = (u32) ktime_us_delta(cpu->sample.time, + cpu->last_sample_time); + if (duration_us > sample_time * 3) { + sample_ratio = div_fp(int_tofp(sample_time), + int_tofp(duration_us)); + core_busy = mul_fp(core_busy, sample_ratio); + } + + return core_busy; } static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) @@ -648,7 +700,7 @@ static void intel_pstate_timer_func(unsigned long __data) intel_pstate_sample(cpu); - sample = &cpu->samples[cpu->sample_ptr]; + sample = &cpu->sample; intel_pstate_adjust_busy_pstate(cpu); @@ -672,10 +724,14 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x37, byt_params), ICPU(0x3a, core_params), ICPU(0x3c, core_params), + ICPU(0x3d, core_params), ICPU(0x3e, core_params), ICPU(0x3f, core_params), ICPU(0x45, core_params), ICPU(0x46, core_params), + ICPU(0x4c, byt_params), + ICPU(0x4f, core_params), + ICPU(0x56, core_params), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); @@ -696,14 +752,8 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu = all_cpu_data[cpunum]; - intel_pstate_get_cpu_pstates(cpu); - if (!cpu->pstate.current_pstate) { - all_cpu_data[cpunum] = NULL; - kfree(cpu); - return -ENODATA; - } - cpu->cpu = cpunum; + intel_pstate_get_cpu_pstates(cpu); init_timer_deferrable(&cpu->timer); cpu->timer.function = intel_pstate_timer_func; @@ -712,7 +762,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu->timer.expires = jiffies + HZ/100; intel_pstate_busy_pid_reset(cpu); intel_pstate_sample(cpu); - intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate); add_timer_on(&cpu->timer, cpunum); @@ -729,7 +778,7 @@ static unsigned int intel_pstate_get(unsigned int cpu_num) cpu = all_cpu_data[cpu_num]; if (!cpu) return 0; - sample = &cpu->samples[cpu->sample_ptr]; + sample = &cpu->sample; return sample->freq; } @@ -745,9 +794,10 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) { limits.min_perf_pct = 100; limits.min_perf = int_tofp(1); + limits.max_policy_pct = 100; limits.max_perf_pct = 100; limits.max_perf = int_tofp(1); - limits.no_turbo = 0; + limits.no_turbo = limits.turbo_disabled; return 0; } limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq; @@ -787,6 +837,7 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) { struct cpudata *cpu; int rc; + u64 misc_en; rc = intel_pstate_init_cpu(policy->cpu); if (rc) @@ -794,18 +845,24 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu = all_cpu_data[policy->cpu]; - if (!limits.no_turbo && - limits.min_perf_pct == 100 && limits.max_perf_pct == 100) + rdmsrl(MSR_IA32_MISC_ENABLE, misc_en); + if (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE || + cpu->pstate.max_pstate == cpu->pstate.turbo_pstate) { + limits.turbo_disabled = 1; + limits.no_turbo = 1; + } + if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100) policy->policy = CPUFREQ_POLICY_PERFORMANCE; else policy->policy = CPUFREQ_POLICY_POWERSAVE; - policy->min = cpu->pstate.min_pstate * 100000; - policy->max = cpu->pstate.turbo_pstate * 100000; + policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; + policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; /* cpuinfo and default policy values */ - policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000; - policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000; + policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; + policy->cpuinfo.max_freq = + cpu->pstate.turbo_pstate * cpu->pstate.scaling; policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); @@ -863,6 +920,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_max = funcs->get_max; pstate_funcs.get_min = funcs->get_min; pstate_funcs.get_turbo = funcs->get_turbo; + pstate_funcs.get_scaling = funcs->get_scaling; pstate_funcs.set = funcs->set; pstate_funcs.get_vid = funcs->get_vid; } diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c index b6581abc9207..7231967f51b4 100644 --- a/drivers/cpufreq/loongson2_cpufreq.c +++ b/drivers/cpufreq/loongson2_cpufreq.c @@ -62,14 +62,14 @@ static int loongson2_cpufreq_target(struct cpufreq_policy *policy, set_cpus_allowed_ptr(current, &cpus_allowed); /* setting the cpu frequency */ - clk_set_rate(policy->clk, freq); + clk_set_rate(policy->clk, freq * 1000); return 0; } static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy) { - static struct clk *cpuclk; + struct clk *cpuclk; int i; unsigned long rate; int ret; @@ -92,7 +92,7 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy) i++) loongson2_clockmod_table[i].frequency = (rate * i) / 8; - ret = clk_set_rate(cpuclk, rate); + ret = clk_set_rate(cpuclk, rate * 1000); if (ret) { clk_put(cpuclk); return ret; diff --git a/drivers/cpufreq/unicore2-cpufreq.c b/drivers/cpufreq/unicore2-cpufreq.c index 36cc330b8747..99d280d6f370 100644 --- a/drivers/cpufreq/unicore2-cpufreq.c +++ b/drivers/cpufreq/unicore2-cpufreq.c @@ -45,7 +45,7 @@ static int ucv2_target(struct cpufreq_policy *policy, freqs.new = target_freq; cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); - ret = clk_set_rate(policy->mclk, target_freq * 1000); + ret = clk_set_rate(policy->clk, target_freq * 1000); cpufreq_notify_post_transition(policy, &freqs, ret); return ret; diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 0378328f47a7..a4127453baae 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -1348,9 +1348,9 @@ static int ahash_update_first(struct ahash_request *req) struct device *jrdev = ctx->jrdev; gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC; - u8 *next_buf = state->buf_0 + state->current_buf * - CAAM_MAX_HASH_BLOCK_SIZE; - int *next_buflen = &state->buflen_0 + state->current_buf; + u8 *next_buf = state->current_buf ? state->buf_1 : state->buf_0; + int *next_buflen = state->current_buf ? + &state->buflen_1 : &state->buflen_0; int to_hash; u32 *sh_desc = ctx->sh_desc_update_first, *desc; dma_addr_t ptr = ctx->sh_desc_update_first_dma; diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c index 9f25f5296029..0eabd81e1a90 100644 --- a/drivers/crypto/caam/error.c +++ b/drivers/crypto/caam/error.c @@ -16,9 +16,13 @@ char *tmp; \ \ tmp = kmalloc(sizeof(format) + max_alloc, GFP_ATOMIC); \ - sprintf(tmp, format, param); \ - strcat(str, tmp); \ - kfree(tmp); \ + if (likely(tmp)) { \ + sprintf(tmp, format, param); \ + strcat(str, tmp); \ + kfree(tmp); \ + } else { \ + strcat(str, "kmalloc failure in SPRINTFCAT"); \ + } \ } static void report_jump_idx(u32 status, char *outstr) diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index 1d80bd3636c5..b512a4ba7569 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -453,8 +453,8 @@ static int caam_jr_probe(struct platform_device *pdev) int error; jrdev = &pdev->dev; - jrpriv = kmalloc(sizeof(struct caam_drv_private_jr), - GFP_KERNEL); + jrpriv = devm_kmalloc(jrdev, sizeof(struct caam_drv_private_jr), + GFP_KERNEL); if (!jrpriv) return -ENOMEM; @@ -487,10 +487,8 @@ static int caam_jr_probe(struct platform_device *pdev) /* Now do the platform independent part */ error = caam_jr_init(jrdev); /* now turn on hardware */ - if (error) { - kfree(jrpriv); + if (error) return error; - } jrpriv->dev = jrdev; spin_lock(&driver_data.jr_alloc_lock); diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index a999f537228f..92105f3dc8e0 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -190,7 +190,7 @@ static void add_session_id(struct cryp_ctx *ctx) static irqreturn_t cryp_interrupt_handler(int irq, void *param) { struct cryp_ctx *ctx; - int i; + int count; struct cryp_device_data *device_data; if (param == NULL) { @@ -215,12 +215,11 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param) if (cryp_pending_irq_src(device_data, CRYP_IRQ_SRC_OUTPUT_FIFO)) { if (ctx->outlen / ctx->blocksize > 0) { - for (i = 0; i < ctx->blocksize / 4; i++) { - *(ctx->outdata) = readl_relaxed( - &device_data->base->dout); - ctx->outdata += 4; - ctx->outlen -= 4; - } + count = ctx->blocksize / 4; + + readsl(&device_data->base->dout, ctx->outdata, count); + ctx->outdata += count; + ctx->outlen -= count; if (ctx->outlen == 0) { cryp_disable_irq_src(device_data, @@ -230,12 +229,12 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param) } else if (cryp_pending_irq_src(device_data, CRYP_IRQ_SRC_INPUT_FIFO)) { if (ctx->datalen / ctx->blocksize > 0) { - for (i = 0 ; i < ctx->blocksize / 4; i++) { - writel_relaxed(ctx->indata, - &device_data->base->din); - ctx->indata += 4; - ctx->datalen -= 4; - } + count = ctx->blocksize / 4; + + writesl(&device_data->base->din, ctx->indata, count); + + ctx->indata += count; + ctx->datalen -= count; if (ctx->datalen == 0) cryp_disable_irq_src(device_data, diff --git a/drivers/dma/TODO b/drivers/dma/TODO index 734ed0206cd5..b8045cd42ee1 100644 --- a/drivers/dma/TODO +++ b/drivers/dma/TODO @@ -7,7 +7,6 @@ TODO for slave dma - imx-dma - imx-sdma - mxs-dma.c - - dw_dmac - intel_mid_dma 4. Check other subsystems for dma drivers and merge/move to dmaengine 5. Remove dma_slave_config's dma direction. diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index ed610b497518..a4068e2d2b5d 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1014,6 +1014,7 @@ static void dmaengine_unmap(struct kref *kref) dma_unmap_page(dev, unmap->addr[i], unmap->len, DMA_BIDIRECTIONAL); } + cnt = unmap->map_cnt; mempool_free(unmap, __get_unmap_pool(cnt)->pool); } @@ -1079,6 +1080,7 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags) memset(unmap, 0, sizeof(*unmap)); kref_init(&unmap->kref); unmap->dev = dev; + unmap->map_cnt = nr; return unmap; } diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 13ac3f240e79..b0972b3869c7 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -279,6 +279,15 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first) channel_set_bit(dw, CH_EN, dwc->mask); } +static void dwc_dostart_first_queued(struct dw_dma_chan *dwc) +{ + if (list_empty(&dwc->queue)) + return; + + list_move(dwc->queue.next, &dwc->active_list); + dwc_dostart(dwc, dwc_first_active(dwc)); +} + /*----------------------------------------------------------------------*/ static void @@ -335,10 +344,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc) * the completed ones. */ list_splice_init(&dwc->active_list, &list); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); @@ -467,10 +473,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc) /* Try to continue after resetting the channel... */ dwc_chan_disable(dw, dwc); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); } @@ -677,17 +680,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx) * possible, perhaps even appending to those already submitted * for DMA. But this is hard to do in a race-free manner. */ - if (list_empty(&dwc->active_list)) { - dev_vdbg(chan2dev(tx->chan), "%s: started %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } else { - dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->queue); - } + dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, desc->txd.cookie); + list_add_tail(&desc->desc_node, &dwc->queue); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1092,9 +1087,12 @@ dwc_tx_status(struct dma_chan *chan, static void dwc_issue_pending(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + unsigned long flags; - if (!list_empty(&dwc->queue)) - dwc_scan_descriptors(to_dw_dma(chan->device), dwc); + spin_lock_irqsave(&dwc->lock, flags); + if (list_empty(&dwc->active_list)) + dwc_dostart_first_queued(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); } static int dwc_alloc_chan_resources(struct dma_chan *chan) @@ -1545,11 +1543,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) /* Disable BLOCK interrupts as well */ channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); - err = devm_request_irq(chip->dev, chip->irq, dw_dma_interrupt, - IRQF_SHARED, "dw_dmac", dw); - if (err) - return err; - /* Create a pool of consistent memory blocks for hardware descriptors */ dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev, sizeof(struct dw_desc), 4, 0); @@ -1560,6 +1553,11 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw); + err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED, + "dw_dmac", dw); + if (err) + return err; + INIT_LIST_HEAD(&dw->dma.channels); for (i = 0; i < nr_channels; i++) { struct dw_dma_chan *dwc = &dw->chan[i]; @@ -1664,6 +1662,7 @@ int dw_dma_remove(struct dw_dma_chip *chip) dw_dma_off(dw); dma_async_device_unregister(&dw->dma); + free_irq(chip->irq, dw); tasklet_kill(&dw->tasklet); list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels, diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index cd8da451d199..bf5ad0f5a77a 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -182,11 +182,13 @@ static void edma_execute(struct edma_chan *echan) echan->ecc->dummy_slot); } - edma_resume(echan->ch_num); - if (edesc->processed <= MAX_NR_SG) { dev_dbg(dev, "first transfer starting %d\n", echan->ch_num); edma_start(echan->ch_num); + } else { + dev_dbg(dev, "chan: %d: completed %d elements, resuming\n", + echan->ch_num, edesc->processed); + edma_resume(echan->ch_num); } /* diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 766b68ed505c..394cbc5c93e3 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -191,12 +191,10 @@ static void mv_set_mode(struct mv_xor_chan *chan, static void mv_chan_activate(struct mv_xor_chan *chan) { - u32 activation; - dev_dbg(mv_chan_to_devp(chan), " activate chan.\n"); - activation = readl_relaxed(XOR_ACTIVATION(chan)); - activation |= 0x1; - writel_relaxed(activation, XOR_ACTIVATION(chan)); + + /* writel ensures all descriptors are flushed before activation */ + writel(BIT(0), XOR_ACTIVATION(chan)); } static char mv_chan_is_busy(struct mv_xor_chan *chan) diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c index df6575f1430d..682288ced4ac 100644 --- a/drivers/edac/cpc925_edac.c +++ b/drivers/edac/cpc925_edac.c @@ -562,7 +562,7 @@ static void cpc925_mc_check(struct mem_ctl_info *mci) if (apiexcp & UECC_EXCP_DETECTED) { cpc925_mc_printk(mci, KERN_INFO, "DRAM UECC Fault\n"); - edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, pfn, offset, 0, csrow, -1, -1, mci->ctl_name, ""); diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c index 3cda79bc8b00..ece3aef16bb1 100644 --- a/drivers/edac/e7xxx_edac.c +++ b/drivers/edac/e7xxx_edac.c @@ -226,7 +226,7 @@ static void process_ce(struct mem_ctl_info *mci, struct e7xxx_error_info *info) static void process_ce_no_info(struct mem_ctl_info *mci) { edac_dbg(3, "\n"); - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0, -1, -1, -1, "e7xxx CE log register overflow", ""); } diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index fa1326e5a4b0..ad76f10865c6 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -242,11 +242,11 @@ static void i3200_process_error_info(struct mem_ctl_info *mci, -1, -1, "i3000 UE", ""); } else if (log & I3200_ECCERRLOG_CE) { - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, eccerrlog_syndrome(log), eccerrlog_row(channel, log), -1, -1, - "i3000 UE", ""); + "i3000 CE", ""); } } } diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c index 3382f6344e42..4382343a7c60 100644 --- a/drivers/edac/i82860_edac.c +++ b/drivers/edac/i82860_edac.c @@ -124,7 +124,7 @@ static int i82860_process_error_info(struct mem_ctl_info *mci, dimm->location[0], dimm->location[1], -1, "i82860 UE", ""); else - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, info->eap, 0, info->derrsyn, dimm->location[0], dimm->location[1], -1, "i82860 CE", ""); diff --git a/drivers/extcon/extcon-max14577.c b/drivers/extcon/extcon-max14577.c index 3846941801b8..5c948c9625d2 100644 --- a/drivers/extcon/extcon-max14577.c +++ b/drivers/extcon/extcon-max14577.c @@ -650,7 +650,7 @@ static int max14577_muic_probe(struct platform_device *pdev) unsigned int virq = 0; virq = regmap_irq_get_virq(max14577->irq_data, muic_irq->irq); - if (!virq) + if (virq <= 0) return -EINVAL; muic_irq->virq = virq; @@ -710,13 +710,8 @@ static int max14577_muic_probe(struct platform_device *pdev) * driver should notify cable state to upper layer. */ INIT_DELAYED_WORK(&info->wq_detcable, max14577_muic_detect_cable_wq); - ret = queue_delayed_work(system_power_efficient_wq, &info->wq_detcable, + queue_delayed_work(system_power_efficient_wq, &info->wq_detcable, delay_jiffies); - if (ret < 0) { - dev_err(&pdev->dev, - "failed to schedule delayed work for cable detect\n"); - goto err_extcon; - } return ret; diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c index da268fbc901b..4657a91acf56 100644 --- a/drivers/extcon/extcon-max77693.c +++ b/drivers/extcon/extcon-max77693.c @@ -1193,7 +1193,7 @@ static int max77693_muic_probe(struct platform_device *pdev) /* Initialize MUIC register by using platform data or default data */ - if (pdata->muic_data) { + if (pdata && pdata->muic_data) { init_data = pdata->muic_data->init_data; num_init_data = pdata->muic_data->num_init_data; } else { @@ -1226,7 +1226,7 @@ static int max77693_muic_probe(struct platform_device *pdev) = init_data[i].data; } - if (pdata->muic_data) { + if (pdata && pdata->muic_data) { struct max77693_muic_platform_data *muic_pdata = pdata->muic_data; diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c index 6a00464658c5..5e1b88cecb76 100644 --- a/drivers/extcon/extcon-max8997.c +++ b/drivers/extcon/extcon-max8997.c @@ -715,7 +715,7 @@ static int max8997_muic_probe(struct platform_device *pdev) goto err_irq; } - if (pdata->muic_pdata) { + if (pdata && pdata->muic_pdata) { struct max8997_muic_platform_data *muic_pdata = pdata->muic_pdata; diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h index c98764aeeec6..f477308b6e9c 100644 --- a/drivers/firewire/core.h +++ b/drivers/firewire/core.h @@ -237,8 +237,8 @@ static inline bool is_next_generation(int new_generation, int old_generation) #define LOCAL_BUS 0xffc0 -/* arbitrarily chosen maximum range for physical DMA: 128 TB */ -#define FW_MAX_PHYSICAL_RANGE (128ULL << 40) +/* OHCI-1394's default upper bound for physical DMA: 4 GB */ +#define FW_MAX_PHYSICAL_RANGE (1ULL << 32) void fw_core_handle_request(struct fw_card *card, struct fw_packet *request); void fw_core_handle_response(struct fw_card *card, struct fw_packet *packet); diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 8db663219560..586f2f7f6993 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -3716,7 +3716,7 @@ static int pci_probe(struct pci_dev *dev, version >> 16, version & 0xff, ohci->card.index, ohci->n_ir, ohci->n_it, ohci->quirks, reg_read(ohci, OHCI1394_PhyUpperBound) ? - ", >4 GB phys DMA" : ""); + ", physUB" : ""); return 0; diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index 4b9dc836dcf9..e992abc5ef26 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -40,7 +40,7 @@ struct pstore_read_data { static inline u64 generic_id(unsigned long timestamp, unsigned int part, int count) { - return (timestamp * 100 + part) * 1000 + count; + return ((u64) timestamp * 100 + part) * 1000 + count; } static int efi_pstore_read_func(struct efivar_entry *entry, void *data) diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/efi-stub-helper.c index b6bffbfd3be7..3a74def216a5 100644 --- a/drivers/firmware/efi/efi-stub-helper.c +++ b/drivers/firmware/efi/efi-stub-helper.c @@ -468,7 +468,7 @@ grow: chunksize = EFI_READ_CHUNK_SIZE; else chunksize = size; - status = efi_call_phys3(fh->read, + status = efi_call_phys3(files[j].handle->read, files[j].handle, &chunksize, (void *)addr); @@ -480,7 +480,7 @@ grow: size -= chunksize; } - efi_call_phys1(fh->close, files[j].handle); + efi_call_phys1(files[j].handle->close, files[j].handle); } } @@ -497,7 +497,7 @@ free_file_total: close_handles: for (k = j; k < i; k++) - efi_call_phys1(fh->close, files[k].handle); + efi_call_phys1(files[k].handle->close, files[k].handle); free_files: efi_call_phys1(sys_table_arg->boottime->free_pool, files); fail: diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index b22659cccca4..e6125522860a 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -481,7 +481,7 @@ EXPORT_SYMBOL_GPL(efivar_entry_remove); */ static void efivar_entry_list_del_unlock(struct efivar_entry *entry) { - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); list_del(&entry->list); spin_unlock_irq(&__efivars->lock); @@ -507,7 +507,7 @@ int __efivar_entry_delete(struct efivar_entry *entry) const struct efivar_operations *ops = __efivars->ops; efi_status_t status; - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); status = ops->set_variable(entry->var.VariableName, &entry->var.VendorGuid, @@ -667,7 +667,7 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, int strsize1, strsize2; bool found = false; - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); list_for_each_entry_safe(entry, n, head, list) { strsize1 = ucs2_strsize(name, 1024); @@ -739,7 +739,7 @@ int __efivar_entry_get(struct efivar_entry *entry, u32 *attributes, const struct efivar_operations *ops = __efivars->ops; efi_status_t status; - WARN_ON(!spin_is_locked(&__efivars->lock)); + lockdep_assert_held(&__efivars->lock); status = ops->get_variable(entry->var.VariableName, &entry->var.VendorGuid, diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c index 1ac288ea810d..aa379971d703 100644 --- a/drivers/gpio/gpio-mcp23s08.c +++ b/drivers/gpio/gpio-mcp23s08.c @@ -895,8 +895,11 @@ static int mcp23s08_probe(struct spi_device *spi) return -ENODEV; } - for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) + for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) { pullups[addr] = 0; + if (spi_present_mask & (1 << addr)) + chips++; + } } else { type = spi_get_device_id(spi)->driver_data; pdata = dev_get_platdata(&spi->dev); @@ -919,12 +922,12 @@ static int mcp23s08_probe(struct spi_device *spi) pullups[addr] = pdata->chip[addr].pullups; } - if (!chips) - return -ENODEV; - base = pdata->base; } + if (!chips) + return -ENODEV; + data = kzalloc(sizeof *data + chips * sizeof(struct mcp23s08), GFP_KERNEL); if (!data) diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c index 532bcb336eff..8ffdd7d2bade 100644 --- a/drivers/gpio/gpio-mxs.c +++ b/drivers/gpio/gpio-mxs.c @@ -214,7 +214,8 @@ static void __init mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base) ct->regs.ack = PINCTRL_IRQSTAT(port) + MXS_CLR; ct->regs.mask = PINCTRL_IRQEN(port); - irq_setup_generic_chip(gc, IRQ_MSK(32), 0, IRQ_NOREQUEST, 0); + irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK, + IRQ_NOREQUEST, 0); } static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset) diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index d8e398275ca8..66a492aa4f1e 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -678,6 +678,7 @@ static void armada_load_cursor_argb(void __iomem *base, uint32_t *pix, base + LCD_SPU_SRAM_WRDAT); writel_relaxed(addr | SRAM_WRITE, base + LCD_SPU_SRAM_CTRL); + readl_relaxed(base + LCD_SPU_HWC_OVSA_HPXL_VLN); addr += 1; if ((addr & 0x00ff) == 0) addr += 0xf00; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 50535fd5a88d..d830b38e54f6 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -100,7 +100,7 @@ static int ast_detect_chip(struct drm_device *dev) } ast->vga2_clone = false; } else { - ast->chip = 2000; + ast->chip = AST2000; DRM_INFO("AST 2000 detected\n"); } } diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index cca063b11083..d2e56e95d886 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -1012,8 +1012,8 @@ static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height) srcdata32[1].ul = *((u32 *)(srcxor + 4)) & 0xf0f0f0f0; data32.b[0] = srcdata32[0].b[1] | (srcdata32[0].b[0] >> 4); data32.b[1] = srcdata32[0].b[3] | (srcdata32[0].b[2] >> 4); - data32.b[2] = srcdata32[0].b[1] | (srcdata32[1].b[0] >> 4); - data32.b[3] = srcdata32[0].b[3] | (srcdata32[1].b[2] >> 4); + data32.b[2] = srcdata32[1].b[1] | (srcdata32[1].b[0] >> 4); + data32.b[3] = srcdata32[1].b[3] | (srcdata32[1].b[2] >> 4); writel(data32.ul, dstxor); csum += data32.ul; diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h index 741965c001a6..460820551b09 100644 --- a/drivers/gpu/drm/bochs/bochs.h +++ b/drivers/gpu/drm/bochs/bochs.h @@ -1,5 +1,6 @@ #include <linux/io.h> #include <linux/fb.h> +#include <linux/console.h> #include <drm/drmP.h> #include <drm/drm_crtc.h> diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c index 395bba261c9a..9c13df29fd20 100644 --- a/drivers/gpu/drm/bochs/bochs_drv.c +++ b/drivers/gpu/drm/bochs/bochs_drv.c @@ -95,6 +95,49 @@ static struct drm_driver bochs_driver = { }; /* ---------------------------------------------------------------------- */ +/* pm interface */ + +static int bochs_pm_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct bochs_device *bochs = drm_dev->dev_private; + + drm_kms_helper_poll_disable(drm_dev); + + if (bochs->fb.initialized) { + console_lock(); + fb_set_suspend(bochs->fb.helper.fbdev, 1); + console_unlock(); + } + + return 0; +} + +static int bochs_pm_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct bochs_device *bochs = drm_dev->dev_private; + + drm_helper_resume_force_mode(drm_dev); + + if (bochs->fb.initialized) { + console_lock(); + fb_set_suspend(bochs->fb.helper.fbdev, 0); + console_unlock(); + } + + drm_kms_helper_poll_enable(drm_dev); + return 0; +} + +static const struct dev_pm_ops bochs_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(bochs_pm_suspend, + bochs_pm_resume) +}; + +/* ---------------------------------------------------------------------- */ /* pci interface */ static int bochs_kick_out_firmware_fb(struct pci_dev *pdev) @@ -155,6 +198,7 @@ static struct pci_driver bochs_pci_driver = { .id_table = bochs_pci_tbl, .probe = bochs_pci_probe, .remove = bochs_pci_remove, + .driver.pm = &bochs_pm_ops, }; /* ---------------------------------------------------------------------- */ diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c index 953fc8aea69c..faa1f421f1b8 100644 --- a/drivers/gpu/drm/cirrus/cirrus_drv.c +++ b/drivers/gpu/drm/cirrus/cirrus_drv.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/console.h> #include <drm/drmP.h> +#include <drm/drm_crtc_helper.h> #include "cirrus_drv.h" @@ -31,6 +32,8 @@ static struct drm_driver driver; static DEFINE_PCI_DEVICE_TABLE(pciidlist) = { { PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, 0x1af4, 0x1100, 0, 0, 0 }, + { PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, PCI_VENDOR_ID_XEN, + 0x0001, 0, 0, 0 }, {0,} }; @@ -75,6 +78,41 @@ static void cirrus_pci_remove(struct pci_dev *pdev) drm_put_dev(dev); } +static int cirrus_pm_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct cirrus_device *cdev = drm_dev->dev_private; + + drm_kms_helper_poll_disable(drm_dev); + + if (cdev->mode_info.gfbdev) { + console_lock(); + fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 1); + console_unlock(); + } + + return 0; +} + +static int cirrus_pm_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct cirrus_device *cdev = drm_dev->dev_private; + + drm_helper_resume_force_mode(drm_dev); + + if (cdev->mode_info.gfbdev) { + console_lock(); + fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 0); + console_unlock(); + } + + drm_kms_helper_poll_enable(drm_dev); + return 0; +} + static const struct file_operations cirrus_driver_fops = { .owner = THIS_MODULE, .open = drm_open, @@ -103,11 +141,17 @@ static struct drm_driver driver = { .dumb_destroy = drm_gem_dumb_destroy, }; +static const struct dev_pm_ops cirrus_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(cirrus_pm_suspend, + cirrus_pm_resume) +}; + static struct pci_driver cirrus_pci_driver = { .name = DRIVER_NAME, .id_table = pciidlist, .probe = cirrus_pci_probe, .remove = cirrus_pci_remove, + .driver.pm = &cirrus_pm_ops, }; static int __init cirrus_init(void) diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index 530f78f84dee..e9c89df482b5 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -308,6 +308,9 @@ static int cirrus_crtc_mode_set(struct drm_crtc *crtc, WREG_HDR(hdr); cirrus_crtc_do_set_base(crtc, old_fb, x, y, 0); + + /* Unblank (needed on S3 resume, vgabios doesn't do it then) */ + outb(0x20, 0x3c0); return 0; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index ec7bb0fc71bc..9debd6e74439 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -614,15 +614,20 @@ static void intel_resume_hotplug(struct drm_device *dev) drm_helper_hpd_irq_event(dev); } +static int i915_drm_thaw_early(struct drm_device *dev) +{ + intel_uncore_early_sanitize(dev); + intel_uncore_sanitize(dev); + intel_power_domains_init_hw(dev); + + return 0; +} + static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) { struct drm_i915_private *dev_priv = dev->dev_private; int error = 0; - intel_uncore_early_sanitize(dev); - - intel_uncore_sanitize(dev); - if (drm_core_check_feature(dev, DRIVER_MODESET) && restore_gtt_mappings) { mutex_lock(&dev->struct_mutex); @@ -630,8 +635,6 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) mutex_unlock(&dev->struct_mutex); } - intel_power_domains_init_hw(dev); - i915_restore_state(dev); intel_opregion_setup(dev); @@ -700,19 +703,33 @@ static int i915_drm_thaw(struct drm_device *dev) return __i915_drm_thaw(dev, true); } -int i915_resume(struct drm_device *dev) +static int i915_resume_early(struct drm_device *dev) { - struct drm_i915_private *dev_priv = dev->dev_private; - int ret; - if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; + /* + * We have a resume ordering issue with the snd-hda driver also + * requiring our device to be power up. Due to the lack of a + * parent/child relationship we currently solve this with an early + * resume hook. + * + * FIXME: This should be solved with a special hdmi sink device or + * similar so that power domains can be employed. + */ if (pci_enable_device(dev->pdev)) return -EIO; pci_set_master(dev->pdev); + return i915_drm_thaw_early(dev); +} + +int i915_resume(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int ret; + /* * Platforms with opregion should have sane BIOS, older ones (gen3 and * earlier) need to restore the GTT mappings since the BIOS might clear @@ -726,6 +743,14 @@ int i915_resume(struct drm_device *dev) return 0; } +static int i915_resume_legacy(struct drm_device *dev) +{ + i915_resume_early(dev); + i915_resume(dev); + + return 0; +} + /** * i915_reset - reset chip after a hang * @dev: drm device to reset @@ -846,7 +871,6 @@ static int i915_pm_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct drm_device *drm_dev = pci_get_drvdata(pdev); - int error; if (!drm_dev || !drm_dev->dev_private) { dev_err(dev, "DRM not initialized, aborting suspend.\n"); @@ -856,9 +880,25 @@ static int i915_pm_suspend(struct device *dev) if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; - error = i915_drm_freeze(drm_dev); - if (error) - return error; + return i915_drm_freeze(drm_dev); +} + +static int i915_pm_suspend_late(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + + /* + * We have a suspedn ordering issue with the snd-hda driver also + * requiring our device to be power up. Due to the lack of a + * parent/child relationship we currently solve this with an late + * suspend hook. + * + * FIXME: This should be solved with a special hdmi sink device or + * similar so that power domains can be employed. + */ + if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; pci_disable_device(pdev); pci_set_power_state(pdev, PCI_D3hot); @@ -866,6 +906,14 @@ static int i915_pm_suspend(struct device *dev) return 0; } +static int i915_pm_resume_early(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + + return i915_resume_early(drm_dev); +} + static int i915_pm_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -887,6 +935,14 @@ static int i915_pm_freeze(struct device *dev) return i915_drm_freeze(drm_dev); } +static int i915_pm_thaw_early(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + + return i915_drm_thaw_early(drm_dev); +} + static int i915_pm_thaw(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -948,10 +1004,14 @@ static int i915_runtime_resume(struct device *device) static const struct dev_pm_ops i915_pm_ops = { .suspend = i915_pm_suspend, + .suspend_late = i915_pm_suspend_late, + .resume_early = i915_pm_resume_early, .resume = i915_pm_resume, .freeze = i915_pm_freeze, + .thaw_early = i915_pm_thaw_early, .thaw = i915_pm_thaw, .poweroff = i915_pm_poweroff, + .restore_early = i915_pm_resume_early, .restore = i915_pm_resume, .runtime_suspend = i915_runtime_suspend, .runtime_resume = i915_runtime_resume, @@ -994,7 +1054,7 @@ static struct drm_driver driver = { /* Used in place of i915_pm_ops for non-DRIVER_MODESET */ .suspend = i915_suspend, - .resume = i915_resume, + .resume = i915_resume_legacy, .device_is_agp = i915_driver_device_is_agp, .master_create = i915_master_create, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index df77e20e3c3d..4677af964df7 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -734,6 +734,7 @@ enum intel_sbi_destination { #define QUIRK_PIPEA_FORCE (1<<0) #define QUIRK_LVDS_SSC_DISABLE (1<<1) #define QUIRK_INVERT_BRIGHTNESS (1<<2) +#define QUIRK_NO_PCH_PWM_ENABLE (1<<3) struct intel_fbdev; struct intel_fbc_work; @@ -2425,6 +2426,7 @@ extern void intel_modeset_suspend_hw(struct drm_device *dev); extern void intel_modeset_init(struct drm_device *dev); extern void intel_modeset_gem_init(struct drm_device *dev); extern void intel_modeset_cleanup(struct drm_device *dev); +extern void intel_connector_unregister(struct intel_connector *); extern int intel_modeset_vga_set_state(struct drm_device *dev, bool state); extern void intel_modeset_setup_hw_state(struct drm_device *dev, bool force_restore); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 00c836154725..7410a507eacc 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1426,10 +1426,13 @@ unlock: out: switch (ret) { case -EIO: - /* If this -EIO is due to a gpu hang, give the reset code a - * chance to clean up the mess. Otherwise return the proper - * SIGBUS. */ - if (i915_terminally_wedged(&dev_priv->gpu_error)) { + /* + * We eat errors when the gpu is terminally wedged to avoid + * userspace unduly crashing (gl has no provisions for mmaps to + * fail). But any other -EIO isn't ours (e.g. swap in failure) + * and so needs to be reported. + */ + if (!i915_terminally_wedged(&dev_priv->gpu_error)) { ret = VM_FAULT_SIGBUS; break; } @@ -3529,7 +3532,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; drm_i915_private_t *dev_priv = dev->dev_private; - struct i915_vma *vma; + struct i915_vma *vma, *next; int ret; if (obj->cache_level == cache_level) @@ -3540,7 +3543,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, return -EBUSY; } - list_for_each_entry(vma, &obj->vma_list, vma_link) { + list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) { if (!i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) { ret = i915_vma_unbind(vma); if (ret) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index d269ecf46e26..768e6665e4e3 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -766,9 +766,9 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, * relocations were valid. */ for (j = 0; j < exec[i].relocation_count; j++) { - if (copy_to_user(&user_relocs[j].presumed_offset, - &invalid_offset, - sizeof(invalid_offset))) { + if (__copy_to_user(&user_relocs[j].presumed_offset, + &invalid_offset, + sizeof(invalid_offset))) { ret = -EFAULT; mutex_lock(&dev->struct_mutex); goto err; @@ -1329,18 +1329,21 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list, &dev_priv->gtt.base); if (!ret) { + struct drm_i915_gem_exec_object __user *user_exec_list = + 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++) - exec_list[i].offset = exec2_list[i].offset; - /* ... and back out to userspace */ - ret = copy_to_user(to_user_ptr(args->buffers_ptr), - exec_list, - sizeof(*exec_list) * args->buffer_count); - if (ret) { - ret = -EFAULT; - DRM_DEBUG("failed to copy %d exec entries " - "back to user (%d)\n", - args->buffer_count, ret); + for (i = 0; i < args->buffer_count; i++) { + ret = __copy_to_user(&user_exec_list[i].offset, + &exec2_list[i].offset, + sizeof(user_exec_list[i].offset)); + if (ret) { + ret = -EFAULT; + DRM_DEBUG("failed to copy %d exec entries " + "back to user (%d)\n", + args->buffer_count, ret); + break; + } } } @@ -1388,14 +1391,21 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, &dev_priv->gtt.base); if (!ret) { /* Copy the new buffer offsets back to the user's exec list. */ - ret = copy_to_user(to_user_ptr(args->buffers_ptr), - exec2_list, - sizeof(*exec2_list) * args->buffer_count); - if (ret) { - ret = -EFAULT; - DRM_DEBUG("failed to copy %d exec entries " - "back to user (%d)\n", - args->buffer_count, ret); + struct drm_i915_gem_exec_object2 *user_exec_list = + to_user_ptr(args->buffers_ptr); + int i; + + for (i = 0; i < args->buffer_count; i++) { + ret = __copy_to_user(&user_exec_list[i].offset, + &exec2_list[i].offset, + sizeof(user_exec_list[i].offset)); + if (ret) { + ret = -EFAULT; + DRM_DEBUG("failed to copy %d exec entries " + "back to user\n", + args->buffer_count); + break; + } } } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index d278be110805..1855cdca39cd 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -827,6 +827,16 @@ void i915_check_and_clear_faults(struct drm_device *dev) POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS])); } +static void i915_ggtt_flush(struct drm_i915_private *dev_priv) +{ + if (INTEL_INFO(dev_priv->dev)->gen < 6) { + intel_gtt_chipset_flush(); + } else { + I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + POSTING_READ(GFX_FLSH_CNTL_GEN6); + } +} + void i915_gem_suspend_gtt_mappings(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -843,6 +853,8 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev) dev_priv->gtt.base.start / PAGE_SIZE, dev_priv->gtt.base.total / PAGE_SIZE, true); + + i915_ggtt_flush(dev_priv); } void i915_gem_restore_gtt_mappings(struct drm_device *dev) @@ -863,7 +875,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev) i915_gem_gtt_bind_object(obj, obj->cache_level); } - i915_gem_chipset_flush(dev); + i915_ggtt_flush(dev_priv); } int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 28d24caa49f3..3c78b2268209 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -74,6 +74,50 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev) if (base == 0) return 0; + /* make sure we don't clobber the GTT if it's within stolen memory */ + if (INTEL_INFO(dev)->gen <= 4 && !IS_G33(dev) && !IS_G4X(dev)) { + struct { + u32 start, end; + } stolen[2] = { + { .start = base, .end = base + dev_priv->gtt.stolen_size, }, + { .start = base, .end = base + dev_priv->gtt.stolen_size, }, + }; + u64 gtt_start, gtt_end; + + gtt_start = I915_READ(PGTBL_CTL); + if (IS_GEN4(dev)) + gtt_start = (gtt_start & PGTBL_ADDRESS_LO_MASK) | + (gtt_start & PGTBL_ADDRESS_HI_MASK) << 28; + else + gtt_start &= PGTBL_ADDRESS_LO_MASK; + gtt_end = gtt_start + gtt_total_entries(dev_priv->gtt) * 4; + + if (gtt_start >= stolen[0].start && gtt_start < stolen[0].end) + stolen[0].end = gtt_start; + if (gtt_end > stolen[1].start && gtt_end <= stolen[1].end) + stolen[1].start = gtt_end; + + /* pick the larger of the two chunks */ + if (stolen[0].end - stolen[0].start > + stolen[1].end - stolen[1].start) { + base = stolen[0].start; + dev_priv->gtt.stolen_size = stolen[0].end - stolen[0].start; + } else { + base = stolen[1].start; + dev_priv->gtt.stolen_size = stolen[1].end - stolen[1].start; + } + + if (stolen[0].start != stolen[1].start || + stolen[0].end != stolen[1].end) { + DRM_DEBUG_KMS("GTT within stolen memory at 0x%llx-0x%llx\n", + (unsigned long long) gtt_start, + (unsigned long long) gtt_end - 1); + DRM_DEBUG_KMS("Stolen memory adjusted to 0x%x-0x%x\n", + base, base + (u32) dev_priv->gtt.stolen_size - 1); + } + } + + /* Verify that nothing else uses this physical address. Stolen * memory should be reserved by the BIOS and hidden from the * kernel. So if the region is already marked as busy, something diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index d554169ac592..40504504c9e2 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1252,10 +1252,20 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev, spin_lock(&dev_priv->irq_lock); for (i = 1; i < HPD_NUM_PINS; i++) { - WARN_ONCE(hpd[i] & hotplug_trigger && - dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED, - "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n", - hotplug_trigger, i, hpd[i]); + if (hpd[i] & hotplug_trigger && + dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED) { + /* + * On GMCH platforms the interrupt mask bits only + * prevent irq generation, not the setting of the + * hotplug bits itself. So only WARN about unexpected + * interrupts on saner platforms. + */ + WARN_ONCE(INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev), + "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n", + hotplug_trigger, i, hpd[i]); + + continue; + } if (!(hpd[i] & hotplug_trigger) || dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index a48b7cad6f11..0a3b9386eb43 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -631,6 +631,9 @@ /* * Instruction and interrupt control regs */ +#define PGTBL_CTL 0x02020 +#define PGTBL_ADDRESS_LO_MASK 0xfffff000 /* bits [31:12] */ +#define PGTBL_ADDRESS_HI_MASK 0x000000f0 /* bits [35:32] (gen4) */ #define PGTBL_ER 0x02024 #define RENDER_RING_BASE 0x02000 #define BSD_RING_BASE 0x04000 diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 6e580c98dede..783ae08200e8 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -238,14 +238,16 @@ TRACE_EVENT(i915_gem_evict_vm, TP_ARGS(vm), TP_STRUCT__entry( + __field(u32, dev) __field(struct i915_address_space *, vm) ), TP_fast_assign( + __entry->dev = vm->dev->primary->index; __entry->vm = vm; ), - TP_printk("dev=%d, vm=%p", __entry->vm->dev->primary->index, __entry->vm) + TP_printk("dev=%d, vm=%p", __entry->dev, __entry->vm) ); TRACE_EVENT(i915_gem_ring_sync_to, diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index f22041973f3a..08105fddfd2a 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -839,7 +839,7 @@ init_vbt_defaults(struct drm_i915_private *dev_priv) } } -static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id) +static int intel_no_opregion_vbt_callback(const struct dmi_system_id *id) { DRM_DEBUG_KMS("Falling back to manually reading VBT from " "VBIOS ROM for %s\n", diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index e2e39e65f109..834847527982 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -750,7 +750,7 @@ static const struct drm_encoder_funcs intel_crt_enc_funcs = { .destroy = intel_encoder_destroy, }; -static int __init intel_no_crt_dmi_callback(const struct dmi_system_id *id) +static int intel_no_crt_dmi_callback(const struct dmi_system_id *id) { DRM_INFO("Skipping CRT initialization for %s\n", id->ident); return 1; @@ -765,6 +765,14 @@ static const struct dmi_system_id intel_no_crt[] = { DMI_MATCH(DMI_PRODUCT_NAME, "ZGB"), }, }, + { + .callback = intel_no_crt_dmi_callback, + .ident = "DELL XPS 8700", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS 8700"), + }, + }, { } }; @@ -833,6 +841,7 @@ void intel_crt_init(struct drm_device *dev) crt->base.get_hw_state = intel_crt_get_hw_state; } intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->unregister = intel_connector_unregister; drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 9b8a7c7ea7fc..b6fb3ebe553a 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -9354,11 +9354,22 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_I(pipe_src_w); PIPE_CONF_CHECK_I(pipe_src_h); - PIPE_CONF_CHECK_I(gmch_pfit.control); - /* pfit ratios are autocomputed by the hw on gen4+ */ - if (INTEL_INFO(dev)->gen < 4) - PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios); - PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits); + /* + * FIXME: BIOS likes to set up a cloned config with lvds+external + * screen. Since we don't yet re-compute the pipe config when moving + * just the lvds port away to another pipe the sw tracking won't match. + * + * Proper atomic modesets with recomputed global state will fix this. + * Until then just don't check gmch state for inherited modes. + */ + if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_INHERITED_MODE)) { + PIPE_CONF_CHECK_I(gmch_pfit.control); + /* pfit ratios are autocomputed by the hw on gen4+ */ + if (INTEL_INFO(dev)->gen < 4) + PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios); + PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits); + } + PIPE_CONF_CHECK_I(pch_pfit.enabled); if (current_config->pch_pfit.enabled) { PIPE_CONF_CHECK_I(pch_pfit.pos); @@ -10771,6 +10782,17 @@ static void quirk_invert_brightness(struct drm_device *dev) DRM_INFO("applying inverted panel brightness quirk\n"); } +/* + * Some machines (Dell XPS13) suffer broken backlight controls if + * BLM_PCH_PWM_ENABLE is set. + */ +static void quirk_no_pcm_pwm_enable(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + dev_priv->quirks |= QUIRK_NO_PCH_PWM_ENABLE; + DRM_INFO("applying no-PCH_PWM_ENABLE quirk\n"); +} + struct intel_quirk { int device; int subsystem_vendor; @@ -10839,6 +10861,14 @@ static struct intel_quirk intel_quirks[] = { /* Acer Aspire 4736Z */ { 0x2a42, 0x1025, 0x0260, quirk_invert_brightness }, + + /* Acer Aspire 5336 */ + { 0x2a42, 0x1025, 0x048a, quirk_invert_brightness }, + + /* Dell XPS13 HD Sandy Bridge */ + { 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable }, + /* Dell XPS13 HD and XPS13 FHD Ivy Bridge */ + { 0x0166, 0x1028, 0x058b, quirk_no_pcm_pwm_enable }, }; static void intel_init_quirks(struct drm_device *dev) @@ -10962,15 +10992,6 @@ void intel_modeset_init(struct drm_device *dev) intel_disable_fbc(dev); } -static void -intel_connector_break_all_links(struct intel_connector *connector) -{ - connector->base.dpms = DRM_MODE_DPMS_OFF; - connector->base.encoder = NULL; - connector->encoder->connectors_active = false; - connector->encoder->base.crtc = NULL; -} - static void intel_enable_pipe_a(struct drm_device *dev) { struct intel_connector *connector; @@ -11052,8 +11073,17 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) if (connector->encoder->base.crtc != &crtc->base) continue; - intel_connector_break_all_links(connector); + connector->base.dpms = DRM_MODE_DPMS_OFF; + connector->base.encoder = NULL; } + /* multiple connectors may have the same encoder: + * handle them and break crtc link separately */ + list_for_each_entry(connector, &dev->mode_config.connector_list, + base.head) + if (connector->encoder->base.crtc == &crtc->base) { + connector->encoder->base.crtc = NULL; + connector->encoder->connectors_active = false; + } WARN_ON(crtc->active); crtc->base.enabled = false; @@ -11124,6 +11154,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) drm_get_encoder_name(&encoder->base)); encoder->disable(encoder); } + encoder->base.crtc = NULL; + encoder->connectors_active = false; /* Inconsistent output/port/pipe state happens presumably due to * a bug in one of the get_hw_state functions. Or someplace else @@ -11134,8 +11166,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) base.head) { if (connector->encoder != encoder) continue; - - intel_connector_break_all_links(connector); + connector->base.dpms = DRM_MODE_DPMS_OFF; + connector->base.encoder = NULL; } } /* Enabled encoders without active connectors will be fixed in @@ -11177,6 +11209,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) base.head) { memset(&crtc->config, 0, sizeof(crtc->config)); + crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE; + crtc->active = dev_priv->display.get_pipe_config(crtc, &crtc->config); @@ -11334,6 +11368,14 @@ void intel_modeset_gem_init(struct drm_device *dev) mutex_unlock(&dev->mode_config.mutex); } +void intel_connector_unregister(struct intel_connector *intel_connector) +{ + struct drm_connector *connector = &intel_connector->base; + + intel_panel_destroy_backlight(connector); + drm_sysfs_connector_remove(connector); +} + void intel_modeset_cleanup(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -11378,8 +11420,10 @@ void intel_modeset_cleanup(struct drm_device *dev) /* destroy the backlight and sysfs files before encoders/connectors */ list_for_each_entry(connector, &dev->mode_config.connector_list, head) { - intel_panel_destroy_backlight(connector); - drm_sysfs_connector_remove(connector); + struct intel_connector *intel_connector; + + intel_connector = to_intel_connector(connector); + intel_connector->unregister(intel_connector); } drm_mode_config_cleanup(dev); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 2688f6d64bb9..b2d0887b3d12 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -744,6 +744,16 @@ out: return ret; } +static void +intel_dp_connector_unregister(struct intel_connector *intel_connector) +{ + struct intel_dp *intel_dp = intel_attached_dp(&intel_connector->base); + + sysfs_remove_link(&intel_connector->base.kdev->kobj, + intel_dp->adapter.dev.kobj.name); + intel_connector_unregister(intel_connector); +} + static int intel_dp_i2c_init(struct intel_dp *intel_dp, struct intel_connector *intel_connector, const char *name) @@ -761,9 +771,19 @@ intel_dp_i2c_init(struct intel_dp *intel_dp, strncpy(intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1); intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0'; intel_dp->adapter.algo_data = &intel_dp->algo; - intel_dp->adapter.dev.parent = intel_connector->base.kdev; + intel_dp->adapter.dev.parent = intel_connector->base.dev->dev; ret = i2c_dp_aux_add_bus(&intel_dp->adapter); + if (ret < 0) + return ret; + + ret = sysfs_create_link(&intel_connector->base.kdev->kobj, + &intel_dp->adapter.dev.kobj, + intel_dp->adapter.dev.kobj.name); + + if (ret < 0) + i2c_del_adapter(&intel_dp->adapter); + return ret; } @@ -3686,6 +3706,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, intel_connector->get_hw_state = intel_ddi_connector_get_hw_state; else intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->unregister = intel_dp_connector_unregister; intel_dp->aux_ch_ctl_reg = intel_dp->output_reg + 0x10; if (HAS_DDI(dev)) { diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index fbfaaba5cc3b..0b59914344e4 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -187,6 +187,14 @@ struct intel_connector { * and active (i.e. dpms ON state). */ bool (*get_hw_state)(struct intel_connector *); + /* + * Removes all interfaces through which the connector is accessible + * - like sysfs, debugfs entries -, so that no new operations can be + * started on the connector. Also makes sure all currently pending + * operations finish before returing. + */ + void (*unregister)(struct intel_connector *); + /* Panel info for eDP and LVDS */ struct intel_panel panel; @@ -219,7 +227,8 @@ struct intel_crtc_config { * tracked with quirk flags so that fastboot and state checker can act * accordingly. */ -#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */ +#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */ +#define PIPE_CONFIG_QUIRK_INHERITED_MODE (1<<1) /* mode inherited from firmware */ unsigned long quirks; /* User requested mode, only valid as a starting point to diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index fabbf0d895cf..ad05683ac5b6 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -586,6 +586,7 @@ bool intel_dsi_init(struct drm_device *dev) intel_encoder->get_config = intel_dsi_get_config; intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->unregister = intel_connector_unregister; for (i = 0; i < ARRAY_SIZE(intel_dsi_devices); i++) { dsi = &intel_dsi_devices[i]; diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index eeff998e52ef..86eeb8b7d435 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -477,6 +477,7 @@ void intel_dvo_init(struct drm_device *dev) intel_encoder->compute_config = intel_dvo_compute_config; intel_encoder->mode_set = intel_dvo_mode_set; intel_connector->get_hw_state = intel_dvo_connector_get_hw_state; + intel_connector->unregister = intel_connector_unregister; /* Now, try to find a controller */ for (i = 0; i < ARRAY_SIZE(intel_dvo_devices); i++) { diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index ee3181ebcc92..7b277c369dce 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -841,11 +841,11 @@ static void intel_disable_hdmi(struct intel_encoder *encoder) } } -static int hdmi_portclock_limit(struct intel_hdmi *hdmi) +static int hdmi_portclock_limit(struct intel_hdmi *hdmi, bool respect_dvi_limit) { struct drm_device *dev = intel_hdmi_to_dev(hdmi); - if (!hdmi->has_hdmi_sink || IS_G4X(dev)) + if ((respect_dvi_limit && !hdmi->has_hdmi_sink) || IS_G4X(dev)) return 165000; else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8) return 300000; @@ -857,7 +857,8 @@ static enum drm_mode_status intel_hdmi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { - if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector))) + if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector), + true)) return MODE_CLOCK_HIGH; if (mode->clock < 20000) return MODE_CLOCK_LOW; @@ -875,7 +876,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, struct drm_device *dev = encoder->base.dev; struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode; int clock_12bpc = pipe_config->adjusted_mode.crtc_clock * 3 / 2; - int portclock_limit = hdmi_portclock_limit(intel_hdmi); + int portclock_limit = hdmi_portclock_limit(intel_hdmi, false); int desired_bpp; if (intel_hdmi->color_range_auto) { @@ -1261,6 +1262,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, intel_connector->get_hw_state = intel_ddi_connector_get_hw_state; else intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->unregister = intel_connector_unregister; intel_hdmi_add_properties(intel_hdmi, connector); diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 8bcb93a2a9f6..67c9ff389989 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -544,7 +544,7 @@ static const struct drm_encoder_funcs intel_lvds_enc_funcs = { .destroy = intel_encoder_destroy, }; -static int __init intel_no_lvds_dmi_callback(const struct dmi_system_id *id) +static int intel_no_lvds_dmi_callback(const struct dmi_system_id *id) { DRM_INFO("Skipping LVDS initialization for %s\n", id->ident); return 1; @@ -957,6 +957,7 @@ void intel_lvds_init(struct drm_device *dev) intel_encoder->get_hw_state = intel_lvds_get_hw_state; intel_encoder->get_config = intel_lvds_get_config; intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->unregister = intel_connector_unregister; intel_connector_attach_encoder(intel_connector, intel_encoder); intel_encoder->type = INTEL_OUTPUT_LVDS; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 079ea38f14d9..c6d9777bdb45 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -501,6 +501,7 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level, enum pipe pipe = intel_get_pipe_from_connector(connector); u32 freq; unsigned long flags; + u64 n; if (!panel->backlight.present || pipe == INVALID_PIPE) return; @@ -511,10 +512,9 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level, /* scale to hardware max, but be careful to not overflow */ freq = panel->backlight.max; - if (freq < max) - level = level * freq / max; - else - level = freq / max * level; + n = (u64)level * freq; + do_div(n, max); + level = n; panel->backlight.level = level; if (panel->backlight.device) @@ -645,7 +645,7 @@ static void pch_enable_backlight(struct intel_connector *connector) cpu_ctl2 = I915_READ(BLC_PWM_CPU_CTL2); if (cpu_ctl2 & BLM_PWM_ENABLE) { - WARN(1, "cpu backlight already enabled\n"); + DRM_DEBUG_KMS("cpu backlight already enabled\n"); cpu_ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2); } @@ -671,6 +671,10 @@ static void pch_enable_backlight(struct intel_connector *connector) pch_ctl2 = panel->backlight.max << 16; I915_WRITE(BLC_PWM_PCH_CTL2, pch_ctl2); + /* XXX: transitional */ + if (dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE) + return; + pch_ctl1 = 0; if (panel->backlight.active_low_pwm) pch_ctl1 |= BLM_PCH_POLARITY; @@ -689,7 +693,7 @@ static void i9xx_enable_backlight(struct intel_connector *connector) ctl = I915_READ(BLC_PWM_CTL); if (ctl & BACKLIGHT_DUTY_CYCLE_MASK_PNV) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); I915_WRITE(BLC_PWM_CTL, 0); } @@ -720,7 +724,7 @@ static void i965_enable_backlight(struct intel_connector *connector) ctl2 = I915_READ(BLC_PWM_CTL2); if (ctl2 & BLM_PWM_ENABLE) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(BLC_PWM_CTL2, ctl2); } @@ -732,9 +736,6 @@ static void i965_enable_backlight(struct intel_connector *connector) ctl = freq << 16; I915_WRITE(BLC_PWM_CTL, ctl); - /* XXX: combine this into above write? */ - intel_panel_actually_set_backlight(connector, panel->backlight.level); - ctl2 = BLM_PIPE(pipe); if (panel->backlight.combination_mode) ctl2 |= BLM_COMBINATION_MODE; @@ -743,6 +744,8 @@ static void i965_enable_backlight(struct intel_connector *connector) I915_WRITE(BLC_PWM_CTL2, ctl2); POSTING_READ(BLC_PWM_CTL2); I915_WRITE(BLC_PWM_CTL2, ctl2 | BLM_PWM_ENABLE); + + intel_panel_actually_set_backlight(connector, panel->backlight.level); } static void vlv_enable_backlight(struct intel_connector *connector) @@ -755,7 +758,7 @@ static void vlv_enable_backlight(struct intel_connector *connector) ctl2 = I915_READ(VLV_BLC_PWM_CTL2(pipe)); if (ctl2 & BLM_PWM_ENABLE) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(VLV_BLC_PWM_CTL2(pipe), ctl2); } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index e1fc35a72656..8e7245151b96 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -1539,6 +1539,16 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm); + if (IS_I915GM(dev) && enabled) { + struct intel_framebuffer *fb; + + fb = to_intel_framebuffer(enabled->fb); + + /* self-refresh seems busted with untiled */ + if (fb->obj->tiling_mode == I915_TILING_NONE) + enabled = NULL; + } + /* * Overlay gets an aggressive default since video jitter is bad. */ @@ -5128,10 +5138,25 @@ bool intel_display_power_enabled_sw(struct drm_device *dev, { struct drm_i915_private *dev_priv = dev->dev_private; struct i915_power_domains *power_domains; + struct i915_power_well *power_well; + bool is_enabled; + int i; + + if (dev_priv->pm.suspended) + return false; power_domains = &dev_priv->power_domains; + is_enabled = true; + for_each_power_well_rev(i, power_well, BIT(domain), power_domains) { + if (power_well->always_on) + continue; - return power_domains->domain_use_count[domain]; + if (!power_well->count) { + is_enabled = false; + break; + } + } + return is_enabled; } bool intel_display_power_enabled(struct drm_device *dev, diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 31b36c5ac894..d488fc71ef49 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -475,6 +475,9 @@ static int init_ring_common(struct intel_ring_buffer *ring) } } + /* Enforce ordering by reading HEAD register back */ + I915_READ_HEAD(ring); + /* Initialize the ring. This must happen _after_ we've cleared the ring * registers with the above sequence (the readback of the HEAD registers * also enforces ordering), otherwise the hw might lose the new ring diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 95bdfb3c431c..1890264cf115 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1383,7 +1383,9 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, >> SDVO_PORT_MULTIPLY_SHIFT) + 1; } - dotclock = pipe_config->port_clock / pipe_config->pixel_multiplier; + dotclock = pipe_config->port_clock; + if (pipe_config->pixel_multiplier) + dotclock /= pipe_config->pixel_multiplier; if (HAS_PCH_SPLIT(dev)) ironlake_check_encoder_dotclock(pipe_config, dotclock); @@ -2397,6 +2399,7 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector, connector->base.base.doublescan_allowed = 0; connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB; connector->base.get_hw_state = intel_sdvo_connector_get_hw_state; + connector->base.unregister = intel_connector_unregister; intel_connector_attach_encoder(&connector->base, &encoder->base); drm_sysfs_connector_add(&connector->base.base); diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 22cf0f4ba248..9c9606c8bb1a 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -854,6 +854,10 @@ intel_enable_tv(struct intel_encoder *encoder) struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + /* Prevents vblank waits from timing out in intel_tv_detect_type() */ + intel_wait_for_vblank(encoder->base.dev, + to_intel_crtc(encoder->base.crtc)->pipe); + I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE); } @@ -1536,9 +1540,14 @@ static int tv_is_present_in_vbt(struct drm_device *dev) /* * If the device type is not TV, continue. */ - if (p_child->old.device_type != DEVICE_TYPE_INT_TV && - p_child->old.device_type != DEVICE_TYPE_TV) + switch (p_child->old.device_type) { + case DEVICE_TYPE_INT_TV: + case DEVICE_TYPE_TV: + case DEVICE_TYPE_TV_SVIDEO_COMPOSITE: + break; + default: continue; + } /* Only when the addin_offset is non-zero, it is regarded * as present. */ @@ -1634,6 +1643,7 @@ intel_tv_init(struct drm_device *dev) intel_encoder->disable = intel_disable_tv; intel_encoder->get_hw_state = intel_tv_get_hw_state; intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->unregister = intel_connector_unregister; intel_connector_attach_encoder(intel_connector, intel_encoder); intel_encoder->type = INTEL_OUTPUT_TVOUT; diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 87df68f5f504..c8796316d242 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -177,6 +177,8 @@ static void vlv_force_wake_reset(struct drm_i915_private *dev_priv) { __raw_i915_write32(dev_priv, FORCEWAKE_VLV, _MASKED_BIT_DISABLE(0xffff)); + __raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV, + _MASKED_BIT_DISABLE(0xffff)); /* something from same cacheline, but !FORCEWAKE_VLV */ __raw_posting_read(dev_priv, FORCEWAKE_ACK_VLV); } diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c index 7cf8b1348632..6fdf6e385bf7 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c @@ -51,6 +51,14 @@ nv04_disp_scanoutpos(struct nouveau_object *object, u32 mthd, args->htotal = nv_rd32(priv, 0x680824 + (head * 0x2000)) & 0xffff; args->hblanke = args->htotal - 1; + /* + * If output is vga instead of digital then vtotal/htotal is invalid + * so we have to give up and trigger the timestamping fallback in the + * drm core. + */ + if (!args->vtotal || !args->htotal) + return -ENOTSUPP; + args->time[0] = ktime_to_ns(ktime_get()); line = nv_rd32(priv, 0x600868 + (head * 0x2000)); args->time[1] = ktime_to_ns(ktime_get()); diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c index 1c5e4e8b2c82..e031d7c88fa3 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c @@ -732,7 +732,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, } if (outp == 8) - return false; + return conf; data = exec_lookup(priv, head, outp, ctrl, dcb, &ver, &hdr, &cnt, &len, &info1); if (data == 0x0000) diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c index a86bd3352bf8..e69bfde37aef 100644 --- a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c +++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c @@ -1318,10 +1318,12 @@ nv108_grctx_generate_mods(struct nvc0_graph_priv *priv, struct nvc0_grctx *info) mmio_list(0x408010, 0x80000000, 0, 0); mmio_list(0x419004, 0x00000000, 8, 1); mmio_list(0x419008, 0x00000000, 0, 0); + mmio_list(0x4064cc, 0x80000000, 0, 0); mmio_list(0x408004, 0x00000000, 8, 0); mmio_list(0x408008, 0x80000030, 0, 0); mmio_list(0x418808, 0x00000000, 8, 0); mmio_list(0x41880c, 0x80000030, 0, 0); + mmio_list(0x4064c8, 0x00c20200, 0, 0); mmio_list(0x418810, 0x80000000, 12, 2); mmio_list(0x419848, 0x10000000, 12, 2); diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c index 2d9b9d7a7992..f3edd2841f2d 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c @@ -124,6 +124,7 @@ dcb_outp_parse(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len, struct dcb_output *outp) { u16 dcb = dcb_outp(bios, idx, ver, len); + memset(outp, 0x00, sizeof(*outp)); if (dcb) { if (*ver >= 0x20) { u32 conn = nv_ro32(bios, dcb + 0x00); diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c index e8822a934c48..90d8bf8ce0dc 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c @@ -26,6 +26,7 @@ const struct nouveau_mc_intr nv50_mc_intr[] = { + { 0x04000000, NVDEV_ENGINE_DISP }, /* DISP before FIFO, so pageflip-timestamping works! */ { 0x00000001, NVDEV_ENGINE_MPEG }, { 0x00000100, NVDEV_ENGINE_FIFO }, { 0x00001000, NVDEV_ENGINE_GR }, @@ -34,7 +35,6 @@ nv50_mc_intr[] = { { 0x00020000, NVDEV_ENGINE_VP }, /* NV84- */ { 0x00100000, NVDEV_SUBDEV_TIMER }, { 0x00200000, NVDEV_SUBDEV_GPIO }, - { 0x04000000, NVDEV_ENGINE_DISP }, { 0x10000000, NVDEV_SUBDEV_BUS }, { 0x80000000, NVDEV_ENGINE_SW }, { 0x0002d101, NVDEV_SUBDEV_FB }, diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c index f8a6f18e2d34..95b3d35388a8 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c @@ -26,6 +26,7 @@ static const struct nouveau_mc_intr nv98_mc_intr[] = { + { 0x04000000, NVDEV_ENGINE_DISP }, /* DISP first, so pageflip timestamps work */ { 0x00000001, NVDEV_ENGINE_PPP }, { 0x00000100, NVDEV_ENGINE_FIFO }, { 0x00001000, NVDEV_ENGINE_GR }, @@ -37,7 +38,6 @@ nv98_mc_intr[] = { { 0x00100000, NVDEV_SUBDEV_TIMER }, { 0x00200000, NVDEV_SUBDEV_GPIO }, { 0x00400000, NVDEV_ENGINE_COPY0 }, /* NVA3- */ - { 0x04000000, NVDEV_ENGINE_DISP }, { 0x10000000, NVDEV_SUBDEV_BUS }, { 0x80000000, NVDEV_ENGINE_SW }, { 0x0042d101, NVDEV_SUBDEV_FB }, diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c index 34472d317097..ac7f99a15fa7 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c @@ -26,6 +26,7 @@ const struct nouveau_mc_intr nvc0_mc_intr[] = { + { 0x04000000, NVDEV_ENGINE_DISP }, /* DISP first, so pageflip timestamps work. */ { 0x00000001, NVDEV_ENGINE_PPP }, { 0x00000020, NVDEV_ENGINE_COPY0 }, { 0x00000040, NVDEV_ENGINE_COPY1 }, @@ -40,7 +41,6 @@ nvc0_mc_intr[] = { { 0x00200000, NVDEV_SUBDEV_GPIO }, { 0x01000000, NVDEV_SUBDEV_PWR }, { 0x02000000, NVDEV_SUBDEV_LTCG }, - { 0x04000000, NVDEV_ENGINE_DISP }, { 0x08000000, NVDEV_SUBDEV_FB }, { 0x10000000, NVDEV_SUBDEV_BUS }, { 0x40000000, NVDEV_SUBDEV_IBUS }, diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c index 95f6129eeede..29d4c417a5b3 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c +++ b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c @@ -54,8 +54,10 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target) /* check that we're not already at the target duty cycle */ duty = fan->get(therm); - if (duty == target) - goto done; + if (duty == target) { + spin_unlock_irqrestore(&fan->lock, flags); + return 0; + } /* smooth out the fanspeed increase/decrease */ if (!immediate && duty >= 0) { @@ -73,8 +75,15 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target) nv_debug(therm, "FAN update: %d\n", duty); ret = fan->set(therm, duty); - if (ret) - goto done; + if (ret) { + spin_unlock_irqrestore(&fan->lock, flags); + return ret; + } + + /* fan speed updated, drop the fan lock before grabbing the + * alarm-scheduling lock and risking a deadlock + */ + spin_unlock_irqrestore(&fan->lock, flags); /* schedule next fan update, if not at target speed already */ if (list_empty(&fan->alarm.head) && target != duty) { @@ -92,8 +101,6 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target) ptimer->alarm(ptimer, delay * 1000 * 1000, &fan->alarm); } -done: - spin_unlock_irqrestore(&fan->lock, flags); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 83face3f608f..279206997e5c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -389,9 +389,6 @@ bool nouveau_acpi_rom_supported(struct pci_dev *pdev) acpi_status status; acpi_handle dhandle, rom_handle; - if (!nouveau_dsm_priv.dsm_detected && !nouveau_dsm_priv.optimus_detected) - return false; - dhandle = ACPI_HANDLE(&pdev->dev); if (!dhandle) return false; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 24011596af43..6601690ab29c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -734,6 +734,9 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, fb->bits_per_pixel, fb->pitches[0], crtc->x, crtc->y, new_bo->bo.offset }; + /* Keep vblanks on during flip, for the target crtc of this flip */ + drm_vblank_get(dev, nouveau_crtc(crtc)->index); + /* Emit a page flip */ if (nv_device(drm->device)->card_type >= NV_50) { ret = nv50_display_flip_next(crtc, fb, chan, swap_interval); @@ -762,9 +765,9 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, } ret = nouveau_page_flip_emit(chan, old_bo, new_bo, s, &fence); - mutex_unlock(&chan->cli->mutex); if (ret) goto fail_unreserve; + mutex_unlock(&chan->cli->mutex); /* Update the crtc struct and cleanup */ crtc->fb = fb; @@ -777,6 +780,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, return 0; fail_unreserve: + drm_vblank_put(dev, nouveau_crtc(crtc)->index); ttm_bo_unreserve(&old_bo->bo); fail_unpin: mutex_unlock(&chan->cli->mutex); @@ -796,6 +800,7 @@ nouveau_finish_page_flip(struct nouveau_channel *chan, struct drm_device *dev = drm->dev; struct nouveau_page_flip_state *s; unsigned long flags; + int crtcid = -1; spin_lock_irqsave(&dev->event_lock, flags); @@ -806,8 +811,16 @@ nouveau_finish_page_flip(struct nouveau_channel *chan, } s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head); - if (s->event) - drm_send_vblank_event(dev, s->crtc, s->event); + if (s->event) { + /* Vblank timestamps/counts are only correct on >= NV-50 */ + if (nv_device(drm->device)->card_type >= NV_50) + crtcid = s->crtc; + + drm_send_vblank_event(dev, crtcid, s->event); + } + + /* Give up ownership of vblank for page-flipped crtc */ + drm_vblank_put(dev, s->crtc); list_del(&s->head); if (ps) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h index 23ca7a517246..74ed08a750f4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.h +++ b/drivers/gpu/drm/nouveau/nouveau_drm.h @@ -10,7 +10,7 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 1 -#define DRIVER_PATCHLEVEL 1 +#define DRIVER_PATCHLEVEL 2 /* * 1.1.1: @@ -21,6 +21,8 @@ * to control registers on the MPs to enable performance counters, * and to control the warp error enable mask (OpenGL requires out of * bounds access to local memory to be silently ignored / return 0). + * 1.1.2: + * - fixes multiple bugs in flip completion events and timestamping */ #include <core/client.h> diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c index 471347edc27e..a92fb01459c9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vga.c +++ b/drivers/gpu/drm/nouveau/nouveau_vga.c @@ -100,7 +100,16 @@ void nouveau_vga_fini(struct nouveau_drm *drm) { struct drm_device *dev = drm->dev; + bool runtime = false; + + if (nouveau_runtime_pm == 1) + runtime = true; + if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm())) + runtime = true; + vga_switcheroo_unregister_client(dev->pdev); + if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus()) + vga_switcheroo_fini_domain_pm_ops(drm->dev->dev); vga_client_register(dev->pdev, NULL, NULL, NULL); } diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c index f926b4caf449..56c60552abba 100644 --- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c +++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c @@ -199,7 +199,7 @@ static struct dmm_txn *dmm_txn_init(struct dmm *dmm, struct tcm *tcm) static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area, struct page **pages, uint32_t npages, uint32_t roll) { - dma_addr_t pat_pa = 0; + dma_addr_t pat_pa = 0, data_pa = 0; uint32_t *data; struct pat *pat; struct refill_engine *engine = txn->engine_handle; @@ -223,7 +223,9 @@ static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area, .lut_id = engine->tcm->lut_id, }; - data = alloc_dma(txn, 4*i, &pat->data_pa); + data = alloc_dma(txn, 4*i, &data_pa); + /* FIXME: what if data_pa is more than 32-bit ? */ + pat->data_pa = data_pa; while (i--) { int n = i + roll; diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 5aec3e81fe24..5fd3bab8b803 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -791,7 +791,7 @@ int omap_gem_get_paddr(struct drm_gem_object *obj, omap_obj->paddr = tiler_ssptr(block); omap_obj->block = block; - DBG("got paddr: %08x", omap_obj->paddr); + DBG("got paddr: %pad", &omap_obj->paddr); } omap_obj->paddr_cnt++; @@ -988,9 +988,9 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m) off = drm_vma_node_start(&obj->vma_node); - seq_printf(m, "%08x: %2d (%2d) %08llx %08Zx (%2d) %p %4d", + seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d", omap_obj->flags, obj->name, obj->refcount.refcount.counter, - off, omap_obj->paddr, omap_obj->paddr_cnt, + off, &omap_obj->paddr, omap_obj->paddr_cnt, omap_obj->vaddr, omap_obj->roll); if (omap_obj->flags & OMAP_BO_TILED) { @@ -1468,8 +1468,8 @@ void omap_gem_init(struct drm_device *dev) entry->paddr = tiler_ssptr(block); entry->block = block; - DBG("%d:%d: %dx%d: paddr=%08x stride=%d", i, j, w, h, - entry->paddr, + DBG("%d:%d: %dx%d: paddr=%pad stride=%d", i, j, w, h, + &entry->paddr, usergart[i].stride_pfn << PAGE_SHIFT); } } diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c index 046d5e660c04..5b62e212cbe5 100644 --- a/drivers/gpu/drm/omapdrm/omap_plane.c +++ b/drivers/gpu/drm/omapdrm/omap_plane.c @@ -142,8 +142,8 @@ static void omap_plane_pre_apply(struct omap_drm_apply *apply) DBG("%dx%d -> %dx%d (%d)", info->width, info->height, info->out_width, info->out_height, info->screen_width); - DBG("%d,%d %08x %08x", info->pos_x, info->pos_y, - info->paddr, info->p_uv_addr); + DBG("%d,%d %pad %pad", info->pos_x, info->pos_y, + &info->paddr, &info->p_uv_addr); /* TODO: */ ilace = false; diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 798bde2e5881..c39c414c7751 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -523,7 +523,6 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, struct qxl_framebuffer *qfb; struct qxl_bo *bo, *old_bo = NULL; struct qxl_crtc *qcrtc = to_qxl_crtc(crtc); - uint32_t width, height, base_offset; bool recreate_primary = false; int ret; int surf_id; @@ -553,9 +552,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, if (qcrtc->index == 0) recreate_primary = true; - width = mode->hdisplay; - height = mode->vdisplay; - base_offset = 0; + if (bo->surf.stride * bo->surf.height > qdev->vram_size) { + DRM_ERROR("Mode doesn't fit in vram size (vgamem)"); + return -EINVAL; + } ret = qxl_bo_reserve(bo, false); if (ret != 0) @@ -569,10 +569,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, if (recreate_primary) { qxl_io_destroy_primary(qdev); qxl_io_log(qdev, - "recreate primary: %dx%d (was %dx%d,%d,%d)\n", - width, height, bo->surf.width, - bo->surf.height, bo->surf.stride, bo->surf.format); - qxl_io_create_primary(qdev, base_offset, bo); + "recreate primary: %dx%d,%d,%d\n", + bo->surf.width, bo->surf.height, + bo->surf.stride, bo->surf.format); + qxl_io_create_primary(qdev, 0, bo); bo->is_primary = true; surf_id = 0; } else { diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c index 28f84b4fce32..3485bdccf8b8 100644 --- a/drivers/gpu/drm/qxl/qxl_irq.c +++ b/drivers/gpu/drm/qxl/qxl_irq.c @@ -33,6 +33,9 @@ irqreturn_t qxl_irq_handler(int irq, void *arg) pending = xchg(&qdev->ram_header->int_pending, 0); + if (!pending) + return IRQ_NONE; + atomic_inc(&qdev->irq_received); if (pending & QXL_INTERRUPT_DISPLAY) { diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index c7e7e6590c2b..c82c1d6a965a 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -433,6 +433,7 @@ static int qxl_sync_obj_flush(void *sync_obj) static void qxl_sync_obj_unref(void **sync_obj) { + *sync_obj = NULL; } static void *qxl_sync_obj_ref(void *sync_obj) diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index daa4dd375ab1..0cca5f24196a 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -270,8 +270,6 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode) switch (mode) { case DRM_MODE_DPMS_ON: radeon_crtc->enabled = true; - /* adjust pm to dpms changes BEFORE enabling crtcs */ - radeon_pm_compute_clocks(rdev); atombios_enable_crtc(crtc, ATOM_ENABLE); if (ASIC_IS_DCE3(rdev) && !ASIC_IS_DCE6(rdev)) atombios_enable_crtc_memreq(crtc, ATOM_ENABLE); @@ -289,10 +287,10 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode) atombios_enable_crtc_memreq(crtc, ATOM_DISABLE); atombios_enable_crtc(crtc, ATOM_DISABLE); radeon_crtc->enabled = false; - /* adjust pm to dpms changes AFTER disabling crtcs */ - radeon_pm_compute_clocks(rdev); break; } + /* adjust pm to dpms */ + radeon_pm_compute_clocks(rdev); } static void @@ -864,14 +862,16 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc, args.v5.ucMiscInfo = 0; /* HDMI depth, etc. */ if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK)) args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_REF_DIV_SRC; - switch (bpc) { - case 8: - default: - args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP; - break; - case 10: - args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP; - break; + if (encoder_mode == ATOM_ENCODER_MODE_HDMI) { + switch (bpc) { + case 8: + default: + args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP; + break; + case 10: + args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP; + break; + } } args.v5.ucTransmitterID = encoder_id; args.v5.ucEncoderMode = encoder_mode; @@ -886,20 +886,22 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc, args.v6.ucMiscInfo = 0; /* HDMI depth, etc. */ if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK)) args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_REF_DIV_SRC; - switch (bpc) { - case 8: - default: - args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP; - break; - case 10: - args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP; - break; - case 12: - args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP; - break; - case 16: - args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP; - break; + if (encoder_mode == ATOM_ENCODER_MODE_HDMI) { + switch (bpc) { + case 8: + default: + args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP; + break; + case 10: + args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP; + break; + case 12: + args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP; + break; + case 16: + args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP; + break; + } } args.v6.ucTransmitterID = encoder_id; args.v6.ucEncoderMode = encoder_mode; diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 4ad7643fce5f..5727dbdeda7f 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -386,6 +386,19 @@ static int dp_get_max_dp_pix_clock(int link_rate, /***** radeon specific DP functions *****/ +static int radeon_dp_get_max_link_rate(struct drm_connector *connector, + u8 dpcd[DP_DPCD_SIZE]) +{ + int max_link_rate; + + if (radeon_connector_is_dp12_capable(connector)) + max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000); + else + max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000); + + return max_link_rate; +} + /* First get the min lane# when low rate is used according to pixel clock * (prefer low rate), second check max lane# supported by DP panel, * if the max lane# < low rate lane# then use max lane# instead. @@ -395,7 +408,7 @@ static int radeon_dp_get_dp_lane_number(struct drm_connector *connector, int pix_clock) { int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector)); - int max_link_rate = drm_dp_max_link_rate(dpcd); + int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd); int max_lane_num = drm_dp_max_lane_count(dpcd); int lane_num; int max_dp_pix_clock; @@ -433,7 +446,7 @@ static int radeon_dp_get_dp_link_clock(struct drm_connector *connector, return 540000; } - return drm_dp_max_link_rate(dpcd); + return radeon_dp_get_max_link_rate(connector, dpcd); } static u8 radeon_dp_encoder_service(struct radeon_device *rdev, diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 607dc14d195e..e7bfd5502410 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -183,7 +183,6 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, struct backlight_properties props; struct radeon_backlight_privdata *pdata; struct radeon_encoder_atom_dig *dig; - u8 backlight_level; char bl_name[16]; /* Mac laptops with multiple GPUs use the gmux driver for backlight @@ -222,12 +221,17 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, pdata->encoder = radeon_encoder; - backlight_level = radeon_atom_get_backlight_level_from_reg(rdev); - dig = radeon_encoder->enc_priv; dig->bl_dev = bd; bd->props.brightness = radeon_atom_backlight_get_brightness(bd); + /* Set a reasonable default here if the level is 0 otherwise + * fbdev will attempt to turn the backlight on after console + * unblanking and it will try and restore 0 which turns the backlight + * off again. + */ + if (bd->props.brightness == 0) + bd->props.brightness = RADEON_MAX_BL_LEVEL; bd->props.power = FB_BLANK_UNBLANK; backlight_update_status(bd); @@ -1898,8 +1902,11 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder) args.v2.ucEncodeMode = ATOM_ENCODER_MODE_CRT; else args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder); - } else + } else if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { + args.v2.ucEncodeMode = ATOM_ENCODER_MODE_LVDS; + } else { args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder); + } switch (radeon_encoder->encoder_id) { case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 8d49104ca6c2..543ba2d4a659 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -21,8 +21,10 @@ * */ +#include <linux/firmware.h> #include "drmP.h" #include "radeon.h" +#include "radeon_ucode.h" #include "cikd.h" #include "r600_dpm.h" #include "ci_dpm.h" @@ -849,6 +851,9 @@ static int ci_set_thermal_temperature_range(struct radeon_device *rdev, WREG32_SMC(CG_THERMAL_CTRL, tmp); #endif + rdev->pm.dpm.thermal.min_temp = low_temp; + rdev->pm.dpm.thermal.max_temp = high_temp; + return 0; } @@ -920,7 +925,18 @@ static void ci_get_leakage_voltages(struct radeon_device *rdev) pi->vddc_leakage.count = 0; pi->vddci_leakage.count = 0; - if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) { + if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) { + for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) { + virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i; + if (radeon_atom_get_voltage_evv(rdev, virtual_voltage_id, &vddc) != 0) + continue; + if (vddc != 0 && vddc != virtual_voltage_id) { + pi->vddc_leakage.actual_voltage[pi->vddc_leakage.count] = vddc; + pi->vddc_leakage.leakage_id[pi->vddc_leakage.count] = virtual_voltage_id; + pi->vddc_leakage.count++; + } + } + } else if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) { for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) { virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i; if (radeon_atom_get_leakage_vddc_based_on_leakage_params(rdev, &vddc, &vddci, @@ -1159,7 +1175,7 @@ static int ci_stop_dpm(struct radeon_device *rdev) tmp &= ~GLOBAL_PWRMGT_EN; WREG32_SMC(GENERAL_PWRMGT, tmp); - tmp = RREG32(SCLK_PWRMGT_CNTL); + tmp = RREG32_SMC(SCLK_PWRMGT_CNTL); tmp &= ~DYNAMIC_PM_EN; WREG32_SMC(SCLK_PWRMGT_CNTL, tmp); @@ -5106,6 +5122,12 @@ int ci_dpm_init(struct radeon_device *rdev) pi->mclk_dpm_key_disabled = 0; pi->pcie_dpm_key_disabled = 0; + /* mclk dpm is unstable on some R7 260X cards with the old mc ucode */ + if ((rdev->pdev->device == 0x6658) && + (rdev->mc_fw->size == (BONAIRE_MC_UCODE_SIZE * 4))) { + pi->mclk_dpm_key_disabled = 1; + } + pi->caps_sclk_ds = true; pi->mclk_strobe_mode_threshold = 40000; diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index bbb17841a9e5..ab5c26575622 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -38,6 +38,7 @@ MODULE_FIRMWARE("radeon/BONAIRE_me.bin"); MODULE_FIRMWARE("radeon/BONAIRE_ce.bin"); MODULE_FIRMWARE("radeon/BONAIRE_mec.bin"); MODULE_FIRMWARE("radeon/BONAIRE_mc.bin"); +MODULE_FIRMWARE("radeon/BONAIRE_mc2.bin"); MODULE_FIRMWARE("radeon/BONAIRE_rlc.bin"); MODULE_FIRMWARE("radeon/BONAIRE_sdma.bin"); MODULE_FIRMWARE("radeon/BONAIRE_smc.bin"); @@ -46,6 +47,7 @@ MODULE_FIRMWARE("radeon/HAWAII_me.bin"); MODULE_FIRMWARE("radeon/HAWAII_ce.bin"); MODULE_FIRMWARE("radeon/HAWAII_mec.bin"); MODULE_FIRMWARE("radeon/HAWAII_mc.bin"); +MODULE_FIRMWARE("radeon/HAWAII_mc2.bin"); MODULE_FIRMWARE("radeon/HAWAII_rlc.bin"); MODULE_FIRMWARE("radeon/HAWAII_sdma.bin"); MODULE_FIRMWARE("radeon/HAWAII_smc.bin"); @@ -1095,7 +1097,7 @@ static const u32 spectre_golden_registers[] = 0x8a14, 0xf000003f, 0x00000007, 0x8b24, 0xffffffff, 0x00ffffff, 0x28350, 0x3f3f3fff, 0x00000082, - 0x28355, 0x0000003f, 0x00000000, + 0x28354, 0x0000003f, 0x00000000, 0x3e78, 0x00000001, 0x00000002, 0x913c, 0xffff03df, 0x00000004, 0xc768, 0x00000008, 0x00000008, @@ -1702,20 +1704,20 @@ int ci_mc_load_microcode(struct radeon_device *rdev) const __be32 *fw_data; u32 running, blackout = 0; u32 *io_mc_regs; - int i, ucode_size, regs_size; + int i, regs_size, ucode_size; if (!rdev->mc_fw) return -EINVAL; + ucode_size = rdev->mc_fw->size / 4; + switch (rdev->family) { case CHIP_BONAIRE: io_mc_regs = (u32 *)&bonaire_io_mc_regs; - ucode_size = CIK_MC_UCODE_SIZE; regs_size = BONAIRE_IO_MC_REGS_SIZE; break; case CHIP_HAWAII: io_mc_regs = (u32 *)&hawaii_io_mc_regs; - ucode_size = HAWAII_MC_UCODE_SIZE; regs_size = HAWAII_IO_MC_REGS_SIZE; break; default: @@ -1782,7 +1784,7 @@ static int cik_init_microcode(struct radeon_device *rdev) const char *chip_name; size_t pfp_req_size, me_req_size, ce_req_size, mec_req_size, rlc_req_size, mc_req_size = 0, - sdma_req_size, smc_req_size = 0; + sdma_req_size, smc_req_size = 0, mc2_req_size = 0; char fw_name[30]; int err; @@ -1796,7 +1798,8 @@ static int cik_init_microcode(struct radeon_device *rdev) ce_req_size = CIK_CE_UCODE_SIZE * 4; mec_req_size = CIK_MEC_UCODE_SIZE * 4; rlc_req_size = BONAIRE_RLC_UCODE_SIZE * 4; - mc_req_size = CIK_MC_UCODE_SIZE * 4; + mc_req_size = BONAIRE_MC_UCODE_SIZE * 4; + mc2_req_size = BONAIRE_MC2_UCODE_SIZE * 4; sdma_req_size = CIK_SDMA_UCODE_SIZE * 4; smc_req_size = ALIGN(BONAIRE_SMC_UCODE_SIZE, 4); break; @@ -1808,6 +1811,7 @@ static int cik_init_microcode(struct radeon_device *rdev) mec_req_size = CIK_MEC_UCODE_SIZE * 4; rlc_req_size = BONAIRE_RLC_UCODE_SIZE * 4; mc_req_size = HAWAII_MC_UCODE_SIZE * 4; + mc2_req_size = HAWAII_MC2_UCODE_SIZE * 4; sdma_req_size = CIK_SDMA_UCODE_SIZE * 4; smc_req_size = ALIGN(HAWAII_SMC_UCODE_SIZE, 4); break; @@ -1903,16 +1907,22 @@ static int cik_init_microcode(struct radeon_device *rdev) /* No SMC, MC ucode on APUs */ if (!(rdev->flags & RADEON_IS_IGP)) { - snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name); err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev); - if (err) - goto out; - if (rdev->mc_fw->size != mc_req_size) { + if (err) { + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev); + if (err) + goto out; + } + if ((rdev->mc_fw->size != mc_req_size) && + (rdev->mc_fw->size != mc2_req_size)){ printk(KERN_ERR "cik_mc: Bogus length %zu in firmware \"%s\"\n", rdev->mc_fw->size, fw_name); err = -EINVAL; } + DRM_INFO("%s: %zu bytes\n", fw_name, rdev->mc_fw->size); snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name); err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev); @@ -2209,6 +2219,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev) gb_tile_moden = 0; break; } + rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden; WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden); } } else if (num_pipe_configs == 8) { @@ -3220,6 +3231,7 @@ static void cik_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x130B) || (rdev->pdev->device == 0x130E) || (rdev->pdev->device == 0x1315) || + (rdev->pdev->device == 0x1318) || (rdev->pdev->device == 0x131B)) { rdev->config.cik.max_cu_per_sh = 4; rdev->config.cik.max_backends_per_se = 1; @@ -4380,7 +4392,7 @@ struct bonaire_mqd */ static int cik_cp_compute_resume(struct radeon_device *rdev) { - int r, i, idx; + int r, i, j, idx; u32 tmp; bool use_doorbell = true; u64 hqd_gpu_addr; @@ -4499,7 +4511,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev) mqd->queue_state.cp_hqd_pq_wptr= 0; if (RREG32(CP_HQD_ACTIVE) & 1) { WREG32(CP_HQD_DEQUEUE_REQUEST, 1); - for (i = 0; i < rdev->usec_timeout; i++) { + for (j = 0; j < rdev->usec_timeout; j++) { if (!(RREG32(CP_HQD_ACTIVE) & 1)) break; udelay(1); @@ -5533,12 +5545,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev, void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) { struct radeon_ring *ring = &rdev->ring[ridx]; + int usepfp = (ridx == RADEON_RING_TYPE_GFX_INDEX); if (vm == NULL) return; radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | + radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) | WRITE_DATA_DST_SEL(0))); if (vm->id < 8) { radeon_ring_write(ring, @@ -5588,7 +5601,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) radeon_ring_write(ring, 1 << vm->id); /* compute doesn't have PFP */ - if (ridx == RADEON_RING_TYPE_GFX_INDEX) { + if (usepfp) { /* sync PFP to ME, otherwise we might get invalid PFP reads */ radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0)); radeon_ring_write(ring, 0x0); @@ -6521,8 +6534,8 @@ void cik_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer) buffer[count++] = cpu_to_le32(0x00000000); break; case CHIP_HAWAII: - buffer[count++] = 0x3a00161a; - buffer[count++] = 0x0000002e; + buffer[count++] = cpu_to_le32(0x3a00161a); + buffer[count++] = cpu_to_le32(0x0000002e); break; default: buffer[count++] = cpu_to_le32(0x00000000); @@ -6662,6 +6675,19 @@ static void cik_disable_interrupt_state(struct radeon_device *rdev) WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); } + /* pflip */ + if (rdev->num_crtc >= 2) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); + } + if (rdev->num_crtc >= 4) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0); + } + if (rdev->num_crtc >= 6) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); + } /* dac hotplug */ WREG32(DAC_AUTODETECT_INT_CONTROL, 0); @@ -7018,6 +7044,25 @@ int cik_irq_set(struct radeon_device *rdev) WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6); } + if (rdev->num_crtc >= 2) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + } + if (rdev->num_crtc >= 4) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + } + if (rdev->num_crtc >= 6) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + } + WREG32(DC_HPD1_INT_CONTROL, hpd1); WREG32(DC_HPD2_INT_CONTROL, hpd2); WREG32(DC_HPD3_INT_CONTROL, hpd3); @@ -7054,6 +7099,29 @@ static inline void cik_irq_ack(struct radeon_device *rdev) rdev->irq.stat_regs.cik.disp_int_cont5 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE5); rdev->irq.stat_regs.cik.disp_int_cont6 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE6); + rdev->irq.stat_regs.cik.d1grph_int = RREG32(GRPH_INT_STATUS + + EVERGREEN_CRTC0_REGISTER_OFFSET); + rdev->irq.stat_regs.cik.d2grph_int = RREG32(GRPH_INT_STATUS + + EVERGREEN_CRTC1_REGISTER_OFFSET); + if (rdev->num_crtc >= 4) { + rdev->irq.stat_regs.cik.d3grph_int = RREG32(GRPH_INT_STATUS + + EVERGREEN_CRTC2_REGISTER_OFFSET); + rdev->irq.stat_regs.cik.d4grph_int = RREG32(GRPH_INT_STATUS + + EVERGREEN_CRTC3_REGISTER_OFFSET); + } + if (rdev->num_crtc >= 6) { + rdev->irq.stat_regs.cik.d5grph_int = RREG32(GRPH_INT_STATUS + + EVERGREEN_CRTC4_REGISTER_OFFSET); + rdev->irq.stat_regs.cik.d6grph_int = RREG32(GRPH_INT_STATUS + + EVERGREEN_CRTC5_REGISTER_OFFSET); + } + + if (rdev->irq.stat_regs.cik.d1grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, + GRPH_PFLIP_INT_CLEAR); + if (rdev->irq.stat_regs.cik.d2grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, + GRPH_PFLIP_INT_CLEAR); if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT) WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, VBLANK_ACK); if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT) @@ -7064,6 +7132,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev) WREG32(LB_VLINE_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, VLINE_ACK); if (rdev->num_crtc >= 4) { + if (rdev->irq.stat_regs.cik.d3grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, + GRPH_PFLIP_INT_CLEAR); + if (rdev->irq.stat_regs.cik.d4grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET, + GRPH_PFLIP_INT_CLEAR); if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VBLANK_ACK); if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) @@ -7075,6 +7149,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev) } if (rdev->num_crtc >= 6) { + if (rdev->irq.stat_regs.cik.d5grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, + GRPH_PFLIP_INT_CLEAR); + if (rdev->irq.stat_regs.cik.d6grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET, + GRPH_PFLIP_INT_CLEAR); if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VBLANK_ACK); if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) @@ -7193,6 +7273,7 @@ static inline u32 cik_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } @@ -7426,6 +7507,15 @@ restart_ih: break; } break; + case 8: /* D1 page flip */ + case 10: /* D2 page flip */ + case 12: /* D3 page flip */ + case 14: /* D4 page flip */ + case 16: /* D5 page flip */ + case 18: /* D6 page flip */ + DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1); + radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1); + break; case 42: /* HPD hotplug */ switch (src_data) { case 0: @@ -7690,6 +7780,7 @@ restart_ih: static int cik_startup(struct radeon_device *rdev) { struct radeon_ring *ring; + u32 nop; int r; /* enable pcie gen2/3 link */ @@ -7807,9 +7898,15 @@ static int cik_startup(struct radeon_device *rdev) } cik_irq_set(rdev); + if (rdev->family == CHIP_HAWAII) { + nop = RADEON_CP_PACKET2; + } else { + nop = PACKET3(PACKET3_NOP, 0x3FFF); + } + ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]; r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET, - PACKET3(PACKET3_NOP, 0x3FFF)); + nop); if (r) return r; @@ -7817,7 +7914,7 @@ static int cik_startup(struct radeon_device *rdev) /* type-2 packets are deprecated on MEC, use type-3 instead */ ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]; r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP1_RPTR_OFFSET, - PACKET3(PACKET3_NOP, 0x3FFF)); + nop); if (r) return r; ring->me = 1; /* first MEC */ @@ -7828,7 +7925,7 @@ static int cik_startup(struct radeon_device *rdev) /* type-2 packets are deprecated on MEC, use type-3 instead */ ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]; r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP2_RPTR_OFFSET, - PACKET3(PACKET3_NOP, 0x3FFF)); + nop); if (r) return r; /* dGPU only have 1 MEC */ diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c index 94626ea90fa5..66ba713ba7d7 100644 --- a/drivers/gpu/drm/radeon/cik_sdma.c +++ b/drivers/gpu/drm/radeon/cik_sdma.c @@ -461,13 +461,6 @@ int cik_sdma_resume(struct radeon_device *rdev) { int r; - /* Reset dma */ - WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - RREG32(SRBM_SOFT_RESET); - r = cik_sdma_load_microcode(rdev); if (r) return r; @@ -599,7 +592,7 @@ int cik_sdma_ring_test(struct radeon_device *rdev, tmp = 0xCAFEDEAD; writel(tmp, ptr); - r = radeon_ring_lock(rdev, ring, 4); + r = radeon_ring_lock(rdev, ring, 5); if (r) { DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r); return r; diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h index 98bae9d7b74d..a0a9f974cdd7 100644 --- a/drivers/gpu/drm/radeon/cikd.h +++ b/drivers/gpu/drm/radeon/cikd.h @@ -882,6 +882,15 @@ # define DC_HPD6_RX_INTERRUPT (1 << 18) #define DISP_INTERRUPT_STATUS_CONTINUE6 0x6780 +/* 0x6858, 0x7458, 0x10058, 0x10c58, 0x11858, 0x12458 */ +#define GRPH_INT_STATUS 0x6858 +# define GRPH_PFLIP_INT_OCCURRED (1 << 0) +# define GRPH_PFLIP_INT_CLEAR (1 << 8) +/* 0x685c, 0x745c, 0x1005c, 0x10c5c, 0x1185c, 0x1245c */ +#define GRPH_INT_CONTROL 0x685c +# define GRPH_PFLIP_INT_MASK (1 << 0) +# define GRPH_PFLIP_INT_TYPE (1 << 8) + #define DAC_AUTODETECT_INT_CONTROL 0x67c8 #define DC_HPD1_INT_STATUS 0x601c @@ -1736,12 +1745,12 @@ #define EOP_TC_WB_ACTION_EN (1 << 15) /* L2 */ #define EOP_TCL1_ACTION_EN (1 << 16) #define EOP_TC_ACTION_EN (1 << 17) /* L2 */ +#define EOP_TCL2_VOLATILE (1 << 24) #define EOP_CACHE_POLICY(x) ((x) << 25) /* 0 - LRU * 1 - Stream * 2 - Bypass */ -#define EOP_TCL2_VOLATILE (1 << 27) #define DATA_SEL(x) ((x) << 29) /* 0 - discard * 1 - send low 32bit data diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c index cf783fc0ef21..cf777193c85f 100644 --- a/drivers/gpu/drm/radeon/cypress_dpm.c +++ b/drivers/gpu/drm/radeon/cypress_dpm.c @@ -1551,7 +1551,7 @@ int cypress_populate_smc_voltage_tables(struct radeon_device *rdev, table->voltageMaskTable.highMask[RV770_SMC_VOLTAGEMASK_VDDCI] = 0; table->voltageMaskTable.lowMask[RV770_SMC_VOLTAGEMASK_VDDCI] = - cpu_to_be32(eg_pi->vddc_voltage_table.mask_low); + cpu_to_be32(eg_pi->vddci_voltage_table.mask_low); } return 0; diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 94e858751994..0a65dc7e93e7 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -309,11 +309,17 @@ int dce6_audio_init(struct radeon_device *rdev) rdev->audio.enabled = true; - if (ASIC_IS_DCE8(rdev)) + if (ASIC_IS_DCE81(rdev)) /* KV: 4 streams, 7 endpoints */ + rdev->audio.num_pins = 7; + else if (ASIC_IS_DCE83(rdev)) /* KB: 2 streams, 3 endpoints */ + rdev->audio.num_pins = 3; + else if (ASIC_IS_DCE8(rdev)) /* BN/HW: 6 streams, 7 endpoints */ + rdev->audio.num_pins = 7; + else if (ASIC_IS_DCE61(rdev)) /* TN: 4 streams, 6 endpoints */ rdev->audio.num_pins = 6; - else if (ASIC_IS_DCE61(rdev)) - rdev->audio.num_pins = 4; - else + else if (ASIC_IS_DCE64(rdev)) /* OL: 2 streams, 2 endpoints */ + rdev->audio.num_pins = 2; + else /* SI: 6 streams, 6 endpoints */ rdev->audio.num_pins = 6; for (i = 0; i < rdev->audio.num_pins; i++) { diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 27b0ff16082e..4b3c5f7ae63b 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -189,7 +189,7 @@ static const u32 evergreen_golden_registers[] = 0x8c1c, 0xffffffff, 0x00001010, 0x28350, 0xffffffff, 0x00000000, 0xa008, 0xffffffff, 0x00010000, - 0x5cc, 0xffffffff, 0x00000001, + 0x5c4, 0xffffffff, 0x00000001, 0x9508, 0xffffffff, 0x00000002, 0x913c, 0x0000000f, 0x0000000a }; @@ -476,7 +476,7 @@ static const u32 cedar_golden_registers[] = 0x8c1c, 0xffffffff, 0x00001010, 0x28350, 0xffffffff, 0x00000000, 0xa008, 0xffffffff, 0x00010000, - 0x5cc, 0xffffffff, 0x00000001, + 0x5c4, 0xffffffff, 0x00000001, 0x9508, 0xffffffff, 0x00000002 }; @@ -635,7 +635,7 @@ static const u32 juniper_mgcg_init[] = static const u32 supersumo_golden_registers[] = { 0x5eb4, 0xffffffff, 0x00000002, - 0x5cc, 0xffffffff, 0x00000001, + 0x5c4, 0xffffffff, 0x00000001, 0x7030, 0xffffffff, 0x00000011, 0x7c30, 0xffffffff, 0x00000011, 0x6104, 0x01000300, 0x00000000, @@ -719,7 +719,7 @@ static const u32 sumo_golden_registers[] = static const u32 wrestler_golden_registers[] = { 0x5eb4, 0xffffffff, 0x00000002, - 0x5cc, 0xffffffff, 0x00000001, + 0x5c4, 0xffffffff, 0x00000001, 0x7030, 0xffffffff, 0x00000011, 0x7c30, 0xffffffff, 0x00000011, 0x6104, 0x01000300, 0x00000000, @@ -4375,7 +4375,6 @@ int evergreen_irq_set(struct radeon_device *rdev) u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0; u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6; u32 grbm_int_cntl = 0; - u32 grph1 = 0, grph2 = 0, grph3 = 0, grph4 = 0, grph5 = 0, grph6 = 0; u32 afmt1 = 0, afmt2 = 0, afmt3 = 0, afmt4 = 0, afmt5 = 0, afmt6 = 0; u32 dma_cntl, dma_cntl1 = 0; u32 thermal_int = 0; @@ -4558,15 +4557,21 @@ int evergreen_irq_set(struct radeon_device *rdev) WREG32(INT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6); } - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, grph1); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, grph2); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); if (rdev->num_crtc >= 4) { - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); } if (rdev->num_crtc >= 6) { - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); } WREG32(DC_HPD1_INT_CONTROL, hpd1); @@ -4758,6 +4763,7 @@ static u32 evergreen_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } @@ -4955,6 +4961,15 @@ restart_ih: break; } break; + case 8: /* D1 page flip */ + case 10: /* D2 page flip */ + case 12: /* D3 page flip */ + case 14: /* D4 page flip */ + case 16: /* D5 page flip */ + case 18: /* D6 page flip */ + DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1); + radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1); + break; case 42: /* HPD hotplug */ switch (src_data) { case 0: diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c index 7cf96b15377f..94fa49e974eb 100644 --- a/drivers/gpu/drm/radeon/ni_dma.c +++ b/drivers/gpu/drm/radeon/ni_dma.c @@ -191,12 +191,6 @@ int cayman_dma_resume(struct radeon_device *rdev) u32 reg_offset, wb_offset; int i, r; - /* Reset dma */ - WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - for (i = 0; i < 2; i++) { if (i == 0) { ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX]; diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index ca814276b075..03f08a3cf864 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -1315,7 +1315,7 @@ static void ni_populate_smc_voltage_tables(struct radeon_device *rdev, table->voltageMaskTable.highMask[NISLANDS_SMC_VOLTAGEMASK_VDDCI] = 0; table->voltageMaskTable.lowMask[NISLANDS_SMC_VOLTAGEMASK_VDDCI] = - cpu_to_be32(eg_pi->vddc_voltage_table.mask_low); + cpu_to_be32(eg_pi->vddci_voltage_table.mask_low); } } diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 647ef4079217..788f602e8989 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3509,7 +3509,6 @@ int r600_irq_set(struct radeon_device *rdev) u32 hpd1, hpd2, hpd3, hpd4 = 0, hpd5 = 0, hpd6 = 0; u32 grbm_int_cntl = 0; u32 hdmi0, hdmi1; - u32 d1grph = 0, d2grph = 0; u32 dma_cntl; u32 thermal_int = 0; @@ -3618,8 +3617,8 @@ int r600_irq_set(struct radeon_device *rdev) WREG32(CP_INT_CNTL, cp_int_cntl); WREG32(DMA_CNTL, dma_cntl); WREG32(DxMODE_INT_MASK, mode_int); - WREG32(D1GRPH_INTERRUPT_CONTROL, d1grph); - WREG32(D2GRPH_INTERRUPT_CONTROL, d2grph); + WREG32(D1GRPH_INTERRUPT_CONTROL, DxGRPH_PFLIP_INT_MASK); + WREG32(D2GRPH_INTERRUPT_CONTROL, DxGRPH_PFLIP_INT_MASK); WREG32(GRBM_INT_CNTL, grbm_int_cntl); if (ASIC_IS_DCE3(rdev)) { WREG32(DC_HPD1_INT_CONTROL, hpd1); @@ -3796,6 +3795,7 @@ static u32 r600_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } @@ -3922,6 +3922,14 @@ restart_ih: break; } break; + case 9: /* D1 pflip */ + DRM_DEBUG("IH: D1 flip\n"); + radeon_crtc_handle_flip(rdev, 0); + break; + case 11: /* D2 pflip */ + DRM_DEBUG("IH: D2 flip\n"); + radeon_crtc_handle_flip(rdev, 1); + break; case 19: /* HPD/DAC hotplug */ switch (src_data) { case 0: diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c index b2d4c91e6272..99495513f6b1 100644 --- a/drivers/gpu/drm/radeon/r600_dma.c +++ b/drivers/gpu/drm/radeon/r600_dma.c @@ -124,15 +124,6 @@ int r600_dma_resume(struct radeon_device *rdev) u32 rb_bufsz; int r; - /* Reset dma */ - if (rdev->family >= CHIP_RV770) - WREG32(SRBM_SOFT_RESET, RV770_SOFT_RESET_DMA); - else - WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL, 0); WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL, 0); diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c index e4cc9b314ce9..813db8de52b7 100644 --- a/drivers/gpu/drm/radeon/r600_dpm.c +++ b/drivers/gpu/drm/radeon/r600_dpm.c @@ -158,16 +158,18 @@ u32 r600_dpm_get_vblank_time(struct radeon_device *rdev) u32 line_time_us, vblank_lines; u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - radeon_crtc = to_radeon_crtc(crtc); - if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) { - line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) / - radeon_crtc->hw_mode.clock; - vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end - - radeon_crtc->hw_mode.crtc_vdisplay + - (radeon_crtc->v_border * 2); - vblank_time_us = vblank_lines * line_time_us; - break; + if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) { + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + radeon_crtc = to_radeon_crtc(crtc); + if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) { + line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) / + radeon_crtc->hw_mode.clock; + vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end - + radeon_crtc->hw_mode.crtc_vdisplay + + (radeon_crtc->v_border * 2); + vblank_time_us = vblank_lines * line_time_us; + break; + } } } @@ -181,14 +183,15 @@ u32 r600_dpm_get_vrefresh(struct radeon_device *rdev) struct radeon_crtc *radeon_crtc; u32 vrefresh = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - radeon_crtc = to_radeon_crtc(crtc); - if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) { - vrefresh = radeon_crtc->hw_mode.vrefresh; - break; + if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) { + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + radeon_crtc = to_radeon_crtc(crtc); + if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) { + vrefresh = radeon_crtc->hw_mode.vrefresh; + break; + } } } - return vrefresh; } diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index e887d027b6d0..b837e9f9f8ce 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -294,6 +294,9 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r u16 *vddc, u16 *vddci, u16 virtual_voltage_id, u16 vbios_voltage_id); +int radeon_atom_get_voltage_evv(struct radeon_device *rdev, + u16 virtual_voltage_id, + u16 *voltage); int radeon_atom_round_to_true_voltage(struct radeon_device *rdev, u8 voltage_type, u16 nominal_voltage, @@ -733,6 +736,12 @@ struct cik_irq_stat_regs { u32 disp_int_cont4; u32 disp_int_cont5; u32 disp_int_cont6; + u32 d1grph_int; + u32 d2grph_int; + u32 d3grph_int; + u32 d4grph_int; + u32 d5grph_int; + u32 d6grph_int; }; union radeon_irq_stat_regs { @@ -742,7 +751,7 @@ union radeon_irq_stat_regs { struct cik_irq_stat_regs cik; }; -#define RADEON_MAX_HPD_PINS 6 +#define RADEON_MAX_HPD_PINS 7 #define RADEON_MAX_CRTCS 6 #define RADEON_MAX_AFMT_BLOCKS 7 @@ -2242,6 +2251,7 @@ struct radeon_device { bool have_disp_power_ref; }; +bool radeon_is_px(struct drm_device *dev); int radeon_device_init(struct radeon_device *rdev, struct drm_device *ddev, struct pci_dev *pdev, @@ -2552,6 +2562,9 @@ void r100_pll_errata_after_index(struct radeon_device *rdev); #define ASIC_IS_DCE64(rdev) ((rdev->family == CHIP_OLAND)) #define ASIC_IS_NODCE(rdev) ((rdev->family == CHIP_HAINAN)) #define ASIC_IS_DCE8(rdev) ((rdev->family >= CHIP_BONAIRE)) +#define ASIC_IS_DCE81(rdev) ((rdev->family == CHIP_KAVERI)) +#define ASIC_IS_DCE82(rdev) ((rdev->family == CHIP_BONAIRE)) +#define ASIC_IS_DCE83(rdev) ((rdev->family == CHIP_KABINI)) #define ASIC_IS_LOMBOK(rdev) ((rdev->ddev->pdev->device == 0x6849) || \ (rdev->ddev->pdev->device == 0x6850) || \ diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index dda02bfc10a4..5600d4c5f981 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -2034,8 +2034,8 @@ static struct radeon_asic ci_asic = { .blit_ring_index = RADEON_RING_TYPE_GFX_INDEX, .dma = &cik_copy_dma, .dma_ring_index = R600_RING_TYPE_DMA_INDEX, - .copy = &cik_copy_dma, - .copy_ring_index = R600_RING_TYPE_DMA_INDEX, + .copy = &cik_copy_cpdma, + .copy_ring_index = RADEON_RING_TYPE_GFX_INDEX, }, .surface = { .set_reg = r600_set_surface_reg, diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 30844814c25a..e2de749327ad 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -447,6 +447,13 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev, } } + /* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */ + if ((dev->pdev->device == 0x9805) && + (dev->pdev->subsystem_vendor == 0x1734) && + (dev->pdev->subsystem_device == 0x11bd)) { + if (*connector_type == DRM_MODE_CONNECTOR_VGA) + return false; + } return true; } @@ -1955,7 +1962,7 @@ static const char *thermal_controller_names[] = { "adm1032", "adm1030", "max6649", - "lm64", + "lm63", /* lm64 */ "f75375", "asc7xxx", }; @@ -1966,7 +1973,7 @@ static const char *pp_lib_thermal_controller_names[] = { "adm1032", "adm1030", "max6649", - "lm64", + "lm63", /* lm64 */ "f75375", "RV6xx", "RV770", @@ -2273,19 +2280,31 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r (controller->ucFanParameters & ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); rdev->pm.int_thermal_type = THERMAL_TYPE_KV; - } else if ((controller->ucType == - ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) || - (controller->ucType == - ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) || - (controller->ucType == - ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL)) { - DRM_INFO("Special thermal controller config\n"); + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) { + DRM_INFO("External GPIO thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL_GPIO; + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) { + DRM_INFO("ADT7473 with internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_ADT7473_WITH_INTERNAL; + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL) { + DRM_INFO("EMC2103 with internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EMC2103_WITH_INTERNAL; } else if (controller->ucType < ARRAY_SIZE(pp_lib_thermal_controller_names)) { DRM_INFO("Possible %s thermal controller at 0x%02x %s fan control\n", pp_lib_thermal_controller_names[controller->ucType], controller->ucI2cAddress >> 1, (controller->ucFanParameters & ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL; i2c_bus = radeon_lookup_i2c_gpio(rdev, controller->ucI2cLine); rdev->pm.i2c_bus = radeon_i2c_lookup(rdev, &i2c_bus); if (rdev->pm.i2c_bus) { @@ -3228,6 +3247,41 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r return 0; } +union get_voltage_info { + struct _GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 in; + struct _GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 evv_out; +}; + +int radeon_atom_get_voltage_evv(struct radeon_device *rdev, + u16 virtual_voltage_id, + u16 *voltage) +{ + int index = GetIndexIntoMasterTable(COMMAND, GetVoltageInfo); + u32 entry_id; + u32 count = rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count; + union get_voltage_info args; + + for (entry_id = 0; entry_id < count; entry_id++) { + if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].v == + virtual_voltage_id) + break; + } + + if (entry_id >= count) + return -EINVAL; + + args.in.ucVoltageType = VOLTAGE_TYPE_VDDC; + args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE; + args.in.ulSCLKFreq = + cpu_to_le32(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk); + + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + + *voltage = le16_to_cpu(args.evv_out.usVoltageLevel); + + return 0; +} + int radeon_atom_get_voltage_gpio_settings(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type, u32 *gpio_value, u32 *gpio_mask) diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index fa9a9c02751e..a9fb0d016d38 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -59,7 +59,7 @@ struct atpx_mux { u16 mux; } __packed; -bool radeon_is_px(void) { +bool radeon_has_atpx(void) { return radeon_atpx_priv.atpx_detected; } @@ -528,6 +528,13 @@ static bool radeon_atpx_detect(void) has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); } + /* some newer PX laptops mark the dGPU as a non-VGA display device */ + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { + vga_count++; + + has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); + } + if (has_atpx && vga_count == 2) { acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer); printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n", diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index b3633d9a5317..9ab30976287d 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -196,6 +196,20 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev) } } + if (!found) { + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { + dhandle = ACPI_HANDLE(&pdev->dev); + if (!dhandle) + continue; + + status = acpi_get_handle(dhandle, "ATRM", &atrm_handle); + if (!ACPI_FAILURE(status)) { + found = true; + break; + } + } + } + if (!found) return false; diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 82d4f865546e..4d36b9e86275 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1402,7 +1402,7 @@ bool radeon_connector_is_dp12_capable(struct drm_connector *connector) struct radeon_device *rdev = dev->dev_private; if (ASIC_IS_DCE5(rdev) && - (rdev->clock.dp_extclk >= 53900) && + (rdev->clock.default_dispclk >= 53900) && radeon_connector_encoder_is_hbr2(connector)) { return true; } diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index dfb5a1db87d4..7f2d6c0d11c1 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -97,6 +97,12 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) uint32_t domain = r->write_domain ? r->write_domain : r->read_domains; + if (domain & RADEON_GEM_DOMAIN_CPU) { + DRM_ERROR("RADEON_GEM_DOMAIN_CPU is not valid " + "for command submission\n"); + return -EINVAL; + } + p->relocs[i].lobj.domain = domain; if (domain == RADEON_GEM_DOMAIN_VRAM) domain |= RADEON_GEM_DOMAIN_GTT; @@ -276,10 +282,17 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) return -EINVAL; /* we only support VM on some SI+ rings */ - if ((p->rdev->asic->ring[p->ring]->cs_parse == NULL) && - ((p->cs_flags & RADEON_CS_USE_VM) == 0)) { - DRM_ERROR("Ring %d requires VM!\n", p->ring); - return -EINVAL; + if ((p->cs_flags & RADEON_CS_USE_VM) == 0) { + if (p->rdev->asic->ring[p->ring]->cs_parse == NULL) { + DRM_ERROR("Ring %d requires VM!\n", p->ring); + return -EINVAL; + } + } else { + if (p->rdev->asic->ring[p->ring]->ib_parse == NULL) { + DRM_ERROR("VM not supported on ring %d!\n", + p->ring); + return -EINVAL; + } } } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 044bc98fb459..e39026cc7d07 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -102,11 +102,14 @@ static const char radeon_family_name[][16] = { "LAST", }; -#if defined(CONFIG_VGA_SWITCHEROO) -bool radeon_is_px(void); -#else -static inline bool radeon_is_px(void) { return false; } -#endif +bool radeon_is_px(struct drm_device *dev) +{ + struct radeon_device *rdev = dev->dev_private; + + if (rdev->flags & RADEON_IS_PX) + return true; + return false; +} /** * radeon_program_register_sequence - program an array of registers. @@ -1082,7 +1085,7 @@ static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero { struct drm_device *dev = pci_get_drvdata(pdev); - if (radeon_is_px() && state == VGA_SWITCHEROO_OFF) + if (radeon_is_px(dev) && state == VGA_SWITCHEROO_OFF) return; if (state == VGA_SWITCHEROO_ON) { @@ -1303,9 +1306,7 @@ int radeon_device_init(struct radeon_device *rdev, * ignore it */ vga_client_register(rdev->pdev, rdev, NULL, radeon_vga_set_decode); - if (radeon_runtime_pm == 1) - runtime = true; - if ((radeon_runtime_pm == -1) && radeon_is_px()) + if (rdev->flags & RADEON_IS_PX) runtime = true; vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops, runtime); if (runtime) @@ -1313,7 +1314,7 @@ int radeon_device_init(struct radeon_device *rdev, r = radeon_init(rdev); if (r) - return r; + goto failed; r = radeon_ib_ring_tests(rdev); if (r) @@ -1333,7 +1334,7 @@ int radeon_device_init(struct radeon_device *rdev, radeon_agp_disable(rdev); r = radeon_init(rdev); if (r) - return r; + goto failed; } if ((radeon_testing & 1)) { @@ -1355,6 +1356,11 @@ int radeon_device_init(struct radeon_device *rdev, DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n"); } return 0; + +failed: + if (runtime) + vga_switcheroo_fini_domain_pm_ops(rdev->dev); + return r; } static void radeon_debugfs_remove_files(struct radeon_device *rdev); @@ -1375,6 +1381,8 @@ void radeon_device_fini(struct radeon_device *rdev) radeon_bo_evict_vram(rdev); radeon_fini(rdev); vga_switcheroo_unregister_client(rdev->pdev); + if (rdev->flags & RADEON_IS_PX) + vga_switcheroo_fini_domain_pm_ops(rdev->dev); vga_client_register(rdev->pdev, NULL, NULL, NULL); if (rdev->rio_mem) pci_iounmap(rdev->pdev, rdev->rio_mem); @@ -1535,6 +1543,10 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon) radeon_restore_bios_scratch_regs(rdev); + /* set the power state here in case we are a PX system or headless */ + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) + radeon_pm_compute_clocks(rdev); + if (fbcon) { radeon_fbdev_set_suspend(rdev, 0); console_unlock(); @@ -1595,7 +1607,6 @@ int radeon_gpu_reset(struct radeon_device *rdev) radeon_save_bios_scratch_regs(rdev); /* block TTM */ resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev); - radeon_pm_suspend(rdev); radeon_suspend(rdev); for (i = 0; i < RADEON_NUM_RINGS; ++i) { @@ -1641,9 +1652,24 @@ retry: } } - radeon_pm_resume(rdev); + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) { + /* do dpm late init */ + r = radeon_pm_late_init(rdev); + if (r) { + rdev->pm.dpm_enabled = false; + DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); + } + } else { + /* resume old pm late */ + radeon_pm_resume(rdev); + } + drm_helper_resume_force_mode(rdev->ddev); + /* set the power state here in case we are a PX system or headless */ + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) + radeon_pm_compute_clocks(rdev); + ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched); if (r) { /* bad news, how to tell it to userspace ? */ diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index fbd8b930f2be..11d06c7b5afa 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -282,6 +282,10 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id) u32 update_pending; int vpos, hpos; + /* can happen during initialization */ + if (radeon_crtc == NULL) + return; + spin_lock_irqsave(&rdev->ddev->event_lock, flags); work = radeon_crtc->unpin_work; if (work == NULL || @@ -751,6 +755,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector) struct radeon_device *rdev = dev->dev_private; int ret = 0; + /* don't leak the edid if we already fetched it in detect() */ + if (radeon_connector->edid) + goto got_edid; + /* on hw with routers, select right port */ if (radeon_connector->router.ddc_valid) radeon_router_select_ddc_port(radeon_connector); @@ -790,8 +798,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector) radeon_connector->edid = radeon_bios_get_hardcoded_edid(rdev); } if (radeon_connector->edid) { +got_edid: drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid); ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid); + drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid); return ret; } drm_mode_connector_update_edid_property(&radeon_connector->base, NULL); diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index f633c2782170..9c0056f0a68a 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -113,6 +113,7 @@ extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int flags, int *vpos, int *hpos, ktime_t *stime, ktime_t *etime); +extern bool radeon_is_px(struct drm_device *dev); extern const struct drm_ioctl_desc radeon_ioctls_kms[]; extern int radeon_max_kms_ioctl; int radeon_mmap(struct file *filp, struct vm_area_struct *vma); @@ -142,11 +143,9 @@ void radeon_debugfs_cleanup(struct drm_minor *minor); #if defined(CONFIG_VGA_SWITCHEROO) void radeon_register_atpx_handler(void); void radeon_unregister_atpx_handler(void); -bool radeon_is_px(void); #else static inline void radeon_register_atpx_handler(void) {} static inline void radeon_unregister_atpx_handler(void) {} -static inline bool radeon_is_px(void) { return false; } #endif int radeon_no_wb; @@ -403,12 +402,7 @@ static int radeon_pmops_runtime_suspend(struct device *dev) struct drm_device *drm_dev = pci_get_drvdata(pdev); int ret; - if (radeon_runtime_pm == 0) { - pm_runtime_forbid(dev); - return -EBUSY; - } - - if (radeon_runtime_pm == -1 && !radeon_is_px()) { + if (!radeon_is_px(drm_dev)) { pm_runtime_forbid(dev); return -EBUSY; } @@ -432,10 +426,7 @@ static int radeon_pmops_runtime_resume(struct device *dev) struct drm_device *drm_dev = pci_get_drvdata(pdev); int ret; - if (radeon_runtime_pm == 0) - return -EINVAL; - - if (radeon_runtime_pm == -1 && !radeon_is_px()) + if (!radeon_is_px(drm_dev)) return -EINVAL; drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; @@ -460,14 +451,7 @@ static int radeon_pmops_runtime_idle(struct device *dev) struct drm_device *drm_dev = pci_get_drvdata(pdev); struct drm_crtc *crtc; - if (radeon_runtime_pm == 0) { - pm_runtime_forbid(dev); - return -EBUSY; - } - - /* are we PX enabled? */ - if (radeon_runtime_pm == -1 && !radeon_is_px()) { - DRM_DEBUG_DRIVER("failing to power off - not px\n"); + if (!radeon_is_px(drm_dev)) { pm_runtime_forbid(dev); return -EBUSY; } diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h index 614ad549297f..9da5da4ffd17 100644 --- a/drivers/gpu/drm/radeon/radeon_family.h +++ b/drivers/gpu/drm/radeon/radeon_family.h @@ -115,6 +115,7 @@ enum radeon_chip_flags { RADEON_NEW_MEMMAP = 0x00400000UL, RADEON_IS_PCI = 0x00800000UL, RADEON_IS_IGPGART = 0x01000000UL, + RADEON_IS_PX = 0x02000000UL, }; #endif diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 66ed3ea71440..0bc9106ef435 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -35,9 +35,9 @@ #include <linux/pm_runtime.h> #if defined(CONFIG_VGA_SWITCHEROO) -bool radeon_is_px(void); +bool radeon_has_atpx(void); #else -static inline bool radeon_is_px(void) { return false; } +static inline bool radeon_has_atpx(void) { return false; } #endif /** @@ -107,6 +107,11 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) flags |= RADEON_IS_PCI; } + if ((radeon_runtime_pm != 0) && + radeon_has_atpx() && + ((flags & RADEON_IS_IGP) == 0)) + flags |= RADEON_IS_PX; + /* radeon_device_init should report only fatal error * like memory allocation failure or iomapping failure, * or memory manager initialization failure, it must @@ -137,8 +142,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) "Error during ACPI methods call\n"); } - if ((radeon_runtime_pm == 1) || - ((radeon_runtime_pm == -1) && radeon_is_px())) { + if (radeon_is_px(dev)) { pm_runtime_use_autosuspend(dev->dev); pm_runtime_set_autosuspend_delay(dev->dev, 5000); pm_runtime_set_active(dev->dev); @@ -250,7 +254,14 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file } break; case RADEON_INFO_ACCEL_WORKING2: - *value = rdev->accel_working; + if (rdev->family == CHIP_HAWAII) { + if (rdev->accel_working) + *value = 2; + else + *value = 0; + } else { + *value = rdev->accel_working; + } break; case RADEON_INFO_TILING_CONFIG: if (rdev->family >= CHIP_BONAIRE) diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 08595cf90b01..11bb88afbac1 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -586,22 +586,30 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) rbo = container_of(bo, struct radeon_bo, tbo); radeon_bo_check_tiling(rbo, 0, 0); rdev = rbo->rdev; - if (bo->mem.mem_type == TTM_PL_VRAM) { - size = bo->mem.num_pages << PAGE_SHIFT; - offset = bo->mem.start << PAGE_SHIFT; - if ((offset + size) > rdev->mc.visible_vram_size) { - /* hurrah the memory is not visible ! */ - radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM); - rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT; - r = ttm_bo_validate(bo, &rbo->placement, false, false); - if (unlikely(r != 0)) - return r; - offset = bo->mem.start << PAGE_SHIFT; - /* this should not happen */ - if ((offset + size) > rdev->mc.visible_vram_size) - return -EINVAL; - } + if (bo->mem.mem_type != TTM_PL_VRAM) + return 0; + + size = bo->mem.num_pages << PAGE_SHIFT; + offset = bo->mem.start << PAGE_SHIFT; + if ((offset + size) <= rdev->mc.visible_vram_size) + return 0; + + /* hurrah the memory is not visible ! */ + radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM); + rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT; + r = ttm_bo_validate(bo, &rbo->placement, false, false); + if (unlikely(r == -ENOMEM)) { + radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT); + return ttm_bo_validate(bo, &rbo->placement, false, false); + } else if (unlikely(r != 0)) { + return r; } + + offset = bo->mem.start << PAGE_SHIFT; + /* this should never happen */ + if ((offset + size) > rdev->mc.visible_vram_size) + return -EINVAL; + return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 8e8153e471c2..cfb513f933d5 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -361,6 +361,11 @@ static ssize_t radeon_set_pm_profile(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct radeon_device *rdev = ddev->dev_private; + /* Can't set profile when the card is off */ + if ((rdev->flags & RADEON_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + mutex_lock(&rdev->pm.mutex); if (rdev->pm.pm_method == PM_METHOD_PROFILE) { if (strncmp("default", buf, strlen("default")) == 0) @@ -409,6 +414,13 @@ static ssize_t radeon_set_pm_method(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct radeon_device *rdev = ddev->dev_private; + /* Can't set method when the card is off */ + if ((rdev->flags & RADEON_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) { + count = -EINVAL; + goto fail; + } + /* we don't support the legacy modes with dpm */ if (rdev->pm.pm_method == PM_METHOD_DPM) { count = -EINVAL; @@ -472,7 +484,12 @@ static ssize_t radeon_set_dpm_state(struct device *dev, goto fail; } mutex_unlock(&rdev->pm.mutex); - radeon_pm_compute_clocks(rdev); + + /* Can't set dpm state when the card is off */ + if (!(rdev->flags & RADEON_IS_PX) || + (ddev->switch_power_state == DRM_SWITCH_POWER_ON)) + radeon_pm_compute_clocks(rdev); + fail: return count; } @@ -485,6 +502,10 @@ static ssize_t radeon_get_dpm_forced_performance_level(struct device *dev, struct radeon_device *rdev = ddev->dev_private; enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level; + if ((rdev->flags & RADEON_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return snprintf(buf, PAGE_SIZE, "off\n"); + return snprintf(buf, PAGE_SIZE, "%s\n", (level == RADEON_DPM_FORCED_LEVEL_AUTO) ? "auto" : (level == RADEON_DPM_FORCED_LEVEL_LOW) ? "low" : "high"); @@ -500,6 +521,11 @@ static ssize_t radeon_set_dpm_forced_performance_level(struct device *dev, enum radeon_dpm_forced_level level; int ret = 0; + /* Can't force performance level when the card is off */ + if ((rdev->flags & RADEON_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + mutex_lock(&rdev->pm.mutex); if (strncmp("low", buf, strlen("low")) == 0) { level = RADEON_DPM_FORCED_LEVEL_LOW; @@ -538,8 +564,14 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev, char *buf) { struct radeon_device *rdev = dev_get_drvdata(dev); + struct drm_device *ddev = rdev->ddev; int temp; + /* Can't get temperature when the card is off */ + if ((rdev->flags & RADEON_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + if (rdev->asic->pm.get_temperature) temp = radeon_get_temperature(rdev); else @@ -603,7 +635,6 @@ static const struct attribute_group *hwmon_groups[] = { static int radeon_hwmon_init(struct radeon_device *rdev) { int err = 0; - struct device *hwmon_dev; switch (rdev->pm.int_thermal_type) { case THERMAL_TYPE_RV6XX: @@ -616,11 +647,11 @@ static int radeon_hwmon_init(struct radeon_device *rdev) case THERMAL_TYPE_KV: if (rdev->asic->pm.get_temperature == NULL) return err; - hwmon_dev = hwmon_device_register_with_groups(rdev->dev, - "radeon", rdev, - hwmon_groups); - if (IS_ERR(hwmon_dev)) { - err = PTR_ERR(hwmon_dev); + rdev->pm.int_hwmon_dev = hwmon_device_register_with_groups(rdev->dev, + "radeon", rdev, + hwmon_groups); + if (IS_ERR(rdev->pm.int_hwmon_dev)) { + err = PTR_ERR(rdev->pm.int_hwmon_dev); dev_err(rdev->dev, "Unable to register hwmon device: %d\n", err); } @@ -632,6 +663,12 @@ static int radeon_hwmon_init(struct radeon_device *rdev) return err; } +static void radeon_hwmon_fini(struct radeon_device *rdev) +{ + if (rdev->pm.int_hwmon_dev) + hwmon_device_unregister(rdev->pm.int_hwmon_dev); +} + static void radeon_dpm_thermal_work_handler(struct work_struct *work) { struct radeon_device *rdev = @@ -1041,7 +1078,6 @@ static void radeon_pm_resume_dpm(struct radeon_device *rdev) if (ret) goto dpm_resume_fail; rdev->pm.dpm_enabled = true; - radeon_pm_compute_clocks(rdev); return; dpm_resume_fail: @@ -1235,10 +1271,7 @@ int radeon_pm_init(struct radeon_device *rdev) case CHIP_RV670: case CHIP_RS780: case CHIP_RS880: - case CHIP_BARTS: - case CHIP_TURKS: - case CHIP_CAICOS: - case CHIP_CAYMAN: + case CHIP_RV770: /* DPM requires the RLC, RV770+ dGPU requires SMC */ if (!rdev->rlc_fw) rdev->pm.pm_method = PM_METHOD_PROFILE; @@ -1251,7 +1284,6 @@ int radeon_pm_init(struct radeon_device *rdev) else rdev->pm.pm_method = PM_METHOD_PROFILE; break; - case CHIP_RV770: case CHIP_RV730: case CHIP_RV710: case CHIP_RV740: @@ -1263,6 +1295,10 @@ int radeon_pm_init(struct radeon_device *rdev) case CHIP_PALM: case CHIP_SUMO: case CHIP_SUMO2: + case CHIP_BARTS: + case CHIP_TURKS: + case CHIP_CAICOS: + case CHIP_CAYMAN: case CHIP_ARUBA: case CHIP_TAHITI: case CHIP_PITCAIRN: @@ -1331,6 +1367,8 @@ static void radeon_pm_fini_old(struct radeon_device *rdev) device_remove_file(rdev->dev, &dev_attr_power_method); } + radeon_hwmon_fini(rdev); + if (rdev->pm.power_state) kfree(rdev->pm.power_state); } @@ -1350,6 +1388,8 @@ static void radeon_pm_fini_dpm(struct radeon_device *rdev) } radeon_dpm_fini(rdev); + radeon_hwmon_fini(rdev); + if (rdev->pm.power_state) kfree(rdev->pm.power_state); } @@ -1375,12 +1415,14 @@ static void radeon_pm_compute_clocks_old(struct radeon_device *rdev) rdev->pm.active_crtcs = 0; rdev->pm.active_crtc_count = 0; - list_for_each_entry(crtc, - &ddev->mode_config.crtc_list, head) { - radeon_crtc = to_radeon_crtc(crtc); - if (radeon_crtc->enabled) { - rdev->pm.active_crtcs |= (1 << radeon_crtc->crtc_id); - rdev->pm.active_crtc_count++; + if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) { + list_for_each_entry(crtc, + &ddev->mode_config.crtc_list, head) { + radeon_crtc = to_radeon_crtc(crtc); + if (radeon_crtc->enabled) { + rdev->pm.active_crtcs |= (1 << radeon_crtc->crtc_id); + rdev->pm.active_crtc_count++; + } } } @@ -1447,12 +1489,14 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev) /* update active crtc counts */ rdev->pm.dpm.new_active_crtcs = 0; rdev->pm.dpm.new_active_crtc_count = 0; - list_for_each_entry(crtc, - &ddev->mode_config.crtc_list, head) { - radeon_crtc = to_radeon_crtc(crtc); - if (crtc->enabled) { - rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id); - rdev->pm.dpm.new_active_crtc_count++; + if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) { + list_for_each_entry(crtc, + &ddev->mode_config.crtc_list, head) { + radeon_crtc = to_radeon_crtc(crtc); + if (crtc->enabled) { + rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id); + rdev->pm.dpm.new_active_crtc_count++; + } } } @@ -1578,8 +1622,12 @@ static int radeon_debugfs_pm_info(struct seq_file *m, void *data) struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; struct radeon_device *rdev = dev->dev_private; + struct drm_device *ddev = rdev->ddev; - if (rdev->pm.dpm_enabled) { + if ((rdev->flags & RADEON_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) { + seq_printf(m, "PX asic powered off\n"); + } else if (rdev->pm.dpm_enabled) { mutex_lock(&rdev->pm.mutex); if (rdev->asic->dpm.debugfs_print_current_performance_level) radeon_dpm_debugfs_print_current_performance_level(rdev, m); diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 15e44a7281ab..8391fca52a58 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -257,6 +257,7 @@ int radeon_ib_ring_tests(struct radeon_device *rdev) r = radeon_ib_test(rdev, i, ring); if (r) { ring->ready = false; + rdev->needs_reset = false; if (i == RADEON_RING_TYPE_GFX_INDEX) { /* oh, oh, that's really bad */ diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c index 9006b32d5eed..eb7b60047e86 100644 --- a/drivers/gpu/drm/radeon/radeon_semaphore.c +++ b/drivers/gpu/drm/radeon/radeon_semaphore.c @@ -34,7 +34,7 @@ int radeon_semaphore_create(struct radeon_device *rdev, struct radeon_semaphore **semaphore) { - uint32_t *cpu_addr; + uint64_t *cpu_addr; int i, r; *semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL); diff --git a/drivers/gpu/drm/radeon/radeon_ucode.h b/drivers/gpu/drm/radeon/radeon_ucode.h index a77cd274dfc3..58d12938c0b8 100644 --- a/drivers/gpu/drm/radeon/radeon_ucode.h +++ b/drivers/gpu/drm/radeon/radeon_ucode.h @@ -57,9 +57,14 @@ #define BTC_MC_UCODE_SIZE 6024 #define CAYMAN_MC_UCODE_SIZE 6037 #define SI_MC_UCODE_SIZE 7769 +#define TAHITI_MC_UCODE_SIZE 7808 +#define PITCAIRN_MC_UCODE_SIZE 7775 +#define VERDE_MC_UCODE_SIZE 7875 #define OLAND_MC_UCODE_SIZE 7863 -#define CIK_MC_UCODE_SIZE 7866 +#define BONAIRE_MC_UCODE_SIZE 7866 +#define BONAIRE_MC2_UCODE_SIZE 7948 #define HAWAII_MC_UCODE_SIZE 7933 +#define HAWAII_MC2_UCODE_SIZE 8091 /* SDMA */ #define CIK_SDMA_UCODE_SIZE 1050 diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 3e6804b2b2ef..414e07928693 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -465,6 +465,10 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p, cmd = radeon_get_ib_value(p, p->idx) >> 1; if (cmd < 0x4) { + if (end <= start) { + DRM_ERROR("invalid reloc offset %X!\n", offset); + return -EINVAL; + } if ((end - start) < buf_sizes[cmd]) { DRM_ERROR("buffer (%d) to small (%d / %d)!\n", cmd, (unsigned)(end - start), buf_sizes[cmd]); diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 72d3616de08e..95b693c11640 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -646,8 +646,10 @@ int rs600_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr) return -EINVAL; } addr = addr & 0xFFFFFFFFFFFFF000ULL; - addr |= R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED; - addr |= R600_PTE_READABLE | R600_PTE_WRITEABLE; + if (addr != rdev->dummy_page.addr) + addr |= R600_PTE_VALID | R600_PTE_READABLE | + R600_PTE_WRITEABLE; + addr |= R600_PTE_SYSTEM | R600_PTE_SNOOPED; writeq(addr, ptr + (i * 8)); return 0; } diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c index b5f63f5e22a3..8fcb932a3a55 100644 --- a/drivers/gpu/drm/radeon/rv770_dpm.c +++ b/drivers/gpu/drm/radeon/rv770_dpm.c @@ -2332,12 +2332,6 @@ void rv770_get_engine_memory_ss(struct radeon_device *rdev) pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss, ASIC_INTERNAL_MEMORY_SS, 0); - /* disable ss, causes hangs on some cayman boards */ - if (rdev->family == CHIP_CAYMAN) { - pi->sclk_ss = false; - pi->mclk_ss = false; - } - if (pi->sclk_ss || pi->mclk_ss) pi->dynamic_ss = true; else diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 9a124d0608b3..559564c1dc97 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -39,30 +39,35 @@ MODULE_FIRMWARE("radeon/TAHITI_pfp.bin"); MODULE_FIRMWARE("radeon/TAHITI_me.bin"); MODULE_FIRMWARE("radeon/TAHITI_ce.bin"); MODULE_FIRMWARE("radeon/TAHITI_mc.bin"); +MODULE_FIRMWARE("radeon/TAHITI_mc2.bin"); MODULE_FIRMWARE("radeon/TAHITI_rlc.bin"); MODULE_FIRMWARE("radeon/TAHITI_smc.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_pfp.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_me.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_ce.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_mc.bin"); +MODULE_FIRMWARE("radeon/PITCAIRN_mc2.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_rlc.bin"); MODULE_FIRMWARE("radeon/PITCAIRN_smc.bin"); MODULE_FIRMWARE("radeon/VERDE_pfp.bin"); MODULE_FIRMWARE("radeon/VERDE_me.bin"); MODULE_FIRMWARE("radeon/VERDE_ce.bin"); MODULE_FIRMWARE("radeon/VERDE_mc.bin"); +MODULE_FIRMWARE("radeon/VERDE_mc2.bin"); MODULE_FIRMWARE("radeon/VERDE_rlc.bin"); MODULE_FIRMWARE("radeon/VERDE_smc.bin"); MODULE_FIRMWARE("radeon/OLAND_pfp.bin"); MODULE_FIRMWARE("radeon/OLAND_me.bin"); MODULE_FIRMWARE("radeon/OLAND_ce.bin"); MODULE_FIRMWARE("radeon/OLAND_mc.bin"); +MODULE_FIRMWARE("radeon/OLAND_mc2.bin"); MODULE_FIRMWARE("radeon/OLAND_rlc.bin"); MODULE_FIRMWARE("radeon/OLAND_smc.bin"); MODULE_FIRMWARE("radeon/HAINAN_pfp.bin"); MODULE_FIRMWARE("radeon/HAINAN_me.bin"); MODULE_FIRMWARE("radeon/HAINAN_ce.bin"); MODULE_FIRMWARE("radeon/HAINAN_mc.bin"); +MODULE_FIRMWARE("radeon/HAINAN_mc2.bin"); MODULE_FIRMWARE("radeon/HAINAN_rlc.bin"); MODULE_FIRMWARE("radeon/HAINAN_smc.bin"); @@ -1467,36 +1472,33 @@ int si_mc_load_microcode(struct radeon_device *rdev) const __be32 *fw_data; u32 running, blackout = 0; u32 *io_mc_regs; - int i, ucode_size, regs_size; + int i, regs_size, ucode_size; if (!rdev->mc_fw) return -EINVAL; + ucode_size = rdev->mc_fw->size / 4; + switch (rdev->family) { case CHIP_TAHITI: io_mc_regs = (u32 *)&tahiti_io_mc_regs; - ucode_size = SI_MC_UCODE_SIZE; regs_size = TAHITI_IO_MC_REGS_SIZE; break; case CHIP_PITCAIRN: io_mc_regs = (u32 *)&pitcairn_io_mc_regs; - ucode_size = SI_MC_UCODE_SIZE; regs_size = TAHITI_IO_MC_REGS_SIZE; break; case CHIP_VERDE: default: io_mc_regs = (u32 *)&verde_io_mc_regs; - ucode_size = SI_MC_UCODE_SIZE; regs_size = TAHITI_IO_MC_REGS_SIZE; break; case CHIP_OLAND: io_mc_regs = (u32 *)&oland_io_mc_regs; - ucode_size = OLAND_MC_UCODE_SIZE; regs_size = TAHITI_IO_MC_REGS_SIZE; break; case CHIP_HAINAN: io_mc_regs = (u32 *)&hainan_io_mc_regs; - ucode_size = OLAND_MC_UCODE_SIZE; regs_size = TAHITI_IO_MC_REGS_SIZE; break; } @@ -1552,7 +1554,7 @@ static int si_init_microcode(struct radeon_device *rdev) const char *chip_name; const char *rlc_chip_name; size_t pfp_req_size, me_req_size, ce_req_size, rlc_req_size, mc_req_size; - size_t smc_req_size; + size_t smc_req_size, mc2_req_size; char fw_name[30]; int err; @@ -1567,6 +1569,7 @@ static int si_init_microcode(struct radeon_device *rdev) ce_req_size = SI_CE_UCODE_SIZE * 4; rlc_req_size = SI_RLC_UCODE_SIZE * 4; mc_req_size = SI_MC_UCODE_SIZE * 4; + mc2_req_size = TAHITI_MC_UCODE_SIZE * 4; smc_req_size = ALIGN(TAHITI_SMC_UCODE_SIZE, 4); break; case CHIP_PITCAIRN: @@ -1577,6 +1580,7 @@ static int si_init_microcode(struct radeon_device *rdev) ce_req_size = SI_CE_UCODE_SIZE * 4; rlc_req_size = SI_RLC_UCODE_SIZE * 4; mc_req_size = SI_MC_UCODE_SIZE * 4; + mc2_req_size = PITCAIRN_MC_UCODE_SIZE * 4; smc_req_size = ALIGN(PITCAIRN_SMC_UCODE_SIZE, 4); break; case CHIP_VERDE: @@ -1587,6 +1591,7 @@ static int si_init_microcode(struct radeon_device *rdev) ce_req_size = SI_CE_UCODE_SIZE * 4; rlc_req_size = SI_RLC_UCODE_SIZE * 4; mc_req_size = SI_MC_UCODE_SIZE * 4; + mc2_req_size = VERDE_MC_UCODE_SIZE * 4; smc_req_size = ALIGN(VERDE_SMC_UCODE_SIZE, 4); break; case CHIP_OLAND: @@ -1596,7 +1601,7 @@ static int si_init_microcode(struct radeon_device *rdev) me_req_size = SI_PM4_UCODE_SIZE * 4; ce_req_size = SI_CE_UCODE_SIZE * 4; rlc_req_size = SI_RLC_UCODE_SIZE * 4; - mc_req_size = OLAND_MC_UCODE_SIZE * 4; + mc_req_size = mc2_req_size = OLAND_MC_UCODE_SIZE * 4; smc_req_size = ALIGN(OLAND_SMC_UCODE_SIZE, 4); break; case CHIP_HAINAN: @@ -1606,7 +1611,7 @@ static int si_init_microcode(struct radeon_device *rdev) me_req_size = SI_PM4_UCODE_SIZE * 4; ce_req_size = SI_CE_UCODE_SIZE * 4; rlc_req_size = SI_RLC_UCODE_SIZE * 4; - mc_req_size = OLAND_MC_UCODE_SIZE * 4; + mc_req_size = mc2_req_size = OLAND_MC_UCODE_SIZE * 4; smc_req_size = ALIGN(HAINAN_SMC_UCODE_SIZE, 4); break; default: BUG(); @@ -1659,16 +1664,22 @@ static int si_init_microcode(struct radeon_device *rdev) err = -EINVAL; } - snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name); err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev); - if (err) - goto out; - if (rdev->mc_fw->size != mc_req_size) { + if (err) { + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev); + if (err) + goto out; + } + if ((rdev->mc_fw->size != mc_req_size) && + (rdev->mc_fw->size != mc2_req_size)) { printk(KERN_ERR "si_mc: Bogus length %zu in firmware \"%s\"\n", rdev->mc_fw->size, fw_name); err = -EINVAL; } + DRM_INFO("%s: %zu bytes\n", fw_name, rdev->mc_fw->size); snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name); err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev); @@ -4799,7 +4810,7 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) /* write new base address */ radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | + radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) | WRITE_DATA_DST_SEL(0))); if (vm->id < 8) { @@ -5777,7 +5788,6 @@ int si_irq_set(struct radeon_device *rdev) u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0; u32 hpd1 = 0, hpd2 = 0, hpd3 = 0, hpd4 = 0, hpd5 = 0, hpd6 = 0; u32 grbm_int_cntl = 0; - u32 grph1 = 0, grph2 = 0, grph3 = 0, grph4 = 0, grph5 = 0, grph6 = 0; u32 dma_cntl, dma_cntl1; u32 thermal_int = 0; @@ -5916,16 +5926,22 @@ int si_irq_set(struct radeon_device *rdev) } if (rdev->num_crtc >= 2) { - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, grph1); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, grph2); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); } if (rdev->num_crtc >= 4) { - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); } if (rdev->num_crtc >= 6) { - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, + GRPH_PFLIP_INT_MASK); } if (!ASIC_IS_NODCE(rdev)) { @@ -6082,6 +6098,7 @@ static inline u32 si_get_ih_wptr(struct radeon_device *rdev) tmp = RREG32(IH_RB_CNTL); tmp |= IH_WPTR_OVERFLOW_CLEAR; WREG32(IH_RB_CNTL, tmp); + wptr &= ~RB_OVERFLOW; } return (wptr & rdev->ih.ptr_mask); } @@ -6289,6 +6306,15 @@ restart_ih: break; } break; + case 8: /* D1 page flip */ + case 10: /* D2 page flip */ + case 12: /* D3 page flip */ + case 14: /* D4 page flip */ + case 16: /* D5 page flip */ + case 18: /* D6 page flip */ + DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1); + radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1); + break; case 42: /* HPD hotplug */ switch (src_data) { case 0: diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 0a2f5b4bca43..879e62844b2b 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -6200,7 +6200,7 @@ static void si_parse_pplib_clock_info(struct radeon_device *rdev, if ((rps->class2 & ATOM_PPLIB_CLASSIFICATION2_ULV) && index == 0) { /* XXX disable for A0 tahiti */ - si_pi->ulv.supported = true; + si_pi->ulv.supported = false; si_pi->ulv.pl = *pl; si_pi->ulv.one_pcie_lane_in_ulv = false; si_pi->ulv.volt_change_delay = SISLANDS_ULVVOLTAGECHANGEDELAY_DFLT; diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h index 9239a6d29128..3007cddc7e70 100644 --- a/drivers/gpu/drm/radeon/sid.h +++ b/drivers/gpu/drm/radeon/sid.h @@ -107,8 +107,8 @@ #define SPLL_CHG_STATUS (1 << 1) #define SPLL_CNTL_MODE 0x618 #define SPLL_SW_DIR_CONTROL (1 << 0) -# define SPLL_REFCLK_SEL(x) ((x) << 8) -# define SPLL_REFCLK_SEL_MASK 0xFF00 +# define SPLL_REFCLK_SEL(x) ((x) << 26) +# define SPLL_REFCLK_SEL_MASK (3 << 26) #define CG_SPLL_SPREAD_SPECTRUM 0x620 #define SSEN (1 << 0) diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c index 2da0e17eb960..d9cfa09b2e3f 100644 --- a/drivers/gpu/drm/radeon/trinity_dpm.c +++ b/drivers/gpu/drm/radeon/trinity_dpm.c @@ -1877,7 +1877,16 @@ int trinity_dpm_init(struct radeon_device *rdev) for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) pi->at[i] = TRINITY_AT_DFLT; - pi->enable_bapm = false; + /* There are stability issues reported on with + * bapm enabled when switching between AC and battery + * power. At the same time, some MSI boards hang + * if it's not enabled and dpm is enabled. Just enable + * it for MSI boards right now. + */ + if (rdev->pdev->subsystem_vendor == 0x1462) + pi->enable_bapm = true; + else + pi->enable_bapm = false; pi->enable_nbps_policy = true; pi->enable_sclk_ds = true; pi->enable_gfx_power_gating = true; diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c index d4a68af1a279..c310a0aeebb9 100644 --- a/drivers/gpu/drm/radeon/uvd_v1_0.c +++ b/drivers/gpu/drm/radeon/uvd_v1_0.c @@ -83,7 +83,10 @@ int uvd_v1_0_init(struct radeon_device *rdev) int r; /* raise clocks while booting up the VCPU */ - radeon_set_uvd_clocks(rdev, 53300, 40000); + if (rdev->family < CHIP_RV740) + radeon_set_uvd_clocks(rdev, 10000, 10000); + else + radeon_set_uvd_clocks(rdev, 53300, 40000); r = uvd_v1_0_start(rdev); if (r) @@ -407,7 +410,10 @@ int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring) struct radeon_fence *fence = NULL; int r; - r = radeon_set_uvd_clocks(rdev, 53300, 40000); + if (rdev->family < CHIP_RV740) + r = radeon_set_uvd_clocks(rdev, 10000, 10000); + else + r = radeon_set_uvd_clocks(rdev, 53300, 40000); if (r) { DRM_ERROR("radeon: failed to raise UVD clocks (%d).\n", r); return r; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 171a8203892c..52b47115b5cb 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -84,6 +84,7 @@ static int modeset_init(struct drm_device *dev) if ((priv->num_encoders == 0) || (priv->num_connectors == 0)) { /* oh nos! */ dev_err(dev->dev, "no encoders/connectors found\n"); + drm_mode_config_cleanup(dev); return -ENXIO; } @@ -122,6 +123,7 @@ static int tilcdc_unload(struct drm_device *dev) struct tilcdc_drm_private *priv = dev->dev_private; struct tilcdc_module *mod, *cur; + drm_fbdev_cma_fini(priv->fbdev); drm_kms_helper_poll_fini(dev); drm_mode_config_cleanup(dev); drm_vblank_cleanup(dev); @@ -177,33 +179,37 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) dev->dev_private = priv; priv->wq = alloc_ordered_workqueue("tilcdc", 0); + if (!priv->wq) { + ret = -ENOMEM; + goto fail_free_priv; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(dev->dev, "failed to get memory resource\n"); ret = -EINVAL; - goto fail; + goto fail_free_wq; } priv->mmio = ioremap_nocache(res->start, resource_size(res)); if (!priv->mmio) { dev_err(dev->dev, "failed to ioremap\n"); ret = -ENOMEM; - goto fail; + goto fail_free_wq; } priv->clk = clk_get(dev->dev, "fck"); if (IS_ERR(priv->clk)) { dev_err(dev->dev, "failed to get functional clock\n"); ret = -ENODEV; - goto fail; + goto fail_iounmap; } priv->disp_clk = clk_get(dev->dev, "dpll_disp_ck"); if (IS_ERR(priv->clk)) { dev_err(dev->dev, "failed to get display clock\n"); ret = -ENODEV; - goto fail; + goto fail_put_clk; } #ifdef CONFIG_CPU_FREQ @@ -213,7 +219,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) CPUFREQ_TRANSITION_NOTIFIER); if (ret) { dev_err(dev->dev, "failed to register cpufreq notifier\n"); - goto fail; + goto fail_put_disp_clk; } #endif @@ -258,13 +264,13 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) ret = modeset_init(dev); if (ret < 0) { dev_err(dev->dev, "failed to initialize mode setting\n"); - goto fail; + goto fail_cpufreq_unregister; } ret = drm_vblank_init(dev, 1); if (ret < 0) { dev_err(dev->dev, "failed to initialize vblank\n"); - goto fail; + goto fail_mode_config_cleanup; } pm_runtime_get_sync(dev->dev); @@ -272,7 +278,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) pm_runtime_put_sync(dev->dev); if (ret < 0) { dev_err(dev->dev, "failed to install IRQ handler\n"); - goto fail; + goto fail_vblank_cleanup; } platform_set_drvdata(pdev, dev); @@ -288,13 +294,48 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) priv->fbdev = drm_fbdev_cma_init(dev, bpp, dev->mode_config.num_crtc, dev->mode_config.num_connector); + if (IS_ERR(priv->fbdev)) { + ret = PTR_ERR(priv->fbdev); + goto fail_irq_uninstall; + } drm_kms_helper_poll_init(dev); return 0; -fail: - tilcdc_unload(dev); +fail_irq_uninstall: + pm_runtime_get_sync(dev->dev); + drm_irq_uninstall(dev); + pm_runtime_put_sync(dev->dev); + +fail_vblank_cleanup: + drm_vblank_cleanup(dev); + +fail_mode_config_cleanup: + drm_mode_config_cleanup(dev); + +fail_cpufreq_unregister: + pm_runtime_disable(dev->dev); +#ifdef CONFIG_CPU_FREQ + cpufreq_unregister_notifier(&priv->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +fail_put_disp_clk: + clk_put(priv->disp_clk); +#endif + +fail_put_clk: + clk_put(priv->clk); + +fail_iounmap: + iounmap(priv->mmio); + +fail_free_wq: + flush_workqueue(priv->wq); + destroy_workqueue(priv->wq); + +fail_free_priv: + dev->dev_private = NULL; + kfree(priv); return ret; } @@ -628,10 +669,10 @@ static int __init tilcdc_drm_init(void) static void __exit tilcdc_drm_fini(void) { DBG("fini"); - tilcdc_tfp410_fini(); - tilcdc_slave_fini(); - tilcdc_panel_fini(); platform_driver_unregister(&tilcdc_platform_driver); + tilcdc_panel_fini(); + tilcdc_slave_fini(); + tilcdc_tfp410_fini(); } late_initcall(tilcdc_drm_init); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c index 86c67329b605..b085dcc54fb5 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c @@ -151,6 +151,7 @@ struct panel_connector { static void panel_connector_destroy(struct drm_connector *connector) { struct panel_connector *panel_connector = to_panel_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(panel_connector); } @@ -285,10 +286,8 @@ static void panel_destroy(struct tilcdc_module *mod) { struct panel_module *panel_mod = to_panel_module(mod); - if (panel_mod->timings) { + if (panel_mod->timings) display_timings_release(panel_mod->timings); - kfree(panel_mod->timings); - } tilcdc_module_cleanup(mod); kfree(panel_mod->info); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c index 595068ba2d5e..2f83ffb7f37e 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c @@ -166,6 +166,7 @@ struct slave_connector { static void slave_connector_destroy(struct drm_connector *connector) { struct slave_connector *slave_connector = to_slave_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(slave_connector); } diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c index c38b56b268ac..ce75ac8de4f8 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c @@ -167,6 +167,7 @@ struct tfp410_connector { static void tfp410_connector_destroy(struct drm_connector *connector) { struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(tfp410_connector); } diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index 863bef9f9234..cf4bad2c1d59 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -297,8 +297,10 @@ static void ttm_pool_update_free_locked(struct ttm_page_pool *pool, * * @pool: to free the pages from * @free_all: If set to true will free all pages in pool + * @gfp: GFP flags. **/ -static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free) +static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free, + gfp_t gfp) { unsigned long irq_flags; struct page *p; @@ -309,8 +311,7 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free) if (NUM_PAGES_TO_ALLOC < nr_free) npages_to_free = NUM_PAGES_TO_ALLOC; - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), - GFP_KERNEL); + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp); if (!pages_to_free) { pr_err("Failed to allocate memory for pool free operation\n"); return 0; @@ -382,32 +383,35 @@ out: * * XXX: (dchinner) Deadlock warning! * - * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means - * this can deadlock when called a sc->gfp_mask that is not equal to - * GFP_KERNEL. + * We need to pass sc->gfp_mask to ttm_page_pool_free(). * * This code is crying out for a shrinker per pool.... */ static unsigned long ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - static atomic_t start_pool = ATOMIC_INIT(0); + static DEFINE_MUTEX(lock); + static unsigned start_pool; unsigned i; - unsigned pool_offset = atomic_add_return(1, &start_pool); + unsigned pool_offset; struct ttm_page_pool *pool; int shrink_pages = sc->nr_to_scan; unsigned long freed = 0; - pool_offset = pool_offset % NUM_POOLS; + if (!mutex_trylock(&lock)) + return SHRINK_STOP; + pool_offset = ++start_pool % NUM_POOLS; /* select start pool in round robin fashion */ for (i = 0; i < NUM_POOLS; ++i) { unsigned nr_free = shrink_pages; if (shrink_pages == 0) break; pool = &_manager->pools[(i + pool_offset)%NUM_POOLS]; - shrink_pages = ttm_page_pool_free(pool, nr_free); + shrink_pages = ttm_page_pool_free(pool, nr_free, + sc->gfp_mask); freed += nr_free - shrink_pages; } + mutex_unlock(&lock); return freed; } @@ -706,7 +710,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, } spin_unlock_irqrestore(&pool->lock, irq_flags); if (npages) - ttm_page_pool_free(pool, npages); + ttm_page_pool_free(pool, npages, GFP_KERNEL); } /* @@ -846,7 +850,8 @@ void ttm_page_alloc_fini(void) ttm_pool_mm_shrink_fini(_manager); for (i = 0; i < NUM_POOLS; ++i) - ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES); + ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES, + GFP_KERNEL); kobject_put(&_manager->kobj); _manager = NULL; diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c index fb8259f69839..ca65df144765 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c @@ -411,8 +411,10 @@ static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page) * * @pool: to free the pages from * @nr_free: If set to true will free all pages in pool + * @gfp: GFP flags. **/ -static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free) +static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free, + gfp_t gfp) { unsigned long irq_flags; struct dma_page *dma_p, *tmp; @@ -430,8 +432,7 @@ static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free) npages_to_free, nr_free); } #endif - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), - GFP_KERNEL); + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp); if (!pages_to_free) { pr_err("%s: Failed to allocate memory for pool free operation\n", @@ -530,7 +531,7 @@ static void ttm_dma_free_pool(struct device *dev, enum pool_type type) if (pool->type != type) continue; /* Takes a spinlock.. */ - ttm_dma_page_pool_free(pool, FREE_ALL_PAGES); + ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, GFP_KERNEL); WARN_ON(((pool->npages_in_use + pool->npages_free) != 0)); /* This code path is called after _all_ references to the * struct device has been dropped - so nobody should be @@ -983,7 +984,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev) /* shrink pool if necessary (only on !is_cached pools)*/ if (npages) - ttm_dma_page_pool_free(pool, npages); + ttm_dma_page_pool_free(pool, npages, GFP_KERNEL); ttm->state = tt_unpopulated; } EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); @@ -993,10 +994,7 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); * * XXX: (dchinner) Deadlock warning! * - * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention - * needs to be paid to sc->gfp_mask to determine if this can be done or not. - * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really - * bad. + * We need to pass sc->gfp_mask to ttm_dma_page_pool_free(). * * I'm getting sadder as I hear more pathetical whimpers about needing per-pool * shrinkers @@ -1004,9 +1002,9 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); static unsigned long ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - static atomic_t start_pool = ATOMIC_INIT(0); + static unsigned start_pool; unsigned idx = 0; - unsigned pool_offset = atomic_add_return(1, &start_pool); + unsigned pool_offset; unsigned shrink_pages = sc->nr_to_scan; struct device_pools *p; unsigned long freed = 0; @@ -1014,8 +1012,11 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) if (list_empty(&_manager->pools)) return SHRINK_STOP; - mutex_lock(&_manager->lock); - pool_offset = pool_offset % _manager->npools; + if (!mutex_trylock(&_manager->lock)) + return SHRINK_STOP; + if (!_manager->npools) + goto out; + pool_offset = ++start_pool % _manager->npools; list_for_each_entry(p, &_manager->pools, pools) { unsigned nr_free; @@ -1027,13 +1028,15 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) if (++idx < pool_offset) continue; nr_free = shrink_pages; - shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free); + shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free, + sc->gfp_mask); freed += nr_free - shrink_pages; pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n", p->pool->dev_name, p->pool->name, current->pid, nr_free, shrink_pages); } +out: mutex_unlock(&_manager->lock); return freed; } @@ -1044,7 +1047,8 @@ ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc) struct device_pools *p; unsigned long count = 0; - mutex_lock(&_manager->lock); + if (!mutex_trylock(&_manager->lock)) + return 0; list_for_each_entry(p, &_manager->pools, pools) count += p->pool->npages_free; mutex_unlock(&_manager->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c index 1e80152674b5..4fbcfdb02360 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c @@ -117,10 +117,10 @@ static void vmw_hw_context_destroy(struct vmw_resource *res) (void) vmw_context_binding_state_kill (&container_of(res, struct vmw_user_context, res)->cbs); (void) vmw_gb_context_destroy(res); + mutex_unlock(&dev_priv->binding_mutex); if (dev_priv->pinned_bo != NULL && !dev_priv->query_cid_valid) __vmw_execbuf_release_pinned_bo(dev_priv, NULL); - mutex_unlock(&dev_priv->binding_mutex); mutex_unlock(&dev_priv->cmdbuf_mutex); return; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 0083cbf99edf..fb7c36e93fd4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -688,7 +688,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_err0; } - if (unlikely(dev_priv->prim_bb_mem < dev_priv->vram_size)) + /* + * Limit back buffer size to VRAM size. Remove this once + * screen targets are implemented. + */ + if (dev_priv->prim_bb_mem > dev_priv->vram_size) dev_priv->prim_bb_mem = dev_priv->vram_size; mutex_unlock(&dev_priv->hw_mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index efb575a7996c..a3480c13eb1b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1214,14 +1214,36 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, SVGA3dCmdSurfaceDMA dma; } *cmd; int ret; + SVGA3dCmdSurfaceDMASuffix *suffix; + uint32_t bo_size; cmd = container_of(header, struct vmw_dma_cmd, header); + suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->dma + + header->size - sizeof(*suffix)); + + /* Make sure device and verifier stays in sync. */ + if (unlikely(suffix->suffixSize != sizeof(*suffix))) { + DRM_ERROR("Invalid DMA suffix size.\n"); + return -EINVAL; + } + ret = vmw_translate_guest_ptr(dev_priv, sw_context, &cmd->dma.guest.ptr, &vmw_bo); if (unlikely(ret != 0)) return ret; + /* Make sure DMA doesn't cross BO boundaries. */ + bo_size = vmw_bo->base.num_pages * PAGE_SIZE; + if (unlikely(cmd->dma.guest.ptr.offset > bo_size)) { + DRM_ERROR("Invalid DMA offset.\n"); + return -EINVAL; + } + + bo_size -= cmd->dma.guest.ptr.offset; + if (unlikely(suffix->maximumOffset > bo_size)) + suffix->maximumOffset = bo_size; + ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, user_surface_converter, &cmd->dma.host.sid, NULL); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index ed5ce2a41bbf..1b0f34bd3a03 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -147,7 +147,7 @@ static int vmw_fb_check_var(struct fb_var_screeninfo *var, } if (!vmw_kms_validate_mode_vram(vmw_priv, - info->fix.line_length, + var->xres * var->bits_per_pixel/8, var->yoffset + var->yres)) { DRM_ERROR("Requested geom can not fit in framebuffer\n"); return -EINVAL; @@ -162,6 +162,8 @@ static int vmw_fb_set_par(struct fb_info *info) struct vmw_private *vmw_priv = par->vmw_priv; int ret; + info->fix.line_length = info->var.xres * info->var.bits_per_pixel/8; + ret = vmw_kms_write_svga(vmw_priv, info->var.xres, info->var.yres, info->fix.line_length, par->bpp, par->depth); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index 6ccd993e26bf..6eae14d2a3f7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -180,8 +180,9 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) mutex_lock(&dev_priv->hw_mutex); + vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC); while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0) - vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC); + ; dev_priv->last_read_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 8a650413dea5..c8f8ecf7b282 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1954,6 +1954,14 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }; int i; + u32 assumed_bpp = 2; + + /* + * If using screen objects, then assume 32-bpp because that's what the + * SVGA device is assuming + */ + if (dev_priv->sou_priv) + assumed_bpp = 4; /* Add preferred mode */ { @@ -1964,8 +1972,9 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, mode->vdisplay = du->pref_height; vmw_guess_mode_timing(mode); - if (vmw_kms_validate_mode_vram(dev_priv, mode->hdisplay * 2, - mode->vdisplay)) { + if (vmw_kms_validate_mode_vram(dev_priv, + mode->hdisplay * assumed_bpp, + mode->vdisplay)) { drm_mode_probed_add(connector, mode); } else { drm_mode_destroy(dev, mode); @@ -1987,7 +1996,8 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, bmode->vdisplay > max_height) continue; - if (!vmw_kms_validate_mode_vram(dev_priv, bmode->hdisplay * 2, + if (!vmw_kms_validate_mode_vram(dev_priv, + bmode->hdisplay * assumed_bpp, bmode->vdisplay)) continue; diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c index db9017adfe2b..498b37e39058 100644 --- a/drivers/gpu/host1x/hw/intr_hw.c +++ b/drivers/gpu/host1x/hw/intr_hw.c @@ -47,7 +47,7 @@ static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id) unsigned long reg; int i, id; - for (i = 0; i <= BIT_WORD(host->info->nb_pts); i++) { + for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) { reg = host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i)); for_each_set_bit(id, ®, BITS_PER_LONG) { @@ -64,7 +64,7 @@ static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host) { u32 i; - for (i = 0; i <= BIT_WORD(host->info->nb_pts); ++i) { + for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); ++i) { host1x_sync_writel(host, 0xffffffffu, HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(i)); host1x_sync_writel(host, 0xffffffffu, diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index ec0ae2d1686a..37ac7b5dbd06 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -623,7 +623,8 @@ static int vga_switcheroo_runtime_suspend(struct device *dev) ret = dev->bus->pm->runtime_suspend(dev); if (ret) return ret; - + if (vgasr_priv.handler->switchto) + vgasr_priv.handler->switchto(VGA_SWITCHEROO_IGD); vga_switcheroo_power_switch(pdev, VGA_SWITCHEROO_OFF); return 0; } @@ -659,6 +660,12 @@ int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain * } EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_ops); +void vga_switcheroo_fini_domain_pm_ops(struct device *dev) +{ + dev->pm_domain = NULL; +} +EXPORT_SYMBOL(vga_switcheroo_fini_domain_pm_ops); + static int vga_switcheroo_runtime_resume_hdmi_audio(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c index 1bdcccc54a1d..f745d2c1325e 100644 --- a/drivers/hid/hid-cherry.c +++ b/drivers/hid/hid-cherry.c @@ -28,7 +28,7 @@ static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { + if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { hid_info(hdev, "fixing up Cherry Cymotion report descriptor\n"); rdesc[11] = rdesc[16] = 0xff; rdesc[12] = rdesc[17] = 0x03; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index cc32a6f96c64..7cd42ea30d6d 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -718,6 +718,9 @@ static int hid_scan_main(struct hid_parser *parser, struct hid_item *item) case HID_MAIN_ITEM_TAG_END_COLLECTION: break; case HID_MAIN_ITEM_TAG_INPUT: + /* ignore constant inputs, they will be ignored by hid-input */ + if (data & HID_MAIN_ITEM_CONSTANT) + break; for (i = 0; i < parser->local.usage_index; i++) hid_scan_input_usage(parser, parser->local.usage[i]); break; @@ -839,7 +842,17 @@ struct hid_report *hid_validate_values(struct hid_device *hid, * ->numbered being checked, which may not always be the case when * drivers go to access report values. */ - report = hid->report_enum[type].report_id_hash[id]; + if (id == 0) { + /* + * Validating on id 0 means we should examine the first + * report in the list. + */ + report = list_entry( + hid->report_enum[type].report_list.next, + struct hid_report, list); + } else { + report = hid->report_enum[type].report_id_hash[id]; + } if (!report) { hid_err(hid, "missing %s %u\n", hid_report_names[type], id); return NULL; @@ -1780,8 +1793,6 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) }, - { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2) }, - { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2) }, { HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) }, { HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) }, { HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 22f28d6b33a8..91bc66b4b151 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -292,6 +292,11 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7 0x73f7 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 +#define USB_VENDOR_ID_ELAN 0x04f3 +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN 0x0089 +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B 0x009b +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F 0x016f + #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 @@ -624,8 +629,6 @@ #define USB_DEVICE_ID_MS_PRESENTER_8K_USB 0x0713 #define USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K 0x0730 #define USB_DEVICE_ID_MS_COMFORT_MOUSE_4500 0x076c -#define USB_DEVICE_ID_MS_TOUCH_COVER_2 0x07a7 -#define USB_DEVICE_ID_MS_TYPE_COVER_2 0x07a9 #define USB_VENDOR_ID_MOJO 0x8282 #define USB_DEVICE_ID_RETRO_ADAPTER 0x3201 @@ -830,6 +833,7 @@ #define USB_DEVICE_ID_SYNAPTICS_LTS2 0x1d10 #define USB_DEVICE_ID_SYNAPTICS_HD 0x0ac3 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD 0x1ac3 +#define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 #define USB_VENDOR_ID_THINGM 0x27b8 #define USB_DEVICE_ID_BLINK1 0x01ed diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c index e77696367591..b92bf01a1ae8 100644 --- a/drivers/hid/hid-kye.c +++ b/drivers/hid/hid-kye.c @@ -300,7 +300,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, * - change the button usage range to 4-7 for the extra * buttons */ - if (*rsize >= 74 && + if (*rsize >= 75 && rdesc[61] == 0x05 && rdesc[62] == 0x08 && rdesc[63] == 0x19 && rdesc[64] == 0x08 && rdesc[65] == 0x29 && rdesc[66] == 0x0f && diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c index 9fe9d4ac3114..b8207e0bfdc0 100644 --- a/drivers/hid/hid-lg.c +++ b/drivers/hid/hid-lg.c @@ -345,14 +345,14 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc, struct usb_device_descriptor *udesc; __u16 bcdDevice, rev_maj, rev_min; - if ((drv_data->quirks & LG_RDESC) && *rsize >= 90 && rdesc[83] == 0x26 && + if ((drv_data->quirks & LG_RDESC) && *rsize >= 91 && rdesc[83] == 0x26 && rdesc[84] == 0x8c && rdesc[85] == 0x02) { hid_info(hdev, "fixing up Logitech keyboard report descriptor\n"); rdesc[84] = rdesc[89] = 0x4d; rdesc[85] = rdesc[90] = 0x10; } - if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 50 && + if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 51 && rdesc[32] == 0x81 && rdesc[33] == 0x06 && rdesc[49] == 0x81 && rdesc[50] == 0x06) { hid_info(hdev, diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index f45279c3b11a..5da115a6fd22 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -237,13 +237,6 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev, return; } - if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) || - (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) { - dev_err(&djrcv_hdev->dev, "%s: invalid device index:%d\n", - __func__, dj_report->device_index); - return; - } - if (djrcv_dev->paired_dj_devices[dj_report->device_index]) { /* The device is already known. No need to reallocate it. */ dbg_hid("%s: device is already known\n", __func__); @@ -694,7 +687,6 @@ static int logi_dj_raw_event(struct hid_device *hdev, struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); struct dj_report *dj_report = (struct dj_report *) data; unsigned long flags; - bool report_processed = false; dbg_hid("%s, size:%d\n", __func__, size); @@ -722,27 +714,41 @@ static int logi_dj_raw_event(struct hid_device *hdev, * anything else with it. */ + /* case 1) */ + if (data[0] != REPORT_ID_DJ_SHORT) + return false; + + if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) || + (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) { + /* + * Device index is wrong, bail out. + * This driver can ignore safely the receiver notifications, + * so ignore those reports too. + */ + if (dj_report->device_index != DJ_RECEIVER_INDEX) + dev_err(&hdev->dev, "%s: invalid device index:%d\n", + __func__, dj_report->device_index); + return false; + } + spin_lock_irqsave(&djrcv_dev->lock, flags); - if (dj_report->report_id == REPORT_ID_DJ_SHORT) { - switch (dj_report->report_type) { - case REPORT_TYPE_NOTIF_DEVICE_PAIRED: - case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: - logi_dj_recv_queue_notification(djrcv_dev, dj_report); - break; - case REPORT_TYPE_NOTIF_CONNECTION_STATUS: - if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == - STATUS_LINKLOSS) { - logi_dj_recv_forward_null_report(djrcv_dev, dj_report); - } - break; - default: - logi_dj_recv_forward_report(djrcv_dev, dj_report); + switch (dj_report->report_type) { + case REPORT_TYPE_NOTIF_DEVICE_PAIRED: + case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: + logi_dj_recv_queue_notification(djrcv_dev, dj_report); + break; + case REPORT_TYPE_NOTIF_CONNECTION_STATUS: + if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == + STATUS_LINKLOSS) { + logi_dj_recv_forward_null_report(djrcv_dev, dj_report); } - report_processed = true; + break; + default: + logi_dj_recv_forward_report(djrcv_dev, dj_report); } spin_unlock_irqrestore(&djrcv_dev->lock, flags); - return report_processed; + return true; } static int logi_dj_probe(struct hid_device *hdev, diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h index 4a4000340ce1..daeb0aa4bee9 100644 --- a/drivers/hid/hid-logitech-dj.h +++ b/drivers/hid/hid-logitech-dj.h @@ -27,6 +27,7 @@ #define DJ_MAX_PAIRED_DEVICES 6 #define DJ_MAX_NUMBER_NOTIFICATIONS 8 +#define DJ_RECEIVER_INDEX 0 #define DJ_DEVICE_INDEX_MIN 1 #define DJ_DEVICE_INDEX_MAX 6 diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 3b43d1cfa936..991ba79cfc72 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -290,6 +290,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, if (size < 4 || ((size - 4) % 9) != 0) return 0; npoints = (size - 4) / 9; + if (npoints > 15) { + hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n", + size); + return 0; + } msc->ntouches = 0; for (ii = 0; ii < npoints; ii++) magicmouse_emit_touch(msc, ii, data + ii * 9 + 4); @@ -307,6 +312,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, if (size < 6 || ((size - 6) % 8) != 0) return 0; npoints = (size - 6) / 8; + if (npoints > 15) { + hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n", + size); + return 0; + } msc->ntouches = 0; for (ii = 0; ii < npoints; ii++) magicmouse_emit_touch(msc, ii, data + ii * 8 + 6); diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index 404a3a8a82f1..c6ef6eed3091 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -208,10 +208,6 @@ static const struct hid_device_id ms_devices[] = { .driver_data = MS_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_COMFORT_MOUSE_4500), .driver_data = MS_DUPLICATE_USAGES }, - { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2), - .driver_data = 0 }, - { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), - .driver_data = 0 }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT), .driver_data = MS_PRESENTER }, diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c index 9e14c00eb1b6..25daf28b26bd 100644 --- a/drivers/hid/hid-monterey.c +++ b/drivers/hid/hid-monterey.c @@ -24,7 +24,7 @@ static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 30 && rdesc[29] == 0x05 && rdesc[30] == 0x09) { + if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) { hid_info(hdev, "fixing up button/consumer in HID report descriptor\n"); rdesc[30] = 0x0c; } diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c index 736b2502df4f..6aca4f2554bf 100644 --- a/drivers/hid/hid-petalynx.c +++ b/drivers/hid/hid-petalynx.c @@ -25,7 +25,7 @@ static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 60 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 && + if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 && rdesc[41] == 0x00 && rdesc[59] == 0x26 && rdesc[60] == 0xf9 && rdesc[61] == 0x00) { hid_info(hdev, "fixing up Petalynx Maxter Remote report descriptor\n"); diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c index acbb021065ec..020df3c2e8b4 100644 --- a/drivers/hid/hid-picolcd_core.c +++ b/drivers/hid/hid-picolcd_core.c @@ -350,6 +350,12 @@ static int picolcd_raw_event(struct hid_device *hdev, if (!data) return 1; + if (size > 64) { + hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n", + size); + return 0; + } + if (report->id == REPORT_KEY_STATE) { if (data->input_keys) ret = picolcd_raw_keypad(data, report, raw_data+1, size-1); diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c index 87fc91e1c8de..91072fa54663 100644 --- a/drivers/hid/hid-sunplus.c +++ b/drivers/hid/hid-sunplus.c @@ -24,7 +24,7 @@ static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - if (*rsize >= 107 && rdesc[104] == 0x26 && rdesc[105] == 0x80 && + if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 && rdesc[106] == 0x03) { hid_info(hdev, "fixing up Sunplus Wireless Desktop report descriptor\n"); rdesc[105] = rdesc[110] = 0x03; diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 44df131d390a..617c47f9ebe6 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -82,7 +82,7 @@ static int hid_start_in(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; spin_lock_irqsave(&usbhid->lock, flags); - if (hid->open > 0 && + if ((hid->open > 0 || hid->quirks & HID_QUIRK_ALWAYS_POLL) && !test_bit(HID_DISCONNECTED, &usbhid->iofl) && !test_bit(HID_SUSPENDED, &usbhid->iofl) && !test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) { @@ -292,6 +292,8 @@ static void hid_irq_in(struct urb *urb) case 0: /* success */ usbhid_mark_busy(usbhid); usbhid->retry_delay = 0; + if ((hid->quirks & HID_QUIRK_ALWAYS_POLL) && !hid->open) + break; hid_input_report(urb->context, HID_INPUT_REPORT, urb->transfer_buffer, urb->actual_length, 1); @@ -734,8 +736,10 @@ void usbhid_close(struct hid_device *hid) if (!--hid->open) { spin_unlock_irq(&usbhid->lock); hid_cancel_delayed_stuff(usbhid); - usb_kill_urb(usbhid->urbin); - usbhid->intf->needs_remote_wakeup = 0; + if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { + usb_kill_urb(usbhid->urbin); + usbhid->intf->needs_remote_wakeup = 0; + } } else { spin_unlock_irq(&usbhid->lock); } @@ -1119,6 +1123,19 @@ static int usbhid_start(struct hid_device *hid) set_bit(HID_STARTED, &usbhid->iofl); + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { + ret = usb_autopm_get_interface(usbhid->intf); + if (ret) + goto fail; + usbhid->intf->needs_remote_wakeup = 1; + ret = hid_start_in(hid); + if (ret) { + dev_err(&hid->dev, + "failed to start in urb: %d\n", ret); + } + usb_autopm_put_interface(usbhid->intf); + } + /* Some keyboards don't work until their LEDs have been set. * Since BIOSes do set the LEDs, it must be safe for any device * that supports the keyboard boot protocol. @@ -1151,6 +1168,9 @@ static void usbhid_stop(struct hid_device *hid) if (WARN_ON(!usbhid)) return; + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) + usbhid->intf->needs_remote_wakeup = 0; + clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index dbd83878ff99..deb364306636 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -69,6 +69,9 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET }, { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, @@ -119,6 +122,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_HD, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD, HID_QUIRK_NO_INIT_REPORTS }, + { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103, HID_QUIRK_NO_INIT_REPORTS }, { 0, 0 } }; diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 69ea36f07b4d..e99e71a6ea59 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -164,8 +164,10 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, ret = vmbus_post_msg(open_msg, sizeof(struct vmbus_channel_open_channel)); - if (ret != 0) + if (ret != 0) { + err = ret; goto error1; + } t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ); if (t == 0) { @@ -362,7 +364,6 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, u32 next_gpadl_handle; unsigned long flags; int ret = 0; - int t; next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle); atomic_inc(&vmbus_connection.next_gpadl_handle); @@ -409,9 +410,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, } } - t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ); - BUG_ON(t == 0); - + wait_for_completion(&msginfo->waitevent); /* At this point, we received the gpadl created msg */ *gpadl_handle = gpadlmsg->gpadl; @@ -434,7 +433,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) struct vmbus_channel_gpadl_teardown *msg; struct vmbus_channel_msginfo *info; unsigned long flags; - int ret, t; + int ret; info = kmalloc(sizeof(*info) + sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL); @@ -456,11 +455,12 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown)); - BUG_ON(ret != 0); - t = wait_for_completion_timeout(&info->waitevent, 5*HZ); - BUG_ON(t == 0); + if (ret) + goto post_msg_err; + + wait_for_completion(&info->waitevent); - /* Received a torndown response */ +post_msg_err: spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_del(&info->msglistentry); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); @@ -470,7 +470,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); -static void vmbus_close_internal(struct vmbus_channel *channel) +static int vmbus_close_internal(struct vmbus_channel *channel) { struct vmbus_channel_close_channel *msg; int ret; @@ -492,11 +492,28 @@ static void vmbus_close_internal(struct vmbus_channel *channel) ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel)); - BUG_ON(ret != 0); + if (ret) { + pr_err("Close failed: close post msg return is %d\n", ret); + /* + * If we failed to post the close msg, + * it is perhaps better to leak memory. + */ + return ret; + } + /* Tear down the gpadl for the channel's ring buffer */ - if (channel->ringbuffer_gpadlhandle) - vmbus_teardown_gpadl(channel, - channel->ringbuffer_gpadlhandle); + if (channel->ringbuffer_gpadlhandle) { + ret = vmbus_teardown_gpadl(channel, + channel->ringbuffer_gpadlhandle); + if (ret) { + pr_err("Close failed: teardown gpadl return %d\n", ret); + /* + * If we failed to teardown gpadl, + * it is perhaps better to leak memory. + */ + return ret; + } + } /* Cleanup the ring buffers for this channel */ hv_ringbuffer_cleanup(&channel->outbound); @@ -505,7 +522,7 @@ static void vmbus_close_internal(struct vmbus_channel *channel) free_pages((unsigned long)channel->ringbuffer_pages, get_order(channel->ringbuffer_pagecount * PAGE_SIZE)); - + return ret; } /* diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index f2d7bf90c9fe..d8fd95cb0456 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -55,6 +55,9 @@ static __u32 vmbus_get_next_version(__u32 current_version) case (VERSION_WIN8): return VERSION_WIN7; + case (VERSION_WIN8_1): + return VERSION_WIN8; + case (VERSION_WS2008): default: return VERSION_INVAL; @@ -77,7 +80,7 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, msg->interrupt_page = virt_to_phys(vmbus_connection.int_page); msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]); msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]); - if (version == VERSION_WIN8) + if (version == VERSION_WIN8_1) msg->target_vcpu = hv_context.vp_index[smp_processor_id()]; /* @@ -221,8 +224,8 @@ cleanup: vmbus_connection.int_page = NULL; } - free_pages((unsigned long)vmbus_connection.monitor_pages[0], 1); - free_pages((unsigned long)vmbus_connection.monitor_pages[1], 1); + free_pages((unsigned long)vmbus_connection.monitor_pages[0], 0); + free_pages((unsigned long)vmbus_connection.monitor_pages[1], 0); vmbus_connection.monitor_pages[0] = NULL; vmbus_connection.monitor_pages[1] = NULL; @@ -316,9 +319,13 @@ static void process_chn_event(u32 relid) */ do { - hv_begin_read(&channel->inbound); + if (read_state) + hv_begin_read(&channel->inbound); channel->onchannel_callback(arg); - bytes_to_read = hv_end_read(&channel->inbound); + if (read_state) + bytes_to_read = hv_end_read(&channel->inbound); + else + bytes_to_read = 0; } while (read_state && (bytes_to_read != 0)); } else { pr_err("no channel callback for relid - %u\n", relid); @@ -401,10 +408,21 @@ int vmbus_post_msg(void *buffer, size_t buflen) * insufficient resources. Retry the operation a couple of * times before giving up. */ - while (retries < 3) { - ret = hv_post_message(conn_id, 1, buffer, buflen); - if (ret != HV_STATUS_INSUFFICIENT_BUFFERS) + while (retries < 10) { + ret = hv_post_message(conn_id, 1, buffer, buflen); + + switch (ret) { + case HV_STATUS_INSUFFICIENT_BUFFERS: + ret = -ENOMEM; + case -ENOMEM: + break; + case HV_STATUS_SUCCESS: return ret; + default: + pr_err("hv_post_msg() failed; error code:%d\n", ret); + return -EINVAL; + } + retries++; msleep(100); } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 7e17a5495e02..393fd8a98735 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -19,6 +19,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> +#include <linux/jiffies.h> #include <linux/mman.h> #include <linux/delay.h> #include <linux/init.h> @@ -459,6 +460,11 @@ static bool do_hot_add; */ static uint pressure_report_delay = 45; +/* + * The last time we posted a pressure report to host. + */ +static unsigned long last_post_time; + module_param(hot_add, bool, (S_IRUGO | S_IWUSR)); MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add"); @@ -542,6 +548,7 @@ struct hv_dynmem_device { static struct hv_dynmem_device dm_device; +static void post_status(struct hv_dynmem_device *dm); #ifdef CONFIG_MEMORY_HOTPLUG static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size) @@ -612,7 +619,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, * have not been "onlined" within the allowed time. */ wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ); - + post_status(&dm_device); } return; @@ -951,11 +958,17 @@ static void post_status(struct hv_dynmem_device *dm) { struct dm_status status; struct sysinfo val; + unsigned long now = jiffies; + unsigned long last_post = last_post_time; if (pressure_report_delay > 0) { --pressure_report_delay; return; } + + if (!time_after(now, (last_post_time + HZ))) + return; + si_meminfo(&val); memset(&status, 0, sizeof(struct dm_status)); status.hdr.type = DM_STATUS_REPORT; @@ -983,6 +996,14 @@ static void post_status(struct hv_dynmem_device *dm) if (status.hdr.trans_id != atomic_read(&trans_id)) return; + /* + * If the last post time that we sampled has changed, + * we have raced, don't post the status. + */ + if (last_post != last_post_time) + return; + + last_post_time = jiffies; vmbus_sendpacket(dm->dev->channel, &status, sizeof(struct dm_status), (unsigned long)NULL, @@ -1117,7 +1138,7 @@ static void balloon_up(struct work_struct *dummy) if (ret == -EAGAIN) msleep(20); - + post_status(&dm_device); } while (ret == -EAGAIN); if (ret) { @@ -1144,8 +1165,10 @@ static void balloon_down(struct hv_dynmem_device *dm, struct dm_unballoon_response resp; int i; - for (i = 0; i < range_count; i++) + for (i = 0; i < range_count; i++) { free_balloon_pages(dm, &range_array[i]); + post_status(&dm_device); + } if (req->more_pages == 1) return; diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index 09988b289622..816782a65488 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -127,6 +127,15 @@ kvp_work_func(struct work_struct *dummy) kvp_respond_to_host(NULL, HV_E_FAIL); } +static void poll_channel(struct vmbus_channel *channel) +{ + unsigned long flags; + + spin_lock_irqsave(&channel->inbound_lock, flags); + hv_kvp_onchannelcallback(channel); + spin_unlock_irqrestore(&channel->inbound_lock, flags); +} + static int kvp_handle_handshake(struct hv_kvp_msg *msg) { int ret = 1; @@ -155,7 +164,7 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg) kvp_register(dm_reg_value); kvp_transaction.active = false; if (kvp_transaction.kvp_context) - hv_kvp_onchannelcallback(kvp_transaction.kvp_context); + poll_channel(kvp_transaction.kvp_context); } return ret; } @@ -568,6 +577,7 @@ response_done: vmbus_sendpacket(channel, recv_buffer, buf_len, req_id, VM_PKT_DATA_INBAND, 0); + poll_channel(channel); } @@ -603,7 +613,7 @@ void hv_kvp_onchannelcallback(void *context) return; } - vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen, + vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen, &requestid); if (recvlen > 0) { diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 62dfd246b948..d016be36cc03 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -312,7 +312,7 @@ static int util_probe(struct hv_device *dev, (struct hv_util_service *)dev_id->driver_data; int ret; - srv->recv_buffer = kmalloc(PAGE_SIZE * 2, GFP_KERNEL); + srv->recv_buffer = kmalloc(PAGE_SIZE * 4, GFP_KERNEL); if (!srv->recv_buffer) return -ENOMEM; if (srv->util_init) { diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 5ce43d8dfa98..7703e3bc604b 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -971,7 +971,7 @@ config SENSORS_NCT6775 config SENSORS_NTC_THERMISTOR tristate "NTC thermistor support" - depends on (!OF && !IIO) || (OF && IIO) + depends on !OF || IIO=n || IIO help This driver supports NTC thermistors sensor reading and its interpretation. The driver can also monitor the temperature and diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c index 29dd9f746dfa..233b374334ed 100644 --- a/drivers/hwmon/adm1021.c +++ b/drivers/hwmon/adm1021.c @@ -185,7 +185,7 @@ static ssize_t set_temp_max(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct adm1021_data *data = i2c_get_clientdata(client); long temp; - int err; + int reg_val, err; err = kstrtol(buf, 10, &temp); if (err) @@ -193,10 +193,11 @@ static ssize_t set_temp_max(struct device *dev, temp /= 1000; mutex_lock(&data->update_lock); - data->temp_max[index] = clamp_val(temp, -128, 127); + reg_val = clamp_val(temp, -128, 127); + data->temp_max[index] = reg_val * 1000; if (!read_only) i2c_smbus_write_byte_data(client, ADM1021_REG_TOS_W(index), - data->temp_max[index]); + reg_val); mutex_unlock(&data->update_lock); return count; @@ -210,7 +211,7 @@ static ssize_t set_temp_min(struct device *dev, struct i2c_client *client = to_i2c_client(dev); struct adm1021_data *data = i2c_get_clientdata(client); long temp; - int err; + int reg_val, err; err = kstrtol(buf, 10, &temp); if (err) @@ -218,10 +219,11 @@ static ssize_t set_temp_min(struct device *dev, temp /= 1000; mutex_lock(&data->update_lock); - data->temp_min[index] = clamp_val(temp, -128, 127); + reg_val = clamp_val(temp, -128, 127); + data->temp_min[index] = reg_val * 1000; if (!read_only) i2c_smbus_write_byte_data(client, ADM1021_REG_THYST_W(index), - data->temp_min[index]); + reg_val); mutex_unlock(&data->update_lock); return count; diff --git a/drivers/hwmon/adm1029.c b/drivers/hwmon/adm1029.c index d19c790e410a..e38115ce0350 100644 --- a/drivers/hwmon/adm1029.c +++ b/drivers/hwmon/adm1029.c @@ -232,6 +232,9 @@ static ssize_t set_fan_div(struct device *dev, /* Update the value */ reg = (reg & 0x3F) | (val << 6); + /* Update the cache */ + data->fan_div[attr->index] = reg; + /* Write value */ i2c_smbus_write_byte_data(client, ADM1029_REG_FAN_DIV[attr->index], reg); diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c index a8a540ca8c34..51c1a5a165ab 100644 --- a/drivers/hwmon/adm1031.c +++ b/drivers/hwmon/adm1031.c @@ -365,6 +365,7 @@ set_auto_temp_min(struct device *dev, struct device_attribute *attr, if (ret) return ret; + val = clamp_val(val, 0, 127000); mutex_lock(&data->update_lock); data->auto_temp[nr] = AUTO_TEMP_MIN_TO_REG(val, data->auto_temp[nr]); adm1031_write_value(client, ADM1031_REG_AUTO_TEMP(nr), @@ -394,6 +395,7 @@ set_auto_temp_max(struct device *dev, struct device_attribute *attr, if (ret) return ret; + val = clamp_val(val, 0, 127000); mutex_lock(&data->update_lock); data->temp_max[nr] = AUTO_TEMP_MAX_TO_REG(val, data->auto_temp[nr], data->pwm[nr]); @@ -696,7 +698,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr, if (ret) return ret; - val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875); + val = clamp_val(val, -55000, 127000); mutex_lock(&data->update_lock); data->temp_min[nr] = TEMP_TO_REG(val); adm1031_write_value(client, ADM1031_REG_TEMP_MIN(nr), @@ -717,7 +719,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr, if (ret) return ret; - val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875); + val = clamp_val(val, -55000, 127000); mutex_lock(&data->update_lock); data->temp_max[nr] = TEMP_TO_REG(val); adm1031_write_value(client, ADM1031_REG_TEMP_MAX(nr), @@ -738,7 +740,7 @@ static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr, if (ret) return ret; - val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875); + val = clamp_val(val, -55000, 127000); mutex_lock(&data->update_lock); data->temp_crit[nr] = TEMP_TO_REG(val); adm1031_write_value(client, ADM1031_REG_TEMP_CRIT(nr), diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c index 7f9dc2f86b63..126516414c11 100644 --- a/drivers/hwmon/ads1015.c +++ b/drivers/hwmon/ads1015.c @@ -198,7 +198,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) } channel = be32_to_cpup(property); - if (channel > ADS1015_CHANNELS) { + if (channel >= ADS1015_CHANNELS) { dev_err(&client->dev, "invalid channel index %d on %s\n", channel, node->full_name); @@ -212,6 +212,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) dev_err(&client->dev, "invalid gain on %s\n", node->full_name); + return -EINVAL; } } @@ -222,6 +223,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) dev_err(&client->dev, "invalid data_rate on %s\n", node->full_name); + return -EINVAL; } } diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index 0f4dea5ccf17..9ee3913850d6 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -515,7 +515,7 @@ static ssize_t set_temp_min(struct device *dev, return -EINVAL; temp = DIV_ROUND_CLOSEST(temp, 1000); - temp = clamp_val(temp, 0, 255); + temp = clamp_val(temp, -128, 127); mutex_lock(&data->lock); data->temp_min[attr->index] = temp; @@ -549,7 +549,7 @@ static ssize_t set_temp_max(struct device *dev, return -EINVAL; temp = DIV_ROUND_CLOSEST(temp, 1000); - temp = clamp_val(temp, 0, 255); + temp = clamp_val(temp, -128, 127); mutex_lock(&data->lock); data->temp_max[attr->index] = temp; @@ -826,7 +826,7 @@ static ssize_t set_pwm_tmin(struct device *dev, return -EINVAL; temp = DIV_ROUND_CLOSEST(temp, 1000); - temp = clamp_val(temp, 0, 255); + temp = clamp_val(temp, -128, 127); mutex_lock(&data->lock); data->pwm_tmin[attr->index] = temp; diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c index eea817296513..8a67ec6279a4 100644 --- a/drivers/hwmon/amc6821.c +++ b/drivers/hwmon/amc6821.c @@ -360,11 +360,13 @@ static ssize_t set_pwm1_enable( if (config) return config; + mutex_lock(&data->update_lock); config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF1); if (config < 0) { dev_err(&client->dev, "Error reading configuration register, aborting.\n"); - return config; + count = config; + goto unlock; } switch (val) { @@ -381,14 +383,15 @@ static ssize_t set_pwm1_enable( config |= AMC6821_CONF1_FDRC1; break; default: - return -EINVAL; + count = -EINVAL; + goto unlock; } - mutex_lock(&data->update_lock); if (i2c_smbus_write_byte_data(client, AMC6821_REG_CONF1, config)) { dev_err(&client->dev, "Configuration register write error, aborting.\n"); count = -EIO; } +unlock: mutex_unlock(&data->update_lock); return count; } @@ -493,8 +496,9 @@ static ssize_t set_temp_auto_point_temp( return -EINVAL; } - data->valid = 0; mutex_lock(&data->update_lock); + data->valid = 0; + switch (ix) { case 0: ptemp[0] = clamp_val(val / 1000, 0, @@ -658,13 +662,14 @@ static ssize_t set_fan1_div( if (config) return config; + mutex_lock(&data->update_lock); config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF4); if (config < 0) { dev_err(&client->dev, "Error reading configuration register, aborting.\n"); - return config; + count = config; + goto EXIT; } - mutex_lock(&data->update_lock); switch (val) { case 2: config &= ~AMC6821_CONF4_PSPR; @@ -704,7 +709,7 @@ static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, get_temp_alarm, NULL, IDX_TEMP1_MAX); static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, get_temp_alarm, NULL, IDX_TEMP1_CRIT); -static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO | S_IWUSR, +static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, get_temp, NULL, IDX_TEMP2_INPUT); static SENSOR_DEVICE_ATTR(temp2_min, S_IRUGO | S_IWUSR, get_temp, set_temp, IDX_TEMP2_MIN); diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index bbb0b0d463f7..15993103c1a2 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -369,12 +369,12 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) if (cpu_has_tjmax(c)) dev_warn(dev, "Unable to read TjMax from CPU %u\n", id); } else { - val = (eax >> 16) & 0x7f; + val = (eax >> 16) & 0xff; /* * If the TjMax is not plausible, an assumption * will be used */ - if (val >= 85) { + if (val) { dev_dbg(dev, "TjMax is %d degrees C\n", val); return val * 1000; } diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c index afd31042b452..d14ab3c45daa 100644 --- a/drivers/hwmon/da9052-hwmon.c +++ b/drivers/hwmon/da9052-hwmon.c @@ -194,7 +194,7 @@ static ssize_t da9052_hwmon_show_name(struct device *dev, struct device_attribute *devattr, char *buf) { - return sprintf(buf, "da9052-hwmon\n"); + return sprintf(buf, "da9052\n"); } static ssize_t show_label(struct device *dev, diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c index 73b3865f1207..35eb7738d711 100644 --- a/drivers/hwmon/da9055-hwmon.c +++ b/drivers/hwmon/da9055-hwmon.c @@ -204,7 +204,7 @@ static ssize_t da9055_hwmon_show_name(struct device *dev, struct device_attribute *devattr, char *buf) { - return sprintf(buf, "da9055-hwmon\n"); + return sprintf(buf, "da9055\n"); } static ssize_t show_label(struct device *dev, diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c index 4ae3fff13f44..bea0a344fab5 100644 --- a/drivers/hwmon/dme1737.c +++ b/drivers/hwmon/dme1737.c @@ -247,8 +247,8 @@ struct dme1737_data { u8 pwm_acz[3]; u8 pwm_freq[6]; u8 pwm_rr[2]; - u8 zone_low[3]; - u8 zone_abs[3]; + s8 zone_low[3]; + s8 zone_abs[3]; u8 zone_hyst[2]; u32 alarms; }; @@ -277,7 +277,7 @@ static inline int IN_FROM_REG(int reg, int nominal, int res) return (reg * nominal + (3 << (res - 3))) / (3 << (res - 2)); } -static inline int IN_TO_REG(int val, int nominal) +static inline int IN_TO_REG(long val, int nominal) { return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255); } @@ -293,7 +293,7 @@ static inline int TEMP_FROM_REG(int reg, int res) return (reg * 1000) >> (res - 8); } -static inline int TEMP_TO_REG(int val) +static inline int TEMP_TO_REG(long val) { return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127); } @@ -308,7 +308,7 @@ static inline int TEMP_RANGE_FROM_REG(int reg) return TEMP_RANGE[(reg >> 4) & 0x0f]; } -static int TEMP_RANGE_TO_REG(int val, int reg) +static int TEMP_RANGE_TO_REG(long val, int reg) { int i; @@ -331,7 +331,7 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix) return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000; } -static inline int TEMP_HYST_TO_REG(int val, int ix, int reg) +static inline int TEMP_HYST_TO_REG(long val, int ix, int reg) { int hyst = clamp_val((val + 500) / 1000, 0, 15); @@ -347,7 +347,7 @@ static inline int FAN_FROM_REG(int reg, int tpc) return (reg == 0 || reg == 0xffff) ? 0 : 90000 * 60 / reg; } -static inline int FAN_TO_REG(int val, int tpc) +static inline int FAN_TO_REG(long val, int tpc) { if (tpc) { return clamp_val(val / tpc, 0, 0xffff); @@ -379,7 +379,7 @@ static inline int FAN_TYPE_FROM_REG(int reg) return (edge > 0) ? 1 << (edge - 1) : 0; } -static inline int FAN_TYPE_TO_REG(int val, int reg) +static inline int FAN_TYPE_TO_REG(long val, int reg) { int edge = (val == 4) ? 3 : val; @@ -402,7 +402,7 @@ static int FAN_MAX_FROM_REG(int reg) return 1000 + i * 500; } -static int FAN_MAX_TO_REG(int val) +static int FAN_MAX_TO_REG(long val) { int i; @@ -460,7 +460,7 @@ static inline int PWM_ACZ_FROM_REG(int reg) return acz[(reg >> 5) & 0x07]; } -static inline int PWM_ACZ_TO_REG(int val, int reg) +static inline int PWM_ACZ_TO_REG(long val, int reg) { int acz = (val == 4) ? 2 : val - 1; @@ -476,7 +476,7 @@ static inline int PWM_FREQ_FROM_REG(int reg) return PWM_FREQ[reg & 0x0f]; } -static int PWM_FREQ_TO_REG(int val, int reg) +static int PWM_FREQ_TO_REG(long val, int reg) { int i; @@ -510,7 +510,7 @@ static inline int PWM_RR_FROM_REG(int reg, int ix) return (rr & 0x08) ? PWM_RR[rr & 0x07] : 0; } -static int PWM_RR_TO_REG(int val, int ix, int reg) +static int PWM_RR_TO_REG(long val, int ix, int reg) { int i; @@ -528,7 +528,7 @@ static inline int PWM_RR_EN_FROM_REG(int reg, int ix) return PWM_RR_FROM_REG(reg, ix) ? 1 : 0; } -static inline int PWM_RR_EN_TO_REG(int val, int ix, int reg) +static inline int PWM_RR_EN_TO_REG(long val, int ix, int reg) { int en = (ix == 1) ? 0x80 : 0x08; @@ -1481,13 +1481,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct dme1737_data *data = dev_get_drvdata(dev); - long val; + unsigned long val; int err; - err = kstrtol(buf, 10, &val); + err = kstrtoul(buf, 10, &val); if (err) return err; + if (val > 255) + return -EINVAL; + data->vrm = val; return count; } diff --git a/drivers/hwmon/ds1621.c b/drivers/hwmon/ds1621.c index fc6f5d54e7f7..8890870309e4 100644 --- a/drivers/hwmon/ds1621.c +++ b/drivers/hwmon/ds1621.c @@ -309,6 +309,7 @@ static ssize_t set_convrate(struct device *dev, struct device_attribute *da, data->conf |= (resol << DS1621_REG_CONFIG_RESOL_SHIFT); i2c_smbus_write_byte_data(client, DS1621_REG_CONF, data->conf); data->update_interval = ds1721_convrates[resol]; + data->zbits = 7 - resol; mutex_unlock(&data->update_lock); return count; diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c index 90ec1173b8a1..01723f04fe45 100644 --- a/drivers/hwmon/emc1403.c +++ b/drivers/hwmon/emc1403.c @@ -163,7 +163,7 @@ static ssize_t store_hyst(struct device *dev, if (retval < 0) goto fail; - hyst = val - retval * 1000; + hyst = retval * 1000 - val; hyst = DIV_ROUND_CLOSEST(hyst, 1000); if (hyst < 0 || hyst > 255) { retval = -ERANGE; @@ -330,7 +330,7 @@ static int emc1403_detect(struct i2c_client *client, } id = i2c_smbus_read_byte_data(client, THERMAL_REVISION_REG); - if (id != 0x01) + if (id < 0x01 || id > 0x04) return -ENODEV; return 0; @@ -355,9 +355,9 @@ static int emc1403_probe(struct i2c_client *client, if (id->driver_data) data->groups[1] = &emc1404_group; - hwmon_dev = hwmon_device_register_with_groups(&client->dev, - client->name, data, - data->groups); + hwmon_dev = devm_hwmon_device_register_with_groups(&client->dev, + client->name, data, + data->groups); if (IS_ERR(hwmon_dev)) return PTR_ERR(hwmon_dev); diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c index 2c137b26acb4..5790246a7e1d 100644 --- a/drivers/hwmon/emc2103.c +++ b/drivers/hwmon/emc2103.c @@ -250,9 +250,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *da, if (result < 0) return result; - val = DIV_ROUND_CLOSEST(val, 1000); - if ((val < -63) || (val > 127)) - return -EINVAL; + val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -63, 127); mutex_lock(&data->update_lock); data->temp_min[nr] = val; @@ -274,9 +272,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *da, if (result < 0) return result; - val = DIV_ROUND_CLOSEST(val, 1000); - if ((val < -63) || (val > 127)) - return -EINVAL; + val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -63, 127); mutex_lock(&data->update_lock); data->temp_max[nr] = val; @@ -390,15 +386,14 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da, { struct emc2103_data *data = emc2103_update_device(dev); struct i2c_client *client = to_i2c_client(dev); - long rpm_target; + unsigned long rpm_target; - int result = kstrtol(buf, 10, &rpm_target); + int result = kstrtoul(buf, 10, &rpm_target); if (result < 0) return result; /* Datasheet states 16384 as maximum RPM target (table 3.2) */ - if ((rpm_target < 0) || (rpm_target > 16384)) - return -EINVAL; + rpm_target = clamp_val(rpm_target, 0, 16384); mutex_lock(&data->update_lock); diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 73181be5b30b..814f7ee9026b 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -173,7 +173,7 @@ static int get_fan_speed_index(struct gpio_fan_data *fan_data) return -ENODEV; } -static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm) +static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm) { struct gpio_fan_speed *speed = fan_data->speed; int i; diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 93d26e8af3e2..bfd3f3eeabcd 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -148,7 +148,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg) switch (reg) { case INA2XX_SHUNT_VOLTAGE: - val = DIV_ROUND_CLOSEST(data->regs[reg], + /* signed register */ + val = DIV_ROUND_CLOSEST((s16)data->regs[reg], data->config->shunt_div); break; case INA2XX_BUS_VOLTAGE: @@ -160,8 +161,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg) val = data->regs[reg] * data->config->power_lsb; break; case INA2XX_CURRENT: - /* LSB=1mA (selected). Is in mA */ - val = data->regs[reg]; + /* signed register, LSB=1mA (selected), in mA */ + val = (s16)data->regs[reg]; break; default: /* programmer goofed */ diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c index 9efadfc851bc..c1eb464f0fd0 100644 --- a/drivers/hwmon/lm78.c +++ b/drivers/hwmon/lm78.c @@ -108,7 +108,7 @@ static inline int FAN_FROM_REG(u8 val, int div) * TEMP: mC (-128C to +127C) * REG: 1C/bit, two's complement */ -static inline s8 TEMP_TO_REG(int val) +static inline s8 TEMP_TO_REG(long val) { int nval = clamp_val(val, -128000, 127000) ; return nval < 0 ? (nval - 500) / 1000 : (nval + 500) / 1000; diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c index bed4af358308..21d6cc813a6d 100644 --- a/drivers/hwmon/lm85.c +++ b/drivers/hwmon/lm85.c @@ -158,7 +158,7 @@ static inline u16 FAN_TO_REG(unsigned long val) /* Temperature is reported in .001 degC increments */ #define TEMP_TO_REG(val) \ - clamp_val(SCALE(val, 1000, 1), -127, 127) + DIV_ROUND_CLOSEST(clamp_val((val), -127000, 127000), 1000) #define TEMPEXT_FROM_REG(val, ext) \ SCALE(((val) << 4) + (ext), 16, 1000) #define TEMP_FROM_REG(val) ((val) * 1000) @@ -192,7 +192,7 @@ static const int lm85_range_map[] = { 13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000 }; -static int RANGE_TO_REG(int range) +static int RANGE_TO_REG(long range) { int i; @@ -214,7 +214,7 @@ static const int adm1027_freq_map[8] = { /* 1 Hz */ 11, 15, 22, 29, 35, 44, 59, 88 }; -static int FREQ_TO_REG(const int *map, int freq) +static int FREQ_TO_REG(const int *map, unsigned long freq) { int i; @@ -463,6 +463,9 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, if (err) return err; + if (val > 255) + return -EINVAL; + data->vrm = val; return count; } diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index 8a17f01e8672..e76feb86a1d4 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -44,6 +44,7 @@ struct ntc_compensation { unsigned int ohm; }; +/* Order matters, ntc_match references the entries by index */ static const struct platform_device_id ntc_thermistor_id[] = { { "ncp15wb473", TYPE_NCPXXWB473 }, { "ncp18wb473", TYPE_NCPXXWB473 }, @@ -141,7 +142,7 @@ struct ntc_data { char name[PLATFORM_NAME_SIZE]; }; -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_IIO) static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata) { struct iio_channel *channel = pdata->chan; @@ -163,15 +164,15 @@ static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata) static const struct of_device_id ntc_match[] = { { .compatible = "ntc,ncp15wb473", - .data = &ntc_thermistor_id[TYPE_NCPXXWB473] }, + .data = &ntc_thermistor_id[0] }, { .compatible = "ntc,ncp18wb473", - .data = &ntc_thermistor_id[TYPE_NCPXXWB473] }, + .data = &ntc_thermistor_id[1] }, { .compatible = "ntc,ncp21wb473", - .data = &ntc_thermistor_id[TYPE_NCPXXWB473] }, + .data = &ntc_thermistor_id[2] }, { .compatible = "ntc,ncp03wb473", - .data = &ntc_thermistor_id[TYPE_NCPXXWB473] }, + .data = &ntc_thermistor_id[3] }, { .compatible = "ntc,ncp15wl333", - .data = &ntc_thermistor_id[TYPE_NCPXXWL333] }, + .data = &ntc_thermistor_id[4] }, { }, }; MODULE_DEVICE_TABLE(of, ntc_match); @@ -223,6 +224,8 @@ ntc_thermistor_parse_dt(struct platform_device *pdev) return NULL; } +#define ntc_match NULL + static void ntc_iio_channel_release(struct ntc_thermistor_platform_data *pdata) { } #endif diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c index 3532026e25da..bf1d7893d51c 100644 --- a/drivers/hwmon/sis5595.c +++ b/drivers/hwmon/sis5595.c @@ -159,7 +159,7 @@ static inline int TEMP_FROM_REG(s8 val) { return val * 830 + 52120; } -static inline s8 TEMP_TO_REG(int val) +static inline s8 TEMP_TO_REG(long val) { int nval = clamp_val(val, -54120, 157530) ; return nval < 0 ? (nval - 5212 - 415) / 830 : (nval - 5212 + 415) / 830; diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c index efee4c59239f..34b9a601ad07 100644 --- a/drivers/hwmon/smsc47m192.c +++ b/drivers/hwmon/smsc47m192.c @@ -86,7 +86,7 @@ static inline u8 IN_TO_REG(unsigned long val, int n) */ static inline s8 TEMP_TO_REG(int val) { - return clamp_val(SCALE(val, 1, 1000), -128000, 127000); + return SCALE(clamp_val(val, -128000, 127000), 1, 1000); } static inline int TEMP_FROM_REG(s8 val) @@ -384,6 +384,8 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, err = kstrtoul(buf, 10, &val); if (err) return err; + if (val > 255) + return -EINVAL; data->vrm = val; return count; diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index de17c5593d97..c5eec0290b37 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -110,6 +110,7 @@ config I2C_I801 Wellsburg (PCH) Coleto Creek (PCH) Wildcat Point-LP (PCH) + BayTrail (SOC) This driver can also be built as a module. If so, the module will be called i2c-i801. diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c index 843d01268ae9..8873d84e1d4f 100644 --- a/drivers/i2c/busses/i2c-at91.c +++ b/drivers/i2c/busses/i2c-at91.c @@ -101,6 +101,7 @@ struct at91_twi_dev { unsigned twi_cwgr_reg; struct at91_twi_pdata *pdata; bool use_dma; + bool recv_len_abort; struct at91_twi_dma dma; }; @@ -210,7 +211,7 @@ static void at91_twi_write_data_dma_callback(void *data) struct at91_twi_dev *dev = (struct at91_twi_dev *)data; dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg), - dev->buf_len, DMA_MEM_TO_DEV); + dev->buf_len, DMA_TO_DEVICE); at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); } @@ -267,12 +268,24 @@ static void at91_twi_read_next_byte(struct at91_twi_dev *dev) *dev->buf = at91_twi_read(dev, AT91_TWI_RHR) & 0xff; --dev->buf_len; + /* return if aborting, we only needed to read RHR to clear RXRDY*/ + if (dev->recv_len_abort) + return; + /* handle I2C_SMBUS_BLOCK_DATA */ if (unlikely(dev->msg->flags & I2C_M_RECV_LEN)) { - dev->msg->flags &= ~I2C_M_RECV_LEN; - dev->buf_len += *dev->buf; - dev->msg->len = dev->buf_len + 1; - dev_dbg(dev->dev, "received block length %d\n", dev->buf_len); + /* ensure length byte is a valid value */ + if (*dev->buf <= I2C_SMBUS_BLOCK_MAX && *dev->buf > 0) { + dev->msg->flags &= ~I2C_M_RECV_LEN; + dev->buf_len += *dev->buf; + dev->msg->len = dev->buf_len + 1; + dev_dbg(dev->dev, "received block length %d\n", + dev->buf_len); + } else { + /* abort and send the stop by reading one more byte */ + dev->recv_len_abort = true; + dev->buf_len = 1; + } } /* send stop if second but last byte has been read */ @@ -289,7 +302,7 @@ static void at91_twi_read_data_dma_callback(void *data) struct at91_twi_dev *dev = (struct at91_twi_dev *)data; dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg), - dev->buf_len, DMA_DEV_TO_MEM); + dev->buf_len, DMA_FROM_DEVICE); /* The last two bytes have to be read without using dma */ dev->buf += dev->buf_len - 2; @@ -421,8 +434,8 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) } } - ret = wait_for_completion_interruptible_timeout(&dev->cmd_complete, - dev->adapter.timeout); + ret = wait_for_completion_timeout(&dev->cmd_complete, + dev->adapter.timeout); if (ret == 0) { dev_err(dev->dev, "controller timed out\n"); at91_init_twi_bus(dev); @@ -444,6 +457,12 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) ret = -EIO; goto error; } + if (dev->recv_len_abort) { + dev_err(dev->dev, "invalid smbus block length recvd\n"); + ret = -EPROTO; + goto error; + } + dev_dbg(dev->dev, "transfer complete\n"); return 0; @@ -500,6 +519,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) dev->buf_len = m_start->len; dev->buf = m_start->buf; dev->msg = m_start; + dev->recv_len_abort = false; ret = at91_do_twi_transfer(dev); diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index 14c4b30d4ccc..d95b93016b0d 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -417,6 +417,9 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) */ dw_writel(dev, msgs[dev->msg_write_idx].addr | ic_tar, DW_IC_TAR); + /* enforce disabled interrupts (due to HW issues) */ + i2c_dw_disable_int(dev); + /* Enable the adapter */ __i2c_dw_enable(dev, true); diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 349c2d35e792..899f55937ca6 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -60,6 +60,7 @@ Wellsburg (PCH) MS 0x8d7f 32 hard yes yes yes Coleto Creek (PCH) 0x23b0 32 hard yes yes yes Wildcat Point-LP (PCH) 0x9ca2 32 hard yes yes yes + BayTrail (SOC) 0x0f12 32 hard yes yes yes Features supported by this driver: Software PEC no @@ -161,6 +162,7 @@ STATUS_ERROR_FLAGS) /* Older devices have their ID defined in <linux/pci_ids.h> */ +#define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS 0x0f12 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS 0x1c22 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS 0x1d22 /* Patsburg also has three 'Integrated Device Function' SMBus controllers */ @@ -822,6 +824,7 @@ static DEFINE_PCI_DEVICE_TABLE(i801_ids) = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS2) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_COLETOCREEK_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_SMBUS) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS) }, { 0, } }; diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 8ce4f517fc56..6e932d140573 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -497,7 +497,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc->wr_len_cmd = dma_size; desc->control |= ISMT_DESC_BLK; priv->dma_buffer[0] = command; - memcpy(&priv->dma_buffer[1], &data->block[1], dma_size); + memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1); } else { /* Block Read */ dev_dbg(dev, "I2C_SMBUS_BLOCK_DATA: READ\n"); @@ -525,7 +525,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc->wr_len_cmd = dma_size; desc->control |= ISMT_DESC_I2C; priv->dma_buffer[0] = command; - memcpy(&priv->dma_buffer[1], &data->block[1], dma_size); + memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1); } else { /* i2c Block Read */ dev_dbg(dev, "I2C_SMBUS_I2C_BLOCK_DATA: READ\n"); diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index d52d84937ad3..cf891752cc73 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -748,8 +748,7 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, } tclk = clk_get_rate(drv_data->clk); - rc = of_property_read_u32(np, "clock-frequency", &bus_freq); - if (rc) + if (of_property_read_u32(np, "clock-frequency", &bus_freq)) bus_freq = 100000; /* 100kHz by default */ if (!mv64xxx_find_baud_factors(bus_freq, tclk, diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 0282d4d42805..d3c5d6216575 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -561,6 +561,12 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, ret = -EINVAL; for (i = 0; i < num; i++) { + /* This HW can't send STOP after address phase */ + if (msgs[i].len == 0) { + ret = -EOPNOTSUPP; + break; + } + /*-------------- spin lock -----------------*/ spin_lock_irqsave(&priv->lock, flags); @@ -625,7 +631,8 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, static u32 rcar_i2c_func(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; + /* This HW can't do SMBUS_QUICK and NOSTART */ + return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK); } static const struct i2c_algorithm rcar_i2c_algo = { diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 684d21e71e4a..93ec37649346 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -1247,10 +1247,10 @@ static int s3c24xx_i2c_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev); - i2c->suspended = 0; clk_prepare_enable(i2c->clk); s3c24xx_i2c_init(i2c); clk_disable_unprepare(i2c->clk); + i2c->suspended = 0; return 0; } diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c index bfec313492b3..6f039c300141 100644 --- a/drivers/iio/accel/bma180.c +++ b/drivers/iio/accel/bma180.c @@ -68,13 +68,13 @@ /* Defaults values */ #define BMA180_DEF_PMODE 0 #define BMA180_DEF_BW 20 -#define BMA180_DEF_SCALE 250 +#define BMA180_DEF_SCALE 2452 /* Available values for sysfs */ #define BMA180_FLP_FREQ_AVAILABLE \ "10 20 40 75 150 300" #define BMA180_SCALE_AVAILABLE \ - "0.000130 0.000190 0.000250 0.000380 0.000500 0.000990 0.001980" + "0.001275 0.001863 0.002452 0.003727 0.004903 0.009709 0.019417" struct bma180_data { struct i2c_client *client; @@ -94,7 +94,7 @@ enum bma180_axis { }; static int bw_table[] = { 10, 20, 40, 75, 150, 300 }; /* Hz */ -static int scale_table[] = { 130, 190, 250, 380, 500, 990, 1980 }; +static int scale_table[] = { 1275, 1863, 2452, 3727, 4903, 9709, 19417 }; static int bma180_get_acc_reg(struct bma180_data *data, enum bma180_axis axis) { @@ -376,6 +376,8 @@ static int bma180_write_raw(struct iio_dev *indio_dev, mutex_unlock(&data->mutex); return ret; case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY: + if (val2) + return -EINVAL; mutex_lock(&data->mutex); ret = bma180_set_bw(data, val); mutex_unlock(&data->mutex); @@ -569,7 +571,7 @@ static int bma180_probe(struct i2c_client *client, trig->ops = &bma180_trigger_ops; iio_trigger_set_drvdata(trig, indio_dev); data->trig = trig; - indio_dev->trig = trig; + indio_dev->trig = iio_trigger_get(trig); ret = iio_trigger_register(trig); if (ret) diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 9a4e0e32a771..eb799a43aef0 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -472,7 +472,7 @@ static int ad_sd_probe_trigger(struct iio_dev *indio_dev) goto error_free_irq; /* select default trigger */ - indio_dev->trig = sigma_delta->trig; + indio_dev->trig = iio_trigger_get(sigma_delta->trig); return 0; diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index 5b1aa027c034..e6bf77d1ec08 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -322,12 +322,11 @@ static int at91_adc_channel_init(struct iio_dev *idev) return idev->num_channels; } -static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev, +static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev, struct at91_adc_trigger *triggers, const char *trigger_name) { struct at91_adc_state *st = iio_priv(idev); - u8 value = 0; int i; for (i = 0; i < st->trigger_number; i++) { @@ -340,15 +339,16 @@ static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev, return -ENOMEM; if (strcmp(trigger_name, name) == 0) { - value = triggers[i].value; kfree(name); - break; + if (triggers[i].value == 0) + return -EINVAL; + return triggers[i].value; } kfree(name); } - return value; + return -EINVAL; } static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) @@ -358,14 +358,14 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) struct iio_buffer *buffer = idev->buffer; struct at91_adc_reg_desc *reg = st->registers; u32 status = at91_adc_readl(st, reg->trigger_register); - u8 value; + int value; u8 bit; value = at91_adc_get_trigger_value_by_name(idev, st->trigger_list, idev->trig->name); - if (value == 0) - return -EINVAL; + if (value < 0) + return value; if (state) { st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL); @@ -765,14 +765,17 @@ static int at91_adc_probe_pdata(struct at91_adc_state *st, if (!pdata) return -EINVAL; + st->caps = (struct at91_adc_caps *) + platform_get_device_id(pdev)->driver_data; + st->use_external = pdata->use_external_triggers; st->vref_mv = pdata->vref; st->channels_mask = pdata->channels_used; - st->num_channels = pdata->num_channels; + st->num_channels = st->caps->num_channels; st->startup_time = pdata->startup_time; st->trigger_number = pdata->trigger_number; st->trigger_list = pdata->trigger_list; - st->registers = pdata->registers; + st->registers = &st->caps->registers; return 0; } @@ -1101,7 +1104,6 @@ static int at91_adc_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_OF static struct at91_adc_caps at91sam9260_caps = { .calc_startup_ticks = calc_startup_ticks_9260, .num_channels = 4, @@ -1154,11 +1156,27 @@ static const struct of_device_id at91_adc_dt_ids[] = { {}, }; MODULE_DEVICE_TABLE(of, at91_adc_dt_ids); -#endif + +static const struct platform_device_id at91_adc_ids[] = { + { + .name = "at91sam9260-adc", + .driver_data = (unsigned long)&at91sam9260_caps, + }, { + .name = "at91sam9g45-adc", + .driver_data = (unsigned long)&at91sam9g45_caps, + }, { + .name = "at91sam9x5-adc", + .driver_data = (unsigned long)&at91sam9x5_caps, + }, { + /* terminator */ + } +}; +MODULE_DEVICE_TABLE(platform, at91_adc_ids); static struct platform_driver at91_adc_driver = { .probe = at91_adc_probe, .remove = at91_adc_remove, + .id_table = at91_adc_ids, .driver = { .name = DRIVER_NAME, .of_match_table = of_match_ptr(at91_adc_dt_ids), diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index 360259266d4f..ef5ffc0c37a4 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -1258,8 +1258,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1038_channels, + .num_channels = ARRAY_SIZE(max1038_channels), }, [max11605] = { .bits = 8, @@ -1268,8 +1268,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1038_channels, + .num_channels = ARRAY_SIZE(max1038_channels), }, [max11606] = { .bits = 10, @@ -1318,8 +1318,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1138_channels, + .num_channels = ARRAY_SIZE(max1138_channels), }, [max11611] = { .bits = 10, @@ -1328,8 +1328,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1138_channels, + .num_channels = ARRAY_SIZE(max1138_channels), }, [max11612] = { .bits = 12, diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 31e786e3999b..63b2bb6bdbbc 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -375,7 +375,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, return -EAGAIN; } } - map_val = chan->channel + TOTAL_CHANNELS; + map_val = adc_dev->channel_step[chan->scan_index]; /* * We check the complete FIFO. We programmed just one entry but in case diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c index 7dcf83998e6f..1be235b01934 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c @@ -99,7 +99,8 @@ int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name, dev_err(&indio_dev->dev, "Trigger Register Failed\n"); goto error_free_trig; } - indio_dev->trig = attrb->trigger = trig; + attrb->trigger = trig; + indio_dev->trig = iio_trigger_get(trig); return ret; diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index 1665c8e4b62b..e18bc6782256 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -71,7 +71,7 @@ int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) goto st_sensors_free_memory; } - for (i = 0; i < n * num_data_channels; i++) { + for (i = 0; i < n * byte_for_channel; i++) { if (i < n) buf[i] = rx_array[i]; else diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 8fc3a97eb266..8d8ca6f1e16a 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -49,7 +49,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); goto iio_trigger_register_error; } - indio_dev->trig = sdata->trig; + indio_dev->trig = iio_trigger_get(sdata->trig); return 0; diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c index e3b3c5084070..eef50e91f17c 100644 --- a/drivers/iio/gyro/itg3200_buffer.c +++ b/drivers/iio/gyro/itg3200_buffer.c @@ -132,7 +132,7 @@ int itg3200_probe_trigger(struct iio_dev *indio_dev) goto error_free_irq; /* select default trigger */ - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); return 0; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index df7f1e1157ae..27a91768cc72 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -661,6 +661,7 @@ static int inv_mpu_probe(struct i2c_client *client, { struct inv_mpu6050_state *st; struct iio_dev *indio_dev; + struct inv_mpu6050_platform_data *pdata; int result; if (!i2c_check_functionality(client->adapter, @@ -673,8 +674,10 @@ static int inv_mpu_probe(struct i2c_client *client, st = iio_priv(indio_dev); st->client = client; - st->plat_data = *(struct inv_mpu6050_platform_data - *)dev_get_platdata(&client->dev); + pdata = (struct inv_mpu6050_platform_data + *)dev_get_platdata(&client->dev); + if (pdata) + st->plat_data = *pdata; /* power is turned on inside check chip type*/ result = inv_check_and_setup_chip(st, id); if (result) diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 03b9372c1212..926fccea8de0 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -135,7 +135,7 @@ int inv_mpu6050_probe_trigger(struct iio_dev *indio_dev) ret = iio_trigger_register(st->trig); if (ret) goto error_free_irq; - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); return 0; diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index c67d83bdc8f0..0f1d9b2ccdfa 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -165,7 +165,8 @@ static ssize_t iio_scan_el_show(struct device *dev, int ret; struct iio_dev *indio_dev = dev_to_iio_dev(dev); - ret = test_bit(to_iio_dev_attr(attr)->address, + /* Ensure ret is 0 or 1. */ + ret = !!test_bit(to_iio_dev_attr(attr)->address, indio_dev->buffer->scan_mask); return sprintf(buf, "%d\n", ret); @@ -866,7 +867,8 @@ int iio_scan_mask_query(struct iio_dev *indio_dev, if (!buffer->scan_mask) return 0; - return test_bit(bit, buffer->scan_mask); + /* Ensure return value is 0 or 1. */ + return !!test_bit(bit, buffer->scan_mask); }; EXPORT_SYMBOL_GPL(iio_scan_mask_query); @@ -951,7 +953,7 @@ static int iio_buffer_update_demux(struct iio_dev *indio_dev, /* Now we have the two masks, work from least sig and build up sizes */ for_each_set_bit(out_ind, - indio_dev->active_scan_mask, + buffer->scan_mask, indio_dev->masklength) { in_ind = find_next_bit(indio_dev->active_scan_mask, indio_dev->masklength, diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c index c9c1419fe6e0..f9360f497ed4 100644 --- a/drivers/iio/industrialio-event.c +++ b/drivers/iio/industrialio-event.c @@ -343,6 +343,9 @@ static int iio_device_add_event(struct iio_dev *indio_dev, &indio_dev->event_interface->dev_attr_list); kfree(postfix); + if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE)) + continue; + if (ret) return ret; diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 0cf5f8e06cfc..4fc88e617acf 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -178,12 +178,12 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np, index = of_property_match_string(np, "io-channel-names", name); chan = of_iio_channel_get(np, index); - if (!IS_ERR(chan)) + if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER) break; else if (name && index >= 0) { pr_err("ERROR: could not get IIO channel %s:%s(%i)\n", np->full_name, name ? name : "", index); - return chan; + return NULL; } /* @@ -193,8 +193,9 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np, */ np = np->parent; if (np && !of_get_property(np, "io-channel-ranges", NULL)) - break; + return NULL; } + return chan; } @@ -317,6 +318,7 @@ struct iio_channel *iio_channel_get(struct device *dev, if (channel != NULL) return channel; } + return iio_channel_get_sys(name, channel_name); } EXPORT_SYMBOL_GPL(iio_channel_get); diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index 47a6dbac2d0c..d976e6ce60db 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -221,6 +221,7 @@ static int cm32181_read_raw(struct iio_dev *indio_dev, *val = cm32181->calibscale; return IIO_VAL_INT; case IIO_CHAN_INFO_INT_TIME: + *val = 0; ret = cm32181_read_als_it(cm32181, val2); return ret; } diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c index a45e07492db3..39fc67e82138 100644 --- a/drivers/iio/light/cm36651.c +++ b/drivers/iio/light/cm36651.c @@ -652,7 +652,19 @@ static int cm36651_probe(struct i2c_client *client, cm36651->client = client; cm36651->ps_client = i2c_new_dummy(client->adapter, CM36651_I2C_ADDR_PS); + if (!cm36651->ps_client) { + dev_err(&client->dev, "%s: new i2c device failed\n", __func__); + ret = -ENODEV; + goto error_disable_reg; + } + cm36651->ara_client = i2c_new_dummy(client->adapter, CM36651_ARA); + if (!cm36651->ara_client) { + dev_err(&client->dev, "%s: new i2c device failed\n", __func__); + ret = -ENODEV; + goto error_i2c_unregister_ps; + } + mutex_init(&cm36651->lock); indio_dev->dev.parent = &client->dev; indio_dev->channels = cm36651_channels; @@ -664,7 +676,7 @@ static int cm36651_probe(struct i2c_client *client, ret = cm36651_setup_reg(cm36651); if (ret) { dev_err(&client->dev, "%s: register setup failed\n", __func__); - goto error_disable_reg; + goto error_i2c_unregister_ara; } ret = request_threaded_irq(client->irq, NULL, cm36651_irq_handler, @@ -672,7 +684,7 @@ static int cm36651_probe(struct i2c_client *client, "cm36651", indio_dev); if (ret) { dev_err(&client->dev, "%s: request irq failed\n", __func__); - goto error_disable_reg; + goto error_i2c_unregister_ara; } ret = iio_device_register(indio_dev); @@ -685,6 +697,10 @@ static int cm36651_probe(struct i2c_client *client, error_free_irq: free_irq(client->irq, indio_dev); +error_i2c_unregister_ara: + i2c_unregister_device(cm36651->ara_client); +error_i2c_unregister_ps: + i2c_unregister_device(cm36651->ps_client); error_disable_reg: regulator_disable(cm36651->vled_reg); return ret; @@ -698,6 +714,8 @@ static int cm36651_remove(struct i2c_client *client) iio_device_unregister(indio_dev); regulator_disable(cm36651->vled_reg); free_irq(client->irq, indio_dev); + i2c_unregister_device(cm36651->ps_client); + i2c_unregister_device(cm36651->ara_client); return 0; } diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 05423543f89d..053117c02bbc 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -352,8 +352,6 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val) { struct ak8975_data *data = iio_priv(indio_dev); struct i2c_client *client = data->client; - u16 meas_reg; - s16 raw; int ret; mutex_lock(&data->lock); @@ -401,16 +399,11 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val) dev_err(&client->dev, "Read axis data fails\n"); goto exit; } - meas_reg = ret; mutex_unlock(&data->lock); - /* Endian conversion of the measured values. */ - raw = (s16) (le16_to_cpu(meas_reg)); - /* Clamp to valid range. */ - raw = clamp_t(s16, raw, -4096, 4095); - *val = raw; + *val = clamp_t(s16, ret, -4096, 4095); return IIO_VAL_INT; exit: diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 52bbcfa1e077..476aa132a192 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -42,7 +42,8 @@ #define ST_MAGN_FS_AVL_5600MG 5600 #define ST_MAGN_FS_AVL_8000MG 8000 #define ST_MAGN_FS_AVL_8100MG 8100 -#define ST_MAGN_FS_AVL_10000MG 10000 +#define ST_MAGN_FS_AVL_12000MG 12000 +#define ST_MAGN_FS_AVL_16000MG 16000 /* CUSTOM VALUES FOR SENSOR 1 */ #define ST_MAGN_1_WAI_EXP 0x3c @@ -69,20 +70,20 @@ #define ST_MAGN_1_FS_AVL_4700_VAL 0x05 #define ST_MAGN_1_FS_AVL_5600_VAL 0x06 #define ST_MAGN_1_FS_AVL_8100_VAL 0x07 -#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 1100 -#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 855 -#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 670 -#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 450 -#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 400 -#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 330 -#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 230 -#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 980 -#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 760 -#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 600 -#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 400 -#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 355 -#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 295 -#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 205 +#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 909 +#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 1169 +#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 1492 +#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 2222 +#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 2500 +#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 3030 +#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 4347 +#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 1020 +#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 1315 +#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 1666 +#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 2500 +#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 2816 +#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 3389 +#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 4878 #define ST_MAGN_1_MULTIREAD_BIT false /* CUSTOM VALUES FOR SENSOR 2 */ @@ -105,10 +106,12 @@ #define ST_MAGN_2_FS_MASK 0x60 #define ST_MAGN_2_FS_AVL_4000_VAL 0x00 #define ST_MAGN_2_FS_AVL_8000_VAL 0x01 -#define ST_MAGN_2_FS_AVL_10000_VAL 0x02 -#define ST_MAGN_2_FS_AVL_4000_GAIN 430 -#define ST_MAGN_2_FS_AVL_8000_GAIN 230 -#define ST_MAGN_2_FS_AVL_10000_GAIN 230 +#define ST_MAGN_2_FS_AVL_12000_VAL 0x02 +#define ST_MAGN_2_FS_AVL_16000_VAL 0x03 +#define ST_MAGN_2_FS_AVL_4000_GAIN 146 +#define ST_MAGN_2_FS_AVL_8000_GAIN 292 +#define ST_MAGN_2_FS_AVL_12000_GAIN 438 +#define ST_MAGN_2_FS_AVL_16000_GAIN 584 #define ST_MAGN_2_MULTIREAD_BIT false #define ST_MAGN_2_OUT_X_L_ADDR 0x28 #define ST_MAGN_2_OUT_Y_L_ADDR 0x2a @@ -266,9 +269,14 @@ static const struct st_sensors st_magn_sensors[] = { .gain = ST_MAGN_2_FS_AVL_8000_GAIN, }, [2] = { - .num = ST_MAGN_FS_AVL_10000MG, - .value = ST_MAGN_2_FS_AVL_10000_VAL, - .gain = ST_MAGN_2_FS_AVL_10000_GAIN, + .num = ST_MAGN_FS_AVL_12000MG, + .value = ST_MAGN_2_FS_AVL_12000_VAL, + .gain = ST_MAGN_2_FS_AVL_12000_GAIN, + }, + [3] = { + .num = ST_MAGN_FS_AVL_16000MG, + .value = ST_MAGN_2_FS_AVL_16000_VAL, + .gain = ST_MAGN_2_FS_AVL_16000_GAIN, }, }, }, diff --git a/drivers/iio/pressure/mpl3115.c b/drivers/iio/pressure/mpl3115.c index ac8c8ab723e5..fe53669eeeeb 100644 --- a/drivers/iio/pressure/mpl3115.c +++ b/drivers/iio/pressure/mpl3115.c @@ -98,7 +98,7 @@ static int mpl3115_read_raw(struct iio_dev *indio_dev, mutex_unlock(&data->lock); if (ret < 0) return ret; - *val = sign_extend32(be32_to_cpu(tmp) >> 12, 23); + *val = be32_to_cpu(tmp) >> 12; return IIO_VAL_INT; case IIO_TEMP: /* in 0.0625 celsius / LSB */ mutex_lock(&data->lock); @@ -112,7 +112,7 @@ static int mpl3115_read_raw(struct iio_dev *indio_dev, mutex_unlock(&data->lock); if (ret < 0) return ret; - *val = sign_extend32(be32_to_cpu(tmp) >> 20, 15); + *val = sign_extend32(be32_to_cpu(tmp) >> 20, 11); return IIO_VAL_INT; default: return -EINVAL; @@ -185,7 +185,7 @@ static const struct iio_chan_spec mpl3115_channels[] = { BIT(IIO_CHAN_INFO_SCALE), .scan_index = 0, .scan_type = { - .sign = 's', + .sign = 'u', .realbits = 20, .storagebits = 32, .shift = 12, diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 0601b9daf840..c3239170d8b7 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -349,23 +349,6 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc, grh, &av->ah_attr); } -int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac) -{ - struct cm_id_private *cm_id_priv; - - cm_id_priv = container_of(id, struct cm_id_private, id); - - if (smac != NULL) - memcpy(cm_id_priv->av.smac, smac, sizeof(cm_id_priv->av.smac)); - - if (alt_smac != NULL) - memcpy(cm_id_priv->alt_av.smac, alt_smac, - sizeof(cm_id_priv->alt_av.smac)); - - return 0; -} -EXPORT_SYMBOL(ib_update_cm_av); - static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av) { struct cm_device *cm_dev; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 199958d9ddc8..42c3058e6e9c 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1284,15 +1284,6 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event; int offset, ret; - u8 smac[ETH_ALEN]; - u8 alt_smac[ETH_ALEN]; - u8 *psmac = smac; - u8 *palt_smac = alt_smac; - int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) == - RDMA_TRANSPORT_IB) && - (rdma_port_get_link_layer(cm_id->device, - ib_event->param.req_rcvd.port) == - IB_LINK_LAYER_ETHERNET)); listen_id = cm_id->context; if (!cma_check_req_qp_type(&listen_id->id, ib_event)) @@ -1336,28 +1327,11 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) ret = conn_id->id.event_handler(&conn_id->id, &event); if (ret) goto err3; - - if (is_iboe) { - if (ib_event->param.req_rcvd.primary_path != NULL) - rdma_addr_find_smac_by_sgid( - &ib_event->param.req_rcvd.primary_path->sgid, - psmac, NULL); - else - psmac = NULL; - if (ib_event->param.req_rcvd.alternate_path != NULL) - rdma_addr_find_smac_by_sgid( - &ib_event->param.req_rcvd.alternate_path->sgid, - palt_smac, NULL); - else - palt_smac = NULL; - } /* * Acquire mutex to prevent user executing rdma_destroy_id() * while we're accessing the cm_id. */ mutex_lock(&lock); - if (is_iboe) - ib_update_cm_av(cm_id, psmac, palt_smac); if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD)) ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 3d2e489ab732..ff9163dc1596 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -46,6 +46,7 @@ #include <linux/completion.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/sysctl.h> #include <rdma/iw_cm.h> #include <rdma/ib_addr.h> @@ -65,6 +66,20 @@ struct iwcm_work { struct list_head free_list; }; +static unsigned int default_backlog = 256; + +static struct ctl_table_header *iwcm_ctl_table_hdr; +static struct ctl_table iwcm_ctl_table[] = { + { + .procname = "default_backlog", + .data = &default_backlog, + .maxlen = sizeof(default_backlog), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + /* * The following services provide a mechanism for pre-allocating iwcm_work * elements. The design pre-allocates them based on the cm_id type: @@ -425,6 +440,9 @@ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog) cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); + if (!backlog) + backlog = default_backlog; + ret = alloc_work_entries(cm_id_priv, backlog); if (ret) return ret; @@ -1030,11 +1048,20 @@ static int __init iw_cm_init(void) if (!iwcm_wq) return -ENOMEM; + iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm", + iwcm_ctl_table); + if (!iwcm_ctl_table_hdr) { + pr_err("iw_cm: couldn't register sysctl paths\n"); + destroy_workqueue(iwcm_wq); + return -ENOMEM; + } + return 0; } static void __exit iw_cm_cleanup(void) { + unregister_net_sysctl_table(iwcm_ctl_table_hdr); destroy_workqueue(iwcm_wq); } diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index f0d588f8859e..1acb99100556 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -98,7 +98,7 @@ struct ib_umad_port { struct ib_umad_device { int start_port, end_port; - struct kref ref; + struct kobject kobj; struct ib_umad_port port[0]; }; @@ -134,14 +134,18 @@ static DECLARE_BITMAP(dev_map, IB_UMAD_MAX_PORTS); static void ib_umad_add_one(struct ib_device *device); static void ib_umad_remove_one(struct ib_device *device); -static void ib_umad_release_dev(struct kref *ref) +static void ib_umad_release_dev(struct kobject *kobj) { struct ib_umad_device *dev = - container_of(ref, struct ib_umad_device, ref); + container_of(kobj, struct ib_umad_device, kobj); kfree(dev); } +static struct kobj_type ib_umad_dev_ktype = { + .release = ib_umad_release_dev, +}; + static int hdr_size(struct ib_umad_file *file) { return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) : @@ -780,27 +784,19 @@ static int ib_umad_open(struct inode *inode, struct file *filp) { struct ib_umad_port *port; struct ib_umad_file *file; - int ret; + int ret = -ENXIO; port = container_of(inode->i_cdev, struct ib_umad_port, cdev); - if (port) - kref_get(&port->umad_dev->ref); - else - return -ENXIO; mutex_lock(&port->file_mutex); - if (!port->ib_dev) { - ret = -ENXIO; + if (!port->ib_dev) goto out; - } + ret = -ENOMEM; file = kzalloc(sizeof *file, GFP_KERNEL); - if (!file) { - kref_put(&port->umad_dev->ref, ib_umad_release_dev); - ret = -ENOMEM; + if (!file) goto out; - } mutex_init(&file->mutex); spin_lock_init(&file->send_lock); @@ -814,6 +810,13 @@ static int ib_umad_open(struct inode *inode, struct file *filp) list_add_tail(&file->port_list, &port->file_list); ret = nonseekable_open(inode, filp); + if (ret) { + list_del(&file->port_list); + kfree(file); + goto out; + } + + kobject_get(&port->umad_dev->kobj); out: mutex_unlock(&port->file_mutex); @@ -852,7 +855,7 @@ static int ib_umad_close(struct inode *inode, struct file *filp) mutex_unlock(&file->port->file_mutex); kfree(file); - kref_put(&dev->ref, ib_umad_release_dev); + kobject_put(&dev->kobj); return 0; } @@ -880,10 +883,6 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp) int ret; port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev); - if (port) - kref_get(&port->umad_dev->ref); - else - return -ENXIO; if (filp->f_flags & O_NONBLOCK) { if (down_trylock(&port->sm_sem)) { @@ -898,17 +897,27 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp) } ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props); - if (ret) { - up(&port->sm_sem); - goto fail; - } + if (ret) + goto err_up_sem; filp->private_data = port; - return nonseekable_open(inode, filp); + ret = nonseekable_open(inode, filp); + if (ret) + goto err_clr_sm_cap; + + kobject_get(&port->umad_dev->kobj); + + return 0; + +err_clr_sm_cap: + swap(props.set_port_cap_mask, props.clr_port_cap_mask); + ib_modify_port(port->ib_dev, port->port_num, 0, &props); + +err_up_sem: + up(&port->sm_sem); fail: - kref_put(&port->umad_dev->ref, ib_umad_release_dev); return ret; } @@ -927,7 +936,7 @@ static int ib_umad_sm_close(struct inode *inode, struct file *filp) up(&port->sm_sem); - kref_put(&port->umad_dev->ref, ib_umad_release_dev); + kobject_put(&port->umad_dev->kobj); return ret; } @@ -995,6 +1004,7 @@ static int find_overflow_devnum(void) } static int ib_umad_init_port(struct ib_device *device, int port_num, + struct ib_umad_device *umad_dev, struct ib_umad_port *port) { int devnum; @@ -1027,6 +1037,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num, cdev_init(&port->cdev, &umad_fops); port->cdev.owner = THIS_MODULE; + port->cdev.kobj.parent = &umad_dev->kobj; kobject_set_name(&port->cdev.kobj, "umad%d", port->dev_num); if (cdev_add(&port->cdev, base, 1)) goto err_cdev; @@ -1045,6 +1056,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num, base += IB_UMAD_MAX_PORTS; cdev_init(&port->sm_cdev, &umad_sm_fops); port->sm_cdev.owner = THIS_MODULE; + port->sm_cdev.kobj.parent = &umad_dev->kobj; kobject_set_name(&port->sm_cdev.kobj, "issm%d", port->dev_num); if (cdev_add(&port->sm_cdev, base, 1)) goto err_sm_cdev; @@ -1138,7 +1150,7 @@ static void ib_umad_add_one(struct ib_device *device) if (!umad_dev) return; - kref_init(&umad_dev->ref); + kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype); umad_dev->start_port = s; umad_dev->end_port = e; @@ -1146,7 +1158,8 @@ static void ib_umad_add_one(struct ib_device *device) for (i = s; i <= e; ++i) { umad_dev->port[i - s].umad_dev = umad_dev; - if (ib_umad_init_port(device, i, &umad_dev->port[i - s])) + if (ib_umad_init_port(device, i, umad_dev, + &umad_dev->port[i - s])) goto err; } @@ -1158,7 +1171,7 @@ err: while (--i >= s) ib_umad_kill_port(&umad_dev->port[i - s]); - kref_put(&umad_dev->ref, ib_umad_release_dev); + kobject_put(&umad_dev->kobj); } static void ib_umad_remove_one(struct ib_device *device) @@ -1172,7 +1185,7 @@ static void ib_umad_remove_one(struct ib_device *device) for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i) ib_umad_kill_port(&umad_dev->port[i]); - kref_put(&umad_dev->ref, ib_umad_release_dev); + kobject_put(&umad_dev->kobj); } static char *umad_devnode(struct device *dev, umode_t *mode) diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index e7bee46868d1..abd97247443e 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -140,5 +140,9 @@ void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst, dst->packet_life_time = src->packet_life_time; dst->preference = src->preference; dst->packet_life_time_selector = src->packet_life_time_selector; + + memset(dst->smac, 0, sizeof(dst->smac)); + memset(dst->dmac, 0, sizeof(dst->dmac)); + dst->vlan_id = 0xffff; } EXPORT_SYMBOL(ib_copy_path_rec_from_user); diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c index 212150c25ea0..8cc837537768 100644 --- a/drivers/infiniband/hw/ehca/ehca_cq.c +++ b/drivers/infiniband/hw/ehca/ehca_cq.c @@ -283,6 +283,7 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector, (my_cq->galpas.user.fw_handle & (PAGE_SIZE - 1)); if (ib_copy_to_udata(udata, &resp, sizeof(resp))) { ehca_err(device, "Copy to udata failed."); + cq = ERR_PTR(-EFAULT); goto create_cq_exit4; } } diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c index 714293b78518..45802e97332e 100644 --- a/drivers/infiniband/hw/ipath/ipath_diag.c +++ b/drivers/infiniband/hw/ipath/ipath_diag.c @@ -326,7 +326,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp, size_t count, loff_t *off) { u32 __iomem *piobuf; - u32 plen, clen, pbufn; + u32 plen, pbufn, maxlen_reserve; struct ipath_diag_pkt odp; struct ipath_diag_xpkt dp; u32 *tmpbuf = NULL; @@ -335,42 +335,24 @@ static ssize_t ipath_diagpkt_write(struct file *fp, u64 val; u32 l_state, lt_state; /* LinkState, LinkTrainingState */ - if (count < sizeof(odp)) { - ret = -EINVAL; - goto bail; - } if (count == sizeof(dp)) { if (copy_from_user(&dp, data, sizeof(dp))) { ret = -EFAULT; goto bail; } - } else if (copy_from_user(&odp, data, sizeof(odp))) { - ret = -EFAULT; - goto bail; - } - - /* - * Due to padding/alignment issues (lessened with new struct) - * the old and new structs are the same length. We need to - * disambiguate them, which we can do because odp.len has never - * been less than the total of LRH+BTH+DETH so far, while - * dp.unit (same offset) unit is unlikely to get that high. - * Similarly, dp.data, the pointer to user at the same offset - * as odp.unit, is almost certainly at least one (512byte)page - * "above" NULL. The if-block below can be omitted if compatibility - * between a new driver and older diagnostic code is unimportant. - * compatibility the other direction (new diags, old driver) is - * handled in the diagnostic code, with a warning. - */ - if (dp.unit >= 20 && dp.data < 512) { - /* very probable version mismatch. Fix it up */ - memcpy(&odp, &dp, sizeof(odp)); - /* We got a legacy dp, copy elements to dp */ + } else if (count == sizeof(odp)) { + if (copy_from_user(&odp, data, sizeof(odp))) { + ret = -EFAULT; + goto bail; + } + dp.len = odp.len; dp.unit = odp.unit; dp.data = odp.data; - dp.len = odp.len; - dp.pbc_wd = 0; /* Indicate we need to compute PBC wd */ + dp.pbc_wd = 0; + } else { + ret = -EINVAL; + goto bail; } /* send count must be an exact number of dwords */ @@ -379,7 +361,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp, goto bail; } - clen = dp.len >> 2; + plen = dp.len >> 2; dd = ipath_lookup(dp.unit); if (!dd || !(dd->ipath_flags & IPATH_PRESENT) || @@ -422,16 +404,22 @@ static ssize_t ipath_diagpkt_write(struct file *fp, goto bail; } - /* need total length before first word written */ - /* +1 word is for the qword padding */ - plen = sizeof(u32) + dp.len; - - if ((plen + 4) > dd->ipath_ibmaxlen) { + /* + * need total length before first word written, plus 2 Dwords. One Dword + * is for padding so we get the full user data when not aligned on + * a word boundary. The other Dword is to make sure we have room for the + * ICRC which gets tacked on later. + */ + maxlen_reserve = 2 * sizeof(u32); + if (dp.len > dd->ipath_ibmaxlen - maxlen_reserve) { ipath_dbg("Pkt len 0x%x > ibmaxlen %x\n", - plen - 4, dd->ipath_ibmaxlen); + dp.len, dd->ipath_ibmaxlen); ret = -EINVAL; - goto bail; /* before writing pbc */ + goto bail; } + + plen = sizeof(u32) + dp.len; + tmpbuf = vmalloc(plen); if (!tmpbuf) { dev_info(&dd->pcidev->dev, "Unable to allocate tmp buffer, " @@ -473,11 +461,11 @@ static ssize_t ipath_diagpkt_write(struct file *fp, */ if (dd->ipath_flags & IPATH_PIO_FLUSH_WC) { ipath_flush_wc(); - __iowrite32_copy(piobuf + 2, tmpbuf, clen - 1); + __iowrite32_copy(piobuf + 2, tmpbuf, plen - 1); ipath_flush_wc(); - __raw_writel(tmpbuf[clen - 1], piobuf + clen + 1); + __raw_writel(tmpbuf[plen - 1], piobuf + plen + 1); } else - __iowrite32_copy(piobuf + 2, tmpbuf, clen); + __iowrite32_copy(piobuf + 2, tmpbuf, plen); ipath_flush_wc(); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index f9c12e92fdd6..11f0606792bb 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1622,6 +1622,7 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, struct inet6_dev *in6_dev; union ib_gid *pgid; struct inet6_ifaddr *ifp; + union ib_gid default_gid; #endif union ib_gid gid; @@ -1642,12 +1643,15 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) + mlx4_make_default_gid(dev, &default_gid); /* IPv6 gids */ in6_dev = in6_dev_get(dev); if (in6_dev) { read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { pgid = (union ib_gid *)&ifp->addr; + if (!memcmp(pgid, &default_gid, sizeof(*pgid))) + continue; update_gid_table(ibdev, port, pgid, 0, 0); } read_unlock_bh(&in6_dev->lock); @@ -1723,31 +1727,34 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev) port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } else { - reset_gid_table(ibdev, port); - } - /* if using bonding/team and a slave port is down, we don't the bond IP - * based gids in the table since flows that select port by gid may get - * the down port. - */ - if (curr_master && (port_state == IB_PORT_DOWN)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } - /* if bonding is used it is possible that we add it to masters - * only after IP address is assigned to the net bonding - * interface. - */ - if (curr_master && (old_master != curr_master)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_master, ibdev, port); - } + /* if using bonding/team and a slave port is down, we + * don't the bond IP based gids in the table since + * flows that select port by gid may get the down port. + */ + if (curr_master && (port_state == IB_PORT_DOWN)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + } + /* if bonding is used it is possible that we add it to + * masters only after IP address is assigned to the + * net bonding interface. + */ + if (curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_master, ibdev, port); + } - if (!curr_master && (old_master != curr_master)) { + if (!curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); + } + } else { reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); } } diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index b1705ce6eb88..8c726f183980 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -32,6 +32,7 @@ #include <linux/kref.h> #include <rdma/ib_umem.h> +#include <rdma/ib_user_verbs.h> #include "mlx5_ib.h" #include "user.h" @@ -540,14 +541,24 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata, int *cqe_size, int *index, int *inlen) { struct mlx5_ib_create_cq ucmd; + size_t ucmdlen; int page_shift; int npages; int ncont; int err; - if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) + ucmdlen = + (udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) < + sizeof(ucmd)) ? (sizeof(ucmd) - + sizeof(ucmd.reserved)) : sizeof(ucmd); + + if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) return -EFAULT; + if (ucmdlen == sizeof(ucmd) && + ucmd.reserved != 0) + return -EINVAL; + if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128) return -EINVAL; diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 210b3eaf188a..384af6dec5eb 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -35,6 +35,7 @@ #include <linux/mlx5/srq.h> #include <linux/slab.h> #include <rdma/ib_umem.h> +#include <rdma/ib_user_verbs.h> #include "mlx5_ib.h" #include "user.h" @@ -78,16 +79,27 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_ib_create_srq ucmd; + size_t ucmdlen; int err; int npages; int page_shift; int ncont; u32 offset; - if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) { + ucmdlen = + (udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) < + sizeof(ucmd)) ? (sizeof(ucmd) - + sizeof(ucmd.reserved)) : sizeof(ucmd); + + if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) { mlx5_ib_dbg(dev, "failed copy udata\n"); return -EFAULT; } + + if (ucmdlen == sizeof(ucmd) && + ucmd.reserved != 0) + return -EINVAL; + srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE); srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, buf_size, diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h index 0f4f8e42a17f..d0ba264ac1ed 100644 --- a/drivers/infiniband/hw/mlx5/user.h +++ b/drivers/infiniband/hw/mlx5/user.h @@ -91,6 +91,7 @@ struct mlx5_ib_create_cq { __u64 buf_addr; __u64 db_addr; __u32 cqe_size; + __u32 reserved; /* explicit padding (optional on i386) */ }; struct mlx5_ib_create_cq_resp { @@ -109,6 +110,7 @@ struct mlx5_ib_create_srq { __u64 buf_addr; __u64 db_addr; __u32 flags; + __u32 reserved; /* explicit padding (optional on i386) */ }; struct mlx5_ib_create_srq_resp { diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 5b71d43bd89c..42dde06fdb91 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -695,6 +695,7 @@ static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries, if (context && ib_copy_to_udata(udata, &cq->cqn, sizeof (__u32))) { mthca_free_cq(to_mdev(ibdev), cq); + err = -EFAULT; goto err_free; } diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 8308e3634767..eb624611f94b 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -1186,7 +1186,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd, nes_free_resource(nesadapter, nesadapter->allocated_qps, qp_num); kfree(nesqp->allocated_buffer); nes_debug(NES_DBG_QP, "ib_copy_from_udata() Failed \n"); - return NULL; + return ERR_PTR(-EFAULT); } if (req.user_wqe_buffers) { virt_wqs = 1; diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 799a0c3bffc4..6abd3ed3cd51 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -193,6 +193,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) struct qib_qp_iter *iter; loff_t n = *pos; + rcu_read_lock(); iter = qib_qp_iter_init(s->private); if (!iter) return NULL; @@ -224,7 +225,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) { - /* nothing for now */ + rcu_read_unlock(); } static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr) diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 275f247f9fca..2023cd61b897 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -1578,7 +1578,7 @@ static int do_qib_user_sdma_queue_create(struct file *fp) struct qib_ctxtdata *rcd = fd->rcd; struct qib_devdata *dd = rcd->dd; - if (dd->flags & QIB_HAS_SEND_DMA) + if (dd->flags & QIB_HAS_SEND_DMA) { fd->pq = qib_user_sdma_queue_create(&dd->pcidev->dev, dd->unit, @@ -1586,6 +1586,7 @@ static int do_qib_user_sdma_queue_create(struct file *fp) fd->subctxt); if (!fd->pq) return -ENOMEM; + } return 0; } diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index 24e802f4ea2f..76c3e177164d 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -1097,14 +1097,10 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra) int ret; dd = (struct qib_devdata *) ib_alloc_device(sizeof(*dd) + extra); - if (!dd) { - dd = ERR_PTR(-ENOMEM); - goto bail; - } + if (!dd) + return ERR_PTR(-ENOMEM); -#ifdef CONFIG_DEBUG_FS - qib_dbg_ibdev_init(&dd->verbs_dev); -#endif + INIT_LIST_HEAD(&dd->list); idr_preload(GFP_KERNEL); spin_lock_irqsave(&qib_devs_lock, flags); @@ -1121,11 +1117,6 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra) if (ret < 0) { qib_early_err(&pdev->dev, "Could not allocate unit ID: error %d\n", -ret); -#ifdef CONFIG_DEBUG_FS - qib_dbg_ibdev_exit(&dd->verbs_dev); -#endif - ib_dealloc_device(&dd->verbs_dev.ibdev); - dd = ERR_PTR(ret); goto bail; } @@ -1139,9 +1130,15 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra) qib_early_err(&pdev->dev, "Could not alloc cpulist info, cpu affinity might be wrong\n"); } - -bail: +#ifdef CONFIG_DEBUG_FS + qib_dbg_ibdev_init(&dd->verbs_dev); +#endif return dd; +bail: + if (!list_empty(&dd->list)) + list_del_init(&dd->list); + ib_dealloc_device(&dd->verbs_dev.ibdev); + return ERR_PTR(ret);; } /* diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index ccb119143d20..1dd9fcbb7c9a 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -1028,7 +1028,7 @@ static int set_pkeys(struct qib_devdata *dd, u8 port, u16 *pkeys) event.event = IB_EVENT_PKEY_CHANGE; event.device = &dd->verbs_dev.ibdev; - event.element.port_num = 1; + event.element.port_num = port; ib_dispatch_event(&event); } return 0; diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 0cad0c40d742..6a71b2b41b27 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -1324,7 +1324,6 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) struct qib_qp *pqp = iter->qp; struct qib_qp *qp; - rcu_read_lock(); for (; n < dev->qp_table_size; n++) { if (pqp) qp = rcu_dereference(pqp->next); @@ -1332,18 +1331,11 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) qp = rcu_dereference(dev->qp_table[n]); pqp = qp; if (qp) { - if (iter->qp) - atomic_dec(&iter->qp->refcount); - atomic_inc(&qp->refcount); - rcu_read_unlock(); iter->qp = qp; iter->n = n; return 0; } } - rcu_read_unlock(); - if (iter->qp) - atomic_dec(&iter->qp->refcount); return ret; } diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 8ee228e9ab5a..c5c194c2e0b6 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -28,6 +28,7 @@ #include <target/target_core_base.h> #include <target/target_core_fabric.h> #include <target/iscsi/iscsi_transport.h> +#include <linux/semaphore.h> #include "isert_proto.h" #include "ib_isert.h" @@ -436,11 +437,18 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn) { struct fast_reg_descriptor *fr_desc; struct isert_device *device = isert_conn->conn_device; - int i, ret; + struct se_session *se_sess = isert_conn->conn->sess->se_sess; + struct se_node_acl *se_nacl = se_sess->se_node_acl; + int i, ret, tag_num; + /* + * Setup the number of FRMRs based upon the number of tags + * available to session in iscsi_target_locate_portal(). + */ + tag_num = max_t(u32, ISCSIT_MIN_TAGS, se_nacl->queue_depth); + tag_num = (tag_num * 2) + ISCSIT_EXTRA_TAGS; - INIT_LIST_HEAD(&isert_conn->conn_fr_pool); isert_conn->conn_fr_pool_size = 0; - for (i = 0; i < ISCSI_DEF_XMIT_CMDS_MAX; i++) { + for (i = 0; i < tag_num; i++) { fr_desc = kzalloc(sizeof(*fr_desc), GFP_KERNEL); if (!fr_desc) { pr_err("Failed to allocate fast_reg descriptor\n"); @@ -481,6 +489,14 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) struct ib_device *ib_dev = cma_id->device; int ret = 0; + spin_lock_bh(&np->np_thread_lock); + if (!np->enabled) { + spin_unlock_bh(&np->np_thread_lock); + pr_debug("iscsi_np is not enabled, reject connect request\n"); + return rdma_reject(cma_id, NULL, 0); + } + spin_unlock_bh(&np->np_thread_lock); + pr_debug("Entering isert_connect_request cma_id: %p, context: %p\n", cma_id, cma_id->context); @@ -495,9 +511,9 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) init_completion(&isert_conn->conn_wait); init_completion(&isert_conn->conn_wait_comp_err); kref_init(&isert_conn->conn_kref); - kref_get(&isert_conn->conn_kref); mutex_init(&isert_conn->conn_mutex); spin_lock_init(&isert_conn->conn_lock); + INIT_LIST_HEAD(&isert_conn->conn_fr_pool); cma_id->context = isert_conn; isert_conn->conn_cm_id = cma_id; @@ -569,31 +585,19 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) goto out_mr; } - if (device->use_fastreg) { - ret = isert_conn_create_fastreg_pool(isert_conn); - if (ret) { - pr_err("Conn: %p failed to create fastreg pool\n", - isert_conn); - goto out_fastreg; - } - } - ret = isert_conn_setup_qp(isert_conn, cma_id); if (ret) goto out_conn_dev; mutex_lock(&isert_np->np_accept_mutex); - list_add_tail(&isert_np->np_accept_list, &isert_conn->conn_accept_node); + list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list); mutex_unlock(&isert_np->np_accept_mutex); - pr_debug("isert_connect_request() waking up np_accept_wq: %p\n", np); - wake_up(&isert_np->np_accept_wq); + pr_debug("isert_connect_request() up np_sem np: %p\n", np); + up(&isert_np->np_sem); return 0; out_conn_dev: - if (device->use_fastreg) - isert_conn_free_fastreg_pool(isert_conn); -out_fastreg: ib_dereg_mr(isert_conn->conn_mr); out_mr: ib_dealloc_pd(isert_conn->conn_pd); @@ -658,7 +662,9 @@ isert_connect_release(struct isert_conn *isert_conn) static void isert_connected_handler(struct rdma_cm_id *cma_id) { - return; + struct isert_conn *isert_conn = cma_id->context; + + kref_get(&isert_conn->conn_kref); } static void @@ -700,26 +706,24 @@ isert_disconnect_work(struct work_struct *work) isert_put_conn(isert_conn); return; } - if (!isert_conn->logout_posted) { - pr_debug("Calling rdma_disconnect for !logout_posted from" - " isert_disconnect_work\n"); + + if (isert_conn->disconnect) { + /* Send DREQ/DREP towards our initiator */ rdma_disconnect(isert_conn->conn_cm_id); - mutex_unlock(&isert_conn->conn_mutex); - iscsit_cause_connection_reinstatement(isert_conn->conn, 0); - goto wake_up; } + mutex_unlock(&isert_conn->conn_mutex); wake_up: complete(&isert_conn->conn_wait); - isert_put_conn(isert_conn); } static void -isert_disconnected_handler(struct rdma_cm_id *cma_id) +isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect) { struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context; + isert_conn->disconnect = disconnect; INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work); schedule_work(&isert_conn->conn_logout_work); } @@ -728,29 +732,28 @@ static int isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { int ret = 0; + bool disconnect = false; pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n", event->event, event->status, cma_id->context, cma_id); switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: - pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n"); ret = isert_connect_request(cma_id, event); break; case RDMA_CM_EVENT_ESTABLISHED: - pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n"); isert_connected_handler(cma_id); break; - case RDMA_CM_EVENT_DISCONNECTED: - pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n"); - isert_disconnected_handler(cma_id); - break; - case RDMA_CM_EVENT_DEVICE_REMOVAL: - case RDMA_CM_EVENT_ADDR_CHANGE: + case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */ + case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */ + disconnect = true; + case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */ + isert_disconnected_handler(cma_id, disconnect); break; case RDMA_CM_EVENT_CONNECT_ERROR: default: - pr_err("Unknown RDMA CMA event: %d\n", event->event); + pr_err("Unhandled RDMA CMA event: %d\n", event->event); break; } @@ -967,6 +970,15 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, } if (!login->login_failed) { if (login->login_complete) { + if (isert_conn->conn_device->use_fastreg) { + ret = isert_conn_create_fastreg_pool(isert_conn); + if (ret) { + pr_err("Conn: %p failed to create" + " fastreg pool\n", isert_conn); + return ret; + } + } + ret = isert_alloc_rx_descriptors(isert_conn); if (ret) return ret; @@ -1111,6 +1123,8 @@ sequence_cmd: if (!rc && dump_payload == false && unsol_data) iscsit_set_unsoliticed_dataout(cmd); + else if (dump_payload && imm_data) + target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); return 0; } @@ -1451,7 +1465,7 @@ isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn) } static void -isert_put_cmd(struct isert_cmd *isert_cmd) +isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err) { struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; struct isert_conn *isert_conn = isert_cmd->conn; @@ -1467,8 +1481,21 @@ isert_put_cmd(struct isert_cmd *isert_cmd) list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); - if (cmd->data_direction == DMA_TO_DEVICE) + if (cmd->data_direction == DMA_TO_DEVICE) { iscsit_stop_dataout_timer(cmd); + /* + * Check for special case during comp_err where + * WRITE_PENDING has been handed off from core, + * but requires an extra target_put_sess_cmd() + * before transport_generic_free_cmd() below. + */ + if (comp_err && + cmd->se_cmd.t_state == TRANSPORT_WRITE_PENDING) { + struct se_cmd *se_cmd = &cmd->se_cmd; + + target_put_sess_cmd(se_cmd->se_sess, se_cmd); + } + } device->unreg_rdma_mem(isert_cmd, isert_conn); transport_generic_free_cmd(&cmd->se_cmd, 0); @@ -1523,7 +1550,7 @@ isert_unmap_tx_desc(struct iser_tx_desc *tx_desc, struct ib_device *ib_dev) static void isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd, - struct ib_device *ib_dev) + struct ib_device *ib_dev, bool comp_err) { if (isert_cmd->pdu_buf_dma != 0) { pr_debug("Calling ib_dma_unmap_single for isert_cmd->pdu_buf_dma\n"); @@ -1533,7 +1560,7 @@ isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd, } isert_unmap_tx_desc(tx_desc, ib_dev); - isert_put_cmd(isert_cmd); + isert_put_cmd(isert_cmd, comp_err); } static void @@ -1577,28 +1604,25 @@ isert_do_control_comp(struct work_struct *work) iscsit_tmr_post_handler(cmd, cmd->conn); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev); + isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false); break; case ISTATE_SEND_REJECT: pr_debug("Got isert_do_control_comp ISTATE_SEND_REJECT: >>>\n"); atomic_dec(&isert_conn->post_send_buf_count); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev); + isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false); break; case ISTATE_SEND_LOGOUTRSP: pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n"); - /* - * Call atomic_dec(&isert_conn->post_send_buf_count) - * from isert_wait_conn() - */ - isert_conn->logout_posted = true; + + atomic_dec(&isert_conn->post_send_buf_count); iscsit_logout_post_handler(cmd, cmd->conn); break; case ISTATE_SEND_TEXTRSP: atomic_dec(&isert_conn->post_send_buf_count); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev); + isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false); break; default: pr_err("Unknown do_control_comp i_state %d\n", cmd->i_state); @@ -1629,7 +1653,7 @@ isert_response_completion(struct iser_tx_desc *tx_desc, atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(tx_desc, isert_cmd, ib_dev); + isert_completion_put(tx_desc, isert_cmd, ib_dev, false); } static void @@ -1710,7 +1734,7 @@ isert_cq_drain_comp_llist(struct isert_conn *isert_conn, struct ib_device *ib_de wr = &t->isert_cmd->rdma_wr; atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); - isert_completion_put(t, t->isert_cmd, ib_dev); + isert_completion_put(t, t->isert_cmd, ib_dev, true); } } @@ -1729,14 +1753,14 @@ isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn wr = &t->isert_cmd->rdma_wr; atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); - isert_completion_put(t, t->isert_cmd, ib_dev); + isert_completion_put(t, t->isert_cmd, ib_dev, true); } tx_desc->comp_llnode_batch = NULL; if (!isert_cmd) isert_unmap_tx_desc(tx_desc, ib_dev); else - isert_completion_put(tx_desc, isert_cmd, ib_dev); + isert_completion_put(tx_desc, isert_cmd, ib_dev, true); } static void @@ -1762,6 +1786,8 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn) isert_conn->state = ISER_CONN_DOWN; mutex_unlock(&isert_conn->conn_mutex); + iscsit_cause_connection_reinstatement(isert_conn->conn, 0); + complete(&isert_conn->conn_wait_comp_err); } @@ -2018,7 +2044,7 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) int rc; isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc); - rc = iscsit_build_text_rsp(cmd, conn, hdr); + rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_INFINIBAND); if (rc < 0) return rc; @@ -2551,7 +2577,7 @@ isert_setup_np(struct iscsi_np *np, pr_err("Unable to allocate struct isert_np\n"); return -ENOMEM; } - init_waitqueue_head(&isert_np->np_accept_wq); + sema_init(&isert_np->np_sem, 0); mutex_init(&isert_np->np_accept_mutex); INIT_LIST_HEAD(&isert_np->np_accept_list); init_completion(&isert_np->np_login_comp); @@ -2600,18 +2626,6 @@ out: } static int -isert_check_accept_queue(struct isert_np *isert_np) -{ - int empty; - - mutex_lock(&isert_np->np_accept_mutex); - empty = list_empty(&isert_np->np_accept_list); - mutex_unlock(&isert_np->np_accept_mutex); - - return empty; -} - -static int isert_rdma_accept(struct isert_conn *isert_conn) { struct rdma_cm_id *cm_id = isert_conn->conn_cm_id; @@ -2703,16 +2717,19 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) int max_accept = 0, ret; accept_wait: - ret = wait_event_interruptible(isert_np->np_accept_wq, - !isert_check_accept_queue(isert_np) || - np->np_thread_state == ISCSI_NP_THREAD_RESET); + ret = down_interruptible(&isert_np->np_sem); if (max_accept > 5) return -ENODEV; spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) { spin_unlock_bh(&np->np_thread_lock); - pr_err("ISCSI_NP_THREAD_RESET for isert_accept_np\n"); + pr_debug("np_thread_state %d for isert_accept_np\n", + np->np_thread_state); + /** + * No point in stalling here when np_thread + * is in state RESET/SHUTDOWN/EXIT - bail + **/ return -ENODEV; } spin_unlock_bh(&np->np_thread_lock); @@ -2762,15 +2779,9 @@ static void isert_wait_conn(struct iscsi_conn *conn) struct isert_conn *isert_conn = conn->context; pr_debug("isert_wait_conn: Starting \n"); - /* - * Decrement post_send_buf_count for special case when called - * from isert_do_control_comp() -> iscsit_logout_post_handler() - */ - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->logout_posted) - atomic_dec(&isert_conn->post_send_buf_count); - if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) { + mutex_lock(&isert_conn->conn_mutex); + if (isert_conn->conn_cm_id) { pr_debug("Calling rdma_disconnect from isert_wait_conn\n"); rdma_disconnect(isert_conn->conn_cm_id); } @@ -2789,6 +2800,7 @@ static void isert_wait_conn(struct iscsi_conn *conn) wait_for_completion(&isert_conn->conn_wait_comp_err); wait_for_completion(&isert_conn->conn_wait); + isert_put_conn(isert_conn); } static void isert_free_conn(struct iscsi_conn *conn) @@ -2845,6 +2857,7 @@ destroy_rx_wq: static void __exit isert_exit(void) { + flush_scheduled_work(); destroy_workqueue(isert_comp_wq); destroy_workqueue(isert_rx_wq); iscsit_unregister_transport(&iser_target_transport); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index f6ae7f5dd408..cbecaabe90b9 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -93,7 +93,6 @@ struct isert_device; struct isert_conn { enum iser_conn_state state; - bool logout_posted; int post_recv_buf_count; atomic_t post_send_buf_count; u32 responder_resources; @@ -128,6 +127,7 @@ struct isert_conn { #define ISERT_COMP_BATCH_COUNT 8 int conn_comp_batch; struct llist_head conn_comp_llist; + bool disconnect; }; #define ISERT_MAX_CQ 64 @@ -158,7 +158,7 @@ struct isert_device { }; struct isert_np { - wait_queue_head_t np_accept_wq; + struct semaphore np_sem; struct rdma_cm_id *np_cm_id; struct mutex np_accept_mutex; struct list_head np_accept_list; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 529b6bcdca7a..ca0bc6c67abe 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -120,6 +120,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr); static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event); static struct scsi_transport_template *ib_srp_transport_template; +static struct workqueue_struct *srp_remove_wq; static struct ib_client srp_client = { .name = "srp", @@ -539,7 +540,7 @@ static bool srp_queue_remove_work(struct srp_target_port *target) spin_unlock_irq(&target->lock); if (changed) - queue_work(system_long_wq, &target->remove_work); + queue_work(srp_remove_wq, &target->remove_work); return changed; } @@ -1576,6 +1577,12 @@ err_unmap: err_iu: srp_put_tx_iu(target, iu, SRP_IU_CMD); + /* + * Avoid that the loops that iterate over the request ring can + * encounter a dangling SCSI command pointer. + */ + req->scmnd = NULL; + spin_lock_irqsave(&target->lock, flags); list_add(&req->list, &target->free_reqs); @@ -2880,9 +2887,10 @@ static void srp_remove_one(struct ib_device *device) spin_unlock(&host->target_lock); /* - * Wait for target port removal tasks. + * Wait for tl_err and target port removal tasks. */ flush_workqueue(system_long_wq); + flush_workqueue(srp_remove_wq); kfree(host); } @@ -2934,16 +2942,22 @@ static int __init srp_init_module(void) indirect_sg_entries = cmd_sg_entries; } + srp_remove_wq = create_workqueue("srp_remove"); + if (IS_ERR(srp_remove_wq)) { + ret = PTR_ERR(srp_remove_wq); + goto out; + } + + ret = -ENOMEM; ib_srp_transport_template = srp_attach_transport(&ib_srp_transport_functions); if (!ib_srp_transport_template) - return -ENOMEM; + goto destroy_wq; ret = class_register(&srp_class); if (ret) { pr_err("couldn't register class infiniband_srp\n"); - srp_release_transport(ib_srp_transport_template); - return ret; + goto release_tr; } ib_sa_register_client(&srp_sa_client); @@ -2951,13 +2965,22 @@ static int __init srp_init_module(void) ret = ib_register_client(&srp_client); if (ret) { pr_err("couldn't register IB client\n"); - srp_release_transport(ib_srp_transport_template); - ib_sa_unregister_client(&srp_sa_client); - class_unregister(&srp_class); - return ret; + goto unreg_sa; } - return 0; +out: + return ret; + +unreg_sa: + ib_sa_unregister_client(&srp_sa_client); + class_unregister(&srp_class); + +release_tr: + srp_release_transport(ib_srp_transport_template); + +destroy_wq: + destroy_workqueue(srp_remove_wq); + goto out; } static void __exit srp_cleanup_module(void) @@ -2966,6 +2989,7 @@ static void __exit srp_cleanup_module(void) ib_sa_unregister_client(&srp_sa_client); class_unregister(&srp_class); srp_release_transport(ib_srp_transport_template); + destroy_workqueue(srp_remove_wq); } module_init(srp_init_module); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 0e537d8d0e47..d1078ce73095 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1078,6 +1078,7 @@ static void srpt_unmap_sg_to_ib_sge(struct srpt_rdma_ch *ch, static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, struct srpt_send_ioctx *ioctx) { + struct ib_device *dev = ch->sport->sdev->device; struct se_cmd *cmd; struct scatterlist *sg, *sg_orig; int sg_cnt; @@ -1124,7 +1125,7 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, db = ioctx->rbufs; tsize = cmd->data_length; - dma_len = sg_dma_len(&sg[0]); + dma_len = ib_sg_dma_len(dev, &sg[0]); riu = ioctx->rdma_ius; /* @@ -1155,7 +1156,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, ++j; if (j < count) { sg = sg_next(sg); - dma_len = sg_dma_len(sg); + dma_len = ib_sg_dma_len( + dev, sg); } } } else { @@ -1192,8 +1194,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, tsize = cmd->data_length; riu = ioctx->rdma_ius; sg = sg_orig; - dma_len = sg_dma_len(&sg[0]); - dma_addr = sg_dma_address(&sg[0]); + dma_len = ib_sg_dma_len(dev, &sg[0]); + dma_addr = ib_sg_dma_address(dev, &sg[0]); /* this second loop is really mapped sg_addres to rdma_iu->ib_sge */ for (i = 0, j = 0; @@ -1216,8 +1218,10 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, ++j; if (j < count) { sg = sg_next(sg); - dma_len = sg_dma_len(sg); - dma_addr = sg_dma_address(sg); + dma_len = ib_sg_dma_len( + dev, sg); + dma_addr = ib_sg_dma_address( + dev, sg); } } } else { diff --git a/drivers/input/input.c b/drivers/input/input.c index 1c4c0db05550..29ca0bb4f561 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -257,9 +257,10 @@ static int input_handle_abs_event(struct input_dev *dev, } static int input_get_disposition(struct input_dev *dev, - unsigned int type, unsigned int code, int value) + unsigned int type, unsigned int code, int *pval) { int disposition = INPUT_IGNORE_EVENT; + int value = *pval; switch (type) { @@ -357,6 +358,7 @@ static int input_get_disposition(struct input_dev *dev, break; } + *pval = value; return disposition; } @@ -365,7 +367,7 @@ static void input_handle_event(struct input_dev *dev, { int disposition; - disposition = input_get_disposition(dev, type, code, value); + disposition = input_get_disposition(dev, type, code, &value); if ((disposition & INPUT_PASS_TO_DEVICE) && dev->event) dev->event(dev, type, code, value); diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 2626773ff29b..6f5d79569136 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -243,6 +243,12 @@ static void (*atkbd_platform_fixup)(struct atkbd *, const void *data); static void *atkbd_platform_fixup_data; static unsigned int (*atkbd_platform_scancode_fixup)(struct atkbd *, unsigned int); +/* + * Certain keyboards to not like ATKBD_CMD_RESET_DIS and stop responding + * to many commands until full reset (ATKBD_CMD_RESET_BAT) is performed. + */ +static bool atkbd_skip_deactivate; + static ssize_t atkbd_attr_show_helper(struct device *dev, char *buf, ssize_t (*handler)(struct atkbd *, char *)); static ssize_t atkbd_attr_set_helper(struct device *dev, const char *buf, size_t count, @@ -768,7 +774,8 @@ static int atkbd_probe(struct atkbd *atkbd) * Make sure nothing is coming from the keyboard and disturbs our * internal state. */ - atkbd_deactivate(atkbd); + if (!atkbd_skip_deactivate) + atkbd_deactivate(atkbd); return 0; } @@ -1638,6 +1645,12 @@ static int __init atkbd_setup_scancode_fixup(const struct dmi_system_id *id) return 1; } +static int __init atkbd_deactivate_fixup(const struct dmi_system_id *id) +{ + atkbd_skip_deactivate = true; + return 1; +} + static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = { { .matches = { @@ -1775,6 +1788,12 @@ static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = { .callback = atkbd_setup_scancode_fixup, .driver_data = atkbd_oqo_01plus_scancode_fixup, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + }, + .callback = atkbd_deactivate_fixup, + }, { } }; diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index ef1cf52f8bb9..0b75b5764f31 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -11,6 +11,7 @@ */ #include <linux/delay.h> +#include <linux/dmi.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/input.h> @@ -472,8 +473,15 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse, input_report_key(dev, BTN_TOOL_FINGER, fingers == 1); input_report_key(dev, BTN_TOOL_DOUBLETAP, fingers == 2); input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3); - input_report_key(dev, BTN_LEFT, packet[0] & 0x01); - input_report_key(dev, BTN_RIGHT, packet[0] & 0x02); + + /* For clickpads map both buttons to BTN_LEFT */ + if (etd->fw_version & 0x001000) { + input_report_key(dev, BTN_LEFT, packet[0] & 0x03); + } else { + input_report_key(dev, BTN_LEFT, packet[0] & 0x01); + input_report_key(dev, BTN_RIGHT, packet[0] & 0x02); + } + input_report_abs(dev, ABS_PRESSURE, pres); input_report_abs(dev, ABS_TOOL_WIDTH, width); @@ -483,10 +491,17 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse, static void elantech_input_sync_v4(struct psmouse *psmouse) { struct input_dev *dev = psmouse->dev; + struct elantech_data *etd = psmouse->private; unsigned char *packet = psmouse->packet; - input_report_key(dev, BTN_LEFT, packet[0] & 0x01); - input_report_key(dev, BTN_RIGHT, packet[0] & 0x02); + /* For clickpads map both buttons to BTN_LEFT */ + if (etd->fw_version & 0x001000) { + input_report_key(dev, BTN_LEFT, packet[0] & 0x03); + } else { + input_report_key(dev, BTN_LEFT, packet[0] & 0x01); + input_report_key(dev, BTN_RIGHT, packet[0] & 0x02); + } + input_mt_report_pointer_emulation(dev, true); input_sync(dev); } @@ -831,7 +846,11 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse) break; case 3: - etd->reg_10 = 0x0b; + if (etd->set_hw_resolution) + etd->reg_10 = 0x0b; + else + etd->reg_10 = 0x01; + if (elantech_write_reg(psmouse, 0x10, etd->reg_10)) rc = -1; @@ -1234,6 +1253,13 @@ static bool elantech_is_signature_valid(const unsigned char *param) if (param[1] == 0) return true; + /* + * Some models have a revision higher then 20. Meaning param[2] may + * be 10 or 20, skip the rates check for these. + */ + if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40) + return true; + for (i = 0; i < ARRAY_SIZE(rates); i++) if (param[2] == rates[i]) return false; @@ -1331,6 +1357,23 @@ static int elantech_reconnect(struct psmouse *psmouse) } /* + * Some hw_version 3 models go into error state when we try to set + * bit 3 and/or bit 1 of r10. + */ +static const struct dmi_system_id no_hw_res_dmi_table[] = { +#if defined(CONFIG_DMI) && defined(CONFIG_X86) + { + /* Gigabyte U2442 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "U2442"), + }, + }, +#endif + { } +}; + +/* * determine hardware version and set some properties according to it. */ static int elantech_set_properties(struct elantech_data *etd) @@ -1389,6 +1432,9 @@ static int elantech_set_properties(struct elantech_data *etd) */ etd->crc_enabled = ((etd->fw_version & 0x4000) == 0x4000); + /* Enable real hardware resolution on hw_version 3 ? */ + etd->set_hw_resolution = !dmi_check_system(no_hw_res_dmi_table); + return 0; } diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h index 036a04abaef7..9e0e2a1f340d 100644 --- a/drivers/input/mouse/elantech.h +++ b/drivers/input/mouse/elantech.h @@ -130,6 +130,7 @@ struct elantech_data { bool jumpy_cursor; bool reports_pressure; bool crc_enabled; + bool set_hw_resolution; unsigned char hw_version; unsigned int fw_version; unsigned int single_finger_reports; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index d8d49d10f9bb..a50a2a7a43f7 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -117,6 +117,82 @@ void synaptics_reset(struct psmouse *psmouse) } #ifdef CONFIG_MOUSE_PS2_SYNAPTICS +struct min_max_quirk { + const char * const *pnp_ids; + int x_min, x_max, y_min, y_max; +}; + +static const struct min_max_quirk min_max_pnpid_table[] = { + { + (const char * const []){"LEN0033", NULL}, + 1024, 5052, 2258, 4832 + }, + { + (const char * const []){"LEN0035", "LEN0042", NULL}, + 1232, 5710, 1156, 4696 + }, + { + (const char * const []){"LEN0034", "LEN0036", "LEN2002", + "LEN2004", NULL}, + 1024, 5112, 2024, 4832 + }, + { + (const char * const []){"LEN2001", NULL}, + 1024, 5022, 2508, 4832 + }, + { } +}; + +/* This list has been kindly provided by Synaptics. */ +static const char * const topbuttonpad_pnp_ids[] = { + "LEN0017", + "LEN0018", + "LEN0019", + "LEN0023", + "LEN002A", + "LEN002B", + "LEN002C", + "LEN002D", + "LEN002E", + "LEN0033", /* Helix */ + "LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */ + "LEN0035", /* X240 */ + "LEN0036", /* T440 */ + "LEN0037", + "LEN0038", + "LEN0041", + "LEN0042", /* Yoga */ + "LEN0045", + "LEN0046", + "LEN0047", + "LEN0048", + "LEN0049", + "LEN2000", + "LEN2001", /* Edge E431 */ + "LEN2002", /* Edge E531 */ + "LEN2003", + "LEN2004", /* L440 */ + "LEN2005", + "LEN2006", + "LEN2007", + "LEN2008", + "LEN2009", + "LEN200A", + "LEN200B", + NULL +}; + +static bool matches_pnp_id(struct psmouse *psmouse, const char * const ids[]) +{ + int i; + + if (!strncmp(psmouse->ps2dev.serio->firmware_id, "PNP:", 4)) + for (i = 0; ids[i]; i++) + if (strstr(psmouse->ps2dev.serio->firmware_id, ids[i])) + return true; + + return false; +} /***************************************************************************** * Synaptics communications functions @@ -266,20 +342,11 @@ static int synaptics_identify(struct psmouse *psmouse) * Resolution is left zero if touchpad does not support the query */ -static const int *quirk_min_max; - static int synaptics_resolution(struct psmouse *psmouse) { struct synaptics_data *priv = psmouse->private; unsigned char resp[3]; - - if (quirk_min_max) { - priv->x_min = quirk_min_max[0]; - priv->x_max = quirk_min_max[1]; - priv->y_min = quirk_min_max[2]; - priv->y_max = quirk_min_max[3]; - return 0; - } + int i; if (SYN_ID_MAJOR(priv->identity) < 4) return 0; @@ -291,6 +358,16 @@ static int synaptics_resolution(struct psmouse *psmouse) } } + for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) { + if (matches_pnp_id(psmouse, min_max_pnpid_table[i].pnp_ids)) { + priv->x_min = min_max_pnpid_table[i].x_min; + priv->x_max = min_max_pnpid_table[i].x_max; + priv->y_min = min_max_pnpid_table[i].y_min; + priv->y_max = min_max_pnpid_table[i].y_max; + return 0; + } + } + if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 5 && SYN_CAP_MAX_DIMENSIONS(priv->ext_cap_0c)) { if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MAX_COORDS, resp)) { @@ -549,10 +626,61 @@ static int synaptics_parse_hw_state(const unsigned char buf[], ((buf[0] & 0x04) >> 1) | ((buf[3] & 0x04) >> 2)); + if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) || + SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) && + hw->w == 2) { + synaptics_parse_agm(buf, priv, hw); + return 1; + } + + hw->x = (((buf[3] & 0x10) << 8) | + ((buf[1] & 0x0f) << 8) | + buf[4]); + hw->y = (((buf[3] & 0x20) << 7) | + ((buf[1] & 0xf0) << 4) | + buf[5]); + hw->z = buf[2]; + hw->left = (buf[0] & 0x01) ? 1 : 0; hw->right = (buf[0] & 0x02) ? 1 : 0; - if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { + if (SYN_CAP_FORCEPAD(priv->ext_cap_0c)) { + /* + * ForcePads, like Clickpads, use middle button + * bits to report primary button clicks. + * Unfortunately they report primary button not + * only when user presses on the pad above certain + * threshold, but also when there are more than one + * finger on the touchpad, which interferes with + * out multi-finger gestures. + */ + if (hw->z == 0) { + /* No contacts */ + priv->press = priv->report_press = false; + } else if (hw->w >= 4 && ((buf[0] ^ buf[3]) & 0x01)) { + /* + * Single-finger touch with pressure above + * the threshold. If pressure stays long + * enough, we'll start reporting primary + * button. We rely on the device continuing + * sending data even if finger does not + * move. + */ + if (!priv->press) { + priv->press_start = jiffies; + priv->press = true; + } else if (time_after(jiffies, + priv->press_start + + msecs_to_jiffies(50))) { + priv->report_press = true; + } + } else { + priv->press = false; + } + + hw->left = priv->report_press; + + } else if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { /* * Clickpad's button is transmitted as middle button, * however, since it is primary button, we will report @@ -571,21 +699,6 @@ static int synaptics_parse_hw_state(const unsigned char buf[], hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0; } - if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) || - SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) && - hw->w == 2) { - synaptics_parse_agm(buf, priv, hw); - return 1; - } - - hw->x = (((buf[3] & 0x10) << 8) | - ((buf[1] & 0x0f) << 8) | - buf[4]); - hw->y = (((buf[3] & 0x20) << 7) | - ((buf[1] & 0xf0) << 4) | - buf[5]); - hw->z = buf[2]; - if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) && ((buf[0] ^ buf[3]) & 0x02)) { switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) { @@ -1255,8 +1368,10 @@ static void set_abs_position_params(struct input_dev *dev, input_abs_set_res(dev, y_code, priv->y_res); } -static void set_input_params(struct input_dev *dev, struct synaptics_data *priv) +static void set_input_params(struct psmouse *psmouse, + struct synaptics_data *priv) { + struct input_dev *dev = psmouse->dev; int i; /* Things that apply to both modes */ @@ -1325,6 +1440,8 @@ static void set_input_params(struct input_dev *dev, struct synaptics_data *priv) if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { __set_bit(INPUT_PROP_BUTTONPAD, dev->propbit); + if (matches_pnp_id(psmouse, topbuttonpad_pnp_ids)) + __set_bit(INPUT_PROP_TOPBUTTONPAD, dev->propbit); /* Clickpads report only left button */ __clear_bit(BTN_RIGHT, dev->keybit); __clear_bit(BTN_MIDDLE, dev->keybit); @@ -1496,54 +1613,10 @@ static const struct dmi_system_id olpc_dmi_table[] __initconst = { { } }; -static const struct dmi_system_id min_max_dmi_table[] __initconst = { -#if defined(CONFIG_DMI) - { - /* Lenovo ThinkPad Helix */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"), - }, - .driver_data = (int []){1024, 5052, 2258, 4832}, - }, - { - /* Lenovo ThinkPad X240 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"), - }, - .driver_data = (int []){1232, 5710, 1156, 4696}, - }, - { - /* Lenovo ThinkPad T440s */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"), - }, - .driver_data = (int []){1024, 5112, 2024, 4832}, - }, - { - /* Lenovo ThinkPad T540p */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"), - }, - .driver_data = (int []){1024, 5056, 2058, 4832}, - }, -#endif - { } -}; - void __init synaptics_module_init(void) { - const struct dmi_system_id *min_max_dmi; - impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table); broken_olpc_ec = dmi_check_system(olpc_dmi_table); - - min_max_dmi = dmi_first_match(min_max_dmi_table); - if (min_max_dmi) - quirk_min_max = min_max_dmi->driver_data; } static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode) @@ -1593,7 +1666,7 @@ static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode) priv->capabilities, priv->ext_cap, priv->ext_cap_0c, priv->board_id, priv->firmware_id); - set_input_params(psmouse->dev, priv); + set_input_params(psmouse, priv); /* * Encode touchpad model so that it can be used to set diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h index e594af0b264b..fb2e076738ae 100644 --- a/drivers/input/mouse/synaptics.h +++ b/drivers/input/mouse/synaptics.h @@ -78,6 +78,11 @@ * 2 0x08 image sensor image sensor tracks 5 fingers, but only * reports 2. * 2 0x20 report min query 0x0f gives min coord reported + * 2 0x80 forcepad forcepad is a variant of clickpad that + * does not have physical buttons but rather + * uses pressure above certain threshold to + * report primary clicks. Forcepads also have + * clickpad bit set. */ #define SYN_CAP_CLICKPAD(ex0c) ((ex0c) & 0x100000) /* 1-button ClickPad */ #define SYN_CAP_CLICKPAD2BTN(ex0c) ((ex0c) & 0x000100) /* 2-button ClickPad */ @@ -86,6 +91,7 @@ #define SYN_CAP_ADV_GESTURE(ex0c) ((ex0c) & 0x080000) #define SYN_CAP_REDUCED_FILTERING(ex0c) ((ex0c) & 0x000400) #define SYN_CAP_IMAGE_SENSOR(ex0c) ((ex0c) & 0x000800) +#define SYN_CAP_FORCEPAD(ex0c) ((ex0c) & 0x008000) /* synaptics modes query bits */ #define SYN_MODE_ABSOLUTE(m) ((m) & (1 << 7)) @@ -177,6 +183,11 @@ struct synaptics_data { */ struct synaptics_hw_state agm; bool agm_pending; /* new AGM packet received */ + + /* ForcePad handling */ + unsigned long press_start; + bool press; + bool report_press; }; void synaptics_module_init(void); diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 0ec9abbe31fe..8fca488fdc15 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -101,6 +101,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { }, { .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"), + }, + }, + { + .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"), DMI_MATCH(DMI_PRODUCT_VERSION, "8500"), @@ -458,6 +464,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), }, }, + { + /* Avatar AVIU-145A6 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel"), + DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"), + }, + }, { } }; @@ -601,6 +614,30 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), }, }, + { + /* Fujitsu A544 laptop */ + /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"), + }, + }, + { + /* Fujitsu AH544 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"), + }, + }, + { + /* Fujitsu U574 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), + }, + }, { } }; @@ -702,6 +739,17 @@ static int i8042_pnp_aux_irq; static char i8042_pnp_kbd_name[32]; static char i8042_pnp_aux_name[32]; +static void i8042_pnp_id_to_string(struct pnp_id *id, char *dst, int dst_size) +{ + strlcpy(dst, "PNP:", dst_size); + + while (id) { + strlcat(dst, " ", dst_size); + strlcat(dst, id->id, dst_size); + id = id->next; + } +} + static int i8042_pnp_kbd_probe(struct pnp_dev *dev, const struct pnp_device_id *did) { if (pnp_port_valid(dev, 0) && pnp_port_len(dev, 0) == 1) @@ -718,6 +766,8 @@ static int i8042_pnp_kbd_probe(struct pnp_dev *dev, const struct pnp_device_id * strlcat(i8042_pnp_kbd_name, ":", sizeof(i8042_pnp_kbd_name)); strlcat(i8042_pnp_kbd_name, pnp_dev_name(dev), sizeof(i8042_pnp_kbd_name)); } + i8042_pnp_id_to_string(dev->id, i8042_kbd_firmware_id, + sizeof(i8042_kbd_firmware_id)); /* Keyboard ports are always supposed to be wakeup-enabled */ device_set_wakeup_enable(&dev->dev, true); @@ -742,6 +792,8 @@ static int i8042_pnp_aux_probe(struct pnp_dev *dev, const struct pnp_device_id * strlcat(i8042_pnp_aux_name, ":", sizeof(i8042_pnp_aux_name)); strlcat(i8042_pnp_aux_name, pnp_dev_name(dev), sizeof(i8042_pnp_aux_name)); } + i8042_pnp_id_to_string(dev->id, i8042_aux_firmware_id, + sizeof(i8042_aux_firmware_id)); i8042_pnp_aux_devices++; return 0; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 020053fa5aaa..3807c3e971cc 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -87,6 +87,8 @@ MODULE_PARM_DESC(debug, "Turn i8042 debugging mode on and off"); #endif static bool i8042_bypass_aux_irq_test; +static char i8042_kbd_firmware_id[128]; +static char i8042_aux_firmware_id[128]; #include "i8042.h" @@ -1218,6 +1220,8 @@ static int __init i8042_create_kbd_port(void) serio->dev.parent = &i8042_platform_device->dev; strlcpy(serio->name, "i8042 KBD port", sizeof(serio->name)); strlcpy(serio->phys, I8042_KBD_PHYS_DESC, sizeof(serio->phys)); + strlcpy(serio->firmware_id, i8042_kbd_firmware_id, + sizeof(serio->firmware_id)); port->serio = serio; port->irq = I8042_KBD_IRQ; @@ -1244,6 +1248,8 @@ static int __init i8042_create_aux_port(int idx) if (idx < 0) { strlcpy(serio->name, "i8042 AUX port", sizeof(serio->name)); strlcpy(serio->phys, I8042_AUX_PHYS_DESC, sizeof(serio->phys)); + strlcpy(serio->firmware_id, i8042_aux_firmware_id, + sizeof(serio->firmware_id)); serio->close = i8042_port_close; } else { snprintf(serio->name, sizeof(serio->name), "i8042 AUX%d port", idx); diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c index 8f4c4ab04bc2..b29134de983b 100644 --- a/drivers/input/serio/serio.c +++ b/drivers/input/serio/serio.c @@ -451,6 +451,13 @@ static ssize_t serio_set_bind_mode(struct device *dev, struct device_attribute * return retval; } +static ssize_t firmware_id_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct serio *serio = to_serio_port(dev); + + return sprintf(buf, "%s\n", serio->firmware_id); +} + static DEVICE_ATTR_RO(type); static DEVICE_ATTR_RO(proto); static DEVICE_ATTR_RO(id); @@ -473,12 +480,14 @@ static DEVICE_ATTR_RO(modalias); static DEVICE_ATTR_WO(drvctl); static DEVICE_ATTR(description, S_IRUGO, serio_show_description, NULL); static DEVICE_ATTR(bind_mode, S_IWUSR | S_IRUGO, serio_show_bind_mode, serio_set_bind_mode); +static DEVICE_ATTR_RO(firmware_id); static struct attribute *serio_device_attrs[] = { &dev_attr_modalias.attr, &dev_attr_description.attr, &dev_attr_drvctl.attr, &dev_attr_bind_mode.attr, + &dev_attr_firmware_id.attr, NULL }; @@ -921,9 +930,14 @@ static int serio_uevent(struct device *dev, struct kobj_uevent_env *env) SERIO_ADD_UEVENT_VAR("SERIO_PROTO=%02x", serio->id.proto); SERIO_ADD_UEVENT_VAR("SERIO_ID=%02x", serio->id.id); SERIO_ADD_UEVENT_VAR("SERIO_EXTRA=%02x", serio->id.extra); + SERIO_ADD_UEVENT_VAR("MODALIAS=serio:ty%02Xpr%02Xid%02Xex%02X", serio->id.type, serio->id.proto, serio->id.id, serio->id.extra); + if (serio->firmware_id[0]) + SERIO_ADD_UEVENT_VAR("SERIO_FIRMWARE_ID=%s", + serio->firmware_id); + return 0; } #undef SERIO_ADD_UEVENT_VAR diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index 0cb7ef59071b..69175b825346 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/serio.h> #include <linux/tty.h> +#include <linux/compat.h> MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); MODULE_DESCRIPTION("Input device TTY line discipline"); @@ -198,28 +199,55 @@ static ssize_t serport_ldisc_read(struct tty_struct * tty, struct file * file, u return 0; } +static void serport_set_type(struct tty_struct *tty, unsigned long type) +{ + struct serport *serport = tty->disc_data; + + serport->id.proto = type & 0x000000ff; + serport->id.id = (type & 0x0000ff00) >> 8; + serport->id.extra = (type & 0x00ff0000) >> 16; +} + /* * serport_ldisc_ioctl() allows to set the port protocol, and device ID */ -static int serport_ldisc_ioctl(struct tty_struct * tty, struct file * file, unsigned int cmd, unsigned long arg) +static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg) { - struct serport *serport = (struct serport*) tty->disc_data; - unsigned long type; - if (cmd == SPIOCSTYPE) { + unsigned long type; + if (get_user(type, (unsigned long __user *) arg)) return -EFAULT; - serport->id.proto = type & 0x000000ff; - serport->id.id = (type & 0x0000ff00) >> 8; - serport->id.extra = (type & 0x00ff0000) >> 16; + serport_set_type(tty, type); + return 0; + } + + return -EINVAL; +} + +#ifdef CONFIG_COMPAT +#define COMPAT_SPIOCSTYPE _IOW('q', 0x01, compat_ulong_t) +static long serport_ldisc_compat_ioctl(struct tty_struct *tty, + struct file *file, + unsigned int cmd, unsigned long arg) +{ + if (cmd == COMPAT_SPIOCSTYPE) { + void __user *uarg = compat_ptr(arg); + compat_ulong_t compat_type; + + if (get_user(compat_type, (compat_ulong_t __user *)uarg)) + return -EFAULT; + serport_set_type(tty, compat_type); return 0; } return -EINVAL; } +#endif static void serport_ldisc_write_wakeup(struct tty_struct * tty) { @@ -243,6 +271,9 @@ static struct tty_ldisc_ops serport_ldisc = { .close = serport_ldisc_close, .read = serport_ldisc_read, .ioctl = serport_ldisc_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = serport_ldisc_compat_ioctl, +#endif .receive_buf = serport_ldisc_receive, .write_wakeup = serport_ldisc_write_wakeup }; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index faf0da4bb3a2..9cbef59d404a 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3227,14 +3227,16 @@ free_domains: static void cleanup_domain(struct protection_domain *domain) { - struct iommu_dev_data *dev_data, *next; + struct iommu_dev_data *entry; unsigned long flags; write_lock_irqsave(&amd_iommu_devtable_lock, flags); - list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) { - __detach_device(dev_data); - atomic_set(&dev_data->bind, 0); + while (!list_empty(&domain->dev_list)) { + entry = list_first_entry(&domain->dev_list, + struct iommu_dev_data, list); + __detach_device(entry); + atomic_set(&entry->bind, 0); } write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); @@ -3999,7 +4001,7 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic) iommu_flush_dte(iommu, devid); if (devid != alias) { irq_lookup_table[alias] = table; - set_dte_irq_entry(devid, table); + set_dte_irq_entry(alias, table); iommu_flush_dte(iommu, alias); } diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 1d9ab39af29f..2ecac467f78f 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -794,8 +794,11 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain) reg |= TTBCR_EAE | (TTBCR_SH_IS << TTBCR_SH0_SHIFT) | (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) | - (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT) | - (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT); + (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT); + + if (!stage1) + reg |= (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT); + writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR); /* MAIR0 (stage-1 only) */ diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a22c86c867fa..40f6b47c28f6 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4075,7 +4075,7 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { struct dmar_domain *dmar_domain = domain->priv; - int order; + int order, iommu_id; order = dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT, (iova + size - 1) >> VTD_PAGE_SHIFT); @@ -4083,6 +4083,22 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, if (dmar_domain->max_addr == iova + size) dmar_domain->max_addr = iova; + for_each_set_bit(iommu_id, dmar_domain->iommu_bmp, g_num_of_iommus) { + struct intel_iommu *iommu = g_iommus[iommu_id]; + int num, ndomains; + + /* + * find bit position of dmar_domain + */ + ndomains = cap_ndoms(iommu->cap); + for_each_set_bit(num, iommu->domain_ids, ndomains) { + if (iommu->domains[num] == dmar_domain) + iommu_flush_iotlb_psi(iommu, num, + iova >> VTD_PAGE_SHIFT, + 1 << order, 0); + } + } + return PAGE_SIZE << order; } diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 540956465ed2..939eb0d8fbf1 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -130,8 +130,7 @@ static int armada_370_xp_setup_msi_irq(struct msi_chip *chip, struct msi_desc *desc) { struct msi_msg msg; - irq_hw_number_t hwirq; - int virq; + int virq, hwirq; hwirq = armada_370_xp_alloc_msi(); if (hwirq < 0) @@ -157,8 +156,19 @@ static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip, unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); + unsigned long hwirq = d->hwirq; + irq_dispose_mapping(irq); - armada_370_xp_free_msi(d->hwirq); + armada_370_xp_free_msi(hwirq); +} + +static int armada_370_xp_check_msi_device(struct msi_chip *chip, struct pci_dev *dev, + int nvec, int type) +{ + /* We support MSI, but not MSI-X */ + if (type == PCI_CAP_ID_MSI) + return 0; + return -EINVAL; } static struct irq_chip armada_370_xp_msi_irq_chip = { @@ -199,6 +209,7 @@ static int armada_370_xp_msi_init(struct device_node *node, msi_chip->setup_irq = armada_370_xp_setup_msi_irq; msi_chip->teardown_irq = armada_370_xp_teardown_msi_irq; + msi_chip->check_device = armada_370_xp_check_msi_device; msi_chip->of_node = node; armada_370_xp_msi_domain = diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 341c6016812d..12698ee9e06b 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -42,6 +42,7 @@ #include <linux/irqchip/chained_irq.h> #include <linux/irqchip/arm-gic.h> +#include <asm/cputype.h> #include <asm/irq.h> #include <asm/exception.h> #include <asm/smp_plat.h> @@ -246,10 +247,14 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3); - unsigned int shift = (gic_irq(d) % 4) * 8; - unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask); + unsigned int cpu, shift = (gic_irq(d) % 4) * 8; u32 val, mask, bit; + if (!force) + cpu = cpumask_any_and(mask_val, cpu_online_mask); + else + cpu = cpumask_first(mask_val); + if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids) return -EINVAL; @@ -899,7 +904,9 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start, } for_each_possible_cpu(cpu) { - unsigned long offset = percpu_offset * cpu_logical_map(cpu); + u32 mpidr = cpu_logical_map(cpu); + u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); + unsigned long offset = percpu_offset * core_id; *per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset; *per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset; } @@ -1004,8 +1011,10 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent) gic_cnt++; return 0; } +IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init); IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init); IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init); +IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init); IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init); IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init); diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c index 8527743b5cef..391b9cea73ed 100644 --- a/drivers/irqchip/spear-shirq.c +++ b/drivers/irqchip/spear-shirq.c @@ -125,7 +125,7 @@ static struct spear_shirq spear320_shirq_ras2 = { }; static struct spear_shirq spear320_shirq_ras3 = { - .irq_nr = 3, + .irq_nr = 7, .irq_bit_off = 0, .invalid_irq = 1, .regs = { diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c index 02125e6a9109..5a4da94aefb0 100644 --- a/drivers/isdn/isdnloop/isdnloop.c +++ b/drivers/isdn/isdnloop/isdnloop.c @@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] = static void isdnloop_fake_err(isdnloop_card *card) { - char buf[60]; + char buf[64]; - sprintf(buf, "E%s", card->omsg); + snprintf(buf, sizeof(buf), "E%s", card->omsg); isdnloop_fake(card, buf, -1); isdnloop_fake(card, "NAK", -1); } @@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card *card) case 7: /* 0x;EAZ */ p += 3; + if (strlen(p) >= sizeof(card->eazlist[0])) + break; strcpy(card->eazlist[ch - 1], p); break; case 8: @@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp) return -EBUSY; if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef))) return -EFAULT; + + for (i = 0; i < 3; i++) { + if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i]))) + return -EINVAL; + } + spin_lock_irqsave(&card->isdnloop_lock, flags); switch (sdef.ptype) { case ISDN_PTYPE_EURO: @@ -1127,7 +1135,7 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card) { ulong a; int i; - char cbuf[60]; + char cbuf[80]; isdn_ctrl cmd; isdnloop_cdef cdef; @@ -1192,7 +1200,6 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card) break; if ((c->arg & 255) < ISDNLOOP_BCH) { char *p; - char dial[50]; char dcode[4]; a = c->arg; @@ -1204,10 +1211,10 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card) } else /* Normal Dial */ strcpy(dcode, "CAL"); - strcpy(dial, p); - sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1), - dcode, dial, c->parm.setup.si1, - c->parm.setup.si2, c->parm.setup.eazmsn); + snprintf(cbuf, sizeof(cbuf), + "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1), + dcode, p, c->parm.setup.si1, + c->parm.setup.si2, c->parm.setup.eazmsn); i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card); } break; diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c index 605047428b5a..a7b369fc3554 100644 --- a/drivers/leds/leds-pwm.c +++ b/drivers/leds/leds-pwm.c @@ -84,6 +84,15 @@ static inline size_t sizeof_pwm_leds_priv(int num_leds) (sizeof(struct led_pwm_data) * num_leds); } +static void led_pwm_cleanup(struct led_pwm_priv *priv) +{ + while (priv->num_leds--) { + led_classdev_unregister(&priv->leds[priv->num_leds].cdev); + if (priv->leds[priv->num_leds].can_sleep) + cancel_work_sync(&priv->leds[priv->num_leds].work); + } +} + static int led_pwm_create_of(struct platform_device *pdev, struct led_pwm_priv *priv) { @@ -131,8 +140,7 @@ static int led_pwm_create_of(struct platform_device *pdev, return 0; err: - while (priv->num_leds--) - led_classdev_unregister(&priv->leds[priv->num_leds].cdev); + led_pwm_cleanup(priv); return ret; } @@ -200,8 +208,8 @@ static int led_pwm_probe(struct platform_device *pdev) return 0; err: - while (i--) - led_classdev_unregister(&priv->leds[i].cdev); + priv->num_leds = i; + led_pwm_cleanup(priv); return ret; } @@ -209,13 +217,8 @@ err: static int led_pwm_remove(struct platform_device *pdev) { struct led_pwm_priv *priv = platform_get_drvdata(pdev); - int i; - for (i = 0; i < priv->num_leds; i++) { - led_classdev_unregister(&priv->leds[i].cdev); - if (priv->leds[i].can_sleep) - cancel_work_sync(&priv->leds[i].work); - } + led_pwm_cleanup(priv); return 0; } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 66c5d130c8c2..ca1621b49453 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -465,6 +465,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty) c->n_buffers[dirty]++; b->list_mode = dirty; list_move(&b->lru_list, &c->lru[dirty]); + b->last_accessed = jiffies; } /*---------------------------------------------------------------- @@ -1485,9 +1486,9 @@ static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { freed += __cleanup_old_buffer(b, gfp_mask, 0); if (!--nr_to_scan) - break; + return freed; + dm_bufio_cond_resched(); } - dm_bufio_cond_resched(); } return freed; } @@ -1541,7 +1542,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign BUG_ON(block_size < 1 << SECTOR_SHIFT || (block_size & (block_size - 1))); - c = kmalloc(sizeof(*c), GFP_KERNEL); + c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) { r = -ENOMEM; goto bad_client; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 9ef0752e8a08..a87d3fab0271 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -120,6 +120,12 @@ struct dm_cache_metadata { unsigned policy_version[CACHE_POLICY_VERSION_SIZE]; size_t policy_hint_size; struct dm_cache_statistics stats; + + /* + * Reading the space map root can fail, so we read it into this + * buffer before the superblock is locked and updated. + */ + __u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE]; }; /*------------------------------------------------------------------- @@ -260,11 +266,31 @@ static void __setup_mapping_info(struct dm_cache_metadata *cmd) } } +static int __save_sm_root(struct dm_cache_metadata *cmd) +{ + int r; + size_t metadata_len; + + r = dm_sm_root_size(cmd->metadata_sm, &metadata_len); + if (r < 0) + return r; + + return dm_sm_copy_root(cmd->metadata_sm, &cmd->metadata_space_map_root, + metadata_len); +} + +static void __copy_sm_root(struct dm_cache_metadata *cmd, + struct cache_disk_superblock *disk_super) +{ + memcpy(&disk_super->metadata_space_map_root, + &cmd->metadata_space_map_root, + sizeof(cmd->metadata_space_map_root)); +} + static int __write_initial_superblock(struct dm_cache_metadata *cmd) { int r; struct dm_block *sblock; - size_t metadata_len; struct cache_disk_superblock *disk_super; sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT; @@ -272,12 +298,16 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd) if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS) bdev_size = DM_CACHE_METADATA_MAX_SECTORS; - r = dm_sm_root_size(cmd->metadata_sm, &metadata_len); + r = dm_tm_pre_commit(cmd->tm); if (r < 0) return r; - r = dm_tm_pre_commit(cmd->tm); - if (r < 0) + /* + * dm_sm_copy_root() can fail. So we need to do it before we start + * updating the superblock. + */ + r = __save_sm_root(cmd); + if (r) return r; r = superblock_lock_zero(cmd, &sblock); @@ -293,10 +323,7 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd) memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version)); disk_super->policy_hint_size = 0; - r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root, - metadata_len); - if (r < 0) - goto bad_locked; + __copy_sm_root(cmd, disk_super); disk_super->mapping_root = cpu_to_le64(cmd->root); disk_super->hint_root = cpu_to_le64(cmd->hint_root); @@ -313,10 +340,6 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd) disk_super->write_misses = cpu_to_le32(0); return dm_tm_commit(cmd->tm, sblock); - -bad_locked: - dm_bm_unlock(sblock); - return r; } static int __format_metadata(struct dm_cache_metadata *cmd) @@ -402,6 +425,15 @@ static int __open_metadata(struct dm_cache_metadata *cmd) disk_super = dm_block_data(sblock); + /* Verify the data block size hasn't changed */ + if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) { + DMERR("changing the data block size (from %u to %llu) is not supported", + le32_to_cpu(disk_super->data_block_size), + (unsigned long long)cmd->data_block_size); + r = -EINVAL; + goto bad; + } + r = __check_incompat_features(disk_super, cmd); if (r < 0) goto bad; @@ -530,8 +562,9 @@ static int __begin_transaction_flags(struct dm_cache_metadata *cmd, disk_super = dm_block_data(sblock); update_flags(disk_super, mutator); read_superblock_fields(cmd, disk_super); + dm_bm_unlock(sblock); - return dm_bm_flush_and_unlock(cmd->bm, sblock); + return dm_bm_flush(cmd->bm); } static int __begin_transaction(struct dm_cache_metadata *cmd) @@ -559,7 +592,6 @@ static int __commit_transaction(struct dm_cache_metadata *cmd, flags_mutator mutator) { int r; - size_t metadata_len; struct cache_disk_superblock *disk_super; struct dm_block *sblock; @@ -577,8 +609,8 @@ static int __commit_transaction(struct dm_cache_metadata *cmd, if (r < 0) return r; - r = dm_sm_root_size(cmd->metadata_sm, &metadata_len); - if (r < 0) + r = __save_sm_root(cmd); + if (r) return r; r = superblock_lock(cmd, &sblock); @@ -605,13 +637,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd, disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses); disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits); disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses); - - r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root, - metadata_len); - if (r < 0) { - dm_bm_unlock(sblock); - return r; - } + __copy_sm_root(cmd, disk_super); return dm_tm_commit(cmd->tm, sblock); } @@ -1228,22 +1254,12 @@ static int begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *po return 0; } -int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy) +static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock, uint32_t hint) { + struct dm_cache_metadata *cmd = context; + __le32 value = cpu_to_le32(hint); int r; - down_write(&cmd->root_lock); - r = begin_hints(cmd, policy); - up_write(&cmd->root_lock); - - return r; -} - -static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock, - uint32_t hint) -{ - int r; - __le32 value = cpu_to_le32(hint); __dm_bless_for_disk(&value); r = dm_array_set_value(&cmd->hint_info, cmd->hint_root, @@ -1253,16 +1269,25 @@ static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock, return r; } -int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock, - uint32_t hint) +static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy) { int r; - if (!hints_array_initialized(cmd)) - return 0; + r = begin_hints(cmd, policy); + if (r) { + DMERR("begin_hints failed"); + return r; + } + + return policy_walk_mappings(policy, save_hint, cmd); +} + +int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy) +{ + int r; down_write(&cmd->root_lock); - r = save_hint(cmd, cblock, hint); + r = write_hints(cmd, policy); up_write(&cmd->root_lock); return r; diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h index cd906f14f98d..f0fb1dd26524 100644 --- a/drivers/md/dm-cache-metadata.h +++ b/drivers/md/dm-cache-metadata.h @@ -128,14 +128,7 @@ void dm_cache_dump(struct dm_cache_metadata *cmd); * rather than querying the policy for each cblock, we let it walk its data * structures and fill in the hints in whatever order it wishes. */ - -int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p); - -/* - * requests hints for every cblock and stores in the metadata device. - */ -int dm_cache_save_hint(struct dm_cache_metadata *cmd, - dm_cblock_t cblock, uint32_t hint); +int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p); /* * Query method. Are all the blocks in the cache clean? diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 074b9c8e4cf0..2331543005b2 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -231,7 +231,7 @@ struct cache { /* * cache_size entries, dirty if set */ - dm_cblock_t nr_dirty; + atomic_t nr_dirty; unsigned long *dirty_bitset; /* @@ -239,7 +239,7 @@ struct cache { */ dm_dblock_t discard_nr_blocks; unsigned long *discard_bitset; - uint32_t discard_block_size; /* a power of 2 times sectors per block */ + uint32_t discard_block_size; /* * Rather than reconstructing the table line for the status we just @@ -493,7 +493,7 @@ static bool is_dirty(struct cache *cache, dm_cblock_t b) static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock) { if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) { - cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1); + atomic_inc(&cache->nr_dirty); policy_set_dirty(cache->policy, oblock); } } @@ -502,8 +502,7 @@ static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cbl { if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) { policy_clear_dirty(cache->policy, oblock); - cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1); - if (!from_cblock(cache->nr_dirty)) + if (atomic_dec_return(&cache->nr_dirty) == 0) dm_table_event(cache->ti->table); } } @@ -891,8 +890,8 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg) struct cache *cache = mg->cache; if (mg->writeback) { - cell_defer(cache, mg->old_ocell, false); clear_dirty(cache, mg->old_oblock, mg->cblock); + cell_defer(cache, mg->old_ocell, false); cleanup_migration(mg); return; @@ -947,13 +946,13 @@ static void migration_success_post_commit(struct dm_cache_migration *mg) } } else { + clear_dirty(cache, mg->new_oblock, mg->cblock); if (mg->requeue_holder) cell_defer(cache, mg->new_ocell, true); else { bio_endio(mg->new_ocell->holder, 0); cell_defer(cache, mg->new_ocell, false); } - clear_dirty(cache, mg->new_oblock, mg->cblock); cleanup_migration(mg); } } @@ -2171,35 +2170,6 @@ static int create_cache_policy(struct cache *cache, struct cache_args *ca, return 0; } -/* - * We want the discard block size to be a power of two, at least the size - * of the cache block size, and have no more than 2^14 discard blocks - * across the origin. - */ -#define MAX_DISCARD_BLOCKS (1 << 14) - -static bool too_many_discard_blocks(sector_t discard_block_size, - sector_t origin_size) -{ - (void) sector_div(origin_size, discard_block_size); - - return origin_size > MAX_DISCARD_BLOCKS; -} - -static sector_t calculate_discard_block_size(sector_t cache_block_size, - sector_t origin_size) -{ - sector_t discard_block_size; - - discard_block_size = roundup_pow_of_two(cache_block_size); - - if (origin_size) - while (too_many_discard_blocks(discard_block_size, origin_size)) - discard_block_size *= 2; - - return discard_block_size; -} - #define DEFAULT_MIGRATION_THRESHOLD 2048 static int cache_create(struct cache_args *ca, struct cache **result) @@ -2224,6 +2194,8 @@ static int cache_create(struct cache_args *ca, struct cache **result) ti->num_discard_bios = 1; ti->discards_supported = true; ti->discard_zeroes_data_unsupported = true; + /* Discard bios must be split on a block boundary */ + ti->split_discard_bios = true; cache->features = ca->features; ti->per_bio_data_size = get_per_bio_data_size(cache); @@ -2313,7 +2285,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) atomic_set(&cache->quiescing_ack, 0); r = -ENOMEM; - cache->nr_dirty = 0; + atomic_set(&cache->nr_dirty, 0); cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size)); if (!cache->dirty_bitset) { *error = "could not allocate dirty bitset"; @@ -2321,9 +2293,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) } clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size)); - cache->discard_block_size = - calculate_discard_block_size(cache->sectors_per_block, - cache->origin_sectors); + cache->discard_block_size = cache->sectors_per_block; cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks); cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks)); if (!cache->discard_bitset) { @@ -2537,6 +2507,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio) } else { inc_hit_counter(cache, bio); + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) && !is_dirty(cache, lookup_result.cblock)) @@ -2631,30 +2602,6 @@ static int write_discard_bitset(struct cache *cache) return 0; } -static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock, - uint32_t hint) -{ - struct cache *cache = context; - return dm_cache_save_hint(cache->cmd, cblock, hint); -} - -static int write_hints(struct cache *cache) -{ - int r; - - r = dm_cache_begin_hints(cache->cmd, cache->policy); - if (r) { - DMERR("dm_cache_begin_hints failed"); - return r; - } - - r = policy_walk_mappings(cache->policy, save_hint, cache); - if (r) - DMERR("policy_walk_mappings failed"); - - return r; -} - /* * returns true on success */ @@ -2672,7 +2619,7 @@ static bool sync_metadata(struct cache *cache) save_stats(cache); - r3 = write_hints(cache); + r3 = dm_cache_write_hints(cache->cmd, cache->policy); if (r3) DMERR("could not write hints"); @@ -2880,7 +2827,7 @@ 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 %llu ", + DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ", (unsigned)(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT), (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata), (unsigned long long)nr_blocks_metadata, @@ -2893,7 +2840,7 @@ static void cache_status(struct dm_target *ti, status_type_t type, (unsigned) atomic_read(&cache->stats.write_miss), (unsigned) atomic_read(&cache->stats.demotion), (unsigned) atomic_read(&cache->stats.promotion), - (unsigned long long) from_cblock(cache->nr_dirty)); + (unsigned long) atomic_read(&cache->nr_dirty)); if (writethrough_mode(&cache->features)) DMEMIT("1 writethrough "); @@ -3120,7 +3067,7 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits) /* * FIXME: these limits may be incompatible with the cache device */ - limits->max_discard_sectors = cache->discard_block_size * 1024; + limits->max_discard_sectors = cache->discard_block_size; limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT; } @@ -3145,7 +3092,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type cache_target = { .name = "cache", - .version = {1, 3, 0}, + .version = {1, 4, 0}, .module = THIS_MODULE, .ctr = cache_ctr, .dtr = cache_dtr, diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 784695d22fde..9533f835ce07 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -19,7 +19,6 @@ #include <linux/crypto.h> #include <linux/workqueue.h> #include <linux/backing-dev.h> -#include <linux/percpu.h> #include <linux/atomic.h> #include <linux/scatterlist.h> #include <asm/page.h> @@ -43,6 +42,7 @@ struct convert_context { struct bvec_iter iter_out; sector_t cc_sector; atomic_t cc_pending; + struct ablkcipher_request *req; }; /* @@ -111,15 +111,7 @@ struct iv_tcw_private { enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID }; /* - * Duplicated per-CPU state for cipher. - */ -struct crypt_cpu { - struct ablkcipher_request *req; -}; - -/* - * The fields in here must be read only after initialization, - * changing state should be in crypt_cpu. + * The fields in here must be read only after initialization. */ struct crypt_config { struct dm_dev *dev; @@ -150,12 +142,6 @@ struct crypt_config { sector_t iv_offset; unsigned int iv_size; - /* - * Duplicated per cpu state. Access through - * per_cpu_ptr() only. - */ - struct crypt_cpu __percpu *cpu; - /* ESSIV: struct crypto_cipher *essiv_tfm */ void *iv_private; struct crypto_ablkcipher **tfms; @@ -192,11 +178,6 @@ static void clone_init(struct dm_crypt_io *, struct bio *); static void kcryptd_queue_crypt(struct dm_crypt_io *io); static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq); -static struct crypt_cpu *this_crypt_config(struct crypt_config *cc) -{ - return this_cpu_ptr(cc->cpu); -} - /* * Use this to access cipher attributes that are the same for each CPU. */ @@ -903,16 +884,15 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, static void crypt_alloc_req(struct crypt_config *cc, struct convert_context *ctx) { - struct crypt_cpu *this_cc = this_crypt_config(cc); unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1); - if (!this_cc->req) - this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO); + if (!ctx->req) + ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO); - ablkcipher_request_set_tfm(this_cc->req, cc->tfms[key_index]); - ablkcipher_request_set_callback(this_cc->req, + ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]); + ablkcipher_request_set_callback(ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - kcryptd_async_done, dmreq_of_req(cc, this_cc->req)); + kcryptd_async_done, dmreq_of_req(cc, ctx->req)); } /* @@ -921,7 +901,6 @@ static void crypt_alloc_req(struct crypt_config *cc, static int crypt_convert(struct crypt_config *cc, struct convert_context *ctx) { - struct crypt_cpu *this_cc = this_crypt_config(cc); int r; atomic_set(&ctx->cc_pending, 1); @@ -932,7 +911,7 @@ static int crypt_convert(struct crypt_config *cc, atomic_inc(&ctx->cc_pending); - r = crypt_convert_block(cc, ctx, this_cc->req); + r = crypt_convert_block(cc, ctx, ctx->req); switch (r) { /* async */ @@ -941,7 +920,7 @@ static int crypt_convert(struct crypt_config *cc, reinit_completion(&ctx->restart); /* fall through*/ case -EINPROGRESS: - this_cc->req = NULL; + ctx->req = NULL; ctx->cc_sector++; continue; @@ -1040,6 +1019,7 @@ static struct dm_crypt_io *crypt_io_alloc(struct crypt_config *cc, io->sector = sector; io->error = 0; io->base_io = NULL; + io->ctx.req = NULL; atomic_set(&io->io_pending, 0); return io; @@ -1065,6 +1045,8 @@ static void crypt_dec_pending(struct dm_crypt_io *io) if (!atomic_dec_and_test(&io->io_pending)) return; + if (io->ctx.req) + mempool_free(io->ctx.req, cc->req_pool); mempool_free(io, cc->io_pool); if (likely(!base_io)) @@ -1492,8 +1474,6 @@ static int crypt_wipe_key(struct crypt_config *cc) static void crypt_dtr(struct dm_target *ti) { struct crypt_config *cc = ti->private; - struct crypt_cpu *cpu_cc; - int cpu; ti->private = NULL; @@ -1505,13 +1485,6 @@ static void crypt_dtr(struct dm_target *ti) if (cc->crypt_queue) destroy_workqueue(cc->crypt_queue); - if (cc->cpu) - for_each_possible_cpu(cpu) { - cpu_cc = per_cpu_ptr(cc->cpu, cpu); - if (cpu_cc->req) - mempool_free(cpu_cc->req, cc->req_pool); - } - crypt_free_tfms(cc); if (cc->bs) @@ -1530,9 +1503,6 @@ static void crypt_dtr(struct dm_target *ti) if (cc->dev) dm_put_device(ti, cc->dev); - if (cc->cpu) - free_percpu(cc->cpu); - kzfree(cc->cipher); kzfree(cc->cipher_string); @@ -1588,13 +1558,6 @@ static int crypt_ctr_cipher(struct dm_target *ti, if (tmp) DMWARN("Ignoring unexpected additional cipher options"); - cc->cpu = __alloc_percpu(sizeof(*(cc->cpu)), - __alignof__(struct crypt_cpu)); - if (!cc->cpu) { - ti->error = "Cannot allocate per cpu state"; - goto bad_mem; - } - /* * For compatibility with the original dm-crypt mapping format, if * only the cipher name is supplied, use cbc-plain. @@ -1718,6 +1681,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) unsigned int key_size, opt_params; unsigned long long tmpll; int ret; + size_t iv_size_padding; struct dm_arg_set as; const char *opt_string; char dummy; @@ -1754,12 +1718,23 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) cc->dmreq_start = sizeof(struct ablkcipher_request); cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc)); - cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment()); - cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) & - ~(crypto_tfm_ctx_alignment() - 1); + cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request)); + + if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) { + /* Allocate the padding exactly */ + iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request)) + & crypto_ablkcipher_alignmask(any_tfm(cc)); + } else { + /* + * If the cipher requires greater alignment than kmalloc + * alignment, we don't know the exact position of the + * initialization vector. We must assume worst case. + */ + iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc)); + } cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + - sizeof(struct dm_crypt_request) + cc->iv_size); + sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size); if (!cc->req_pool) { ti->error = "Cannot allocate crypt request mempool"; goto bad; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 3842ac738f98..db404a0f7e2c 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -10,6 +10,7 @@ #include <linux/device-mapper.h> #include <linux/bio.h> +#include <linux/completion.h> #include <linux/mempool.h> #include <linux/module.h> #include <linux/sched.h> @@ -32,7 +33,7 @@ struct dm_io_client { struct io { unsigned long error_bits; atomic_t count; - struct task_struct *sleeper; + struct completion *wait; struct dm_io_client *client; io_notify_fn callback; void *context; @@ -121,8 +122,8 @@ static void dec_count(struct io *io, unsigned int region, int error) invalidate_kernel_vmap_range(io->vma_invalidate_address, io->vma_invalidate_size); - if (io->sleeper) - wake_up_process(io->sleeper); + if (io->wait) + complete(io->wait); else { unsigned long r = io->error_bits; @@ -387,6 +388,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, */ volatile char io_[sizeof(struct io) + __alignof__(struct io) - 1]; struct io *io = (struct io *)PTR_ALIGN(&io_, __alignof__(struct io)); + DECLARE_COMPLETION_ONSTACK(wait); if (num_regions > 1 && (rw & RW_MASK) != WRITE) { WARN_ON(1); @@ -395,7 +397,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, io->error_bits = 0; atomic_set(&io->count, 1); /* see dispatch_io() */ - io->sleeper = current; + io->wait = &wait; io->client = client; io->vma_invalidate_address = dp->vma_invalidate_address; @@ -403,15 +405,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, dispatch_io(rw, num_regions, where, dp, io, 1); - while (1) { - set_current_state(TASK_UNINTERRUPTIBLE); - - if (!atomic_read(&io->count)) - break; - - io_schedule(); - } - set_current_state(TASK_RUNNING); + wait_for_completion_io(&wait); if (error_bits) *error_bits = io->error_bits; @@ -434,7 +428,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions, io = mempool_alloc(client->pool, GFP_NOIO); io->error_bits = 0; atomic_set(&io->count, 1); /* see dispatch_io() */ - io->sleeper = NULL; + io->wait = NULL; io->client = client; io->callback = fn; io->context = context; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index 08d9a207259a..c69d0b787746 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -272,7 +272,7 @@ int dm_ulog_tfr_init(void) r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback); if (r) { - cn_del_callback(&ulog_cn_id); + kfree(prealloced_cn_msg); return r; } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index fb9efc829182..e9d33ad59df5 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -192,6 +192,13 @@ struct dm_pool_metadata { * operation possible in this state is the closing of the device. */ bool fail_io:1; + + /* + * Reading the space map roots can fail, so we read it into these + * buffers before the superblock is locked and updated. + */ + __u8 data_space_map_root[SPACE_MAP_ROOT_SIZE]; + __u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE]; }; struct dm_thin_device { @@ -431,26 +438,53 @@ static void __setup_btree_details(struct dm_pool_metadata *pmd) pmd->details_info.value_type.equal = NULL; } +static int save_sm_roots(struct dm_pool_metadata *pmd) +{ + int r; + size_t len; + + r = dm_sm_root_size(pmd->metadata_sm, &len); + if (r < 0) + return r; + + r = dm_sm_copy_root(pmd->metadata_sm, &pmd->metadata_space_map_root, len); + if (r < 0) + return r; + + r = dm_sm_root_size(pmd->data_sm, &len); + if (r < 0) + return r; + + return dm_sm_copy_root(pmd->data_sm, &pmd->data_space_map_root, len); +} + +static void copy_sm_roots(struct dm_pool_metadata *pmd, + struct thin_disk_superblock *disk) +{ + memcpy(&disk->metadata_space_map_root, + &pmd->metadata_space_map_root, + sizeof(pmd->metadata_space_map_root)); + + memcpy(&disk->data_space_map_root, + &pmd->data_space_map_root, + sizeof(pmd->data_space_map_root)); +} + static int __write_initial_superblock(struct dm_pool_metadata *pmd) { int r; struct dm_block *sblock; - size_t metadata_len, data_len; struct thin_disk_superblock *disk_super; sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT; if (bdev_size > THIN_METADATA_MAX_SECTORS) bdev_size = THIN_METADATA_MAX_SECTORS; - r = dm_sm_root_size(pmd->metadata_sm, &metadata_len); - if (r < 0) - return r; - - r = dm_sm_root_size(pmd->data_sm, &data_len); + r = dm_sm_commit(pmd->data_sm); if (r < 0) return r; - r = dm_sm_commit(pmd->data_sm); + r = save_sm_roots(pmd); if (r < 0) return r; @@ -471,15 +505,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) disk_super->trans_id = 0; disk_super->held_root = 0; - r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root, - metadata_len); - if (r < 0) - goto bad_locked; - - r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root, - data_len); - if (r < 0) - goto bad_locked; + copy_sm_roots(pmd, disk_super); disk_super->data_mapping_root = cpu_to_le64(pmd->root); disk_super->device_details_root = cpu_to_le64(pmd->details_root); @@ -488,10 +514,6 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) disk_super->data_block_size = cpu_to_le32(pmd->data_block_size); return dm_tm_commit(pmd->tm, sblock); - -bad_locked: - dm_bm_unlock(sblock); - return r; } static int __format_metadata(struct dm_pool_metadata *pmd) @@ -591,6 +613,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd) disk_super = dm_block_data(sblock); + /* Verify the data block size hasn't changed */ + if (le32_to_cpu(disk_super->data_block_size) != pmd->data_block_size) { + DMERR("changing the data block size (from %u to %llu) is not supported", + le32_to_cpu(disk_super->data_block_size), + (unsigned long long)pmd->data_block_size); + r = -EINVAL; + goto bad_unlock_sblock; + } + r = __check_incompat_features(disk_super, pmd); if (r < 0) goto bad_unlock_sblock; @@ -769,6 +800,10 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) if (r < 0) return r; + r = save_sm_roots(pmd); + if (r < 0) + return r; + r = superblock_lock(pmd, &sblock); if (r) return r; @@ -780,21 +815,9 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) disk_super->trans_id = cpu_to_le64(pmd->trans_id); disk_super->flags = cpu_to_le32(pmd->flags); - r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root, - metadata_len); - if (r < 0) - goto out_locked; - - r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root, - data_len); - if (r < 0) - goto out_locked; + copy_sm_roots(pmd, disk_super); return dm_tm_commit(pmd->tm, sblock); - -out_locked: - dm_bm_unlock(sblock); - return r; } struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index be70d38745f7..359af3a519b5 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -25,6 +25,9 @@ #define MAPPING_POOL_SIZE 1024 #define PRISON_CELLS 1024 #define COMMIT_PERIOD HZ +#define NO_SPACE_TIMEOUT_SECS 60 + +static unsigned no_space_timeout_secs = NO_SPACE_TIMEOUT_SECS; DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, "A percentage of time allocated for copy on write"); @@ -173,6 +176,7 @@ struct pool { struct workqueue_struct *wq; struct work_struct worker; struct delayed_work waker; + struct delayed_work no_space_timeout; unsigned long last_commit_jiffies; unsigned ref_count; @@ -920,7 +924,7 @@ static int commit(struct pool *pool) { int r; - if (get_pool_mode(pool) != PM_WRITE) + if (get_pool_mode(pool) >= PM_READ_ONLY) return -EINVAL; r = dm_pool_commit_metadata(pool->pmd); @@ -1392,9 +1396,9 @@ static void process_deferred_bios(struct pool *pool) */ if (ensure_next_mapping(pool)) { spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->deferred_bios, bio); bio_list_merge(&pool->deferred_bios, &bios); spin_unlock_irqrestore(&pool->lock, flags); - break; } @@ -1449,6 +1453,20 @@ static void do_waker(struct work_struct *ws) queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD); } +/* + * We're holding onto IO to allow userland time to react. After the + * timeout either the pool will have been resized (and thus back in + * PM_WRITE mode), or we degrade to PM_READ_ONLY and start erroring IO. + */ +static void do_no_space_timeout(struct work_struct *ws) +{ + struct pool *pool = container_of(to_delayed_work(ws), struct pool, + no_space_timeout); + + if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) + set_pool_mode(pool, PM_READ_ONLY); +} + /*----------------------------------------------------------------*/ struct noflush_work { @@ -1513,6 +1531,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) struct pool_c *pt = pool->ti->private; bool needs_check = dm_pool_metadata_needs_check(pool->pmd); enum pool_mode old_mode = get_pool_mode(pool); + unsigned long no_space_timeout = ACCESS_ONCE(no_space_timeout_secs) * HZ; /* * Never allow the pool to transition to PM_WRITE mode if user @@ -1574,6 +1593,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) pool->process_discard = process_discard; pool->process_prepared_mapping = process_prepared_mapping; pool->process_prepared_discard = process_prepared_discard_passdown; + + if (!pool->pf.error_if_no_space && no_space_timeout) + queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout); break; case PM_WRITE: @@ -1956,6 +1978,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, INIT_WORK(&pool->worker, do_worker); INIT_DELAYED_WORK(&pool->waker, do_waker); + INIT_DELAYED_WORK(&pool->no_space_timeout, do_no_space_timeout); spin_lock_init(&pool->lock); bio_list_init(&pool->deferred_bios); bio_list_init(&pool->deferred_flush_bios); @@ -2519,6 +2542,7 @@ static void pool_postsuspend(struct dm_target *ti) struct pool *pool = pt->pool; cancel_delayed_work(&pool->waker); + cancel_delayed_work(&pool->no_space_timeout); flush_workqueue(pool->wq); (void) commit(pool); } @@ -2901,7 +2925,8 @@ static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits) */ if (pt->adjusted_pf.discard_passdown) { data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits; - limits->discard_granularity = data_limits->discard_granularity; + limits->discard_granularity = max(data_limits->discard_granularity, + pool->sectors_per_block << SECTOR_SHIFT); } else limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT; } @@ -3305,6 +3330,9 @@ static void dm_thin_exit(void) module_init(dm_thin_init); module_exit(dm_thin_exit); +module_param_named(no_space_timeout, no_space_timeout_secs, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(no_space_timeout, "Out of data space queue IO timeout in seconds"); + MODULE_DESCRIPTION(DM_NAME " thin provisioning target"); MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c index 796007a5e0e1..7a7bab8947ae 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity.c @@ -330,15 +330,17 @@ test_block_hash: return r; } } - todo = 1 << v->data_dev_block_bits; - while (io->iter.bi_size) { + do { u8 *page; + unsigned len; struct bio_vec bv = bio_iter_iovec(bio, io->iter); page = kmap_atomic(bv.bv_page); - r = crypto_shash_update(desc, page + bv.bv_offset, - bv.bv_len); + len = bv.bv_len; + if (likely(len >= todo)) + len = todo; + r = crypto_shash_update(desc, page + bv.bv_offset, len); kunmap_atomic(page); if (r < 0) { @@ -346,8 +348,9 @@ test_block_hash: return r; } - bio_advance_iter(bio, &io->iter, bv.bv_len); - } + bio_advance_iter(bio, &io->iter, len); + todo -= len; + } while (todo); if (!v->version) { r = crypto_shash_update(desc, v->salt, v->salt_size); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 8c53b09b9a2c..65ee3a0d4683 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -54,6 +54,8 @@ static void do_deferred_remove(struct work_struct *w); static DECLARE_WORK(deferred_remove_work, do_deferred_remove); +static struct workqueue_struct *deferred_remove_workqueue; + /* * For bio-based dm. * One of these is allocated per bio. @@ -283,16 +285,24 @@ static int __init local_init(void) if (r) goto out_free_rq_tio_cache; + deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1); + if (!deferred_remove_workqueue) { + r = -ENOMEM; + goto out_uevent_exit; + } + _major = major; r = register_blkdev(_major, _name); if (r < 0) - goto out_uevent_exit; + goto out_free_workqueue; if (!_major) _major = r; return 0; +out_free_workqueue: + destroy_workqueue(deferred_remove_workqueue); out_uevent_exit: dm_uevent_exit(); out_free_rq_tio_cache: @@ -306,6 +316,7 @@ out_free_io_cache: static void local_exit(void) { flush_scheduled_work(); + destroy_workqueue(deferred_remove_workqueue); kmem_cache_destroy(_rq_tio_cache); kmem_cache_destroy(_io_cache); @@ -414,7 +425,7 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode) if (atomic_dec_and_test(&md->open_count) && (test_bit(DMF_DEFERRED_REMOVE, &md->flags))) - schedule_work(&deferred_remove_work); + queue_work(deferred_remove_workqueue, &deferred_remove_work); dm_put(md); diff --git a/drivers/md/md.c b/drivers/md/md.c index 4ad5cc4e63e8..73aedcb639c0 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7395,8 +7395,10 @@ void md_do_sync(struct md_thread *thread) /* just incase thread restarts... */ if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) return; - if (mddev->ro) /* never try to sync a read-only array */ + if (mddev->ro) {/* never try to sync a read-only array */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); return; + } if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) { @@ -7503,6 +7505,19 @@ void md_do_sync(struct md_thread *thread) rdev->recovery_offset < j) j = rdev->recovery_offset; rcu_read_unlock(); + + /* If there is a bitmap, we need to make sure all + * writes that started before we added a spare + * complete before we start doing a recovery. + * Otherwise the write might complete and (via + * bitmap_endwrite) set a bit in the bitmap after the + * recovery has checked that bit and skipped that + * region. + */ + if (mddev->bitmap) { + mddev->pers->quiesce(mddev, 1); + mddev->pers->quiesce(mddev, 0); + } } printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev)); @@ -7838,6 +7853,7 @@ void md_check_recovery(struct mddev *mddev) /* There is no thread, but we need to call * ->spare_active and clear saved_raid_disk */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_reap_sync_thread(mddev); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); goto unlock; @@ -8530,7 +8546,8 @@ static int md_notify_reboot(struct notifier_block *this, if (mddev_trylock(mddev)) { if (mddev->pers) __md_stop_writes(mddev); - mddev->safemode = 2; + if (mddev->persistent) + mddev->safemode = 2; mddev_unlock(mddev); } need_delay = 1; diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 455f79279a16..087411c95ffc 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -595,25 +595,14 @@ int dm_bm_unlock(struct dm_block *b) } EXPORT_SYMBOL_GPL(dm_bm_unlock); -int dm_bm_flush_and_unlock(struct dm_block_manager *bm, - struct dm_block *superblock) +int dm_bm_flush(struct dm_block_manager *bm) { - int r; - if (bm->read_only) return -EPERM; - r = dm_bufio_write_dirty_buffers(bm->bufio); - if (unlikely(r)) { - dm_bm_unlock(superblock); - return r; - } - - dm_bm_unlock(superblock); - return dm_bufio_write_dirty_buffers(bm->bufio); } -EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock); +EXPORT_SYMBOL_GPL(dm_bm_flush); void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b) { diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h index 13cd58e1fe69..1b95dfc17786 100644 --- a/drivers/md/persistent-data/dm-block-manager.h +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -105,8 +105,7 @@ int dm_bm_unlock(struct dm_block *b); * * This method always blocks. */ -int dm_bm_flush_and_unlock(struct dm_block_manager *bm, - struct dm_block *superblock); +int dm_bm_flush(struct dm_block_manager *bm); /* * Request data is prefetched into the cache. diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index 81da1a26042e..3bc30a0ae3d6 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -154,7 +154,7 @@ int dm_tm_pre_commit(struct dm_transaction_manager *tm) if (r < 0) return r; - return 0; + return dm_bm_flush(tm->bm); } EXPORT_SYMBOL_GPL(dm_tm_pre_commit); @@ -164,8 +164,9 @@ int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root) return -EWOULDBLOCK; wipe_shadow_table(tm); + dm_bm_unlock(root); - return dm_bm_flush_and_unlock(tm->bm, root); + return dm_bm_flush(tm->bm); } EXPORT_SYMBOL_GPL(dm_tm_commit); diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h index b5b139076ca5..2772ed2a781a 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.h +++ b/drivers/md/persistent-data/dm-transaction-manager.h @@ -38,18 +38,17 @@ struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transac /* * We use a 2-phase commit here. * - * i) In the first phase the block manager is told to start flushing, and - * the changes to the space map are written to disk. You should interrogate - * your particular space map to get detail of its root node etc. to be - * included in your superblock. + * i) Make all changes for the transaction *except* for the superblock. + * Then call dm_tm_pre_commit() to flush them to disk. * - * ii) @root will be committed last. You shouldn't use more than the - * first 512 bytes of @root if you wish the transaction to survive a power - * failure. You *must* have a write lock held on @root for both stage (i) - * and (ii). The commit will drop the write lock. + * ii) Lock your superblock. Update. Then call dm_tm_commit() which will + * unlock the superblock and flush it. No other blocks should be updated + * during this period. Care should be taken to never unlock a partially + * updated superblock; perform any operations that could fail *before* you + * take the superblock lock. */ int dm_tm_pre_commit(struct dm_transaction_manager *tm); -int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root); +int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *superblock); /* * These methods are the only way to get hold of a writeable block. diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 4a6ca1cb2e78..55de4f6f7eaf 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -97,6 +97,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) struct pool_info *pi = data; struct r1bio *r1_bio; struct bio *bio; + int need_pages; int i, j; r1_bio = r1bio_pool_alloc(gfp_flags, pi); @@ -119,15 +120,15 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) * RESYNC_PAGES for each bio. */ if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) - j = pi->raid_disks; + need_pages = pi->raid_disks; else - j = 1; - while(j--) { + need_pages = 1; + for (j = 0; j < need_pages; j++) { bio = r1_bio->bios[j]; bio->bi_vcnt = RESYNC_PAGES; if (bio_alloc_pages(bio, gfp_flags)) - goto out_free_bio; + goto out_free_pages; } /* If not user-requests, copy the page pointers to all bios */ if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) { @@ -141,6 +142,14 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) return r1_bio; +out_free_pages: + while (--j >= 0) { + struct bio_vec *bv; + + bio_for_each_segment_all(bv, r1_bio->bios[j], i) + __free_page(bv->bv_page); + } + out_free_bio: while (++j < pi->raid_disks) bio_put(r1_bio->bios[j]); @@ -531,11 +540,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect has_nonrot_disk = 0; choose_next_idle = 0; - if (conf->mddev->recovery_cp < MaxSector && - (this_sector + sectors >= conf->next_resync)) - choose_first = 1; - else - choose_first = 0; + choose_first = (conf->mddev->recovery_cp < this_sector + sectors); for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { sector_t dist; @@ -822,7 +827,7 @@ static void flush_pending_writes(struct r1conf *conf) * there is no normal IO happeing. It must arrange to call * lower_barrier when the particular background IO completes. */ -static void raise_barrier(struct r1conf *conf) +static void raise_barrier(struct r1conf *conf, sector_t sector_nr) { spin_lock_irq(&conf->resync_lock); @@ -832,6 +837,7 @@ static void raise_barrier(struct r1conf *conf) /* block any new IO from starting */ conf->barrier++; + conf->next_resync = sector_nr; /* For these conditions we must wait: * A: while the array is in frozen state @@ -840,14 +846,17 @@ static void raise_barrier(struct r1conf *conf) * C: next_resync + RESYNC_SECTORS > start_next_window, meaning * next resync will reach to the window which normal bios are * handling. + * D: while there are any active requests in the current window. */ wait_event_lock_irq(conf->wait_barrier, !conf->array_frozen && conf->barrier < RESYNC_DEPTH && + conf->current_window_requests == 0 && (conf->start_next_window >= conf->next_resync + RESYNC_SECTORS), conf->resync_lock); + conf->nr_pending++; spin_unlock_irq(&conf->resync_lock); } @@ -857,6 +866,7 @@ static void lower_barrier(struct r1conf *conf) BUG_ON(conf->barrier <= 0); spin_lock_irqsave(&conf->resync_lock, flags); conf->barrier--; + conf->nr_pending--; spin_unlock_irqrestore(&conf->resync_lock, flags); wake_up(&conf->wait_barrier); } @@ -868,12 +878,10 @@ static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio) if (conf->array_frozen || !bio) wait = true; else if (conf->barrier && bio_data_dir(bio) == WRITE) { - if (conf->next_resync < RESYNC_WINDOW_SECTORS) - wait = true; - else if ((conf->next_resync - RESYNC_WINDOW_SECTORS - >= bio_end_sector(bio)) || - (conf->next_resync + NEXT_NORMALIO_DISTANCE - <= bio->bi_iter.bi_sector)) + if ((conf->mddev->curr_resync_completed + >= bio_end_sector(bio)) || + (conf->next_resync + NEXT_NORMALIO_DISTANCE + <= bio->bi_iter.bi_sector)) wait = false; else wait = true; @@ -910,8 +918,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio) } if (bio && bio_data_dir(bio) == WRITE) { - if (conf->next_resync + NEXT_NORMALIO_DISTANCE - <= bio->bi_iter.bi_sector) { + if (bio->bi_iter.bi_sector >= + conf->mddev->curr_resync_completed) { if (conf->start_next_window == MaxSector) conf->start_next_window = conf->next_resync + @@ -1177,6 +1185,7 @@ read_again: atomic_read(&bitmap->behind_writes) == 0); } r1_bio->read_disk = rdisk; + r1_bio->start_next_window = 0; read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector, @@ -1492,12 +1501,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) mddev->degraded++; set_bit(Faulty, &rdev->flags); spin_unlock_irqrestore(&conf->device_lock, flags); - /* - * if recovery is running, make sure it aborts. - */ - set_bit(MD_RECOVERY_INTR, &mddev->recovery); } else set_bit(Faulty, &rdev->flags); + /* + * if recovery is running, make sure it aborts. + */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(MD_CHANGE_DEVS, &mddev->flags); printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n" @@ -1539,8 +1548,13 @@ static void close_sync(struct r1conf *conf) mempool_destroy(conf->r1buf_pool); conf->r1buf_pool = NULL; + spin_lock_irq(&conf->resync_lock); conf->next_resync = 0; conf->start_next_window = MaxSector; + conf->current_window_requests += + conf->next_window_requests; + conf->next_window_requests = 0; + spin_unlock_irq(&conf->resync_lock); } static int raid1_spare_active(struct mddev *mddev) @@ -2141,7 +2155,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) + !test_bit(Faulty, &rdev->flags)) r1_sync_page_io(rdev, sect, s, conf->tmppage, WRITE); } @@ -2153,7 +2167,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) { + !test_bit(Faulty, &rdev->flags)) { if (r1_sync_page_io(rdev, sect, s, conf->tmppage, READ)) { atomic_add(s, &rdev->corrected_errors); @@ -2532,9 +2546,8 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp bitmap_cond_end_sync(mddev->bitmap, sector_nr); r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO); - raise_barrier(conf); - conf->next_resync = sector_nr; + raise_barrier(conf, sector_nr); rcu_read_lock(); /* diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 33fc408e5eac..a46124ecafc7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1172,6 +1172,13 @@ static void __make_request(struct mddev *mddev, struct bio *bio) int max_sectors; int sectors; + /* + * Register the new request and wait if the reconstruction + * thread has put up a bar for new requests. + * Continue immediately if no resync is active currently. + */ + wait_barrier(conf); + sectors = bio_sectors(bio); while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && bio->bi_iter.bi_sector < conf->reshape_progress && @@ -1552,12 +1559,6 @@ static void make_request(struct mddev *mddev, struct bio *bio) md_write_start(mddev, bio); - /* - * Register the new request and wait if the reconstruction - * thread has put up a bar for new requests. - * Continue immediately if no resync is active currently. - */ - wait_barrier(conf); do { @@ -1683,13 +1684,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) spin_unlock_irqrestore(&conf->device_lock, flags); return; } - if (test_and_clear_bit(In_sync, &rdev->flags)) { + if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - /* - * if recovery is running, make sure it aborts. - */ - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - } + /* + * If recovery is running, make sure it aborts. + */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); @@ -2953,6 +2953,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, */ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { end_reshape(conf); + close_sync(conf); return 0; } @@ -4410,7 +4411,7 @@ read_more: read_bio->bi_private = r10_bio; read_bio->bi_end_io = end_sync_read; read_bio->bi_rw = READ; - read_bio->bi_flags &= ~(BIO_POOL_MASK - 1); + read_bio->bi_flags &= (~0UL << BIO_RESET_BITS); read_bio->bi_flags |= 1 << BIO_UPTODATE; read_bio->bi_vcnt = 0; read_bio->bi_iter.bi_size = 0; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 16f5c21963db..4913c0690872 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -64,6 +64,10 @@ #define cpu_to_group(cpu) cpu_to_node(cpu) #define ANY_GROUP NUMA_NO_NODE +static bool devices_handle_discard_safely = false; +module_param(devices_handle_discard_safely, bool, 0644); +MODULE_PARM_DESC(devices_handle_discard_safely, + "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions"); static struct workqueue_struct *raid5_wq; /* * Stripe cache @@ -3779,6 +3783,8 @@ static void handle_stripe(struct stripe_head *sh) set_bit(R5_Wantwrite, &dev->flags); if (prexor) continue; + if (s.failed > 1) + continue; if (!test_bit(R5_Insync, &dev->flags) || ((i == sh->pd_idx || i == sh->qd_idx) && s.failed == 0)) @@ -6115,7 +6121,7 @@ static int run(struct mddev *mddev) mddev->queue->limits.discard_granularity = stripe; /* * unaligned part of discard request will be ignored, so can't - * guarantee discard_zerors_data + * guarantee discard_zeroes_data */ mddev->queue->limits.discard_zeroes_data = 0; @@ -6140,6 +6146,18 @@ static int run(struct mddev *mddev) !bdev_get_queue(rdev->bdev)-> limits.discard_zeroes_data) discard_supported = false; + /* Unfortunately, discard_zeroes_data is not currently + * a guarantee - just a hint. So we only allow DISCARD + * if the sysadmin has confirmed that only safe devices + * are in use by setting a module parameter. + */ + if (!devices_handle_discard_safely) { + if (discard_supported) { + pr_info("md/raid456: discard support disabled due to uncertainty.\n"); + pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n"); + } + discard_supported = false; + } } if (discard_supported && diff --git a/drivers/media/common/siano/Kconfig b/drivers/media/common/siano/Kconfig index f953d33ee151..4bfbd5f463d1 100644 --- a/drivers/media/common/siano/Kconfig +++ b/drivers/media/common/siano/Kconfig @@ -22,8 +22,7 @@ config SMS_SIANO_DEBUGFS bool "Enable debugfs for smsdvb" depends on SMS_SIANO_MDTV depends on DEBUG_FS - depends on SMS_USB_DRV - depends on CONFIG_SMS_USB_DRV = CONFIG_SMS_SDIO_DRV + depends on SMS_USB_DRV = SMS_SDIO_DRV ---help--- Choose Y to enable visualizing a dump of the frontend diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h index f19a2ccd1e4b..fabe2fce9bc5 100644 --- a/drivers/media/dvb-core/dvb-usb-ids.h +++ b/drivers/media/dvb-core/dvb-usb-ids.h @@ -257,6 +257,7 @@ #define USB_PID_TERRATEC_T5 0x10a1 #define USB_PID_NOXON_DAB_STICK 0x00b3 #define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 +#define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e #define USB_PID_PINNACLE_PCTV2000E 0x022c #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 @@ -278,6 +279,8 @@ #define USB_PID_PCTV_400E 0x020f #define USB_PID_PCTV_450E 0x0222 #define USB_PID_PCTV_452E 0x021f +#define USB_PID_PCTV_78E 0x025a +#define USB_PID_PCTV_79E 0x0262 #define USB_PID_REALTEK_RTL2831U 0x2831 #define USB_PID_REALTEK_RTL2832U 0x2832 #define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 @@ -360,6 +363,7 @@ #define USB_PID_FRIIO_WHITE 0x0001 #define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_SVEON_STV20 0xe39d +#define USB_PID_SVEON_STV20_RTL2832U 0xd39d #define USB_PID_SVEON_STV22 0xe401 #define USB_PID_SVEON_STV22_IT9137 0xe411 #define USB_PID_AZUREWAVE_AZ6027 0x3275 @@ -374,4 +378,5 @@ #define USB_PID_CTVDIGDUAL_V2 0xe410 #define USB_PID_PCTV_2002E 0x025c #define USB_PID_PCTV_2002E_SE 0x025d +#define USB_PID_SVEON_STV27 0xd3af #endif diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c index 1e344b033277..22e8c2032f6d 100644 --- a/drivers/media/dvb-frontends/ds3000.c +++ b/drivers/media/dvb-frontends/ds3000.c @@ -864,6 +864,13 @@ struct dvb_frontend *ds3000_attach(const struct ds3000_config *config, memcpy(&state->frontend.ops, &ds3000_ops, sizeof(struct dvb_frontend_ops)); state->frontend.demodulator_priv = state; + + /* + * Some devices like T480 starts with voltage on. Be sure + * to turn voltage off during init, as this can otherwise + * interfere with Unicable SCR systems. + */ + ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF); return &state->frontend; error3: diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c index b2351466b0da..32cffca14d0b 100644 --- a/drivers/media/dvb-frontends/m88rs2000.c +++ b/drivers/media/dvb-frontends/m88rs2000.c @@ -715,6 +715,22 @@ static int m88rs2000_get_frontend(struct dvb_frontend *fe) return 0; } +static int m88rs2000_get_tune_settings(struct dvb_frontend *fe, + struct dvb_frontend_tune_settings *tune) +{ + struct dtv_frontend_properties *c = &fe->dtv_property_cache; + + if (c->symbol_rate > 3000000) + tune->min_delay_ms = 2000; + else + tune->min_delay_ms = 3000; + + tune->step_size = c->symbol_rate / 16000; + tune->max_drift = c->symbol_rate / 2000; + + return 0; +} + static int m88rs2000_i2c_gate_ctrl(struct dvb_frontend *fe, int enable) { struct m88rs2000_state *state = fe->demodulator_priv; @@ -746,7 +762,7 @@ static struct dvb_frontend_ops m88rs2000_ops = { .symbol_rate_tolerance = 500, /* ppm */ .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | - FE_CAN_QPSK | + FE_CAN_QPSK | FE_CAN_INVERSION_AUTO | FE_CAN_FEC_AUTO }, @@ -766,6 +782,7 @@ static struct dvb_frontend_ops m88rs2000_ops = { .set_frontend = m88rs2000_set_frontend, .get_frontend = m88rs2000_get_frontend, + .get_tune_settings = m88rs2000_get_tune_settings, }; struct dvb_frontend *m88rs2000_attach(const struct m88rs2000_config *config, diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c index 8ad3a57cf640..287b977862e2 100644 --- a/drivers/media/dvb-frontends/tda10071.c +++ b/drivers/media/dvb-frontends/tda10071.c @@ -667,6 +667,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) struct dtv_frontend_properties *c = &fe->dtv_property_cache; int ret, i; u8 mode, rolloff, pilot, inversion, div; + fe_modulation_t modulation; dev_dbg(&priv->i2c->dev, "%s: delivery_system=%d modulation=%d " \ "frequency=%d symbol_rate=%d inversion=%d pilot=%d " \ @@ -701,10 +702,13 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) switch (c->delivery_system) { case SYS_DVBS: + modulation = QPSK; rolloff = 0; pilot = 2; break; case SYS_DVBS2: + modulation = c->modulation; + switch (c->rolloff) { case ROLLOFF_20: rolloff = 2; @@ -749,7 +753,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) { if (c->delivery_system == TDA10071_MODCOD[i].delivery_system && - c->modulation == TDA10071_MODCOD[i].modulation && + modulation == TDA10071_MODCOD[i].modulation && c->fec_inner == TDA10071_MODCOD[i].fec) { mode = TDA10071_MODCOD[i].val; dev_dbg(&priv->i2c->dev, "%s: mode found=%02x\n", diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index 71c8570bd9ea..112394d138c9 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -1984,7 +1984,7 @@ static int adv7604_log_status(struct v4l2_subdev *sd) v4l2_info(sd, "HDCP keys read: %s%s\n", (hdmi_read(sd, 0x04) & 0x20) ? "yes" : "no", (hdmi_read(sd, 0x04) & 0x10) ? "ERROR" : ""); - if (!is_hdmi(sd)) { + if (is_hdmi(sd)) { bool audio_pll_locked = hdmi_read(sd, 0x04) & 0x01; bool audio_sample_packet_detect = hdmi_read(sd, 0x18) & 0x01; bool audio_mute = io_read(sd, 0x65) & 0x40; diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c index 36c504b78f2c..008ac87a9031 100644 --- a/drivers/media/i2c/mt9v032.c +++ b/drivers/media/i2c/mt9v032.c @@ -305,8 +305,8 @@ mt9v032_update_hblank(struct mt9v032 *mt9v032) if (mt9v032->version->version == MT9V034_CHIP_ID_REV1) min_hblank += (mt9v032->hratio - 1) * 10; - min_hblank = max_t(unsigned int, (int)mt9v032->model->data->min_row_time - crop->width, - (int)min_hblank); + min_hblank = max_t(int, mt9v032->model->data->min_row_time - crop->width, + min_hblank); hblank = max_t(unsigned int, mt9v032->hblank, min_hblank); return mt9v032_write(client, MT9V032_HORIZONTAL_BLANKING, hblank); diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c index e8a1ce204036..cdd7c1b7259b 100644 --- a/drivers/media/i2c/ov7670.c +++ b/drivers/media/i2c/ov7670.c @@ -1109,7 +1109,7 @@ static int ov7670_enum_framesizes(struct v4l2_subdev *sd, * windows that fall outside that. */ for (i = 0; i < n_win_sizes; i++) { - struct ov7670_win_size *win = &info->devtype->win_sizes[index]; + struct ov7670_win_size *win = &info->devtype->win_sizes[i]; if (info->min_width && win->width < info->min_width) continue; if (info->min_height && win->height < info->min_height) diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c index 72af644fa051..cf93021a6500 100644 --- a/drivers/media/i2c/tda7432.c +++ b/drivers/media/i2c/tda7432.c @@ -293,7 +293,7 @@ static int tda7432_s_ctrl(struct v4l2_ctrl *ctrl) if (t->mute->val) { lf |= TDA7432_MUTE; lr |= TDA7432_MUTE; - lf |= TDA7432_MUTE; + rf |= TDA7432_MUTE; rr |= TDA7432_MUTE; } /* Mute & update balance*/ diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index d5a7a135f75d..88c1606fd555 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -93,6 +93,7 @@ static long media_device_enum_entities(struct media_device *mdev, struct media_entity *ent; struct media_entity_desc u_ent; + memset(&u_ent, 0, sizeof(u_ent)); if (copy_from_user(&u_ent.id, &uent->id, sizeof(u_ent.id))) return -EFAULT; @@ -105,8 +106,6 @@ static long media_device_enum_entities(struct media_device *mdev, if (ent->name) { strncpy(u_ent.name, ent->name, sizeof(u_ent.name)); u_ent.name[sizeof(u_ent.name) - 1] = '\0'; - } else { - memset(u_ent.name, 0, sizeof(u_ent.name)); } u_ent.type = ent->type; u_ent.revision = ent->revision; diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c index 716bdc57fac6..83f5074706f9 100644 --- a/drivers/media/pci/cx18/cx18-driver.c +++ b/drivers/media/pci/cx18/cx18-driver.c @@ -1091,6 +1091,7 @@ static int cx18_probe(struct pci_dev *pci_dev, setup.addr = ADDR_UNSET; setup.type = cx->options.tuner; setup.mode_mask = T_ANALOG_TV; /* matches TV tuners */ + setup.config = NULL; if (cx->options.radio > 0) setup.mode_mask |= T_RADIO; setup.tuner_callback = (setup.type == TUNER_XC2028) ? diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c index e1863dbf4edc..7a9b98bc208b 100644 --- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c +++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c @@ -159,6 +159,12 @@ static int snd_ivtv_pcm_capture_open(struct snd_pcm_substream *substream) /* Instruct the CX2341[56] to start sending packets */ snd_ivtv_lock(itvsc); + + if (ivtv_init_on_first_open(itv)) { + snd_ivtv_unlock(itvsc); + return -ENXIO; + } + s = &itv->streams[IVTV_ENC_STREAM_TYPE_PCM]; v4l2_fh_init(&item.fh, s->vdev); diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c index c9b2350e92c8..6e4bdb90aa92 100644 --- a/drivers/media/pci/saa7134/saa7134-cards.c +++ b/drivers/media/pci/saa7134/saa7134-cards.c @@ -8045,8 +8045,8 @@ int saa7134_board_init2(struct saa7134_dev *dev) break; } /* switch() */ - /* initialize tuner */ - if (TUNER_ABSENT != dev->tuner_type) { + /* initialize tuner (don't do this when resuming) */ + if (!dev->insuspend && TUNER_ABSENT != dev->tuner_type) { int has_demod = (dev->tda9887_conf & TDA9887_PRESENT); /* Note: radio tuner address is always filled in, diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c index eb472b5b26a0..40396e8b16a8 100644 --- a/drivers/media/pci/saa7134/saa7134-video.c +++ b/drivers/media/pci/saa7134/saa7134-video.c @@ -1243,6 +1243,7 @@ static int video_release(struct file *file) videobuf_streamoff(&dev->cap); res_free(dev, fh, RESOURCE_VIDEO); videobuf_mmap_free(&dev->cap); + INIT_LIST_HEAD(&dev->cap.stream); } if (dev->cap.read_buf) { buffer_release(&dev->cap, dev->cap.read_buf); @@ -1254,6 +1255,7 @@ static int video_release(struct file *file) videobuf_stop(&dev->vbi); res_free(dev, fh, RESOURCE_VBI); videobuf_mmap_free(&dev->vbi); + INIT_LIST_HEAD(&dev->vbi.stream); } /* ts-capture will not work in planar mode, so turn it off Hac: 04.05*/ @@ -1987,17 +1989,12 @@ int saa7134_streamoff(struct file *file, void *priv, enum v4l2_buf_type type) { struct saa7134_dev *dev = video_drvdata(file); - int err; int res = saa7134_resource(file); if (res != RESOURCE_EMPRESS) pm_qos_remove_request(&dev->qos_request); - err = videobuf_streamoff(saa7134_queue(file)); - if (err < 0) - return err; - res_free(dev, priv, res); - return 0; + return videobuf_streamoff(saa7134_queue(file)); } EXPORT_SYMBOL_GPL(saa7134_streamoff); diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c index 1c776c1186f1..1dbff1472809 100644 --- a/drivers/media/platform/omap3isp/isppreview.c +++ b/drivers/media/platform/omap3isp/isppreview.c @@ -1079,6 +1079,7 @@ static void preview_config_input_format(struct isp_prev_device *prev, */ static void preview_config_input_size(struct isp_prev_device *prev, u32 active) { + const struct v4l2_mbus_framefmt *format = &prev->formats[PREV_PAD_SINK]; struct isp_device *isp = to_isp_device(prev); unsigned int sph = prev->crop.left; unsigned int eph = prev->crop.left + prev->crop.width - 1; @@ -1086,6 +1087,14 @@ static void preview_config_input_size(struct isp_prev_device *prev, u32 active) unsigned int elv = prev->crop.top + prev->crop.height - 1; u32 features; + if (format->code != V4L2_MBUS_FMT_Y8_1X8 && + format->code != V4L2_MBUS_FMT_Y10_1X10) { + sph -= 2; + eph += 2; + slv -= 2; + elv += 2; + } + features = (prev->params.params[0].features & active) | (prev->params.params[1].features & ~active); diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c index b4687a834f85..7245cca89257 100644 --- a/drivers/media/platform/vsp1/vsp1_video.c +++ b/drivers/media/platform/vsp1/vsp1_video.c @@ -635,8 +635,6 @@ static int vsp1_video_buffer_prepare(struct vb2_buffer *vb) if (vb->num_planes < format->num_planes) return -EINVAL; - buf->video = video; - for (i = 0; i < vb->num_planes; ++i) { buf->addr[i] = vb2_dma_contig_plane_dma_addr(vb, i); buf->length[i] = vb2_plane_size(vb, i); diff --git a/drivers/media/platform/vsp1/vsp1_video.h b/drivers/media/platform/vsp1/vsp1_video.h index d8612a378345..47b7a8ab5e2f 100644 --- a/drivers/media/platform/vsp1/vsp1_video.h +++ b/drivers/media/platform/vsp1/vsp1_video.h @@ -89,7 +89,6 @@ static inline struct vsp1_pipeline *to_vsp1_pipeline(struct media_entity *e) } struct vsp1_video_buffer { - struct vsp1_video *video; struct vb2_buffer buf; struct list_head queue; diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c index 3aecaf465094..f0c9c42867de 100644 --- a/drivers/media/tuners/fc2580.c +++ b/drivers/media/tuners/fc2580.c @@ -195,7 +195,7 @@ static int fc2580_set_params(struct dvb_frontend *fe) f_ref = 2UL * priv->cfg->clock / r_val; n_val = div_u64_rem(f_vco, f_ref, &k_val); - k_val_reg = 1UL * k_val * (1 << 20) / f_ref; + k_val_reg = div_u64(1ULL * k_val * (1 << 20), f_ref); ret = fc2580_wr_reg(priv, 0x18, r18_val | ((k_val_reg >> 16) & 0xff)); if (ret < 0) @@ -348,8 +348,8 @@ static int fc2580_set_params(struct dvb_frontend *fe) if (ret < 0) goto err; - ret = fc2580_wr_reg(priv, 0x37, 1UL * priv->cfg->clock * \ - fc2580_if_filter_lut[i].mul / 1000000000); + ret = fc2580_wr_reg(priv, 0x37, div_u64(1ULL * priv->cfg->clock * + fc2580_if_filter_lut[i].mul, 1000000000)); if (ret < 0) goto err; diff --git a/drivers/media/tuners/fc2580_priv.h b/drivers/media/tuners/fc2580_priv.h index be38a9e637e0..646c99452136 100644 --- a/drivers/media/tuners/fc2580_priv.h +++ b/drivers/media/tuners/fc2580_priv.h @@ -22,6 +22,7 @@ #define FC2580_PRIV_H #include "fc2580.h" +#include <linux/math64.h> struct fc2580_reg_val { u8 reg; diff --git a/drivers/media/tuners/m88ts2022.c b/drivers/media/tuners/m88ts2022.c index 40c42dec721b..7a62097aa9ea 100644 --- a/drivers/media/tuners/m88ts2022.c +++ b/drivers/media/tuners/m88ts2022.c @@ -314,7 +314,7 @@ static int m88ts2022_set_params(struct dvb_frontend *fe) div_min = gdiv28 * 78 / 100; div_max = clamp_val(div_max, 0U, 63U); - f_3db_hz = c->symbol_rate * 135UL / 200UL; + f_3db_hz = mult_frac(c->symbol_rate, 135, 200); f_3db_hz += 2000000U + (frequency_offset_khz * 1000U); f_3db_hz = clamp(f_3db_hz, 7000000U, 40000000U); diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index 2018befabb5a..e71decbfd0af 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -93,7 +93,7 @@ struct xc4000_priv { struct firmware_description *firm; int firm_size; u32 if_khz; - u32 freq_hz; + u32 freq_hz, freq_offset; u32 bandwidth; u8 video_standard; u8 rf_mode; @@ -1157,14 +1157,14 @@ static int xc4000_set_params(struct dvb_frontend *fe) case SYS_ATSC: dprintk(1, "%s() VSB modulation\n", __func__); priv->rf_mode = XC_RF_MODE_AIR; - priv->freq_hz = c->frequency - 1750000; + priv->freq_offset = 1750000; priv->video_standard = XC4000_DTV6; type = DTV6; break; case SYS_DVBC_ANNEX_B: dprintk(1, "%s() QAM modulation\n", __func__); priv->rf_mode = XC_RF_MODE_CABLE; - priv->freq_hz = c->frequency - 1750000; + priv->freq_offset = 1750000; priv->video_standard = XC4000_DTV6; type = DTV6; break; @@ -1173,23 +1173,23 @@ static int xc4000_set_params(struct dvb_frontend *fe) dprintk(1, "%s() OFDM\n", __func__); if (bw == 0) { if (c->frequency < 400000000) { - priv->freq_hz = c->frequency - 2250000; + priv->freq_offset = 2250000; } else { - priv->freq_hz = c->frequency - 2750000; + priv->freq_offset = 2750000; } priv->video_standard = XC4000_DTV7_8; type = DTV78; } else if (bw <= 6000000) { priv->video_standard = XC4000_DTV6; - priv->freq_hz = c->frequency - 1750000; + priv->freq_offset = 1750000; type = DTV6; } else if (bw <= 7000000) { priv->video_standard = XC4000_DTV7; - priv->freq_hz = c->frequency - 2250000; + priv->freq_offset = 2250000; type = DTV7; } else { priv->video_standard = XC4000_DTV8; - priv->freq_hz = c->frequency - 2750000; + priv->freq_offset = 2750000; type = DTV8; } priv->rf_mode = XC_RF_MODE_AIR; @@ -1200,6 +1200,8 @@ static int xc4000_set_params(struct dvb_frontend *fe) goto fail; } + priv->freq_hz = c->frequency - priv->freq_offset; + dprintk(1, "%s() frequency=%d (compensated)\n", __func__, priv->freq_hz); @@ -1520,7 +1522,7 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc4000_priv *priv = fe->tuner_priv; - *freq = priv->freq_hz; + *freq = priv->freq_hz + priv->freq_offset; if (debug) { mutex_lock(&priv->lock); diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c index 5cd09a681b6a..b2d9e9cb97f7 100644 --- a/drivers/media/tuners/xc5000.c +++ b/drivers/media/tuners/xc5000.c @@ -55,7 +55,7 @@ struct xc5000_priv { u32 if_khz; u16 xtal_khz; - u32 freq_hz; + u32 freq_hz, freq_offset; u32 bandwidth; u8 video_standard; u8 rf_mode; @@ -755,13 +755,13 @@ static int xc5000_set_params(struct dvb_frontend *fe) case SYS_ATSC: dprintk(1, "%s() VSB modulation\n", __func__); priv->rf_mode = XC_RF_MODE_AIR; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; priv->video_standard = DTV6; break; case SYS_DVBC_ANNEX_B: dprintk(1, "%s() QAM modulation\n", __func__); priv->rf_mode = XC_RF_MODE_CABLE; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; priv->video_standard = DTV6; break; case SYS_ISDBT: @@ -776,15 +776,15 @@ static int xc5000_set_params(struct dvb_frontend *fe) switch (bw) { case 6000000: priv->video_standard = DTV6; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; break; case 7000000: priv->video_standard = DTV7; - priv->freq_hz = freq - 2250000; + priv->freq_offset = 2250000; break; case 8000000: priv->video_standard = DTV8; - priv->freq_hz = freq - 2750000; + priv->freq_offset = 2750000; break; default: printk(KERN_ERR "xc5000 bandwidth not set!\n"); @@ -798,15 +798,15 @@ static int xc5000_set_params(struct dvb_frontend *fe) priv->rf_mode = XC_RF_MODE_CABLE; if (bw <= 6000000) { priv->video_standard = DTV6; - priv->freq_hz = freq - 1750000; + priv->freq_offset = 1750000; b = 6; } else if (bw <= 7000000) { priv->video_standard = DTV7; - priv->freq_hz = freq - 2250000; + priv->freq_offset = 2250000; b = 7; } else { priv->video_standard = DTV7_8; - priv->freq_hz = freq - 2750000; + priv->freq_offset = 2750000; b = 8; } dprintk(1, "%s() Bandwidth %dMHz (%d)\n", __func__, @@ -817,6 +817,8 @@ static int xc5000_set_params(struct dvb_frontend *fe) return -EINVAL; } + priv->freq_hz = freq - priv->freq_offset; + dprintk(1, "%s() frequency=%d (compensated to %d)\n", __func__, freq, priv->freq_hz); @@ -1067,7 +1069,7 @@ static int xc5000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc5000_priv *priv = fe->tuner_priv; dprintk(1, "%s()\n", __func__); - *freq = priv->freq_hz; + *freq = priv->freq_hz + priv->freq_offset; return 0; } diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index f6154546b5c0..7ed75efa1c36 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -787,11 +787,27 @@ static int au0828_i2s_init(struct au0828_dev *dev) /* * Auvitek au0828 analog stream enable - * Please set interface0 to AS5 before enable the stream */ static int au0828_analog_stream_enable(struct au0828_dev *d) { + struct usb_interface *iface; + int ret; + dprintk(1, "au0828_analog_stream_enable called\n"); + + iface = usb_ifnum_to_if(d->usbdev, 0); + if (iface && iface->cur_altsetting->desc.bAlternateSetting != 5) { + dprintk(1, "Changing intf#0 to alt 5\n"); + /* set au0828 interface0 to AS5 here again */ + ret = usb_set_interface(d->usbdev, 0, 5); + if (ret < 0) { + printk(KERN_INFO "Au0828 can't set alt setting to 5!\n"); + return -EBUSY; + } + } + + /* FIXME: size should be calculated using d->width, d->height */ + au0828_writereg(d, AU0828_SENSORCTRL_VBI_103, 0x00); au0828_writereg(d, 0x106, 0x00); /* set x position */ @@ -1002,15 +1018,6 @@ static int au0828_v4l2_open(struct file *filp) return -ERESTARTSYS; } if (dev->users == 0) { - /* set au0828 interface0 to AS5 here again */ - ret = usb_set_interface(dev->usbdev, 0, 5); - if (ret < 0) { - mutex_unlock(&dev->lock); - printk(KERN_INFO "Au0828 can't set alternate to 5!\n"); - kfree(fh); - return -EBUSY; - } - au0828_analog_stream_enable(dev); au0828_analog_stream_reset(dev); @@ -1252,13 +1259,6 @@ static int au0828_set_format(struct au0828_dev *dev, unsigned int cmd, } } - /* set au0828 interface0 to AS5 here again */ - ret = usb_set_interface(dev->usbdev, 0, 5); - if (ret < 0) { - printk(KERN_INFO "Au0828 can't set alt setting to 5!\n"); - return -EBUSY; - } - au0828_analog_stream_enable(dev); return 0; diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c index 8ede8ea762e6..88228f735342 100644 --- a/drivers/media/usb/dvb-usb-v2/af9035.c +++ b/drivers/media/usb/dvb-usb-v2/af9035.c @@ -1541,6 +1541,10 @@ static const struct usb_device_id af9035_id_table[] = { &af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) }, { DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900, &af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) }, + { DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_78E, + &af9035_props, "PCTV 78e", RC_MAP_IT913X_V1) }, + { DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_79E, + &af9035_props, "PCTV 79e", RC_MAP_IT913X_V2) }, { } }; MODULE_DEVICE_TABLE(usb, af9035_id_table); diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index fda5c64ba0e8..fd1312d0b078 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -1382,6 +1382,7 @@ static const struct dvb_usb_device_properties rtl2832u_props = { }; static const struct usb_device_id rtl28xxu_id_table[] = { + /* RTL2831U devices: */ { DVB_USB_DEVICE(USB_VID_REALTEK, USB_PID_REALTEK_RTL2831U, &rtl2831u_props, "Realtek RTL2831U reference design", NULL) }, { DVB_USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_FREECOM_DVBT, @@ -1389,6 +1390,7 @@ static const struct usb_device_id rtl28xxu_id_table[] = { { DVB_USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_FREECOM_DVBT_2, &rtl2831u_props, "Freecom USB2.0 DVB-T", NULL) }, + /* RTL2832U devices: */ { DVB_USB_DEVICE(USB_VID_REALTEK, 0x2832, &rtl2832u_props, "Realtek RTL2832U reference design", NULL) }, { DVB_USB_DEVICE(USB_VID_REALTEK, 0x2838, @@ -1401,6 +1403,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = { &rtl2832u_props, "TerraTec NOXON DAB Stick", NULL) }, { DVB_USB_DEVICE(USB_VID_TERRATEC, USB_PID_NOXON_DAB_STICK_REV2, &rtl2832u_props, "TerraTec NOXON DAB Stick (rev 2)", NULL) }, + { DVB_USB_DEVICE(USB_VID_TERRATEC, USB_PID_NOXON_DAB_STICK_REV3, + &rtl2832u_props, "TerraTec NOXON DAB Stick (rev 3)", NULL) }, { DVB_USB_DEVICE(USB_VID_GTEK, USB_PID_TREKSTOR_TERRES_2_0, &rtl2832u_props, "Trekstor DVB-T Stick Terres 2.0", NULL) }, { DVB_USB_DEVICE(USB_VID_DEXATEK, 0x1101, @@ -1429,7 +1433,16 @@ static const struct usb_device_id rtl28xxu_id_table[] = { &rtl2832u_props, "Leadtek WinFast DTV Dongle mini", NULL) }, { DVB_USB_DEVICE(USB_VID_GTEK, USB_PID_CPYTO_REDI_PC50A, &rtl2832u_props, "Crypto ReDi PC 50 A", NULL) }, - + { DVB_USB_DEVICE(USB_VID_KYE, 0x707f, + &rtl2832u_props, "Genius TVGo DVB-T03", NULL) }, + { DVB_USB_DEVICE(USB_VID_KWORLD_2, 0xd395, + &rtl2832u_props, "Peak DVB-T USB", NULL) }, + { DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_SVEON_STV20_RTL2832U, + &rtl2832u_props, "Sveon STV20", NULL) }, + { DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_SVEON_STV27, + &rtl2832u_props, "Sveon STV27", NULL) }, + + /* RTL2832P devices: */ { DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131, &rtl2832u_props, "Astrometa DVB-T2", NULL) }, { } diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c index 05e9bd11a3ff..dfdfa772eb1e 100644 --- a/drivers/media/usb/em28xx/em28xx-audio.c +++ b/drivers/media/usb/em28xx/em28xx-audio.c @@ -252,7 +252,7 @@ static int snd_em28xx_capture_open(struct snd_pcm_substream *substream) { struct em28xx *dev = snd_pcm_substream_chip(substream); struct snd_pcm_runtime *runtime = substream->runtime; - int ret = 0; + int nonblock, ret = 0; if (!dev) { em28xx_err("BUG: em28xx can't find device struct." @@ -265,15 +265,15 @@ static int snd_em28xx_capture_open(struct snd_pcm_substream *substream) dprintk("opening device and trying to acquire exclusive lock\n"); + nonblock = !!(substream->f_flags & O_NONBLOCK); + if (nonblock) { + if (!mutex_trylock(&dev->lock)) + return -EAGAIN; + } else + mutex_lock(&dev->lock); + runtime->hw = snd_em28xx_hw_capture; if ((dev->alt == 0 || dev->is_audio_only) && dev->adev.users == 0) { - int nonblock = !!(substream->f_flags & O_NONBLOCK); - - if (nonblock) { - if (!mutex_trylock(&dev->lock)) - return -EAGAIN; - } else - mutex_lock(&dev->lock); if (dev->is_audio_only) /* vendor audio is on a separate interface */ dev->alt = 1; @@ -299,11 +299,11 @@ static int snd_em28xx_capture_open(struct snd_pcm_substream *substream) ret = em28xx_audio_analog_set(dev); if (ret < 0) goto err; - - dev->adev.users++; - mutex_unlock(&dev->lock); } + dev->adev.users++; + mutex_unlock(&dev->lock); + /* Dynamically adjust the period size */ snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c index 4d97a76cc3b0..c1a3f8f95750 100644 --- a/drivers/media/usb/em28xx/em28xx-cards.c +++ b/drivers/media/usb/em28xx/em28xx-cards.c @@ -2993,16 +2993,6 @@ static int em28xx_init_dev(struct em28xx *dev, struct usb_device *udev, } } - if (dev->chip_id == CHIP_ID_EM2870 || - dev->chip_id == CHIP_ID_EM2874 || - dev->chip_id == CHIP_ID_EM28174 || - dev->chip_id == CHIP_ID_EM28178) { - /* Digital only device - don't load any alsa module */ - dev->audio_mode.has_audio = false; - dev->has_audio_class = false; - dev->has_alsa_audio = false; - } - if (chip_name != default_chip_name) printk(KERN_INFO DRIVER_NAME ": chip ID is %s\n", chip_name); @@ -3272,7 +3262,6 @@ static int em28xx_usb_probe(struct usb_interface *interface, dev->alt = -1; dev->is_audio_only = has_audio && !(has_video || has_dvb); dev->has_alsa_audio = has_audio; - dev->audio_mode.has_audio = has_audio; dev->has_video = has_video; dev->ifnum = ifnum; diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c index 898fb9bd88a2..97fd881a4e7b 100644 --- a/drivers/media/usb/em28xx/em28xx-core.c +++ b/drivers/media/usb/em28xx/em28xx-core.c @@ -506,8 +506,18 @@ int em28xx_audio_setup(struct em28xx *dev) int vid1, vid2, feat, cfg; u32 vid; - if (!dev->audio_mode.has_audio) + if (dev->chip_id == CHIP_ID_EM2870 || + dev->chip_id == CHIP_ID_EM2874 || + dev->chip_id == CHIP_ID_EM28174 || + dev->chip_id == CHIP_ID_EM28178) { + /* Digital only device - don't load any alsa module */ + dev->audio_mode.has_audio = false; + dev->has_audio_class = false; + dev->has_alsa_audio = false; return 0; + } + + dev->audio_mode.has_audio = true; /* See how this device is configured */ cfg = em28xx_read_reg(dev, EM28XX_R00_CHIPCFG); diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c index a0a669e81362..1373cfa4e974 100644 --- a/drivers/media/usb/em28xx/em28xx-dvb.c +++ b/drivers/media/usb/em28xx/em28xx-dvb.c @@ -693,7 +693,8 @@ static void pctv_520e_init(struct em28xx *dev) static int em28xx_pctv_290e_set_lna(struct dvb_frontend *fe) { struct dtv_frontend_properties *c = &fe->dtv_property_cache; - struct em28xx *dev = fe->dvb->priv; + struct em28xx_i2c_bus *i2c_bus = fe->dvb->priv; + struct em28xx *dev = i2c_bus->dev; #ifdef CONFIG_GPIOLIB struct em28xx_dvb *dvb = dev->dvb; int ret; diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c index c3c928937dcd..e24ee08e634e 100644 --- a/drivers/media/usb/em28xx/em28xx-video.c +++ b/drivers/media/usb/em28xx/em28xx-video.c @@ -953,13 +953,16 @@ static int em28xx_stop_streaming(struct vb2_queue *vq) } spin_lock_irqsave(&dev->slock, flags); + if (dev->usb_ctl.vid_buf != NULL) { + vb2_buffer_done(&dev->usb_ctl.vid_buf->vb, VB2_BUF_STATE_ERROR); + dev->usb_ctl.vid_buf = NULL; + } while (!list_empty(&vidq->active)) { struct em28xx_buffer *buf; buf = list_entry(vidq->active.next, struct em28xx_buffer, list); list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); } - dev->usb_ctl.vid_buf = NULL; spin_unlock_irqrestore(&dev->slock, flags); return 0; @@ -981,13 +984,16 @@ int em28xx_stop_vbi_streaming(struct vb2_queue *vq) } spin_lock_irqsave(&dev->slock, flags); + if (dev->usb_ctl.vbi_buf != NULL) { + vb2_buffer_done(&dev->usb_ctl.vbi_buf->vb, VB2_BUF_STATE_ERROR); + dev->usb_ctl.vbi_buf = NULL; + } while (!list_empty(&vbiq->active)) { struct em28xx_buffer *buf; buf = list_entry(vbiq->active.next, struct em28xx_buffer, list); list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); } - dev->usb_ctl.vbi_buf = NULL; spin_unlock_irqrestore(&dev->slock, flags); return 0; diff --git a/drivers/media/usb/gspca/pac7302.c b/drivers/media/usb/gspca/pac7302.c index 2fd1c5e31a0f..339adce7c7a5 100644 --- a/drivers/media/usb/gspca/pac7302.c +++ b/drivers/media/usb/gspca/pac7302.c @@ -928,6 +928,7 @@ static const struct usb_device_id device_table[] = { {USB_DEVICE(0x093a, 0x2620)}, {USB_DEVICE(0x093a, 0x2621)}, {USB_DEVICE(0x093a, 0x2622), .driver_info = FL_VFLIP}, + {USB_DEVICE(0x093a, 0x2623), .driver_info = FL_VFLIP}, {USB_DEVICE(0x093a, 0x2624), .driver_info = FL_VFLIP}, {USB_DEVICE(0x093a, 0x2625)}, {USB_DEVICE(0x093a, 0x2626)}, diff --git a/drivers/media/usb/gspca/sn9c20x.c b/drivers/media/usb/gspca/sn9c20x.c index 2a38621cf718..41a9a892f79c 100644 --- a/drivers/media/usb/gspca/sn9c20x.c +++ b/drivers/media/usb/gspca/sn9c20x.c @@ -2359,6 +2359,7 @@ static const struct usb_device_id device_table[] = { {USB_DEVICE(0x045e, 0x00f4), SN9C20X(OV9650, 0x30, 0)}, {USB_DEVICE(0x145f, 0x013d), SN9C20X(OV7660, 0x21, 0)}, {USB_DEVICE(0x0458, 0x7029), SN9C20X(HV7131R, 0x11, 0)}, + {USB_DEVICE(0x0458, 0x7045), SN9C20X(MT9M112, 0x5d, LED_REVERSE)}, {USB_DEVICE(0x0458, 0x704a), SN9C20X(MT9M112, 0x5d, 0)}, {USB_DEVICE(0x0458, 0x704c), SN9C20X(MT9M112, 0x5d, 0)}, {USB_DEVICE(0xa168, 0x0610), SN9C20X(HV7131R, 0x11, 0)}, diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c index 0500c4175d5f..6bce01a674f9 100644 --- a/drivers/media/usb/hdpvr/hdpvr-video.c +++ b/drivers/media/usb/hdpvr/hdpvr-video.c @@ -82,7 +82,7 @@ static void hdpvr_read_bulk_callback(struct urb *urb) } /*=========================================================================*/ -/* bufffer bits */ +/* buffer bits */ /* function expects dev->io_mutex to be hold by caller */ int hdpvr_cancel_queue(struct hdpvr_device *dev) @@ -926,7 +926,7 @@ static int hdpvr_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_MPEG_AUDIO_ENCODING: if (dev->flags & HDPVR_FLAG_AC3_CAP) { opt->audio_codec = ctrl->val; - return hdpvr_set_audio(dev, opt->audio_input, + return hdpvr_set_audio(dev, opt->audio_input + 1, opt->audio_codec); } return 0; @@ -1198,7 +1198,7 @@ int hdpvr_register_videodev(struct hdpvr_device *dev, struct device *parent, v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops, V4L2_CID_MPEG_AUDIO_ENCODING, ac3 ? V4L2_MPEG_AUDIO_ENCODING_AC3 : V4L2_MPEG_AUDIO_ENCODING_AAC, - 0x7, V4L2_MPEG_AUDIO_ENCODING_AAC); + 0x7, ac3 ? dev->options.audio_codec : V4L2_MPEG_AUDIO_ENCODING_AAC); v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops, V4L2_CID_MPEG_VIDEO_ENCODING, V4L2_MPEG_VIDEO_ENCODING_MPEG_4_AVC, 0x3, diff --git a/drivers/media/usb/stk1160/stk1160-core.c b/drivers/media/usb/stk1160/stk1160-core.c index 34a26e0cfe77..03504dcf3c52 100644 --- a/drivers/media/usb/stk1160/stk1160-core.c +++ b/drivers/media/usb/stk1160/stk1160-core.c @@ -67,17 +67,25 @@ int stk1160_read_reg(struct stk1160 *dev, u16 reg, u8 *value) { int ret; int pipe = usb_rcvctrlpipe(dev->udev, 0); + u8 *buf; *value = 0; + + buf = kmalloc(sizeof(u8), GFP_KERNEL); + if (!buf) + return -ENOMEM; ret = usb_control_msg(dev->udev, pipe, 0x00, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - 0x00, reg, value, sizeof(u8), HZ); + 0x00, reg, buf, sizeof(u8), HZ); if (ret < 0) { stk1160_err("read failed on reg 0x%x (%d)\n", reg, ret); + kfree(buf); return ret; } + *value = *buf; + kfree(buf); return 0; } diff --git a/drivers/media/usb/stk1160/stk1160.h b/drivers/media/usb/stk1160/stk1160.h index 05b05b160e1e..abdea484c998 100644 --- a/drivers/media/usb/stk1160/stk1160.h +++ b/drivers/media/usb/stk1160/stk1160.h @@ -143,7 +143,6 @@ struct stk1160 { int num_alt; struct stk1160_isoc_ctl isoc_ctl; - char urb_buf[255]; /* urb control msg buffer */ /* frame properties */ int width; /* current frame width */ diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index c3bb2502225b..753ad4cfc118 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2210,6 +2210,15 @@ static struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = UVC_QUIRK_PROBE_DEF }, + /* Dell XPS M1330 (OmniVision OV7670 webcam) */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x05a9, + .idProduct = 0x7670, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_QUIRK_PROBE_DEF }, /* Apple Built-In iSight */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index 898c208889cd..2ef5b0f8ef77 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -361,6 +361,14 @@ static int uvc_commit_video(struct uvc_streaming *stream, * Clocks and timestamps */ +static inline void uvc_video_get_ts(struct timespec *ts) +{ + if (uvc_clock_param == CLOCK_MONOTONIC) + ktime_get_ts(ts); + else + ktime_get_real_ts(ts); +} + static void uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, const __u8 *data, int len) @@ -420,7 +428,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, stream->clock.last_sof = dev_sof; host_sof = usb_get_current_frame_number(stream->dev->udev); - ktime_get_ts(&ts); + uvc_video_get_ts(&ts); /* The UVC specification allows device implementations that can't obtain * the USB frame number to keep their own frame counters as long as they @@ -1011,10 +1019,7 @@ static int uvc_video_decode_start(struct uvc_streaming *stream, return -ENODATA; } - if (uvc_clock_param == CLOCK_MONOTONIC) - ktime_get_ts(&ts); - else - ktime_get_real_ts(&ts); + uvc_video_get_ts(&ts); buf->buf.v4l2_buf.sequence = stream->sequence; buf->buf.v4l2_buf.timestamp.tv_sec = ts.tv_sec; @@ -1847,7 +1852,25 @@ int uvc_video_enable(struct uvc_streaming *stream, int enable) if (!enable) { uvc_uninit_video(stream, 1); - usb_set_interface(stream->dev->udev, stream->intfnum, 0); + if (stream->intf->num_altsetting > 1) { + usb_set_interface(stream->dev->udev, + stream->intfnum, 0); + } else { + /* UVC doesn't specify how to inform a bulk-based device + * when the video stream is stopped. Windows sends a + * CLEAR_FEATURE(HALT) request to the video streaming + * bulk endpoint, mimic the same behaviour. + */ + unsigned int epnum = stream->header.bEndpointAddress + & USB_ENDPOINT_NUMBER_MASK; + unsigned int dir = stream->header.bEndpointAddress + & USB_ENDPOINT_DIR_MASK; + unsigned int pipe; + + pipe = usb_sndbulkpipe(stream->dev->udev, epnum) | dir; + usb_clear_halt(stream->dev->udev, pipe); + } + uvc_queue_enable(&stream->queue, 0); uvc_video_clock_cleanup(stream); return 0; diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 433d6d77942e..c5521cec933b 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -431,16 +431,13 @@ static unsigned int clamp_align(unsigned int x, unsigned int min, /* Bits that must be zero to be aligned */ unsigned int mask = ~((1 << align) - 1); + /* Clamp to aligned min and max */ + x = clamp(x, (min + ~mask) & mask, max & mask); + /* Round to nearest aligned value */ if (align) x = (x + (1 << (align - 1))) & mask; - /* Clamp to aligned value of min and max */ - if (x < min) - x = (min + ~mask) & mask; - else if (x > max) - x = max & mask; - return x; } diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 8f7a6a454a4c..fca336b65351 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -178,6 +178,9 @@ struct v4l2_create_buffers32 { static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up) { + if (get_user(kp->type, &up->type)) + return -EFAULT; + switch (kp->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_OUTPUT: @@ -204,17 +207,16 @@ static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __us static int get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up) { - if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)) || - get_user(kp->type, &up->type)) - return -EFAULT; + if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32))) + return -EFAULT; return __get_v4l2_format32(kp, up); } static int get_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up) { if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_create_buffers32)) || - copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format.fmt))) - return -EFAULT; + copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format))) + return -EFAULT; return __get_v4l2_format32(&kp->format, &up->format); } @@ -787,8 +789,8 @@ static int put_v4l2_subdev_edid32(struct v4l2_subdev_edid *kp, struct v4l2_subde #define VIDIOC_DQBUF32 _IOWR('V', 17, struct v4l2_buffer32) #define VIDIOC_ENUMSTD32 _IOWR('V', 25, struct v4l2_standard32) #define VIDIOC_ENUMINPUT32 _IOWR('V', 26, struct v4l2_input32) -#define VIDIOC_SUBDEV_G_EDID32 _IOWR('V', 63, struct v4l2_subdev_edid32) -#define VIDIOC_SUBDEV_S_EDID32 _IOWR('V', 64, struct v4l2_subdev_edid32) +#define VIDIOC_SUBDEV_G_EDID32 _IOWR('V', 40, struct v4l2_subdev_edid32) +#define VIDIOC_SUBDEV_S_EDID32 _IOWR('V', 41, struct v4l2_subdev_edid32) #define VIDIOC_TRY_FMT32 _IOWR('V', 64, struct v4l2_format32) #define VIDIOC_G_EXT_CTRLS32 _IOWR('V', 71, struct v4l2_ext_controls32) #define VIDIOC_S_EXT_CTRLS32 _IOWR('V', 72, struct v4l2_ext_controls32) diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c index f7902fe8a526..78d99b137d91 100644 --- a/drivers/media/v4l2-core/v4l2-dv-timings.c +++ b/drivers/media/v4l2-core/v4l2-dv-timings.c @@ -26,6 +26,10 @@ #include <linux/v4l2-dv-timings.h> #include <media/v4l2-dv-timings.h> +MODULE_AUTHOR("Hans Verkuil"); +MODULE_DESCRIPTION("V4L2 DV Timings Helper Functions"); +MODULE_LICENSE("GPL"); + const struct v4l2_dv_timings v4l2_dv_timings_presets[] = { V4L2_DV_BT_CEA_640X480P59_94, V4L2_DV_BT_CEA_720X480I59_94, @@ -591,10 +595,10 @@ struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait) aspect.denominator = 9; } else if (ratio == 34) { aspect.numerator = 4; - aspect.numerator = 3; + aspect.denominator = 3; } else if (ratio == 68) { aspect.numerator = 15; - aspect.numerator = 9; + aspect.denominator = 9; } else { aspect.numerator = hor_landscape + 99; aspect.denominator = 100; diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index a127925c9d61..06faea4d60ee 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -745,6 +745,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) * to the userspace. */ req->count = allocated_buffers; + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); return 0; } @@ -793,6 +794,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create memset(q->plane_sizes, 0, sizeof(q->plane_sizes)); memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx)); q->memory = create->memory; + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); } num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers); @@ -1447,6 +1449,7 @@ static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b) * dequeued in dqbuf. */ list_add_tail(&vb->queued_entry, &q->queued_list); + q->waiting_for_buffers = false; vb->state = VB2_BUF_STATE_QUEUED; /* @@ -1841,6 +1844,7 @@ static int vb2_internal_streamoff(struct vb2_queue *q, enum v4l2_buf_type type) * and videobuf, effectively returning control over them to userspace. */ __vb2_queue_cancel(q); + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); dprintk(3, "Streamoff successful\n"); return 0; @@ -2150,9 +2154,16 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait) } /* - * There is nothing to wait for if no buffers have already been queued. + * There is nothing to wait for if the queue isn't streaming. */ - if (list_empty(&q->queued_list)) + if (!vb2_is_streaming(q)) + return res | POLLERR; + /* + * For compatibility with vb1: if QBUF hasn't been called yet, then + * return POLLERR as well. This only affects capture queues, output + * queues will always initialize waiting_for_buffers to false. + */ + if (q->waiting_for_buffers) return res | POLLERR; if (list_empty(&q->done_list)) diff --git a/drivers/memory/mvebu-devbus.c b/drivers/memory/mvebu-devbus.c index 110c03627051..b59a17fb7c3e 100644 --- a/drivers/memory/mvebu-devbus.c +++ b/drivers/memory/mvebu-devbus.c @@ -108,8 +108,19 @@ static int devbus_set_timing_params(struct devbus *devbus, node->full_name); return err; } - /* Convert bit width to byte width */ - r.bus_width /= 8; + + /* + * The bus width is encoded into the register as 0 for 8 bits, + * and 1 for 16 bits, so we do the necessary conversion here. + */ + if (r.bus_width == 8) + r.bus_width = 0; + else if (r.bus_width == 16) + r.bus_width = 1; + else { + dev_err(devbus->dev, "invalid bus width %d\n", r.bus_width); + return -EINVAL; + } err = get_timing_param_ps(devbus, node, "devbus,badr-skew-ps", &r.badr_skew); diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c index 5653e505f91f..424f51d1e2ce 100644 --- a/drivers/message/fusion/mptspi.c +++ b/drivers/message/fusion/mptspi.c @@ -1422,6 +1422,11 @@ mptspi_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto out_mptspi_probe; } + /* VMWare emulation doesn't properly implement WRITE_SAME + */ + if (pdev->subsystem_vendor == 0x15AD) + sh->no_write_same = 1; + spin_lock_irqsave(&ioc->FreeQlock, flags); /* Attach the SCSI Host to the IOC structure diff --git a/drivers/mfd/88pm800.c b/drivers/mfd/88pm800.c index 7dca1e640970..841717a2842c 100644 --- a/drivers/mfd/88pm800.c +++ b/drivers/mfd/88pm800.c @@ -571,7 +571,7 @@ static int pm800_probe(struct i2c_client *client, ret = pm800_pages_init(chip); if (ret) { dev_err(&client->dev, "pm800_pages_init failed!\n"); - goto err_page_init; + goto err_device_init; } ret = device_800_init(chip, pdata); @@ -587,7 +587,6 @@ static int pm800_probe(struct i2c_client *client, err_device_init: pm800_pages_exit(chip); -err_page_init: err_subchip_alloc: pm80x_deinit(); out_init: diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c index c9b1f6422941..bcfc9e85b4a0 100644 --- a/drivers/mfd/88pm860x-core.c +++ b/drivers/mfd/88pm860x-core.c @@ -1179,12 +1179,18 @@ static int pm860x_probe(struct i2c_client *client, chip->companion_addr = pdata->companion_addr; chip->companion = i2c_new_dummy(chip->client->adapter, chip->companion_addr); + if (!chip->companion) { + dev_err(&client->dev, + "Failed to allocate I2C companion device\n"); + return -ENODEV; + } chip->regmap_companion = regmap_init_i2c(chip->companion, &pm860x_regmap_config); if (IS_ERR(chip->regmap_companion)) { ret = PTR_ERR(chip->regmap_companion); dev_err(&chip->companion->dev, "Failed to allocate register map: %d\n", ret); + i2c_unregister_device(chip->companion); return ret; } i2c_set_clientdata(chip->companion, chip); diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c index d3e23278d299..38917a822335 100644 --- a/drivers/mfd/kempld-core.c +++ b/drivers/mfd/kempld-core.c @@ -322,9 +322,12 @@ static int kempld_detect_device(struct kempld_device_data *pld) return -ENODEV; } - /* Release hardware mutex if aquired */ - if (!(index_reg & KEMPLD_MUTEX_KEY)) + /* Release hardware mutex if acquired */ + if (!(index_reg & KEMPLD_MUTEX_KEY)) { iowrite8(KEMPLD_MUTEX_KEY, pld->io_index); + /* PXT and COMe-cPC2 boards may require a second release */ + iowrite8(KEMPLD_MUTEX_KEY, pld->io_index); + } mutex_unlock(&pld->lock); diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c index f53d5823a3f7..e5fce765accb 100644 --- a/drivers/mfd/max77686.c +++ b/drivers/mfd/max77686.c @@ -121,6 +121,10 @@ static int max77686_i2c_probe(struct i2c_client *i2c, dev_info(max77686->dev, "device found\n"); max77686->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC); + if (!max77686->rtc) { + dev_err(max77686->dev, "Failed to allocate I2C device for RTC\n"); + return -ENODEV; + } i2c_set_clientdata(max77686->rtc, max77686); max77686_irq_init(max77686); diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c index e0859987ab6b..c5535f018466 100644 --- a/drivers/mfd/max77693.c +++ b/drivers/mfd/max77693.c @@ -148,9 +148,18 @@ static int max77693_i2c_probe(struct i2c_client *i2c, dev_info(max77693->dev, "device ID: 0x%x\n", reg_data); max77693->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC); + if (!max77693->muic) { + dev_err(max77693->dev, "Failed to allocate I2C device for MUIC\n"); + return -ENODEV; + } i2c_set_clientdata(max77693->muic, max77693); max77693->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC); + if (!max77693->haptic) { + dev_err(max77693->dev, "Failed to allocate I2C device for Haptic\n"); + ret = -ENODEV; + goto err_i2c_haptic; + } i2c_set_clientdata(max77693->haptic, max77693); /* @@ -184,8 +193,9 @@ err_mfd: max77693_irq_exit(max77693); err_irq: err_regmap_muic: - i2c_unregister_device(max77693->muic); i2c_unregister_device(max77693->haptic); +err_i2c_haptic: + i2c_unregister_device(max77693->muic); return ret; } diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c index 176aa26fc787..a83eed5c15ca 100644 --- a/drivers/mfd/max8925-i2c.c +++ b/drivers/mfd/max8925-i2c.c @@ -181,9 +181,18 @@ static int max8925_probe(struct i2c_client *client, mutex_init(&chip->io_lock); chip->rtc = i2c_new_dummy(chip->i2c->adapter, RTC_I2C_ADDR); + if (!chip->rtc) { + dev_err(chip->dev, "Failed to allocate I2C device for RTC\n"); + return -ENODEV; + } i2c_set_clientdata(chip->rtc, chip); chip->adc = i2c_new_dummy(chip->i2c->adapter, ADC_I2C_ADDR); + if (!chip->adc) { + dev_err(chip->dev, "Failed to allocate I2C device for ADC\n"); + i2c_unregister_device(chip->rtc); + return -ENODEV; + } i2c_set_clientdata(chip->adc, chip); device_init_wakeup(&client->dev, 1); diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c index 5adede0fb04c..8cf7a015cfe5 100644 --- a/drivers/mfd/max8997.c +++ b/drivers/mfd/max8997.c @@ -208,10 +208,26 @@ static int max8997_i2c_probe(struct i2c_client *i2c, mutex_init(&max8997->iolock); max8997->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC); + if (!max8997->rtc) { + dev_err(max8997->dev, "Failed to allocate I2C device for RTC\n"); + return -ENODEV; + } i2c_set_clientdata(max8997->rtc, max8997); + max8997->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC); + if (!max8997->haptic) { + dev_err(max8997->dev, "Failed to allocate I2C device for Haptic\n"); + ret = -ENODEV; + goto err_i2c_haptic; + } i2c_set_clientdata(max8997->haptic, max8997); + max8997->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC); + if (!max8997->muic) { + dev_err(max8997->dev, "Failed to allocate I2C device for MUIC\n"); + ret = -ENODEV; + goto err_i2c_muic; + } i2c_set_clientdata(max8997->muic, max8997); pm_runtime_set_active(max8997->dev); @@ -239,7 +255,9 @@ static int max8997_i2c_probe(struct i2c_client *i2c, err_mfd: mfd_remove_devices(max8997->dev); i2c_unregister_device(max8997->muic); +err_i2c_muic: i2c_unregister_device(max8997->haptic); +err_i2c_haptic: i2c_unregister_device(max8997->rtc); return ret; } diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c index 5d5e186b5d8b..592db06098e6 100644 --- a/drivers/mfd/max8998.c +++ b/drivers/mfd/max8998.c @@ -215,6 +215,10 @@ static int max8998_i2c_probe(struct i2c_client *i2c, mutex_init(&max8998->iolock); max8998->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR); + if (!max8998->rtc) { + dev_err(&i2c->dev, "Failed to allocate I2C device for RTC\n"); + return -ENODEV; + } i2c_set_clientdata(max8998->rtc, max8998); max8998_irq_init(max8998); diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index 90b630ccc8bc..0aefe501fd3c 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -445,7 +445,7 @@ static unsigned omap_usbhs_rev1_hostconfig(struct usbhs_hcd_omap *omap, for (i = 0; i < omap->nports; i++) { if (is_ehci_phy_mode(pdata->port_mode[i])) { - reg &= OMAP_UHH_HOSTCONFIG_ULPI_BYPASS; + reg &= ~OMAP_UHH_HOSTCONFIG_ULPI_BYPASS; break; } } diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c index 1d15735f9ef9..89b4c4216d0c 100644 --- a/drivers/mfd/rtsx_pcr.c +++ b/drivers/mfd/rtsx_pcr.c @@ -1177,7 +1177,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, pcr->msi_en = msi_en; if (pcr->msi_en) { ret = pci_enable_msi(pcidev); - if (ret < 0) + if (ret) pcr->msi_en = false; } diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c index 714e2135210e..a76cd85a2868 100644 --- a/drivers/mfd/sec-core.c +++ b/drivers/mfd/sec-core.c @@ -252,6 +252,10 @@ static int sec_pmic_probe(struct i2c_client *i2c, } sec_pmic->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR); + if (!sec_pmic->rtc) { + dev_err(&i2c->dev, "Failed to allocate I2C for RTC\n"); + return -ENODEV; + } i2c_set_clientdata(sec_pmic->rtc, sec_pmic); sec_pmic->regmap_rtc = devm_regmap_init_i2c(sec_pmic->rtc, diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index d4e860413bb5..e87a2485468f 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -54,11 +54,11 @@ void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val) unsigned long flags; spin_lock_irqsave(&tsadc->reg_lock, flags); - tsadc->reg_se_cache = val; + tsadc->reg_se_cache |= val; if (tsadc->adc_waiting) wake_up(&tsadc->reg_se_wait); else if (!tsadc->adc_in_use) - tscadc_writel(tsadc, REG_SE, val); + tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache); spin_unlock_irqrestore(&tsadc->reg_lock, flags); } @@ -97,6 +97,7 @@ static void am335x_tscadc_need_adc(struct ti_tscadc_dev *tsadc) void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val) { spin_lock_irq(&tsadc->reg_lock); + tsadc->reg_se_cache |= val; am335x_tscadc_need_adc(tsadc); tscadc_writel(tsadc, REG_SE, val); diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c index 1f142d76cbbc..d6573318977f 100644 --- a/drivers/mfd/tps65910.c +++ b/drivers/mfd/tps65910.c @@ -255,8 +255,10 @@ static int tps65910_irq_init(struct tps65910 *tps65910, int irq, ret = regmap_add_irq_chip(tps65910->regmap, tps65910->chip_irq, IRQF_ONESHOT, pdata->irq_base, tps6591x_irqs_chip, &tps65910->irq_data); - if (ret < 0) + if (ret < 0) { dev_warn(tps65910->dev, "Failed to add irq_chip %d\n", ret); + tps65910->chip_irq = 0; + } return ret; } diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c index ed718328eff1..e87140bef667 100644 --- a/drivers/mfd/twl-core.c +++ b/drivers/mfd/twl-core.c @@ -282,11 +282,11 @@ static struct reg_default twl4030_49_defaults[] = { static bool twl4030_49_nop_reg(struct device *dev, unsigned int reg) { switch (reg) { - case 0: - case 3: - case 40: - case 41: - case 42: + case 0x00: + case 0x03: + case 0x40: + case 0x41: + case 0x42: return false; default: return true; diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 4bc7d620d695..9a07bba3ade4 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -71,7 +71,7 @@ static int mei_cl_device_probe(struct device *dev) dev_dbg(dev, "Device probe\n"); - strncpy(id.name, dev_name(dev), sizeof(id.name)); + strlcpy(id.name, dev_name(dev), sizeof(id.name)); return driver->probe(device, &id); } diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 89a557972d1b..540fe114ec60 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -74,23 +74,69 @@ int mei_me_cl_by_id(struct mei_device *dev, u8 client_id) /** - * mei_io_list_flush - removes list entry belonging to cl. + * mei_cl_cmp_id - tells if the clients are the same * - * @list: An instance of our list structure - * @cl: host client + * @cl1: host client 1 + * @cl2: host client 2 + * + * returns true - if the clients has same host and me ids + * false - otherwise + */ +static inline bool mei_cl_cmp_id(const struct mei_cl *cl1, + const struct mei_cl *cl2) +{ + return cl1 && cl2 && + (cl1->host_client_id == cl2->host_client_id) && + (cl1->me_client_id == cl2->me_client_id); +} + +/** + * mei_io_list_flush - removes cbs belonging to cl. + * + * @list: an instance of our list structure + * @cl: host client, can be NULL for flushing the whole list + * @free: whether to free the cbs */ -void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl) +static void __mei_io_list_flush(struct mei_cl_cb *list, + struct mei_cl *cl, bool free) { struct mei_cl_cb *cb; struct mei_cl_cb *next; + /* enable removing everything if no cl is specified */ list_for_each_entry_safe(cb, next, &list->list, list) { - if (cb->cl && mei_cl_cmp_id(cl, cb->cl)) + if (!cl || (cb->cl && mei_cl_cmp_id(cl, cb->cl))) { list_del(&cb->list); + if (free) + mei_io_cb_free(cb); + } } } /** + * mei_io_list_flush - removes list entry belonging to cl. + * + * @list: An instance of our list structure + * @cl: host client + */ +static inline void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl) +{ + __mei_io_list_flush(list, cl, false); +} + + +/** + * mei_io_list_free - removes cb belonging to cl and free them + * + * @list: An instance of our list structure + * @cl: host client + */ +static inline void mei_io_list_free(struct mei_cl_cb *list, struct mei_cl *cl) +{ + __mei_io_list_flush(list, cl, true); +} + +/** * mei_io_cb_free - free mei_cb_private related memory * * @cb: mei callback struct @@ -196,8 +242,8 @@ int mei_cl_flush_queues(struct mei_cl *cl) cl_dbg(dev, cl, "remove list entry belonging to cl\n"); mei_io_list_flush(&cl->dev->read_list, cl); - mei_io_list_flush(&cl->dev->write_list, cl); - mei_io_list_flush(&cl->dev->write_waiting_list, cl); + mei_io_list_free(&cl->dev->write_list, cl); + mei_io_list_free(&cl->dev->write_waiting_list, cl); mei_io_list_flush(&cl->dev->ctrl_wr_list, cl); mei_io_list_flush(&cl->dev->ctrl_rd_list, cl); mei_io_list_flush(&cl->dev->amthif_cmd_list, cl); @@ -413,6 +459,7 @@ int mei_cl_disconnect(struct mei_cl *cl) cl_err(dev, cl, "failed to disconnect.\n"); goto free; } + cl->timer_count = MEI_CONNECT_TIMEOUT; mdelay(10); /* Wait for hardware disconnection ready */ list_add_tail(&cb->list, &dev->ctrl_rd_list.list); } else { @@ -517,6 +564,7 @@ int mei_cl_connect(struct mei_cl *cl, struct file *file) cl->timer_count = MEI_CONNECT_TIMEOUT; list_add_tail(&cb->list, &dev->ctrl_rd_list.list); } else { + cl->state = MEI_FILE_INITIALIZING; list_add_tail(&cb->list, &dev->ctrl_wr_list.list); } @@ -942,20 +990,8 @@ void mei_cl_all_wakeup(struct mei_device *dev) */ void mei_cl_all_write_clear(struct mei_device *dev) { - struct mei_cl_cb *cb, *next; - struct list_head *list; - - list = &dev->write_list.list; - list_for_each_entry_safe(cb, next, list, list) { - list_del(&cb->list); - mei_io_cb_free(cb); - } - - list = &dev->write_waiting_list.list; - list_for_each_entry_safe(cb, next, list, list) { - list_del(&cb->list); - mei_io_cb_free(cb); - } + mei_io_list_free(&dev->write_list, NULL); + mei_io_list_free(&dev->write_waiting_list, NULL); } diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index c8396e582f1c..0820e121d137 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -45,8 +45,6 @@ static inline void mei_io_list_init(struct mei_cl_cb *list) { INIT_LIST_HEAD(&list->list); } -void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl); - /* * MEI Host Client Functions */ @@ -61,22 +59,6 @@ int mei_cl_unlink(struct mei_cl *cl); int mei_cl_flush_queues(struct mei_cl *cl); struct mei_cl_cb *mei_cl_find_read_cb(struct mei_cl *cl); -/** - * mei_cl_cmp_id - tells if file private data have same id - * - * @fe1: private data of 1. file object - * @fe2: private data of 2. file object - * - * returns true - if ids are the same and not NULL - */ -static inline bool mei_cl_cmp_id(const struct mei_cl *cl1, - const struct mei_cl *cl2) -{ - return cl1 && cl2 && - (cl1->host_client_id == cl2->host_client_id) && - (cl1->me_client_id == cl2->me_client_id); -} - int mei_cl_flow_ctrl_creds(struct mei_cl *cl); diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 66f411a6e8ea..cabc04383685 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -115,6 +115,11 @@ #define MEI_DEV_ID_LPT_HR 0x8CBA /* Lynx Point H Refresh */ #define MEI_DEV_ID_WPT_LP 0x9CBA /* Wildcat Point LP */ + +/* Host Firmware Status Registers in PCI Config Space */ +#define PCI_CFG_HFS_1 0x40 +#define PCI_CFG_HFS_2 0x48 + /* * MEI HW Section */ diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 6f656c053b14..fbc4a7bbdfa9 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -164,6 +164,9 @@ static void mei_me_hw_reset_release(struct mei_device *dev) hcsr |= H_IG; hcsr &= ~H_RST; mei_hcsr_set(hw, hcsr); + + /* complete this write before we set host ready on another CPU */ + mmiowb(); } /** * mei_me_hw_reset - resets fw via mei csr register. @@ -183,8 +186,21 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) else hcsr &= ~H_IE; + dev->recvd_hw_ready = false; mei_me_reg_write(hw, H_CSR, hcsr); + /* + * Host reads the H_CSR once to ensure that the + * posted write to H_CSR completes. + */ + hcsr = mei_hcsr_read(hw); + + if ((hcsr & H_RST) == 0) + dev_warn(&dev->pdev->dev, "H_RST is not set = 0x%08X", hcsr); + + if ((hcsr & H_RDY) == H_RDY) + dev_warn(&dev->pdev->dev, "H_RDY is not cleared 0x%08X", hcsr); + if (intr_enable == false) mei_me_hw_reset_release(dev); @@ -201,6 +217,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) static void mei_me_host_set_ready(struct mei_device *dev) { struct mei_me_hw *hw = to_me_hw(dev); + hw->host_hw_state = mei_hcsr_read(hw); hw->host_hw_state |= H_IE | H_IG | H_RDY; mei_hcsr_set(hw, hw->host_hw_state); } @@ -233,10 +250,7 @@ static bool mei_me_hw_is_ready(struct mei_device *dev) static int mei_me_hw_ready_wait(struct mei_device *dev) { int err; - if (mei_me_hw_is_ready(dev)) - return 0; - dev->recvd_hw_ready = false; mutex_unlock(&dev->device_lock); err = wait_event_interruptible_timeout(dev->wait_hw_ready, dev->recvd_hw_ready, @@ -491,14 +505,13 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) /* check if we need to start the dev */ if (!mei_host_is_ready(dev)) { if (mei_hw_is_ready(dev)) { + mei_me_hw_reset_release(dev); dev_dbg(&dev->pdev->dev, "we need to start the dev.\n"); dev->recvd_hw_ready = true; wake_up_interruptible(&dev->wait_hw_ready); } else { - - dev_dbg(&dev->pdev->dev, "Reset Completed.\n"); - mei_me_hw_reset_release(dev); + dev_dbg(&dev->pdev->dev, "Spurious Interrupt\n"); } goto end; } diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index f0fbb5179f80..d36286874946 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -428,8 +428,7 @@ int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list) cl->status = 0; list_del(&cb->list); - if (MEI_WRITING == cl->writing_state && - cb->fop_type == MEI_FOP_WRITE && + if (cb->fop_type == MEI_FOP_WRITE && cl != &dev->iamthif_cl) { cl_dbg(dev, cl, "MEI WRITE COMPLETE\n"); cl->writing_state = MEI_WRITE_COMPLETE; diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 5424f8ff3f7f..cfe1789923a3 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -653,8 +653,7 @@ static unsigned int mei_poll(struct file *file, poll_table *wait) goto out; } - if (MEI_WRITE_COMPLETE == cl->writing_state) - mask |= (POLLIN | POLLRDNORM); + mask |= (POLLIN | POLLRDNORM); out: mutex_unlock(&dev->device_lock); diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c index a58320c0c049..31149010224b 100644 --- a/drivers/misc/mei/nfc.c +++ b/drivers/misc/mei/nfc.c @@ -342,9 +342,10 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length) ndev = (struct mei_nfc_dev *) cldev->priv_data; dev = ndev->cl->dev; + err = -ENOMEM; mei_buf = kzalloc(length + MEI_NFC_HEADER_SIZE, GFP_KERNEL); if (!mei_buf) - return -ENOMEM; + goto out; hdr = (struct mei_nfc_hci_hdr *) mei_buf; hdr->cmd = MEI_NFC_CMD_HCI_SEND; @@ -354,12 +355,9 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length) hdr->data_size = length; memcpy(mei_buf + MEI_NFC_HEADER_SIZE, buf, length); - err = __mei_cl_send(ndev->cl, mei_buf, length + MEI_NFC_HEADER_SIZE); if (err < 0) - return err; - - kfree(mei_buf); + goto out; if (!wait_event_interruptible_timeout(ndev->send_wq, ndev->recv_req_id == ndev->req_id, HZ)) { @@ -368,7 +366,8 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length) } else { ndev->req_id++; } - +out: + kfree(mei_buf); return err; } diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index ddadd08956f4..bf4bb74c39ff 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -100,15 +100,31 @@ static bool mei_me_quirk_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { u32 reg; - if (ent->device == MEI_DEV_ID_PBG_1) { - pci_read_config_dword(pdev, 0x48, ®); - /* make sure that bit 9 is up and bit 10 is down */ - if ((reg & 0x600) == 0x200) { - dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n"); - return false; - } + /* Cougar Point || Patsburg */ + if (ent->device == MEI_DEV_ID_CPT_1 || + ent->device == MEI_DEV_ID_PBG_1) { + pci_read_config_dword(pdev, PCI_CFG_HFS_2, ®); + /* make sure that bit 9 (NM) is up and bit 10 (DM) is down */ + if ((reg & 0x600) == 0x200) + goto no_mei; } + + /* Lynx Point */ + if (ent->device == MEI_DEV_ID_LPT_H || + ent->device == MEI_DEV_ID_LPT_W || + ent->device == MEI_DEV_ID_LPT_HR) { + /* Read ME FW Status check for SPS Firmware */ + pci_read_config_dword(pdev, PCI_CFG_HFS_1, ®); + /* if bits [19:16] = 15, running SPS Firmware */ + if ((reg & 0xf0000) == 0xf0000) + goto no_mei; + } + return true; + +no_mei: + dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n"); + return false; } /** * mei_probe - Device Initialization Routine diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index c46feda07d56..ca297d741207 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -246,6 +246,9 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host, case MMC_RSP_R1: rsp_type = SD_RSP_TYPE_R1; break; + case MMC_RSP_R1 & ~MMC_RSP_CRC: + rsp_type = SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7; + break; case MMC_RSP_R1B: rsp_type = SD_RSP_TYPE_R1b; break; @@ -339,6 +342,13 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host, } if (rsp_type == SD_RSP_TYPE_R2) { + /* + * The controller offloads the last byte {CRC-7, end bit 1'b1} + * of response type R2. Assign dummy CRC, 0, and end bit to the + * byte(ptr[16], goes into the LSB of resp[3] later). + */ + ptr[16] = 1; + for (i = 0; i < 4; i++) { cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4); dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n", diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c index 7a190fe4dff1..e5565aa5ed36 100644 --- a/drivers/mmc/host/sdhci-bcm-kona.c +++ b/drivers/mmc/host/sdhci-bcm-kona.c @@ -314,7 +314,7 @@ err_pltfm_free: return ret; } -static int __exit sdhci_bcm_kona_remove(struct platform_device *pdev) +static int sdhci_bcm_kona_remove(struct platform_device *pdev) { return sdhci_pltfm_unregister(pdev); } diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c index 0955777b6c7e..19bfa0ad70c4 100644 --- a/drivers/mmc/host/sdhci-pci.c +++ b/drivers/mmc/host/sdhci-pci.c @@ -103,6 +103,10 @@ static const struct sdhci_pci_fixes sdhci_cafe = { SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, }; +static const struct sdhci_pci_fixes sdhci_intel_qrk = { + .quirks = SDHCI_QUIRK_NO_HISPD_BIT, +}; + static int mrst_hc_probe_slot(struct sdhci_pci_slot *slot) { slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA; @@ -733,6 +737,14 @@ static const struct pci_device_id pci_ids[] = { { .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_QRK_SD, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .driver_data = (kernel_ulong_t)&sdhci_intel_qrk, + }, + + { + .vendor = PCI_VENDOR_ID_INTEL, .device = PCI_DEVICE_ID_INTEL_MRST_SD0, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h index 6d718719659e..c101477ef3be 100644 --- a/drivers/mmc/host/sdhci-pci.h +++ b/drivers/mmc/host/sdhci-pci.h @@ -17,6 +17,7 @@ #define PCI_DEVICE_ID_INTEL_CLV_SDIO2 0x08fb #define PCI_DEVICE_ID_INTEL_CLV_EMMC0 0x08e5 #define PCI_DEVICE_ID_INTEL_CLV_EMMC1 0x08e6 +#define PCI_DEVICE_ID_INTEL_QRK_SD 0x08A7 /* * PCI registers diff --git a/drivers/mtd/devices/elm.c b/drivers/mtd/devices/elm.c index d1dd6a33a050..3059a7a53bff 100644 --- a/drivers/mtd/devices/elm.c +++ b/drivers/mtd/devices/elm.c @@ -428,6 +428,7 @@ static int elm_context_save(struct elm_info *info) ELM_SYNDROME_FRAGMENT_1 + offset); regs->elm_syndrome_fragment_0[i] = elm_read_reg(info, ELM_SYNDROME_FRAGMENT_0 + offset); + break; default: return -EINVAL; } @@ -466,6 +467,7 @@ static int elm_context_restore(struct elm_info *info) regs->elm_syndrome_fragment_1[i]); elm_write_reg(info, ELM_SYNDROME_FRAGMENT_0 + offset, regs->elm_syndrome_fragment_0[i]); + break; default: return -EINVAL; } diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c index 19d637266fcd..71e4f6ccae2f 100644 --- a/drivers/mtd/ftl.c +++ b/drivers/mtd/ftl.c @@ -1075,7 +1075,6 @@ static void ftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd) return; } - ftl_freepart(partition); kfree(partition); } diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c index c36e9b84487c..2c059890a394 100644 --- a/drivers/mtd/nand/atmel_nand.c +++ b/drivers/mtd/nand/atmel_nand.c @@ -1220,6 +1220,7 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev, goto err; } + nand_chip->options |= NAND_NO_SUBPAGE_WRITE; nand_chip->ecc.read_page = atmel_nand_pmecc_read_page; nand_chip->ecc.write_page = atmel_nand_pmecc_write_page; diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c index fec31d71b84e..fe8a020ecf25 100644 --- a/drivers/mtd/nand/diskonchip.c +++ b/drivers/mtd/nand/diskonchip.c @@ -1438,7 +1438,7 @@ static int __init doc_probe(unsigned long physadr) int reg, len, numchips; int ret = 0; - if (!request_mem_region(physadr, DOC_IOREMAP_LEN, NULL)) + if (!request_mem_region(physadr, DOC_IOREMAP_LEN, "DiskOnChip")) return -EBUSY; virtadr = ioremap(physadr, DOC_IOREMAP_LEN); if (!virtadr) { diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c index bcf60800c3ce..c09ab95a2219 100644 --- a/drivers/mtd/nand/fsl_elbc_nand.c +++ b/drivers/mtd/nand/fsl_elbc_nand.c @@ -724,6 +724,19 @@ static int fsl_elbc_write_page(struct mtd_info *mtd, struct nand_chip *chip, return 0; } +/* ECC will be calculated automatically, and errors will be detected in + * waitfunc. + */ +static int fsl_elbc_write_subpage(struct mtd_info *mtd, struct nand_chip *chip, + uint32_t offset, uint32_t data_len, + const uint8_t *buf, int oob_required) +{ + fsl_elbc_write_buf(mtd, buf, mtd->writesize); + fsl_elbc_write_buf(mtd, chip->oob_poi, mtd->oobsize); + + return 0; +} + static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv) { struct fsl_lbc_ctrl *ctrl = priv->ctrl; @@ -762,6 +775,7 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv) chip->ecc.read_page = fsl_elbc_read_page; chip->ecc.write_page = fsl_elbc_write_page; + chip->ecc.write_subpage = fsl_elbc_write_subpage; /* If CS Base Register selects full hardware ECC then use it */ if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) == diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c index 9ee09a8177c6..7360f7872d9a 100644 --- a/drivers/mtd/nand/nuc900_nand.c +++ b/drivers/mtd/nand/nuc900_nand.c @@ -225,7 +225,7 @@ static void nuc900_nand_enable(struct nuc900_nand *nand) val = __raw_readl(nand->reg + REG_FMICSR); if (!(val & NAND_EN)) - __raw_writel(val | NAND_EN, REG_FMICSR); + __raw_writel(val | NAND_EN, nand->reg + REG_FMICSR); val = __raw_readl(nand->reg + REG_SMCSR); diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index bf642ceef681..64d8e32b6ca0 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -933,7 +933,7 @@ static int omap_calculate_ecc(struct mtd_info *mtd, const u_char *dat, u32 val; val = readl(info->reg.gpmc_ecc_config); - if (((val >> ECC_CONFIG_CS_SHIFT) & ~CS_MASK) != info->gpmc_cs) + if (((val >> ECC_CONFIG_CS_SHIFT) & CS_MASK) != info->gpmc_cs) return -EINVAL; /* read ecc result */ @@ -1451,7 +1451,7 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data, /* Check if any error reported */ if (!is_error_reported) - return 0; + return stat; /* Decode BCH error using ELM module */ elm_decode_bch_error_page(info->elm_dev, ecc_vec, err_vec); diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 2a7a0b27ac38..51e15fd53108 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -128,10 +128,10 @@ /* macros for registers read/write */ #define nand_writel(info, off, val) \ - __raw_writel((val), (info)->mmio_base + (off)) + writel_relaxed((val), (info)->mmio_base + (off)) #define nand_readl(info, off) \ - __raw_readl((info)->mmio_base + (off)) + readl_relaxed((info)->mmio_base + (off)) /* error code and state */ enum { diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c index 4b8e89583f2a..cf49c22673b9 100644 --- a/drivers/mtd/sm_ftl.c +++ b/drivers/mtd/sm_ftl.c @@ -59,15 +59,12 @@ static struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl) struct attribute_group *attr_group; struct attribute **attributes; struct sm_sysfs_attribute *vendor_attribute; + char *vendor; - int vendor_len = strnlen(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET, - SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET); - - char *vendor = kmalloc(vendor_len, GFP_KERNEL); + vendor = kstrndup(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET, + SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET, GFP_KERNEL); if (!vendor) goto error1; - memcpy(vendor, ftl->cis_buffer + SM_CIS_VENDOR_OFFSET, vendor_len); - vendor[vendor_len] = 0; /* Initialize sysfs attributes */ vendor_attribute = @@ -78,7 +75,7 @@ static struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl) sysfs_attr_init(&vendor_attribute->dev_attr.attr); vendor_attribute->data = vendor; - vendor_attribute->len = vendor_len; + vendor_attribute->len = strlen(vendor); vendor_attribute->dev_attr.attr.name = "vendor"; vendor_attribute->dev_attr.attr.mode = S_IRUGO; vendor_attribute->dev_attr.show = sm_attr_show; diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index c5dad652614d..904b4517fc1e 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -330,6 +330,7 @@ static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai, av = tmp_av; else { ubi_err("orphaned volume in fastmap pool!"); + kmem_cache_free(ai->aeb_slab_cache, new_aeb); return UBI_BAD_FASTMAP; } diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 494b888a6568..7e5c6a8b89e7 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -135,6 +135,7 @@ config MACVLAN config MACVTAP tristate "MAC-VLAN based tap driver" depends on MACVLAN + depends on INET help This adds a specialized tap character device driver that is based on the MAC-VLAN network interface, called macvtap. A macvtap device @@ -205,6 +206,7 @@ config RIONET_RX_SIZE config TUN tristate "Universal TUN/TAP device driver support" + depends on INET select CRC32 ---help--- TUN/TAP provides packet reception and transmission for user space diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e5628fc725c3..cc38948cf65d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3624,8 +3624,14 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev else bond_xmit_slave_id(bond, skb, 0); } else { - slave_id = bond_rr_gen_slave_id(bond); - bond_xmit_slave_id(bond, skb, slave_id % bond->slave_cnt); + int slave_cnt = ACCESS_ONCE(bond->slave_cnt); + + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); + } else { + dev_kfree_skb_any(skb); + } } return NETDEV_TX_OK; @@ -3656,8 +3662,13 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + int slave_cnt = ACCESS_ONCE(bond->slave_cnt); - bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb, bond->slave_cnt)); + if (likely(slave_cnt)) + bond_xmit_slave_id(bond, skb, + bond_xmit_hash(bond, skb, bond->slave_cnt)); + else + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -4068,7 +4079,7 @@ static int bond_check_params(struct bond_params *params) } if (ad_select) { - bond_opt_initstr(&newval, lacp_rate); + bond_opt_initstr(&newval, ad_select); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT), &newval); if (!valptr) { @@ -4536,6 +4547,7 @@ static int __init bonding_init(void) out: return res; err: + bond_destroy_debugfs(); bond_netlink_fini(); err_link: unregister_pernet_subsys(&bond_net_ops); diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 298c26509095..a937a37ae89f 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -70,6 +70,7 @@ static struct bond_opt_value bond_fail_over_mac_tbl[] = { static struct bond_opt_value bond_intmax_tbl[] = { { "off", 0, BOND_VALFLAG_DEFAULT}, { "maxval", INT_MAX, BOND_VALFLAG_MAX}, + { NULL, -1, 0} }; static struct bond_opt_value bond_lacp_rate_tbl[] = { diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 065ca49eb45e..546a848add37 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -551,7 +551,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct sja1000_priv *priv; struct peak_pci_chan *chan; - struct net_device *dev; + struct net_device *dev, *prev_dev; void __iomem *cfg_base, *reg_base; u16 sub_sys_id, icr; int i, err, channels; @@ -687,11 +687,13 @@ failure_remove_channels: writew(0x0, cfg_base + PITA_ICR + 2); chan = NULL; - for (dev = pci_get_drvdata(pdev); dev; dev = chan->prev_dev) { - unregister_sja1000dev(dev); - free_sja1000dev(dev); + for (dev = pci_get_drvdata(pdev); dev; dev = prev_dev) { priv = netdev_priv(dev); chan = priv->priv; + prev_dev = chan->prev_dev; + + unregister_sja1000dev(dev); + free_sja1000dev(dev); } /* free any PCIeC resources too */ @@ -725,10 +727,12 @@ static void peak_pci_remove(struct pci_dev *pdev) /* Loop over all registered devices */ while (1) { + struct net_device *prev_dev = chan->prev_dev; + dev_info(&pdev->dev, "removing device %s\n", dev->name); unregister_sja1000dev(dev); free_sja1000dev(dev); - dev = chan->prev_dev; + dev = prev_dev; if (!dev) { /* do that only for first channel */ diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 3fcdae266377..1d0dab854b90 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -52,6 +52,7 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/workqueue.h> #include <linux/can.h> #include <linux/can/skb.h> @@ -85,6 +86,7 @@ struct slcan { struct tty_struct *tty; /* ptr to TTY structure */ struct net_device *dev; /* easy for intr handling */ spinlock_t lock; + struct work_struct tx_work; /* Flushes transmit buffer */ /* These are pointers to the malloc()ed frame buffers. */ unsigned char rbuff[SLC_MTU]; /* receiver buffer */ @@ -309,34 +311,44 @@ static void slc_encaps(struct slcan *sl, struct can_frame *cf) sl->dev->stats.tx_bytes += cf->can_dlc; } -/* - * Called by the driver when there's room for more data. If we have - * more packets to send, we send them here. - */ -static void slcan_write_wakeup(struct tty_struct *tty) +/* Write out any remaining transmit buffer. Scheduled when tty is writable */ +static void slcan_transmit(struct work_struct *work) { + struct slcan *sl = container_of(work, struct slcan, tx_work); int actual; - struct slcan *sl = (struct slcan *) tty->disc_data; + spin_lock_bh(&sl->lock); /* First make sure we're connected. */ - if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev)) + if (!sl->tty || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev)) { + spin_unlock_bh(&sl->lock); return; + } - spin_lock(&sl->lock); if (sl->xleft <= 0) { /* Now serial buffer is almost free & we can start * transmission of another packet */ sl->dev->stats.tx_packets++; - clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); - spin_unlock(&sl->lock); + clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags); + spin_unlock_bh(&sl->lock); netif_wake_queue(sl->dev); return; } - actual = tty->ops->write(tty, sl->xhead, sl->xleft); + actual = sl->tty->ops->write(sl->tty, sl->xhead, sl->xleft); sl->xleft -= actual; sl->xhead += actual; - spin_unlock(&sl->lock); + spin_unlock_bh(&sl->lock); +} + +/* + * Called by the driver when there's room for more data. + * Schedule the transmit. + */ +static void slcan_write_wakeup(struct tty_struct *tty) +{ + struct slcan *sl = tty->disc_data; + + schedule_work(&sl->tx_work); } /* Send a can_frame to a TTY queue. */ @@ -522,6 +534,7 @@ static struct slcan *slc_alloc(dev_t line) sl->magic = SLCAN_MAGIC; sl->dev = dev; spin_lock_init(&sl->lock); + INIT_WORK(&sl->tx_work, slcan_transmit); slcan_devs[i] = dev; return sl; @@ -620,8 +633,12 @@ static void slcan_close(struct tty_struct *tty) if (!sl || sl->magic != SLCAN_MAGIC || sl->tty != tty) return; + spin_lock_bh(&sl->lock); tty->disc_data = NULL; sl->tty = NULL; + spin_unlock_bh(&sl->lock); + + flush_work(&sl->tx_work); /* Flush network side */ unregister_netdev(sl->dev); diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 511f6eecd58b..62db510b70ea 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -725,6 +725,7 @@ static int emac_open(struct net_device *dev) ret = emac_mdio_probe(dev); if (ret < 0) { + free_irq(dev->irq, dev); netdev_err(dev, "cannot probe MDIO bus\n"); return ret; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 391f29ef6d2e..1fbeaa9dd202 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -337,6 +337,7 @@ struct sw_tx_bd { u8 flags; /* Set on the first BD descriptor when there is a split BD */ #define BNX2X_TSO_SPLIT_BD (1<<0) +#define BNX2X_HAS_SECOND_PBD (1<<1) }; struct sw_rx_page { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index dbcff509dc3f..afa4a1f63270 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -223,6 +223,12 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, --nbd; bd_idx = TX_BD(NEXT_TX_IDX(bd_idx)); + if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) { + /* Skip second parse bd... */ + --nbd; + bd_idx = TX_BD(NEXT_TX_IDX(bd_idx)); + } + /* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */ if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) { tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd; @@ -793,7 +799,8 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp, return; } - bnx2x_frag_free(fp, new_data); + if (new_data) + bnx2x_frag_free(fp, new_data); drop: /* drop the packet and keep the buffer in the bin */ DP(NETIF_MSG_RX_STATUS, @@ -3867,6 +3874,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) /* set encapsulation flag in start BD */ SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_TUNNEL_EXIST, 1); + + tx_buf->flags |= BNX2X_HAS_SECOND_PBD; + nbd++; } else if (xmit_type & XMIT_CSUM) { /* Set PBD in checksum offload case w/o encapsulation */ diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 70a225c8df5c..9373f1f59605 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6923,7 +6923,8 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) skb->protocol = eth_type_trans(skb, tp->dev); if (len > (tp->dev->mtu + ETH_HLEN) && - skb->protocol != htons(ETH_P_8021Q)) { + skb->protocol != htons(ETH_P_8021Q) && + skb->protocol != htons(ETH_P_8021AD)) { dev_kfree_skb(skb); goto drop_it_no_recycle; } @@ -7915,8 +7916,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) entry = tnapi->tx_prod; base_flags = 0; - if (skb->ip_summed == CHECKSUM_PARTIAL) - base_flags |= TXD_FLAG_TCPUDP_CSUM; mss = skb_shinfo(skb)->gso_size; if (mss) { @@ -7932,6 +7931,13 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - ETH_HLEN; + /* HW/FW can not correctly segment packets that have been + * vlan encapsulated. + */ + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) + return tg3_tso_bug(tp, skb); + if (!skb_is_gso_v6(skb)) { iph->check = 0; iph->tot_len = htons(mss + hdr_len); @@ -7978,6 +7984,17 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) base_flags |= tsflags << 12; } } + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + /* HW/FW can not correctly checksum packets that have been + * vlan encapsulated. + */ + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) { + if (skb_checksum_help(skb)) + goto drop; + } else { + base_flags |= TXD_FLAG_TCPUDP_CSUM; + } } if (tg3_flag(tp, USE_JUMBO_BDFLAG) && @@ -12294,7 +12311,9 @@ static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *e if (tg3_flag(tp, MAX_RXPEND_64) && tp->rx_pending > 63) tp->rx_pending = 63; - tp->rx_jumbo_pending = ering->rx_jumbo_pending; + + if (tg3_flag(tp, JUMBO_RING_ENABLE)) + tp->rx_jumbo_pending = ering->rx_jumbo_pending; for (i = 0; i < tp->irq_max; i++) tp->napi[i].tx_pending = ering->tx_pending; diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 4ad1187e82fb..669eeb4eb247 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -600,9 +600,9 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) prefetch(bnad->netdev); cq = ccb->sw_q; - cmpl = &cq[ccb->producer_index]; while (packets < budget) { + cmpl = &cq[ccb->producer_index]; if (!cmpl->valid) break; /* The 'valid' field is set by the adapter, only after writing diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c index ce75de9bae9e..4a79edaf3885 100644 --- a/drivers/net/ethernet/cadence/at91_ether.c +++ b/drivers/net/ethernet/cadence/at91_ether.c @@ -342,6 +342,9 @@ static int __init at91ether_probe(struct platform_device *pdev) } clk_enable(lp->pclk); + lp->hclk = ERR_PTR(-ENOENT); + lp->tx_clk = ERR_PTR(-ENOENT); + /* Install the interrupt handler */ dev->irq = platform_get_irq(pdev, 0); res = devm_request_irq(&pdev->dev, dev->irq, at91ether_interrupt, 0, dev->name, dev); diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index d0c38e01e99f..0085476a0258 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -30,7 +30,6 @@ #include <linux/of_device.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/pinctrl/consumer.h> #include "macb.h" @@ -1810,7 +1809,6 @@ static int __init macb_probe(struct platform_device *pdev) struct phy_device *phydev; u32 config; int err = -ENXIO; - struct pinctrl *pinctrl; const char *mac; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1819,15 +1817,6 @@ static int __init macb_probe(struct platform_device *pdev) goto err_out; } - pinctrl = devm_pinctrl_get_select_default(&pdev->dev); - if (IS_ERR(pinctrl)) { - err = PTR_ERR(pinctrl); - if (err == -EPROBE_DEFER) - goto err_out; - - dev_warn(&pdev->dev, "No pinctrl provided\n"); - } - err = -ENOMEM; dev = alloc_etherdev(sizeof(*bp)); if (!dev) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 36c80612e21a..80bfa0391913 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2797,7 +2797,7 @@ static int be_open(struct net_device *netdev) for_all_evt_queues(adapter, eqo, i) { napi_enable(&eqo->napi); be_enable_busy_poll(eqo); - be_eq_notify(adapter, eqo->q.id, true, false, 0); + be_eq_notify(adapter, eqo->q.id, true, true, 0); } adapter->flags |= BE_FLAGS_NAPI_ENABLED; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 1fc8334fc181..55e3075492da 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -292,6 +292,18 @@ failure: atomic_add(buffers_added, &(pool->available)); } +/* + * The final 8 bytes of the buffer list is a counter of frames dropped + * because there was not a buffer in the buffer list capable of holding + * the frame. + */ +static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter) +{ + __be64 *p = adapter->buffer_list_addr + 4096 - 8; + + adapter->rx_no_buffer = be64_to_cpup(p); +} + /* replenish routine */ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) { @@ -307,8 +319,7 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) ibmveth_replenish_buffer_pool(adapter, pool); } - adapter->rx_no_buffer = *(u64 *)(((char*)adapter->buffer_list_addr) + - 4096 - 8); + ibmveth_update_rx_no_buffer(adapter); } /* empty and free ana buffer pool - also used to do cleanup in error paths */ @@ -698,8 +709,7 @@ static int ibmveth_close(struct net_device *netdev) free_irq(netdev->irq, netdev); - adapter->rx_no_buffer = *(u64 *)(((char *)adapter->buffer_list_addr) + - 4096 - 8); + ibmveth_update_rx_no_buffer(adapter); ibmveth_cleanup(adapter); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 42f0f6717511..70e16f71f574 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1374,7 +1374,7 @@ static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index) /* RAR[1-6] are owned by manageability. Skip those and program the * next address into the SHRA register array. */ - if (index < (u32)(hw->mac.rar_entry_count - 6)) { + if (index < (u32)(hw->mac.rar_entry_count)) { s32 ret_val; ret_val = e1000_acquire_swflag_ich8lan(hw); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 217090df33e7..59865695b282 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -98,7 +98,7 @@ #define PCIE_ICH8_SNOOP_ALL PCIE_NO_SNOOP_ALL #define E1000_ICH_RAR_ENTRIES 7 -#define E1000_PCH2_RAR_ENTRIES 11 /* RAR[0-6], SHRA[0-3] */ +#define E1000_PCH2_RAR_ENTRIES 5 /* RAR[0], SHRA[0-3] */ #define E1000_PCH_LPT_RAR_ENTRIES 12 /* RAR[0], SHRA[0-10] */ #define PHY_PAGE_SHIFT 5 diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 6d91933c4cdd..0af6e060e238 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2976,11 +2976,21 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) u32 rctl, rfctl; u32 pages = 0; - /* Workaround Si errata on PCHx - configure jumbo frame flow */ - if ((hw->mac.type >= e1000_pch2lan) && - (adapter->netdev->mtu > ETH_DATA_LEN) && - e1000_lv_jumbo_workaround_ich8lan(hw, true)) - e_dbg("failed to enable jumbo frame workaround mode\n"); + /* Workaround Si errata on PCHx - configure jumbo frame flow. + * If jumbo frames not set, program related MAC/PHY registers + * to h/w defaults + */ + if (hw->mac.type >= e1000_pch2lan) { + s32 ret_val; + + if (adapter->netdev->mtu > ETH_DATA_LEN) + ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true); + else + ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false); + + if (ret_val) + e_dbg("failed to enable|disable jumbo frame workaround mode\n"); + } /* Program MC offset vector base */ rctl = er32(RCTL); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b901371ca361..5d3206d5cb07 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4024,6 +4024,9 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) DCB_CAP_DCBX_VER_IEEE; pf->flags |= I40E_FLAG_DCB_ENABLED; } + } else { + dev_info(&pf->pdev->dev, "AQ Querying DCB configuration failed: %d\n", + pf->hw.aq.asq_last_status); } out: @@ -8003,7 +8006,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { dev_info(&pdev->dev, "init_pf_dcb failed: %d\n", err); pf->flags &= ~I40E_FLAG_DCB_ENABLED; - goto err_init_dcb; + /* Continue without DCB enabled */ } #endif /* CONFIG_I40E_DCB */ @@ -8119,9 +8122,6 @@ err_vsis: err_switch_setup: i40e_reset_interrupt_capability(pf); del_timer_sync(&pf->service_timer); -#ifdef CONFIG_I40E_DCB -err_init_dcb: -#endif /* CONFIG_I40E_DCB */ err_mac_addr: err_configure_lan_hmc: (void)i40e_shutdown_lan_hmc(hw); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index b9d1c1c8ca5a..178506a201d5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1776,7 +1776,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, u16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen) { struct i40e_hw *hw = &pf->hw; - int local_vf_id = vf_id - hw->func_caps.vf_base_id; + unsigned int local_vf_id = vf_id - hw->func_caps.vf_base_id; struct i40e_vf *vf; int ret; diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 06df6928f44c..4fa5c2a77d49 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -1492,6 +1492,13 @@ static s32 igb_init_hw_82575(struct e1000_hw *hw) s32 ret_val; u16 i, rar_count = mac->rar_entry_count; + if ((hw->mac.type >= e1000_i210) && + !(igb_get_flash_presence_i210(hw))) { + ret_val = igb_pll_workaround_i210(hw); + if (ret_val) + return ret_val; + } + /* Initialize identification LED */ ret_val = igb_id_led_init(hw); if (ret_val) { diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 0571b973be80..20b37668284a 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -46,14 +46,15 @@ /* Extended Device Control */ #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Defineable Pin 3 */ /* Physical Func Reset Done Indication */ -#define E1000_CTRL_EXT_PFRSTD 0x00004000 -#define E1000_CTRL_EXT_LINK_MODE_MASK 0x00C00000 -#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES 0x00C00000 -#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX 0x00400000 -#define E1000_CTRL_EXT_LINK_MODE_SGMII 0x00800000 -#define E1000_CTRL_EXT_LINK_MODE_GMII 0x00000000 -#define E1000_CTRL_EXT_EIAME 0x01000000 -#define E1000_CTRL_EXT_IRCA 0x00000001 +#define E1000_CTRL_EXT_PFRSTD 0x00004000 +#define E1000_CTRL_EXT_SDLPE 0X00040000 /* SerDes Low Power Enable */ +#define E1000_CTRL_EXT_LINK_MODE_MASK 0x00C00000 +#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES 0x00C00000 +#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX 0x00400000 +#define E1000_CTRL_EXT_LINK_MODE_SGMII 0x00800000 +#define E1000_CTRL_EXT_LINK_MODE_GMII 0x00000000 +#define E1000_CTRL_EXT_EIAME 0x01000000 +#define E1000_CTRL_EXT_IRCA 0x00000001 /* Interrupt delay cancellation */ /* Driver loaded bit for FW */ #define E1000_CTRL_EXT_DRV_LOAD 0x10000000 @@ -62,6 +63,7 @@ /* packet buffer parity error detection enabled */ /* descriptor FIFO parity error detection enable */ #define E1000_CTRL_EXT_PBA_CLR 0x80000000 /* PBA Clear */ +#define E1000_CTRL_EXT_PHYPDEN 0x00100000 #define E1000_I2CCMD_REG_ADDR_SHIFT 16 #define E1000_I2CCMD_PHY_ADDR_SHIFT 24 #define E1000_I2CCMD_OPCODE_READ 0x08000000 diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index ab99e2b582a8..b79980ad225b 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -572,4 +572,7 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw); /* These functions must be implemented by drivers */ s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value); s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value); + +void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); +void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); #endif /* _E1000_HW_H_ */ diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index 0c0393316a3a..0217d4e229a0 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -835,3 +835,69 @@ s32 igb_init_nvm_params_i210(struct e1000_hw *hw) } return ret_val; } + +/** + * igb_pll_workaround_i210 + * @hw: pointer to the HW structure + * + * Works around an errata in the PLL circuit where it occasionally + * provides the wrong clock frequency after power up. + **/ +s32 igb_pll_workaround_i210(struct e1000_hw *hw) +{ + s32 ret_val; + u32 wuc, mdicnfg, ctrl, ctrl_ext, reg_val; + u16 nvm_word, phy_word, pci_word, tmp_nvm; + int i; + + /* Get and set needed register values */ + wuc = rd32(E1000_WUC); + mdicnfg = rd32(E1000_MDICNFG); + reg_val = mdicnfg & ~E1000_MDICNFG_EXT_MDIO; + wr32(E1000_MDICNFG, reg_val); + + /* Get data from NVM, or set default */ + ret_val = igb_read_invm_word_i210(hw, E1000_INVM_AUTOLOAD, + &nvm_word); + if (ret_val) + nvm_word = E1000_INVM_DEFAULT_AL; + tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL; + for (i = 0; i < E1000_MAX_PLL_TRIES; i++) { + /* check current state directly from internal PHY */ + igb_read_phy_reg_gs40g(hw, (E1000_PHY_PLL_FREQ_PAGE | + E1000_PHY_PLL_FREQ_REG), &phy_word); + if ((phy_word & E1000_PHY_PLL_UNCONF) + != E1000_PHY_PLL_UNCONF) { + ret_val = 0; + break; + } else { + ret_val = -E1000_ERR_PHY; + } + /* directly reset the internal PHY */ + ctrl = rd32(E1000_CTRL); + wr32(E1000_CTRL, ctrl|E1000_CTRL_PHY_RST); + + ctrl_ext = rd32(E1000_CTRL_EXT); + ctrl_ext |= (E1000_CTRL_EXT_PHYPDEN | E1000_CTRL_EXT_SDLPE); + wr32(E1000_CTRL_EXT, ctrl_ext); + + wr32(E1000_WUC, 0); + reg_val = (E1000_INVM_AUTOLOAD << 4) | (tmp_nvm << 16); + wr32(E1000_EEARBC_I210, reg_val); + + igb_read_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word); + pci_word |= E1000_PCI_PMCSR_D3; + igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word); + usleep_range(1000, 2000); + pci_word &= ~E1000_PCI_PMCSR_D3; + igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word); + reg_val = (E1000_INVM_AUTOLOAD << 4) | (nvm_word << 16); + wr32(E1000_EEARBC_I210, reg_val); + + /* restore WUC register */ + wr32(E1000_WUC, wuc); + } + /* restore MDICNFG setting */ + wr32(E1000_MDICNFG, mdicnfg); + return ret_val; +} diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h index 2d913716573a..710f8e9f10fb 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.h +++ b/drivers/net/ethernet/intel/igb/e1000_i210.h @@ -46,6 +46,7 @@ s32 igb_read_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 *data); s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data); s32 igb_init_nvm_params_i210(struct e1000_hw *hw); bool igb_get_flash_presence_i210(struct e1000_hw *hw); +s32 igb_pll_workaround_i210(struct e1000_hw *hw); #define E1000_STM_OPCODE 0xDB00 #define E1000_EEPROM_FLASH_SIZE_WORD 0x11 @@ -91,4 +92,15 @@ enum E1000_INVM_STRUCTURE_TYPE { #define NVM_LED_1_CFG_DEFAULT_I211 0x0184 #define NVM_LED_0_2_CFG_DEFAULT_I211 0x200C +/* PLL Defines */ +#define E1000_PCI_PMCSR 0x44 +#define E1000_PCI_PMCSR_D3 0x03 +#define E1000_MAX_PLL_TRIES 5 +#define E1000_PHY_PLL_UNCONF 0xFF +#define E1000_PHY_PLL_FREQ_PAGE 0xFC0000 +#define E1000_PHY_PLL_FREQ_REG 0x000E +#define E1000_INVM_DEFAULT_AL 0x202F +#define E1000_INVM_AUTOLOAD 0x0A +#define E1000_INVM_PLL_WO_VAL 0x0010 + #endif diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 82632c6c53af..7156981ec813 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -69,6 +69,7 @@ #define E1000_PBA 0x01000 /* Packet Buffer Allocation - RW */ #define E1000_PBS 0x01008 /* Packet Buffer Size */ #define E1000_EEMNGCTL 0x01010 /* MNG EEprom Control */ +#define E1000_EEARBC_I210 0x12024 /* EEPROM Auto Read Bus Control */ #define E1000_EEWR 0x0102C /* EEPROM Write Register - RW */ #define E1000_I2CCMD 0x01028 /* SFPI2C Command Register - RW */ #define E1000_FRTIMER 0x01048 /* Free Running Timer - RW */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 46d31a49f5ea..5ca8c479666e 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1014,6 +1014,12 @@ static void igb_reset_q_vector(struct igb_adapter *adapter, int v_idx) { struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + /* Coming from igb_set_interrupt_capability, the vectors are not yet + * allocated. So, q_vector is NULL so we should stop here. + */ + if (!q_vector) + return; + if (q_vector->tx.ring) adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL; @@ -1121,6 +1127,7 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) /* If we can't do MSI-X, try MSI */ msi_only: + adapter->flags &= ~IGB_FLAG_HAS_MSIX; #ifdef CONFIG_PCI_IOV /* disable SR-IOV for non MSI-X configurations */ if (adapter->vf_data) { @@ -7121,6 +7128,20 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) } } +void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value) +{ + struct igb_adapter *adapter = hw->back; + + pci_read_config_word(adapter->pdev, reg, value); +} + +void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value) +{ + struct igb_adapter *adapter = hw->back; + + pci_write_config_word(adapter->pdev, reg, *value); +} + s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value) { struct igb_adapter *adapter = hw->back; @@ -7484,6 +7505,8 @@ static int igb_sriov_reinit(struct pci_dev *dev) if (netif_running(netdev)) igb_close(netdev); + else + igb_reset(adapter); igb_clear_interrupt_scheme(adapter); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 8d76fca7fde7..c4c00d9f2c04 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -89,9 +89,8 @@ #define MVNETA_TX_IN_PRGRS BIT(1) #define MVNETA_TX_FIFO_EMPTY BIT(8) #define MVNETA_RX_MIN_FRAME_SIZE 0x247c -#define MVNETA_SERDES_CFG 0x24A0 +#define MVNETA_SGMII_SERDES_CFG 0x24A0 #define MVNETA_SGMII_SERDES_PROTO 0x0cc7 -#define MVNETA_RGMII_SERDES_PROTO 0x0667 #define MVNETA_TYPE_PRIO 0x24bc #define MVNETA_FORCE_UNI BIT(21) #define MVNETA_TXQ_CMD_1 0x24e4 @@ -712,6 +711,35 @@ static void mvneta_rxq_bm_disable(struct mvneta_port *pp, mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val); } + + +/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */ +static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable) +{ + u32 val; + + val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); + + if (enable) + val |= MVNETA_GMAC2_PORT_RGMII; + else + val &= ~MVNETA_GMAC2_PORT_RGMII; + + mvreg_write(pp, MVNETA_GMAC_CTRL_2, val); +} + +/* Config SGMII port */ +static void mvneta_port_sgmii_config(struct mvneta_port *pp) +{ + u32 val; + + val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); + val |= MVNETA_GMAC2_PCS_ENABLE; + mvreg_write(pp, MVNETA_GMAC_CTRL_2, val); + + mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO); +} + /* Start the Ethernet port RX and TX activity */ static void mvneta_port_up(struct mvneta_port *pp) { @@ -1189,7 +1217,7 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto, command = l3_offs << MVNETA_TX_L3_OFF_SHIFT; command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT; - if (l3_proto == swab16(ETH_P_IP)) + if (l3_proto == htons(ETH_P_IP)) command |= MVNETA_TXD_IP_CSUM; else command |= MVNETA_TX_L3_IP6; @@ -2365,7 +2393,7 @@ static void mvneta_adjust_link(struct net_device *ndev) if (phydev->speed == SPEED_1000) val |= MVNETA_GMAC_CONFIG_GMII_SPEED; - else + else if (phydev->speed == SPEED_100) val |= MVNETA_GMAC_CONFIG_MII_SPEED; mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); @@ -2729,15 +2757,12 @@ static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0); if (phy_mode == PHY_INTERFACE_MODE_SGMII) - mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO); - else - mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO); + mvneta_port_sgmii_config(pp); - val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); - - val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII; + mvneta_gmac_rgmii_set(pp, 1); /* Cancel Port Reset */ + val = mvreg_read(pp, MVNETA_GMAC_CTRL_2); val &= ~MVNETA_GMAC2_PORT_RESET; mvreg_write(pp, MVNETA_GMAC_CTRL_2, val); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 70e95324a97d..c2cd8d31bcad 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -66,7 +66,6 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv, cq->ring = ring; cq->is_tx = mode; - spin_lock_init(&cq->lock); /* Allocate HW buffers on provided NUMA node. * dev->numa_node is used in mtt range allocation flow. diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 84a96f70dfb5..2f83f3489fdb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1315,15 +1315,11 @@ static void mlx4_en_netpoll(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_cq *cq; - unsigned long flags; int i; for (i = 0; i < priv->rx_ring_num; i++) { cq = priv->rx_cq[i]; - spin_lock_irqsave(&cq->lock, flags); - napi_synchronize(&cq->napi); - mlx4_en_process_rx_cq(dev, cq, 0); - spin_unlock_irqrestore(&cq->lock, flags); + napi_schedule(&cq->napi); } } #endif diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 7e2995ecea6f..84e41920b5ff 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -398,7 +398,7 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port, MLX4_GET(func_cap->flags1, outbox, QUERY_FUNC_CAP_FLAGS1_OFFSET); if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_ETH) { - if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_OFFSET) { + if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_FORCE_VLAN) { mlx4_err(dev, "VLAN is enforced on this port\n"); err = -EPROTONOSUPPORT; goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d413e60071d4..4a13b0001471 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2275,13 +2275,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) /* Allow large DMA segments, up to the firmware limit of 1 GB */ dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) { - err = -ENOMEM; - goto err_release_regions; - } - - dev = &priv->dev; + dev = pci_get_drvdata(pdev); + priv = mlx4_priv(dev); dev->pdev = pdev; INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); @@ -2399,7 +2394,8 @@ slave_start: * No return code for this call, just warn the user in case of PCI * express device capabilities are under-satisfied by the bus. */ - mlx4_check_pcie_caps(dev); + if (!mlx4_is_slave(dev)) + mlx4_check_pcie_caps(dev); /* In master functions, the communication channel must be initialized * after obtaining its address from fw */ @@ -2464,8 +2460,7 @@ slave_start: mlx4_sense_init(dev); mlx4_start_sense(dev); - priv->pci_dev_data = pci_dev_data; - pci_set_drvdata(pdev, dev); + priv->removed = 0; return 0; @@ -2531,84 +2526,108 @@ err_disable_pdev: static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { + struct mlx4_priv *priv; + struct mlx4_dev *dev; + printk_once(KERN_INFO "%s", mlx4_version); + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + dev = &priv->dev; + pci_set_drvdata(pdev, dev); + priv->pci_dev_data = id->driver_data; + return __mlx4_init_one(pdev, id->driver_data); } -static void mlx4_remove_one(struct pci_dev *pdev) +static void __mlx4_remove_one(struct pci_dev *pdev) { struct mlx4_dev *dev = pci_get_drvdata(pdev); struct mlx4_priv *priv = mlx4_priv(dev); + int pci_dev_data; int p; - if (dev) { - /* in SRIOV it is not allowed to unload the pf's - * driver while there are alive vf's */ - if (mlx4_is_master(dev)) { - if (mlx4_how_many_lives_vf(dev)) - printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n"); - } - mlx4_stop_sense(dev); - mlx4_unregister_device(dev); + if (priv->removed) + return; - for (p = 1; p <= dev->caps.num_ports; p++) { - mlx4_cleanup_port_info(&priv->port[p]); - mlx4_CLOSE_PORT(dev, p); - } + pci_dev_data = priv->pci_dev_data; - if (mlx4_is_master(dev)) - mlx4_free_resource_tracker(dev, - RES_TR_FREE_SLAVES_ONLY); - - mlx4_cleanup_counters_table(dev); - mlx4_cleanup_qp_table(dev); - mlx4_cleanup_srq_table(dev); - mlx4_cleanup_cq_table(dev); - mlx4_cmd_use_polling(dev); - mlx4_cleanup_eq_table(dev); - mlx4_cleanup_mcg_table(dev); - mlx4_cleanup_mr_table(dev); - mlx4_cleanup_xrcd_table(dev); - mlx4_cleanup_pd_table(dev); + /* in SRIOV it is not allowed to unload the pf's + * driver while there are alive vf's */ + if (mlx4_is_master(dev) && mlx4_how_many_lives_vf(dev)) + printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n"); + mlx4_stop_sense(dev); + mlx4_unregister_device(dev); - if (mlx4_is_master(dev)) - mlx4_free_resource_tracker(dev, - RES_TR_FREE_STRUCTS_ONLY); - - iounmap(priv->kar); - mlx4_uar_free(dev, &priv->driver_uar); - mlx4_cleanup_uar_table(dev); - if (!mlx4_is_slave(dev)) - mlx4_clear_steering(dev); - mlx4_free_eq_table(dev); - if (mlx4_is_master(dev)) - mlx4_multi_func_cleanup(dev); - mlx4_close_hca(dev); - if (mlx4_is_slave(dev)) - mlx4_multi_func_cleanup(dev); - mlx4_cmd_cleanup(dev); - - if (dev->flags & MLX4_FLAG_MSI_X) - pci_disable_msix(pdev); - if (dev->flags & MLX4_FLAG_SRIOV) { - mlx4_warn(dev, "Disabling SR-IOV\n"); - pci_disable_sriov(pdev); - } + for (p = 1; p <= dev->caps.num_ports; p++) { + mlx4_cleanup_port_info(&priv->port[p]); + mlx4_CLOSE_PORT(dev, p); + } + + if (mlx4_is_master(dev)) + mlx4_free_resource_tracker(dev, + RES_TR_FREE_SLAVES_ONLY); + + mlx4_cleanup_counters_table(dev); + mlx4_cleanup_qp_table(dev); + mlx4_cleanup_srq_table(dev); + mlx4_cleanup_cq_table(dev); + mlx4_cmd_use_polling(dev); + mlx4_cleanup_eq_table(dev); + mlx4_cleanup_mcg_table(dev); + mlx4_cleanup_mr_table(dev); + mlx4_cleanup_xrcd_table(dev); + mlx4_cleanup_pd_table(dev); - if (!mlx4_is_slave(dev)) - mlx4_free_ownership(dev); + if (mlx4_is_master(dev)) + mlx4_free_resource_tracker(dev, + RES_TR_FREE_STRUCTS_ONLY); - kfree(dev->caps.qp0_tunnel); - kfree(dev->caps.qp0_proxy); - kfree(dev->caps.qp1_tunnel); - kfree(dev->caps.qp1_proxy); + iounmap(priv->kar); + mlx4_uar_free(dev, &priv->driver_uar); + mlx4_cleanup_uar_table(dev); + if (!mlx4_is_slave(dev)) + mlx4_clear_steering(dev); + mlx4_free_eq_table(dev); + if (mlx4_is_master(dev)) + mlx4_multi_func_cleanup(dev); + mlx4_close_hca(dev); + if (mlx4_is_slave(dev)) + mlx4_multi_func_cleanup(dev); + mlx4_cmd_cleanup(dev); - kfree(priv); - pci_release_regions(pdev); - pci_disable_device(pdev); - pci_set_drvdata(pdev, NULL); + if (dev->flags & MLX4_FLAG_MSI_X) + pci_disable_msix(pdev); + if (dev->flags & MLX4_FLAG_SRIOV) { + mlx4_warn(dev, "Disabling SR-IOV\n"); + pci_disable_sriov(pdev); } + + if (!mlx4_is_slave(dev)) + mlx4_free_ownership(dev); + + kfree(dev->caps.qp0_tunnel); + kfree(dev->caps.qp0_proxy); + kfree(dev->caps.qp1_tunnel); + kfree(dev->caps.qp1_proxy); + + pci_release_regions(pdev); + pci_disable_device(pdev); + memset(priv, 0, sizeof(*priv)); + priv->pci_dev_data = pci_dev_data; + priv->removed = 1; +} + +static void mlx4_remove_one(struct pci_dev *pdev) +{ + struct mlx4_dev *dev = pci_get_drvdata(pdev); + struct mlx4_priv *priv = mlx4_priv(dev); + + __mlx4_remove_one(pdev); + kfree(priv); + pci_set_drvdata(pdev, NULL); } int mlx4_restart_one(struct pci_dev *pdev) @@ -2618,7 +2637,7 @@ int mlx4_restart_one(struct pci_dev *pdev) int pci_dev_data; pci_dev_data = priv->pci_dev_data; - mlx4_remove_one(pdev); + __mlx4_remove_one(pdev); return __mlx4_init_one(pdev, pci_dev_data); } @@ -2673,7 +2692,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table); static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t state) { - mlx4_remove_one(pdev); + __mlx4_remove_one(pdev); return state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; @@ -2681,11 +2700,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) { - const struct pci_device_id *id; - int ret; + struct mlx4_dev *dev = pci_get_drvdata(pdev); + struct mlx4_priv *priv = mlx4_priv(dev); + int ret; - id = pci_match_id(mlx4_pci_table, pdev); - ret = __mlx4_init_one(pdev, id->driver_data); + ret = __mlx4_init_one(pdev, priv->pci_dev_data); return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } @@ -2699,7 +2718,7 @@ static struct pci_driver mlx4_driver = { .name = DRV_NAME, .id_table = mlx4_pci_table, .probe = mlx4_init_one, - .shutdown = mlx4_remove_one, + .shutdown = __mlx4_remove_one, .remove = mlx4_remove_one, .err_handler = &mlx4_err_handler, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 7aec6c833973..99d7a28a2ada 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -796,6 +796,7 @@ struct mlx4_priv { spinlock_t ctx_lock; int pci_dev_data; + int removed; struct list_head pgdir_list; struct mutex pgdir_mutex; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index b57e8c87a34e..72db9bedd765 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -309,7 +309,6 @@ struct mlx4_en_cq { struct mlx4_cq mcq; struct mlx4_hwq_resources wqres; int ring; - spinlock_t lock; struct net_device *dev; struct napi_struct napi; int size; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 68026f7e8ba3..4a474dd9c910 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -872,6 +872,10 @@ static int myri10ge_dma_test(struct myri10ge_priv *mgp, int test_type) return -ENOMEM; dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); + if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) { + __free_page(dmatest_page); + return -ENOMEM; + } /* Run a small DMA test. * The magic multipliers to the length tell the firmware @@ -1293,6 +1297,7 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx, int bytes, int watchdog) { struct page *page; + dma_addr_t bus; int idx; #if MYRI10GE_ALLOC_SIZE > 4096 int end_offset; @@ -1317,11 +1322,21 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx, rx->watchdog_needed = 1; return; } + + bus = pci_map_page(mgp->pdev, page, 0, + MYRI10GE_ALLOC_SIZE, + PCI_DMA_FROMDEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) { + __free_pages(page, MYRI10GE_ALLOC_ORDER); + if (rx->fill_cnt - rx->cnt < 16) + rx->watchdog_needed = 1; + return; + } + rx->page = page; rx->page_offset = 0; - rx->bus = pci_map_page(mgp->pdev, page, 0, - MYRI10GE_ALLOC_SIZE, - PCI_DMA_FROMDEVICE); + rx->bus = bus; + } rx->info[idx].page = rx->page; rx->info[idx].page_offset = rx->page_offset; @@ -2765,6 +2780,35 @@ myri10ge_submit_req(struct myri10ge_tx_buf *tx, struct mcp_kreq_ether_send *src, mb(); } +static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp, + struct myri10ge_tx_buf *tx, int idx) +{ + unsigned int len; + int last_idx; + + /* Free any DMA resources we've alloced and clear out the skb slot */ + last_idx = (idx + 1) & tx->mask; + idx = tx->req & tx->mask; + do { + len = dma_unmap_len(&tx->info[idx], len); + if (len) { + if (tx->info[idx].skb != NULL) + pci_unmap_single(mgp->pdev, + dma_unmap_addr(&tx->info[idx], + bus), len, + PCI_DMA_TODEVICE); + else + pci_unmap_page(mgp->pdev, + dma_unmap_addr(&tx->info[idx], + bus), len, + PCI_DMA_TODEVICE); + dma_unmap_len_set(&tx->info[idx], len, 0); + tx->info[idx].skb = NULL; + } + idx = (idx + 1) & tx->mask; + } while (idx != last_idx); +} + /* * Transmit a packet. We need to split the packet so that a single * segment does not cross myri10ge->tx_boundary, so this makes segment @@ -2788,7 +2832,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb, u32 low; __be32 high_swapped; unsigned int len; - int idx, last_idx, avail, frag_cnt, frag_idx, count, mss, max_segments; + int idx, avail, frag_cnt, frag_idx, count, mss, max_segments; u16 pseudo_hdr_offset, cksum_offset, queue; int cum_len, seglen, boundary, rdma_count; u8 flags, odd_flag; @@ -2885,9 +2929,12 @@ again: /* map the skb for DMA */ len = skb_headlen(skb); + bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) + goto drop; + idx = tx->req & tx->mask; tx->info[idx].skb = skb; - bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE); dma_unmap_addr_set(&tx->info[idx], bus, bus); dma_unmap_len_set(&tx->info[idx], len, len); @@ -2986,12 +3033,16 @@ again: break; /* map next fragment for DMA */ - idx = (count + tx->req) & tx->mask; frag = &skb_shinfo(skb)->frags[frag_idx]; frag_idx++; len = skb_frag_size(frag); bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len, DMA_TO_DEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) { + myri10ge_unmap_tx_dma(mgp, tx, idx); + goto drop; + } + idx = (count + tx->req) & tx->mask; dma_unmap_addr_set(&tx->info[idx], bus, bus); dma_unmap_len_set(&tx->info[idx], len, len); } @@ -3022,31 +3073,8 @@ again: return NETDEV_TX_OK; abort_linearize: - /* Free any DMA resources we've alloced and clear out the skb - * slot so as to not trip up assertions, and to avoid a - * double-free if linearizing fails */ + myri10ge_unmap_tx_dma(mgp, tx, idx); - last_idx = (idx + 1) & tx->mask; - idx = tx->req & tx->mask; - tx->info[idx].skb = NULL; - do { - len = dma_unmap_len(&tx->info[idx], len); - if (len) { - if (tx->info[idx].skb != NULL) - pci_unmap_single(mgp->pdev, - dma_unmap_addr(&tx->info[idx], - bus), len, - PCI_DMA_TODEVICE); - else - pci_unmap_page(mgp->pdev, - dma_unmap_addr(&tx->info[idx], - bus), len, - PCI_DMA_TODEVICE); - dma_unmap_len_set(&tx->info[idx], len, 0); - tx->info[idx].skb = NULL; - } - idx = (idx + 1) & tx->mask; - } while (idx != last_idx); if (skb_is_gso(skb)) { netdev_err(mgp->dev, "TSO but wanted to linearize?!?!?\n"); goto drop; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c index 7d4f54912bad..3e46c894a107 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c @@ -1022,6 +1022,7 @@ static int qlcnic_dcb_peer_app_info(struct net_device *netdev, struct qlcnic_dcb_cee *peer; int i; + memset(info, 0, sizeof(*info)); *app_count = 0; if (!test_bit(QLCNIC_DCB_STATE, &adapter->dcb->state)) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 040cb94e8219..957f0ffe31c4 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -301,6 +301,27 @@ static const u16 sh_eth_offset_fast_sh4[SH_ETH_MAX_REGISTER_OFFSET] = { }; static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = { + [EDMR] = 0x0000, + [EDTRR] = 0x0004, + [EDRRR] = 0x0008, + [TDLAR] = 0x000c, + [RDLAR] = 0x0010, + [EESR] = 0x0014, + [EESIPR] = 0x0018, + [TRSCER] = 0x001c, + [RMFCR] = 0x0020, + [TFTR] = 0x0024, + [FDR] = 0x0028, + [RMCR] = 0x002c, + [EDOCR] = 0x0030, + [FCFTR] = 0x0034, + [RPADIR] = 0x0038, + [TRIMD] = 0x003c, + [RBWAR] = 0x0040, + [RDFAR] = 0x0044, + [TBRAR] = 0x004c, + [TDFAR] = 0x0050, + [ECMR] = 0x0160, [ECSR] = 0x0164, [ECSIPR] = 0x0168, @@ -539,7 +560,6 @@ static struct sh_eth_cpu_data sh7757_data = { .register_type = SH_ETH_REG_FAST_SH4, .eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff, - .rmcr_value = RMCR_RNC, .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO, .eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE | @@ -617,7 +637,6 @@ static struct sh_eth_cpu_data sh7757_data_giga = { EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | EESR_ECI, .fdr_value = 0x0000072f, - .rmcr_value = RMCR_RNC, .irq_flags = IRQF_SHARED, .apr = 1, @@ -745,7 +764,6 @@ static struct sh_eth_cpu_data r8a7740_data = { EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | EESR_ECI, .fdr_value = 0x0000070f, - .rmcr_value = RMCR_RNC, .apr = 1, .mpr = 1, @@ -777,7 +795,6 @@ static struct sh_eth_cpu_data r7s72100_data = { EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | EESR_ECI, .fdr_value = 0x0000070f, - .rmcr_value = RMCR_RNC, .no_psr = 1, .apr = 1, @@ -826,9 +843,6 @@ static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd) if (!cd->fdr_value) cd->fdr_value = DEFAULT_FDR_INIT; - if (!cd->rmcr_value) - cd->rmcr_value = DEFAULT_RMCR_VALUE; - if (!cd->tx_check) cd->tx_check = DEFAULT_TX_CHECK; @@ -1281,8 +1295,8 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start) sh_eth_write(ndev, mdp->cd->fdr_value, FDR); sh_eth_write(ndev, 0, TFTR); - /* Frame recv control */ - sh_eth_write(ndev, mdp->cd->rmcr_value, RMCR); + /* Frame recv control (enable multiple-packets per rx irq) */ + sh_eth_write(ndev, RMCR_RNC, RMCR); sh_eth_write(ndev, DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2, TRSCER); diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 6075915b88ec..a096b4bf9799 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -320,7 +320,6 @@ enum TD_STS_BIT { enum RMCR_BIT { RMCR_RNC = 0x00000001, }; -#define DEFAULT_RMCR_VALUE 0x00000000 /* ECMR */ enum FELIC_MODE_BIT { @@ -467,7 +466,6 @@ struct sh_eth_cpu_data { unsigned long fdr_value; unsigned long fcftr_value; unsigned long rpadir_value; - unsigned long rmcr_value; /* interrupt checking mask */ unsigned long tx_check; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 174a92f5fe51..7645a3ce3854 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -565,10 +565,17 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx) * several of each (in fact that's the only option if host * page size is >4K). So we may allocate some extra VIs just * for writing PIO buffers through. + * + * The UC mapping contains (min_vis - 1) complete VIs and the + * first half of the next VI. Then the WC mapping begins with + * the second half of this last VI. */ uc_mem_map_size = PAGE_ALIGN((min_vis - 1) * EFX_VI_PAGE_SIZE + ER_DZ_TX_PIOBUF); if (nic_data->n_piobufs) { + /* pio_write_vi_base rounds down to give the number of complete + * VIs inside the UC mapping. + */ pio_write_vi_base = uc_mem_map_size / EFX_VI_PAGE_SIZE; wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base + nic_data->n_piobufs) * diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 83d464347021..f06c790fba5a 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1603,6 +1603,8 @@ static int efx_probe_nic(struct efx_nic *efx) if (rc) goto fail1; + efx_set_channels(efx); + rc = efx->type->dimension_resources(efx); if (rc) goto fail2; @@ -1613,7 +1615,6 @@ static int efx_probe_nic(struct efx_nic *efx) efx->rx_indir_table[i] = ethtool_rxfh_indir_default(i, efx->rss_spread); - efx_set_channels(efx); netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels); diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h index 4d3f119b67b3..afb94aa2c15e 100644 --- a/drivers/net/ethernet/sfc/io.h +++ b/drivers/net/ethernet/sfc/io.h @@ -66,10 +66,17 @@ #define EFX_USE_QWORD_IO 1 #endif +/* Hardware issue requires that only 64-bit naturally aligned writes + * are seen by hardware. Its not strictly necessary to restrict to + * x86_64 arch, but done for safety since unusual write combining behaviour + * can break PIO. + */ +#ifdef CONFIG_X86_64 /* PIO is a win only if write-combining is possible */ #ifdef ARCH_HAS_IOREMAP_WC #define EFX_USE_PIO 1 #endif +#endif #ifdef EFX_USE_QWORD_IO static inline void _efx_writeq(struct efx_nic *efx, __le64 value, diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index 79226b19e3c4..cb3fb9dba8fb 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -156,13 +156,15 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) efx->net_dev->rx_cpu_rmap = NULL; #endif - /* Disable MSI/MSI-X interrupts */ - efx_for_each_channel(channel, efx) - free_irq(channel->irq, &efx->msi_context[channel->channel]); - - /* Disable legacy interrupt */ - if (efx->legacy_irq) + if (EFX_INT_MODE_USE_MSI(efx)) { + /* Disable MSI/MSI-X interrupts */ + efx_for_each_channel(channel, efx) + free_irq(channel->irq, + &efx->msi_context[channel->channel]); + } else { + /* Disable legacy interrupt */ free_irq(efx->legacy_irq, efx); + } } /* Register dump */ diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 75d11fa4eb0a..d79c842680a5 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -189,6 +189,18 @@ struct efx_short_copy_buffer { u8 buf[L1_CACHE_BYTES]; }; +/* Copy in explicit 64-bit writes. */ +static void efx_memcpy_64(void __iomem *dest, void *src, size_t len) +{ + u64 *src64 = src; + u64 __iomem *dest64 = dest; + size_t l64 = len / 8; + size_t i; + + for (i = 0; i < l64; i++) + writeq(src64[i], &dest64[i]); +} + /* Copy to PIO, respecting that writes to PIO buffers must be dword aligned. * Advances piobuf pointer. Leaves additional data in the copy buffer. */ @@ -198,7 +210,7 @@ static void efx_memcpy_toio_aligned(struct efx_nic *efx, u8 __iomem **piobuf, { int block_len = len & ~(sizeof(copy_buf->buf) - 1); - memcpy_toio(*piobuf, data, block_len); + efx_memcpy_64(*piobuf, data, block_len); *piobuf += block_len; len -= block_len; @@ -230,7 +242,7 @@ static void efx_memcpy_toio_aligned_cb(struct efx_nic *efx, u8 __iomem **piobuf, if (copy_buf->used < sizeof(copy_buf->buf)) return; - memcpy_toio(*piobuf, copy_buf->buf, sizeof(copy_buf->buf)); + efx_memcpy_64(*piobuf, copy_buf->buf, sizeof(copy_buf->buf)); *piobuf += sizeof(copy_buf->buf); data += copy_to_buf; len -= copy_to_buf; @@ -245,7 +257,7 @@ static void efx_flush_copy_buffer(struct efx_nic *efx, u8 __iomem *piobuf, { /* if there's anything in it, write the whole buffer, including junk */ if (copy_buf->used) - memcpy_toio(piobuf, copy_buf->buf, sizeof(copy_buf->buf)); + efx_memcpy_64(piobuf, copy_buf->buf, sizeof(copy_buf->buf)); } /* Traverse skb structure and copy fragments in to PIO buffer. @@ -304,8 +316,8 @@ efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb) */ BUILD_BUG_ON(L1_CACHE_BYTES > SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); - memcpy_toio(tx_queue->piobuf, skb->data, - ALIGN(skb->len, L1_CACHE_BYTES)); + efx_memcpy_64(tx_queue->piobuf, skb->data, + ALIGN(skb->len, L1_CACHE_BYTES)); } EFX_POPULATE_QWORD_5(buffer->option, diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 1c24a8f368bd..fd411d6e19a2 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -1083,6 +1083,24 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac) return vp; } +static void vnet_cleanup(void) +{ + struct vnet *vp; + struct net_device *dev; + + mutex_lock(&vnet_list_mutex); + while (!list_empty(&vnet_list)) { + vp = list_first_entry(&vnet_list, struct vnet, list); + list_del(&vp->list); + dev = vp->dev; + /* vio_unregister_driver() should have cleaned up port_list */ + BUG_ON(!list_empty(&vp->port_list)); + unregister_netdev(dev); + free_netdev(dev); + } + mutex_unlock(&vnet_list_mutex); +} + static const char *local_mac_prop = "local-mac-address"; static struct vnet *vnet_find_parent(struct mdesc_handle *hp, @@ -1240,7 +1258,6 @@ static int vnet_port_remove(struct vio_dev *vdev) kfree(port); - unregister_netdev(vp->dev); } return 0; } @@ -1268,6 +1285,7 @@ static int __init vnet_init(void) static void __exit vnet_exit(void) { vio_unregister_driver(&vnet_port_driver); + vnet_cleanup(); } module_init(vnet_init); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 7d6d8ec676c8..921b9df2faca 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1884,18 +1884,12 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); phyid = be32_to_cpup(parp+1); mdio = of_find_device_by_node(mdio_node); - - if (strncmp(mdio->name, "gpio", 4) == 0) { - /* GPIO bitbang MDIO driver attached */ - struct mii_bus *bus = dev_get_drvdata(&mdio->dev); - - snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, bus->id, phyid); - } else { - /* davinci MDIO driver attached */ - snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, mdio->name, phyid); + if (!mdio) { + pr_err("Missing mdio platform device\n"); + return -EINVAL; } + snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), + PHY_ID_FMT, mdio->name, phyid); mac_addr = of_get_mac_address(slave_node); if (mac_addr) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d6fce9750b95..3c1c33ceffba 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -146,6 +146,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) struct hv_netvsc_packet *packet; int ret; unsigned int i, num_pages, npg_data; + u32 skb_length = skb->len; /* Add multipages for skb->data and additional 2 for RNDIS */ npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1) @@ -216,7 +217,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) ret = rndis_filter_send(net_device_ctx->device_ctx, packet); if (ret == 0) { - net->stats.tx_bytes += skb->len; + net->stats.tx_bytes += skb_length; net->stats.tx_packets++; } else { kfree(packet); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 1831fb7cd017..fbf7dcdc22b0 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -263,11 +263,9 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; - __u8 ip_summed = skb->ip_summed; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = (void *)skb->data; - skb->ip_summed = CHECKSUM_UNNECESSARY; /* send to other bridge ports directly */ if (is_multicast_ether_addr(eth->h_dest)) { @@ -285,7 +283,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) } xmit_world: - skb->ip_summed = ip_summed; skb->dev = vlan->lowerdev; return dev_queue_xmit(skb); } @@ -461,8 +458,10 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change) struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; - if (change & IFF_ALLMULTI) - dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); + } } static void macvlan_set_mac_lists(struct net_device *dev) @@ -518,6 +517,11 @@ static struct lock_class_key macvlan_netdev_addr_lock_key; #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) +static int macvlan_get_nest_level(struct net_device *dev) +{ + return ((struct macvlan_dev *)netdev_priv(dev))->nest_level; +} + static void macvlan_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, void *_unused) @@ -528,8 +532,9 @@ static void macvlan_set_lockdep_class_one(struct net_device *dev, static void macvlan_set_lockdep_class(struct net_device *dev) { - lockdep_set_class(&dev->addr_list_lock, - &macvlan_netdev_addr_lock_key); + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &macvlan_netdev_addr_lock_key, + macvlan_get_nest_level(dev)); netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL); } @@ -543,6 +548,7 @@ static int macvlan_init(struct net_device *dev) (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; dev->features |= ALWAYS_ON_FEATURES; + dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->gso_max_size = lowerdev->gso_max_size; dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; @@ -703,6 +709,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev, features, mask); features |= ALWAYS_ON_FEATURES; + features &= ~NETIF_F_NETNS_LOCAL; return features; } @@ -731,6 +738,7 @@ static const struct net_device_ops macvlan_netdev_ops = { .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, + .ndo_get_lock_subclass = macvlan_get_nest_level, }; void macvlan_common_setup(struct net_device *dev) @@ -859,6 +867,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; + vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) @@ -1036,7 +1045,6 @@ static int macvlan_device_event(struct notifier_block *unused, list_for_each_entry_safe(vlan, next, &port->vlans, list) vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill); unregister_netdevice_many(&list_kill); - list_del(&list_kill); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index ff111a89e17f..f30ceb17d5fc 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -16,6 +16,7 @@ #include <linux/idr.h> #include <linux/fs.h> +#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> @@ -65,7 +66,7 @@ static struct cdev macvtap_cdev; static const struct proto_ops macvtap_socket_ops; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ - NETIF_F_TSO6 | NETIF_F_UFO) + NETIF_F_TSO6) #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG) @@ -112,17 +113,15 @@ out: return err; } +/* Requires RTNL */ static int macvtap_set_queue(struct net_device *dev, struct file *file, struct macvtap_queue *q) { struct macvlan_dev *vlan = netdev_priv(dev); - int err = -EBUSY; - rtnl_lock(); if (vlan->numqueues == MAX_MACVTAP_QUEUES) - goto out; + return -EBUSY; - err = 0; rcu_assign_pointer(q->vlan, vlan); rcu_assign_pointer(vlan->taps[vlan->numvtaps], q); sock_hold(&q->sk); @@ -136,9 +135,7 @@ static int macvtap_set_queue(struct net_device *dev, struct file *file, vlan->numvtaps++; vlan->numqueues++; -out: - rtnl_unlock(); - return err; + return 0; } static int macvtap_disable_queue(struct macvtap_queue *q) @@ -322,6 +319,15 @@ static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb) segs = nskb; } } else { + /* If we receive a partial checksum and the tap side + * doesn't support checksum offload, compute the checksum. + * Note: it doesn't matter which checksum feature to + * check, we either support them all or none. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + !(features & NETIF_F_ALL_CSUM) && + skb_checksum_help(skb)) + goto drop; skb_queue_tail(&q->sk.sk_receive_queue, skb); } @@ -445,11 +451,12 @@ static void macvtap_sock_destruct(struct sock *sk) static int macvtap_open(struct inode *inode, struct file *file) { struct net *net = current->nsproxy->net_ns; - struct net_device *dev = dev_get_by_macvtap_minor(iminor(inode)); + struct net_device *dev; struct macvtap_queue *q; - int err; + int err = -ENODEV; - err = -ENODEV; + rtnl_lock(); + dev = dev_get_by_macvtap_minor(iminor(inode)); if (!dev) goto out; @@ -489,6 +496,7 @@ out: if (dev) dev_put(dev); + rtnl_unlock(); return err; } @@ -562,7 +570,11 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: + pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n", + current->comm); gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; default: return -EINVAL; @@ -607,8 +619,6 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (sinfo->gso_type & SKB_GSO_TCP_ECN) @@ -943,9 +953,6 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) if (arg & TUN_F_TSO6) feature_mask |= NETIF_F_TSO6; } - - if (arg & TUN_F_UFO) - feature_mask |= NETIF_F_UFO; } /* tun/tap driver inverts the usage for TSO offloads, where @@ -956,7 +963,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) * When user space turns off TSO, we turn off GSO/LRO so that * user-space will not receive TSO frames. */ - if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO)) + if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6)) features |= RX_OFFLOADS; else features &= ~RX_OFFLOADS; @@ -1057,7 +1064,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN | TUN_F_UFO)) + TUN_F_TSO_ECN)) return -EINVAL; rtnl_lock(); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2f6989b1e0dc..25f74191a788 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -353,7 +353,7 @@ int phy_device_register(struct phy_device *phydev) phydev->bus->phy_map[phydev->addr] = phydev; /* Run all of the fixups for this PHY */ - err = phy_init_hw(phydev); + err = phy_scan_fixups(phydev); if (err) { pr_err("PHY %d failed to initialize\n", phydev->addr); goto out; @@ -613,8 +613,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, err = phy_init_hw(phydev); if (err) phy_detach(phydev); - - phy_resume(phydev); + else + phy_resume(phydev); return err; } diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 72ff14b811c6..5a1897d86e94 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -601,7 +601,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (file == ppp->owner) ppp_shutdown_interface(ppp); } - if (atomic_long_read(&file->f_count) <= 2) { + if (atomic_long_read(&file->f_count) < 2) { ppp_release(NULL, file); err = 0; } else diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 2ea7efd11857..6c9c16d76935 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -675,7 +675,7 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, po->chan.hdrlen = (sizeof(struct pppoe_hdr) + dev->hard_header_len); - po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr); + po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2; po->chan.private = sk; po->chan.ops = &pppoe_chan_ops; diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 01805319e1e0..1aff970be33e 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) nf_reset(skb); skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ip_send_check(iph); ip_local_out(skb); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index cc70ecfc7062..87526443841f 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -83,6 +83,7 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/workqueue.h> #include "slip.h" #ifdef CONFIG_INET #include <linux/ip.h> @@ -416,34 +417,44 @@ static void sl_encaps(struct slip *sl, unsigned char *icp, int len) #endif } -/* - * Called by the driver when there's room for more data. If we have - * more packets to send, we send them here. - */ -static void slip_write_wakeup(struct tty_struct *tty) +/* Write out any remaining transmit buffer. Scheduled when tty is writable */ +static void slip_transmit(struct work_struct *work) { + struct slip *sl = container_of(work, struct slip, tx_work); int actual; - struct slip *sl = tty->disc_data; + spin_lock_bh(&sl->lock); /* First make sure we're connected. */ - if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev)) + if (!sl->tty || sl->magic != SLIP_MAGIC || !netif_running(sl->dev)) { + spin_unlock_bh(&sl->lock); return; + } - spin_lock(&sl->lock); if (sl->xleft <= 0) { /* Now serial buffer is almost free & we can start * transmission of another packet */ sl->dev->stats.tx_packets++; - clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); - spin_unlock(&sl->lock); + clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags); + spin_unlock_bh(&sl->lock); sl_unlock(sl); return; } - actual = tty->ops->write(tty, sl->xhead, sl->xleft); + actual = sl->tty->ops->write(sl->tty, sl->xhead, sl->xleft); sl->xleft -= actual; sl->xhead += actual; - spin_unlock(&sl->lock); + spin_unlock_bh(&sl->lock); +} + +/* + * Called by the driver when there's room for more data. + * Schedule the transmit. + */ +static void slip_write_wakeup(struct tty_struct *tty) +{ + struct slip *sl = tty->disc_data; + + schedule_work(&sl->tx_work); } static void sl_tx_timeout(struct net_device *dev) @@ -749,6 +760,7 @@ static struct slip *sl_alloc(dev_t line) sl->magic = SLIP_MAGIC; sl->dev = dev; spin_lock_init(&sl->lock); + INIT_WORK(&sl->tx_work, slip_transmit); sl->mode = SL_MODE_DEFAULT; #ifdef CONFIG_SLIP_SMART /* initialize timer_list struct */ @@ -872,8 +884,12 @@ static void slip_close(struct tty_struct *tty) if (!sl || sl->magic != SLIP_MAGIC || sl->tty != tty) return; + spin_lock_bh(&sl->lock); tty->disc_data = NULL; sl->tty = NULL; + spin_unlock_bh(&sl->lock); + + flush_work(&sl->tx_work); /* VSV = very important to remove timers */ #ifdef CONFIG_SLIP_SMART diff --git a/drivers/net/slip/slip.h b/drivers/net/slip/slip.h index 67673cf1266b..cf32aadf508f 100644 --- a/drivers/net/slip/slip.h +++ b/drivers/net/slip/slip.h @@ -53,6 +53,7 @@ struct slip { struct tty_struct *tty; /* ptr to TTY structure */ struct net_device *dev; /* easy for intr handling */ spinlock_t lock; + struct work_struct tx_work; /* Flushes transmit buffer */ #ifdef SL_INCLUDE_CSLIP struct slcompress *slcomp; /* for header compression */ diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index c8624a8235ab..979fe433278c 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -647,7 +647,7 @@ static void team_notify_peers(struct team *team) { if (!team->notify_peers.count || !netif_running(team->dev)) return; - atomic_set(&team->notify_peers.count_pending, team->notify_peers.count); + atomic_add(team->notify_peers.count, &team->notify_peers.count_pending); schedule_delayed_work(&team->notify_peers.dw, 0); } @@ -687,7 +687,7 @@ static void team_mcast_rejoin(struct team *team) { if (!team->mcast_rejoin.count || !netif_running(team->dev)) return; - atomic_set(&team->mcast_rejoin.count_pending, team->mcast_rejoin.count); + atomic_add(team->mcast_rejoin.count, &team->mcast_rejoin.count_pending); schedule_delayed_work(&team->mcast_rejoin.dw, 0); } @@ -1732,6 +1732,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu) * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); + team->port_mtu_change_allowed = true; list_for_each_entry(port, &team->port_list, list) { err = dev_set_mtu(port->dev, new_mtu); if (err) { @@ -1740,6 +1741,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu) goto unwind; } } + team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); dev->mtu = new_mtu; @@ -1749,6 +1751,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu) unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) dev_set_mtu(port->dev, dev->mtu); + team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); return err; @@ -2857,7 +2860,9 @@ static int team_device_event(struct notifier_block *unused, break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ - return NOTIFY_BAD; + if (!port->team->port_mtu_change_allowed) + return NOTIFY_BAD; + break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid to change type of underlaying device */ return NOTIFY_BAD; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 26f8635b027d..2c8b1c21c452 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -65,6 +65,7 @@ #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> +#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> @@ -174,7 +175,7 @@ struct tun_struct { struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ - NETIF_F_TSO6|NETIF_F_UFO) + NETIF_F_TSO6) int vnet_hdr_sz; int sndbuf; @@ -1140,6 +1141,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, break; } + skb_reset_network_header(skb); + if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -1150,8 +1153,20 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: + { + static bool warned; + + if (!warned) { + warned = true; + netdev_warn(tun->dev, + "%s: using disabled UFO feature; please fix this program\n", + current->comm); + } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; + } default: tun->dev->stats.rx_frame_errors++; kfree_skb(skb); @@ -1180,7 +1195,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } - skb_reset_network_header(skb); skb_probe_transport_header(skb, 0); rxhash = skb_get_hash(skb); @@ -1252,8 +1266,6 @@ static ssize_t tun_put_user(struct tun_struct *tun, gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - gso.gso_type = VIRTIO_NET_HDR_GSO_UDP; else { pr_err("unexpected GSO type: " "0x%x, gso_size %d, hdr_len %d\n", @@ -1783,11 +1795,6 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } - - if (arg & TUN_F_UFO) { - features |= NETIF_F_UFO; - arg &= ~TUN_F_UFO; - } } /* This gives the user a way to test for new features in future by diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 054e59ca6946..8cee173eefb2 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -696,6 +696,7 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) { struct usbnet *dev = netdev_priv(net); struct sockaddr *addr = p; + int ret; if (netif_running(net)) return -EBUSY; @@ -705,8 +706,12 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) memcpy(net->dev_addr, addr->sa_data, ETH_ALEN); /* Set the MAC address */ - return ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, + ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, ETH_ALEN, net->dev_addr); + if (ret < 0) + return ret; + + return 0; } static const struct net_device_ops ax88179_netdev_ops = { diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index c9f3281506af..2e025ddcef21 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -120,6 +120,16 @@ static void cdc_mbim_unbind(struct usbnet *dev, struct usb_interface *intf) cdc_ncm_unbind(dev, intf); } +/* verify that the ethernet protocol is IPv4 or IPv6 */ +static bool is_ip_proto(__be16 proto) +{ + switch (proto) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + return true; + } + return false; +} static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) { @@ -128,6 +138,7 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb struct cdc_ncm_ctx *ctx = info->ctx; __le32 sign = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN); u16 tci = 0; + bool is_ip; u8 *c; if (!ctx) @@ -137,25 +148,32 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb if (skb->len <= ETH_HLEN) goto error; + /* Some applications using e.g. packet sockets will + * bypass the VLAN acceleration and create tagged + * ethernet frames directly. We primarily look for + * the accelerated out-of-band tag, but fall back if + * required + */ + skb_reset_mac_header(skb); + if (vlan_get_tag(skb, &tci) < 0 && skb->len > VLAN_ETH_HLEN && + __vlan_get_tag(skb, &tci) == 0) { + is_ip = is_ip_proto(vlan_eth_hdr(skb)->h_vlan_encapsulated_proto); + skb_pull(skb, VLAN_ETH_HLEN); + } else { + is_ip = is_ip_proto(eth_hdr(skb)->h_proto); + skb_pull(skb, ETH_HLEN); + } + /* mapping VLANs to MBIM sessions: * no tag => IPS session <0> * 1 - 255 => IPS session <vlanid> * 256 - 511 => DSS session <vlanid - 256> * 512 - 4095 => unsupported, drop */ - vlan_get_tag(skb, &tci); - switch (tci & 0x0f00) { case 0x0000: /* VLAN ID 0 - 255 */ - /* verify that datagram is IPv4 or IPv6 */ - skb_reset_mac_header(skb); - switch (eth_hdr(skb)->h_proto) { - case htons(ETH_P_IP): - case htons(ETH_P_IPV6): - break; - default: + if (!is_ip) goto error; - } c = (u8 *)&sign; c[3] = tci; break; @@ -169,7 +187,6 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb "unsupported tci=0x%04x\n", tci); goto error; } - skb_pull(skb, ETH_HLEN); } spin_lock_bh(&ctx->mtx); @@ -204,17 +221,23 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci) return; /* need to send the NA on the VLAN dev, if any */ - if (tci) + rcu_read_lock(); + if (tci) { netdev = __vlan_find_dev_deep(dev->net, htons(ETH_P_8021Q), tci); - else + if (!netdev) { + rcu_read_unlock(); + return; + } + } else { netdev = dev->net; - if (!netdev) - return; + } + dev_hold(netdev); + rcu_read_unlock(); in6_dev = in6_dev_get(netdev); if (!in6_dev) - return; + goto out; is_router = !!in6_dev->cnf.forwarding; in6_dev_put(in6_dev); @@ -224,6 +247,8 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci) true /* solicited */, false /* override */, true /* inc_opt */); +out: + dev_put(netdev); } static bool is_neigh_solicit(u8 *buf, size_t len) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index d350d2795e10..75d7d9dbbe35 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -768,7 +768,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) skb_out->len > CDC_NCM_MIN_TX_PKT) memset(skb_put(skb_out, ctx->tx_max - skb_out->len), 0, ctx->tx_max - skb_out->len); - else if ((skb_out->len % dev->maxpacket) == 0) + else if (skb_out->len < ctx->tx_max && (skb_out->len % dev->maxpacket) == 0) *skb_put(skb_out, 1) = 0; /* force short packet */ /* set final frame length */ diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index 312178d7b698..a01462523bc7 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -84,12 +84,13 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, ctx = drvstate->ctx; if (usbnet_dev->status) - /* CDC-WMC r1.1 requires wMaxCommand to be "at least 256 - * decimal (0x100)" + /* The wMaxCommand buffer must be big enough to hold + * any message from the modem. Experience has shown + * that some replies are more than 256 bytes long */ subdriver = usb_cdc_wdm_register(ctx->control, &usbnet_dev->status->desc, - 256, /* wMaxCommand */ + 1024, /* wMaxCommand */ huawei_cdc_ncm_wdm_manage_power); if (IS_ERR(subdriver)) { ret = PTR_ERR(subdriver); @@ -206,6 +207,9 @@ static const struct usb_device_id huawei_cdc_ncm_devs[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x76), .driver_info = (unsigned long)&huawei_cdc_ncm_info, }, + { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x03, 0x16), + .driver_info = (unsigned long)&huawei_cdc_ncm_info, + }, /* Terminating entry */ { diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 313cb6cd4848..d510f1d41bae 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -660,8 +660,25 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x05c6, 0x9084, 4)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 0)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 5)}, + {QMI_FIXED_INTF(0x0846, 0x68a2, 8)}, {QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */ {QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */ + {QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */ + {QMI_FIXED_INTF(0x16d8, 0x6007, 0)}, /* CMOTech CHE-628S */ + {QMI_FIXED_INTF(0x16d8, 0x6008, 0)}, /* CMOTech CMU-301 */ + {QMI_FIXED_INTF(0x16d8, 0x6280, 0)}, /* CMOTech CHU-628 */ + {QMI_FIXED_INTF(0x16d8, 0x7001, 0)}, /* CMOTech CHU-720S */ + {QMI_FIXED_INTF(0x16d8, 0x7002, 0)}, /* CMOTech 7002 */ + {QMI_FIXED_INTF(0x16d8, 0x7003, 4)}, /* CMOTech CHU-629K */ + {QMI_FIXED_INTF(0x16d8, 0x7004, 3)}, /* CMOTech 7004 */ + {QMI_FIXED_INTF(0x16d8, 0x7006, 5)}, /* CMOTech CGU-629 */ + {QMI_FIXED_INTF(0x16d8, 0x700a, 4)}, /* CMOTech CHU-629S */ + {QMI_FIXED_INTF(0x16d8, 0x7211, 0)}, /* CMOTech CHU-720I */ + {QMI_FIXED_INTF(0x16d8, 0x7212, 0)}, /* CMOTech 7212 */ + {QMI_FIXED_INTF(0x16d8, 0x7213, 0)}, /* CMOTech 7213 */ + {QMI_FIXED_INTF(0x16d8, 0x7251, 1)}, /* CMOTech 7251 */ + {QMI_FIXED_INTF(0x16d8, 0x7252, 1)}, /* CMOTech 7252 */ + {QMI_FIXED_INTF(0x16d8, 0x7253, 1)}, /* CMOTech 7253 */ {QMI_FIXED_INTF(0x19d2, 0x0002, 1)}, {QMI_FIXED_INTF(0x19d2, 0x0012, 1)}, {QMI_FIXED_INTF(0x19d2, 0x0017, 3)}, @@ -718,21 +735,40 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1424, 2)}, {QMI_FIXED_INTF(0x19d2, 0x1425, 2)}, {QMI_FIXED_INTF(0x19d2, 0x1426, 2)}, /* ZTE MF91 */ + {QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */ {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ {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 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */ + {QMI_FIXED_INTF(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC73xx */ + {QMI_FIXED_INTF(0x1199, 0x68c0, 10)}, /* Sierra Wireless MC73xx */ + {QMI_FIXED_INTF(0x1199, 0x68c0, 11)}, /* Sierra Wireless MC73xx */ {QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */ + {QMI_FIXED_INTF(0x1199, 0x901f, 8)}, /* Sierra Wireless EM7355 */ + {QMI_FIXED_INTF(0x1199, 0x9041, 8)}, /* Sierra Wireless MC7305/MC7355 */ {QMI_FIXED_INTF(0x1199, 0x9051, 8)}, /* Netgear AirCard 340U */ + {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {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 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ - {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */ + {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */ + {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */ + {QMI_FIXED_INTF(0x0b3c, 0xc002, 4)}, /* Olivetti Olicard 140 */ + {QMI_FIXED_INTF(0x0b3c, 0xc004, 6)}, /* Olivetti Olicard 155 */ + {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */ + {QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)}, /* Olivetti Olicard 160 */ + {QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)}, /* Olivetti Olicard 500 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */ + {QMI_FIXED_INTF(0x413c, 0x81a2, 8)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81a3, 8)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 841b60831df1..07a3255fd3cc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -496,8 +496,17 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_UDP: + { + static bool warned; + + if (!warned) { + warned = true; + netdev_warn(dev, + "host using disabled UFO feature; please fix it\n"); + } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; break; + } case VIRTIO_NET_HDR_GSO_TCPV6: skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; @@ -836,8 +845,6 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) - hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN) @@ -1657,7 +1664,7 @@ static int virtnet_probe(struct virtio_device *vdev) dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { - dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO + dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6; } /* Individual feature bits: what can host handle? */ @@ -1667,11 +1674,9 @@ static int virtnet_probe(struct virtio_device *vdev) dev->hw_features |= NETIF_F_TSO6; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN)) dev->hw_features |= NETIF_F_TSO_ECN; - if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO)) - dev->hw_features |= NETIF_F_UFO; if (gso) - dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO); + dev->features |= dev->hw_features & NETIF_F_ALL_TSO; /* (!csum && gso) case will be fixed by register_netdev() */ } if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) @@ -1711,8 +1716,7 @@ static int virtnet_probe(struct virtio_device *vdev) /* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO)) + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) vi->big_packets = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) @@ -1903,9 +1907,9 @@ static struct virtio_device_id id_table[] = { static unsigned int features[] = { VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC, - VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, + VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6, VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, - VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, + VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1236812c7be6..0704a0402897 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -871,6 +871,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (err) return err; + if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) + return -EAFNOSUPPORT; + spin_lock_bh(&vxlan->hash_lock); err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags, port, vni, ifindex, ndm->ndm_flags); @@ -1331,7 +1334,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1444,9 +1447,6 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) if (!in6_dev) goto out; - if (!pskb_may_pull(skb, skb->len)) - goto out; - iphdr = ipv6_hdr(skb); saddr = &iphdr->saddr; daddr = &iphdr->daddr; @@ -1492,7 +1492,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); @@ -1525,7 +1525,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1546,7 +1546,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); @@ -1767,6 +1767,8 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; + struct net_device *dev = skb->dev; + int len = skb->len; tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); @@ -1790,16 +1792,16 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; - tx_stats->tx_bytes += skb->len; + tx_stats->tx_bytes += len; u64_stats_update_end(&tx_stats->syncp); if (netif_rx(skb) == NET_RX_SUCCESS) { u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; - rx_stats->rx_bytes += skb->len; + rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { - skb->dev->stats.rx_dropped++; + dev->stats.rx_dropped++; } } @@ -1974,7 +1976,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) return arp_reduce(dev, skb); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && - skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *msg; @@ -1983,6 +1986,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb); } + eth = eth_hdr(skb); #endif } @@ -2279,9 +2283,9 @@ static void vxlan_setup(struct net_device *dev) eth_hw_addr_random(dev); ether_setup(dev); if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6) - dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM; + dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM; else - dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM; + dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM; dev->netdev_ops = &vxlan_netdev_ops; dev->destructor = free_netdev; @@ -2612,9 +2616,10 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, vni = nla_get_u32(data[IFLA_VXLAN_ID]); dst->remote_vni = vni; + /* Unless IPv6 is explicitly requested, assume IPv4 */ + dst->remote_ip.sa.sa_family = AF_INET; if (data[IFLA_VXLAN_GROUP]) { dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]); - dst->remote_ip.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_GROUP6]) { if (!IS_ENABLED(CONFIG_IPV6)) return -EPFNOSUPPORT; @@ -2663,8 +2668,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (!tb[IFLA_MTU]) dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); - /* update header length based on lower device */ - dev->hard_header_len = lowerdev->hard_header_len + + dev->needed_headroom = lowerdev->hard_header_len + (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); } else if (use_ipv6) vxlan->flags |= VXLAN_F_IPV6; diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 55897d508a76..0fe7674ad100 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -890,6 +890,15 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq, tx_info = IEEE80211_SKB_CB(skb); tx_info->flags &= ~IEEE80211_TX_CTL_CLEAR_PS_FILT; + + /* + * No aggregation session is running, but there may be frames + * from a previous session or a failed attempt in the queue. + * Send them out as normal data frames + */ + if (!tid->active) + tx_info->flags &= ~IEEE80211_TX_CTL_AMPDU; + if (!(tx_info->flags & IEEE80211_TX_CTL_AMPDU)) { bf->bf_state.bf_type = 0; return bf; @@ -1698,7 +1707,7 @@ int ath_cabq_update(struct ath_softc *sc) ath9k_hw_get_txq_props(sc->sc_ah, qnum, &qi); - qi.tqi_readyTime = (cur_conf->beacon_interval * + qi.tqi_readyTime = (TU_TO_USEC(cur_conf->beacon_interval) * ATH_CABQ_READY_TIME) / 100; ath_txq_update(sc, qnum, &qi); diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h index 8596aba34f96..237d0cda1bcb 100644 --- a/drivers/net/wireless/ath/carl9170/carl9170.h +++ b/drivers/net/wireless/ath/carl9170/carl9170.h @@ -256,6 +256,7 @@ struct ar9170 { atomic_t rx_work_urbs; atomic_t rx_pool_urbs; kernel_ulong_t features; + bool usb_ep_cmd_is_bulk; /* firmware settings */ struct completion fw_load_wait; diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c index ca115f33746f..bc931f6f1f0f 100644 --- a/drivers/net/wireless/ath/carl9170/usb.c +++ b/drivers/net/wireless/ath/carl9170/usb.c @@ -621,9 +621,16 @@ int __carl9170_exec_cmd(struct ar9170 *ar, struct carl9170_cmd *cmd, goto err_free; } - usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev, - AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4, - carl9170_usb_cmd_complete, ar, 1); + if (ar->usb_ep_cmd_is_bulk) + usb_fill_bulk_urb(urb, ar->udev, + usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD), + cmd, cmd->hdr.len + 4, + carl9170_usb_cmd_complete, ar); + else + usb_fill_int_urb(urb, ar->udev, + usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD), + cmd, cmd->hdr.len + 4, + carl9170_usb_cmd_complete, ar, 1); if (free_buf) urb->transfer_flags |= URB_FREE_BUFFER; @@ -1032,9 +1039,10 @@ static void carl9170_usb_firmware_step2(const struct firmware *fw, static int carl9170_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_endpoint_descriptor *ep; struct ar9170 *ar; struct usb_device *udev; - int err; + int i, err; err = usb_reset_device(interface_to_usbdev(intf)); if (err) @@ -1050,6 +1058,21 @@ static int carl9170_usb_probe(struct usb_interface *intf, ar->intf = intf; ar->features = id->driver_info; + /* We need to remember the type of endpoint 4 because it differs + * between high- and full-speed configuration. The high-speed + * configuration specifies it as interrupt and the full-speed + * configuration as bulk endpoint. This information is required + * later when sending urbs to that endpoint. + */ + for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) { + ep = &intf->cur_altsetting->endpoint[i].desc; + + if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD && + usb_endpoint_dir_out(ep) && + usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK) + ar->usb_ep_cmd_is_bulk = true; + } + usb_set_intfdata(intf, ar); SET_IEEE80211_DEV(ar->hw, &intf->dev); diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c index 05ee7f10cc8f..24ccbe96e0c8 100644 --- a/drivers/net/wireless/b43/phy_n.c +++ b/drivers/net/wireless/b43/phy_n.c @@ -5176,22 +5176,22 @@ static void b43_nphy_channel_setup(struct b43_wldev *dev, int ch = new_channel->hw_value; u16 old_band_5ghz; - u32 tmp32; + u16 tmp16; old_band_5ghz = b43_phy_read(dev, B43_NPHY_BANDCTL) & B43_NPHY_BANDCTL_5GHZ; if (new_channel->band == IEEE80211_BAND_5GHZ && !old_band_5ghz) { - tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR); - b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4); + tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR); + b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4); b43_phy_set(dev, B43_PHY_B_BBCFG, 0xC000); - b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32); + b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16); b43_phy_set(dev, B43_NPHY_BANDCTL, B43_NPHY_BANDCTL_5GHZ); } else if (new_channel->band == IEEE80211_BAND_2GHZ && old_band_5ghz) { b43_phy_mask(dev, B43_NPHY_BANDCTL, ~B43_NPHY_BANDCTL_5GHZ); - tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR); - b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4); + tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR); + b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4); b43_phy_mask(dev, B43_PHY_B_BBCFG, 0x3FFF); - b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32); + b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16); } b43_chantab_phy_upload(dev, e); diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c index 50e5ddb12fb3..628ff628e04a 100644 --- a/drivers/net/wireless/b43/xmit.c +++ b/drivers/net/wireless/b43/xmit.c @@ -810,9 +810,13 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr) break; case B43_PHYTYPE_G: status.band = IEEE80211_BAND_2GHZ; - /* chanid is the radio channel cookie value as used - * to tune the radio. */ - status.freq = chanid + 2400; + /* Somewhere between 478.104 and 508.1084 firmware for G-PHY + * has been modified to be compatible with N-PHY and others. + */ + if (dev->fw.rev >= 508) + status.freq = ieee80211_channel_to_frequency(chanid, status.band); + else + status.freq = chanid + 2400; break; case B43_PHYTYPE_N: case B43_PHYTYPE_LP: diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c index fad77dd2a3a5..3f9cb894d001 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c @@ -185,7 +185,13 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr, ifevent->action, ifevent->ifidx, ifevent->bssidx, ifevent->flags, ifevent->role); - if (ifevent->flags & BRCMF_E_IF_FLAG_NOIF) { + /* The P2P Device interface event must not be ignored + * contrary to what firmware tells us. The only way to + * distinguish the P2P Device is by looking at the ifidx + * and bssidx received. + */ + if (!(ifevent->ifidx == 0 && ifevent->bssidx == 1) && + (ifevent->flags & BRCMF_E_IF_FLAG_NOIF)) { brcmf_dbg(EVENT, "event can be ignored\n"); return; } @@ -210,12 +216,12 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr, return; } - if (ifevent->action == BRCMF_E_IF_CHANGE) + if (ifp && ifevent->action == BRCMF_E_IF_CHANGE) brcmf_fws_reset_interface(ifp); err = brcmf_fweh_call_event_handler(ifp, emsg->event_code, emsg, data); - if (ifevent->action == BRCMF_E_IF_DEL) { + if (ifp && ifevent->action == BRCMF_E_IF_DEL) { brcmf_fws_del_interface(ifp); brcmf_del_if(drvr, ifevent->bssidx); } diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h index 51b53a73d074..d26b47698f68 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h +++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h @@ -167,6 +167,8 @@ enum brcmf_fweh_event_code { #define BRCMF_E_IF_ROLE_STA 0 #define BRCMF_E_IF_ROLE_AP 1 #define BRCMF_E_IF_ROLE_WDS 2 +#define BRCMF_E_IF_ROLE_P2P_GO 3 +#define BRCMF_E_IF_ROLE_P2P_CLIENT 4 /** * definitions for event packet validation. diff --git a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c index 82bf3c5d3cdc..2de2736eb332 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c @@ -300,10 +300,10 @@ brcmf_sdio_ai_coredisable(struct brcmf_sdio_dev *sdiodev, wrapbase = ci->c_inf[idx].wrapbase; - /* if core is already in reset, just return */ + /* if core is already in reset, skip reset */ regdata = brcmf_sdiod_regrl(sdiodev, wrapbase + BCMA_RESET_CTL, NULL); if ((regdata & BCMA_RESET_CTL_RESET) != 0) - return; + goto post_reset_config; /* configure reset */ brcmf_sdiod_regwl(sdiodev, wrapbase + BCMA_IOCTL, pre_resetbits | @@ -319,6 +319,7 @@ brcmf_sdio_ai_coredisable(struct brcmf_sdio_dev *sdiodev, SPINWAIT(brcmf_sdiod_regrl(sdiodev, wrapbase + BCMA_RESET_CTL, NULL) != BCMA_RESET_CTL_RESET, 300); +post_reset_config: /* post reset configure */ brcmf_sdiod_regwl(sdiodev, wrapbase + BCMA_IOCTL, pre_resetbits | BCMA_IOCTL_FGC | BCMA_IOCTL_CLK, NULL); diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c index 925034b80e9c..93598cd7ee6a 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c @@ -426,6 +426,12 @@ static int brcms_ops_start(struct ieee80211_hw *hw) bool blocked; int err; + if (!wl->ucode.bcm43xx_bomminor) { + err = brcms_request_fw(wl, wl->wlc->hw->d11core); + if (err) + return -ENOENT; + } + ieee80211_wake_queues(hw); spin_lock_bh(&wl->lock); blocked = brcms_rfkill_set_hw_state(wl); @@ -433,14 +439,6 @@ static int brcms_ops_start(struct ieee80211_hw *hw) if (!blocked) wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy); - if (!wl->ucode.bcm43xx_bomminor) { - err = brcms_request_fw(wl, wl->wlc->hw->d11core); - if (err) { - brcms_remove(wl->wlc->hw->d11core); - return -ENOENT; - } - } - spin_lock_bh(&wl->lock); /* avoid acknowledging frames before a non-monitor device is added */ wl->mute_tx = true; diff --git a/drivers/net/wireless/iwlwifi/dvm/main.c b/drivers/net/wireless/iwlwifi/dvm/main.c index ba1b1ea54252..ea7e70cb34f0 100644 --- a/drivers/net/wireless/iwlwifi/dvm/main.c +++ b/drivers/net/wireless/iwlwifi/dvm/main.c @@ -252,13 +252,17 @@ static void iwl_bg_bt_runtime_config(struct work_struct *work) struct iwl_priv *priv = container_of(work, struct iwl_priv, bt_runtime_config); + mutex_lock(&priv->mutex); if (test_bit(STATUS_EXIT_PENDING, &priv->status)) - return; + goto out; /* dont send host command if rf-kill is on */ if (!iwl_is_ready_rf(priv)) - return; + goto out; + iwlagn_send_advance_bt_config(priv); +out: + mutex_unlock(&priv->mutex); } static void iwl_bg_bt_full_concurrency(struct work_struct *work) diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c index 2a59da2ff87a..e1d546665ae8 100644 --- a/drivers/net/wireless/iwlwifi/iwl-7000.c +++ b/drivers/net/wireless/iwlwifi/iwl-7000.c @@ -67,8 +67,8 @@ #include "iwl-agn-hw.h" /* Highest firmware API version supported */ -#define IWL7260_UCODE_API_MAX 8 -#define IWL3160_UCODE_API_MAX 8 +#define IWL7260_UCODE_API_MAX 9 +#define IWL3160_UCODE_API_MAX 9 /* Oldest version we won't warn about */ #define IWL7260_UCODE_API_OK 7 @@ -223,3 +223,4 @@ const struct iwl_cfg iwl7265_n_cfg = { MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL3160_UCODE_API_OK)); +MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h index 1ced525157dc..b45d78f53f08 100644 --- a/drivers/net/wireless/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/iwlwifi/iwl-config.h @@ -119,6 +119,8 @@ enum iwl_led_mode { #define IWL_LONG_WD_TIMEOUT 10000 #define IWL_MAX_WD_TIMEOUT 120000 +#define IWL_DEFAULT_MAX_TX_POWER 22 + /* Antenna presence definitions */ #define ANT_NONE 0x0 #define ANT_A BIT(0) diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c index 725e954d8475..3c3eb7842c62 100644 --- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c @@ -118,8 +118,6 @@ static const u8 iwl_nvm_channels[] = { #define LAST_2GHZ_HT_PLUS 9 #define LAST_5GHZ_HT 161 -#define DEFAULT_MAX_TX_POWER 16 - /* rate data (static) */ static struct ieee80211_rate iwl_cfg80211_rates[] = { { .bitrate = 1 * 10, .hw_value = 0, .hw_value_short = 0, }, @@ -242,7 +240,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg, * Default value - highest tx power value. max_power * is not used in mvm, and is used for backwards compatibility */ - channel->max_power = DEFAULT_MAX_TX_POWER; + channel->max_power = IWL_DEFAULT_MAX_TX_POWER; is_5ghz = channel->band == IEEE80211_BAND_5GHZ; IWL_DEBUG_EEPROM(dev, "Ch. %d [%sGHz] %s%s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n", diff --git a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c index 18a895a949d4..6b22681068a7 100644 --- a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c +++ b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c @@ -188,7 +188,7 @@ static const __le32 iwl_combined_lookup[BT_COEX_MAX_LUT][BT_COEX_LUT_SIZE] = { cpu_to_le32(0xcc00aaaa), cpu_to_le32(0x0000aaaa), cpu_to_le32(0xc0004000), - cpu_to_le32(0x00000000), + cpu_to_le32(0x00004000), cpu_to_le32(0xf0005000), cpu_to_le32(0xf0005000), }, @@ -211,16 +211,16 @@ static const __le32 iwl_combined_lookup[BT_COEX_MAX_LUT][BT_COEX_LUT_SIZE] = { /* Tx Tx disabled */ cpu_to_le32(0xaaaaaaaa), cpu_to_le32(0xaaaaaaaa), - cpu_to_le32(0xaaaaaaaa), + cpu_to_le32(0xeeaaaaaa), cpu_to_le32(0xaaaaaaaa), cpu_to_le32(0xcc00ff28), cpu_to_le32(0x0000aaaa), cpu_to_le32(0xcc00aaaa), cpu_to_le32(0x0000aaaa), - cpu_to_le32(0xC0004000), - cpu_to_le32(0xC0004000), - cpu_to_le32(0xF0005000), - cpu_to_le32(0xF0005000), + cpu_to_le32(0xc0004000), + cpu_to_le32(0xc0004000), + cpu_to_le32(0xf0005000), + cpu_to_le32(0xf0005000), }, }; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h index 989d7dbdca6c..d0a04779d734 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h +++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h @@ -1415,14 +1415,14 @@ enum iwl_sf_scenario { /** * Smart Fifo configuration command. - * @state: smart fifo state, types listed in iwl_sf_sate. + * @state: smart fifo state, types listed in enum %iwl_sf_sate. * @watermark: Minimum allowed availabe free space in RXF for transient state. * @long_delay_timeouts: aging and idle timer values for each scenario * in long delay state. * @full_on_timeouts: timer values for each scenario in full on state. */ struct iwl_sf_cfg_cmd { - enum iwl_sf_state state; + __le32 state; __le32 watermark[SF_TRANSIENT_STATES_NUMBER]; __le32 long_delay_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES]; __le32 full_on_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES]; diff --git a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c index ba723d50939a..820797af7abf 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c @@ -651,13 +651,9 @@ static void iwl_mvm_mac_ctxt_cmd_common(struct iwl_mvm *mvm, if (vif->bss_conf.qos) cmd->qos_flags |= cpu_to_le32(MAC_QOS_FLG_UPDATE_EDCA); - /* Don't use cts to self as the fw doesn't support it currently. */ - if (vif->bss_conf.use_cts_prot) { + if (vif->bss_conf.use_cts_prot) cmd->protection_flags |= cpu_to_le32(MAC_PROT_FLG_TGG_PROTECT); - if (IWL_UCODE_API(mvm->fw->ucode_ver) >= 8) - cmd->protection_flags |= - cpu_to_le32(MAC_PROT_FLG_SELF_CTS_EN); - } + IWL_DEBUG_RATE(mvm, "use_cts_prot %d, ht_operation_mode %d\n", vif->bss_conf.use_cts_prot, vif->bss_conf.ht_operation_mode); diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index c35b8661b395..d06414ef15c5 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -179,7 +179,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) !iwlwifi_mod_params.sw_crypto) hw->flags |= IEEE80211_HW_MFP_CAPABLE; - if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT) { + if (0 && mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT) { hw->flags |= IEEE80211_HW_SUPPORTS_UAPSD; hw->uapsd_queues = IWL_UAPSD_AC_INFO; hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP; @@ -606,7 +606,7 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, if (ret) goto out_remove_mac; - if (!mvm->bf_allowed_vif && + if (!mvm->bf_allowed_vif && false && vif->type == NL80211_IFTYPE_STATION && !vif->p2p && mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BF_UPDATED){ mvm->bf_allowed_vif = mvmvif; @@ -796,7 +796,7 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac, memcpy(cmd->bssid, vif->bss_conf.bssid, ETH_ALEN); len = roundup(sizeof(*cmd) + cmd->count * ETH_ALEN, 4); - ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_SYNC, len, cmd); + ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_ASYNC, len, cmd); if (ret) IWL_ERR(mvm, "mcast filter cmd error. ret=%d\n", ret); } @@ -812,7 +812,7 @@ static void iwl_mvm_recalc_multicast(struct iwl_mvm *mvm) if (WARN_ON_ONCE(!mvm->mcast_filter_cmd)) return; - ieee80211_iterate_active_interfaces( + ieee80211_iterate_active_interfaces_atomic( mvm->hw, IEEE80211_IFACE_ITER_NORMAL, iwl_mvm_mc_iface_iterator, &iter_data); } @@ -971,6 +971,7 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm, */ iwl_mvm_remove_time_event(mvm, mvmvif, &mvmvif->time_event_data); + iwl_mvm_sf_update(mvm, vif, false); } else if (changes & (BSS_CHANGED_PS | BSS_CHANGED_P2P_PS | BSS_CHANGED_QOS)) { ret = iwl_mvm_power_update_mode(mvm, vif); diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c index 6abf74e1351f..03179d0b08c2 100644 --- a/drivers/net/wireless/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/iwlwifi/mvm/rs.c @@ -59,7 +59,7 @@ /* max allowed rate miss before sync LQ cmd */ #define IWL_MISSED_RATE_MAX 15 #define RS_STAY_IN_COLUMN_TIMEOUT (5*HZ) - +#define RS_IDLE_TIMEOUT (5*HZ) static u8 rs_ht_to_legacy[] = { [IWL_RATE_MCS_0_INDEX] = IWL_RATE_6M_INDEX, @@ -142,7 +142,7 @@ enum rs_column_mode { RS_MIMO2, }; -#define MAX_NEXT_COLUMNS 5 +#define MAX_NEXT_COLUMNS 7 #define MAX_COLUMN_CHECKS 3 typedef bool (*allow_column_func_t) (struct iwl_mvm *mvm, @@ -211,7 +211,9 @@ static const struct rs_tx_column rs_tx_columns[] = { .next_columns = { RS_COLUMN_LEGACY_ANT_B, RS_COLUMN_SISO_ANT_A, - RS_COLUMN_MIMO2, + RS_COLUMN_SISO_ANT_B, + RS_COLUMN_INVALID, + RS_COLUMN_INVALID, RS_COLUMN_INVALID, RS_COLUMN_INVALID, }, @@ -221,8 +223,10 @@ static const struct rs_tx_column rs_tx_columns[] = { .ant = ANT_B, .next_columns = { RS_COLUMN_LEGACY_ANT_A, + RS_COLUMN_SISO_ANT_A, RS_COLUMN_SISO_ANT_B, - RS_COLUMN_MIMO2, + RS_COLUMN_INVALID, + RS_COLUMN_INVALID, RS_COLUMN_INVALID, RS_COLUMN_INVALID, }, @@ -234,7 +238,9 @@ static const struct rs_tx_column rs_tx_columns[] = { RS_COLUMN_SISO_ANT_B, RS_COLUMN_MIMO2, RS_COLUMN_SISO_ANT_A_SGI, - RS_COLUMN_INVALID, + RS_COLUMN_SISO_ANT_B_SGI, + RS_COLUMN_LEGACY_ANT_A, + RS_COLUMN_LEGACY_ANT_B, RS_COLUMN_INVALID, }, .checks = { @@ -248,7 +254,9 @@ static const struct rs_tx_column rs_tx_columns[] = { RS_COLUMN_SISO_ANT_A, RS_COLUMN_MIMO2, RS_COLUMN_SISO_ANT_B_SGI, - RS_COLUMN_INVALID, + RS_COLUMN_SISO_ANT_A_SGI, + RS_COLUMN_LEGACY_ANT_A, + RS_COLUMN_LEGACY_ANT_B, RS_COLUMN_INVALID, }, .checks = { @@ -263,8 +271,10 @@ static const struct rs_tx_column rs_tx_columns[] = { RS_COLUMN_SISO_ANT_B_SGI, RS_COLUMN_MIMO2_SGI, RS_COLUMN_SISO_ANT_A, - RS_COLUMN_INVALID, - RS_COLUMN_INVALID, + RS_COLUMN_SISO_ANT_B, + RS_COLUMN_MIMO2, + RS_COLUMN_LEGACY_ANT_A, + RS_COLUMN_LEGACY_ANT_B, }, .checks = { rs_siso_allow, @@ -279,8 +289,10 @@ static const struct rs_tx_column rs_tx_columns[] = { RS_COLUMN_SISO_ANT_A_SGI, RS_COLUMN_MIMO2_SGI, RS_COLUMN_SISO_ANT_B, - RS_COLUMN_INVALID, - RS_COLUMN_INVALID, + RS_COLUMN_SISO_ANT_A, + RS_COLUMN_MIMO2, + RS_COLUMN_LEGACY_ANT_A, + RS_COLUMN_LEGACY_ANT_B, }, .checks = { rs_siso_allow, @@ -292,10 +304,12 @@ static const struct rs_tx_column rs_tx_columns[] = { .ant = ANT_AB, .next_columns = { RS_COLUMN_SISO_ANT_A, + RS_COLUMN_SISO_ANT_B, + RS_COLUMN_SISO_ANT_A_SGI, + RS_COLUMN_SISO_ANT_B_SGI, RS_COLUMN_MIMO2_SGI, - RS_COLUMN_INVALID, - RS_COLUMN_INVALID, - RS_COLUMN_INVALID, + RS_COLUMN_LEGACY_ANT_A, + RS_COLUMN_LEGACY_ANT_B, }, .checks = { rs_mimo_allow, @@ -307,10 +321,12 @@ static const struct rs_tx_column rs_tx_columns[] = { .sgi = true, .next_columns = { RS_COLUMN_SISO_ANT_A_SGI, + RS_COLUMN_SISO_ANT_B_SGI, + RS_COLUMN_SISO_ANT_A, + RS_COLUMN_SISO_ANT_B, RS_COLUMN_MIMO2, - RS_COLUMN_INVALID, - RS_COLUMN_INVALID, - RS_COLUMN_INVALID, + RS_COLUMN_LEGACY_ANT_A, + RS_COLUMN_LEGACY_ANT_B, }, .checks = { rs_mimo_allow, @@ -503,6 +519,16 @@ static void rs_rate_scale_clear_window(struct iwl_rate_scale_data *window) window->average_tpt = IWL_INVALID_VALUE; } +static void rs_rate_scale_clear_tbl_windows(struct iwl_mvm *mvm, + struct iwl_scale_tbl_info *tbl) +{ + int i; + + IWL_DEBUG_RATE(mvm, "Clearing up window stats\n"); + for (i = 0; i < IWL_RATE_COUNT; i++) + rs_rate_scale_clear_window(&tbl->win[i]); +} + static inline u8 rs_is_valid_ant(u8 valid_antenna, u8 ant_type) { return (ant_type & valid_antenna) == ant_type; @@ -975,6 +1001,13 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband, return; } +#ifdef CPTCFG_MAC80211_DEBUGFS + /* Disable last tx check if we are debugging with fixed rate */ + if (lq_sta->dbg_fixed_rate) { + IWL_DEBUG_RATE(mvm, "Fixed rate. avoid rate scaling\n"); + return; + } +#endif if (!ieee80211_is_data(hdr->frame_control) || info->flags & IEEE80211_TX_CTL_NO_ACK) return; @@ -1017,6 +1050,18 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband, mac_index++; } + if (time_after(jiffies, + (unsigned long)(lq_sta->last_tx + RS_IDLE_TIMEOUT))) { + int tid; + IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); + for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) + ieee80211_stop_tx_ba_session(sta, tid); + + iwl_mvm_rs_rate_init(mvm, sta, sband->band, false); + return; + } + lq_sta->last_tx = jiffies; + /* Here we actually compare this rate to the latest LQ command */ if ((mac_index < 0) || (rate.sgi != !!(mac_flags & IEEE80211_TX_RC_SHORT_GI)) || @@ -1362,7 +1407,6 @@ static u32 rs_bw_from_sta_bw(struct ieee80211_sta *sta) static void rs_stay_in_table(struct iwl_lq_sta *lq_sta, bool force_search) { struct iwl_scale_tbl_info *tbl; - int i; int active_tbl; int flush_interval_passed = 0; struct iwl_mvm *mvm; @@ -1423,9 +1467,7 @@ static void rs_stay_in_table(struct iwl_lq_sta *lq_sta, bool force_search) IWL_DEBUG_RATE(mvm, "LQ: stay in table clear win\n"); - for (i = 0; i < IWL_RATE_COUNT; i++) - rs_rate_scale_clear_window( - &(tbl->win[i])); + rs_rate_scale_clear_tbl_windows(mvm, tbl); } } @@ -1433,9 +1475,7 @@ static void rs_stay_in_table(struct iwl_lq_sta *lq_sta, bool force_search) * bitmaps and stats in active table (this will become the new * "search" table). */ if (lq_sta->rs_state == RS_STATE_SEARCH_CYCLE_STARTED) { - IWL_DEBUG_RATE(mvm, "Clearing up window stats\n"); - for (i = 0; i < IWL_RATE_COUNT; i++) - rs_rate_scale_clear_window(&(tbl->win[i])); + rs_rate_scale_clear_tbl_windows(mvm, tbl); } } } @@ -1628,85 +1668,76 @@ static enum rs_action rs_get_rate_action(struct iwl_mvm *mvm, { enum rs_action action = RS_ACTION_STAY; - /* Too many failures, decrease rate */ if ((sr <= RS_SR_FORCE_DECREASE) || (current_tpt == 0)) { IWL_DEBUG_RATE(mvm, - "decrease rate because of low SR\n"); - action = RS_ACTION_DOWNSCALE; - /* No throughput measured yet for adjacent rates; try increase. */ - } else if ((low_tpt == IWL_INVALID_VALUE) && - (high_tpt == IWL_INVALID_VALUE)) { - if (high != IWL_RATE_INVALID && sr >= IWL_RATE_INCREASE_TH) { - IWL_DEBUG_RATE(mvm, - "Good SR and no high rate measurement. " - "Increase rate\n"); - action = RS_ACTION_UPSCALE; - } else if (low != IWL_RATE_INVALID) { - IWL_DEBUG_RATE(mvm, - "Remain in current rate\n"); - action = RS_ACTION_STAY; - } + "Decrease rate because of low SR\n"); + return RS_ACTION_DOWNSCALE; } - /* Both adjacent throughputs are measured, but neither one has better - * throughput; we're using the best rate, don't change it! - */ - else if ((low_tpt != IWL_INVALID_VALUE) && - (high_tpt != IWL_INVALID_VALUE) && - (low_tpt < current_tpt) && - (high_tpt < current_tpt)) { + if ((low_tpt == IWL_INVALID_VALUE) && + (high_tpt == IWL_INVALID_VALUE) && + (high != IWL_RATE_INVALID)) { IWL_DEBUG_RATE(mvm, - "Both high and low are worse. " - "Maintain rate\n"); - action = RS_ACTION_STAY; + "No data about high/low rates. Increase rate\n"); + return RS_ACTION_UPSCALE; } - /* At least one adjacent rate's throughput is measured, - * and may have better performance. - */ - else { - /* Higher adjacent rate's throughput is measured */ - if (high_tpt != IWL_INVALID_VALUE) { - /* Higher rate has better throughput */ - if (high_tpt > current_tpt && - sr >= IWL_RATE_INCREASE_TH) { - IWL_DEBUG_RATE(mvm, - "Higher rate is better and good " - "SR. Increate rate\n"); - action = RS_ACTION_UPSCALE; - } else { - IWL_DEBUG_RATE(mvm, - "Higher rate isn't better OR " - "no good SR. Maintain rate\n"); - action = RS_ACTION_STAY; - } + if ((high_tpt == IWL_INVALID_VALUE) && + (high != IWL_RATE_INVALID) && + (low_tpt != IWL_INVALID_VALUE) && + (low_tpt < current_tpt)) { + IWL_DEBUG_RATE(mvm, + "No data about high rate and low rate is worse. Increase rate\n"); + return RS_ACTION_UPSCALE; + } - /* Lower adjacent rate's throughput is measured */ - } else if (low_tpt != IWL_INVALID_VALUE) { - /* Lower rate has better throughput */ - if (low_tpt > current_tpt) { - IWL_DEBUG_RATE(mvm, - "Lower rate is better. " - "Decrease rate\n"); - action = RS_ACTION_DOWNSCALE; - } else if (sr >= IWL_RATE_INCREASE_TH) { - IWL_DEBUG_RATE(mvm, - "Lower rate isn't better and " - "good SR. Increase rate\n"); - action = RS_ACTION_UPSCALE; - } - } + if ((high_tpt != IWL_INVALID_VALUE) && + (high_tpt > current_tpt)) { + IWL_DEBUG_RATE(mvm, + "Higher rate is better. Increate rate\n"); + return RS_ACTION_UPSCALE; } - /* Sanity check; asked for decrease, but success rate or throughput - * has been good at old rate. Don't change it. - */ - if ((action == RS_ACTION_DOWNSCALE) && (low != IWL_RATE_INVALID) && - ((sr > IWL_RATE_HIGH_TH) || - (current_tpt > (100 * tbl->expected_tpt[low])))) { + if ((low_tpt != IWL_INVALID_VALUE) && + (high_tpt != IWL_INVALID_VALUE) && + (low_tpt < current_tpt) && + (high_tpt < current_tpt)) { + IWL_DEBUG_RATE(mvm, + "Both high and low are worse. Maintain rate\n"); + return RS_ACTION_STAY; + } + + if ((low_tpt != IWL_INVALID_VALUE) && + (low_tpt > current_tpt)) { + IWL_DEBUG_RATE(mvm, + "Lower rate is better\n"); + action = RS_ACTION_DOWNSCALE; + goto out; + } + + if ((low_tpt == IWL_INVALID_VALUE) && + (low != IWL_RATE_INVALID)) { IWL_DEBUG_RATE(mvm, - "Sanity check failed. Maintain rate\n"); - action = RS_ACTION_STAY; + "No data about lower rate\n"); + action = RS_ACTION_DOWNSCALE; + goto out; + } + + IWL_DEBUG_RATE(mvm, "Maintain rate\n"); + +out: + if ((action == RS_ACTION_DOWNSCALE) && (low != IWL_RATE_INVALID)) { + if (sr >= RS_SR_NO_DECREASE) { + IWL_DEBUG_RATE(mvm, + "SR is above NO DECREASE. Avoid downscale\n"); + action = RS_ACTION_STAY; + } else if (current_tpt > (100 * tbl->expected_tpt[low])) { + IWL_DEBUG_RATE(mvm, + "Current TPT is higher than max expected in low rate. Avoid downscale\n"); + action = RS_ACTION_STAY; + } else { + IWL_DEBUG_RATE(mvm, "Decrease rate\n"); + } } return action; @@ -1725,7 +1756,6 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm, int low = IWL_RATE_INVALID; int high = IWL_RATE_INVALID; int index; - int i; struct iwl_rate_scale_data *window = NULL; int current_tpt = IWL_INVALID_VALUE; int low_tpt = IWL_INVALID_VALUE; @@ -1781,6 +1811,7 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm, "Aggregation changed: prev %d current %d. Update expected TPT table\n", prev_agg, lq_sta->is_agg); rs_set_expected_tpt_table(lq_sta, tbl); + rs_rate_scale_clear_tbl_windows(mvm, tbl); } /* current tx rate */ @@ -2010,8 +2041,7 @@ lq_update: if (lq_sta->search_better_tbl) { /* Access the "search" table, clear its history. */ tbl = &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]); - for (i = 0; i < IWL_RATE_COUNT; i++) - rs_rate_scale_clear_window(&(tbl->win[i])); + rs_rate_scale_clear_tbl_windows(mvm, tbl); /* Use new "search" start rate */ index = tbl->rate.index; @@ -2032,8 +2062,18 @@ lq_update: * stay with best antenna legacy modulation for a while * before next round of mode comparisons. */ tbl1 = &(lq_sta->lq_info[lq_sta->active_tbl]); - if (is_legacy(&tbl1->rate) && !sta->ht_cap.ht_supported) { + if (is_legacy(&tbl1->rate)) { IWL_DEBUG_RATE(mvm, "LQ: STAY in legacy table\n"); + + if (tid != IWL_MAX_TID_COUNT) { + tid_data = &sta_priv->tid_data[tid]; + if (tid_data->state != IWL_AGG_OFF) { + IWL_DEBUG_RATE(mvm, + "Stop aggregation on tid %d\n", + tid); + ieee80211_stop_tx_ba_session(sta, tid); + } + } rs_set_stay_in_table(mvm, 1, lq_sta); } else { /* If we're in an HT mode, and all 3 mode switch actions @@ -2265,10 +2305,10 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, lq_sta->lq.sta_id = sta_priv->sta_id; for (j = 0; j < LQ_SIZE; j++) - for (i = 0; i < IWL_RATE_COUNT; i++) - rs_rate_scale_clear_window(&lq_sta->lq_info[j].win[i]); + rs_rate_scale_clear_tbl_windows(mvm, &lq_sta->lq_info[j]); lq_sta->flush_timer = 0; + lq_sta->last_tx = jiffies; IWL_DEBUG_RATE(mvm, "LQ: *** rate scale station global init for station %d ***\n", @@ -2469,6 +2509,7 @@ static void rs_build_rates_table(struct iwl_mvm *mvm, if (is_siso(&rate)) { num_rates = RS_SECONDARY_SISO_NUM_RATES; num_retries = RS_SECONDARY_SISO_RETRIES; + lq_cmd->mimo_delim = index; } else if (is_legacy(&rate)) { num_rates = RS_SECONDARY_LEGACY_NUM_RATES; num_retries = RS_LEGACY_RETRIES_PER_RATE; diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.h b/drivers/net/wireless/iwlwifi/mvm/rs.h index 7bc6404f6986..f23b68b8eeff 100644 --- a/drivers/net/wireless/iwlwifi/mvm/rs.h +++ b/drivers/net/wireless/iwlwifi/mvm/rs.h @@ -156,6 +156,7 @@ enum { #define IWL_RATE_HIGH_TH 10880 /* 85% */ #define IWL_RATE_INCREASE_TH 6400 /* 50% */ #define RS_SR_FORCE_DECREASE 1920 /* 15% */ +#define RS_SR_NO_DECREASE 10880 /* 85% */ #define LINK_QUAL_AGG_TIME_LIMIT_DEF (4000) /* 4 milliseconds */ #define LINK_QUAL_AGG_TIME_LIMIT_MAX (8000) @@ -310,6 +311,7 @@ struct iwl_lq_sta { u32 visited_columns; /* Bitmask marking which Tx columns were * explored during a search cycle */ + u64 last_tx; bool is_vht; enum ieee80211_band band; diff --git a/drivers/net/wireless/iwlwifi/mvm/sf.c b/drivers/net/wireless/iwlwifi/mvm/sf.c index 8401627c0030..dab8fd13857a 100644 --- a/drivers/net/wireless/iwlwifi/mvm/sf.c +++ b/drivers/net/wireless/iwlwifi/mvm/sf.c @@ -172,7 +172,7 @@ static int iwl_mvm_sf_config(struct iwl_mvm *mvm, u8 sta_id, enum iwl_sf_state new_state) { struct iwl_sf_cfg_cmd sf_cmd = { - .state = new_state, + .state = cpu_to_le32(new_state), }; struct ieee80211_sta *sta; int ret = 0; @@ -274,7 +274,8 @@ int iwl_mvm_sf_update(struct iwl_mvm *mvm, struct ieee80211_vif *changed_vif, return -EINVAL; if (changed_vif->type != NL80211_IFTYPE_STATION) { new_state = SF_UNINIT; - } else if (changed_vif->bss_conf.assoc) { + } else if (changed_vif->bss_conf.assoc && + changed_vif->bss_conf.dtim_period) { mvmvif = iwl_mvm_vif_from_mac80211(changed_vif); sta_id = mvmvif->ap_sta_id; new_state = SF_FULL_ON; diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index 3872ead75488..1ac33d9cd396 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -272,6 +272,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)}, @@ -315,6 +317,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)}, @@ -366,18 +370,21 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5510, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5200, iwl7265_2n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5002, iwl7265_n_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5102, iwl7265_n_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5202, iwl7265_n_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9010, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9012, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9112, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x9200, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)}, diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index f9507807b486..16be0c07c64a 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -318,6 +318,7 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) { int ret; int t = 0; + int iter; IWL_DEBUG_INFO(trans, "iwl_trans_prepare_card_hw enter\n"); @@ -326,18 +327,23 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) if (ret >= 0) return 0; - /* If HW is not ready, prepare the conditions to check again */ - iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, - CSR_HW_IF_CONFIG_REG_PREPARE); + for (iter = 0; iter < 10; iter++) { + /* If HW is not ready, prepare the conditions to check again */ + iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, + CSR_HW_IF_CONFIG_REG_PREPARE); + + do { + ret = iwl_pcie_set_hw_ready(trans); + if (ret >= 0) + return 0; - do { - ret = iwl_pcie_set_hw_ready(trans); - if (ret >= 0) - return 0; + usleep_range(200, 1000); + t += 200; + } while (t < 150000); + msleep(25); + } - usleep_range(200, 1000); - t += 200; - } while (t < 150000); + IWL_DEBUG_INFO(trans, "got NIC after %d iterations\n", iter); return ret; } @@ -1563,6 +1569,10 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, * PCI Tx retries from interfering with C3 CPU state */ pci_write_config_byte(pdev, PCI_CFG_RETRY_TIMEOUT, 0x00); + trans->dev = &pdev->dev; + trans_pcie->pci_dev = pdev; + iwl_disable_interrupts(trans); + err = pci_enable_msi(pdev); if (err) { dev_err(&pdev->dev, "pci_enable_msi failed(0X%x)\n", err); @@ -1574,8 +1584,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, } } - trans->dev = &pdev->dev; - trans_pcie->pci_dev = pdev; trans->hw_rev = iwl_read32(trans, CSR_HW_REV); trans->hw_id = (pdev->device << 16) + pdev->subsystem_device; snprintf(trans->hw_id_str, sizeof(trans->hw_id_str), @@ -1601,8 +1609,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, goto out_pci_disable_msi; } - trans_pcie->inta_mask = CSR_INI_SET_MASK; - if (iwl_pcie_alloc_ict(trans)) goto out_free_cmd_pool; @@ -1614,6 +1620,8 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, goto out_free_ict; } + trans_pcie->inta_mask = CSR_INI_SET_MASK; + return trans; out_free_ict: diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c index 9d3d2758ec35..952a47f6554e 100644 --- a/drivers/net/wireless/mwifiex/main.c +++ b/drivers/net/wireless/mwifiex/main.c @@ -646,6 +646,7 @@ mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) } tx_info = MWIFIEX_SKB_TXCB(skb); + memset(tx_info, 0, sizeof(*tx_info)); tx_info->bss_num = priv->bss_num; tx_info->bss_type = priv->bss_type; tx_info->pkt_len = skb->len; diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c index 2f1cd929c6f6..a511cccc9f01 100644 --- a/drivers/net/wireless/rt2x00/rt2500pci.c +++ b/drivers/net/wireless/rt2x00/rt2500pci.c @@ -1681,8 +1681,13 @@ static int rt2500pci_init_eeprom(struct rt2x00_dev *rt2x00dev) /* * Detect if this device has an hardware controlled radio. */ - if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO)) + if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO)) { __set_bit(CAPABILITY_HW_BUTTON, &rt2x00dev->cap_flags); + /* + * On this device RFKILL initialized during probe does not work. + */ + __set_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags); + } /* * Check if the BBP tuning should be enabled. diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h index a394a9a95919..ebd5625d13f1 100644 --- a/drivers/net/wireless/rt2x00/rt2800.h +++ b/drivers/net/wireless/rt2x00/rt2800.h @@ -52,6 +52,7 @@ * RF5592 2.4G/5G 2T2R * RF3070 2.4G 1T1R * RF5360 2.4G 1T1R + * RF5362 2.4G 1T1R * RF5370 2.4G 1T1R * RF5390 2.4G 1T1R */ @@ -72,6 +73,7 @@ #define RF3070 0x3070 #define RF3290 0x3290 #define RF5360 0x5360 +#define RF5362 0x5362 #define RF5370 0x5370 #define RF5372 0x5372 #define RF5390 0x5390 @@ -2039,7 +2041,7 @@ struct mac_iveiv_entry { * 2 - drop tx power by 12dBm, * 3 - increase tx power by 6dBm */ -#define BBP1_TX_POWER_CTRL FIELD8(0x07) +#define BBP1_TX_POWER_CTRL FIELD8(0x03) #define BBP1_TX_ANTENNA FIELD8(0x18) /* @@ -2145,7 +2147,7 @@ struct mac_iveiv_entry { /* Bits [7-4] for RF3320 (RT3370/RT3390), on other chipsets reserved */ #define RFCSR3_PA1_BIAS_CCK FIELD8(0x70) #define RFCSR3_PA2_CASCODE_BIAS_CCKK FIELD8(0x80) -/* Bits for RF3290/RF5360/RF5370/RF5372/RF5390/RF5392 */ +/* Bits for RF3290/RF5360/RF5362/RF5370/RF5372/RF5390/RF5392 */ #define RFCSR3_VCOCAL_EN FIELD8(0x80) /* Bits for RF3050 */ #define RFCSR3_BIT1 FIELD8(0x02) diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 41d4a8167dc3..4e16d4da9d82 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -3142,6 +3142,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, break; case RF3070: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -3159,6 +3160,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, rt2x00_rf(rt2x00dev, RF3290) || rt2x00_rf(rt2x00dev, RF3322) || rt2x00_rf(rt2x00dev, RF5360) || + rt2x00_rf(rt2x00dev, RF5362) || rt2x00_rf(rt2x00dev, RF5370) || rt2x00_rf(rt2x00dev, RF5372) || rt2x00_rf(rt2x00dev, RF5390) || @@ -4273,6 +4275,7 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev) case RF3070: case RF3290: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7073,6 +7076,7 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev) case RF3320: case RF3322: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7529,6 +7533,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) case RF3320: case RF3322: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7658,6 +7663,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) case RF3070: case RF3290: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index caddc1b427a9..57d3967de32f 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -1062,6 +1062,7 @@ static struct usb_device_id rt2800usb_device_table[] = { /* Ovislink */ { USB_DEVICE(0x1b75, 0x3071) }, { USB_DEVICE(0x1b75, 0x3072) }, + { USB_DEVICE(0x1b75, 0xa200) }, /* Para */ { USB_DEVICE(0x20b8, 0x8888) }, /* Pegatron */ @@ -1235,6 +1236,8 @@ static struct usb_device_id rt2800usb_device_table[] = { /* Arcadyan */ { USB_DEVICE(0x043e, 0x7a12) }, { USB_DEVICE(0x043e, 0x7a32) }, + /* ASUS */ + { USB_DEVICE(0x0b05, 0x17e8) }, /* Azurewave */ { USB_DEVICE(0x13d3, 0x3329) }, { USB_DEVICE(0x13d3, 0x3365) }, @@ -1271,6 +1274,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x057c, 0x8501) }, /* Buffalo */ { USB_DEVICE(0x0411, 0x0241) }, + { USB_DEVICE(0x0411, 0x0253) }, /* D-Link */ { USB_DEVICE(0x2001, 0x3c1a) }, { USB_DEVICE(0x2001, 0x3c21) }, @@ -1361,6 +1365,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x0df6, 0x0053) }, { USB_DEVICE(0x0df6, 0x0069) }, { USB_DEVICE(0x0df6, 0x006f) }, + { USB_DEVICE(0x0df6, 0x0078) }, /* SMC */ { USB_DEVICE(0x083a, 0xa512) }, { USB_DEVICE(0x083a, 0xc522) }, diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h index e3b885d8f7db..5d45a1a740a4 100644 --- a/drivers/net/wireless/rt2x00/rt2x00.h +++ b/drivers/net/wireless/rt2x00/rt2x00.h @@ -693,6 +693,7 @@ enum rt2x00_capability_flags { REQUIRE_SW_SEQNO, REQUIRE_HT_TX_DESC, REQUIRE_PS_AUTOWAKE, + REQUIRE_DELAYED_RFKILL, /* * Capabilities diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c index 2bde6729f5e6..4fa43a2eeb73 100644 --- a/drivers/net/wireless/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/rt2x00/rt2x00dev.c @@ -1126,9 +1126,10 @@ static void rt2x00lib_uninitialize(struct rt2x00_dev *rt2x00dev) return; /* - * Unregister extra components. + * Stop rfkill polling. */ - rt2x00rfkill_unregister(rt2x00dev); + if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags)) + rt2x00rfkill_unregister(rt2x00dev); /* * Allow the HW to uninitialize. @@ -1166,6 +1167,12 @@ static int rt2x00lib_initialize(struct rt2x00_dev *rt2x00dev) set_bit(DEVICE_STATE_INITIALIZED, &rt2x00dev->flags); + /* + * Start rfkill polling. + */ + if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags)) + rt2x00rfkill_register(rt2x00dev); + return 0; } @@ -1375,7 +1382,12 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev) rt2x00link_register(rt2x00dev); rt2x00leds_register(rt2x00dev); rt2x00debug_register(rt2x00dev); - rt2x00rfkill_register(rt2x00dev); + + /* + * Start rfkill polling. + */ + if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags)) + rt2x00rfkill_register(rt2x00dev); return 0; @@ -1391,6 +1403,12 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev) clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags); /* + * Stop rfkill polling. + */ + if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags)) + rt2x00rfkill_unregister(rt2x00dev); + + /* * Disable radio. */ rt2x00lib_disable_radio(rt2x00dev); diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c index ddeb5a709aa3..87a8ad5d2eb7 100644 --- a/drivers/net/wireless/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/rt2x00/rt2x00mac.c @@ -487,6 +487,8 @@ int rt2x00mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, crypto.cipher = rt2x00crypto_key_to_cipher(key); if (crypto.cipher == CIPHER_NONE) return -EOPNOTSUPP; + if (crypto.cipher == CIPHER_TKIP && rt2x00_is_usb(rt2x00dev)) + return -EOPNOTSUPP; crypto.cmd = cmd; @@ -621,20 +623,18 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, bss_conf->bssid); /* - * Update the beacon. This is only required on USB devices. PCI - * devices fetch beacons periodically. - */ - if (changes & BSS_CHANGED_BEACON && rt2x00_is_usb(rt2x00dev)) - rt2x00queue_update_beacon(rt2x00dev, vif); - - /* * Start/stop beaconing. */ if (changes & BSS_CHANGED_BEACON_ENABLED) { if (!bss_conf->enable_beacon && intf->enable_beacon) { - rt2x00queue_clear_beacon(rt2x00dev, vif); rt2x00dev->intf_beaconing--; intf->enable_beacon = false; + /* + * Clear beacon in the H/W for this vif. This is needed + * to disable beaconing on this particular interface + * and keep it running on other interfaces. + */ + rt2x00queue_clear_beacon(rt2x00dev, vif); if (rt2x00dev->intf_beaconing == 0) { /* @@ -645,11 +645,15 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, rt2x00queue_stop_queue(rt2x00dev->bcn); mutex_unlock(&intf->beacon_skb_mutex); } - - } else if (bss_conf->enable_beacon && !intf->enable_beacon) { rt2x00dev->intf_beaconing++; intf->enable_beacon = true; + /* + * Upload beacon to the H/W. This is only required on + * USB devices. PCI devices fetch beacons periodically. + */ + if (rt2x00_is_usb(rt2x00dev)) + rt2x00queue_update_beacon(rt2x00dev, vif); if (rt2x00dev->intf_beaconing == 1) { /* diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c index e06971be7df7..f923d8c9a296 100644 --- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c @@ -1025,9 +1025,20 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw) bool rtstatus = true; int err = 0; u8 tmp_u1b, u1byte; + unsigned long flags; RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "Rtl8188EE hw init\n"); rtlpriv->rtlhal.being_init_adapter = true; + /* As this function can take a very long time (up to 350 ms) + * and can be called with irqs disabled, reenable the irqs + * to let the other devices continue being serviced. + * + * It is safe doing so since our own interrupts will only be enabled + * in a subsequent step. + */ + local_save_flags(flags); + local_irq_enable(); + rtlpriv->intf_ops->disable_aspm(hw); tmp_u1b = rtl_read_byte(rtlpriv, REG_SYS_CLKR+1); @@ -1043,7 +1054,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw) if (rtstatus != true) { RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n"); err = 1; - return err; + goto exit; } err = rtl88e_download_fw(hw, false); @@ -1051,8 +1062,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw) RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING, "Failed to download FW. Init HW without FW now..\n"); err = 1; - rtlhal->fw_ready = false; - return err; + goto exit; } else { rtlhal->fw_ready = true; } @@ -1135,10 +1145,12 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw) } rtl_write_byte(rtlpriv, REG_NAV_CTRL+2, ((30000+127)/128)); rtl88e_dm_init(hw); +exit: + local_irq_restore(flags); rtlpriv->rtlhal.being_init_adapter = false; RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "end of Rtl8188EE hw init %x\n", err); - return 0; + return err; } static enum version_8188e _rtl88ee_read_chip_version(struct ieee80211_hw *hw) diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c index aece6c9cccf1..7622e44567cc 100644 --- a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c +++ b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c @@ -293,7 +293,7 @@ static void _rtl88ee_translate_rx_signal_stuff(struct ieee80211_hw *hw, u8 *psaddr; __le16 fc; u16 type, ufc; - bool match_bssid, packet_toself, packet_beacon, addr; + bool match_bssid, packet_toself, packet_beacon = false, addr; tmp_buf = skb->data + pstatus->rx_drvinfo_size + pstatus->rx_bufshift; diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c index 468bf73cc883..472e592b32ec 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c @@ -985,19 +985,30 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw) struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); int err = 0; static bool iqk_initialized; + unsigned long flags; + + /* As this function can take a very long time (up to 350 ms) + * and can be called with irqs disabled, reenable the irqs + * to let the other devices continue being serviced. + * + * It is safe doing so since our own interrupts will only be enabled + * in a subsequent step. + */ + local_save_flags(flags); + local_irq_enable(); rtlhal->hw_type = HARDWARE_TYPE_RTL8192CU; err = _rtl92cu_init_mac(hw); if (err) { RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "init mac failed!\n"); - return err; + goto exit; } err = rtl92c_download_fw(hw); if (err) { RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING, "Failed to download FW. Init HW without FW now..\n"); err = 1; - return err; + goto exit; } rtlhal->last_hmeboxnum = 0; /* h2c */ _rtl92cu_phy_param_tab_init(hw); @@ -1034,6 +1045,8 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw) _InitPABias(hw); _update_mac_setting(hw); rtl92c_dm_init(hw); +exit: + local_irq_restore(flags); return err; } diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c index c61311084d7e..f58316769159 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c @@ -317,6 +317,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/ {RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ {RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ + {RTL_USB_DEVICE(0x0df6, 0x0070, rtl92cu_hal_cfg)}, /*Sitecom - 150N */ {RTL_USB_DEVICE(0x0df6, 0x0077, rtl92cu_hal_cfg)}, /*Sitecom-WLA2100V2*/ {RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/ {RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/ diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c index 4f461786a7eb..c471400fe8f0 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c @@ -955,7 +955,7 @@ int rtl92se_hw_init(struct ieee80211_hw *hw) struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw)); u8 tmp_byte = 0; - + unsigned long flags; bool rtstatus = true; u8 tmp_u1b; int err = false; @@ -967,6 +967,16 @@ int rtl92se_hw_init(struct ieee80211_hw *hw) rtlpci->being_init_adapter = true; + /* As this function can take a very long time (up to 350 ms) + * and can be called with irqs disabled, reenable the irqs + * to let the other devices continue being serviced. + * + * It is safe doing so since our own interrupts will only be enabled + * in a subsequent step. + */ + local_save_flags(flags); + local_irq_enable(); + rtlpriv->intf_ops->disable_aspm(hw); /* 1. MAC Initialize */ @@ -984,7 +994,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw) RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING, "Failed to download FW. Init HW without FW now... " "Please copy FW into /lib/firmware/rtlwifi\n"); - return 1; + err = 1; + goto exit; } /* After FW download, we have to reset MAC register */ @@ -997,7 +1008,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw) /* 3. Initialize MAC/PHY Config by MACPHY_reg.txt */ if (!rtl92s_phy_mac_config(hw)) { RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "MAC Config failed\n"); - return rtstatus; + err = rtstatus; + goto exit; } /* because last function modify RCR, so we update @@ -1016,7 +1028,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw) /* 4. Initialize BB After MAC Config PHY_reg.txt, AGC_Tab.txt */ if (!rtl92s_phy_bb_config(hw)) { RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG, "BB Config failed\n"); - return rtstatus; + err = rtstatus; + goto exit; } /* 5. Initiailze RF RAIO_A.txt RF RAIO_B.txt */ @@ -1033,7 +1046,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw) if (!rtl92s_phy_rf_config(hw)) { RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "RF Config failed\n"); - return rtstatus; + err = rtstatus; + goto exit; } /* After read predefined TXT, we must set BB/MAC/RF @@ -1122,8 +1136,9 @@ int rtl92se_hw_init(struct ieee80211_hw *hw) rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_ON); rtl92s_dm_init(hw); +exit: + local_irq_restore(flags); rtlpci->being_init_adapter = false; - return err; } diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c index 27efbcdac6a9..d27abef140f0 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c +++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c @@ -49,6 +49,12 @@ static u8 _rtl92se_map_hwqueue_to_fwqueue(struct sk_buff *skb, u8 skb_queue) if (ieee80211_is_nullfunc(fc)) return QSLT_HIGH; + /* Kernel commit 1bf4bbb4024dcdab changed EAPOL packets to use + * queue V0 at priority 7; however, the RTL8192SE appears to have + * that queue at priority 6 + */ + if (skb->priority == 7) + return QSLT_VO; return skb->priority; } diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c index c333dfd116b8..99f6bc5fa986 100644 --- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c @@ -880,14 +880,25 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw) bool rtstatus = true; int err; u8 tmp_u1b; + unsigned long flags; rtlpriv->rtlhal.being_init_adapter = true; + /* As this function can take a very long time (up to 350 ms) + * and can be called with irqs disabled, reenable the irqs + * to let the other devices continue being serviced. + * + * It is safe doing so since our own interrupts will only be enabled + * in a subsequent step. + */ + local_save_flags(flags); + local_irq_enable(); + rtlpriv->intf_ops->disable_aspm(hw); rtstatus = _rtl8712e_init_mac(hw); if (rtstatus != true) { RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n"); err = 1; - return err; + goto exit; } err = rtl8723ae_download_fw(hw); @@ -895,8 +906,7 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw) RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING, "Failed to download FW. Init HW without FW now..\n"); err = 1; - rtlhal->fw_ready = false; - return err; + goto exit; } else { rtlhal->fw_ready = true; } @@ -971,6 +981,8 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw) RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n"); } rtl8723ae_dm_init(hw); +exit: + local_irq_restore(flags); rtlpriv->rtlhal.being_init_adapter = false; return err; } diff --git a/drivers/net/wireless/ti/wl18xx/event.h b/drivers/net/wireless/ti/wl18xx/event.h index 398f3d2c0a6c..a76e98eb8372 100644 --- a/drivers/net/wireless/ti/wl18xx/event.h +++ b/drivers/net/wireless/ti/wl18xx/event.h @@ -68,6 +68,26 @@ struct wl18xx_event_mailbox { /* bitmap of inactive stations (by HLID) */ __le32 inactive_sta_bitmap; + + /* rx BA win size indicated by RX_BA_WIN_SIZE_CHANGE_EVENT_ID */ + u8 rx_ba_role_id; + u8 rx_ba_link_id; + u8 rx_ba_win_size; + u8 padding; + + /* smart config */ + u8 sc_ssid_len; + u8 sc_pwd_len; + u8 sc_token_len; + u8 padding1; + u8 sc_ssid[32]; + u8 sc_pwd[32]; + u8 sc_token[32]; + + /* smart config sync channel */ + u8 sc_sync_channel; + u8 sc_sync_band; + u8 padding2[2]; } __packed; int wl18xx_wait_for_event(struct wl1271 *wl, enum wlcore_wait_event event, diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index ae413a2cbee7..4bf5b334664e 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -113,6 +113,11 @@ struct xenvif { domid_t domid; unsigned int handle; + /* Is this interface disabled? True when backend discovers + * frontend is rogue. + */ + bool disabled; + /* Use NAPI for guest TX */ struct napi_struct napi; /* When feature-split-event-channels = 0, tx_irq = rx_irq. */ diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 301cc037fda8..2e92d52c0a6d 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -62,6 +62,15 @@ static int xenvif_poll(struct napi_struct *napi, int budget) struct xenvif *vif = container_of(napi, struct xenvif, napi); int work_done; + /* This vif is rogue, we pretend we've there is nothing to do + * for this vif to deschedule it from NAPI. But this interface + * will be turned off in thread context later. + */ + if (unlikely(vif->disabled)) { + napi_complete(napi); + return 0; + } + work_done = xenvif_tx_action(vif, budget); if (work_done < budget) { @@ -321,6 +330,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, vif->ip_csum = 1; vif->dev = dev; + vif->disabled = false; + vif->credit_bytes = vif->remaining_credit = ~0UL; vif->credit_usec = 0UL; init_timer(&vif->credit_timeout); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 438d0c09b7e6..97030c193afd 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -192,8 +192,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head) * into multiple copies tend to give large frags their * own buffers as before. */ - if ((offset + size > MAX_BUFFER_OFFSET) && - (size <= MAX_BUFFER_OFFSET) && offset && !head) + BUG_ON(size > MAX_BUFFER_OFFSET); + if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head) return true; return false; @@ -482,6 +482,8 @@ static void xenvif_rx_action(struct xenvif *vif) while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) { RING_IDX max_slots_needed; + RING_IDX old_req_cons; + RING_IDX ring_slots_used; int i; /* We need a cheap worse case estimate for the number of @@ -493,9 +495,28 @@ static void xenvif_rx_action(struct xenvif *vif) PAGE_SIZE); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { unsigned int size; + unsigned int offset; + size = skb_frag_size(&skb_shinfo(skb)->frags[i]); - max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE); + offset = skb_shinfo(skb)->frags[i].page_offset; + + /* For a worse-case estimate we need to factor in + * the fragment page offset as this will affect the + * number of times xenvif_gop_frag_copy() will + * call start_new_rx_buffer(). + */ + max_slots_needed += DIV_ROUND_UP(offset + size, + PAGE_SIZE); } + + /* To avoid the estimate becoming too pessimal for some + * frontends that limit posted rx requests, cap the estimate + * at MAX_SKB_FRAGS. + */ + if (max_slots_needed > MAX_SKB_FRAGS) + max_slots_needed = MAX_SKB_FRAGS; + + /* We may need one more slot for GSO metadata */ if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 || skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) @@ -511,8 +532,12 @@ static void xenvif_rx_action(struct xenvif *vif) vif->rx_last_skb_slots = 0; sco = (struct skb_cb_overlay *)skb->cb; + + old_req_cons = vif->rx.req_cons; sco->meta_slots_used = xenvif_gop_skb(skb, &npo); - BUG_ON(sco->meta_slots_used > max_slots_needed); + ring_slots_used = vif->rx.req_cons - old_req_cons; + + BUG_ON(ring_slots_used > max_slots_needed); __skb_queue_tail(&rxq, skb); } @@ -655,7 +680,8 @@ static void xenvif_tx_err(struct xenvif *vif, static void xenvif_fatal_tx_err(struct xenvif *vif) { netdev_err(vif->dev, "fatal error; disabling device\n"); - xenvif_carrier_off(vif); + vif->disabled = true; + xenvif_kick_thread(vif); } static int xenvif_count_requests(struct xenvif *vif, @@ -1126,7 +1152,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) vif->tx.sring->req_prod, vif->tx.req_cons, XEN_NETIF_TX_RING_SIZE); xenvif_fatal_tx_err(vif); - continue; + break; } work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx); @@ -1548,7 +1574,18 @@ int xenvif_kthread(void *data) while (!kthread_should_stop()) { wait_event_interruptible(vif->wq, rx_work_todo(vif) || + vif->disabled || kthread_should_stop()); + + /* This frontend is found to be rogue, disable it in + * kthread context. Currently this is only set when + * netback finds out frontend sends malformed packet, + * but we cannot disable the interface in softirq + * context so we defer it here. + */ + if (unlikely(vif->disabled && netif_carrier_ok(vif->dev))) + xenvif_carrier_off(vif); + if (kthread_should_stop()) break; diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c index f868333271aa..963a4a5dc88e 100644 --- a/drivers/nfc/microread/microread.c +++ b/drivers/nfc/microread/microread.c @@ -501,9 +501,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate, targets->sens_res = be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A_ATQA]); targets->sel_res = skb->data[MICROREAD_EMCF_A_SAK]; - memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID], - skb->data[MICROREAD_EMCF_A_LEN]); targets->nfcid1_len = skb->data[MICROREAD_EMCF_A_LEN]; + if (targets->nfcid1_len > sizeof(targets->nfcid1)) { + r = -EINVAL; + goto exit_free; + } + memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID], + targets->nfcid1_len); break; case MICROREAD_GATE_ID_MREAD_ISO_A_3: targets->supported_protocols = @@ -511,9 +515,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate, targets->sens_res = be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A3_ATQA]); targets->sel_res = skb->data[MICROREAD_EMCF_A3_SAK]; - memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID], - skb->data[MICROREAD_EMCF_A3_LEN]); targets->nfcid1_len = skb->data[MICROREAD_EMCF_A3_LEN]; + if (targets->nfcid1_len > sizeof(targets->nfcid1)) { + r = -EINVAL; + goto exit_free; + } + memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID], + targets->nfcid1_len); break; case MICROREAD_GATE_ID_MREAD_ISO_B: targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK; diff --git a/drivers/of/base.c b/drivers/of/base.c index 89e888a78899..3935614274eb 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1117,52 +1117,6 @@ int of_property_read_string(struct device_node *np, const char *propname, EXPORT_SYMBOL_GPL(of_property_read_string); /** - * of_property_read_string_index - Find and read a string from a multiple - * strings property. - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @index: index of the string in the list of strings - * @out_string: pointer to null terminated return string, modified only if - * return value is 0. - * - * Search for a property in a device tree node and retrieve a null - * terminated string value (pointer to data, not a copy) in the list of strings - * contained in that property. - * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if - * property does not have a value, and -EILSEQ if the string is not - * null-terminated within the length of the property data. - * - * The out_string pointer is modified only if a valid string can be decoded. - */ -int of_property_read_string_index(struct device_node *np, const char *propname, - int index, const char **output) -{ - struct property *prop = of_find_property(np, propname, NULL); - int i = 0; - size_t l = 0, total = 0; - const char *p; - - if (!prop) - return -EINVAL; - if (!prop->value) - return -ENODATA; - if (strnlen(prop->value, prop->length) >= prop->length) - return -EILSEQ; - - p = prop->value; - - for (i = 0; total < prop->length; total += l, p += l) { - l = strlen(p) + 1; - if (i++ == index) { - *output = p; - return 0; - } - } - return -ENODATA; -} -EXPORT_SYMBOL_GPL(of_property_read_string_index); - -/** * of_property_match_string() - Find string in a list and return index * @np: pointer to node containing string list property * @propname: string list property name @@ -1188,7 +1142,7 @@ int of_property_match_string(struct device_node *np, const char *propname, end = p + prop->length; for (i = 0; p < end; i++, p += l) { - l = strlen(p) + 1; + l = strnlen(p, end - p) + 1; if (p + l > end) return -EILSEQ; pr_debug("comparing %s with %s\n", string, p); @@ -1200,39 +1154,41 @@ int of_property_match_string(struct device_node *np, const char *propname, EXPORT_SYMBOL_GPL(of_property_match_string); /** - * of_property_count_strings - Find and return the number of strings from a - * multiple strings property. + * of_property_read_string_util() - Utility helper for parsing string properties * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. + * @out_strs: output array of string pointers. + * @sz: number of array elements to read. + * @skip: Number of strings to skip over at beginning of list. * - * Search for a property in a device tree node and retrieve the number of null - * terminated string contain in it. Returns the number of strings on - * success, -EINVAL if the property does not exist, -ENODATA if property - * does not have a value, and -EILSEQ if the string is not null-terminated - * within the length of the property data. + * Don't call this function directly. It is a utility helper for the + * of_property_read_string*() family of functions. */ -int of_property_count_strings(struct device_node *np, const char *propname) +int of_property_read_string_helper(struct device_node *np, const char *propname, + const char **out_strs, size_t sz, int skip) { struct property *prop = of_find_property(np, propname, NULL); - int i = 0; - size_t l = 0, total = 0; - const char *p; + int l = 0, i = 0; + const char *p, *end; if (!prop) return -EINVAL; if (!prop->value) return -ENODATA; - if (strnlen(prop->value, prop->length) >= prop->length) - return -EILSEQ; - p = prop->value; + end = p + prop->length; - for (i = 0; total < prop->length; total += l, p += l, i++) - l = strlen(p) + 1; - - return i; + for (i = 0; p < end && (!out_strs || i < skip + sz); i++, p += l) { + l = strnlen(p, end - p) + 1; + if (p + l > end) + return -EILSEQ; + if (out_strs && i >= skip) + *out_strs++ = p; + } + i -= skip; + return i <= 0 ? -ENODATA : i; } -EXPORT_SYMBOL_GPL(of_property_count_strings); +EXPORT_SYMBOL_GPL(of_property_read_string_helper); void of_print_phandle_args(const char *msg, const struct of_phandle_args *args) { diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 9bcf2cf19357..48f20ff1add9 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -301,16 +301,17 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Get the reg property (if any) */ addr = of_get_property(device, "reg", NULL); + /* Try the new-style interrupts-extended first */ + res = of_parse_phandle_with_args(device, "interrupts-extended", + "#interrupt-cells", index, out_irq); + if (!res) + return of_irq_parse_raw(addr, out_irq); + /* Get the interrupts property */ intspec = of_get_property(device, "interrupts", &intlen); - if (intspec == NULL) { - /* Try the new-style interrupts-extended */ - res = of_parse_phandle_with_args(device, "interrupts-extended", - "#interrupt-cells", index, out_irq); - if (res) - return -EINVAL; - return of_irq_parse_raw(addr, out_irq); - } + if (intspec == NULL) + return -EINVAL; + intlen /= sizeof(*intspec); pr_debug(" intspec=%d intlen=%d\n", be32_to_cpup(intspec), intlen); @@ -380,6 +381,32 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) EXPORT_SYMBOL_GPL(of_irq_to_resource); /** + * of_irq_get - Decode a node's IRQ and return it as a Linux irq number + * @dev: pointer to device tree node + * @index: zero-based index of the irq + * + * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain + * is not yet created. + * + */ +int of_irq_get(struct device_node *dev, int index) +{ + int rc; + struct of_phandle_args oirq; + struct irq_domain *domain; + + rc = of_irq_parse_one(dev, index, &oirq); + if (rc) + return rc; + + domain = irq_find_host(oirq.np); + if (!domain) + return -EPROBE_DEFER; + + return irq_create_of_mapping(&oirq); +} + +/** * of_irq_count - Count the number of IRQs a node uses * @dev: pointer to device tree node */ diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 404d1daebefa..bd47fbc53dc9 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -168,7 +168,9 @@ struct platform_device *of_device_alloc(struct device_node *np, rc = of_address_to_resource(np, i, res); WARN_ON(rc); } - WARN_ON(of_irq_to_resource_table(np, res, num_irq) != num_irq); + if (of_irq_to_resource_table(np, res, num_irq) != num_irq) + pr_debug("not all legacy IRQ resources mapped for %s\n", + np->name); } dev->dev.of_node = of_node_get(np); diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c index 6643d1920985..70c61d75b75e 100644 --- a/drivers/of/selftest.c +++ b/drivers/of/selftest.c @@ -132,8 +132,9 @@ static void __init of_selftest_parse_phandle_with_args(void) selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); } -static void __init of_selftest_property_match_string(void) +static void __init of_selftest_property_string(void) { + const char *strings[4]; struct device_node *np; int rc; @@ -150,13 +151,66 @@ static void __init of_selftest_property_match_string(void) rc = of_property_match_string(np, "phandle-list-names", "third"); selftest(rc == 2, "third expected:0 got:%i\n", rc); rc = of_property_match_string(np, "phandle-list-names", "fourth"); - selftest(rc == -ENODATA, "unmatched string; rc=%i", rc); + selftest(rc == -ENODATA, "unmatched string; rc=%i\n", rc); rc = of_property_match_string(np, "missing-property", "blah"); - selftest(rc == -EINVAL, "missing property; rc=%i", rc); + selftest(rc == -EINVAL, "missing property; rc=%i\n", rc); rc = of_property_match_string(np, "empty-property", "blah"); - selftest(rc == -ENODATA, "empty property; rc=%i", rc); + selftest(rc == -ENODATA, "empty property; rc=%i\n", rc); rc = of_property_match_string(np, "unterminated-string", "blah"); - selftest(rc == -EILSEQ, "unterminated string; rc=%i", rc); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + + /* of_property_count_strings() tests */ + rc = of_property_count_strings(np, "string-property"); + selftest(rc == 1, "Incorrect string count; rc=%i\n", rc); + rc = of_property_count_strings(np, "phandle-list-names"); + selftest(rc == 3, "Incorrect string count; rc=%i\n", rc); + rc = of_property_count_strings(np, "unterminated-string"); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + rc = of_property_count_strings(np, "unterminated-string-list"); + selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc); + + /* of_property_read_string_index() tests */ + rc = of_property_read_string_index(np, "string-property", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "foobar"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "string-property", 1, strings); + selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 1, strings); + selftest(rc == 0 && !strcmp(strings[0], "second"), "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 2, strings); + selftest(rc == 0 && !strcmp(strings[0], "third"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "phandle-list-names", 3, strings); + selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "unterminated-string", 0, strings); + selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "unterminated-string-list", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "unterminated-string-list", 2, strings); /* should fail */ + selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + strings[1] = NULL; + + /* of_property_read_string_array() tests */ + rc = of_property_read_string_array(np, "string-property", strings, 4); + selftest(rc == 1, "Incorrect string count; rc=%i\n", rc); + rc = of_property_read_string_array(np, "phandle-list-names", strings, 4); + selftest(rc == 3, "Incorrect string count; rc=%i\n", rc); + rc = of_property_read_string_array(np, "unterminated-string", strings, 4); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + /* -- An incorrectly formed string should cause a failure */ + rc = of_property_read_string_array(np, "unterminated-string-list", strings, 4); + selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc); + /* -- parsing the correctly formed strings should still work: */ + strings[2] = NULL; + rc = of_property_read_string_array(np, "unterminated-string-list", strings, 2); + selftest(rc == 2 && strings[2] == NULL, "of_property_read_string_array() failure; rc=%i\n", rc); + strings[1] = NULL; + rc = of_property_read_string_array(np, "phandle-list-names", strings, 1); + selftest(rc == 1 && strings[1] == NULL, "Overwrote end of string array; rc=%i, str='%s'\n", rc, strings[1]); } static void __init of_selftest_parse_interrupts(void) @@ -379,7 +433,7 @@ static int __init of_selftest(void) pr_info("start of selftest - you will see error messages\n"); of_selftest_parse_phandle_with_args(); - of_selftest_property_match_string(); + of_selftest_property_string(); of_selftest_parse_interrupts(); of_selftest_parse_interrupts_extended(); of_selftest_match_node(); diff --git a/drivers/of/testcase-data/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi index 0007d3cd7dc2..eedee37d70d7 100644 --- a/drivers/of/testcase-data/tests-phandle.dtsi +++ b/drivers/of/testcase-data/tests-phandle.dtsi @@ -32,7 +32,9 @@ phandle-list-bad-args = <&provider2 1 0>, <&provider3 0>; empty-property; + string-property = "foobar"; unterminated-string = [40 41 42 43]; + unterminated-string-list = "first", "second", [40 41 42 43]; }; }; }; diff --git a/drivers/parport/Kconfig b/drivers/parport/Kconfig index 2872ece81f35..44333bd8f908 100644 --- a/drivers/parport/Kconfig +++ b/drivers/parport/Kconfig @@ -5,6 +5,12 @@ # Parport configuration. # +config ARCH_MIGHT_HAVE_PC_PARPORT + bool + help + Select this config option from the architecture Kconfig if + the architecture might have PC parallel port hardware. + menuconfig PARPORT tristate "Parallel port support" depends on HAS_IOMEM @@ -31,12 +37,6 @@ menuconfig PARPORT If unsure, say Y. -config ARCH_MIGHT_HAVE_PC_PARPORT - bool - help - Select this config option from the architecture Kconfig if - the architecture might have PC parallel port hardware. - if PARPORT config PARPORT_PC diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c index e8663a8c3406..ee082509b0ba 100644 --- a/drivers/pci/host/pci-imx6.c +++ b/drivers/pci/host/pci-imx6.c @@ -424,20 +424,40 @@ static void imx6_pcie_reset_phy(struct pcie_port *pp) static int imx6_pcie_link_up(struct pcie_port *pp) { - u32 rc, ltssm, rx_valid; + u32 rc, debug_r0, rx_valid; + int count = 5; /* - * Test if the PHY reports that the link is up and also that - * the link training finished. It might happen that the PHY - * reports the link is already up, but the link training bit - * is still set, so make sure to check the training is done - * as well here. + * Test if the PHY reports that the link is up and also that the LTSSM + * training finished. There are three possible states of the link when + * this code is called: + * 1) The link is DOWN (unlikely) + * The link didn't come up yet for some reason. This usually means + * we have a real problem somewhere. Reset the PHY and exit. This + * state calls for inspection of the DEBUG registers. + * 2) The link is UP, but still in LTSSM training + * Wait for the training to finish, which should take a very short + * time. If the training does not finish, we have a problem and we + * need to inspect the DEBUG registers. If the training does finish, + * the link is up and operating correctly. + * 3) The link is UP and no longer in LTSSM training + * The link is up and operating correctly. */ - rc = readl(pp->dbi_base + PCIE_PHY_DEBUG_R1); - if ((rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_UP) && - !(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_IN_TRAINING)) - return 1; - + while (1) { + rc = readl(pp->dbi_base + PCIE_PHY_DEBUG_R1); + if (!(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_UP)) + break; + if (!(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_IN_TRAINING)) + return 1; + if (!count--) + break; + dev_dbg(pp->dev, "Link is up, but still in training\n"); + /* + * Wait a little bit, then re-check if the link finished + * the training. + */ + usleep_range(1000, 2000); + } /* * From L0, initiate MAC entry to gen2 if EP/RC supports gen2. * Wait 2ms (LTSSM timeout is 24ms, PHY lock is ~5us in gen2). @@ -446,15 +466,16 @@ static int imx6_pcie_link_up(struct pcie_port *pp) * to gen2 is stuck */ pcie_phy_read(pp->dbi_base, PCIE_PHY_RX_ASIC_OUT, &rx_valid); - ltssm = readl(pp->dbi_base + PCIE_PHY_DEBUG_R0) & 0x3F; + debug_r0 = readl(pp->dbi_base + PCIE_PHY_DEBUG_R0); if (rx_valid & 0x01) return 0; - if (ltssm != 0x0d) + if ((debug_r0 & 0x3f) != 0x0d) return 0; dev_err(pp->dev, "transition to gen2 is stuck, reset PHY!\n"); + dev_dbg(pp->dev, "debug_r0=%08x debug_r1=%08x\n", debug_r0, rc); imx6_pcie_reset_phy(pp); diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c index 0e79665afd44..97736674ddcd 100644 --- a/drivers/pci/host/pci-mvebu.c +++ b/drivers/pci/host/pci-mvebu.c @@ -291,6 +291,58 @@ static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port, return PCIBIOS_SUCCESSFUL; } +/* + * Remove windows, starting from the largest ones to the smallest + * ones. + */ +static void mvebu_pcie_del_windows(struct mvebu_pcie_port *port, + phys_addr_t base, size_t size) +{ + while (size) { + size_t sz = 1 << (fls(size) - 1); + + mvebu_mbus_del_window(base, sz); + base += sz; + size -= sz; + } +} + +/* + * MBus windows can only have a power of two size, but PCI BARs do not + * have this constraint. Therefore, we have to split the PCI BAR into + * areas each having a power of two size. We start from the largest + * one (i.e highest order bit set in the size). + */ +static void mvebu_pcie_add_windows(struct mvebu_pcie_port *port, + unsigned int target, unsigned int attribute, + phys_addr_t base, size_t size, + phys_addr_t remap) +{ + size_t size_mapped = 0; + + while (size) { + size_t sz = 1 << (fls(size) - 1); + int ret; + + ret = mvebu_mbus_add_window_remap_by_id(target, attribute, base, + sz, remap); + if (ret) { + dev_err(&port->pcie->pdev->dev, + "Could not create MBus window at 0x%x, size 0x%x: %d\n", + base, sz, ret); + mvebu_pcie_del_windows(port, base - size_mapped, + size_mapped); + return; + } + + size -= sz; + size_mapped += sz; + base += sz; + if (remap != MVEBU_MBUS_NO_REMAP) + remap += sz; + } +} + static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port) { phys_addr_t iobase; @@ -302,8 +354,8 @@ static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port) /* If a window was configured, remove it */ if (port->iowin_base) { - mvebu_mbus_del_window(port->iowin_base, - port->iowin_size); + mvebu_pcie_del_windows(port, port->iowin_base, + port->iowin_size); port->iowin_base = 0; port->iowin_size = 0; } @@ -329,11 +381,11 @@ static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port) port->iowin_base = port->pcie->io.start + iobase; port->iowin_size = ((0xFFF | ((port->bridge.iolimit & 0xF0) << 8) | (port->bridge.iolimitupper << 16)) - - iobase); + iobase) + 1; - mvebu_mbus_add_window_remap_by_id(port->io_target, port->io_attr, - port->iowin_base, port->iowin_size, - iobase); + mvebu_pcie_add_windows(port, port->io_target, port->io_attr, + port->iowin_base, port->iowin_size, + iobase); } static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port) @@ -344,8 +396,8 @@ static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port) /* If a window was configured, remove it */ if (port->memwin_base) { - mvebu_mbus_del_window(port->memwin_base, - port->memwin_size); + mvebu_pcie_del_windows(port, port->memwin_base, + port->memwin_size); port->memwin_base = 0; port->memwin_size = 0; } @@ -362,10 +414,11 @@ static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port) port->memwin_base = ((port->bridge.membase & 0xFFF0) << 16); port->memwin_size = (((port->bridge.memlimit & 0xFFF0) << 16) | 0xFFFFF) - - port->memwin_base; + port->memwin_base + 1; - mvebu_mbus_add_window_by_id(port->mem_target, port->mem_attr, - port->memwin_base, port->memwin_size); + mvebu_pcie_add_windows(port, port->mem_target, port->mem_attr, + port->memwin_base, port->memwin_size, + MVEBU_MBUS_NO_REMAP); } /* @@ -721,14 +774,21 @@ static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev, /* * On the PCI-to-PCI bridge side, the I/O windows must have at - * least a 64 KB size and be aligned on their size, and the - * memory windows must have at least a 1 MB size and be - * aligned on their size + * least a 64 KB size and the memory windows must have at + * least a 1 MB size. Moreover, MBus windows need to have a + * base address aligned on their size, and their size must be + * a power of two. This means that if the BAR doesn't have a + * power of two size, several MBus windows will actually be + * created. We need to ensure that the biggest MBus window + * (which will be the first one) is aligned on its size, which + * explains the rounddown_pow_of_two() being done here. */ if (res->flags & IORESOURCE_IO) - return round_up(start, max_t(resource_size_t, SZ_64K, size)); + return round_up(start, max_t(resource_size_t, SZ_64K, + rounddown_pow_of_two(size))); else if (res->flags & IORESOURCE_MEM) - return round_up(start, max_t(resource_size_t, SZ_1M, size)); + return round_up(start, max_t(resource_size_t, SZ_1M, + rounddown_pow_of_two(size))); else return start; } @@ -795,9 +855,9 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, rangesz = pna + na + ns; nranges = rlen / sizeof(__be32) / rangesz; - for (i = 0; i < nranges; i++) { + for (i = 0; i < nranges; i++, range += rangesz) { u32 flags = of_read_number(range, 1); - u32 slot = of_read_number(range, 2); + u32 slot = of_read_number(range + 1, 1); u64 cpuaddr = of_read_number(range + na, pna); unsigned long rtype; @@ -805,14 +865,14 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, rtype = IORESOURCE_IO; else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32) rtype = IORESOURCE_MEM; + else + continue; if (slot == PCI_SLOT(devfn) && type == rtype) { *tgt = DT_CPUADDR_TO_TARGET(cpuaddr); *attr = DT_CPUADDR_TO_ATTR(cpuaddr); return 0; } - - range += rangesz; } return -ENOENT; diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c index 17ce88f79d2b..f173dd09fce4 100644 --- a/drivers/pci/host/pcie-designware.c +++ b/drivers/pci/host/pcie-designware.c @@ -522,13 +522,13 @@ static void dw_pcie_prog_viewport_cfg1(struct pcie_port *pp, u32 busdev) dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1, PCIE_ATU_VIEWPORT); dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG1, PCIE_ATU_CR1); - dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2); dw_pcie_writel_rc(pp, pp->cfg1_base, PCIE_ATU_LOWER_BASE); dw_pcie_writel_rc(pp, (pp->cfg1_base >> 32), PCIE_ATU_UPPER_BASE); dw_pcie_writel_rc(pp, pp->cfg1_base + pp->config.cfg1_size - 1, PCIE_ATU_LIMIT); dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET); dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET); + dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2); } static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp) @@ -537,7 +537,6 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp) dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0, PCIE_ATU_VIEWPORT); dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_MEM, PCIE_ATU_CR1); - dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2); dw_pcie_writel_rc(pp, pp->mem_base, PCIE_ATU_LOWER_BASE); dw_pcie_writel_rc(pp, (pp->mem_base >> 32), PCIE_ATU_UPPER_BASE); dw_pcie_writel_rc(pp, pp->mem_base + pp->config.mem_size - 1, @@ -545,6 +544,7 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp) dw_pcie_writel_rc(pp, pp->config.mem_bus_addr, PCIE_ATU_LOWER_TARGET); dw_pcie_writel_rc(pp, upper_32_bits(pp->config.mem_bus_addr), PCIE_ATU_UPPER_TARGET); + dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2); } static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp) @@ -553,7 +553,6 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp) dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1, PCIE_ATU_VIEWPORT); dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_IO, PCIE_ATU_CR1); - dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2); dw_pcie_writel_rc(pp, pp->io_base, PCIE_ATU_LOWER_BASE); dw_pcie_writel_rc(pp, (pp->io_base >> 32), PCIE_ATU_UPPER_BASE); dw_pcie_writel_rc(pp, pp->io_base + pp->config.io_size - 1, @@ -561,6 +560,7 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp) dw_pcie_writel_rc(pp, pp->config.io_bus_addr, PCIE_ATU_LOWER_TARGET); dw_pcie_writel_rc(pp, upper_32_bits(pp->config.io_bus_addr), PCIE_ATU_UPPER_TARGET); + dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2); } static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus, @@ -800,7 +800,7 @@ void dw_pcie_setup_rc(struct pcie_port *pp) /* setup RC BARs */ dw_pcie_writel_rc(pp, 0x00000004, PCI_BASE_ADDRESS_0); - dw_pcie_writel_rc(pp, 0x00000004, PCI_BASE_ADDRESS_1); + dw_pcie_writel_rc(pp, 0x00000000, PCI_BASE_ADDRESS_1); /* setup interrupt pins */ dw_pcie_readl_rc(pp, PCI_INTERRUPT_LINE, &val); diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c index 58499277903a..6efc2ec5e4db 100644 --- a/drivers/pci/hotplug/shpchp_ctrl.c +++ b/drivers/pci/hotplug/shpchp_ctrl.c @@ -282,8 +282,8 @@ static int board_added(struct slot *p_slot) return WRONG_BUS_FREQUENCY; } - bsp = ctrl->pci_dev->bus->cur_bus_speed; - msp = ctrl->pci_dev->bus->max_bus_speed; + bsp = ctrl->pci_dev->subordinate->cur_bus_speed; + msp = ctrl->pci_dev->subordinate->max_bus_speed; /* Check if there are other slots or devices on the same bus */ if (!list_empty(&ctrl->pci_dev->subordinate->devices)) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 955ab7990c5b..fb02fc2fb034 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -414,7 +414,7 @@ static void free_msi_irqs(struct pci_dev *dev) if (dev->msi_irq_groups) { sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups); msi_attrs = dev->msi_irq_groups[0]->attrs; - list_for_each_entry(entry, &dev->msi_list, list) { + while (msi_attrs[count]) { dev_attr = container_of(msi_attrs[count], struct device_attribute, attr); kfree(dev_attr->attr.name); diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c index 45113daaa778..e27a3dc9f4e8 100644 --- a/drivers/pci/pci-label.c +++ b/drivers/pci/pci-label.c @@ -168,8 +168,8 @@ enum acpi_attr_enum { static void dsm_label_utf16s_to_utf8s(union acpi_object *obj, char *buf) { int len; - len = utf16s_to_utf8s((const wchar_t *)obj->string.pointer, - obj->string.length, + len = utf16s_to_utf8s((const wchar_t *)obj->buffer.pointer, + obj->buffer.length, UTF16_LITTLE_ENDIAN, buf, PAGE_SIZE); buf[len] = '\n'; @@ -194,16 +194,22 @@ dsm_get_label(struct device *dev, char *buf, enum acpi_attr_enum attr) tmp = obj->package.elements; if (obj->type == ACPI_TYPE_PACKAGE && obj->package.count == 2 && tmp[0].type == ACPI_TYPE_INTEGER && - tmp[1].type == ACPI_TYPE_STRING) { + (tmp[1].type == ACPI_TYPE_STRING || + tmp[1].type == ACPI_TYPE_BUFFER)) { /* * The second string element is optional even when * this _DSM is implemented; when not implemented, * this entry must return a null string. */ - if (attr == ACPI_ATTR_INDEX_SHOW) + if (attr == ACPI_ATTR_INDEX_SHOW) { scnprintf(buf, PAGE_SIZE, "%llu\n", tmp->integer.value); - else if (attr == ACPI_ATTR_LABEL_SHOW) - dsm_label_utf16s_to_utf8s(tmp + 1, buf); + } else if (attr == ACPI_ATTR_LABEL_SHOW) { + if (tmp[1].type == ACPI_TYPE_STRING) + scnprintf(buf, PAGE_SIZE, "%s\n", + tmp[1].string.pointer); + else if (tmp[1].type == ACPI_TYPE_BUFFER) + dsm_label_utf16s_to_utf8s(tmp + 1, buf); + } len = strlen(buf) > 0 ? strlen(buf) : -1; } diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 276ef9c18802..a943c6c0f206 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -178,7 +178,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, { struct pci_dev *pci_dev = to_pci_dev(dev); - return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n", + return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n", pci_dev->vendor, pci_dev->device, pci_dev->subsystem_vendor, pci_dev->subsystem_device, (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8), @@ -186,9 +186,9 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(modalias); -static ssize_t enabled_store(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) +static ssize_t enable_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct pci_dev *pdev = to_pci_dev(dev); unsigned long val; @@ -212,15 +212,15 @@ static ssize_t enabled_store(struct device *dev, return result < 0 ? result : count; } -static ssize_t enabled_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t enable_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct pci_dev *pdev; pdev = to_pci_dev (dev); return sprintf (buf, "%u\n", atomic_read(&pdev->enable_cnt)); } -static DEVICE_ATTR_RW(enabled); +static DEVICE_ATTR_RW(enable); #ifdef CONFIG_NUMA static ssize_t @@ -526,7 +526,7 @@ static struct attribute *pci_dev_attrs[] = { #endif &dev_attr_dma_mask_bits.attr, &dev_attr_consistent_dma_mask_bits.attr, - &dev_attr_enabled.attr, + &dev_attr_enable.attr, &dev_attr_broken_parity_status.attr, &dev_attr_msi_bus.attr, #if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index fdbc294821e6..dae70d216762 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -830,12 +830,6 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) if (!__pci_complete_power_transition(dev, state)) error = 0; - /* - * When aspm_policy is "powersave" this call ensures - * that ASPM is configured. - */ - if (!error && dev->bus->self) - pcie_aspm_powersave_config_link(dev->bus->self); return error; } @@ -1181,12 +1175,18 @@ EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state); static int do_pci_enable_device(struct pci_dev *dev, int bars) { int err; + struct pci_dev *bridge; u16 cmd; u8 pin; err = pci_set_power_state(dev, PCI_D0); if (err < 0 && err != -EIO) return err; + + bridge = pci_upstream_bridge(dev); + if (bridge) + pcie_aspm_powersave_config_link(bridge); + err = pcibios_enable_device(dev, bars); if (err < 0) return err; @@ -3043,7 +3043,8 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev) if (!pci_is_pcie(dev)) return 1; - return pci_wait_for_pending(dev, PCI_EXP_DEVSTA, PCI_EXP_DEVSTA_TRPND); + return pci_wait_for_pending(dev, pci_pcie_cap(dev) + PCI_EXP_DEVSTA, + PCI_EXP_DEVSTA_TRPND); } EXPORT_SYMBOL(pci_wait_for_pending_transaction); @@ -3084,8 +3085,13 @@ static int pci_af_flr(struct pci_dev *dev, int probe) if (probe) return 0; - /* Wait for Transaction Pending bit clean */ - if (pci_wait_for_pending(dev, PCI_AF_STATUS, PCI_AF_STATUS_TP)) + /* + * Wait for Transaction Pending bit to clear. A word-aligned test + * is used, so we use the conrol offset rather than status and shift + * the test bit to match. + */ + if (pci_wait_for_pending(dev, pos + PCI_AF_CTRL, + PCI_AF_STATUS_TP << 8)) goto clear; dev_err(&dev->dev, "transaction is not cleared; " @@ -4101,7 +4107,7 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode, u16 cmd; int rc; - WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) & (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY))); + WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) && (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY))); /* ARCH specific VGA enables */ rc = pci_set_vga_state_arch(dev, decode, command_bits, flags); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 5cb726c193de..6e8776b59a2c 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -24,6 +24,7 @@ #include <linux/ioport.h> #include <linux/sched.h> #include <linux/ktime.h> +#include <linux/mm.h> #include <asm/dma.h> /* isa_dma_bridge_buggy */ #include "pci.h" @@ -287,6 +288,25 @@ static void quirk_citrine(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CITRINE, quirk_citrine); +/* On IBM Crocodile ipr SAS adapters, expand BAR to system page size */ +static void quirk_extend_bar_to_page(struct pci_dev *dev) +{ + int i; + + for (i = 0; i < PCI_STD_RESOURCE_END; i++) { + struct resource *r = &dev->resource[i]; + + if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) { + r->end = PAGE_SIZE - 1; + r->start = 0; + r->flags |= IORESOURCE_UNSET; + dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n", + i, r); + } + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page); + /* * S3 868 and 968 chips report region size equal to 32M, but they decode 64M. * If it's needed, re-allocate the region. @@ -2949,6 +2969,7 @@ static void disable_igfx_irq(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0152, disable_igfx_irq); /* * PCI devices which are on Intel chips can skip the 10ms delay diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 6c738376daff..34d56f7864d6 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -553,8 +553,9 @@ struct phy *phy_create(struct device *dev, const struct phy_ops *ops, return phy; put_dev: - put_device(&phy->dev); - ida_remove(&phy_ida, phy->id); + put_device(&phy->dev); /* calls phy_release() which frees resources */ + return ERR_PTR(ret); + free_phy: kfree(phy); return ERR_PTR(ret); @@ -738,7 +739,7 @@ static void phy_release(struct device *dev) phy = to_phy(dev); dev_vdbg(dev, "releasing '%s'\n", dev_name(dev)); - ida_remove(&phy_ida, phy->id); + ida_simple_remove(&phy_ida, phy->id); kfree(phy); } diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c index 7f139326a642..ff026689358c 100644 --- a/drivers/phy/phy-exynos-mipi-video.c +++ b/drivers/phy/phy-exynos-mipi-video.c @@ -101,7 +101,7 @@ static struct phy *exynos_mipi_video_phy_xlate(struct device *dev, { struct exynos_mipi_video_phy *state = dev_get_drvdata(dev); - if (WARN_ON(args->args[0] > EXYNOS_MIPI_PHYS_NUM)) + if (WARN_ON(args->args[0] >= EXYNOS_MIPI_PHYS_NUM)) return ERR_PTR(-ENODEV); return state->phys[args->args[0]].phy; diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index c3ace1db8136..aaac3594f83b 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -34,6 +34,7 @@ #include <linux/delay.h> #include <linux/usb/otg.h> #include <linux/phy/phy.h> +#include <linux/pm_runtime.h> #include <linux/usb/musb-omap.h> #include <linux/usb/ulpi.h> #include <linux/i2c/twl.h> @@ -422,37 +423,55 @@ static void twl4030_phy_power(struct twl4030_usb *twl, int on) } } -static int twl4030_phy_power_off(struct phy *phy) +static int twl4030_usb_runtime_suspend(struct device *dev) { - struct twl4030_usb *twl = phy_get_drvdata(phy); + struct twl4030_usb *twl = dev_get_drvdata(dev); + dev_dbg(twl->dev, "%s\n", __func__); if (twl->asleep) return 0; twl4030_phy_power(twl, 0); twl->asleep = 1; - dev_dbg(twl->dev, "%s\n", __func__); + return 0; } -static void __twl4030_phy_power_on(struct twl4030_usb *twl) +static int twl4030_usb_runtime_resume(struct device *dev) { + struct twl4030_usb *twl = dev_get_drvdata(dev); + + dev_dbg(twl->dev, "%s\n", __func__); + if (!twl->asleep) + return 0; + twl4030_phy_power(twl, 1); - twl4030_i2c_access(twl, 1); - twl4030_usb_set_mode(twl, twl->usb_mode); - if (twl->usb_mode == T2_USB_MODE_ULPI) - twl4030_i2c_access(twl, 0); + twl->asleep = 0; + + return 0; +} + +static int twl4030_phy_power_off(struct phy *phy) +{ + struct twl4030_usb *twl = phy_get_drvdata(phy); + + dev_dbg(twl->dev, "%s\n", __func__); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + + return 0; } static int twl4030_phy_power_on(struct phy *phy) { struct twl4030_usb *twl = phy_get_drvdata(phy); - if (!twl->asleep) - return 0; - __twl4030_phy_power_on(twl); - twl->asleep = 0; dev_dbg(twl->dev, "%s\n", __func__); + pm_runtime_get_sync(twl->dev); + twl4030_i2c_access(twl, 1); + twl4030_usb_set_mode(twl, twl->usb_mode); + if (twl->usb_mode == T2_USB_MODE_ULPI) + twl4030_i2c_access(twl, 0); /* * XXX When VBUS gets driven after musb goes to A mode, @@ -558,9 +577,27 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) * USB_LINK_VBUS state. musb_hdrc won't care until it * starts to handle softconnect right. */ + if ((status == OMAP_MUSB_VBUS_VALID) || + (status == OMAP_MUSB_ID_GROUND)) { + if (twl->asleep) + pm_runtime_get_sync(twl->dev); + } else { + if (!twl->asleep) { + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + } + } omap_musb_mailbox(status); } - sysfs_notify(&twl->dev->kobj, NULL, "vbus"); + + /* don't schedule during sleep - irq works right then */ + if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) { + cancel_delayed_work(&twl->id_workaround_work); + schedule_delayed_work(&twl->id_workaround_work, HZ); + } + + if (irq) + sysfs_notify(&twl->dev->kobj, NULL, "vbus"); return IRQ_HANDLED; } @@ -569,29 +606,8 @@ static void twl4030_id_workaround_work(struct work_struct *work) { struct twl4030_usb *twl = container_of(work, struct twl4030_usb, id_workaround_work.work); - enum omap_musb_vbus_id_status status; - bool status_changed = false; - - status = twl4030_usb_linkstat(twl); - - spin_lock_irq(&twl->lock); - if (status >= 0 && status != twl->linkstat) { - twl->linkstat = status; - status_changed = true; - } - spin_unlock_irq(&twl->lock); - - if (status_changed) { - dev_dbg(twl->dev, "handle missing status change to %d\n", - status); - omap_musb_mailbox(status); - } - /* don't schedule during sleep - irq works right then */ - if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) { - cancel_delayed_work(&twl->id_workaround_work); - schedule_delayed_work(&twl->id_workaround_work, HZ); - } + twl4030_usb_irq(0, twl); } static int twl4030_phy_init(struct phy *phy) @@ -599,22 +615,17 @@ static int twl4030_phy_init(struct phy *phy) struct twl4030_usb *twl = phy_get_drvdata(phy); enum omap_musb_vbus_id_status status; - /* - * Start in sleep state, we'll get called through set_suspend() - * callback when musb is runtime resumed and it's time to start. - */ - __twl4030_phy_power(twl, 0); - twl->asleep = 1; - + pm_runtime_get_sync(twl->dev); status = twl4030_usb_linkstat(twl); twl->linkstat = status; - if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) { + if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) omap_musb_mailbox(twl->linkstat); - twl4030_phy_power_on(phy); - } sysfs_notify(&twl->dev->kobj, NULL, "vbus"); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + return 0; } @@ -650,6 +661,11 @@ static const struct phy_ops ops = { .owner = THIS_MODULE, }; +static const struct dev_pm_ops twl4030_usb_pm_ops = { + SET_RUNTIME_PM_OPS(twl4030_usb_runtime_suspend, + twl4030_usb_runtime_resume, NULL) +}; + static int twl4030_usb_probe(struct platform_device *pdev) { struct twl4030_usb_data *pdata = dev_get_platdata(&pdev->dev); @@ -726,6 +742,11 @@ static int twl4030_usb_probe(struct platform_device *pdev) ATOMIC_INIT_NOTIFIER_HEAD(&twl->phy.notifier); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_autosuspend_delay(&pdev->dev, 2000); + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + /* Our job is to use irqs and status from the power module * to keep the transceiver disabled when nothing's connected. * @@ -744,6 +765,9 @@ static int twl4030_usb_probe(struct platform_device *pdev) return status; } + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(twl->dev); + dev_info(&pdev->dev, "Initialized TWL4030 USB module\n"); return 0; } @@ -753,6 +777,7 @@ static int twl4030_usb_remove(struct platform_device *pdev) struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; + pm_runtime_get_sync(twl->dev); cancel_delayed_work(&twl->id_workaround_work); device_remove_file(twl->dev, &dev_attr_vbus); @@ -772,9 +797,8 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - - if (!twl->asleep) - twl4030_phy_power(twl, 0); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put(twl->dev); return 0; } @@ -792,6 +816,7 @@ static struct platform_driver twl4030_usb_driver = { .remove = twl4030_usb_remove, .driver = { .name = "twl4030_usb", + .pm = &twl4030_usb_pm_ops, .owner = THIS_MODULE, .of_match_table = of_match_ptr(twl4030_usb_id_table), }, diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c index 92ed4b2e3c07..c862f9c0e9ce 100644 --- a/drivers/pinctrl/pinctrl-as3722.c +++ b/drivers/pinctrl/pinctrl-as3722.c @@ -64,7 +64,6 @@ struct as3722_pin_function { }; struct as3722_gpio_pin_control { - bool enable_gpio_invert; unsigned mode_prop; int io_function; }; @@ -320,10 +319,8 @@ static int as3722_pinctrl_gpio_set_direction(struct pinctrl_dev *pctldev, return mode; } - if (as_pci->gpio_control[offset].enable_gpio_invert) - mode |= AS3722_GPIO_INV; - - return as3722_write(as3722, AS3722_GPIOn_CONTROL_REG(offset), mode); + return as3722_update_bits(as3722, AS3722_GPIOn_CONTROL_REG(offset), + AS3722_GPIO_MODE_MASK, mode); } static const struct pinmux_ops as3722_pinmux_ops = { @@ -496,10 +493,18 @@ static void as3722_gpio_set(struct gpio_chip *chip, unsigned offset, { struct as3722_pctrl_info *as_pci = to_as_pci(chip); struct as3722 *as3722 = as_pci->as3722; - int en_invert = as_pci->gpio_control[offset].enable_gpio_invert; + int en_invert; u32 val; int ret; + ret = as3722_read(as3722, AS3722_GPIOn_CONTROL_REG(offset), &val); + if (ret < 0) { + dev_err(as_pci->dev, + "GPIO_CONTROL%d_REG read failed: %d\n", offset, ret); + return; + } + en_invert = !!(val & AS3722_GPIO_INV); + if (value) val = (en_invert) ? 0 : AS3722_GPIOn_SIGNAL(offset); else diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c index 665b96bc0c3a..eb9f1906952a 100644 --- a/drivers/pinctrl/pinctrl-baytrail.c +++ b/drivers/pinctrl/pinctrl-baytrail.c @@ -263,7 +263,7 @@ static int byt_gpio_direction_output(struct gpio_chip *chip, spin_lock_irqsave(&vg->lock, flags); reg_val = readl(reg) | BYT_DIR_MASK; - reg_val &= ~BYT_OUTPUT_EN; + reg_val &= ~(BYT_OUTPUT_EN | BYT_INPUT_EN); if (value) writel(reg_val | BYT_LEVEL, reg); diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index c91f69b39db4..dcfcaea76048 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -570,6 +570,17 @@ static const struct dmi_system_id video_vendor_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5750"), }, }, + { + /* + * Note no video_set_backlight_video_vendor, we must use the + * acer interface, as there is no native backlight interface. + */ + .ident = "Acer KAV80", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "KAV80"), + }, + }, {} }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index defb6afc1409..e2a91c845ac9 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8447,9 +8447,21 @@ static void mute_led_exit(void) tpacpi_led_set(i, false); } +static void mute_led_resume(void) +{ + int i; + + for (i = 0; i < TPACPI_LED_MAX; i++) { + struct tp_led_table *t = &led_tables[i]; + if (t->state >= 0) + mute_led_on_off(t, t->state); + } +} + static struct ibm_struct mute_led_driver_data = { .name = "mute_led", .exit = mute_led_exit, + .resume = mute_led_resume, }; /**************************************************************************** diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c index 9f611cbbc294..da1c6cb1a41e 100644 --- a/drivers/pnp/pnpacpi/core.c +++ b/drivers/pnp/pnpacpi/core.c @@ -83,8 +83,7 @@ static int pnpacpi_set_resources(struct pnp_dev *dev) { struct acpi_device *acpi_dev; acpi_handle handle; - struct acpi_buffer buffer; - int ret; + int ret = 0; pnp_dbg(&dev->dev, "set resources\n"); @@ -97,19 +96,26 @@ static int pnpacpi_set_resources(struct pnp_dev *dev) if (WARN_ON_ONCE(acpi_dev != dev->data)) dev->data = acpi_dev; - ret = pnpacpi_build_resource_template(dev, &buffer); - if (ret) - return ret; - ret = pnpacpi_encode_resources(dev, &buffer); - if (ret) { + if (acpi_has_method(handle, METHOD_NAME__SRS)) { + struct acpi_buffer buffer; + + ret = pnpacpi_build_resource_template(dev, &buffer); + if (ret) + return ret; + + ret = pnpacpi_encode_resources(dev, &buffer); + if (!ret) { + acpi_status status; + + status = acpi_set_current_resources(handle, &buffer); + if (ACPI_FAILURE(status)) + ret = -EIO; + } kfree(buffer.pointer); - return ret; } - if (ACPI_FAILURE(acpi_set_current_resources(handle, &buffer))) - ret = -EINVAL; - else if (acpi_bus_power_manageable(handle)) + if (!ret && acpi_bus_power_manageable(handle)) ret = acpi_bus_set_power(handle, ACPI_STATE_D0); - kfree(buffer.pointer); + return ret; } @@ -117,7 +123,7 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev) { struct acpi_device *acpi_dev; acpi_handle handle; - int ret; + acpi_status status; dev_dbg(&dev->dev, "disable resources\n"); @@ -128,13 +134,15 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev) } /* acpi_unregister_gsi(pnp_irq(dev, 0)); */ - ret = 0; if (acpi_bus_power_manageable(handle)) acpi_bus_set_power(handle, ACPI_STATE_D3_COLD); - /* continue even if acpi_bus_set_power() fails */ - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DIS", NULL, NULL))) - ret = -ENODEV; - return ret; + + /* continue even if acpi_bus_set_power() fails */ + status = acpi_evaluate_object(handle, "_DIS", NULL, NULL); + if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) + return -ENODEV; + + return 0; } #ifdef CONFIG_ACPI_SLEEP @@ -331,8 +339,7 @@ static int __init acpi_pnp_match(struct device *dev, void *_pnp) struct pnp_dev *pnp = _pnp; /* true means it matched */ - return !acpi->physical_node_count - && compare_pnp_id(pnp->id, acpi_device_hid(acpi)); + return pnp->data == acpi; } static struct acpi_device * __init acpi_pnp_find_companion(struct device *dev) diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c index 79a37f6d3307..e384844a1ae1 100644 --- a/drivers/power/bq2415x_charger.c +++ b/drivers/power/bq2415x_charger.c @@ -840,8 +840,7 @@ static int bq2415x_notifier_call(struct notifier_block *nb, if (bq->automode < 1) return NOTIFY_OK; - sysfs_notify(&bq->charger.dev->kobj, NULL, "reported_mode"); - bq2415x_set_mode(bq, bq->reported_mode); + schedule_delayed_work(&bq->work, 0); return NOTIFY_OK; } @@ -892,6 +891,11 @@ static void bq2415x_timer_work(struct work_struct *work) int error; int boost; + if (bq->automode > 0 && (bq->reported_mode != bq->mode)) { + sysfs_notify(&bq->charger.dev->kobj, NULL, "reported_mode"); + bq2415x_set_mode(bq, bq->reported_mode); + } + if (!bq->autotimer) return; diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c index 9e4dab46eefd..ef1f4c928431 100644 --- a/drivers/power/charger-manager.c +++ b/drivers/power/charger-manager.c @@ -1720,6 +1720,11 @@ static int charger_manager_probe(struct platform_device *pdev) return -EINVAL; } + if (!desc->psy_fuel_gauge) { + dev_err(&pdev->dev, "No fuel gauge power supply defined\n"); + return -EINVAL; + } + /* Counting index only */ while (desc->psy_charger_stat[i]) i++; diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c index 91245f5dbe81..47257b6eea84 100644 --- a/drivers/rapidio/devices/tsi721_dma.c +++ b/drivers/rapidio/devices/tsi721_dma.c @@ -287,6 +287,12 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan) "desc %p not ACKed\n", tx_desc); } + if (ret == NULL) { + dev_dbg(bdma_chan->dchan.device->dev, + "%s: unable to obtain tx descriptor\n", __func__); + goto err_out; + } + i = bdma_chan->wr_count_next % bdma_chan->bd_num; if (i == bdma_chan->bd_num - 1) { i = 0; @@ -297,7 +303,7 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan) tx_desc->txd.phys = bdma_chan->bd_phys + i * sizeof(struct tsi721_dma_desc); tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i]; - +err_out: spin_unlock_bh(&bdma_chan->lock); return ret; diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c index 4f6c2055f6b2..8b963a757883 100644 --- a/drivers/regulator/arizona-ldo1.c +++ b/drivers/regulator/arizona-ldo1.c @@ -141,8 +141,6 @@ static struct regulator_ops arizona_ldo1_ops = { .map_voltage = regulator_map_voltage_linear, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, - .get_bypass = regulator_get_bypass_regmap, - .set_bypass = regulator_set_bypass_regmap, }; static const struct regulator_desc arizona_ldo1 = { @@ -153,11 +151,9 @@ static const struct regulator_desc arizona_ldo1 = { .vsel_reg = ARIZONA_LDO1_CONTROL_1, .vsel_mask = ARIZONA_LDO1_VSEL_MASK, - .bypass_reg = ARIZONA_LDO1_CONTROL_1, - .bypass_mask = ARIZONA_LDO1_BYPASS, .min_uV = 900000, - .uV_step = 50000, - .n_voltages = 7, + .uV_step = 25000, + .n_voltages = 13, .enable_time = 500, .owner = THIS_MODULE, @@ -203,6 +199,7 @@ static int arizona_ldo1_probe(struct platform_device *pdev) */ switch (arizona->type) { case WM5102: + case WM8997: desc = &arizona_ldo1_hc; ldo1->init_data = arizona_ldo1_dvfs; break; diff --git a/drivers/regulator/max77693.c b/drivers/regulator/max77693.c index 5fb899f461d0..24c926bfe6d4 100644 --- a/drivers/regulator/max77693.c +++ b/drivers/regulator/max77693.c @@ -232,7 +232,7 @@ static int max77693_pmic_probe(struct platform_device *pdev) struct max77693_pmic_dev *max77693_pmic; struct max77693_regulator_data *rdata = NULL; int num_rdata, i; - struct regulator_config config; + struct regulator_config config = { }; num_rdata = max77693_pmic_init_rdata(&pdev->dev, &rdata); if (!rdata || num_rdata <= 0) { diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c index 3281c90691c3..44fe83ee9bee 100644 --- a/drivers/rtc/rtc-at91rm9200.c +++ b/drivers/rtc/rtc-at91rm9200.c @@ -48,6 +48,7 @@ struct at91_rtc_config { static const struct at91_rtc_config *at91_rtc_config; static DECLARE_COMPLETION(at91_rtc_updated); +static DECLARE_COMPLETION(at91_rtc_upd_rdy); static unsigned int at91_alarm_year = AT91_RTC_EPOCH; static void __iomem *at91_rtc_regs; static int irq; @@ -161,6 +162,8 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm) 1900 + tm->tm_year, tm->tm_mon, tm->tm_mday, tm->tm_hour, tm->tm_min, tm->tm_sec); + wait_for_completion(&at91_rtc_upd_rdy); + /* Stop Time/Calendar from counting */ cr = at91_rtc_read(AT91_RTC_CR); at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM); @@ -183,7 +186,9 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm) /* Restart Time/Calendar */ cr = at91_rtc_read(AT91_RTC_CR); + at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_SECEV); at91_rtc_write(AT91_RTC_CR, cr & ~(AT91_RTC_UPDCAL | AT91_RTC_UPDTIM)); + at91_rtc_write_ier(AT91_RTC_SECEV); return 0; } @@ -290,8 +295,10 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id) if (rtsr) { /* this interrupt is shared! Is it ours? */ if (rtsr & AT91_RTC_ALARM) events |= (RTC_AF | RTC_IRQF); - if (rtsr & AT91_RTC_SECEV) - events |= (RTC_UF | RTC_IRQF); + if (rtsr & AT91_RTC_SECEV) { + complete(&at91_rtc_upd_rdy); + at91_rtc_write_idr(AT91_RTC_SECEV); + } if (rtsr & AT91_RTC_ACKUPD) complete(&at91_rtc_updated); @@ -413,6 +420,11 @@ static int __init at91_rtc_probe(struct platform_device *pdev) return PTR_ERR(rtc); platform_set_drvdata(pdev, rtc); + /* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy + * completion. + */ + at91_rtc_write_ier(AT91_RTC_SECEV); + dev_info(&pdev->dev, "AT91 Real Time Clock driver.\n"); return 0; } diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c index bd628a6f981d..e5f13c4310fe 100644 --- a/drivers/rtc/rtc-hym8563.c +++ b/drivers/rtc/rtc-hym8563.c @@ -569,6 +569,9 @@ static int hym8563_probe(struct i2c_client *client, if (IS_ERR(hym8563->rtc)) return PTR_ERR(hym8563->rtc); + /* the hym8563 alarm only supports a minute accuracy */ + hym8563->rtc->uie_unsupported = 1; + #ifdef CONFIG_COMMON_CLK hym8563_clkout_register_clk(hym8563); #endif diff --git a/drivers/rtc/rtc-puv3.c b/drivers/rtc/rtc-puv3.c index 1ecfe3bd92ac..1cff2a21db67 100644 --- a/drivers/rtc/rtc-puv3.c +++ b/drivers/rtc/rtc-puv3.c @@ -71,7 +71,7 @@ static int puv3_rtc_setpie(struct device *dev, int enabled) { unsigned int tmp; - dev_debug(dev, "%s: pie=%d\n", __func__, enabled); + dev_dbg(dev, "%s: pie=%d\n", __func__, enabled); spin_lock_irq(&puv3_rtc_pie_lock); tmp = readl(RTC_RTSR) & ~RTC_RTSR_HZE; @@ -140,7 +140,7 @@ static int puv3_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) rtc_tm_to_time(tm, &rtcalarm_count); writel(rtcalarm_count, RTC_RTAR); - puv3_rtc_setaie(&dev->dev, alrm->enabled); + puv3_rtc_setaie(dev, alrm->enabled); if (alrm->enabled) enable_irq_wake(puv3_rtc_alarmno); diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index eb5d22795c47..bb86494e2b7b 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -922,7 +922,7 @@ static int __init con3215_init(void) raw3215_freelist = req; } - cdev = ccw_device_probe_console(); + cdev = ccw_device_probe_console(&raw3215_ccw_driver); if (IS_ERR(cdev)) return -ENODEV; diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c index 699fd3e363df..bb6b0df50b33 100644 --- a/drivers/s390/char/con3270.c +++ b/drivers/s390/char/con3270.c @@ -576,7 +576,6 @@ static struct console con3270 = { static int __init con3270_init(void) { - struct ccw_device *cdev; struct raw3270 *rp; void *cbuf; int i; @@ -591,10 +590,7 @@ con3270_init(void) cpcmd("TERM AUTOCR OFF", NULL, 0, NULL); } - cdev = ccw_device_probe_console(); - if (IS_ERR(cdev)) - return -ENODEV; - rp = raw3270_setup_console(cdev); + rp = raw3270_setup_console(); if (IS_ERR(rp)) return PTR_ERR(rp); diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index 2cdec21e8924..de2c0483949f 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -776,16 +776,24 @@ raw3270_setup_device(struct ccw_device *cdev, struct raw3270 *rp, char *ascebc) } #ifdef CONFIG_TN3270_CONSOLE +/* Tentative definition - see below for actual definition. */ +static struct ccw_driver raw3270_ccw_driver; + /* * Setup 3270 device configured as console. */ -struct raw3270 __init *raw3270_setup_console(struct ccw_device *cdev) +struct raw3270 __init *raw3270_setup_console(void) { + struct ccw_device *cdev; unsigned long flags; struct raw3270 *rp; char *ascebc; int rc; + cdev = ccw_device_probe_console(&raw3270_ccw_driver); + if (IS_ERR(cdev)) + return ERR_CAST(cdev); + rp = kzalloc(sizeof(struct raw3270), GFP_KERNEL | GFP_DMA); ascebc = kzalloc(256, GFP_KERNEL); rc = raw3270_setup_device(cdev, rp, ascebc); diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h index 7b73ff8c1bd7..359276a88396 100644 --- a/drivers/s390/char/raw3270.h +++ b/drivers/s390/char/raw3270.h @@ -190,7 +190,7 @@ raw3270_put_view(struct raw3270_view *view) wake_up(&raw3270_wait_queue); } -struct raw3270 *raw3270_setup_console(struct ccw_device *cdev); +struct raw3270 *raw3270_setup_console(void); void raw3270_wait_cons_dev(struct raw3270 *); /* Notifier for device addition/removal */ diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 9f0ea6cb6922..e3bf885f4a6c 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -541,18 +541,27 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area) static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm) { - do { + static int ntsm_unsupported; + + while (true) { memset(sei, 0, sizeof(*sei)); sei->request.length = 0x0010; sei->request.code = 0x000e; - sei->ntsm = ntsm; + if (!ntsm_unsupported) + sei->ntsm = ntsm; if (chsc(sei)) break; if (sei->response.code != 0x0001) { - CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n", - sei->response.code); + CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x, ntsm=%llx)\n", + sei->response.code, sei->ntsm); + + if (sei->response.code == 3 && sei->ntsm) { + /* Fallback for old firmware. */ + ntsm_unsupported = 1; + continue; + } break; } @@ -568,7 +577,10 @@ static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm) CIO_CRW_EVENT(2, "chsc: unhandled nt: %d\n", sei->nt); break; } - } while (sei->u.nt0_area.flags & 0x80); + + if (!(sei->u.nt0_area.flags & 0x80)) + break; + } } /* diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index e9d783563cbb..4283dd3cdd49 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1609,7 +1609,7 @@ out_unlock: return rc; } -struct ccw_device *ccw_device_probe_console(void) +struct ccw_device *ccw_device_probe_console(struct ccw_driver *drv) { struct io_subchannel_private *io_priv; struct ccw_device *cdev; @@ -1631,6 +1631,7 @@ struct ccw_device *ccw_device_probe_console(void) kfree(io_priv); return cdev; } + cdev->drv = drv; set_io_private(sch, io_priv); ret = ccw_device_console_enable(cdev, sch); if (ret) { diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c index 160e7510aca6..0787b9756165 100644 --- a/drivers/sbus/char/bbc_envctrl.c +++ b/drivers/sbus/char/bbc_envctrl.c @@ -452,6 +452,9 @@ static void attach_one_temp(struct bbc_i2c_bus *bp, struct platform_device *op, if (!tp) return; + INIT_LIST_HEAD(&tp->bp_list); + INIT_LIST_HEAD(&tp->glob_list); + tp->client = bbc_i2c_attach(bp, op); if (!tp->client) { kfree(tp); @@ -497,6 +500,9 @@ static void attach_one_fan(struct bbc_i2c_bus *bp, struct platform_device *op, if (!fp) return; + INIT_LIST_HEAD(&fp->bp_list); + INIT_LIST_HEAD(&fp->glob_list); + fp->client = bbc_i2c_attach(bp, op); if (!fp->client) { kfree(fp); diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c index c7763e482eb2..812b5f0361b6 100644 --- a/drivers/sbus/char/bbc_i2c.c +++ b/drivers/sbus/char/bbc_i2c.c @@ -300,13 +300,18 @@ static struct bbc_i2c_bus * attach_one_i2c(struct platform_device *op, int index if (!bp) return NULL; + INIT_LIST_HEAD(&bp->temps); + INIT_LIST_HEAD(&bp->fans); + bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs"); if (!bp->i2c_control_regs) goto fail; - bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel"); - if (!bp->i2c_bussel_reg) - goto fail; + if (op->num_resources == 2) { + bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel"); + if (!bp->i2c_bussel_reg) + goto fail; + } bp->waiting = 0; init_waitqueue_head(&bp->wq); diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index 4f6a30b8e5f9..652b41b4ddbd 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -2500,16 +2500,15 @@ static int arcmsr_polling_ccbdone(struct AdapterControlBlock *acb, static int arcmsr_iop_confirm(struct AdapterControlBlock *acb) { uint32_t cdb_phyaddr, cdb_phyaddr_hi32; - dma_addr_t dma_coherent_handle; + /* ******************************************************************** ** here we need to tell iop 331 our freeccb.HighPart ** if freeccb.HighPart is not zero ******************************************************************** */ - dma_coherent_handle = acb->dma_coherent_handle; - cdb_phyaddr = (uint32_t)(dma_coherent_handle); - cdb_phyaddr_hi32 = (uint32_t)((cdb_phyaddr >> 16) >> 16); + cdb_phyaddr = lower_32_bits(acb->dma_coherent_handle); + cdb_phyaddr_hi32 = upper_32_bits(acb->dma_coherent_handle); acb->cdb_phyaddr_hi32 = cdb_phyaddr_hi32; /* *********************************************************************** diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index b2fcac78feaa..5bb9406688c9 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -897,17 +897,20 @@ mgmt_static_ip_modify(struct beiscsi_hba *phba, if (ip_action == IP_ACTION_ADD) { memcpy(req->ip_params.ip_record.ip_addr.addr, ip_param->value, - ip_param->len); + sizeof(req->ip_params.ip_record.ip_addr.addr)); if (subnet_param) memcpy(req->ip_params.ip_record.ip_addr.subnet_mask, - subnet_param->value, subnet_param->len); + subnet_param->value, + sizeof(req->ip_params.ip_record.ip_addr.subnet_mask)); } else { memcpy(req->ip_params.ip_record.ip_addr.addr, - if_info->ip_addr.addr, ip_param->len); + if_info->ip_addr.addr, + sizeof(req->ip_params.ip_record.ip_addr.addr)); memcpy(req->ip_params.ip_record.ip_addr.subnet_mask, - if_info->ip_addr.subnet_mask, ip_param->len); + if_info->ip_addr.subnet_mask, + sizeof(req->ip_params.ip_record.ip_addr.subnet_mask)); } rc = mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0); @@ -935,7 +938,7 @@ static int mgmt_modify_gateway(struct beiscsi_hba *phba, uint8_t *gt_addr, req->action = gtway_action; req->ip_addr.ip_type = BE2_IPV4; - memcpy(req->ip_addr.addr, gt_addr, param_len); + memcpy(req->ip_addr.addr, gt_addr, sizeof(req->ip_addr.addr)); return mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0); } diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h index 2e28392c2fb6..a38aafa030b3 100644 --- a/drivers/scsi/bfa/bfa_ioc.h +++ b/drivers/scsi/bfa/bfa_ioc.h @@ -72,7 +72,7 @@ struct bfa_sge_s { } while (0) #define bfa_swap_words(_x) ( \ - ((_x) << 32) | ((_x) >> 32)) + ((u64)(_x) << 32) | ((u64)(_x) >> 32)) #ifdef __BIG_ENDIAN #define bfa_sge_to_be(_x) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 868318a7067c..528bff5ec91f 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -3131,7 +3131,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp) } if (ioc->Request.Type.Direction == XFER_WRITE) { if (copy_from_user(buff[sg_used], data_ptr, sz)) { - status = -ENOMEM; + status = -EFAULT; goto cleanup1; } } else @@ -4367,9 +4367,9 @@ static inline void hpsa_set_driver_support_bits(struct ctlr_info *h) { u32 driver_support; -#ifdef CONFIG_X86 - /* Need to enable prefetch in the SCSI core for 6400 in x86 */ driver_support = readl(&(h->cfgtable->driver_support)); + /* Need to enable prefetch in the SCSI core for 6400 in x86 */ +#ifdef CONFIG_X86 driver_support |= ENABLE_SCSI_PREFETCH; #endif driver_support |= ENABLE_UNIT_ATTN; diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index fa764406df68..c5bb0e0a36b9 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -185,6 +185,11 @@ static struct viosrp_crq *crq_queue_next_crq(struct crq_queue *queue) if (crq->valid & 0x80) { if (++queue->cur == queue->size) queue->cur = 0; + + /* Ensure the read of the valid bit occurs before reading any + * other bits of the CRQ entry + */ + rmb(); } else crq = NULL; spin_unlock_irqrestore(&queue->lock, flags); @@ -203,6 +208,11 @@ static int ibmvscsi_send_crq(struct ibmvscsi_host_data *hostdata, { struct vio_dev *vdev = to_vio_dev(hostdata->dev); + /* + * Ensure the command buffer is flushed to memory before handing it + * over to the VIOS to prevent it from fetching any stale data. + */ + mb(); return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2); } @@ -797,7 +807,8 @@ static void purge_requests(struct ibmvscsi_host_data *hostdata, int error_code) evt->hostdata->dev); if (evt->cmnd_done) evt->cmnd_done(evt->cmnd); - } else if (evt->done) + } else if (evt->done && evt->crq.format != VIOSRP_MAD_FORMAT && + evt->iu.srp.login_req.opcode != SRP_LOGIN_REQ) evt->done(evt); free_event_struct(&evt->hostdata->pool, evt); spin_lock_irqsave(hostdata->host->host_lock, flags); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 40462415291e..454998669c2a 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -717,11 +717,21 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, return NULL; } + if (data_size > ISCSI_DEF_MAX_RECV_SEG_LEN) { + iscsi_conn_printk(KERN_ERR, conn, "Invalid buffer len of %u for login task. Max len is %u\n", data_size, ISCSI_DEF_MAX_RECV_SEG_LEN); + return NULL; + } + task = conn->login_task; } else { if (session->state != ISCSI_STATE_LOGGED_IN) return NULL; + if (data_size != 0) { + iscsi_conn_printk(KERN_ERR, conn, "Can not send data buffer of len %u for op 0x%x\n", data_size, opcode); + return NULL; + } + BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE); BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED); diff --git a/drivers/scsi/megaraid/megaraid_mm.c b/drivers/scsi/megaraid/megaraid_mm.c index dfffd0f37916..a70692779a16 100644 --- a/drivers/scsi/megaraid/megaraid_mm.c +++ b/drivers/scsi/megaraid/megaraid_mm.c @@ -486,6 +486,8 @@ mimd_to_kioc(mimd_t __user *umimd, mraid_mmadp_t *adp, uioc_t *kioc) pthru32->dataxferaddr = kioc->buf_paddr; if (kioc->data_dir & UIOC_WR) { + if (pthru32->dataxferlen > kioc->xferlen) + return -EINVAL; if (copy_from_user(kioc->buf_vaddr, kioc->user_data, pthru32->dataxferlen)) { return (-EFAULT); diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index 7f0af4fcc001..6fd7d40b2c4d 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -8293,7 +8293,6 @@ _scsih_suspend(struct pci_dev *pdev, pm_message_t state) mpt2sas_base_free_resources(ioc); pci_save_state(pdev); - pci_disable_device(pdev); pci_set_power_state(pdev, device_state); return 0; } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 89a53002b585..23c1b0cd3074 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2536,7 +2536,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) ha->flags.enable_64bit_addressing ? "enable" : "disable"); ret = qla2x00_mem_alloc(ha, req_length, rsp_length, &req, &rsp); - if (!ret) { + if (ret) { ql_log_pci(ql_log_fatal, pdev, 0x0031, "Failed to allocate memory for adapter, aborting.\n"); @@ -3039,10 +3039,8 @@ qla2x00_unmap_iobases(struct qla_hw_data *ha) } static void -qla2x00_clear_drv_active(scsi_qla_host_t *vha) +qla2x00_clear_drv_active(struct qla_hw_data *ha) { - struct qla_hw_data *ha = vha->hw; - if (IS_QLA8044(ha)) { qla8044_idc_lock(ha); qla8044_clear_drv_active(ha); @@ -3111,7 +3109,7 @@ qla2x00_remove_one(struct pci_dev *pdev) scsi_host_put(base_vha->host); - qla2x00_clear_drv_active(base_vha); + qla2x00_clear_drv_active(ha); qla2x00_unmap_iobases(ha); @@ -3478,10 +3476,10 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, else { qla2x00_set_reserved_loop_ids(ha); ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0123, - "loop_id_map=%p. \n", ha->loop_id_map); + "loop_id_map=%p.\n", ha->loop_id_map); } - return 1; + return 0; fail_async_pd: dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0cb73074c199..2f264ac79546 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1382,12 +1382,10 @@ static inline void qlt_unmap_sg(struct scsi_qla_host *vha, static int qlt_check_reserve_free_req(struct scsi_qla_host *vha, uint32_t req_cnt) { - struct qla_hw_data *ha = vha->hw; - device_reg_t __iomem *reg = ha->iobase; uint32_t cnt; if (vha->req->cnt < (req_cnt + 2)) { - cnt = (uint16_t)RD_REG_DWORD(®->isp24.req_q_out); + cnt = (uint16_t)RD_REG_DWORD(vha->req->req_q_out); ql_dbg(ql_dbg_tgt, vha, 0xe00a, "Request ring circled: cnt=%d, vha->->ring_index=%d, " diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 788c4fe2b0c9..9d81f7693f99 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -707,7 +707,16 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess) pr_debug("fc_rport domain: port_id 0x%06x\n", nacl->nport_id); node = btree_remove32(&lport->lport_fcport_map, nacl->nport_id); - WARN_ON(node && (node != se_nacl)); + if (WARN_ON(node && (node != se_nacl))) { + /* + * The nacl no longer matches what we think it should be. + * Most likely a new dynamic acl has been added while + * someone dropped the hardware lock. It clearly is a + * bug elsewhere, but this bit can't make things worse. + */ + btree_insert32(&lport->lport_fcport_map, nacl->nport_id, + node, GFP_ATOMIC); + } pr_debug("Removed from fcport_map: %p for WWNN: 0x%016LX, port_id: 0x%06x\n", se_nacl, nacl->nport_wwnn, nacl->nport_id); diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index f969aca0b54e..49014a143c6a 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -222,6 +222,7 @@ static struct { {"PIONEER", "CD-ROM DRM-602X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"PIONEER", "CD-ROM DRM-604X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, + {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC}, {"Promise", "", NULL, BLIST_SPARSELUN}, {"QUANTUM", "XP34301", "1071", BLIST_NOTQ}, {"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN}, diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 78b004da2885..edb4d46fa874 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -131,7 +131,7 @@ scmd_eh_abort_handler(struct work_struct *work) "aborting command %p\n", scmd)); rtn = scsi_try_to_abort_cmd(sdev->host->hostt, scmd); if (rtn == SUCCESS) { - scmd->result |= DID_TIME_OUT << 16; + set_host_byte(scmd, DID_TIME_OUT); if (scsi_host_eh_past_deadline(sdev->host)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, @@ -167,7 +167,7 @@ scmd_eh_abort_handler(struct work_struct *work) scmd_printk(KERN_WARNING, scmd, "scmd %p terminate " "aborted command\n", scmd)); - scmd->result |= DID_TIME_OUT << 16; + set_host_byte(scmd, DID_TIME_OUT); scsi_finish_command(scmd); } } @@ -290,7 +290,7 @@ enum blk_eh_timer_return scsi_times_out(struct request *req) if (scsi_abort_command(scmd) == SUCCESS) return BLK_EH_NOT_HANDLED; - scmd->result |= DID_TIME_OUT << 16; + set_host_byte(scmd, DID_TIME_OUT); if (unlikely(rtn == BLK_EH_NOT_HANDLED && !scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD))) @@ -1157,6 +1157,15 @@ int scsi_eh_get_sense(struct list_head *work_q, __func__)); break; } + if (status_byte(scmd->result) != CHECK_CONDITION) + /* + * don't request sense if there's no check condition + * status because the error we're processing isn't one + * that has a sense code (and some devices get + * confused by sense requests out of the blue) + */ + continue; + SCSI_LOG_ERROR_RECOVERY(2, scmd_printk(KERN_INFO, scmd, "%s: requesting sense\n", current->comm)); @@ -1764,7 +1773,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) break; case DID_ABORT: if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { - scmd->result |= DID_TIME_OUT << 16; + set_host_byte(scmd, DID_TIME_OUT); return SUCCESS; } case DID_NO_CONNECT: diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 62ec84b42e31..64e487a8bf59 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -831,6 +831,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) scsi_next_command(cmd); return; } + } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) { + /* + * Certain non BLOCK_PC requests are commands that don't + * actually transfer anything (FLUSH), so cannot use + * good_bytes != blk_rq_bytes(req) as the signal for an error. + * This sets the error explicitly for the problem case. + */ + error = __scsi_error_from_host_byte(cmd, result); } /* no bidi support for !REQ_TYPE_BLOCK_PC yet */ diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c index fe30ea94ffe6..109802f776ed 100644 --- a/drivers/scsi/scsi_netlink.c +++ b/drivers/scsi/scsi_netlink.c @@ -77,7 +77,7 @@ scsi_nl_rcv_msg(struct sk_buff *skb) goto next_msg; } - if (!capable(CAP_SYS_ADMIN)) { + if (!netlink_capable(skb, CAP_SYS_ADMIN)) { err = -EPERM; goto next_msg; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 307a81137607..054ec2c412a4 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -320,6 +320,7 @@ static void scsi_target_destroy(struct scsi_target *starget) struct Scsi_Host *shost = dev_to_shost(dev->parent); unsigned long flags; + starget->state = STARGET_DEL; transport_destroy_device(dev); spin_lock_irqsave(shost->host_lock, flags); if (shost->hostt->target_destroy) @@ -371,6 +372,37 @@ static struct scsi_target *__scsi_find_target(struct device *parent, } /** + * scsi_target_reap_ref_release - remove target from visibility + * @kref: the reap_ref in the target being released + * + * Called on last put of reap_ref, which is the indication that no device + * under this target is visible anymore, so render the target invisible in + * sysfs. Note: we have to be in user context here because the target reaps + * should be done in places where the scsi device visibility is being removed. + */ +static void scsi_target_reap_ref_release(struct kref *kref) +{ + struct scsi_target *starget + = container_of(kref, struct scsi_target, reap_ref); + + /* + * if we get here and the target is still in the CREATED state that + * means it was allocated but never made visible (because a scan + * turned up no LUNs), so don't call device_del() on it. + */ + if (starget->state != STARGET_CREATED) { + transport_remove_device(&starget->dev); + device_del(&starget->dev); + } + scsi_target_destroy(starget); +} + +static void scsi_target_reap_ref_put(struct scsi_target *starget) +{ + kref_put(&starget->reap_ref, scsi_target_reap_ref_release); +} + +/** * scsi_alloc_target - allocate a new or find an existing target * @parent: parent of the target (need not be a scsi host) * @channel: target channel number (zero if no channels) @@ -392,7 +424,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent, + shost->transportt->target_size; struct scsi_target *starget; struct scsi_target *found_target; - int error; + int error, ref_got; starget = kzalloc(size, GFP_KERNEL); if (!starget) { @@ -401,7 +433,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent, } dev = &starget->dev; device_initialize(dev); - starget->reap_ref = 1; + kref_init(&starget->reap_ref); dev->parent = get_device(parent); dev_set_name(dev, "target%d:%d:%d", shost->host_no, channel, id); dev->bus = &scsi_bus_type; @@ -441,29 +473,36 @@ static struct scsi_target *scsi_alloc_target(struct device *parent, return starget; found: - found_target->reap_ref++; + /* + * release routine already fired if kref is zero, so if we can still + * take the reference, the target must be alive. If we can't, it must + * be dying and we need to wait for a new target + */ + ref_got = kref_get_unless_zero(&found_target->reap_ref); + spin_unlock_irqrestore(shost->host_lock, flags); - if (found_target->state != STARGET_DEL) { + if (ref_got) { put_device(dev); return found_target; } - /* Unfortunately, we found a dying target; need to - * wait until it's dead before we can get a new one */ + /* + * Unfortunately, we found a dying target; need to wait until it's + * dead before we can get a new one. There is an anomaly here. We + * *should* call scsi_target_reap() to balance the kref_get() of the + * reap_ref above. However, since the target being released, it's + * already invisible and the reap_ref is irrelevant. If we call + * scsi_target_reap() we might spuriously do another device_del() on + * an already invisible target. + */ put_device(&found_target->dev); - flush_scheduled_work(); + /* + * length of time is irrelevant here, we just want to yield the CPU + * for a tick to avoid busy waiting for the target to die. + */ + msleep(1); goto retry; } -static void scsi_target_reap_usercontext(struct work_struct *work) -{ - struct scsi_target *starget = - container_of(work, struct scsi_target, ew.work); - - transport_remove_device(&starget->dev); - device_del(&starget->dev); - scsi_target_destroy(starget); -} - /** * scsi_target_reap - check to see if target is in use and destroy if not * @starget: target to be checked @@ -474,28 +513,13 @@ static void scsi_target_reap_usercontext(struct work_struct *work) */ void scsi_target_reap(struct scsi_target *starget) { - struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); - unsigned long flags; - enum scsi_target_state state; - int empty = 0; - - spin_lock_irqsave(shost->host_lock, flags); - state = starget->state; - if (--starget->reap_ref == 0 && list_empty(&starget->devices)) { - empty = 1; - starget->state = STARGET_DEL; - } - spin_unlock_irqrestore(shost->host_lock, flags); - - if (!empty) - return; - - BUG_ON(state == STARGET_DEL); - if (state == STARGET_CREATED) - scsi_target_destroy(starget); - else - execute_in_process_context(scsi_target_reap_usercontext, - &starget->ew); + /* + * serious problem if this triggers: STARGET_DEL is only set in the if + * the reap_ref drops to zero, so we're trying to do another final put + * on an already released kref + */ + BUG_ON(starget->state == STARGET_DEL); + scsi_target_reap_ref_put(starget); } /** @@ -898,6 +922,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, if (*bflags & BLIST_USE_10_BYTE_MS) sdev->use_10_for_ms = 1; + /* some devices don't like REPORT SUPPORTED OPERATION CODES + * and will simply timeout causing sd_mod init to take a very + * very long time */ + if (*bflags & BLIST_NO_RSOC) + sdev->no_report_opcodes = 1; + /* set the device running here so that slave configure * may do I/O */ ret = scsi_device_set_state(sdev, SDEV_RUNNING); @@ -926,7 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT; - if (*bflags & BLIST_SKIP_VPD_PAGES) + if (*bflags & BLIST_TRY_VPD_PAGES) + sdev->try_vpd_pages = 1; + else if (*bflags & BLIST_SKIP_VPD_PAGES) sdev->skip_vpd_pages = 1; transport_configure_device(&sdev->sdev_gendev); @@ -1212,6 +1244,12 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget, max_dev_lun = min(8U, max_dev_lun); /* + * Stop scanning at 255 unless BLIST_SCSI3LUN + */ + if (!(bflags & BLIST_SCSI3LUN)) + max_dev_lun = min(256U, max_dev_lun); + + /* * We have already scanned LUN 0, so start at LUN 1. Keep scanning * until we reach the max, or no LUN is found and we are not * sparse_lun. @@ -1532,6 +1570,10 @@ struct scsi_device *__scsi_add_device(struct Scsi_Host *shost, uint channel, } mutex_unlock(&shost->scan_mutex); scsi_autopm_put_target(starget); + /* + * paired with scsi_alloc_target(). Target will be destroyed unless + * scsi_probe_and_add_lun made an underlying device visible + */ scsi_target_reap(starget); put_device(&starget->dev); @@ -1612,8 +1654,10 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel, out_reap: scsi_autopm_put_target(starget); - /* now determine if the target has any children at all - * and if not, nuke it */ + /* + * paired with scsi_alloc_target(): determine if the target has + * any children at all and if not, nuke it + */ scsi_target_reap(starget); put_device(&starget->dev); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 9117d0bf408e..665acbf83693 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -383,17 +383,14 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) { struct scsi_device *sdev; struct device *parent; - struct scsi_target *starget; struct list_head *this, *tmp; unsigned long flags; sdev = container_of(work, struct scsi_device, ew.work); parent = sdev->sdev_gendev.parent; - starget = to_scsi_target(parent); spin_lock_irqsave(sdev->host->host_lock, flags); - starget->reap_ref++; list_del(&sdev->siblings); list_del(&sdev->same_target_siblings); list_del(&sdev->starved_entry); @@ -413,8 +410,6 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) /* NULL queue means the device can't be used */ sdev->request_queue = NULL; - scsi_target_reap(scsi_target(sdev)); - kfree(sdev->inquiry); kfree(sdev); @@ -1071,6 +1066,13 @@ void __scsi_remove_device(struct scsi_device *sdev) sdev->host->hostt->slave_destroy(sdev); transport_destroy_device(dev); + /* + * Paired with the kref_get() in scsi_sysfs_initialize(). We have + * remoed sysfs visibility from the device, so make the target + * invisible if this was the last device underneath it. + */ + scsi_target_reap(scsi_target(sdev)); + put_device(dev); } @@ -1133,7 +1135,7 @@ void scsi_remove_target(struct device *dev) continue; if (starget->dev.parent == dev || &starget->dev == dev) { /* assuming new targets arrive at the end */ - starget->reap_ref++; + kref_get(&starget->reap_ref); spin_unlock_irqrestore(shost->host_lock, flags); if (last) scsi_target_reap(last); @@ -1217,6 +1219,12 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev) list_add_tail(&sdev->same_target_siblings, &starget->devices); list_add_tail(&sdev->siblings, &shost->__devices); spin_unlock_irqrestore(shost->host_lock, flags); + /* + * device can now only be removed via __scsi_remove_device() so hold + * the target. Target will be held in CREATED state until something + * beneath it becomes visible (in which case it moves to RUNNING) + */ + kref_get(&starget->reap_ref); } int scsi_is_sdev_device(const struct device *dev) diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 1b681427dde0..c341f855fadc 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -1621,8 +1621,6 @@ void sas_rphy_free(struct sas_rphy *rphy) list_del(&rphy->list); mutex_unlock(&sas_host->lock); - sas_bsg_remove(shost, rphy); - transport_destroy_device(dev); put_device(dev); @@ -1681,6 +1679,7 @@ sas_rphy_remove(struct sas_rphy *rphy) } sas_rphy_unlink(rphy); + sas_bsg_remove(NULL, rphy); transport_remove_device(dev); device_del(dev); } diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index d47ffc8d3e43..e3e794ee7ddd 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -473,7 +473,8 @@ static void __srp_start_tl_fail_timers(struct srp_rport *rport) if (delay > 0) queue_delayed_work(system_long_wq, &rport->reconnect_work, 1UL * delay * HZ); - if (srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) { + if ((fast_io_fail_tmo >= 0 || dev_loss_tmo >= 0) && + srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) { pr_debug("%s new state: %d\n", dev_name(&shost->shost_gendev), rport->state); scsi_target_block(&shost->shost_gendev); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 470954aba728..e8abb731c7ec 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1463,8 +1463,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp) sd_print_sense_hdr(sdkp, &sshdr); /* we need to evaluate the error return */ if (scsi_sense_valid(&sshdr) && - /* 0x3a is medium not present */ - sshdr.asc == 0x3a) + (sshdr.asc == 0x3a || /* medium not present */ + sshdr.asc == 0x20)) /* invalid command */ /* this is no error here */ return 0; @@ -2686,6 +2686,11 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) static int sd_try_extended_inquiry(struct scsi_device *sdp) { + /* Attempt VPD inquiry if the device blacklist explicitly calls + * for it. + */ + if (sdp->try_vpd_pages) + return 1; /* * Although VPD inquiries can go to SCSI-2 type devices, * some USB ones crash on receiving them, and the pages diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 9969fa1ef7c4..ed0f899e8aa5 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -33,6 +33,7 @@ #include <linux/device.h> #include <linux/hyperv.h> #include <linux/mempool.h> +#include <linux/blkdev.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_host.h> @@ -330,17 +331,17 @@ static int storvsc_timeout = 180; static void storvsc_on_channel_callback(void *context); -/* - * In Hyper-V, each port/path/target maps to 1 scsi host adapter. In - * reality, the path/target is not used (ie always set to 0) so our - * scsi host adapter essentially has 1 bus with 1 target that contains - * up to 256 luns. - */ -#define STORVSC_MAX_LUNS_PER_TARGET 64 -#define STORVSC_MAX_TARGETS 1 -#define STORVSC_MAX_CHANNELS 1 +#define STORVSC_MAX_LUNS_PER_TARGET 255 +#define STORVSC_MAX_TARGETS 2 +#define STORVSC_MAX_CHANNELS 8 +#define STORVSC_FC_MAX_LUNS_PER_TARGET 255 +#define STORVSC_FC_MAX_TARGETS 128 +#define STORVSC_FC_MAX_CHANNELS 8 +#define STORVSC_IDE_MAX_LUNS_PER_TARGET 64 +#define STORVSC_IDE_MAX_TARGETS 1 +#define STORVSC_IDE_MAX_CHANNELS 1 struct storvsc_cmd_request { struct list_head entry; @@ -1017,6 +1018,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, case ATA_12: set_host_byte(scmnd, DID_PASSTHROUGH); break; + /* + * On Some Windows hosts TEST_UNIT_READY command can return + * SRB_STATUS_ERROR, let the upper level code deal with it + * based on the sense information. + */ + case TEST_UNIT_READY: + break; default: set_host_byte(scmnd, DID_TARGET_FAILURE); } @@ -1518,6 +1526,16 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) return SUCCESS; } +/* + * The host guarantees to respond to each command, although I/O latencies might + * be unbounded on Azure. Reset the timer unconditionally to give the host a + * chance to perform EH. + */ +static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd) +{ + return BLK_EH_RESET_TIMER; +} + static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd) { bool allowed = true; @@ -1553,9 +1571,19 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) struct vmscsi_request *vm_srb; struct stor_mem_pools *memp = scmnd->device->hostdata; - if (!storvsc_scsi_cmd_ok(scmnd)) { - scmnd->scsi_done(scmnd); - return 0; + if (vmstor_current_major <= VMSTOR_WIN8_MAJOR) { + /* + * On legacy hosts filter unimplemented commands. + * Future hosts are expected to correctly handle + * unsupported commands. Furthermore, it is + * possible that some of the currently + * unsupported commands maybe supported in + * future versions of the host. + */ + if (!storvsc_scsi_cmd_ok(scmnd)) { + scmnd->scsi_done(scmnd); + return 0; + } } request_size = sizeof(struct storvsc_cmd_request); @@ -1580,26 +1608,24 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) vm_srb = &cmd_request->vstor_packet.vm_srb; vm_srb->win8_extension.time_out_value = 60; + vm_srb->win8_extension.srb_flags |= + (SRB_FLAGS_QUEUE_ACTION_ENABLE | + SRB_FLAGS_DISABLE_SYNCH_TRANSFER); /* Build the SRB */ switch (scmnd->sc_data_direction) { case DMA_TO_DEVICE: vm_srb->data_in = WRITE_TYPE; vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_OUT; - vm_srb->win8_extension.srb_flags |= - (SRB_FLAGS_QUEUE_ACTION_ENABLE | - SRB_FLAGS_DISABLE_SYNCH_TRANSFER); break; case DMA_FROM_DEVICE: vm_srb->data_in = READ_TYPE; vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_IN; - vm_srb->win8_extension.srb_flags |= - (SRB_FLAGS_QUEUE_ACTION_ENABLE | - SRB_FLAGS_DISABLE_SYNCH_TRANSFER); break; default: vm_srb->data_in = UNKNOWN_TYPE; - vm_srb->win8_extension.srb_flags = 0; + vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN | + SRB_FLAGS_DATA_OUT); break; } @@ -1687,11 +1713,11 @@ static struct scsi_host_template scsi_driver = { .bios_param = storvsc_get_chs, .queuecommand = storvsc_queuecommand, .eh_host_reset_handler = storvsc_host_reset_handler, + .eh_timed_out = storvsc_eh_timed_out, .slave_alloc = storvsc_device_alloc, .slave_destroy = storvsc_device_destroy, .slave_configure = storvsc_device_configure, - .cmd_per_lun = 1, - /* 64 max_queue * 1 target */ + .cmd_per_lun = 255, .can_queue = STORVSC_MAX_IO_REQUESTS*STORVSC_MAX_TARGETS, .this_id = -1, /* no use setting to 0 since ll_blk_rw reset it to 1 */ @@ -1743,19 +1769,25 @@ static int storvsc_probe(struct hv_device *device, * set state to properly communicate with the host. */ - if (vmbus_proto_version == VERSION_WIN8) { - sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE; - vmscsi_size_delta = 0; - vmstor_current_major = VMSTOR_WIN8_MAJOR; - vmstor_current_minor = VMSTOR_WIN8_MINOR; - } else { + switch (vmbus_proto_version) { + case VERSION_WS2008: + case VERSION_WIN7: sense_buffer_size = PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE; vmscsi_size_delta = sizeof(struct vmscsi_win8_extension); vmstor_current_major = VMSTOR_WIN7_MAJOR; vmstor_current_minor = VMSTOR_WIN7_MINOR; + break; + default: + sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE; + vmscsi_size_delta = 0; + vmstor_current_major = VMSTOR_WIN8_MAJOR; + vmstor_current_minor = VMSTOR_WIN8_MINOR; + break; } - + if (dev_id->driver_data == SFC_GUID) + scsi_driver.can_queue = (STORVSC_MAX_IO_REQUESTS * + STORVSC_FC_MAX_TARGETS); host = scsi_host_alloc(&scsi_driver, sizeof(struct hv_host_device)); if (!host) @@ -1789,12 +1821,25 @@ static int storvsc_probe(struct hv_device *device, host_dev->path = stor_device->path_id; host_dev->target = stor_device->target_id; - /* max # of devices per target */ - host->max_lun = STORVSC_MAX_LUNS_PER_TARGET; - /* max # of targets per channel */ - host->max_id = STORVSC_MAX_TARGETS; - /* max # of channels */ - host->max_channel = STORVSC_MAX_CHANNELS - 1; + switch (dev_id->driver_data) { + case SFC_GUID: + host->max_lun = STORVSC_FC_MAX_LUNS_PER_TARGET; + host->max_id = STORVSC_FC_MAX_TARGETS; + host->max_channel = STORVSC_FC_MAX_CHANNELS - 1; + break; + + case SCSI_GUID: + host->max_lun = STORVSC_MAX_LUNS_PER_TARGET; + host->max_id = STORVSC_MAX_TARGETS; + host->max_channel = STORVSC_MAX_CHANNELS - 1; + break; + + default: + host->max_lun = STORVSC_IDE_MAX_LUNS_PER_TARGET; + host->max_id = STORVSC_IDE_MAX_TARGETS; + host->max_channel = STORVSC_IDE_MAX_CHANNELS - 1; + break; + } /* max cmd length */ host->max_cmd_len = STORVSC_MAX_CMD_LEN; diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c index d92fe4037e94..6b349e301869 100644 --- a/drivers/scsi/sym53c8xx_2/sym_hipd.c +++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c @@ -3000,7 +3000,11 @@ sym_dequeue_from_squeue(struct sym_hcb *np, int i, int target, int lun, int task if ((target == -1 || cp->target == target) && (lun == -1 || cp->lun == lun) && (task == -1 || cp->tag == task)) { +#ifdef SYM_OPT_HANDLE_DEVICE_QUEUEING sym_set_cam_status(cp->cmd, DID_SOFT_ERROR); +#else + sym_set_cam_status(cp->cmd, DID_REQUEUE); +#endif sym_remque(&cp->link_ccbq); sym_insque_tail(&cp->link_ccbq, &np->comp_ccbq); } diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 16bfd50cd3fe..8490aa411739 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -273,6 +273,16 @@ static void virtscsi_req_done(struct virtqueue *vq) virtscsi_vq_done(vscsi, req_vq, virtscsi_complete_cmd); }; +static void virtscsi_poll_requests(struct virtio_scsi *vscsi) +{ + int i, num_vqs; + + num_vqs = vscsi->num_queues; + for (i = 0; i < num_vqs; i++) + virtscsi_vq_done(vscsi, &vscsi->req_vqs[i], + virtscsi_complete_cmd); +} + static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf) { struct virtio_scsi_cmd *cmd = buf; @@ -291,6 +301,8 @@ static void virtscsi_ctrl_done(struct virtqueue *vq) virtscsi_vq_done(vscsi, &vscsi->ctrl_vq, virtscsi_complete_free); }; +static void virtscsi_handle_event(struct work_struct *work); + static int virtscsi_kick_event(struct virtio_scsi *vscsi, struct virtio_scsi_event_node *event_node) { @@ -298,6 +310,7 @@ static int virtscsi_kick_event(struct virtio_scsi *vscsi, struct scatterlist sg; unsigned long flags; + INIT_WORK(&event_node->work, virtscsi_handle_event); sg_init_one(&sg, &event_node->event, sizeof(struct virtio_scsi_event)); spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags); @@ -415,7 +428,6 @@ static void virtscsi_complete_event(struct virtio_scsi *vscsi, void *buf) { struct virtio_scsi_event_node *event_node = buf; - INIT_WORK(&event_node->work, virtscsi_handle_event); schedule_work(&event_node->work); } @@ -605,6 +617,18 @@ static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd) cmd->resp.tmf.response == VIRTIO_SCSI_S_FUNCTION_SUCCEEDED) ret = SUCCESS; + /* + * The spec guarantees that all requests related to the TMF have + * been completed, but the callback might not have run yet if + * we're using independent interrupts (e.g. MSI). Poll the + * virtqueues once. + * + * In the abort case, sc->scsi_done will do nothing, because + * the block layer must have detected a timeout and as a result + * REQ_ATOM_COMPLETE has been set. + */ + virtscsi_poll_requests(vscsi); + out: mempool_free(cmd, virtscsi_cmd_pool); return ret; @@ -750,8 +774,12 @@ static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity) vscsi->affinity_hint_set = true; } else { - for (i = 0; i < vscsi->num_queues; i++) + for (i = 0; i < vscsi->num_queues; i++) { + if (!vscsi->req_vqs[i].vq) + continue; + virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1); + } vscsi->affinity_hint_set = false; } diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index 6d207afec8cb..a4c45ea8f688 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -89,7 +89,13 @@ err_exit: static void mid_spi_dma_exit(struct dw_spi *dws) { + if (!dws->dma_inited) + return; + + dmaengine_terminate_all(dws->txchan); dma_release_channel(dws->txchan); + + dmaengine_terminate_all(dws->rxchan); dma_release_channel(dws->rxchan); } @@ -136,7 +142,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change) txconf.dst_addr = dws->dma_addr; txconf.dst_maxburst = LNW_DMA_MSIZE_16; txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + txconf.dst_addr_width = dws->dma_width; txconf.device_fc = false; txchan->device->device_control(txchan, DMA_SLAVE_CONFIG, @@ -159,7 +165,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change) rxconf.src_addr = dws->dma_addr; rxconf.src_maxburst = LNW_DMA_MSIZE_16; rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + rxconf.src_addr_width = dws->dma_width; rxconf.device_fc = false; rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG, diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c index 3f3dc1226edf..e14960470d8d 100644 --- a/drivers/spi/spi-dw-pci.c +++ b/drivers/spi/spi-dw-pci.c @@ -62,6 +62,8 @@ static int spi_pci_probe(struct pci_dev *pdev, if (ret) return ret; + dws->regs = pcim_iomap_table(pdev)[pci_bar]; + dws->bus_num = 0; dws->num_cs = 4; dws->irq = pdev->irq; diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index bf98d63d92b3..e63d27013142 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -671,12 +671,6 @@ static int dw_spi_setup(struct spi_device *spi) return 0; } -static void dw_spi_cleanup(struct spi_device *spi) -{ - struct chip_data *chip = spi_get_ctldata(spi); - kfree(chip); -} - static int init_queue(struct dw_spi *dws) { INIT_LIST_HEAD(&dws->queue); @@ -806,7 +800,6 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws) master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16); master->bus_num = dws->bus_num; master->num_chipselect = dws->num_cs; - master->cleanup = dw_spi_cleanup; master->setup = dw_spi_setup; master->transfer = dw_spi_transfer; diff --git a/drivers/spi/spi-efm32.c b/drivers/spi/spi-efm32.c index d4d3cc534792..8933eb7ab79b 100644 --- a/drivers/spi/spi-efm32.c +++ b/drivers/spi/spi-efm32.c @@ -487,6 +487,9 @@ static int efm32_spi_remove(struct platform_device *pdev) static const struct of_device_id efm32_spi_dt_ids[] = { { + .compatible = "energymicro,efm32-spi", + }, { + /* doesn't follow the "vendor,device" scheme, don't use */ .compatible = "efm32,spi", }, { /* sentinel */ diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index a25392065d9b..a5db6f930fa3 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -45,7 +45,7 @@ #define SPI_TCR 0x08 -#define SPI_CTAR(x) (0x0c + (x * 4)) +#define SPI_CTAR(x) (0x0c + (((x) & 0x3) * 4)) #define SPI_CTAR_FMSZ(x) (((x) & 0x0000000f) << 27) #define SPI_CTAR_CPOL(x) ((x) << 26) #define SPI_CTAR_CPHA(x) ((x) << 25) @@ -69,7 +69,7 @@ #define SPI_PUSHR 0x34 #define SPI_PUSHR_CONT (1 << 31) -#define SPI_PUSHR_CTAS(x) (((x) & 0x00000007) << 28) +#define SPI_PUSHR_CTAS(x) (((x) & 0x00000003) << 28) #define SPI_PUSHR_EOQ (1 << 27) #define SPI_PUSHR_CTCNT (1 << 26) #define SPI_PUSHR_PCS(x) (((1 << x) & 0x0000003f) << 16) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index a72127f08e39..b0059e7552b0 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -147,6 +147,7 @@ struct omap2_mcspi_cs { void __iomem *base; unsigned long phys; int word_len; + u16 mode; struct list_head node; /* Context save and restore shadow register */ u32 chconf0; @@ -320,7 +321,8 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi, disable_fifo: if (t->rx_buf != NULL) chconf &= ~OMAP2_MCSPI_CHCONF_FFER; - else + + if (t->tx_buf != NULL) chconf &= ~OMAP2_MCSPI_CHCONF_FFET; mcspi_write_chconf0(spi, chconf); @@ -899,6 +901,8 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi, mcspi_write_chconf0(spi, l); + cs->mode = spi->mode; + dev_dbg(&spi->dev, "setup: speed %d, sample %s edge, clk %s\n", OMAP2_MCSPI_MAX_FREQ >> div, (spi->mode & SPI_CPHA) ? "trailing" : "leading", @@ -971,6 +975,7 @@ static int omap2_mcspi_setup(struct spi_device *spi) return -ENOMEM; cs->base = mcspi->base + spi->chip_select * 0x14; cs->phys = mcspi->phys + spi->chip_select * 0x14; + cs->mode = 0; cs->chconf0 = 0; spi->controller_state = cs; /* Link this to context save list */ @@ -1051,6 +1056,16 @@ static void omap2_mcspi_work(struct omap2_mcspi *mcspi, struct spi_message *m) cs = spi->controller_state; cd = spi->controller_data; + /* + * The slave driver could have changed spi->mode in which case + * it will be different from cs->mode (the current hardware setup). + * If so, set par_override (even though its not a parity issue) so + * omap2_mcspi_setup_transfer will be called to configure the hardware + * with the correct mode on the first iteration of the loop below. + */ + if (spi->mode != cs->mode) + par_override = 1; + omap2_mcspi_set_enable(spi, 0); list_for_each_entry(t, &m->transfers, transfer_list) { if (t->tx_buf == NULL && t->rx_buf == NULL && t->len) { diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index 7f2121fe2622..977b0619bb78 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -404,8 +404,6 @@ static int orion_spi_probe(struct platform_device *pdev) struct resource *r; unsigned long tclk_hz; int status = 0; - const u32 *iprop; - int size; master = spi_alloc_master(&pdev->dev, sizeof(*spi)); if (master == NULL) { @@ -416,10 +414,10 @@ static int orion_spi_probe(struct platform_device *pdev) if (pdev->id != -1) master->bus_num = pdev->id; if (pdev->dev.of_node) { - iprop = of_get_property(pdev->dev.of_node, "cell-index", - &size); - if (iprop && size == sizeof(*iprop)) - master->bus_num = *iprop; + u32 cell_index; + if (!of_property_read_u32(pdev->dev.of_node, "cell-index", + &cell_index)) + master->bus_num = cell_index; } /* we support only mode 0, and no options */ diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c index 2789b452e711..971855e859c7 100644 --- a/drivers/spi/spi-pl022.c +++ b/drivers/spi/spi-pl022.c @@ -1075,7 +1075,7 @@ err_rxdesc: pl022->sgt_tx.nents, DMA_TO_DEVICE); err_tx_sgmap: dma_unmap_sg(rxchan->device->dev, pl022->sgt_rx.sgl, - pl022->sgt_tx.nents, DMA_FROM_DEVICE); + pl022->sgt_rx.nents, DMA_FROM_DEVICE); err_rx_sgmap: sg_free_table(&pl022->sgt_tx); err_alloc_tx_sg: diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index c702fc536a77..7ab3ccb592eb 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1078,6 +1078,7 @@ static struct acpi_device_id pxa2xx_spi_acpi_match[] = { { "INT3430", 0 }, { "INT3431", 0 }, { "80860F0E", 0 }, + { "8086228E", 0 }, { }, }; MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match); @@ -1279,7 +1280,9 @@ static int pxa2xx_spi_suspend(struct device *dev) if (status != 0) return status; write_SSCR0(0, drv_data->ioaddr); - clk_disable_unprepare(ssp->clk); + + if (!pm_runtime_suspended(dev)) + clk_disable_unprepare(ssp->clk); return 0; } @@ -1293,7 +1296,8 @@ static int pxa2xx_spi_resume(struct device *dev) pxa2xx_spi_dma_resume(drv_data); /* Enable the SSP clock */ - clk_prepare_enable(ssp->clk); + if (!pm_runtime_suspended(dev)) + clk_prepare_enable(ssp->clk); /* Restore LPSS private register bits */ lpss_ssp_setup(drv_data); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index d0b28bba38be..fbf3b22efe5a 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1568,7 +1568,7 @@ EXPORT_SYMBOL_GPL(spi_busnum_to_master); */ int spi_setup(struct spi_device *spi) { - unsigned bad_bits; + unsigned bad_bits, ugly_bits; int status = 0; /* check mode to prevent that DUAL and QUAD set at the same time @@ -1588,6 +1588,15 @@ int spi_setup(struct spi_device *spi) * that aren't supported with their current master */ bad_bits = spi->mode & ~spi->master->mode_bits; + ugly_bits = bad_bits & + (SPI_TX_DUAL | SPI_TX_QUAD | SPI_RX_DUAL | SPI_RX_QUAD); + if (ugly_bits) { + dev_warn(&spi->dev, + "setup: ignoring unsupported mode bits %x\n", + ugly_bits); + spi->mode &= ~ugly_bits; + bad_bits &= ~ugly_bits; + } if (bad_bits) { dev_err(&spi->dev, "setup: unsupported mode bits %x\n", bad_bits); diff --git a/drivers/staging/comedi/comedi_buf.c b/drivers/staging/comedi/comedi_buf.c index 924fce977985..257595016161 100644 --- a/drivers/staging/comedi/comedi_buf.c +++ b/drivers/staging/comedi/comedi_buf.c @@ -61,6 +61,8 @@ static void __comedi_buf_free(struct comedi_device *dev, struct comedi_subdevice *s) { struct comedi_async *async = s->async; + struct comedi_buf_map *bm; + unsigned long flags; if (async->prealloc_buf) { vunmap(async->prealloc_buf); @@ -68,8 +70,11 @@ static void __comedi_buf_free(struct comedi_device *dev, async->prealloc_bufsz = 0; } - comedi_buf_map_put(async->buf_map); + spin_lock_irqsave(&s->spin_lock, flags); + bm = async->buf_map; async->buf_map = NULL; + spin_unlock_irqrestore(&s->spin_lock, flags); + comedi_buf_map_put(bm); } static void __comedi_buf_alloc(struct comedi_device *dev, @@ -80,6 +85,7 @@ static void __comedi_buf_alloc(struct comedi_device *dev, struct page **pages = NULL; struct comedi_buf_map *bm; struct comedi_buf_page *buf; + unsigned long flags; unsigned i; if (!IS_ENABLED(CONFIG_HAS_DMA) && s->async_dma_dir != DMA_NONE) { @@ -92,8 +98,10 @@ static void __comedi_buf_alloc(struct comedi_device *dev, if (!bm) return; - async->buf_map = bm; kref_init(&bm->refcount); + spin_lock_irqsave(&s->spin_lock, flags); + async->buf_map = bm; + spin_unlock_irqrestore(&s->spin_lock, flags); bm->dma_dir = s->async_dma_dir; if (bm->dma_dir != DMA_NONE) /* Need ref to hardware device to free buffer later. */ @@ -127,7 +135,9 @@ static void __comedi_buf_alloc(struct comedi_device *dev, pages[i] = virt_to_page(buf->virt_addr); } + spin_lock_irqsave(&s->spin_lock, flags); bm->n_pages = i; + spin_unlock_irqrestore(&s->spin_lock, flags); /* vmap the prealloc_buf if all the pages were allocated */ if (i == n_pages) @@ -150,6 +160,29 @@ int comedi_buf_map_put(struct comedi_buf_map *bm) return 1; } +/* returns s->async->buf_map and increments its kref refcount */ +struct comedi_buf_map * +comedi_buf_map_from_subdev_get(struct comedi_subdevice *s) +{ + struct comedi_async *async = s->async; + struct comedi_buf_map *bm = NULL; + unsigned long flags; + + if (!async) + return NULL; + + spin_lock_irqsave(&s->spin_lock, flags); + bm = async->buf_map; + /* only want it if buffer pages allocated */ + if (bm && bm->n_pages) + comedi_buf_map_get(bm); + else + bm = NULL; + spin_unlock_irqrestore(&s->spin_lock, flags); + + return bm; +} + bool comedi_buf_is_mmapped(struct comedi_async *async) { struct comedi_buf_map *bm = async->buf_map; diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c index c22c617b0da1..eae3ee139330 100644 --- a/drivers/staging/comedi/comedi_fops.c +++ b/drivers/staging/comedi/comedi_fops.c @@ -1923,14 +1923,21 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma) struct comedi_device *dev = file->private_data; struct comedi_subdevice *s; struct comedi_async *async; - struct comedi_buf_map *bm; + struct comedi_buf_map *bm = NULL; unsigned long start = vma->vm_start; unsigned long size; int n_pages; int i; int retval; - mutex_lock(&dev->mutex); + /* + * 'trylock' avoids circular dependency with current->mm->mmap_sem + * and down-reading &dev->attach_lock should normally succeed without + * contention unless the device is in the process of being attached + * or detached. + */ + if (!down_read_trylock(&dev->attach_lock)) + return -EAGAIN; if (!dev->attached) { dev_dbg(dev->class_dev, "no driver attached\n"); @@ -1970,7 +1977,9 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma) } n_pages = size >> PAGE_SHIFT; - bm = async->buf_map; + + /* get reference to current buf map (if any) */ + bm = comedi_buf_map_from_subdev_get(s); if (!bm || n_pages > bm->n_pages) { retval = -EINVAL; goto done; @@ -1994,7 +2003,8 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma) retval = 0; done: - mutex_unlock(&dev->mutex); + up_read(&dev->attach_lock); + comedi_buf_map_put(bm); /* put reference to buf map - okay if NULL */ return retval; } diff --git a/drivers/staging/comedi/comedi_internal.h b/drivers/staging/comedi/comedi_internal.h index 9a746570f161..a492f2d2436e 100644 --- a/drivers/staging/comedi/comedi_internal.h +++ b/drivers/staging/comedi/comedi_internal.h @@ -19,6 +19,8 @@ void comedi_buf_reset(struct comedi_async *async); bool comedi_buf_is_mmapped(struct comedi_async *async); void comedi_buf_map_get(struct comedi_buf_map *bm); int comedi_buf_map_put(struct comedi_buf_map *bm); +struct comedi_buf_map *comedi_buf_map_from_subdev_get( + struct comedi_subdevice *s); unsigned int comedi_buf_write_n_allocated(struct comedi_async *async); void comedi_device_cancel_all(struct comedi_device *dev); diff --git a/drivers/staging/comedi/drivers/8255_pci.c b/drivers/staging/comedi/drivers/8255_pci.c index 8a57c3c1ade0..1097dc6a3086 100644 --- a/drivers/staging/comedi/drivers/8255_pci.c +++ b/drivers/staging/comedi/drivers/8255_pci.c @@ -56,6 +56,7 @@ Configuration Options: not applicable, uses PCI auto config #include "../comedidev.h" #include "8255.h" +#include "mite.h" enum pci_8255_boardid { BOARD_ADLINK_PCI7224, @@ -79,6 +80,7 @@ struct pci_8255_boardinfo { const char *name; int dio_badr; int n_8255; + unsigned int has_mite:1; }; static const struct pci_8255_boardinfo pci_8255_boards[] = { @@ -126,36 +128,43 @@ static const struct pci_8255_boardinfo pci_8255_boards[] = { .name = "ni_pci-dio-96", .dio_badr = 1, .n_8255 = 4, + .has_mite = 1, }, [BOARD_NI_PCIDIO96B] = { .name = "ni_pci-dio-96b", .dio_badr = 1, .n_8255 = 4, + .has_mite = 1, }, [BOARD_NI_PXI6508] = { .name = "ni_pxi-6508", .dio_badr = 1, .n_8255 = 4, + .has_mite = 1, }, [BOARD_NI_PCI6503] = { .name = "ni_pci-6503", .dio_badr = 1, .n_8255 = 1, + .has_mite = 1, }, [BOARD_NI_PCI6503B] = { .name = "ni_pci-6503b", .dio_badr = 1, .n_8255 = 1, + .has_mite = 1, }, [BOARD_NI_PCI6503X] = { .name = "ni_pci-6503x", .dio_badr = 1, .n_8255 = 1, + .has_mite = 1, }, [BOARD_NI_PXI_6503] = { .name = "ni_pxi-6503", .dio_badr = 1, .n_8255 = 1, + .has_mite = 1, }, }; @@ -163,6 +172,25 @@ struct pci_8255_private { void __iomem *mmio_base; }; +static int pci_8255_mite_init(struct pci_dev *pcidev) +{ + void __iomem *mite_base; + u32 main_phys_addr; + + /* ioremap the MITE registers (BAR 0) temporarily */ + mite_base = pci_ioremap_bar(pcidev, 0); + if (!mite_base) + return -ENOMEM; + + /* set data window to main registers (BAR 1) */ + main_phys_addr = pci_resource_start(pcidev, 1); + writel(main_phys_addr | WENAB, mite_base + MITE_IODWBSR); + + /* finished with MITE registers */ + iounmap(mite_base); + return 0; +} + static int pci_8255_mmio(int dir, int port, int data, unsigned long iobase) { void __iomem *mmio_base = (void __iomem *)iobase; @@ -201,6 +229,12 @@ static int pci_8255_auto_attach(struct comedi_device *dev, if (ret) return ret; + if (board->has_mite) { + ret = pci_8255_mite_init(pcidev); + if (ret) + return ret; + } + is_mmio = (pci_resource_flags(pcidev, board->dio_badr) & IORESOURCE_MEM) != 0; if (is_mmio) { diff --git a/drivers/staging/comedi/drivers/ni_daq_700.c b/drivers/staging/comedi/drivers/ni_daq_700.c index e4cdca349157..6417af0bdaab 100644 --- a/drivers/staging/comedi/drivers/ni_daq_700.c +++ b/drivers/staging/comedi/drivers/ni_daq_700.c @@ -122,6 +122,8 @@ static int daq700_ai_rinsn(struct comedi_device *dev, /* write channel to multiplexer */ /* set mask scan bit high to disable scanning */ outb(chan | 0x80, dev->iobase + CMD_R1); + /* mux needs 2us to really settle [Fred Brooks]. */ + udelay(2); /* convert n samples */ for (n = 0; n < insn->n; n++) { diff --git a/drivers/staging/comedi/drivers/usbdux.c b/drivers/staging/comedi/drivers/usbdux.c index 71db683098d6..b59af0303581 100644 --- a/drivers/staging/comedi/drivers/usbdux.c +++ b/drivers/staging/comedi/drivers/usbdux.c @@ -493,7 +493,7 @@ static void usbduxsub_ao_isoc_irq(struct urb *urb) /* pointer to the DA */ *datap++ = val & 0xff; *datap++ = (val >> 8) & 0xff; - *datap++ = chan; + *datap++ = chan << 6; devpriv->ao_readback[chan] = val; s->async->events |= COMEDI_CB_BLOCK; @@ -1040,11 +1040,8 @@ static int usbdux_ao_cmd(struct comedi_device *dev, struct comedi_subdevice *s) /* set current channel of the running acquisition to zero */ s->async->cur_chan = 0; - for (i = 0; i < cmd->chanlist_len; ++i) { - unsigned int chan = CR_CHAN(cmd->chanlist[i]); - - devpriv->ao_chanlist[i] = chan << 6; - } + for (i = 0; i < cmd->chanlist_len; ++i) + devpriv->ao_chanlist[i] = CR_CHAN(cmd->chanlist[i]); /* we count in steps of 1ms (125us) */ /* 125us mode not used yet */ diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c index e516bb69f3b4..907aa3078946 100644 --- a/drivers/staging/et131x/et131x.c +++ b/drivers/staging/et131x/et131x.c @@ -1422,22 +1422,16 @@ static int et131x_mii_read(struct et131x_adapter *adapter, u8 reg, u16 *value) * @reg: the register to read * @value: 16-bit value to write */ -static int et131x_mii_write(struct et131x_adapter *adapter, u8 reg, u16 value) +static int et131x_mii_write(struct et131x_adapter *adapter, u8 addr, u8 reg, + u16 value) { struct mac_regs __iomem *mac = &adapter->regs->mac; - struct phy_device *phydev = adapter->phydev; int status = 0; - u8 addr; u32 delay = 0; u32 mii_addr; u32 mii_cmd; u32 mii_indicator; - if (!phydev) - return -EIO; - - addr = phydev->addr; - /* Save a local copy of the registers we are dealing with so we can * set them back */ @@ -1632,17 +1626,7 @@ static int et131x_mdio_write(struct mii_bus *bus, int phy_addr, struct net_device *netdev = bus->priv; struct et131x_adapter *adapter = netdev_priv(netdev); - return et131x_mii_write(adapter, reg, value); -} - -static int et131x_mdio_reset(struct mii_bus *bus) -{ - struct net_device *netdev = bus->priv; - struct et131x_adapter *adapter = netdev_priv(netdev); - - et131x_mii_write(adapter, MII_BMCR, BMCR_RESET); - - return 0; + return et131x_mii_write(adapter, phy_addr, reg, value); } /* et1310_phy_power_switch - PHY power control @@ -1657,18 +1641,20 @@ static int et131x_mdio_reset(struct mii_bus *bus) static void et1310_phy_power_switch(struct et131x_adapter *adapter, bool down) { u16 data; + struct phy_device *phydev = adapter->phydev; et131x_mii_read(adapter, MII_BMCR, &data); data &= ~BMCR_PDOWN; if (down) data |= BMCR_PDOWN; - et131x_mii_write(adapter, MII_BMCR, data); + et131x_mii_write(adapter, phydev->addr, MII_BMCR, data); } /* et131x_xcvr_init - Init the phy if we are setting it into force mode */ static void et131x_xcvr_init(struct et131x_adapter *adapter) { u16 lcr2; + struct phy_device *phydev = adapter->phydev; /* Set the LED behavior such that LED 1 indicates speed (off = * 10Mbits, blink = 100Mbits, on = 1000Mbits) and LED 2 indicates @@ -1689,7 +1675,7 @@ static void et131x_xcvr_init(struct et131x_adapter *adapter) else lcr2 |= (LED_VAL_LINKON << LED_TXRX_SHIFT); - et131x_mii_write(adapter, PHY_LED_2, lcr2); + et131x_mii_write(adapter, phydev->addr, PHY_LED_2, lcr2); } } @@ -3638,14 +3624,14 @@ static void et131x_adjust_link(struct net_device *netdev) et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG, ®ister18); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18 | 0x4); - et131x_mii_write(adapter, PHY_INDEX_REG, + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18 | 0x4); + et131x_mii_write(adapter, phydev->addr, PHY_INDEX_REG, register18 | 0x8402); - et131x_mii_write(adapter, PHY_DATA_REG, + et131x_mii_write(adapter, phydev->addr, PHY_DATA_REG, register18 | 511); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18); + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18); } et1310_config_flow_control(adapter); @@ -3657,7 +3643,8 @@ static void et131x_adjust_link(struct net_device *netdev) et131x_mii_read(adapter, PHY_CONFIG, ®); reg &= ~ET_PHY_CONFIG_TX_FIFO_DEPTH; reg |= ET_PHY_CONFIG_FIFO_DEPTH_32; - et131x_mii_write(adapter, PHY_CONFIG, reg); + et131x_mii_write(adapter, phydev->addr, PHY_CONFIG, + reg); } et131x_set_rx_dma_timer(adapter); @@ -3670,14 +3657,14 @@ static void et131x_adjust_link(struct net_device *netdev) et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG, ®ister18); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18 | 0x4); - et131x_mii_write(adapter, PHY_INDEX_REG, - register18 | 0x8402); - et131x_mii_write(adapter, PHY_DATA_REG, - register18 | 511); - et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG, - register18); + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18 | 0x4); + et131x_mii_write(adapter, phydev->addr, + PHY_INDEX_REG, register18 | 0x8402); + et131x_mii_write(adapter, phydev->addr, + PHY_DATA_REG, register18 | 511); + et131x_mii_write(adapter, phydev->addr, + PHY_MPHY_CONTROL_REG, register18); } /* Free the packets being actively sent & stopped */ @@ -4646,10 +4633,6 @@ static int et131x_pci_setup(struct pci_dev *pdev, /* Copy address into the net_device struct */ memcpy(netdev->dev_addr, adapter->addr, ETH_ALEN); - /* Init variable for counting how long we do not have link status */ - adapter->boot_coma = 0; - et1310_disable_phy_coma(adapter); - rc = -ENOMEM; /* Setup the mii_bus struct */ @@ -4665,7 +4648,6 @@ static int et131x_pci_setup(struct pci_dev *pdev, adapter->mii_bus->priv = netdev; adapter->mii_bus->read = et131x_mdio_read; adapter->mii_bus->write = et131x_mdio_write; - adapter->mii_bus->reset = et131x_mdio_reset; adapter->mii_bus->irq = kmalloc_array(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL); if (!adapter->mii_bus->irq) @@ -4689,6 +4671,10 @@ static int et131x_pci_setup(struct pci_dev *pdev, /* Setup et1310 as per the documentation */ et131x_adapter_setup(adapter); + /* Init variable for counting how long we do not have link status */ + adapter->boot_coma = 0; + et1310_disable_phy_coma(adapter); + /* We can enable interrupts now * * NOTE - Because registration of interrupt handler is done in the diff --git a/drivers/staging/iio/adc/ad7291.c b/drivers/staging/iio/adc/ad7291.c index 357cef2a6f4c..7194bd138762 100644 --- a/drivers/staging/iio/adc/ad7291.c +++ b/drivers/staging/iio/adc/ad7291.c @@ -465,7 +465,7 @@ static int ad7291_probe(struct i2c_client *client, struct ad7291_platform_data *pdata = client->dev.platform_data; struct ad7291_chip_info *chip; struct iio_dev *indio_dev; - int ret = 0; + int ret; indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*chip)); if (!indio_dev) @@ -475,7 +475,7 @@ static int ad7291_probe(struct i2c_client *client, if (pdata && pdata->use_external_ref) { chip->reg = devm_regulator_get(&client->dev, "vref"); if (IS_ERR(chip->reg)) - return ret; + return PTR_ERR(chip->reg); ret = regulator_enable(chip->reg); if (ret) diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c index 514844efac75..9ec1df9cff95 100644 --- a/drivers/staging/iio/adc/mxs-lradc.c +++ b/drivers/staging/iio/adc/mxs-lradc.c @@ -846,6 +846,14 @@ static int mxs_lradc_read_single(struct iio_dev *iio_dev, int chan, int *val) LRADC_CTRL1); mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0); + /* Enable / disable the divider per requirement */ + if (test_bit(chan, &lradc->is_divided)) + mxs_lradc_reg_set(lradc, 1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET, + LRADC_CTRL2); + else + mxs_lradc_reg_clear(lradc, + 1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET, LRADC_CTRL2); + /* Clean the slot's previous content, then set new one. */ mxs_lradc_reg_clear(lradc, LRADC_CTRL4_LRADCSELECT_MASK(0), LRADC_CTRL4); mxs_lradc_reg_set(lradc, chan, LRADC_CTRL4); @@ -964,15 +972,11 @@ static int mxs_lradc_write_raw(struct iio_dev *iio_dev, if (val == scale_avail[MXS_LRADC_DIV_DISABLED].integer && val2 == scale_avail[MXS_LRADC_DIV_DISABLED].nano) { /* divider by two disabled */ - writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET, - lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_CLR); clear_bit(chan->channel, &lradc->is_divided); ret = 0; } else if (val == scale_avail[MXS_LRADC_DIV_ENABLED].integer && val2 == scale_avail[MXS_LRADC_DIV_ENABLED].nano) { /* divider by two enabled */ - writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET, - lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_SET); set_bit(chan->channel, &lradc->is_divided); ret = 0; } diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 2b96665da8a2..97d4b3fb7e95 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -115,6 +115,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .channel = 0, .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), .address = AD5933_REG_TEMP_DATA, + .scan_index = -1, .scan_type = { .sign = 's', .realbits = 14, @@ -124,9 +125,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "real_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "real", .address = AD5933_REG_REAL_DATA, .scan_index = 0, .scan_type = { @@ -138,9 +137,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "imag_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "imag", .address = AD5933_REG_IMAG_DATA, .scan_index = 1, .scan_type = { @@ -748,14 +745,14 @@ static int ad5933_probe(struct i2c_client *client, indio_dev->name = id->name; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = ad5933_channels; - indio_dev->num_channels = 1; /* only register temp0_input */ + indio_dev->num_channels = ARRAY_SIZE(ad5933_channels); ret = ad5933_register_ring_funcs_and_init(indio_dev); if (ret) goto error_disable_reg; - /* skip temp0_input, register in0_(real|imag)_raw */ - ret = iio_buffer_register(indio_dev, &ad5933_channels[1], 2); + ret = iio_buffer_register(indio_dev, ad5933_channels, + ARRAY_SIZE(ad5933_channels)); if (ret) goto error_unreg_ring; diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c index 1e538086d48b..ce1e74e000bb 100644 --- a/drivers/staging/iio/light/tsl2x7x_core.c +++ b/drivers/staging/iio/light/tsl2x7x_core.c @@ -667,9 +667,13 @@ static int tsl2x7x_chip_on(struct iio_dev *indio_dev) chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] = chip->tsl2x7x_settings.prox_pulse_count; chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] = - chip->tsl2x7x_settings.prox_thres_low; + (chip->tsl2x7x_settings.prox_thres_low) & 0xFF; + chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] = + (chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF; chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] = - chip->tsl2x7x_settings.prox_thres_high; + (chip->tsl2x7x_settings.prox_thres_high) & 0xFF; + chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] = + (chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF; /* and make sure we're not already on */ if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) { diff --git a/drivers/staging/iio/meter/ade7758.h b/drivers/staging/iio/meter/ade7758.h index 07318203a836..e8c98cf57070 100644 --- a/drivers/staging/iio/meter/ade7758.h +++ b/drivers/staging/iio/meter/ade7758.h @@ -119,7 +119,6 @@ struct ade7758_state { u8 *tx; u8 *rx; struct mutex buf_lock; - const struct iio_chan_spec *ade7758_ring_channels; struct spi_transfer ring_xfer[4]; struct spi_message ring_msg; /* diff --git a/drivers/staging/iio/meter/ade7758_core.c b/drivers/staging/iio/meter/ade7758_core.c index cba183e24838..94d9914a602c 100644 --- a/drivers/staging/iio/meter/ade7758_core.c +++ b/drivers/staging/iio/meter/ade7758_core.c @@ -630,9 +630,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_A, AD7758_VOLTAGE), .scan_index = 0, .scan_type = { @@ -644,9 +641,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 0, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_A, AD7758_CURRENT), .scan_index = 1, .scan_type = { @@ -658,9 +652,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_A, AD7758_APP_PWR), .scan_index = 2, .scan_type = { @@ -672,9 +664,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_A, AD7758_ACT_PWR), .scan_index = 3, .scan_type = { @@ -686,9 +676,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_A, AD7758_REACT_PWR), .scan_index = 4, .scan_type = { @@ -700,9 +688,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 1, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_B, AD7758_VOLTAGE), .scan_index = 5, .scan_type = { @@ -714,9 +699,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 1, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_B, AD7758_CURRENT), .scan_index = 6, .scan_type = { @@ -728,9 +710,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_B, AD7758_APP_PWR), .scan_index = 7, .scan_type = { @@ -742,9 +722,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_B, AD7758_ACT_PWR), .scan_index = 8, .scan_type = { @@ -756,9 +734,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_B, AD7758_REACT_PWR), .scan_index = 9, .scan_type = { @@ -770,9 +746,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 2, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_C, AD7758_VOLTAGE), .scan_index = 10, .scan_type = { @@ -784,9 +757,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 2, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_C, AD7758_CURRENT), .scan_index = 11, .scan_type = { @@ -798,9 +768,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_C, AD7758_APP_PWR), .scan_index = 12, .scan_type = { @@ -812,9 +780,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_C, AD7758_ACT_PWR), .scan_index = 13, .scan_type = { @@ -826,9 +792,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_C, AD7758_REACT_PWR), .scan_index = 14, .scan_type = { @@ -869,13 +833,14 @@ static int ade7758_probe(struct spi_device *spi) goto error_free_rx; } st->us = spi; - st->ade7758_ring_channels = &ade7758_channels[0]; mutex_init(&st->buf_lock); indio_dev->name = spi->dev.driver->name; indio_dev->dev.parent = &spi->dev; indio_dev->info = &ade7758_info; indio_dev->modes = INDIO_DIRECT_MODE; + indio_dev->channels = ade7758_channels; + indio_dev->num_channels = ARRAY_SIZE(ade7758_channels); ret = ade7758_configure_ring(indio_dev); if (ret) diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c index c0accf8cce93..6e9006490742 100644 --- a/drivers/staging/iio/meter/ade7758_ring.c +++ b/drivers/staging/iio/meter/ade7758_ring.c @@ -85,17 +85,16 @@ static irqreturn_t ade7758_trigger_handler(int irq, void *p) **/ static int ade7758_ring_preenable(struct iio_dev *indio_dev) { - struct ade7758_state *st = iio_priv(indio_dev); unsigned channel; - if (!bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength)) + if (bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength)) return -EINVAL; channel = find_first_bit(indio_dev->active_scan_mask, indio_dev->masklength); ade7758_write_waveform_type(&indio_dev->dev, - st->ade7758_ring_channels[channel].address); + indio_dev->channels[channel].address); return 0; } diff --git a/drivers/staging/iio/meter/ade7758_trigger.c b/drivers/staging/iio/meter/ade7758_trigger.c index 7a94ddd42f59..8c4f2896cd0d 100644 --- a/drivers/staging/iio/meter/ade7758_trigger.c +++ b/drivers/staging/iio/meter/ade7758_trigger.c @@ -85,7 +85,7 @@ int ade7758_probe_trigger(struct iio_dev *indio_dev) ret = iio_trigger_register(st->trig); /* select default trigger */ - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); if (ret) goto error_free_irq; diff --git a/drivers/staging/imx-drm/ipuv3-plane.c b/drivers/staging/imx-drm/ipuv3-plane.c index 34b642a12f8b..c70f1734b274 100644 --- a/drivers/staging/imx-drm/ipuv3-plane.c +++ b/drivers/staging/imx-drm/ipuv3-plane.c @@ -277,7 +277,8 @@ static void ipu_plane_dpms(struct ipu_plane *ipu_plane, int mode) ipu_idmac_put(ipu_plane->ipu_ch); ipu_dmfc_put(ipu_plane->dmfc); - ipu_dp_put(ipu_plane->dp); + if (ipu_plane->dp) + ipu_dp_put(ipu_plane->dp); } } diff --git a/drivers/staging/lustre/lustre/Kconfig b/drivers/staging/lustre/lustre/Kconfig index 209e4c7e6f8a..4f65ba1158bf 100644 --- a/drivers/staging/lustre/lustre/Kconfig +++ b/drivers/staging/lustre/lustre/Kconfig @@ -57,4 +57,5 @@ config LUSTRE_TRANSLATE_ERRNOS config LUSTRE_LLITE_LLOOP tristate "Lustre virtual block device" depends on LUSTRE_FS && BLOCK + depends on !PPC_64K_PAGES && !ARM64_64K_PAGES default m diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c index b2cd3a85166d..bbf236e842a9 100644 --- a/drivers/staging/media/bcm2048/radio-bcm2048.c +++ b/drivers/staging/media/bcm2048/radio-bcm2048.c @@ -737,7 +737,7 @@ static int bcm2048_set_region(struct bcm2048_device *bdev, u8 region) int err; u32 new_frequency = 0; - if (region > ARRAY_SIZE(region_configs)) + if (region >= ARRAY_SIZE(region_configs)) return -EINVAL; mutex_lock(&bdev->mutex); diff --git a/drivers/staging/media/omap4iss/Kconfig b/drivers/staging/media/omap4iss/Kconfig index b9fe753969bd..15940f8fdd24 100644 --- a/drivers/staging/media/omap4iss/Kconfig +++ b/drivers/staging/media/omap4iss/Kconfig @@ -1,6 +1,6 @@ config VIDEO_OMAP4 bool "OMAP 4 Camera support" - depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && I2C && ARCH_OMAP4 + depends on VIDEO_V4L2=y && VIDEO_V4L2_SUBDEV_API && I2C=y && ARCH_OMAP4 select VIDEOBUF2_DMA_CONTIG ---help--- Driver for an OMAP 4 ISS controller. diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c index 51dbc13e757f..5a40925680ac 100644 --- a/drivers/staging/mt29f_spinand/mt29f_spinand.c +++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c @@ -924,6 +924,7 @@ static int spinand_remove(struct spi_device *spi) static const struct of_device_id spinand_dt[] = { { .compatible = "spinand,mt29f", }, + {} }; /* diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index c9c180649c12..cec3f1628cd8 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -542,7 +542,7 @@ _func_exit_; /* set the security information in the recv_frame */ static union recv_frame *portctrl(struct adapter *adapter, union recv_frame *precv_frame) { - u8 *psta_addr = NULL, *ptr; + u8 *psta_addr, *ptr; uint auth_alg; struct recv_frame_hdr *pfhdr; struct sta_info *psta; @@ -556,7 +556,6 @@ static union recv_frame *portctrl(struct adapter *adapter, union recv_frame *pre _func_enter_; pstapriv = &adapter->stapriv; - psta = rtw_get_stainfo(pstapriv, psta_addr); auth_alg = adapter->securitypriv.dot11AuthAlgrthm; @@ -564,6 +563,7 @@ _func_enter_; pfhdr = &precv_frame->u.hdr; pattrib = &pfhdr->attrib; psta_addr = pattrib->ta; + psta = rtw_get_stainfo(pstapriv, psta_addr); prtnframe = NULL; diff --git a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c index 96df62f95b6b..9b4678c73c0d 100644 --- a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c +++ b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c @@ -1601,13 +1601,18 @@ int update_sta_support_rate(struct adapter *padapter, u8 *pvar_ie, uint var_ie_l pIE = (struct ndis_802_11_var_ie *)rtw_get_ie(pvar_ie, _SUPPORTEDRATES_IE_, &ie_len, var_ie_len); if (pIE == NULL) return _FAIL; + if (ie_len > NDIS_802_11_LENGTH_RATES_EX) + return _FAIL; memcpy(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates, pIE->data, ie_len); supportRateNum = ie_len; pIE = (struct ndis_802_11_var_ie *)rtw_get_ie(pvar_ie, _EXT_SUPPORTEDRATES_IE_, &ie_len, var_ie_len); - if (pIE) + if (pIE) { + if (supportRateNum + ie_len > NDIS_802_11_LENGTH_RATES_EX) + return _FAIL; memcpy((pmlmeinfo->FW_sta_info[cam_idx].SupportedRates + supportRateNum), pIE->data, ie_len); + } return _SUCCESS; } diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index 2f40ff5901d6..fed699fc5918 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -53,9 +53,11 @@ static struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */ /*=== Customer ID ===*/ /****** 8188EUS ********/ + {USB_DEVICE(0x056e, 0x4008)}, /* Elecom WDC-150SU2M */ {USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */ {USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */ {USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */ + {USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ {} /* Terminating entry */ }; diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c index 77964885b3f2..334d949afd63 100644 --- a/drivers/staging/rtl8192e/rtllib_tx.c +++ b/drivers/staging/rtl8192e/rtllib_tx.c @@ -171,7 +171,7 @@ inline int rtllib_put_snap(u8 *data, u16 h_proto) snap->oui[1] = oui[1]; snap->oui[2] = oui[2]; - *(u16 *)(data + SNAP_SIZE) = h_proto; + *(__be16 *)(data + SNAP_SIZE) = htons(h_proto); return SNAP_SIZE + sizeof(u16); } diff --git a/drivers/staging/rtl8712/rtl871x_recv.c b/drivers/staging/rtl8712/rtl871x_recv.c index 23ec684b60e1..274c359279ef 100644 --- a/drivers/staging/rtl8712/rtl871x_recv.c +++ b/drivers/staging/rtl8712/rtl871x_recv.c @@ -254,7 +254,7 @@ union recv_frame *r8712_portctrl(struct _adapter *adapter, struct sta_info *psta; struct sta_priv *pstapriv; union recv_frame *prtnframe; - u16 ether_type = 0; + u16 ether_type; pstapriv = &adapter->stapriv; ptr = get_recvframe_data(precv_frame); @@ -263,15 +263,14 @@ union recv_frame *r8712_portctrl(struct _adapter *adapter, psta = r8712_get_stainfo(pstapriv, psta_addr); auth_alg = adapter->securitypriv.AuthAlgrthm; if (auth_alg == 2) { + /* get ether_type */ + ptr = ptr + pfhdr->attrib.hdrlen + LLC_HEADER_SIZE; + memcpy(ðer_type, ptr, 2); + ether_type = ntohs((unsigned short)ether_type); + if ((psta != NULL) && (psta->ieee8021x_blocked)) { /* blocked * only accept EAPOL frame */ - prtnframe = precv_frame; - /*get ether_type */ - ptr = ptr + pfhdr->attrib.hdrlen + - pfhdr->attrib.iv_len + LLC_HEADER_SIZE; - memcpy(ðer_type, ptr, 2); - ether_type = ntohs((unsigned short)ether_type); if (ether_type == 0x888e) prtnframe = precv_frame; else { diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c index f0fcbf7c7d7f..868226953d5c 100644 --- a/drivers/staging/serqt_usb2/serqt_usb2.c +++ b/drivers/staging/serqt_usb2/serqt_usb2.c @@ -724,7 +724,7 @@ static int qt_startup(struct usb_serial *serial) goto startup_error; } - switch (serial->dev->descriptor.idProduct) { + switch (le16_to_cpu(serial->dev->descriptor.idProduct)) { case QUATECH_DSU100: case QUATECH_QSU100: case QUATECH_ESU100A: diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index ef5933b93590..f61f9cf95ed7 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -2218,6 +2218,7 @@ static void __exit speakup_exit(void) unregister_keyboard_notifier(&keyboard_notifier_block); unregister_vt_notifier(&vt_notifier_block); speakup_unregister_devsynth(); + speakup_cancel_paste(); del_timer(&cursor_timer); kthread_stop(speakup_task); speakup_task = NULL; diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c index f0fb00392d6b..ca04d3669acc 100644 --- a/drivers/staging/speakup/selection.c +++ b/drivers/staging/speakup/selection.c @@ -4,6 +4,10 @@ #include <linux/sched.h> #include <linux/device.h> /* for dev_warn */ #include <linux/selection.h> +#include <linux/workqueue.h> +#include <linux/tty.h> +#include <linux/tty_flip.h> +#include <asm/cmpxchg.h> #include "speakup.h" @@ -121,31 +125,61 @@ int speakup_set_selection(struct tty_struct *tty) return 0; } -/* TODO: move to some helper thread, probably. That'd fix having to check for - * in_atomic(). */ -int speakup_paste_selection(struct tty_struct *tty) +struct speakup_paste_work { + struct work_struct work; + struct tty_struct *tty; +}; + +static void __speakup_paste_selection(struct work_struct *work) { + struct speakup_paste_work *spw = + container_of(work, struct speakup_paste_work, work); + struct tty_struct *tty = xchg(&spw->tty, NULL); struct vc_data *vc = (struct vc_data *) tty->driver_data; int pasted = 0, count; + struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); + + ld = tty_ldisc_ref_wait(tty); + tty_buffer_lock_exclusive(&vc->port); + add_wait_queue(&vc->paste_wait, &wait); while (sel_buffer && sel_buffer_lth > pasted) { set_current_state(TASK_INTERRUPTIBLE); if (test_bit(TTY_THROTTLED, &tty->flags)) { - if (in_atomic()) - /* if we are in an interrupt handler, abort */ - break; schedule(); continue; } count = sel_buffer_lth - pasted; - count = min_t(int, count, tty->receive_room); - tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted, - NULL, count); + count = tty_ldisc_receive_buf(ld, sel_buffer + pasted, NULL, + count); pasted += count; } remove_wait_queue(&vc->paste_wait, &wait); current->state = TASK_RUNNING; + + tty_buffer_unlock_exclusive(&vc->port); + tty_ldisc_deref(ld); + tty_kref_put(tty); +} + +static struct speakup_paste_work speakup_paste_work = { + .work = __WORK_INITIALIZER(speakup_paste_work.work, + __speakup_paste_selection) +}; + +int speakup_paste_selection(struct tty_struct *tty) +{ + if (cmpxchg(&speakup_paste_work.tty, NULL, tty) != NULL) + return -EBUSY; + + tty_kref_get(tty); + schedule_work_on(WORK_CPU_UNBOUND, &speakup_paste_work.work); return 0; } +void speakup_cancel_paste(void) +{ + cancel_work_sync(&speakup_paste_work.work); + tty_kref_put(speakup_paste_work.tty); +} diff --git a/drivers/staging/speakup/speakup.h b/drivers/staging/speakup/speakup.h index 0126f714821a..74fe72429b2d 100644 --- a/drivers/staging/speakup/speakup.h +++ b/drivers/staging/speakup/speakup.h @@ -77,6 +77,7 @@ extern void synth_buffer_clear(void); extern void speakup_clear_selection(void); extern int speakup_set_selection(struct tty_struct *tty); extern int speakup_paste_selection(struct tty_struct *tty); +extern void speakup_cancel_paste(void); extern void speakup_register_devsynth(void); extern void speakup_unregister_devsynth(void); extern void synth_write(const char *buf, size_t count); diff --git a/drivers/staging/tidspbridge/core/dsp-clock.c b/drivers/staging/tidspbridge/core/dsp-clock.c index 2f084e181d39..a1aca4416ca7 100644 --- a/drivers/staging/tidspbridge/core/dsp-clock.c +++ b/drivers/staging/tidspbridge/core/dsp-clock.c @@ -226,7 +226,7 @@ int dsp_clk_enable(enum dsp_clk_id clk_id) case GPT_CLK: status = omap_dm_timer_start(timer[clk_id - 1]); break; -#ifdef CONFIG_OMAP_MCBSP +#ifdef CONFIG_SND_OMAP_SOC_MCBSP case MCBSP_CLK: omap_mcbsp_request(MCBSP_ID(clk_id)); omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PAD_SRC); @@ -302,7 +302,7 @@ int dsp_clk_disable(enum dsp_clk_id clk_id) case GPT_CLK: status = omap_dm_timer_stop(timer[clk_id - 1]); break; -#ifdef CONFIG_OMAP_MCBSP +#ifdef CONFIG_SND_OMAP_SOC_MCBSP case MCBSP_CLK: omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PRCM_SRC); omap_mcbsp_free(MCBSP_ID(clk_id)); diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c index d7efd0173a9a..7d7578872a84 100644 --- a/drivers/staging/vt6655/bssdb.c +++ b/drivers/staging/vt6655/bssdb.c @@ -983,7 +983,7 @@ start: pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1)); } - { + if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) { pDevice->byReAssocCount++; /* 10 sec timeout */ if ((pDevice->byReAssocCount > 10) && (!pDevice->bLinkPass)) { diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index a952df1bf9d6..6f13f0e597f8 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -2430,6 +2430,7 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { int handled = 0; unsigned char byData = 0; int ii = 0; + unsigned long flags; // unsigned char byRSSI; MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr); @@ -2455,7 +2456,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { handled = 1; MACvIntDisable(pDevice->PortOffset); - spin_lock_irq(&pDevice->lock); + + spin_lock_irqsave(&pDevice->lock, flags); //Make sure current page is 0 VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel); @@ -2696,7 +2698,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { MACvSelectPage1(pDevice->PortOffset); } - spin_unlock_irq(&pDevice->lock); + spin_unlock_irqrestore(&pDevice->lock, flags); + MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE); return IRQ_RETVAL(handled); diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index b83ec378d04f..104f29e6b290 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -460,6 +460,7 @@ int iscsit_del_np(struct iscsi_np *np) spin_lock_bh(&np->np_thread_lock); np->np_exports--; if (np->np_exports) { + np->enabled = true; spin_unlock_bh(&np->np_thread_lock); return 0; } @@ -1289,7 +1290,7 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf, if (cmd->data_direction != DMA_TO_DEVICE) { pr_err("Command ITT: 0x%08x received DataOUT for a" " NON-WRITE command.\n", cmd->init_task_tag); - return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, buf); + return iscsit_dump_data_payload(conn, payload_length, 1); } se_cmd = &cmd->se_cmd; iscsit_mod_dataout_timer(cmd); @@ -1564,7 +1565,9 @@ int iscsit_process_nop_out(struct iscsi_conn *conn, struct iscsi_cmd *cmd, * Initiator is expecting a NopIN ping reply.. */ if (hdr->itt != RESERVED_ITT) { - BUG_ON(!cmd); + if (!cmd) + return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, + (unsigned char *)hdr); spin_lock_bh(&conn->cmd_lock); list_add_tail(&cmd->i_conn_node, &conn->conn_cmd_list); @@ -2468,6 +2471,7 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn) { struct iscsi_cmd *cmd; struct iscsi_conn *conn_p; + bool found = false; /* * Only send a Asynchronous Message on connections whos network @@ -2476,11 +2480,12 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn) list_for_each_entry(conn_p, &conn->sess->sess_conn_list, conn_list) { if (conn_p->conn_state == TARG_CONN_STATE_LOGGED_IN) { iscsit_inc_conn_usage_count(conn_p); + found = true; break; } } - if (!conn_p) + if (!found) return; cmd = iscsit_allocate_cmd(conn_p, TASK_RUNNING); @@ -3356,7 +3361,9 @@ static bool iscsit_check_inaddr_any(struct iscsi_np *np) #define SENDTARGETS_BUF_LIMIT 32768U -static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd) +static int +iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, + enum iscsit_transport_type network_transport) { char *payload = NULL; struct iscsi_conn *conn = cmd->conn; @@ -3433,6 +3440,9 @@ static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd) struct iscsi_np *np = tpg_np->tpg_np; bool inaddr_any = iscsit_check_inaddr_any(np); + if (np->np_network_transport != network_transport) + continue; + if (!target_name_printed) { len = sprintf(buf, "TargetName=%s", tiqn->tiqn); @@ -3486,11 +3496,12 @@ eob: int iscsit_build_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn, - struct iscsi_text_rsp *hdr) + struct iscsi_text_rsp *hdr, + enum iscsit_transport_type network_transport) { int text_length, padding; - text_length = iscsit_build_sendtargets_response(cmd); + text_length = iscsit_build_sendtargets_response(cmd, network_transport); if (text_length < 0) return text_length; @@ -3528,7 +3539,7 @@ static int iscsit_send_text_rsp( u32 tx_size = 0; int text_length, iov_count = 0, rc; - rc = iscsit_build_text_rsp(cmd, conn, hdr); + rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_TCP); if (rc < 0) return rc; @@ -4200,8 +4211,6 @@ int iscsit_close_connection( if (conn->conn_transport->iscsit_wait_conn) conn->conn_transport->iscsit_wait_conn(conn); - iscsit_free_queue_reqs_for_conn(conn); - /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4218,6 +4227,7 @@ int iscsit_close_connection( iscsit_clear_ooo_cmdsns_for_conn(conn); iscsit_release_commands_from_conn(conn); } + iscsit_free_queue_reqs_for_conn(conn); /* * Handle decrementing session or connection usage count if @@ -4503,6 +4513,7 @@ static void iscsit_logout_post_handler_diffcid( { struct iscsi_conn *l_conn; struct iscsi_session *sess = conn->sess; + bool conn_found = false; if (!sess) return; @@ -4511,12 +4522,13 @@ static void iscsit_logout_post_handler_diffcid( list_for_each_entry(l_conn, &sess->sess_conn_list, conn_list) { if (l_conn->cid == cid) { iscsit_inc_conn_usage_count(l_conn); + conn_found = true; break; } } spin_unlock_bh(&sess->conn_lock); - if (!l_conn) + if (!conn_found) return; if (l_conn->sock) diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index de77d9aa22c6..6689de6c5591 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -314,6 +314,16 @@ static int chap_server_compute_md5( goto out; } /* + * During mutual authentication, the CHAP_C generated by the + * initiator must not match the original CHAP_C generated by + * the target. + */ + if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) { + pr_err("initiator CHAP_C matches target CHAP_C, failing" + " login attempt\n"); + goto out; + } + /* * Generate CHAP_N and CHAP_R for mutual authentication. */ tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h index 48f7b3bf4e8c..1d4a8c86551f 100644 --- a/drivers/target/iscsi/iscsi_target_core.h +++ b/drivers/target/iscsi/iscsi_target_core.h @@ -773,6 +773,7 @@ struct iscsi_np { int np_ip_proto; int np_sock_type; enum np_thread_state_table np_thread_state; + bool enabled; enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index e29279e6b577..d509aa74cfa1 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -249,6 +249,28 @@ static void iscsi_login_set_conn_values( mutex_unlock(&auth_id_lock); } +static __printf(2, 3) int iscsi_change_param_sprintf( + struct iscsi_conn *conn, + const char *fmt, ...) +{ + va_list args; + unsigned char buf[64]; + + memset(buf, 0, sizeof buf); + + va_start(args, fmt); + vsnprintf(buf, sizeof buf, fmt, args); + va_end(args); + + if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) { + iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, + ISCSI_LOGIN_STATUS_NO_RESOURCES); + return -1; + } + + return 0; +} + /* * This is the leading connection of a new session, * or session reinstatement. @@ -337,7 +359,6 @@ static int iscsi_login_zero_tsih_s2( { struct iscsi_node_attrib *na; struct iscsi_session *sess = conn->sess; - unsigned char buf[32]; bool iser = false; sess->tpg = conn->tpg; @@ -378,26 +399,16 @@ static int iscsi_login_zero_tsih_s2( * * In our case, we have already located the struct iscsi_tiqn at this point. */ - memset(buf, 0, 32); - sprintf(buf, "TargetPortalGroupTag=%hu", sess->tpg->tpgt); - if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) { - iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, - ISCSI_LOGIN_STATUS_NO_RESOURCES); + if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt)) return -1; - } /* * Workaround for Initiators that have broken connection recovery logic. * * "We would really like to get rid of this." Linux-iSCSI.org team */ - memset(buf, 0, 32); - sprintf(buf, "ErrorRecoveryLevel=%d", na->default_erl); - if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) { - iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, - ISCSI_LOGIN_STATUS_NO_RESOURCES); + if (iscsi_change_param_sprintf(conn, "ErrorRecoveryLevel=%d", na->default_erl)) return -1; - } if (iscsi_login_disable_FIM_keys(conn->param_list, conn) < 0) return -1; @@ -409,12 +420,9 @@ static int iscsi_login_zero_tsih_s2( unsigned long mrdsl, off; int rc; - sprintf(buf, "RDMAExtensions=Yes"); - if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) { - iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, - ISCSI_LOGIN_STATUS_NO_RESOURCES); + if (iscsi_change_param_sprintf(conn, "RDMAExtensions=Yes")) return -1; - } + /* * Make MaxRecvDataSegmentLength PAGE_SIZE aligned for * Immediate Data + Unsolicitied Data-OUT if necessary.. @@ -444,12 +452,8 @@ static int iscsi_login_zero_tsih_s2( pr_warn("Aligning ISER MaxRecvDataSegmentLength: %lu down" " to PAGE_SIZE\n", mrdsl); - sprintf(buf, "MaxRecvDataSegmentLength=%lu\n", mrdsl); - if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) { - iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, - ISCSI_LOGIN_STATUS_NO_RESOURCES); + if (iscsi_change_param_sprintf(conn, "MaxRecvDataSegmentLength=%lu\n", mrdsl)) return -1; - } } return 0; @@ -591,13 +595,8 @@ static int iscsi_login_non_zero_tsih_s2( * * In our case, we have already located the struct iscsi_tiqn at this point. */ - memset(buf, 0, 32); - sprintf(buf, "TargetPortalGroupTag=%hu", sess->tpg->tpgt); - if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) { - iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, - ISCSI_LOGIN_STATUS_NO_RESOURCES); + if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt)) return -1; - } return iscsi_login_disable_FIM_keys(conn->param_list, conn); } @@ -982,6 +981,7 @@ int iscsi_target_setup_login_socket( } np->np_transport = t; + np->enabled = true; return 0; } @@ -1196,7 +1196,7 @@ old_sess_out: static int __iscsi_target_login_thread(struct iscsi_np *np) { u8 *buffer, zero_tsih = 0; - int ret = 0, rc, stop; + int ret = 0, rc; struct iscsi_conn *conn = NULL; struct iscsi_login *login; struct iscsi_portal_group *tpg = NULL; @@ -1210,6 +1210,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; complete(&np->np_restart_comp); + } else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) { + spin_unlock_bh(&np->np_thread_lock); + goto exit; } else { np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; } @@ -1402,10 +1405,8 @@ old_sess_out: } out: - stop = kthread_should_stop(); - /* Wait for another socket.. */ - if (!stop) - return 1; + return 1; + exit: iscsi_stop_login_thread_timer(np); spin_lock_bh(&np->np_thread_lock); @@ -1422,7 +1423,7 @@ int iscsi_target_login_thread(void *arg) allow_signal(SIGINT); - while (!kthread_should_stop()) { + while (1) { ret = __iscsi_target_login_thread(np); /* * We break and exit here unless another sock_accept() call diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index 4d2e23fc76fd..43b7e6a616b8 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -601,7 +601,7 @@ int iscsi_copy_param_list( param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL); if (!param_list) { pr_err("Unable to allocate memory for struct iscsi_param_list.\n"); - goto err_out; + return -1; } INIT_LIST_HEAD(¶m_list->param_list); INIT_LIST_HEAD(¶m_list->extra_response_list); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 44a5471de00f..d875f7972325 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -184,6 +184,8 @@ static void iscsit_clear_tpg_np_login_thread( return; } + if (shutdown) + tpg_np->tpg_np->enabled = false; iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg, shutdown); } diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index e655b042ed18..ab77f80ead2b 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1295,6 +1295,8 @@ int iscsit_tx_login_rsp(struct iscsi_conn *conn, u8 status_class, u8 status_deta login->login_failed = 1; iscsit_collect_login_stats(conn, status_class, status_detail); + memset(&login->rsp[0], 0, ISCSI_HDR_LEN); + hdr = (struct iscsi_login_rsp *)&login->rsp[0]; hdr->opcode = ISCSI_OP_LOGIN_RSP; hdr->status_class = status_class; diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index c3d9df6aaf5f..f0f0cc0e5752 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -564,7 +564,16 @@ static inline int core_alua_state_standby( case REPORT_LUNS: case RECEIVE_DIAGNOSTIC: case SEND_DIAGNOSTIC: + case READ_CAPACITY: return 0; + case SERVICE_ACTION_IN: + switch (cdb[1] & 0x1f) { + case SAI_READ_CAPACITY_16: + return 0; + default: + *alua_ascq = ASCQ_04H_ALUA_TG_PT_STANDBY; + return 1; + } case MAINTENANCE_IN: switch (cdb[1] & 0x1f) { case MI_REPORT_TARGET_PGS: diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index f0e85b119692..f30385385544 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -2223,6 +2223,11 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state( " tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id); return -EINVAL; } + if (!(dev->dev_flags & DF_CONFIGURED)) { + pr_err("Unable to set alua_access_state while device is" + " not configured\n"); + return -ENODEV; + } ret = kstrtoul(page, 0, &tmp); if (ret < 0) { @@ -2354,7 +2359,7 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_support_##_name(\ pr_err("Invalid value '%ld', must be '0' or '1'\n", tmp); \ return -EINVAL; \ } \ - if (!tmp) \ + if (tmp) \ t->_var |= _bit; \ else \ t->_var &= ~_bit; \ diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 65001e133670..38b4be24d13f 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -616,6 +616,7 @@ void core_dev_unexport( dev->export_count--; spin_unlock(&hba->device_lock); + lun->lun_sep = NULL; lun->lun_se_dev = NULL; } @@ -798,10 +799,10 @@ int se_dev_set_emulate_write_cache(struct se_device *dev, int flag) pr_err("emulate_write_cache not supported for pSCSI\n"); return -EINVAL; } - if (dev->transport->get_write_cache) { - pr_warn("emulate_write_cache cannot be changed when underlying" - " HW reports WriteCacheEnabled, ignoring request\n"); - return 0; + if (flag && + dev->transport->get_write_cache) { + pr_err("emulate_write_cache not supported for this device\n"); + return -EINVAL; } dev->dev_attrib.emulate_write_cache = flag; @@ -936,6 +937,10 @@ int se_dev_set_pi_prot_type(struct se_device *dev, int flag) return 0; } if (!dev->transport->init_prot || !dev->transport->free_prot) { + /* 0 is only allowed value for non-supporting backends */ + if (flag == 0) + return 0; + pr_err("DIF protection not supported by backend: %s\n", dev->transport->name); return -ENOSYS; @@ -1404,7 +1409,8 @@ int core_dev_add_initiator_node_lun_acl( * Check to see if there are any existing persistent reservation APTPL * pre-registrations that need to be enabled for this LUN ACL.. */ - core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, lacl); + core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, nacl, + lacl->mapped_lun); return 0; } diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 554d4f75a75a..9e0232cca92e 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -203,10 +203,9 @@ static void iblock_free_device(struct se_device *dev) if (ib_dev->ibd_bd != NULL) blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); - if (ib_dev->ibd_bio_set != NULL) { - bioset_integrity_free(ib_dev->ibd_bio_set); + if (ib_dev->ibd_bio_set != NULL) bioset_free(ib_dev->ibd_bio_set); - } + kfree(ib_dev); } diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 3013287a2aaa..1205dbd4f83d 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -944,10 +944,10 @@ int core_scsi3_check_aptpl_registration( struct se_device *dev, struct se_portal_group *tpg, struct se_lun *lun, - struct se_lun_acl *lun_acl) + struct se_node_acl *nacl, + u32 mapped_lun) { - struct se_node_acl *nacl = lun_acl->se_lun_nacl; - struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun]; + struct se_dev_entry *deve = nacl->device_list[mapped_lun]; if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) return 0; diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h index 2ee2936fa0bd..749fd7bb7510 100644 --- a/drivers/target/target_core_pr.h +++ b/drivers/target/target_core_pr.h @@ -60,7 +60,7 @@ extern int core_scsi3_alloc_aptpl_registration( unsigned char *, u16, u32, int, int, u8); extern int core_scsi3_check_aptpl_registration(struct se_device *, struct se_portal_group *, struct se_lun *, - struct se_lun_acl *); + struct se_node_acl *, u32); extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *, struct se_node_acl *); extern void core_scsi3_free_all_registrations(struct se_device *); diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index 66a5aba5a0d9..7b331b95a3ef 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -158,7 +158,7 @@ static int rd_allocate_sgl_table(struct rd_dev *rd_dev, struct rd_dev_sg_table * - 1; for (j = 0; j < sg_per_table; j++) { - pg = alloc_pages(GFP_KERNEL, 0); + pg = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); if (!pg) { pr_err("Unable to allocate scatterlist" " pages for struct rd_dev_sg_table\n"); @@ -242,7 +242,7 @@ static void rd_release_prot_space(struct rd_dev *rd_dev) rd_dev->sg_prot_count = 0; } -static int rd_build_prot_space(struct rd_dev *rd_dev, int prot_length) +static int rd_build_prot_space(struct rd_dev *rd_dev, int prot_length, int block_size) { struct rd_dev_sg_table *sg_table; u32 total_sg_needed, sg_tables; @@ -252,8 +252,13 @@ static int rd_build_prot_space(struct rd_dev *rd_dev, int prot_length) if (rd_dev->rd_flags & RDF_NULLIO) return 0; - - total_sg_needed = rd_dev->rd_page_count / prot_length; + /* + * prot_length=8byte dif data + * tot sg needed = rd_page_count * (PGSZ/block_size) * + * (prot_length/block_size) + pad + * PGSZ canceled each other. + */ + total_sg_needed = (rd_dev->rd_page_count * prot_length / block_size) + 1; sg_tables = (total_sg_needed / max_sg_per_table) + 1; @@ -606,7 +611,8 @@ static int rd_init_prot(struct se_device *dev) if (!dev->dev_attrib.pi_prot_type) return 0; - return rd_build_prot_space(rd_dev, dev->prot_length); + return rd_build_prot_space(rd_dev, dev->prot_length, + dev->dev_attrib.block_size); } static void rd_free_prot(struct se_device *dev) diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 77e6531fb0a1..379033f5903b 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -81,7 +81,7 @@ sbc_emulate_readcapacity(struct se_cmd *cmd) transport_kunmap_data_sg(cmd); } - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, 8); return 0; } @@ -134,7 +134,7 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd) transport_kunmap_data_sg(cmd); } - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, 32); return 0; } @@ -425,13 +425,14 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd) goto out; } - write_sg = kzalloc(sizeof(struct scatterlist) * cmd->t_data_nents, + write_sg = kmalloc(sizeof(struct scatterlist) * cmd->t_data_nents, GFP_KERNEL); if (!write_sg) { pr_err("Unable to allocate compare_and_write sg\n"); ret = TCM_OUT_OF_RESOURCES; goto out; } + sg_init_table(write_sg, cmd->t_data_nents); /* * Setup verify and write data payloads from total NumberLBAs. */ diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 3bebc71ea033..fcdf98fc947c 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -714,6 +714,7 @@ spc_emulate_inquiry(struct se_cmd *cmd) unsigned char *buf; sense_reason_t ret; int p; + int len = 0; buf = kzalloc(SE_INQUIRY_BUF, GFP_KERNEL); if (!buf) { @@ -735,6 +736,7 @@ spc_emulate_inquiry(struct se_cmd *cmd) } ret = spc_emulate_inquiry_std(cmd, buf); + len = buf[4] + 5; goto out; } @@ -742,6 +744,7 @@ spc_emulate_inquiry(struct se_cmd *cmd) if (cdb[2] == evpd_handlers[p].page) { buf[1] = cdb[2]; ret = evpd_handlers[p].emulate(cmd, buf); + len = get_unaligned_be16(&buf[2]) + 4; goto out; } } @@ -758,7 +761,7 @@ out: kfree(buf); if (!ret) - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, len); return ret; } @@ -1089,7 +1092,7 @@ set_length: transport_kunmap_data_sg(cmd); } - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, length); return 0; } @@ -1266,7 +1269,7 @@ done: buf[3] = (lun_count & 0xff); transport_kunmap_data_sg(cmd); - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8); return 0; } EXPORT_SYMBOL(spc_emulate_report_luns); diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index c036595b17cf..fb8a1a12dda9 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -40,6 +40,7 @@ #include <target/target_core_fabric.h> #include "target_core_internal.h" +#include "target_core_pr.h" extern struct se_device *g_lun0_dev; @@ -166,6 +167,13 @@ void core_tpg_add_node_to_devs( core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun, lun_access, acl, tpg); + /* + * Check to see if there are any existing persistent reservation + * APTPL pre-registrations that need to be enabled for this dynamic + * LUN ACL now.. + */ + core_scsi3_check_aptpl_registration(dev, tpg, lun, acl, + lun->unpacked_lun); spin_lock(&tpg->tpg_lun_lock); } spin_unlock(&tpg->tpg_lun_lock); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 2956250b7225..9232c7738ed1 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -560,7 +560,7 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists, spin_unlock_irqrestore(&cmd->t_state_lock, flags); - complete(&cmd->t_transport_stop_comp); + complete_all(&cmd->t_transport_stop_comp); return 1; } @@ -676,7 +676,7 @@ 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); - complete(&cmd->t_transport_stop_comp); + complete_all(&cmd->t_transport_stop_comp); return; } else if (!success) { INIT_WORK(&cmd->work, target_complete_failure_work); @@ -692,6 +692,23 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) } EXPORT_SYMBOL(target_complete_cmd); +void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length) +{ + if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) { + if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) { + cmd->residual_count += cmd->data_length - length; + } else { + cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT; + cmd->residual_count = cmd->data_length - length; + } + + cmd->data_length = length; + } + + target_complete_cmd(cmd, scsi_status); +} +EXPORT_SYMBOL(target_complete_cmd_with_length); + static void target_add_to_state_list(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1102,6 +1119,7 @@ void transport_init_se_cmd( init_completion(&cmd->cmd_wait_comp); init_completion(&cmd->task_stop_comp); spin_lock_init(&cmd->t_state_lock); + kref_init(&cmd->cmd_kref); cmd->transport_state = CMD_T_DEV_ACTIVE; cmd->se_tfo = tfo; @@ -1747,7 +1765,7 @@ void target_execute_cmd(struct se_cmd *cmd) cmd->se_tfo->get_task_tag(cmd)); spin_unlock_irq(&cmd->t_state_lock); - complete(&cmd->t_transport_stop_comp); + complete_all(&cmd->t_transport_stop_comp); return; } @@ -1837,8 +1855,7 @@ static void transport_complete_qf(struct se_cmd *cmd) if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) { trace_target_cmd_complete(cmd); ret = cmd->se_tfo->queue_status(cmd); - if (ret) - goto out; + goto out; } switch (cmd->data_direction) { @@ -2292,7 +2309,6 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, unsigned long flags; int ret = 0; - kref_init(&se_cmd->cmd_kref); /* * Add a second kref if the fabric caller is expecting to handle * fabric acknowledgement that requires two target_put_sess_cmd() @@ -2342,6 +2358,10 @@ static void target_release_cmd_kref(struct kref *kref) */ int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd) { + if (!se_sess) { + se_cmd->se_tfo->release_cmd(se_cmd); + return 1; + } return kref_put_spinlock_irqsave(&se_cmd->cmd_kref, target_release_cmd_kref, &se_sess->sess_cmd_lock); } @@ -2864,6 +2884,12 @@ static void target_tmr_work(struct work_struct *work) int transport_generic_handle_tmr( struct se_cmd *cmd) { + unsigned long flags; + + spin_lock_irqsave(&cmd->t_state_lock, flags); + cmd->transport_state |= CMD_T_ACTIVE; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + INIT_WORK(&cmd->work, target_tmr_work); queue_work(cmd->se_dev->tmr_wq, &cmd->work); return 0; diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index 8b2c1aaf81de..d22cdc77e9d4 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -90,18 +90,18 @@ static void ft_free_cmd(struct ft_cmd *cmd) { struct fc_frame *fp; struct fc_lport *lport; - struct se_session *se_sess; + struct ft_sess *sess; if (!cmd) return; - se_sess = cmd->sess->se_sess; + sess = cmd->sess; fp = cmd->req_frame; lport = fr_dev(fp); if (fr_seq(fp)) lport->tt.seq_release(fr_seq(fp)); fc_frame_free(fp); - percpu_ida_free(&se_sess->sess_tag_pool, cmd->se_cmd.map_tag); - ft_sess_put(cmd->sess); /* undo get from lookup at recv */ + percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag); + ft_sess_put(sess); /* undo get from lookup at recv */ } void ft_release_cmd(struct se_cmd *se_cmd) diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index ae52c08dad09..e9fe60fa7df1 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -68,6 +68,7 @@ static struct ft_tport *ft_tport_create(struct fc_lport *lport) if (tport) { tport->tpg = tpg; + tpg->tport = tport; return tport; } diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index fdb07199d9c2..1967bee4f076 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -140,6 +140,12 @@ thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon, return NULL; } +static bool thermal_zone_crit_temp_valid(struct thermal_zone_device *tz) +{ + unsigned long temp; + return tz->ops->get_crit_temp && !tz->ops->get_crit_temp(tz, &temp); +} + int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) { struct thermal_hwmon_device *hwmon; @@ -189,21 +195,18 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) if (result) goto free_temp_mem; - if (tz->ops->get_crit_temp) { - unsigned long temperature; - if (!tz->ops->get_crit_temp(tz, &temperature)) { - snprintf(temp->temp_crit.name, - sizeof(temp->temp_crit.name), + if (thermal_zone_crit_temp_valid(tz)) { + snprintf(temp->temp_crit.name, + sizeof(temp->temp_crit.name), "temp%d_crit", hwmon->count); - temp->temp_crit.attr.attr.name = temp->temp_crit.name; - temp->temp_crit.attr.attr.mode = 0444; - temp->temp_crit.attr.show = temp_crit_show; - sysfs_attr_init(&temp->temp_crit.attr.attr); - result = device_create_file(hwmon->device, - &temp->temp_crit.attr); - if (result) - goto unregister_input; - } + temp->temp_crit.attr.attr.name = temp->temp_crit.name; + temp->temp_crit.attr.attr.mode = 0444; + temp->temp_crit.attr.show = temp_crit_show; + sysfs_attr_init(&temp->temp_crit.attr.attr); + result = device_create_file(hwmon->device, + &temp->temp_crit.attr); + if (result) + goto unregister_input; } mutex_lock(&thermal_hwmon_list_lock); @@ -250,7 +253,7 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) } device_remove_file(hwmon->device, &temp->temp_input.attr); - if (tz->ops->get_crit_temp) + if (thermal_zone_crit_temp_valid(tz)) device_remove_file(hwmon->device, &temp->temp_crit.attr); mutex_lock(&thermal_hwmon_list_lock); diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index 50b46881b6ca..0ff7fda0742f 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -31,6 +31,7 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/major.h> +#include <linux/atomic.h> #include <linux/sysrq.h> #include <linux/tty.h> #include <linux/tty_flip.h> @@ -70,6 +71,9 @@ static struct task_struct *hvc_task; /* Picks up late kicks after list walk but before schedule() */ static int hvc_kicked; +/* hvc_init is triggered from hvc_alloc, i.e. only when actually used */ +static atomic_t hvc_needs_init __read_mostly = ATOMIC_INIT(-1); + static int hvc_init(void); #ifdef CONFIG_MAGIC_SYSRQ @@ -186,7 +190,7 @@ static struct tty_driver *hvc_console_device(struct console *c, int *index) return hvc_driver; } -static int __init hvc_console_setup(struct console *co, char *options) +static int hvc_console_setup(struct console *co, char *options) { if (co->index < 0 || co->index >= MAX_NR_HVC_CONSOLES) return -ENODEV; @@ -851,7 +855,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data, int i; /* We wait until a driver actually comes along */ - if (!hvc_driver) { + if (atomic_inc_not_zero(&hvc_needs_init)) { int err = hvc_init(); if (err) return ERR_PTR(err); diff --git a/drivers/tty/ipwireless/tty.c b/drivers/tty/ipwireless/tty.c index ebd5bff0f5c1..17ee3bf0926b 100644 --- a/drivers/tty/ipwireless/tty.c +++ b/drivers/tty/ipwireless/tty.c @@ -176,9 +176,6 @@ void ipwireless_tty_received(struct ipw_tty *tty, unsigned char *data, ": %d chars not inserted to flip buffer!\n", length - work); - /* - * This may sleep if ->low_latency is set - */ if (work) tty_flip_buffer_push(&tty->port); } diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index d15624c1b751..28ac3f3b7ec3 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1214,15 +1214,16 @@ static void n_tty_receive_parity_error(struct tty_struct *tty, unsigned char c) { struct n_tty_data *ldata = tty->disc_data; - if (I_IGNPAR(tty)) - return; - if (I_PARMRK(tty)) { - put_tty_queue('\377', ldata); - put_tty_queue('\0', ldata); - put_tty_queue(c, ldata); - } else if (I_INPCK(tty)) - put_tty_queue('\0', ldata); - else + if (I_INPCK(tty)) { + if (I_IGNPAR(tty)) + return; + if (I_PARMRK(tty)) { + put_tty_queue('\377', ldata); + put_tty_queue('\0', ldata); + put_tty_queue(c, ldata); + } else + put_tty_queue('\0', ldata); + } else put_tty_queue(c, ldata); if (waitqueue_active(&tty->read_wait)) wake_up_interruptible(&tty->read_wait); @@ -2356,8 +2357,12 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file, if (tty->ops->flush_chars) tty->ops->flush_chars(tty); } else { + struct n_tty_data *ldata = tty->disc_data; + while (nr > 0) { + mutex_lock(&ldata->output_lock); c = tty->ops->write(tty, b, nr); + mutex_unlock(&ldata->output_lock); if (c < 0) { retval = c; goto break_out; diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 69932b7556cf..612dfc720738 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -555,7 +555,7 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) */ if ((p->port.type == PORT_XR17V35X) || (p->port.type == PORT_XR17D15X)) { - serial_out(p, UART_EXAR_SLEEP, 0xff); + serial_out(p, UART_EXAR_SLEEP, sleep ? 0xff : 0); return; } @@ -1520,7 +1520,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) status = serial8250_rx_chars(up, status); } serial8250_modem_status(up); - if (status & UART_LSR_THRE) + if (!up->dma && (status & UART_LSR_THRE)) serial8250_tx_chars(up); spin_unlock_irqrestore(&port->lock, flags); @@ -2356,7 +2356,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; if (termios->c_iflag & INPCK) port->read_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= UART_LSR_BI; /* diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 7046769608d4..148ffe4c232f 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -20,12 +20,15 @@ static void __dma_tx_complete(void *param) struct uart_8250_port *p = param; struct uart_8250_dma *dma = p->dma; struct circ_buf *xmit = &p->port.state->xmit; - - dma->tx_running = 0; + unsigned long flags; dma_sync_single_for_cpu(dma->txchan->device->dev, dma->tx_addr, UART_XMIT_SIZE, DMA_TO_DEVICE); + spin_lock_irqsave(&p->port.lock, flags); + + dma->tx_running = 0; + xmit->tail += dma->tx_size; xmit->tail &= UART_XMIT_SIZE - 1; p->port.icount.tx += dma->tx_size; @@ -35,6 +38,8 @@ static void __dma_tx_complete(void *param) if (!uart_circ_empty(xmit) && !uart_tx_stopped(&p->port)) serial8250_tx_dma(p); + + spin_unlock_irqrestore(&p->port.lock, flags); } static void __dma_rx_complete(void *param) @@ -187,21 +192,28 @@ int serial8250_request_dma(struct uart_8250_port *p) dma->rx_buf = dma_alloc_coherent(dma->rxchan->device->dev, dma->rx_size, &dma->rx_addr, GFP_KERNEL); - if (!dma->rx_buf) { - dma_release_channel(dma->rxchan); - dma_release_channel(dma->txchan); - return -ENOMEM; - } + if (!dma->rx_buf) + goto err; /* TX buffer */ dma->tx_addr = dma_map_single(dma->txchan->device->dev, p->port.state->xmit.buf, UART_XMIT_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dma->txchan->device->dev, dma->tx_addr)) { + dma_free_coherent(dma->rxchan->device->dev, dma->rx_size, + dma->rx_buf, dma->rx_addr); + goto err; + } dev_dbg_ratelimited(p->port.dev, "got both dma channels\n"); return 0; +err: + dma_release_channel(dma->rxchan); + dma_release_channel(dma->txchan); + + return -ENOMEM; } EXPORT_SYMBOL_GPL(serial8250_request_dma); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 0ff3e3624d4c..feda34404ed0 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1766,6 +1766,7 @@ pci_wch_ch353_setup(struct serial_private *priv, #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e +#define PCI_DEVICE_ID_INTEL_QRK_UART 0x0936 #define PCI_VENDOR_ID_SUNIX 0x1fd4 #define PCI_DEVICE_ID_SUNIX_1999 0x1999 @@ -1876,6 +1877,13 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_QRK_UART, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_default_setup, + }, /* * ITE */ @@ -2710,6 +2718,7 @@ enum pci_board_num_t { pbn_ADDIDATA_PCIe_8_3906250, pbn_ce4100_1_115200, pbn_byt, + pbn_qrk, pbn_omegapci, pbn_NETMOS9900_2s_115200, pbn_brcm_trumanage, @@ -3456,6 +3465,12 @@ static struct pciserial_board pci_boards[] = { .uart_offset = 0x80, .reg_shift = 2, }, + [pbn_qrk] = { + .flags = FL_BASE0, + .num_ports = 1, + .base_baud = 2764800, + .reg_shift = 2, + }, [pbn_omegapci] = { .flags = FL_BASE0, .num_ports = 8, @@ -5150,6 +5165,12 @@ static struct pci_device_id serial_pci_tbl[] = { pbn_byt }, /* + * Intel Quark x1000 + */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QRK_UART, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_qrk }, + /* * Cronyx Omega PCI */ { PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_CRONYX_OMEGA, diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c index 501667e3e3f5..323376668b72 100644 --- a/drivers/tty/serial/altera_uart.c +++ b/drivers/tty/serial/altera_uart.c @@ -185,6 +185,12 @@ static void altera_uart_set_termios(struct uart_port *port, uart_update_timeout(port, termios->c_cflag, baud); altera_uart_writel(port, baudclk, ALTERA_UART_DIVISOR_REG); spin_unlock_irqrestore(&port->lock, flags); + + /* + * FIXME: port->read_status_mask and port->ignore_status_mask + * need to be initialized based on termios settings for + * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT + */ } static void altera_uart_rx_chars(struct altera_uart *pp) diff --git a/drivers/tty/serial/amba-pl010.c b/drivers/tty/serial/amba-pl010.c index 01c9e72433e1..971af1e22d0f 100644 --- a/drivers/tty/serial/amba-pl010.c +++ b/drivers/tty/serial/amba-pl010.c @@ -420,7 +420,7 @@ pl010_set_termios(struct uart_port *port, struct ktermios *termios, uap->port.read_status_mask = UART01x_RSR_OE; if (termios->c_iflag & INPCK) uap->port.read_status_mask |= UART01x_RSR_FE | UART01x_RSR_PE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) uap->port.read_status_mask |= UART01x_RSR_BE; /* diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index d58783d364e3..b569011ac713 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1744,7 +1744,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios, port->read_status_mask = UART011_DR_OE | 255; if (termios->c_iflag & INPCK) port->read_status_mask |= UART011_DR_FE | UART011_DR_PE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= UART011_DR_BE; /* diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index a49f10d269b2..ce352b81e230 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -1811,7 +1811,7 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, port->read_status_mask = ATMEL_US_OVRE; if (termios->c_iflag & INPCK) port->read_status_mask |= (ATMEL_US_FRAME | ATMEL_US_PARE); - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= ATMEL_US_RXBRK; if (atmel_use_pdc_rx(port)) diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index 78e82b017b92..e0b87d507670 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -565,7 +565,7 @@ static void bcm_uart_set_termios(struct uart_port *port, port->read_status_mask |= UART_FIFO_FRAMEERR_MASK; port->read_status_mask |= UART_FIFO_PARERR_MASK; } - if (new->c_iflag & (BRKINT)) + if (new->c_iflag & (IGNBRK | BRKINT)) port->read_status_mask |= UART_FIFO_BRKDET_MASK; port->ignore_status_mask = 0; diff --git a/drivers/tty/serial/bfin_uart.c b/drivers/tty/serial/bfin_uart.c index 869ceba2ec57..ac86a20992e9 100644 --- a/drivers/tty/serial/bfin_uart.c +++ b/drivers/tty/serial/bfin_uart.c @@ -833,7 +833,7 @@ bfin_serial_set_termios(struct uart_port *port, struct ktermios *termios, port->read_status_mask = OE; if (termios->c_iflag & INPCK) port->read_status_mask |= (FE | PE); - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= BI; /* diff --git a/drivers/tty/serial/dz.c b/drivers/tty/serial/dz.c index 2f2b2e538a54..cdbbc788230a 100644 --- a/drivers/tty/serial/dz.c +++ b/drivers/tty/serial/dz.c @@ -625,7 +625,7 @@ static void dz_set_termios(struct uart_port *uport, struct ktermios *termios, dport->port.read_status_mask = DZ_OERR; if (termios->c_iflag & INPCK) dport->port.read_status_mask |= DZ_FERR | DZ_PERR; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) dport->port.read_status_mask |= DZ_BREAK; /* characters to ignore */ diff --git a/drivers/tty/serial/efm32-uart.c b/drivers/tty/serial/efm32-uart.c index 0eb5b5673ede..948f17b6b497 100644 --- a/drivers/tty/serial/efm32-uart.c +++ b/drivers/tty/serial/efm32-uart.c @@ -407,7 +407,7 @@ static void efm32_uart_set_termios(struct uart_port *port, if (new->c_iflag & INPCK) port->read_status_mask |= UARTn_RXDATAX_FERR | UARTn_RXDATAX_PERR; - if (new->c_iflag & (BRKINT | PARMRK)) + if (new->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= SW_UARTn_RXDATAX_BERR; port->ignore_status_mask = 0; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 8978dc9a58b7..175f123f4f09 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -496,7 +496,7 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios, sport->port.read_status_mask = 0; if (termios->c_iflag & INPCK) sport->port.read_status_mask |= (UARTSR1_FE | UARTSR1_PE); - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) sport->port.read_status_mask |= UARTSR1_FE; /* characters to ignore */ diff --git a/drivers/tty/serial/ip22zilog.c b/drivers/tty/serial/ip22zilog.c index 1d9420548e16..1efd4c36ba0c 100644 --- a/drivers/tty/serial/ip22zilog.c +++ b/drivers/tty/serial/ip22zilog.c @@ -850,7 +850,7 @@ ip22zilog_convert_to_zs(struct uart_ip22zilog_port *up, unsigned int cflag, up->port.read_status_mask = Rx_OVR; if (iflag & INPCK) up->port.read_status_mask |= CRC_ERR | PAR_ERR; - if (iflag & (BRKINT | PARMRK)) + if (iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= BRK_ABRT; up->port.ignore_status_mask = 0; diff --git a/drivers/tty/serial/m32r_sio.c b/drivers/tty/serial/m32r_sio.c index 9cd9b4eba9fc..68f2c53e0b54 100644 --- a/drivers/tty/serial/m32r_sio.c +++ b/drivers/tty/serial/m32r_sio.c @@ -737,7 +737,7 @@ static void m32r_sio_set_termios(struct uart_port *port, up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; if (termios->c_iflag & INPCK) up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= UART_LSR_BI; /* diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 8d71e4047bb3..558af637cd0c 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -842,7 +842,7 @@ static void max310x_set_termios(struct uart_port *port, if (termios->c_iflag & INPCK) port->read_status_mask |= MAX310X_LSR_RXPAR_BIT | MAX310X_LSR_FRERR_BIT; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= MAX310X_LSR_RXBRK_BIT; /* Set status ignore mask */ diff --git a/drivers/tty/serial/mcf.c b/drivers/tty/serial/mcf.c index 0edfaf8cd269..a6f085717f94 100644 --- a/drivers/tty/serial/mcf.c +++ b/drivers/tty/serial/mcf.c @@ -248,6 +248,12 @@ static void mcf_set_termios(struct uart_port *port, struct ktermios *termios, mr1 |= MCFUART_MR1_PARITYNONE; } + /* + * FIXME: port->read_status_mask and port->ignore_status_mask + * need to be initialized based on termios settings for + * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT + */ + if (termios->c_cflag & CSTOPB) mr2 |= MCFUART_MR2_STOP2; else diff --git a/drivers/tty/serial/mfd.c b/drivers/tty/serial/mfd.c index 52c930fac210..445799dc9846 100644 --- a/drivers/tty/serial/mfd.c +++ b/drivers/tty/serial/mfd.c @@ -977,7 +977,7 @@ serial_hsu_set_termios(struct uart_port *port, struct ktermios *termios, up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; if (termios->c_iflag & INPCK) up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= UART_LSR_BI; /* Characters to ignore */ diff --git a/drivers/tty/serial/mpsc.c b/drivers/tty/serial/mpsc.c index e30a3ca3cea3..759c6a6fa74a 100644 --- a/drivers/tty/serial/mpsc.c +++ b/drivers/tty/serial/mpsc.c @@ -1458,7 +1458,7 @@ static void mpsc_set_termios(struct uart_port *port, struct ktermios *termios, pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_PE | SDMA_DESC_CMDSTAT_FR; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_BR; /* Characters/events to ignore */ diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index b5d779cd3c2b..c0f2b3e5452f 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -570,7 +570,7 @@ static void msm_set_termios(struct uart_port *port, struct ktermios *termios, port->read_status_mask = 0; if (termios->c_iflag & INPCK) port->read_status_mask |= UART_SR_PAR_FRAME_ERR; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= UART_SR_RX_BREAK; uart_update_timeout(port, termios->c_cflag, baud); diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index aa97fd845b4d..d98f1d4a9bd3 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -604,7 +604,7 @@ static void mxs_auart_settermios(struct uart_port *u, if (termios->c_iflag & INPCK) u->read_status_mask |= AUART_STAT_PERR; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) u->read_status_mask |= AUART_STAT_BERR; /* diff --git a/drivers/tty/serial/netx-serial.c b/drivers/tty/serial/netx-serial.c index 0a4dd70d29eb..7a6745601d4e 100644 --- a/drivers/tty/serial/netx-serial.c +++ b/drivers/tty/serial/netx-serial.c @@ -419,7 +419,7 @@ netx_set_termios(struct uart_port *port, struct ktermios *termios, } port->read_status_mask = 0; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= SR_BE; if (termios->c_iflag & INPCK) port->read_status_mask |= SR_PE | SR_FE; diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 77f035158d6c..f4e68b3fc39d 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -225,14 +225,19 @@ static inline void serial_omap_enable_wakeirq(struct uart_omap_port *up, if (enable) enable_irq(up->wakeirq); else - disable_irq(up->wakeirq); + disable_irq_nosync(up->wakeirq); } static void serial_omap_enable_wakeup(struct uart_omap_port *up, bool enable) { struct omap_uart_port_info *pdata = dev_get_platdata(up->dev); + if (enable == up->wakeups_enabled) + return; + serial_omap_enable_wakeirq(up, enable); + up->wakeups_enabled = enable; + if (!pdata || !pdata->enable_wakeup) return; @@ -255,8 +260,16 @@ serial_omap_baud_is_mode16(struct uart_port *port, unsigned int baud) { unsigned int n13 = port->uartclk / (13 * baud); unsigned int n16 = port->uartclk / (16 * baud); - int baudAbsDiff13 = baud - (port->uartclk / (13 * n13)); - int baudAbsDiff16 = baud - (port->uartclk / (16 * n16)); + int baudAbsDiff13; + int baudAbsDiff16; + + if (n13 == 0) + n13 = 1; + if (n16 == 0) + n16 = 1; + + baudAbsDiff13 = baud - (port->uartclk / (13 * n13)); + baudAbsDiff16 = baud - (port->uartclk / (16 * n16)); if (baudAbsDiff13 < 0) baudAbsDiff13 = -baudAbsDiff13; if (baudAbsDiff16 < 0) @@ -1488,6 +1501,11 @@ static int serial_omap_suspend(struct device *dev) uart_suspend_port(&serial_omap_reg, &up->port); flush_work(&up->qos_work); + if (device_may_wakeup(dev)) + serial_omap_enable_wakeup(up, true); + else + serial_omap_enable_wakeup(up, false); + return 0; } @@ -1495,6 +1513,9 @@ static int serial_omap_resume(struct device *dev) { struct uart_omap_port *up = dev_get_drvdata(dev); + if (device_may_wakeup(dev)) + serial_omap_enable_wakeup(up, false); + uart_resume_port(&serial_omap_reg, &up->port); return 0; @@ -1870,17 +1891,7 @@ static int serial_omap_runtime_suspend(struct device *dev) up->context_loss_cnt = serial_omap_get_context_loss_count(up); - if (device_may_wakeup(dev)) { - if (!up->wakeups_enabled) { - serial_omap_enable_wakeup(up, true); - up->wakeups_enabled = true; - } - } else { - if (up->wakeups_enabled) { - serial_omap_enable_wakeup(up, false); - up->wakeups_enabled = false; - } - } + serial_omap_enable_wakeup(up, true); up->latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE; schedule_work(&up->qos_work); @@ -1894,6 +1905,8 @@ static int serial_omap_runtime_resume(struct device *dev) int loss_cnt = serial_omap_get_context_loss_count(up); + serial_omap_enable_wakeup(up, false); + if (loss_cnt < 0) { dev_dbg(dev, "serial_omap_get_context_loss_count failed : %d\n", loss_cnt); diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c index e9d420ff3931..8193635103ee 100644 --- a/drivers/tty/serial/pmac_zilog.c +++ b/drivers/tty/serial/pmac_zilog.c @@ -1092,7 +1092,7 @@ static void pmz_convert_to_zs(struct uart_pmac_port *uap, unsigned int cflag, uap->port.read_status_mask = Rx_OVR; if (iflag & INPCK) uap->port.read_status_mask |= CRC_ERR | PAR_ERR; - if (iflag & (BRKINT | PARMRK)) + if (iflag & (IGNBRK | BRKINT | PARMRK)) uap->port.read_status_mask |= BRK_ABRT; uap->port.ignore_status_mask = 0; diff --git a/drivers/tty/serial/pnx8xxx_uart.c b/drivers/tty/serial/pnx8xxx_uart.c index de6c05c63683..2ba24a45c97f 100644 --- a/drivers/tty/serial/pnx8xxx_uart.c +++ b/drivers/tty/serial/pnx8xxx_uart.c @@ -477,7 +477,7 @@ pnx8xxx_set_termios(struct uart_port *port, struct ktermios *termios, sport->port.read_status_mask |= FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE) | FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR); - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) sport->port.read_status_mask |= ISTAT_TO_SM(PNX8XXX_UART_INT_BREAK); diff --git a/drivers/tty/serial/pxa.c b/drivers/tty/serial/pxa.c index f9f20f383760..fc3f308cd6c1 100644 --- a/drivers/tty/serial/pxa.c +++ b/drivers/tty/serial/pxa.c @@ -492,7 +492,7 @@ serial_pxa_set_termios(struct uart_port *port, struct ktermios *termios, up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; if (termios->c_iflag & INPCK) up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= UART_LSR_BI; /* diff --git a/drivers/tty/serial/sb1250-duart.c b/drivers/tty/serial/sb1250-duart.c index a7cdec2962dd..771f361c47ea 100644 --- a/drivers/tty/serial/sb1250-duart.c +++ b/drivers/tty/serial/sb1250-duart.c @@ -596,7 +596,7 @@ static void sbd_set_termios(struct uart_port *uport, struct ktermios *termios, if (termios->c_iflag & INPCK) uport->read_status_mask |= M_DUART_FRM_ERR | M_DUART_PARITY_ERR; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) uport->read_status_mask |= M_DUART_RCVD_BRK; uport->ignore_status_mask = 0; diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c index a447f71538ef..75ea83278ba4 100644 --- a/drivers/tty/serial/sccnxp.c +++ b/drivers/tty/serial/sccnxp.c @@ -667,7 +667,7 @@ static void sccnxp_set_termios(struct uart_port *port, port->read_status_mask = SR_OVR; if (termios->c_iflag & INPCK) port->read_status_mask |= SR_PE | SR_FE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= SR_BRK; /* Set status ignore mask */ diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index ece2049bd270..27b5554e20d9 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -235,6 +235,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) /* * Turn off DTR and RTS early. */ + if (uart_console(uport) && tty) + uport->cons->cflag = tty->termios.c_cflag; + if (!tty || (tty->termios.c_cflag & HUPCL)) uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); @@ -350,7 +353,7 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, * The spd_hi, spd_vhi, spd_shi, spd_warp kludge... * Die! Die! Die! */ - if (baud == 38400) + if (try == 0 && baud == 38400) baud = altbaud; /* diff --git a/drivers/tty/serial/serial_ks8695.c b/drivers/tty/serial/serial_ks8695.c index e1caa99e3d3b..5c79bdab985d 100644 --- a/drivers/tty/serial/serial_ks8695.c +++ b/drivers/tty/serial/serial_ks8695.c @@ -437,7 +437,7 @@ static void ks8695uart_set_termios(struct uart_port *port, struct ktermios *term port->read_status_mask = URLS_URROE; if (termios->c_iflag & INPCK) port->read_status_mask |= (URLS_URFE | URLS_URPE); - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= URLS_URBI; /* diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c index 90a080b1f9ee..cbf501da5df3 100644 --- a/drivers/tty/serial/serial_txx9.c +++ b/drivers/tty/serial/serial_txx9.c @@ -702,7 +702,7 @@ serial_txx9_set_termios(struct uart_port *port, struct ktermios *termios, TXX9_SIDISR_TDIS | TXX9_SIDISR_RDIS; if (termios->c_iflag & INPCK) up->port.read_status_mask |= TXX9_SIDISR_UFER | TXX9_SIDISR_UPER; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= TXX9_SIDISR_UBRK; /* diff --git a/drivers/tty/serial/sirfsoc_uart.c b/drivers/tty/serial/sirfsoc_uart.c index b7bfe24d4ebc..020fe220d0e9 100644 --- a/drivers/tty/serial/sirfsoc_uart.c +++ b/drivers/tty/serial/sirfsoc_uart.c @@ -908,7 +908,7 @@ static void sirfsoc_uart_set_termios(struct uart_port *port, if (termios->c_iflag & INPCK) port->read_status_mask |= uint_en->sirfsoc_frm_err_en; } - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= uint_en->sirfsoc_rxd_brk_en; if (sirfport->uart_reg->uart_type == SIRF_REAL_UART) { if (termios->c_iflag & IGNPAR) diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c index 21e6e84c0df8..0ee31755cb5a 100644 --- a/drivers/tty/serial/st-asc.c +++ b/drivers/tty/serial/st-asc.c @@ -547,7 +547,7 @@ static void asc_set_termios(struct uart_port *port, struct ktermios *termios, ascport->port.read_status_mask = ASC_RXBUF_DUMMY_OE; if (termios->c_iflag & INPCK) ascport->port.read_status_mask |= ASC_RXBUF_FE | ASC_RXBUF_PE; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) ascport->port.read_status_mask |= ASC_RXBUF_DUMMY_BE; /* diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c index 5faa8e905e98..e8f77606561b 100644 --- a/drivers/tty/serial/sunsab.c +++ b/drivers/tty/serial/sunsab.c @@ -157,6 +157,15 @@ receive_chars(struct uart_sunsab_port *up, (up->port.line == up->port.cons->index)) saw_console_brk = 1; + if (count == 0) { + if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) { + stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR | + SAB82532_ISR0_FERR); + up->port.icount.brk++; + uart_handle_break(&up->port); + } + } + for (i = 0; i < count; i++) { unsigned char ch = buf[i], flag; @@ -719,7 +728,7 @@ static void sunsab_convert_to_sab(struct uart_sunsab_port *up, unsigned int cfla if (iflag & INPCK) up->port.read_status_mask |= (SAB82532_ISR0_PERR | SAB82532_ISR0_FERR); - if (iflag & (BRKINT | PARMRK)) + if (iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= (SAB82532_ISR1_BRK << 8); /* diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c index 9a0f24f83720..5326ae195e5f 100644 --- a/drivers/tty/serial/sunsu.c +++ b/drivers/tty/serial/sunsu.c @@ -834,7 +834,7 @@ sunsu_change_speed(struct uart_port *port, unsigned int cflag, up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; if (iflag & INPCK) up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (iflag & (BRKINT | PARMRK)) + if (iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= UART_LSR_BI; /* diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c index a2c40ed287d2..a85db8b87156 100644 --- a/drivers/tty/serial/sunzilog.c +++ b/drivers/tty/serial/sunzilog.c @@ -915,7 +915,7 @@ sunzilog_convert_to_zs(struct uart_sunzilog_port *up, unsigned int cflag, up->port.read_status_mask = Rx_OVR; if (iflag & INPCK) up->port.read_status_mask |= CRC_ERR | PAR_ERR; - if (iflag & (BRKINT | PARMRK)) + if (iflag & (IGNBRK | BRKINT | PARMRK)) up->port.read_status_mask |= BRK_ABRT; up->port.ignore_status_mask = 0; diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c index d569ca58bab6..1c52074c38df 100644 --- a/drivers/tty/serial/ucc_uart.c +++ b/drivers/tty/serial/ucc_uart.c @@ -936,7 +936,7 @@ static void qe_uart_set_termios(struct uart_port *port, port->read_status_mask = BD_SC_EMPTY | BD_SC_OV; if (termios->c_iflag & INPCK) port->read_status_mask |= BD_SC_FR | BD_SC_PR; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= BD_SC_BR; /* diff --git a/drivers/tty/serial/vr41xx_siu.c b/drivers/tty/serial/vr41xx_siu.c index a63c14bc9a24..db0c8a4ab03e 100644 --- a/drivers/tty/serial/vr41xx_siu.c +++ b/drivers/tty/serial/vr41xx_siu.c @@ -559,7 +559,7 @@ static void siu_set_termios(struct uart_port *port, struct ktermios *new, port->read_status_mask = UART_LSR_THRE | UART_LSR_OE | UART_LSR_DR; if (c_iflag & INPCK) port->read_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (c_iflag & (BRKINT | PARMRK)) + if (c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= UART_LSR_BI; port->ignore_status_mask = 0; diff --git a/drivers/tty/serial/zs.c b/drivers/tty/serial/zs.c index 6a169877109b..2b65bb7ffb8a 100644 --- a/drivers/tty/serial/zs.c +++ b/drivers/tty/serial/zs.c @@ -923,7 +923,7 @@ static void zs_set_termios(struct uart_port *uport, struct ktermios *termios, uport->read_status_mask = Rx_OVR; if (termios->c_iflag & INPCK) uport->read_status_mask |= FRM_ERR | PAR_ERR; - if (termios->c_iflag & (BRKINT | PARMRK)) + if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) uport->read_status_mask |= Rx_BRK; uport->ignore_status_mask = 0; diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 765125dff20e..143deb62467d 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -60,6 +60,7 @@ void tty_buffer_lock_exclusive(struct tty_port *port) atomic_inc(&buf->priority); mutex_lock(&buf->lock); } +EXPORT_SYMBOL_GPL(tty_buffer_lock_exclusive); void tty_buffer_unlock_exclusive(struct tty_port *port) { @@ -73,6 +74,7 @@ void tty_buffer_unlock_exclusive(struct tty_port *port) if (restart) queue_work(system_unbound_wq, &buf->work); } +EXPORT_SYMBOL_GPL(tty_buffer_unlock_exclusive); /** * tty_buffer_space_avail - return unused buffer space @@ -258,7 +260,11 @@ static int __tty_buffer_request_room(struct tty_port *port, size_t size, n->flags = flags; buf->tail = n; b->commit = b->used; - smp_mb(); + /* paired w/ barrier in flush_to_ldisc(); ensures the + * latest commit value can be read before the head is + * advanced to the next buffer + */ + smp_wmb(); b->next = n; } else if (change) size = 0; @@ -351,14 +357,11 @@ EXPORT_SYMBOL(tty_insert_flip_string_flags); * Takes any pending buffers and transfers their ownership to the * ldisc side of the queue. It then schedules those characters for * processing by the line discipline. - * Note that this function can only be used when the low_latency flag - * is unset. Otherwise the workqueue won't be flushed. */ void tty_schedule_flip(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; - WARN_ON(port->low_latency); buf->tail->commit = buf->tail->used; schedule_work(&buf->work); @@ -447,17 +450,24 @@ static void flush_to_ldisc(struct work_struct *work) while (1) { struct tty_buffer *head = buf->head; + struct tty_buffer *next; int count; /* Ldisc or user is trying to gain exclusive access */ if (atomic_read(&buf->priority)) break; + next = head->next; + /* paired w/ barrier in __tty_buffer_request_room(); + * ensures commit value read is not stale if the head + * is advancing to the next buffer + */ + smp_rmb(); count = head->commit - head->read; if (!count) { - if (head->next == NULL) + if (next == NULL) break; - buf->head = head->next; + buf->head = next; tty_buffer_free(port, head); continue; } @@ -482,17 +492,15 @@ static void flush_to_ldisc(struct work_struct *work) */ void tty_flush_to_ldisc(struct tty_struct *tty) { - if (!tty->port->low_latency) - flush_work(&tty->port->buf.work); + flush_work(&tty->port->buf.work); } /** * tty_flip_buffer_push - terminal * @port: tty port to push * - * Queue a push of the terminal flip buffers to the line discipline. This - * function must not be called from IRQ context if port->low_latency is - * set. + * Queue a push of the terminal flip buffers to the line discipline. + * Can be called from IRQ/atomic context. * * In the event of the queue being busy for flipping the work will be * held off and retried later. @@ -500,14 +508,7 @@ void tty_flush_to_ldisc(struct tty_struct *tty) void tty_flip_buffer_push(struct tty_port *port) { - struct tty_bufhead *buf = &port->buf; - - buf->tail->commit = buf->tail->used; - - if (port->low_latency) - flush_to_ldisc(&buf->work); - else - schedule_work(&buf->work); + tty_schedule_flip(port); } EXPORT_SYMBOL(tty_flip_buffer_push); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index c74a00ad7add..25d07412e08e 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1271,12 +1271,13 @@ static void pty_line_name(struct tty_driver *driver, int index, char *p) * * Locking: None */ -static void tty_line_name(struct tty_driver *driver, int index, char *p) +static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p) { if (driver->flags & TTY_DRIVER_UNNUMBERED_NODE) - strcpy(p, driver->name); + return sprintf(p, "%s", driver->name); else - sprintf(p, "%s%d", driver->name, index + driver->name_base); + return sprintf(p, "%s%d", driver->name, + index + driver->name_base); } /** @@ -1700,6 +1701,7 @@ int tty_release(struct inode *inode, struct file *filp) int pty_master, tty_closing, o_tty_closing, do_sleep; int idx; char buf[64]; + long timeout = 0; if (tty_paranoia_check(tty, inode, __func__)) return 0; @@ -1784,7 +1786,11 @@ int tty_release(struct inode *inode, struct file *filp) __func__, tty_name(tty, buf)); tty_unlock_pair(tty, o_tty); mutex_unlock(&tty_mutex); - schedule(); + schedule_timeout_killable(timeout); + if (timeout < 120 * HZ) + timeout = 2 * timeout + 1; + else + timeout = MAX_SCHEDULE_TIMEOUT; } /* @@ -3545,9 +3551,19 @@ static ssize_t show_cons_active(struct device *dev, if (i >= ARRAY_SIZE(cs)) break; } - while (i--) - count += sprintf(buf + count, "%s%d%c", - cs[i]->name, cs[i]->index, i ? ' ':'\n'); + while (i--) { + int index = cs[i]->index; + struct tty_driver *drv = cs[i]->device(cs[i], &index); + + /* don't resolve tty0 as some programs depend on it */ + if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR)) + count += tty_line_name(drv, index, buf + count); + else + count += sprintf(buf + count, "%s%d", + cs[i]->name, cs[i]->index); + + count += sprintf(buf + count, "%c", i ? ' ':'\n'); + } console_unlock(); return count; diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index 2d51d852b474..ca1123d415c5 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -20,13 +20,13 @@ static void ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) { struct device *dev = ci->gadget.dev.parent; - int val; switch (event) { case CI_HDRC_CONTROLLER_RESET_EVENT: dev_dbg(dev, "CI_HDRC_CONTROLLER_RESET_EVENT received\n"); writel(0, USB_AHBBURST); writel(0, USB_AHBMODE); + usb_phy_init(ci->transceiver); break; case CI_HDRC_CONTROLLER_STOPPED_EVENT: dev_dbg(dev, "CI_HDRC_CONTROLLER_STOPPED_EVENT received\n"); @@ -34,10 +34,7 @@ static void ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) * Put the transceiver in non-driving mode. Otherwise host * may not detect soft-disconnection. */ - val = usb_phy_io_read(ci->transceiver, ULPI_FUNC_CTRL); - val &= ~ULPI_FUNC_CTRL_OPMODE_MASK; - val |= ULPI_FUNC_CTRL_OPMODE_NONDRIVING; - usb_phy_io_write(ci->transceiver, val, ULPI_FUNC_CTRL); + usb_phy_notify_disconnect(ci->transceiver, USB_SPEED_UNKNOWN); break; default: dev_dbg(dev, "unknown ci_hdrc event\n"); diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 4ab2cb62dfce..86b1fd673749 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1179,8 +1179,8 @@ static int ep_enable(struct usb_ep *ep, if (hwep->type == USB_ENDPOINT_XFER_CONTROL) cap |= QH_IOS; - if (hwep->num) - cap |= QH_ZLT; + + cap |= QH_ZLT; cap |= (hwep->ep.maxpacket << __ffs(QH_MAX_PKT)) & QH_MAX_PKT; /* * For ISO-TX, we set mult at QH as the largest value, and use @@ -1326,6 +1326,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req) struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep); struct ci_hw_req *hwreq = container_of(req, struct ci_hw_req, req); unsigned long flags; + struct td_node *node, *tmpnode; if (ep == NULL || req == NULL || hwreq->req.status != -EALREADY || hwep->ep.desc == NULL || list_empty(&hwreq->queue) || @@ -1336,6 +1337,12 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req) hw_ep_flush(hwep->ci, hwep->num, hwep->dir); + list_for_each_entry_safe(node, tmpnode, &hwreq->tds, td) { + dma_pool_free(hwep->td_pool, node->ptr, node->dma); + list_del(&node->td); + kfree(node); + } + /* pop request */ list_del_init(&hwreq->queue); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 900f7ff805ee..331f06a91cc3 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -122,13 +122,23 @@ static void acm_release_minor(struct acm *acm) static int acm_ctrl_msg(struct acm *acm, int request, int value, void *buf, int len) { - int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0), + int retval; + + retval = usb_autopm_get_interface(acm->control); + if (retval) + return retval; + + retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0), request, USB_RT_ACM, value, acm->control->altsetting[0].desc.bInterfaceNumber, buf, len, 5000); + dev_dbg(&acm->control->dev, "%s - rq 0x%02x, val %#x, len %#x, result %d\n", __func__, request, value, len, retval); + + usb_autopm_put_interface(acm->control); + return retval < 0 ? retval : 0; } @@ -496,6 +506,7 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) { struct acm *acm = container_of(port, struct acm, port); int retval = -ENODEV; + int i; dev_dbg(&acm->control->dev, "%s\n", __func__); @@ -544,6 +555,8 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) return 0; error_submit_read_urbs: + for (i = 0; i < acm->rx_buflimit; i++) + usb_kill_urb(acm->read_urbs[i]); acm->ctrlout = 0; acm_set_control(acm, acm->ctrlout); error_set_control: @@ -571,21 +584,35 @@ static void acm_port_destruct(struct tty_port *port) static void acm_port_shutdown(struct tty_port *port) { struct acm *acm = container_of(port, struct acm, port); + struct urb *urb; + struct acm_wb *wb; int i; + int pm_err; dev_dbg(&acm->control->dev, "%s\n", __func__); mutex_lock(&acm->mutex); if (!acm->disconnected) { - usb_autopm_get_interface(acm->control); + pm_err = usb_autopm_get_interface(acm->control); acm_set_control(acm, acm->ctrlout = 0); + + for (;;) { + urb = usb_get_from_anchor(&acm->delayed); + if (!urb) + break; + wb = urb->context; + wb->use = 0; + usb_autopm_put_interface_async(acm->control); + } + usb_kill_urb(acm->ctrlurb); for (i = 0; i < ACM_NW; i++) usb_kill_urb(acm->wb[i].urb); for (i = 0; i < acm->rx_buflimit; i++) usb_kill_urb(acm->read_urbs[i]); acm->control->needs_remote_wakeup = 0; - usb_autopm_put_interface(acm->control); + if (!pm_err) + usb_autopm_put_interface(acm->control); } mutex_unlock(&acm->mutex); } @@ -644,14 +671,17 @@ static int acm_tty_write(struct tty_struct *tty, memcpy(wb->buf, buf, count); wb->len = count; - usb_autopm_get_interface_async(acm->control); + stat = usb_autopm_get_interface_async(acm->control); + if (stat) { + wb->use = 0; + spin_unlock_irqrestore(&acm->write_lock, flags); + return stat; + } + if (acm->susp_count) { - if (!acm->delayed_wb) - acm->delayed_wb = wb; - else - usb_autopm_put_interface_async(acm->control); + usb_anchor_urb(wb->urb, &acm->delayed); spin_unlock_irqrestore(&acm->write_lock, flags); - return count; /* A white lie */ + return count; } usb_mark_last_busy(acm->dev); @@ -935,11 +965,12 @@ static void acm_tty_set_termios(struct tty_struct *tty, /* FIXME: Needs to clear unsupported bits in the termios */ acm->clocal = ((termios->c_cflag & CLOCAL) != 0); - if (!newline.dwDTERate) { + if (C_BAUD(tty) == B0) { newline.dwDTERate = acm->line.dwDTERate; newctrl &= ~ACM_CTRL_DTR; - } else + } else if (termios_old && (termios_old->c_cflag & CBAUD) == B0) { newctrl |= ACM_CTRL_DTR; + } if (newctrl != acm->ctrlout) acm_set_control(acm, acm->ctrlout = newctrl); @@ -1267,6 +1298,7 @@ made_compressed_probe: acm->bInterval = epread->bInterval; tty_port_init(&acm->port); acm->port.ops = &acm_port_ops; + init_usb_anchor(&acm->delayed); buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma); if (!buf) { @@ -1512,18 +1544,15 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) struct acm *acm = usb_get_intfdata(intf); int cnt; + spin_lock_irq(&acm->read_lock); + spin_lock(&acm->write_lock); if (PMSG_IS_AUTO(message)) { - int b; - - spin_lock_irq(&acm->write_lock); - b = acm->transmitting; - spin_unlock_irq(&acm->write_lock); - if (b) + if (acm->transmitting) { + spin_unlock(&acm->write_lock); + spin_unlock_irq(&acm->read_lock); return -EBUSY; + } } - - spin_lock_irq(&acm->read_lock); - spin_lock(&acm->write_lock); cnt = acm->susp_count++; spin_unlock(&acm->write_lock); spin_unlock_irq(&acm->read_lock); @@ -1531,8 +1560,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) if (cnt) return 0; - if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) - stop_data_traffic(acm); + stop_data_traffic(acm); return 0; } @@ -1540,29 +1568,24 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) static int acm_resume(struct usb_interface *intf) { struct acm *acm = usb_get_intfdata(intf); - struct acm_wb *wb; + struct urb *urb; int rv = 0; - int cnt; spin_lock_irq(&acm->read_lock); - acm->susp_count -= 1; - cnt = acm->susp_count; - spin_unlock_irq(&acm->read_lock); + spin_lock(&acm->write_lock); - if (cnt) - return 0; + if (--acm->susp_count) + goto out; if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) { - rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO); - - spin_lock_irq(&acm->write_lock); - if (acm->delayed_wb) { - wb = acm->delayed_wb; - acm->delayed_wb = NULL; - spin_unlock_irq(&acm->write_lock); - acm_start_wb(acm, wb); - } else { - spin_unlock_irq(&acm->write_lock); + rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC); + + for (;;) { + urb = usb_get_from_anchor(&acm->delayed); + if (!urb) + break; + + acm_start_wb(acm, urb->context); } /* @@ -1570,12 +1593,14 @@ static int acm_resume(struct usb_interface *intf) * do the write path at all cost */ if (rv < 0) - goto err_out; + goto out; - rv = acm_submit_read_urbs(acm, GFP_NOIO); + rv = acm_submit_read_urbs(acm, GFP_ATOMIC); } +out: + spin_unlock(&acm->write_lock); + spin_unlock_irq(&acm->read_lock); -err_out: return rv; } @@ -1648,17 +1673,32 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0572, 0x1328), /* Shiro / Aztech USB MODEM UM-3100 */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, + { USB_DEVICE(0x2184, 0x001c) }, /* GW Instek AFG-2225 */ { USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */ }, /* Motorola H24 HSPA module: */ { USB_DEVICE(0x22b8, 0x2d91) }, /* modem */ - { USB_DEVICE(0x22b8, 0x2d92) }, /* modem + diagnostics */ - { USB_DEVICE(0x22b8, 0x2d93) }, /* modem + AT port */ - { USB_DEVICE(0x22b8, 0x2d95) }, /* modem + AT port + diagnostics */ - { USB_DEVICE(0x22b8, 0x2d96) }, /* modem + NMEA */ - { USB_DEVICE(0x22b8, 0x2d97) }, /* modem + diagnostics + NMEA */ - { USB_DEVICE(0x22b8, 0x2d99) }, /* modem + AT port + NMEA */ - { USB_DEVICE(0x22b8, 0x2d9a) }, /* modem + AT port + diagnostics + NMEA */ + { USB_DEVICE(0x22b8, 0x2d92), /* modem + diagnostics */ + .driver_info = NO_UNION_NORMAL, /* handle only modem interface */ + }, + { USB_DEVICE(0x22b8, 0x2d93), /* modem + AT port */ + .driver_info = NO_UNION_NORMAL, /* handle only modem interface */ + }, + { USB_DEVICE(0x22b8, 0x2d95), /* modem + AT port + diagnostics */ + .driver_info = NO_UNION_NORMAL, /* handle only modem interface */ + }, + { USB_DEVICE(0x22b8, 0x2d96), /* modem + NMEA */ + .driver_info = NO_UNION_NORMAL, /* handle only modem interface */ + }, + { USB_DEVICE(0x22b8, 0x2d97), /* modem + diagnostics + NMEA */ + .driver_info = NO_UNION_NORMAL, /* handle only modem interface */ + }, + { USB_DEVICE(0x22b8, 0x2d99), /* modem + AT port + NMEA */ + .driver_info = NO_UNION_NORMAL, /* handle only modem interface */ + }, + { USB_DEVICE(0x22b8, 0x2d9a), /* modem + AT port + diagnostics + NMEA */ + .driver_info = NO_UNION_NORMAL, /* handle only modem interface */ + }, { USB_DEVICE(0x0572, 0x1329), /* Hummingbird huc56s (Conexant) */ .driver_info = NO_UNION_NORMAL, /* union descriptor misplaced on diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index e38dc785808f..80826f843e04 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -120,7 +120,7 @@ struct acm { unsigned int throttled:1; /* actually throttled */ unsigned int throttle_req:1; /* throttle requested */ u8 bInterval; - struct acm_wb *delayed_wb; /* write queued for a device about to be woken */ + struct usb_anchor delayed; /* writes queued for a device about to be woken */ }; #define CDC_DATA_INTERFACE_TYPE 0x0a diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 90e18f6fa2bb..9ca77166d37e 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1411,7 +1411,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb, u = (is_in ? URB_DIR_IN : URB_DIR_OUT); if (uurb->flags & USBDEVFS_URB_ISO_ASAP) u |= URB_ISO_ASAP; - if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK) + if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK && is_in) u |= URB_SHORT_NOT_OK; if (uurb->flags & USBDEVFS_URB_NO_FSBR) u |= URB_NO_FSBR; diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index ab90a0156828..39c7cd6ffa4b 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -990,8 +990,7 @@ EXPORT_SYMBOL_GPL(usb_deregister); * it doesn't support pre_reset/post_reset/reset_resume or * because it doesn't support suspend/resume. * - * The caller must hold @intf's device's lock, but not its pm_mutex - * and not @intf->dev.sem. + * The caller must hold @intf's device's lock, but not @intf's lock. */ void usb_forced_unbind_intf(struct usb_interface *intf) { @@ -1004,16 +1003,37 @@ void usb_forced_unbind_intf(struct usb_interface *intf) intf->needs_binding = 1; } +/* + * Unbind drivers for @udev's marked interfaces. These interfaces have + * the needs_binding flag set, for example by usb_resume_interface(). + * + * The caller must hold @udev's device lock. + */ +static void unbind_marked_interfaces(struct usb_device *udev) +{ + struct usb_host_config *config; + int i; + struct usb_interface *intf; + + config = udev->actconfig; + if (config) { + for (i = 0; i < config->desc.bNumInterfaces; ++i) { + intf = config->interface[i]; + if (intf->dev.driver && intf->needs_binding) + usb_forced_unbind_intf(intf); + } + } +} + /* Delayed forced unbinding of a USB interface driver and scan * for rebinding. * - * The caller must hold @intf's device's lock, but not its pm_mutex - * and not @intf->dev.sem. + * The caller must hold @intf's device's lock, but not @intf's lock. * * Note: Rebinds will be skipped if a system sleep transition is in * progress and the PM "complete" callback hasn't occurred yet. */ -void usb_rebind_intf(struct usb_interface *intf) +static void usb_rebind_intf(struct usb_interface *intf) { int rc; @@ -1030,68 +1050,66 @@ void usb_rebind_intf(struct usb_interface *intf) } } -#ifdef CONFIG_PM - -/* Unbind drivers for @udev's interfaces that don't support suspend/resume - * There is no check for reset_resume here because it can be determined - * only during resume whether reset_resume is needed. +/* + * Rebind drivers to @udev's marked interfaces. These interfaces have + * the needs_binding flag set. * * The caller must hold @udev's device lock. */ -static void unbind_no_pm_drivers_interfaces(struct usb_device *udev) +static void rebind_marked_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; - struct usb_driver *drv; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; - - if (intf->dev.driver) { - drv = to_usb_driver(intf->dev.driver); - if (!drv->suspend || !drv->resume) - usb_forced_unbind_intf(intf); - } + if (intf->needs_binding) + usb_rebind_intf(intf); } } } -/* Unbind drivers for @udev's interfaces that failed to support reset-resume. - * These interfaces have the needs_binding flag set by usb_resume_interface(). +/* + * Unbind all of @udev's marked interfaces and then rebind all of them. + * This ordering is necessary because some drivers claim several interfaces + * when they are first probed. * * The caller must hold @udev's device lock. */ -static void unbind_no_reset_resume_drivers_interfaces(struct usb_device *udev) +void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev) { - struct usb_host_config *config; - int i; - struct usb_interface *intf; - - config = udev->actconfig; - if (config) { - for (i = 0; i < config->desc.bNumInterfaces; ++i) { - intf = config->interface[i]; - if (intf->dev.driver && intf->needs_binding) - usb_forced_unbind_intf(intf); - } - } + unbind_marked_interfaces(udev); + rebind_marked_interfaces(udev); } -static void do_rebind_interfaces(struct usb_device *udev) +#ifdef CONFIG_PM + +/* Unbind drivers for @udev's interfaces that don't support suspend/resume + * There is no check for reset_resume here because it can be determined + * only during resume whether reset_resume is needed. + * + * The caller must hold @udev's device lock. + */ +static void unbind_no_pm_drivers_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; + struct usb_driver *drv; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; - if (intf->needs_binding) - usb_rebind_intf(intf); + + if (intf->dev.driver) { + drv = to_usb_driver(intf->dev.driver); + if (!drv->suspend || !drv->resume) + usb_forced_unbind_intf(intf); + } } } } @@ -1420,7 +1438,7 @@ int usb_resume_complete(struct device *dev) * whose needs_binding flag is set */ if (udev->state != USB_STATE_NOTATTACHED) - do_rebind_interfaces(udev); + rebind_marked_interfaces(udev); return 0; } @@ -1442,7 +1460,7 @@ int usb_resume(struct device *dev, pm_message_t msg) pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); - unbind_no_reset_resume_drivers_interfaces(udev); + unbind_marked_interfaces(udev); } /* Avoid PM error messages for devices disconnected while suspended @@ -1783,10 +1801,13 @@ int usb_runtime_suspend(struct device *dev) if (status == -EAGAIN || status == -EBUSY) usb_mark_last_busy(udev); - /* The PM core reacts badly unless the return code is 0, - * -EAGAIN, or -EBUSY, so always return -EBUSY on an error. + /* + * The PM core reacts badly unless the return code is 0, + * -EAGAIN, or -EBUSY, so always return -EBUSY on an error + * (except for root hubs, because they don't suspend through + * an upstream port like other USB devices). */ - if (status != 0) + if (status != 0 && udev->parent) return -EBUSY; return status; } diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index d59d99347d54..1f02e65fe305 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -75,7 +75,7 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd, PCI_SLOT(companion->devfn) != slot) continue; companion_hcd = pci_get_drvdata(companion); - if (!companion_hcd) + if (!companion_hcd || !companion_hcd->self.root_hub) continue; fn(pdev, hcd, companion, companion_hcd); } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 2518c3250750..ef6ec13b6ae5 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2057,6 +2057,8 @@ int usb_alloc_streams(struct usb_interface *interface, return -EINVAL; if (dev->speed != USB_SPEED_SUPER) return -EINVAL; + if (dev->state < USB_STATE_CONFIGURED) + return -ENODEV; /* Streams only apply to bulk endpoints. */ for (i = 0; i < num_eps; i++) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 64ea21971be2..d2bd9d7c8f4b 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -884,6 +884,25 @@ static int hub_usb3_port_disable(struct usb_hub *hub, int port1) if (!hub_is_superspeed(hub->hdev)) return -EINVAL; + ret = hub_port_status(hub, port1, &portstatus, &portchange); + if (ret < 0) + return ret; + + /* + * USB controller Advanced Micro Devices, Inc. [AMD] FCH USB XHCI + * Controller [1022:7814] will have spurious result making the following + * usb 3.0 device hotplugging route to the 2.0 root hub and recognized + * as high-speed device if we set the usb 3.0 port link state to + * Disabled. Since it's already in USB_SS_PORT_LS_RX_DETECT state, we + * check the state here to avoid the bug. + */ + if ((portstatus & USB_PORT_STAT_LINK_STATE) == + USB_SS_PORT_LS_RX_DETECT) { + dev_dbg(&hub->ports[port1 - 1]->dev, + "Not disabling port; link state is RxDetect\n"); + return ret; + } + ret = hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_SS_DISABLED); if (ret) return ret; @@ -1676,11 +1695,28 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id) * - Change autosuspend delay of hub can avoid unnecessary auto * suspend timer for hub, also may decrease power consumption * of USB bus. + * + * - If user has indicated to prevent autosuspend by passing + * usbcore.autosuspend = -1 then keep autosuspend disabled. + */ +#ifdef CONFIG_PM_RUNTIME + if (hdev->dev.power.autosuspend_delay >= 0) + pm_runtime_set_autosuspend_delay(&hdev->dev, 0); +#endif + + /* + * Hubs have proper suspend/resume support, except for root hubs + * where the controller driver doesn't have bus_suspend and + * bus_resume methods. */ - pm_runtime_set_autosuspend_delay(&hdev->dev, 0); + if (hdev->parent) { /* normal device */ + usb_enable_autosuspend(hdev); + } else { /* root hub */ + const struct hc_driver *drv = bus_to_hcd(hdev->bus)->driver; - /* Hubs have proper suspend/resume support. */ - usb_enable_autosuspend(hdev); + if (drv->bus_suspend && drv->bus_resume) + usb_enable_autosuspend(hdev); + } if (hdev->level == MAX_TOPO_LEVEL) { dev_err(&intf->dev, @@ -1912,8 +1948,10 @@ void usb_set_device_state(struct usb_device *udev, || new_state == USB_STATE_SUSPENDED) ; /* No change to wakeup settings */ else if (new_state == USB_STATE_CONFIGURED) - wakeup = udev->actconfig->desc.bmAttributes - & USB_CONFIG_ATT_WAKEUP; + wakeup = (udev->quirks & + USB_QUIRK_IGNORE_REMOTE_WAKEUP) ? 0 : + udev->actconfig->desc.bmAttributes & + USB_CONFIG_ATT_WAKEUP; else wakeup = 0; } @@ -3144,6 +3182,43 @@ static int finish_port_resume(struct usb_device *udev) } /* + * There are some SS USB devices which take longer time for link training. + * XHCI specs 4.19.4 says that when Link training is successful, port + * sets CSC bit to 1. So if SW reads port status before successful link + * training, then it will not find device to be present. + * USB Analyzer log with such buggy devices show that in some cases + * device switch on the RX termination after long delay of host enabling + * the VBUS. In few other cases it has been seen that device fails to + * negotiate link training in first attempt. It has been + * reported till now that few devices take as long as 2000 ms to train + * the link after host enabling its VBUS and termination. Following + * routine implements a 2000 ms timeout for link training. If in a case + * link trains before timeout, loop will exit earlier. + * + * FIXME: If a device was connected before suspend, but was removed + * while system was asleep, then the loop in the following routine will + * only exit at timeout. + * + * This routine should only be called when persist is enabled for a SS + * device. + */ +static int wait_for_ss_port_enable(struct usb_device *udev, + struct usb_hub *hub, int *port1, + u16 *portchange, u16 *portstatus) +{ + int status = 0, delay_ms = 0; + + while (delay_ms < 2000) { + if (status || *portstatus & USB_PORT_STAT_CONNECTION) + break; + msleep(20); + delay_ms += 20; + status = hub_port_status(hub, *port1, portstatus, portchange); + } + return status; +} + +/* * usb_port_resume - re-activate a suspended usb device's upstream port * @udev: device to re-activate, not a root hub * Context: must be able to sleep; device not locked; pm locks held @@ -3245,6 +3320,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) clear_bit(port1, hub->busy_bits); + if (udev->persist_enabled && hub_is_superspeed(hub->hdev)) + status = wait_for_ss_port_enable(udev, hub, &port1, &portchange, + &portstatus); + status = check_port_resume_type(udev, hub, port1, status, portchange, portstatus); if (status == 0) @@ -4299,6 +4378,9 @@ check_highspeed (struct usb_hub *hub, struct usb_device *udev, int port1) struct usb_qualifier_descriptor *qual; int status; + if (udev->quirks & USB_QUIRK_DEVICE_QUALIFIER) + return; + qual = kmalloc (sizeof *qual, GFP_KERNEL); if (qual == NULL) return; @@ -4687,9 +4769,10 @@ static void hub_events(void) hub = list_entry(tmp, struct usb_hub, event_list); kref_get(&hub->kref); + hdev = hub->hdev; + usb_get_dev(hdev); spin_unlock_irq(&hub_event_lock); - hdev = hub->hdev; hub_dev = hub->intfdev; intf = to_usb_interface(hub_dev); dev_dbg(hub_dev, "state %d ports %d chg %04x evt %04x\n", @@ -4902,6 +4985,7 @@ static void hub_events(void) usb_autopm_put_interface(intf); loop_disconnected: usb_unlock_device(hdev); + usb_put_dev(hdev); kref_put(&hub->kref, hub_release); } /* end while (1) */ @@ -5340,10 +5424,11 @@ int usb_reset_device(struct usb_device *udev) else if (cintf->condition == USB_INTERFACE_BOUND) rebind = 1; + if (rebind) + cintf->needs_binding = 1; } - if (ret == 0 && rebind) - usb_rebind_intf(cintf); } + usb_unbind_and_rebind_marked_interfaces(udev); } usb_autosuspend_device(udev); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 739ee8e8bdfd..c85459338991 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -93,6 +93,16 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x04e8, 0x6601), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Elan Touchscreen */ + { USB_DEVICE(0x04f3, 0x0089), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + + { USB_DEVICE(0x04f3, 0x009b), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + + { USB_DEVICE(0x04f3, 0x016f), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + /* Roland SC-8820 */ { USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -160,6 +170,10 @@ static const struct usb_device_id usb_interface_quirk_list[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x046d, USB_CLASS_VIDEO, 1, 0), .driver_info = USB_QUIRK_RESET_RESUME }, + /* ASUS Base Station(T100) */ + { USB_DEVICE(0x0b05, 0x17e0), .driver_info = + USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + { } /* terminating entry must be last */ }; diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index 823857767a16..0923add72b59 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -55,7 +55,7 @@ extern int usb_match_one_id_intf(struct usb_device *dev, extern int usb_match_device(struct usb_device *dev, const struct usb_device_id *id); extern void usb_forced_unbind_intf(struct usb_interface *intf); -extern void usb_rebind_intf(struct usb_interface *intf); +extern void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev); extern int usb_hub_claim_port(struct usb_device *hdev, unsigned port, struct dev_state *owner); diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index a49217ae3533..f074755372a0 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -583,12 +583,6 @@ static int dwc3_remove(struct platform_device *pdev) { struct dwc3 *dwc = platform_get_drvdata(pdev); - usb_phy_set_suspend(dwc->usb2_phy, 1); - usb_phy_set_suspend(dwc->usb3_phy, 1); - - pm_runtime_put_sync(&pdev->dev); - pm_runtime_disable(&pdev->dev); - dwc3_debugfs_exit(dwc); switch (dwc->dr_mode) { @@ -609,8 +603,15 @@ static int dwc3_remove(struct platform_device *pdev) dwc3_event_buffers_cleanup(dwc); dwc3_free_event_buffers(dwc); + + usb_phy_set_suspend(dwc->usb2_phy, 1); + usb_phy_set_suspend(dwc->usb3_phy, 1); + dwc3_core_exit(dwc); + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index f8af8d44af85..546e67a2e4cd 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -815,15 +815,15 @@ struct dwc3_event_depevt { * 12 - VndrDevTstRcved * @reserved15_12: Reserved, not used * @event_info: Information about this event - * @reserved31_24: Reserved, not used + * @reserved31_25: Reserved, not used */ struct dwc3_event_devt { u32 one_bit:1; u32 device_event:7; u32 type:4; u32 reserved15_12:4; - u32 event_info:8; - u32 reserved31_24:8; + u32 event_info:9; + u32 reserved31_25:7; } __packed; /** @@ -856,6 +856,19 @@ union dwc3_event { struct dwc3_event_gevt gevt; }; +/** + * struct dwc3_gadget_ep_cmd_params - representation of endpoint command + * parameters + * @param2: third parameter + * @param1: second parameter + * @param0: first parameter + */ +struct dwc3_gadget_ep_cmd_params { + u32 param2; + u32 param1; + u32 param0; +}; + /* * DWC3 Features to be used as Driver Data */ @@ -881,11 +894,31 @@ static inline void dwc3_host_exit(struct dwc3 *dwc) #if IS_ENABLED(CONFIG_USB_DWC3_GADGET) || IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE) int dwc3_gadget_init(struct dwc3 *dwc); void dwc3_gadget_exit(struct dwc3 *dwc); +int dwc3_gadget_set_test_mode(struct dwc3 *dwc, int mode); +int dwc3_gadget_get_link_state(struct dwc3 *dwc); +int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state); +int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep, + unsigned cmd, struct dwc3_gadget_ep_cmd_params *params); +int dwc3_send_gadget_generic_command(struct dwc3 *dwc, int cmd, u32 param); #else static inline int dwc3_gadget_init(struct dwc3 *dwc) { return 0; } static inline void dwc3_gadget_exit(struct dwc3 *dwc) { } +static inline int dwc3_gadget_set_test_mode(struct dwc3 *dwc, int mode) +{ return 0; } +static inline int dwc3_gadget_get_link_state(struct dwc3 *dwc) +{ return 0; } +static inline int dwc3_gadget_set_link_state(struct dwc3 *dwc, + enum dwc3_link_state state) +{ return 0; } + +static inline int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep, + unsigned cmd, struct dwc3_gadget_ep_cmd_params *params) +{ return 0; } +static inline int dwc3_send_gadget_generic_command(struct dwc3 *dwc, + int cmd, u32 param) +{ return 0; } #endif /* power management interface */ diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index b269dbd47fc4..2a6841c95b64 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -582,9 +582,9 @@ static int dwc3_omap_remove(struct platform_device *pdev) if (omap->extcon_id_dev.edev) extcon_unregister_interest(&omap->extcon_id_dev); dwc3_omap_disable_irqs(omap); + device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core); return 0; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 21a352079bc2..0985ff715c0c 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -251,7 +251,7 @@ static void dwc3_ep0_stall_and_restart(struct dwc3 *dwc) /* stall is always issued on EP0 */ dep = dwc->eps[0]; - __dwc3_gadget_ep_set_halt(dep, 1); + __dwc3_gadget_ep_set_halt(dep, 1, false); dep->flags = DWC3_EP_ENABLED; dwc->delayed_status = false; @@ -461,7 +461,7 @@ static int dwc3_ep0_handle_feature(struct dwc3 *dwc, return -EINVAL; if (set == 0 && (dep->flags & DWC3_EP_WEDGE)) break; - ret = __dwc3_gadget_ep_set_halt(dep, set); + ret = __dwc3_gadget_ep_set_halt(dep, set, true); if (ret) return -EINVAL; break; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 2da0a5a2803a..d90c70c23adb 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -532,12 +532,11 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, if (!usb_endpoint_xfer_isoc(desc)) return 0; - memset(&trb_link, 0, sizeof(trb_link)); - /* Link TRB for ISOC. The HWO bit is never reset */ trb_st_hw = &dep->trb_pool[0]; trb_link = &dep->trb_pool[DWC3_TRB_NUM - 1]; + memset(trb_link, 0, sizeof(*trb_link)); trb_link->bpl = lower_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw)); trb_link->bph = upper_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw)); @@ -586,6 +585,10 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) dwc3_remove_requests(dwc, dep); + /* make sure HW endpoint isn't stalled */ + if (dep->flags & DWC3_EP_STALL) + __dwc3_gadget_ep_set_halt(dep, 0, false); + reg = dwc3_readl(dwc->regs, DWC3_DALEPENA); reg &= ~DWC3_DALEPENA_EP(dep->number); dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); @@ -1182,7 +1185,7 @@ out0: return ret; } -int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value) +int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) { struct dwc3_gadget_ep_cmd_params params; struct dwc3 *dwc = dep->dwc; @@ -1191,6 +1194,14 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value) memset(¶ms, 0x00, sizeof(params)); if (value) { + if (!protocol && ((dep->direction && dep->flags & DWC3_EP_BUSY) || + (!list_empty(&dep->req_queued) || + !list_empty(&dep->request_list)))) { + dev_dbg(dwc->dev, "%s: pending request, cannot halt\n", + dep->name); + return -EAGAIN; + } + ret = dwc3_send_gadget_ep_cmd(dwc, dep->number, DWC3_DEPCMD_SETSTALL, ¶ms); if (ret) @@ -1230,7 +1241,7 @@ static int dwc3_gadget_ep_set_halt(struct usb_ep *ep, int value) goto out; } - ret = __dwc3_gadget_ep_set_halt(dep, value); + ret = __dwc3_gadget_ep_set_halt(dep, value, false); out: spin_unlock_irqrestore(&dwc->lock, flags); @@ -1250,7 +1261,7 @@ static int dwc3_gadget_ep_set_wedge(struct usb_ep *ep) if (dep->number == 0 || dep->number == 1) return dwc3_gadget_ep0_set_halt(ep, 1); else - return dwc3_gadget_ep_set_halt(ep, 1); + return __dwc3_gadget_ep_set_halt(dep, 1, false); } /* -------------------------------------------------------------------------- */ diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index febe1aa7b714..ac62558231be 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -56,12 +56,6 @@ struct dwc3; /* DEPXFERCFG parameter 0 */ #define DWC3_DEPXFERCFG_NUM_XFER_RES(n) ((n) & 0xffff) -struct dwc3_gadget_ep_cmd_params { - u32 param2; - u32 param1; - u32 param0; -}; - /* -------------------------------------------------------------------------- */ #define to_dwc3_request(r) (container_of(r, struct dwc3_request, request)) @@ -85,19 +79,13 @@ static inline void dwc3_gadget_move_request_queued(struct dwc3_request *req) void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req, int status); -int dwc3_gadget_set_test_mode(struct dwc3 *dwc, int mode); -int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state); - void dwc3_ep0_interrupt(struct dwc3 *dwc, const struct dwc3_event_depevt *event); void dwc3_ep0_out_start(struct dwc3 *dwc); int dwc3_gadget_ep0_set_halt(struct usb_ep *ep, int value); int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request, gfp_t gfp_flags); -int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value); -int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep, - unsigned cmd, struct dwc3_gadget_ep_cmd_params *params); -int dwc3_send_gadget_generic_command(struct dwc3 *dwc, int cmd, u32 param); +int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol); /** * dwc3_gadget_ep_get_transfer_index - Gets transfer index from HW diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 8154165aa601..fd13ef0a96c9 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -445,7 +445,7 @@ config USB_GOKU gadget drivers to also be dynamically linked. config USB_EG20T - tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC" + tristate "Intel QUARK X1000/EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC" depends on PCI help This is a USB device driver for EG20T PCH. @@ -466,6 +466,7 @@ config USB_EG20T ML7213/ML7831 is companion chip for Intel Atom E6xx series. ML7213/ML7831 is completely compatible for Intel EG20T PCH. + This driver can be used with Intel's Quark X1000 SOC platform # # LAST -- dummy/emulated controller # diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c index cea8c20a1425..1926925a52a9 100644 --- a/drivers/usb/gadget/at91_udc.c +++ b/drivers/usb/gadget/at91_udc.c @@ -1709,16 +1709,6 @@ static int at91udc_probe(struct platform_device *pdev) return -ENODEV; } - if (pdev->num_resources != 2) { - DBG("invalid num_resources\n"); - return -ENODEV; - } - if ((pdev->resource[0].flags != IORESOURCE_MEM) - || (pdev->resource[1].flags != IORESOURCE_IRQ)) { - DBG("invalid resource type\n"); - return -ENODEV; - } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) return -ENXIO; diff --git a/drivers/usb/gadget/atmel_usba_udc.c b/drivers/usb/gadget/atmel_usba_udc.c index 52771d4c44bc..167843de2d8a 100644 --- a/drivers/usb/gadget/atmel_usba_udc.c +++ b/drivers/usb/gadget/atmel_usba_udc.c @@ -1827,12 +1827,12 @@ static int atmel_usba_stop(struct usb_gadget *gadget, toggle_bias(0); usba_writel(udc, CTRL, USBA_DISABLE_MASK); - udc->driver = NULL; - clk_disable_unprepare(udc->hclk); clk_disable_unprepare(udc->pclk); - DBG(DBG_GADGET, "unregistered driver `%s'\n", driver->driver.name); + DBG(DBG_GADGET, "unregistered driver `%s'\n", udc->driver->driver.name); + + udc->driver = NULL; return 0; } diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c index ab1065afbbd0..3384486c2884 100644 --- a/drivers/usb/gadget/f_acm.c +++ b/drivers/usb/gadget/f_acm.c @@ -430,11 +430,12 @@ static int acm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (acm->notify->driver_data) { VDBG(cdev, "reset acm control interface %d\n", intf); usb_ep_disable(acm->notify); - } else { - VDBG(cdev, "init acm ctrl interface %d\n", intf); + } + + if (!acm->notify->desc) if (config_ep_by_speed(cdev->gadget, f, acm->notify)) return -EINVAL; - } + usb_ep_enable(acm->notify); acm->notify->driver_data = acm; diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index 2b4334394076..afd0a159fe61 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -1227,11 +1227,13 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev) ffs->ep0req->context = ffs; lang = ffs->stringtabs; - for (lang = ffs->stringtabs; *lang; ++lang) { - struct usb_string *str = (*lang)->strings; - int id = first_id; - for (; str->s; ++id, ++str) - str->id = id; + if (lang) { + for (; *lang; ++lang) { + struct usb_string *str = (*lang)->strings; + int id = first_id; + for (; str->s; ++id, ++str) + str->id = id; + } } ffs->gadget = cdev->gadget; @@ -1993,8 +1995,6 @@ static inline struct f_fs_opts *ffs_do_functionfs_bind(struct usb_function *f, func->conf = c; func->gadget = c->cdev->gadget; - ffs_data_get(func->ffs); - /* * in drivers/usb/gadget/configfs.c:configfs_composite_bind() * configurations are bound in sequence with list_for_each_entry, diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index b94c049ab0d0..4ac9e9928d67 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -1504,7 +1504,7 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) } break; -#ifndef CONFIG_USB_GADGET_PXA25X +#ifndef CONFIG_USB_PXA25X /* PXA automagically handles this request too */ case USB_REQ_GET_CONFIGURATION: if (ctrl->bRequestType != 0x80) diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c index eb8c3bedb57a..460d953c91b6 100644 --- a/drivers/usb/gadget/pch_udc.c +++ b/drivers/usb/gadget/pch_udc.c @@ -343,6 +343,7 @@ struct pch_vbus_gpio_data { * @setup_data: Received setup data * @phys_addr: of device memory * @base_addr: for mapped device memory + * @bar: Indicates which PCI BAR for USB regs * @irq: IRQ line for the device * @cfg_data: current cfg, intf, and alt in use * @vbus_gpio: GPIO informaton for detecting VBUS @@ -370,14 +371,17 @@ struct pch_udc_dev { struct usb_ctrlrequest setup_data; unsigned long phys_addr; void __iomem *base_addr; + unsigned bar; unsigned irq; struct pch_udc_cfg_data cfg_data; struct pch_vbus_gpio_data vbus_gpio; }; #define to_pch_udc(g) (container_of((g), struct pch_udc_dev, gadget)) +#define PCH_UDC_PCI_BAR_QUARK_X1000 0 #define PCH_UDC_PCI_BAR 1 #define PCI_DEVICE_ID_INTEL_EG20T_UDC 0x8808 +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC 0x0939 #define PCI_VENDOR_ID_ROHM 0x10DB #define PCI_DEVICE_ID_ML7213_IOH_UDC 0x801D #define PCI_DEVICE_ID_ML7831_IOH_UDC 0x8808 @@ -3076,7 +3080,7 @@ static void pch_udc_remove(struct pci_dev *pdev) iounmap(dev->base_addr); if (dev->mem_region) release_mem_region(dev->phys_addr, - pci_resource_len(pdev, PCH_UDC_PCI_BAR)); + pci_resource_len(pdev, dev->bar)); if (dev->active) pci_disable_device(pdev); kfree(dev); @@ -3144,9 +3148,15 @@ static int pch_udc_probe(struct pci_dev *pdev, dev->active = 1; pci_set_drvdata(pdev, dev); + /* Determine BAR based on PCI ID */ + if (id->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC) + dev->bar = PCH_UDC_PCI_BAR_QUARK_X1000; + else + dev->bar = PCH_UDC_PCI_BAR; + /* PCI resource allocation */ - resource = pci_resource_start(pdev, 1); - len = pci_resource_len(pdev, 1); + resource = pci_resource_start(pdev, dev->bar); + len = pci_resource_len(pdev, dev->bar); if (!request_mem_region(resource, len, KBUILD_MODNAME)) { dev_err(&pdev->dev, "%s: pci device used already\n", __func__); @@ -3212,6 +3222,12 @@ finished: static const struct pci_device_id pch_udc_pcidev_id[] = { { + PCI_DEVICE(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC), + .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, + .class_mask = 0xffffffff, + }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EG20T_UDC), .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, .class_mask = 0xffffffff, diff --git a/drivers/usb/gadget/tcm_usb_gadget.c b/drivers/usb/gadget/tcm_usb_gadget.c index 0f8aad78b54f..460c266b8e24 100644 --- a/drivers/usb/gadget/tcm_usb_gadget.c +++ b/drivers/usb/gadget/tcm_usb_gadget.c @@ -1613,7 +1613,7 @@ static struct se_wwn *usbg_make_tport( return ERR_PTR(-ENOMEM); } tport->tport_wwpn = wwpn; - snprintf(tport->tport_name, sizeof(tport->tport_name), wnn_name); + snprintf(tport->tport_name, sizeof(tport->tport_name), "%s", wnn_name); return &tport->tport_wwn; } diff --git a/drivers/usb/gadget/u_serial.c b/drivers/usb/gadget/u_serial.c index b369292d4b90..ad0aca812002 100644 --- a/drivers/usb/gadget/u_serial.c +++ b/drivers/usb/gadget/u_serial.c @@ -549,8 +549,8 @@ static void gs_rx_push(unsigned long _port) port->read_started--; } - /* Push from tty to ldisc; without low_latency set this is handled by - * a workqueue, so we won't get callbacks and can hold port_lock + /* Push from tty to ldisc; this is handled by a workqueue, + * so we won't get callbacks and can hold port_lock */ if (do_push) tty_flip_buffer_push(&port->port); diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c index 27768a7d986a..9ce0b135c8c8 100644 --- a/drivers/usb/gadget/udc-core.c +++ b/drivers/usb/gadget/udc-core.c @@ -456,6 +456,11 @@ static ssize_t usb_udc_softconn_store(struct device *dev, { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + if (!udc->driver) { + dev_err(dev, "soft-connect without a gadget driver\n"); + return -EOPNOTSUPP; + } + if (sysfs_streq(buf, "connect")) { usb_gadget_udc_start(udc->gadget, udc->driver); usb_gadget_connect(udc->gadget); diff --git a/drivers/usb/gadget/zero.c b/drivers/usb/gadget/zero.c index 9f170c53e3d9..134f354ede62 100644 --- a/drivers/usb/gadget/zero.c +++ b/drivers/usb/gadget/zero.c @@ -300,7 +300,7 @@ static int __init zero_bind(struct usb_composite_dev *cdev) ss_opts->isoc_interval = gzero_options.isoc_interval; ss_opts->isoc_maxpacket = gzero_options.isoc_maxpacket; ss_opts->isoc_mult = gzero_options.isoc_mult; - ss_opts->isoc_maxburst = gzero_options.isoc_maxpacket; + ss_opts->isoc_maxburst = gzero_options.isoc_maxburst; ss_opts->bulk_buflen = gzero_options.bulk_buflen; func_ss = usb_get_function(func_inst_ss); diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 6f2c8d3899d2..cf2734b532a7 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -248,7 +248,8 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd, break; } - if (pdata->have_sysif_regs && pdata->controller_ver && + if (pdata->have_sysif_regs && + pdata->controller_ver > FSL_USB_VER_1_6 && (phy_mode == FSL_USB2_PHY_ULPI)) { /* check PHY_CLK_VALID to get phy clk valid */ if (!(spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) & diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 81cda09b47e3..488a30836c36 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -965,8 +965,6 @@ rescan: } qh->exception = 1; - if (ehci->rh_state < EHCI_RH_RUNNING) - qh->qh_state = QH_STATE_IDLE; switch (qh->qh_state) { case QH_STATE_LINKED: WARN_ON(!list_empty(&qh->qtd_list)); diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index 7ae0c4d51741..7d6f64c447bf 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -1239,7 +1239,7 @@ static int ehci_hub_control ( if (selector == EHSET_TEST_SINGLE_STEP_SET_FEATURE) { spin_unlock_irqrestore(&ehci->lock, flags); retval = ehset_single_step_set_feature(hcd, - wIndex); + wIndex + 1); spin_lock_irqsave(&ehci->lock, flags); break; } diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 3e86bf4371b3..ca7b964124af 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -35,6 +35,21 @@ static const char hcd_name[] = "ehci-pci"; #define PCI_DEVICE_ID_INTEL_CE4100_USB 0x2e70 /*-------------------------------------------------------------------------*/ +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC 0x0939 +static inline bool is_intel_quark_x1000(struct pci_dev *pdev) +{ + return pdev->vendor == PCI_VENDOR_ID_INTEL && + pdev->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC; +} + +/* + * 0x84 is the offset of in/out threshold register, + * and it is the same offset as the register of 'hostpc'. + */ +#define intel_quark_x1000_insnreg01 hostpc + +/* Maximum usable threshold value is 0x7f dwords for both IN and OUT */ +#define INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD 0x007f007f /* called after powerup, by probe or system-pm "wakeup" */ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev) @@ -50,6 +65,16 @@ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev) if (!retval) ehci_dbg(ehci, "MWI active\n"); + /* Reset the threshold limit */ + if (is_intel_quark_x1000(pdev)) { + /* + * For the Intel QUARK X1000, raise the I/O threshold to the + * maximum usable value in order to improve performance. + */ + ehci_writel(ehci, INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD, + ehci->regs->intel_quark_x1000_insnreg01); + } + return 0; } diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c index af28b748e87a..633dbea28f30 100644 --- a/drivers/usb/host/ehci-tegra.c +++ b/drivers/usb/host/ehci-tegra.c @@ -513,8 +513,31 @@ static struct platform_driver tegra_ehci_driver = { } }; +static int tegra_ehci_reset(struct usb_hcd *hcd) +{ + struct ehci_hcd *ehci = hcd_to_ehci(hcd); + int retval; + int txfifothresh; + + retval = ehci_setup(hcd); + if (retval) + return retval; + + /* + * We should really pull this value out of tegra_ehci_soc_config, but + * to avoid needing access to it, make use of the fact that Tegra20 is + * the only one so far that needs a value of 10, and Tegra20 is the + * only one which doesn't set has_hostpc. + */ + txfifothresh = ehci->has_hostpc ? 0x10 : 10; + ehci_writel(ehci, txfifothresh << 16, &ehci->regs->txfill_tuning); + + return 0; +} + static const struct ehci_driver_overrides tegra_overrides __initconst = { .extra_priv_size = sizeof(struct tegra_ehci_hcd), + .reset = tegra_ehci_reset, }; static int __init ehci_tegra_init(void) diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c index 45032e933e18..04f2186939d2 100644 --- a/drivers/usb/host/ohci-dbg.c +++ b/drivers/usb/host/ohci-dbg.c @@ -236,7 +236,7 @@ ohci_dump_roothub ( } } -static void ohci_dump (struct ohci_hcd *controller, int verbose) +static void ohci_dump(struct ohci_hcd *controller) { ohci_dbg (controller, "OHCI controller state\n"); @@ -464,15 +464,16 @@ show_list (struct ohci_hcd *ohci, char *buf, size_t count, struct ed *ed) static ssize_t fill_async_buffer(struct debug_buffer *buf) { struct ohci_hcd *ohci; - size_t temp; + size_t temp, size; unsigned long flags; ohci = buf->ohci; + size = PAGE_SIZE; /* display control and bulk lists together, for simplicity */ spin_lock_irqsave (&ohci->lock, flags); - temp = show_list(ohci, buf->page, buf->count, ohci->ed_controltail); - temp += show_list(ohci, buf->page + temp, buf->count - temp, + temp = show_list(ohci, buf->page, size, ohci->ed_controltail); + temp += show_list(ohci, buf->page + temp, size - temp, ohci->ed_bulktail); spin_unlock_irqrestore (&ohci->lock, flags); diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 3586460fb2a1..34fc86ccb591 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -76,8 +76,8 @@ static const char hcd_name [] = "ohci_hcd"; #include "ohci.h" #include "pci-quirks.h" -static void ohci_dump (struct ohci_hcd *ohci, int verbose); -static void ohci_stop (struct usb_hcd *hcd); +static void ohci_dump(struct ohci_hcd *ohci); +static void ohci_stop(struct usb_hcd *hcd); #include "ohci-hub.c" #include "ohci-dbg.c" @@ -744,7 +744,7 @@ retry: ohci->ed_to_check = NULL; } - ohci_dump (ohci, 1); + ohci_dump(ohci); return 0; } @@ -825,7 +825,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) usb_hc_died(hcd); } - ohci_dump (ohci, 1); + ohci_dump(ohci); ohci_usb_reset (ohci); } @@ -925,7 +925,7 @@ static void ohci_stop (struct usb_hcd *hcd) { struct ohci_hcd *ohci = hcd_to_ohci (hcd); - ohci_dump (ohci, 1); + ohci_dump(ohci); if (quirk_nec(ohci)) flush_work(&ohci->nec_work); diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c index c81c8721cc5a..cd871b895013 100644 --- a/drivers/usb/host/ohci-hub.c +++ b/drivers/usb/host/ohci-hub.c @@ -90,6 +90,24 @@ __acquires(ohci->lock) dl_done_list (ohci); finish_unlinks (ohci, ohci_frame_no(ohci)); + /* + * Some controllers don't handle "global" suspend properly if + * there are unsuspended ports. For these controllers, put all + * the enabled ports into suspend before suspending the root hub. + */ + if (ohci->flags & OHCI_QUIRK_GLOBAL_SUSPEND) { + __hc32 __iomem *portstat = ohci->regs->roothub.portstatus; + int i; + unsigned temp; + + for (i = 0; i < ohci->num_ports; (++i, ++portstat)) { + temp = ohci_readl(ohci, portstat); + if ((temp & (RH_PS_PES | RH_PS_PSS)) == + RH_PS_PES) + ohci_writel(ohci, RH_PS_PSS, portstat); + } + } + /* maybe resume can wake root hub */ if (ohci_to_hcd(ohci)->self.root_hub->do_remote_wakeup || autostop) { ohci->hc_control |= OHCI_CTRL_RWE; diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c index 90879e9ccbec..bb1509675727 100644 --- a/drivers/usb/host/ohci-pci.c +++ b/drivers/usb/host/ohci-pci.c @@ -160,6 +160,7 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd) ohci_dbg(ohci, "enabled AMD prefetch quirk\n"); } + ohci->flags |= OHCI_QUIRK_GLOBAL_SUSPEND; return 0; } diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c index d4253e319428..a8bde5b8cbdd 100644 --- a/drivers/usb/host/ohci-q.c +++ b/drivers/usb/host/ohci-q.c @@ -311,8 +311,7 @@ static void periodic_unlink (struct ohci_hcd *ohci, struct ed *ed) * - ED_OPER: when there's any request queued, the ED gets rescheduled * immediately. HC should be working on them. * - * - ED_IDLE: when there's no TD queue. there's no reason for the HC - * to care about this ED; safe to disable the endpoint. + * - ED_IDLE: when there's no TD queue or the HC isn't running. * * When finish_unlinks() runs later, after SOF interrupt, it will often * complete one or more URB unlinks before making that state change. @@ -926,6 +925,10 @@ rescan_all: int completed, modified; __hc32 *prev; + /* Is this ED already invisible to the hardware? */ + if (ed->state == ED_IDLE) + goto ed_idle; + /* only take off EDs that the HC isn't using, accounting for * frame counter wraps and EDs with partially retired TDs */ @@ -955,12 +958,20 @@ skip_ed: } } + /* ED's now officially unlinked, hc doesn't see */ + ed->state = ED_IDLE; + if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT) + ohci->eds_scheduled--; + ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H); + ed->hwNextED = 0; + wmb(); + ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE); +ed_idle: + /* reentrancy: if we drop the schedule lock, someone might * have modified this list. normally it's just prepending * entries (which we'd ignore), but paranoia won't hurt. */ - *last = ed->ed_next; - ed->ed_next = NULL; modified = 0; /* unlink urbs as requested, but rescan the list after @@ -1018,19 +1029,20 @@ rescan_this: if (completed && !list_empty (&ed->td_list)) goto rescan_this; - /* ED's now officially unlinked, hc doesn't see */ - ed->state = ED_IDLE; - if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT) - ohci->eds_scheduled--; - ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H); - ed->hwNextED = 0; - wmb (); - ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE); - - /* but if there's work queued, reschedule */ - if (!list_empty (&ed->td_list)) { - if (ohci->rh_state == OHCI_RH_RUNNING) - ed_schedule (ohci, ed); + /* + * If no TDs are queued, take ED off the ed_rm_list. + * Otherwise, if the HC is running, reschedule. + * If not, leave it on the list for further dequeues. + */ + if (list_empty(&ed->td_list)) { + *last = ed->ed_next; + ed->ed_next = NULL; + } else if (ohci->rh_state == OHCI_RH_RUNNING) { + *last = ed->ed_next; + ed->ed_next = NULL; + ed_schedule(ohci, ed); + } else { + last = &ed->ed_next; } if (modified) diff --git a/drivers/usb/host/ohci.h b/drivers/usb/host/ohci.h index 9250cada13f0..4550ce05af7f 100644 --- a/drivers/usb/host/ohci.h +++ b/drivers/usb/host/ohci.h @@ -405,6 +405,8 @@ struct ohci_hcd { #define OHCI_QUIRK_HUB_POWER 0x100 /* distrust firmware power/oc setup */ #define OHCI_QUIRK_AMD_PLL 0x200 /* AMD PLL quirk*/ #define OHCI_QUIRK_AMD_PREFETCH 0x400 /* pre-fetch for ISO transfer */ +#define OHCI_QUIRK_GLOBAL_SUSPEND 0x800 /* must suspend ports */ + // there are also chip quirks/bugs in init logic struct work_struct nec_work; /* Worker for NEC quirk */ diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 00661d305143..2f3acebb577a 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -656,6 +656,14 @@ static const struct dmi_system_id ehci_dmi_nohandoff_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"), }, }, + { + /* HASEE E200 */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"), + DMI_MATCH(DMI_BOARD_NAME, "E210"), + DMI_MATCH(DMI_BIOS_VERSION, "6.00"), + }, + }, { } }; @@ -665,9 +673,14 @@ static void ehci_bios_handoff(struct pci_dev *pdev, { int try_handoff = 1, tried_handoff = 0; - /* The Pegatron Lucid tablet sporadically waits for 98 seconds trying - * the handoff on its unused controller. Skip it. */ - if (pdev->vendor == 0x8086 && pdev->device == 0x283a) { + /* + * The Pegatron Lucid tablet sporadically waits for 98 seconds trying + * the handoff on its unused controller. Skip it. + * + * The HASEE E200 hangs when the semaphore is set (bugzilla #77021). + */ + if (pdev->vendor == 0x8086 && (pdev->device == 0x283a || + pdev->device == 0x27cc)) { if (dmi_check_system(ehci_dmi_nohandoff_table)) try_handoff = 0; } @@ -847,6 +860,13 @@ void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev) bool ehci_found = false; struct pci_dev *companion = NULL; + /* Sony VAIO t-series with subsystem device ID 90a8 is not capable of + * switching ports from EHCI to xHCI + */ + if (xhci_pdev->subsystem_vendor == PCI_VENDOR_ID_SONY && + xhci_pdev->subsystem_device == 0x90a8) + return; + /* make sure an intel EHCI controller exists */ for_each_pci_dev(companion) { if (companion->class == PCI_CLASS_SERIAL_USB_EHCI && diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 9992fbfec85f..93fe089cd51a 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -470,7 +470,8 @@ static void xhci_hub_report_usb2_link_state(u32 *status, u32 status_reg) } /* Updates Link Status for super Speed port */ -static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg) +static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci, + u32 *status, u32 status_reg) { u32 pls = status_reg & PORT_PLS_MASK; @@ -509,7 +510,8 @@ static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg) * in which sometimes the port enters compliance mode * caused by a delay on the host-device negotiation. */ - if (pls == USB_SS_PORT_LS_COMP_MOD) + if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) && + (pls == USB_SS_PORT_LS_COMP_MOD)) pls |= USB_PORT_STAT_CONNECTION; } @@ -668,7 +670,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, } /* Update Port Link State */ if (hcd->speed == HCD_USB3) { - xhci_hub_report_usb3_link_state(&status, raw_port_status); + xhci_hub_report_usb3_link_state(xhci, &status, raw_port_status); /* * Verify if all USB3 Ports Have entered U0 already. * Delete Compliance Mode Timer if so. diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index bce4391a0e7d..9bce4f0e99be 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1722,6 +1722,16 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) kfree(cur_cd); } + num_ports = HCS_MAX_PORTS(xhci->hcs_params1); + for (i = 0; i < num_ports && xhci->rh_bw; i++) { + struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table; + for (j = 0; j < XHCI_MAX_INTERVAL; j++) { + struct list_head *ep = &bwt->interval_bw[j].endpoints; + while (!list_empty(ep)) + list_del_init(ep->next); + } + } + for (i = 1; i < MAX_HC_SLOTS; ++i) xhci_free_virt_device(xhci, i); @@ -1757,16 +1767,6 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) if (!xhci->rh_bw) goto no_bw; - num_ports = HCS_MAX_PORTS(xhci->hcs_params1); - for (i = 0; i < num_ports; i++) { - struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table; - for (j = 0; j < XHCI_MAX_INTERVAL; j++) { - struct list_head *ep = &bwt->interval_bw[j].endpoints; - while (!list_empty(ep)) - list_del_init(ep->next); - } - } - for (i = 0; i < num_ports; i++) { struct xhci_tt_bw_info *tt, *n; list_for_each_entry_safe(tt, n, &xhci->rh_bw[i].tts, tt_list) { diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 04f986d9234f..75cb1ff9d26b 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -101,6 +101,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) /* AMD PLL quirk */ if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info()) xhci->quirks |= XHCI_AMD_PLL_FIX; + + if (pdev->vendor == PCI_VENDOR_ID_AMD) + xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; @@ -134,6 +138,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) */ if (pdev->subsystem_vendor == PCI_VENDOR_ID_HP) xhci->quirks |= XHCI_SPURIOUS_WAKEUP; + + xhci->quirks |= XHCI_SPURIOUS_REBOOT; } if (pdev->vendor == PCI_VENDOR_ID_ETRON && pdev->device == PCI_DEVICE_ID_ASROCK_P67) { @@ -143,9 +149,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_TRUST_TX_LENGTH; } if (pdev->vendor == PCI_VENDOR_ID_RENESAS && - pdev->device == 0x0015 && - pdev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG && - pdev->subsystem_device == 0xc0cd) + pdev->device == 0x0015) xhci->quirks |= XHCI_RESET_ON_RESUME; if (pdev->vendor == PCI_VENDOR_ID_VIA) xhci->quirks |= XHCI_RESET_ON_RESUME; @@ -190,6 +194,10 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) struct usb_hcd *hcd; driver = (struct hc_driver *)id->driver_data; + + /* Prevent runtime suspending between USB-2 and USB-3 initialization */ + pm_runtime_get_noresume(&dev->dev); + /* Register the USB 2.0 roothub. * FIXME: USB core must know to register the USB 2.0 roothub first. * This is sort of silly, because we could just set the HCD driver flags @@ -199,7 +207,7 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) retval = usb_hcd_pci_probe(dev, id); if (retval) - return retval; + goto put_runtime_pm; /* USB 2.0 roothub is stored in the PCI device now. */ hcd = dev_get_drvdata(&dev->dev); @@ -228,12 +236,17 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) if (xhci->quirks & XHCI_LPM_SUPPORT) hcd_to_bus(xhci->shared_hcd)->root_hub->lpm_capable = 1; + /* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */ + pm_runtime_put_noidle(&dev->dev); + return 0; put_usb3_hcd: usb_put_hcd(xhci->shared_hcd); dealloc_usb2_hcd: usb_hcd_pci_remove(dev); +put_runtime_pm: + pm_runtime_put_noidle(&dev->dev); return retval; } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 0ed64eb68e48..0e6665a82e88 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -550,6 +550,7 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci, struct xhci_generic_trb *trb; struct xhci_ep_ctx *ep_ctx; dma_addr_t addr; + u64 hw_dequeue; ep_ring = xhci_triad_to_transfer_ring(xhci, slot_id, ep_index, stream_id); @@ -559,56 +560,57 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci, stream_id); return; } - state->new_cycle_state = 0; - xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, - "Finding segment containing stopped TRB."); - state->new_deq_seg = find_trb_seg(cur_td->start_seg, - dev->eps[ep_index].stopped_trb, - &state->new_cycle_state); - if (!state->new_deq_seg) { - WARN_ON(1); - return; - } /* Dig out the cycle state saved by the xHC during the stop ep cmd */ xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "Finding endpoint context"); ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index); - state->new_cycle_state = 0x1 & le64_to_cpu(ep_ctx->deq); + hw_dequeue = le64_to_cpu(ep_ctx->deq); + + /* Find virtual address and segment of hardware dequeue pointer */ + state->new_deq_seg = ep_ring->deq_seg; + state->new_deq_ptr = ep_ring->dequeue; + while (xhci_trb_virt_to_dma(state->new_deq_seg, state->new_deq_ptr) + != (dma_addr_t)(hw_dequeue & ~0xf)) { + next_trb(xhci, ep_ring, &state->new_deq_seg, + &state->new_deq_ptr); + if (state->new_deq_ptr == ep_ring->dequeue) { + WARN_ON(1); + return; + } + } + /* + * Find cycle state for last_trb, starting at old cycle state of + * hw_dequeue. If there is only one segment ring, find_trb_seg() will + * return immediately and cannot toggle the cycle state if this search + * wraps around, so add one more toggle manually in that case. + */ + state->new_cycle_state = hw_dequeue & 0x1; + if (ep_ring->first_seg == ep_ring->first_seg->next && + cur_td->last_trb < state->new_deq_ptr) + state->new_cycle_state ^= 0x1; state->new_deq_ptr = cur_td->last_trb; xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "Finding segment containing last TRB in TD."); state->new_deq_seg = find_trb_seg(state->new_deq_seg, - state->new_deq_ptr, - &state->new_cycle_state); + state->new_deq_ptr, &state->new_cycle_state); if (!state->new_deq_seg) { WARN_ON(1); return; } + /* Increment to find next TRB after last_trb. Cycle if appropriate. */ trb = &state->new_deq_ptr->generic; if (TRB_TYPE_LINK_LE32(trb->field[3]) && (trb->field[3] & cpu_to_le32(LINK_TOGGLE))) state->new_cycle_state ^= 0x1; next_trb(xhci, ep_ring, &state->new_deq_seg, &state->new_deq_ptr); - /* - * If there is only one segment in a ring, find_trb_seg()'s while loop - * will not run, and it will return before it has a chance to see if it - * needs to toggle the cycle bit. It can't tell if the stalled transfer - * ended just before the link TRB on a one-segment ring, or if the TD - * wrapped around the top of the ring, because it doesn't have the TD in - * question. Look for the one-segment case where stalled TRB's address - * is greater than the new dequeue pointer address. - */ - if (ep_ring->first_seg == ep_ring->first_seg->next && - state->new_deq_ptr < dev->eps[ep_index].stopped_trb) - state->new_cycle_state ^= 0x1; + /* Don't update the ring cycle state for the producer (us). */ xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "Cycle state = 0x%x", state->new_cycle_state); - /* Don't update the ring cycle state for the producer (us). */ xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "New dequeue segment = %p (virtual)", state->new_deq_seg); @@ -791,7 +793,6 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id, if (list_empty(&ep->cancelled_td_list)) { xhci_stop_watchdog_timer_in_irq(xhci, ep); ep->stopped_td = NULL; - ep->stopped_trb = NULL; ring_doorbell_for_active_rings(xhci, slot_id, ep_index); return; } @@ -859,11 +860,9 @@ remove_finished_td: ring_doorbell_for_active_rings(xhci, slot_id, ep_index); } - /* Clear stopped_td and stopped_trb if endpoint is not halted */ - if (!(ep->ep_state & EP_HALTED)) { + /* Clear stopped_td if endpoint is not halted */ + if (!(ep->ep_state & EP_HALTED)) ep->stopped_td = NULL; - ep->stopped_trb = NULL; - } /* * Drop the lock and complete the URBs in the cancelled TD list. @@ -1579,8 +1578,11 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, xhci_handle_cmd_reset_ep(xhci, slot_id, cmd_trb, cmd_comp_code); break; case TRB_RESET_DEV: - WARN_ON(slot_id != TRB_TO_SLOT_ID( - le32_to_cpu(cmd_trb->generic.field[3]))); + /* SLOT_ID field in reset device cmd completion event TRB is 0. + * Use the SLOT_ID from the command TRB instead (xhci 4.6.11) + */ + slot_id = TRB_TO_SLOT_ID( + le32_to_cpu(cmd_trb->generic.field[3])); xhci_handle_cmd_reset_dev(xhci, slot_id, event); break; case TRB_NEC_GET_FW: @@ -1908,14 +1910,12 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, struct xhci_virt_ep *ep = &xhci->devs[slot_id]->eps[ep_index]; ep->ep_state |= EP_HALTED; ep->stopped_td = td; - ep->stopped_trb = event_trb; ep->stopped_stream = stream_id; xhci_queue_reset_ep(xhci, slot_id, ep_index); xhci_cleanup_stalled_ring(xhci, td->urb->dev, ep_index); ep->stopped_td = NULL; - ep->stopped_trb = NULL; ep->stopped_stream = 0; xhci_ring_cmd_db(xhci); @@ -1997,7 +1997,6 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, * the ring dequeue pointer or take this TD off any lists yet. */ ep->stopped_td = td; - ep->stopped_trb = event_trb; return 0; } else { if (trb_comp_code == COMP_STALL) { @@ -2009,7 +2008,6 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, * USB class driver clear the stall later. */ ep->stopped_td = td; - ep->stopped_trb = event_trb; ep->stopped_stream = ep_ring->stream_id; } else if (xhci_requires_manual_halt_cleanup(xhci, ep_ctx, trb_comp_code)) { @@ -2614,7 +2612,8 @@ static int handle_tx_event(struct xhci_hcd *xhci, * last TRB of the previous TD. The command completion handle * will take care the rest. */ - if (!event_seg && trb_comp_code == COMP_STOP_INVAL) { + if (!event_seg && (trb_comp_code == COMP_STOP || + trb_comp_code == COMP_STOP_INVAL)) { ret = 0; goto cleanup; } @@ -2626,7 +2625,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, * successful event after a short transfer. * Ignore it. */ - if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && + if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && ep_ring->last_td_was_short) { ep_ring->last_td_was_short = false; ret = 0; @@ -3668,7 +3667,7 @@ static unsigned int xhci_get_burst_count(struct xhci_hcd *xhci, return 0; max_burst = urb->ep->ss_ep_comp.bMaxBurst; - return roundup(total_packet_count, max_burst + 1) - 1; + return DIV_ROUND_UP(total_packet_count, max_burst + 1) - 1; } /* diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 924a6ccdb622..82b563fc4fd6 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -404,16 +404,16 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd) #else -static int xhci_try_enable_msi(struct usb_hcd *hcd) +static inline int xhci_try_enable_msi(struct usb_hcd *hcd) { return 0; } -static void xhci_cleanup_msix(struct xhci_hcd *xhci) +static inline void xhci_cleanup_msix(struct xhci_hcd *xhci) { } -static void xhci_msix_sync_irqs(struct xhci_hcd *xhci) +static inline void xhci_msix_sync_irqs(struct xhci_hcd *xhci) { } @@ -928,7 +928,7 @@ int xhci_suspend(struct xhci_hcd *xhci) */ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) { - u32 command, temp = 0; + u32 command, temp = 0, status; struct usb_hcd *hcd = xhci_to_hcd(xhci); struct usb_hcd *secondary_hcd; int retval = 0; @@ -1046,8 +1046,12 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) done: if (retval == 0) { - usb_hcd_resume_root_hub(hcd); - usb_hcd_resume_root_hub(xhci->shared_hcd); + /* Resume root hubs only when have pending events. */ + status = readl(&xhci->op_regs->status); + if (status & STS_EINT) { + usb_hcd_resume_root_hub(hcd); + usb_hcd_resume_root_hub(xhci->shared_hcd); + } } /* @@ -2933,7 +2937,6 @@ void xhci_endpoint_reset(struct usb_hcd *hcd, xhci_ring_cmd_db(xhci); } virt_ep->stopped_td = NULL; - virt_ep->stopped_trb = NULL; virt_ep->stopped_stream = 0; spin_unlock_irqrestore(&xhci->lock, flags); @@ -3925,13 +3928,21 @@ static int __maybe_unused xhci_change_max_exit_latency(struct xhci_hcd *xhci, int ret; spin_lock_irqsave(&xhci->lock, flags); - if (max_exit_latency == xhci->devs[udev->slot_id]->current_mel) { + + virt_dev = xhci->devs[udev->slot_id]; + + /* + * virt_dev might not exists yet if xHC resumed from hibernate (S4) and + * xHC was re-initialized. Exit latency will be set later after + * hub_port_finish_reset() is done and xhci->devs[] are re-allocated + */ + + if (!virt_dev || max_exit_latency == virt_dev->current_mel) { spin_unlock_irqrestore(&xhci->lock, flags); return 0; } /* Attempt to issue an Evaluate Context command to change the MEL. */ - virt_dev = xhci->devs[udev->slot_id]; command = xhci->lpm_command; ctrl_ctx = xhci_get_input_control_ctx(xhci, command->in_ctx); if (!ctrl_ctx) { diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 58ed9d088e63..8faef64371c6 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -864,8 +864,6 @@ struct xhci_virt_ep { #define EP_GETTING_NO_STREAMS (1 << 5) /* ---- Related to URB cancellation ---- */ struct list_head cancelled_td_list; - /* The TRB that was last reported in a stopped endpoint ring */ - union xhci_trb *stopped_trb; struct xhci_td *stopped_td; unsigned int stopped_stream; /* Watchdog timer for stop endpoint command to cancel URBs */ diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c index de98906f786d..0aef801edbc1 100644 --- a/drivers/usb/misc/sisusbvga/sisusb.c +++ b/drivers/usb/misc/sisusbvga/sisusb.c @@ -3248,6 +3248,7 @@ static const struct usb_device_id sisusb_table[] = { { USB_DEVICE(0x0711, 0x0918) }, { USB_DEVICE(0x0711, 0x0920) }, { USB_DEVICE(0x0711, 0x0950) }, + { USB_DEVICE(0x0711, 0x5200) }, { USB_DEVICE(0x182d, 0x021c) }, { USB_DEVICE(0x182d, 0x0269) }, { } diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index f6568b5e9b06..71dcacbab398 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -7,7 +7,7 @@ #include <linux/moduleparam.h> #include <linux/scatterlist.h> #include <linux/mutex.h> - +#include <linux/timer.h> #include <linux/usb.h> #define SIMPLE_IO_TIMEOUT 10000 /* in milliseconds */ @@ -484,6 +484,14 @@ alloc_sglist(int nents, int max, int vary) return sg; } +static void sg_timeout(unsigned long _req) +{ + struct usb_sg_request *req = (struct usb_sg_request *) _req; + + req->status = -ETIMEDOUT; + usb_sg_cancel(req); +} + static int perform_sglist( struct usbtest_dev *tdev, unsigned iterations, @@ -495,6 +503,9 @@ static int perform_sglist( { struct usb_device *udev = testdev_to_usbdev(tdev); int retval = 0; + struct timer_list sg_timer; + + setup_timer_on_stack(&sg_timer, sg_timeout, (unsigned long) req); while (retval == 0 && iterations-- > 0) { retval = usb_sg_init(req, udev, pipe, @@ -505,7 +516,10 @@ static int perform_sglist( if (retval) break; + mod_timer(&sg_timer, jiffies + + msecs_to_jiffies(SIMPLE_IO_TIMEOUT)); usb_sg_wait(req); + del_timer_sync(&sg_timer); retval = req->status; /* FIXME check resulting data pattern */ @@ -1320,6 +1334,11 @@ static int unlink1(struct usbtest_dev *dev, int pipe, int size, int async) urb->context = &completion; urb->complete = unlink1_callback; + if (usb_pipeout(urb->pipe)) { + simple_fill_buf(urb); + urb->transfer_flags |= URB_ZERO_PACKET; + } + /* keep the endpoint busy. there are lots of hc/hcd-internal * states, and testing should get to all of them over time. * @@ -1450,6 +1469,11 @@ static int unlink_queued(struct usbtest_dev *dev, int pipe, unsigned num, unlink_queued_callback, &ctx); ctx.urbs[i]->transfer_dma = buf_dma; ctx.urbs[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP; + + if (usb_pipeout(ctx.urbs[i]->pipe)) { + simple_fill_buf(ctx.urbs[i]); + ctx.urbs[i]->transfer_flags |= URB_ZERO_PACKET; + } } /* Submit all the URBs and then unlink URBs num - 4 and num - 2. */ diff --git a/drivers/usb/musb/musb_am335x.c b/drivers/usb/musb/musb_am335x.c index d2353781bd2d..1e58ed2361cc 100644 --- a/drivers/usb/musb/musb_am335x.c +++ b/drivers/usb/musb/musb_am335x.c @@ -19,21 +19,6 @@ err: return ret; } -static int of_remove_populated_child(struct device *dev, void *d) -{ - struct platform_device *pdev = to_platform_device(dev); - - of_device_unregister(pdev); - return 0; -} - -static int am335x_child_remove(struct platform_device *pdev) -{ - device_for_each_child(&pdev->dev, NULL, of_remove_populated_child); - pm_runtime_disable(&pdev->dev); - return 0; -} - static const struct of_device_id am335x_child_of_match[] = { { .compatible = "ti,am33xx-usb" }, { }, @@ -42,13 +27,17 @@ MODULE_DEVICE_TABLE(of, am335x_child_of_match); static struct platform_driver am335x_child_driver = { .probe = am335x_child_probe, - .remove = am335x_child_remove, .driver = { .name = "am335x-usb-childs", .of_match_table = am335x_child_of_match, }, }; -module_platform_driver(am335x_child_driver); +static int __init am335x_child_init(void) +{ + return platform_driver_register(&am335x_child_driver); +} +module_init(am335x_child_init); + MODULE_DESCRIPTION("AM33xx child devices"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 239ad0b1ceb6..07576907e2c6 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -438,7 +438,6 @@ void musb_hnp_stop(struct musb *musb) static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb, u8 devctl) { - struct usb_otg *otg = musb->xceiv->otg; irqreturn_t handled = IRQ_NONE; dev_dbg(musb->controller, "<== DevCtl=%02x, int_usb=0x%x\n", devctl, @@ -656,7 +655,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb, break; case OTG_STATE_B_PERIPHERAL: musb_g_suspend(musb); - musb->is_active = otg->gadget->b_hnp_enable; + musb->is_active = musb->g.b_hnp_enable; if (musb->is_active) { musb->xceiv->state = OTG_STATE_B_WAIT_ACON; dev_dbg(musb->controller, "HNP: Setting timer for b_ase0_brst\n"); @@ -672,7 +671,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb, break; case OTG_STATE_A_HOST: musb->xceiv->state = OTG_STATE_A_SUSPEND; - musb->is_active = otg->host->b_hnp_enable; + musb->is_active = musb->hcd->self.b_hnp_enable; break; case OTG_STATE_B_HOST: /* Transition to B_PERIPHERAL, see 6.8.2.6 p 44 */ diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c index f88929609bac..1d29bbfeb9d5 100644 --- a/drivers/usb/musb/musb_cppi41.c +++ b/drivers/usb/musb/musb_cppi41.c @@ -190,7 +190,8 @@ static enum hrtimer_restart cppi41_recheck_tx_req(struct hrtimer *timer) } } - if (!list_empty(&controller->early_tx_list)) { + if (!list_empty(&controller->early_tx_list) && + !hrtimer_is_queued(&controller->early_tx)) { ret = HRTIMER_RESTART; hrtimer_forward_now(&controller->early_tx, ktime_set(0, 150 * NSEC_PER_USEC)); @@ -266,7 +267,7 @@ static void cppi41_dma_callback(void *private_data) } list_add_tail(&cppi41_channel->tx_check, &controller->early_tx_list); - if (!hrtimer_active(&controller->early_tx)) { + if (!hrtimer_is_queued(&controller->early_tx)) { hrtimer_start_range_ns(&controller->early_tx, ktime_set(0, 140 * NSEC_PER_USEC), 40 * NSEC_PER_USEC, diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 7a109eae9b9a..865243e818b7 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -707,6 +707,7 @@ static int dsps_suspend(struct device *dev) struct musb *musb = platform_get_drvdata(glue->musb); void __iomem *mbase = musb->ctrl_base; + del_timer_sync(&glue->timer); glue->context.control = dsps_readl(mbase, wrp->control); glue->context.epintr = dsps_readl(mbase, wrp->epintr_set); glue->context.coreintr = dsps_readl(mbase, wrp->coreintr_set); @@ -732,6 +733,9 @@ static int dsps_resume(struct device *dev) dsps_writel(mbase, wrp->mode, glue->context.mode); dsps_writel(mbase, wrp->tx_mode, glue->context.tx_mode); dsps_writel(mbase, wrp->rx_mode, glue->context.rx_mode); + if (musb->xceiv->state == OTG_STATE_B_IDLE && + musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE) + mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ); return 0; } diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 8aa59a2c5eb2..8e90d327e52b 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -416,6 +416,7 @@ static int omap2430_musb_init(struct musb *musb) omap_musb_set_mailbox(glue); phy_init(musb->phy); + phy_power_on(musb->phy); pm_runtime_put_noidle(musb->controller); return 0; @@ -478,6 +479,7 @@ static int omap2430_musb_exit(struct musb *musb) del_timer_sync(&musb_idle_timer); omap2430_low_level_exit(musb); + phy_power_off(musb->phy); phy_exit(musb->phy); return 0; diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c index c2e45e632723..f202e5088461 100644 --- a/drivers/usb/musb/ux500.c +++ b/drivers/usb/musb/ux500.c @@ -274,7 +274,6 @@ static int ux500_probe(struct platform_device *pdev) musb->dev.parent = &pdev->dev; musb->dev.dma_mask = &pdev->dev.coherent_dma_mask; musb->dev.coherent_dma_mask = pdev->dev.coherent_dma_mask; - musb->dev.of_node = pdev->dev.of_node; glue->dev = &pdev->dev; glue->musb = musb; diff --git a/drivers/usb/phy/phy-am335x-control.c b/drivers/usb/phy/phy-am335x-control.c index d75196ad5f2f..35b6083b7999 100644 --- a/drivers/usb/phy/phy-am335x-control.c +++ b/drivers/usb/phy/phy-am335x-control.c @@ -3,6 +3,7 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/io.h> +#include <linux/delay.h> #include "am35x-phy-control.h" struct am335x_control_usb { @@ -86,6 +87,14 @@ static void am335x_phy_power(struct phy_control *phy_ctrl, u32 id, bool on) } writel(val, usb_ctrl->phy_reg + reg); + + /* + * Give the PHY ~1ms to complete the power up operation. + * Tests have shown unstable behaviour if other USB PHY related + * registers are written too shortly after such a transition. + */ + if (on) + mdelay(1); } static const struct phy_control ctrl_am335x = { diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c index 6e146d723b37..69e49be8866b 100644 --- a/drivers/usb/phy/phy-isp1301-omap.c +++ b/drivers/usb/phy/phy-isp1301-omap.c @@ -1295,7 +1295,7 @@ isp1301_set_host(struct usb_otg *otg, struct usb_bus *host) return isp1301_otg_enable(isp); return 0; -#elif !defined(CONFIG_USB_GADGET_OMAP) +#elif !IS_ENABLED(CONFIG_USB_OMAP) // FIXME update its refcount otg->host = host; diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index bbe4f8e6e8d7..8834b70c868c 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -881,8 +881,8 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, return -ENOMEM; } - tegra_phy->config = devm_kzalloc(&pdev->dev, - sizeof(*tegra_phy->config), GFP_KERNEL); + tegra_phy->config = devm_kzalloc(&pdev->dev, sizeof(*config), + GFP_KERNEL); if (!tegra_phy->config) { dev_err(&pdev->dev, "unable to allocate memory for USB UTMIP config\n"); diff --git a/drivers/usb/phy/phy-ulpi.c b/drivers/usb/phy/phy-ulpi.c index 217339dd7a90..17ea3f271bd8 100644 --- a/drivers/usb/phy/phy-ulpi.c +++ b/drivers/usb/phy/phy-ulpi.c @@ -47,6 +47,8 @@ struct ulpi_info { static struct ulpi_info ulpi_ids[] = { ULPI_INFO(ULPI_ID(0x04cc, 0x1504), "NXP ISP1504"), ULPI_INFO(ULPI_ID(0x0424, 0x0006), "SMSC USB331x"), + ULPI_INFO(ULPI_ID(0x0424, 0x0007), "SMSC USB3320"), + ULPI_INFO(ULPI_ID(0x0451, 0x1507), "TI TUSB1210"), }; static int ulpi_set_otg_flags(struct usb_phy *phy) diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 8afa813d690b..0180eef05656 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -229,6 +229,9 @@ struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index) phy = __usb_find_phy_dev(dev, &phy_bind_list, index); if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) { dev_dbg(dev, "unable to find transceiver\n"); + if (!IS_ERR(phy)) + phy = ERR_PTR(-ENODEV); + goto err0; } diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c index 35a2373cde67..9374bd2aba20 100644 --- a/drivers/usb/serial/bus.c +++ b/drivers/usb/serial/bus.c @@ -97,13 +97,19 @@ static int usb_serial_device_remove(struct device *dev) struct usb_serial_port *port; int retval = 0; int minor; + int autopm_err; port = to_usb_serial_port(dev); if (!port) return -ENODEV; - /* make sure suspend/resume doesn't race against port_remove */ - usb_autopm_get_interface(port->serial->interface); + /* + * Make sure suspend/resume doesn't race against port_remove. + * + * Note that no further runtime PM callbacks will be made if + * autopm_get fails. + */ + autopm_err = usb_autopm_get_interface(port->serial->interface); minor = port->minor; tty_unregister_device(usb_serial_tty_driver, minor); @@ -117,7 +123,9 @@ static int usb_serial_device_remove(struct device *dev) dev_info(dev, "%s converter now disconnected from ttyUSB%d\n", driver->description, minor); - usb_autopm_put_interface(port->serial->interface); + if (!autopm_err) + usb_autopm_put_interface(port->serial->interface); + return retval; } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 95fa1217afdd..3beae723ad3a 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -104,6 +104,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8218) }, /* Lipowsky Industrie Elektronik GmbH, HARP-1 */ { USB_DEVICE(0x10C4, 0x822B) }, /* Modem EDGE(GSM) Comander 2 */ { USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */ + { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */ { USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */ { USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */ { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ @@ -121,6 +122,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */ { USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */ + { USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */ @@ -152,7 +154,10 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ + { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ + { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ { USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */ + { USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */ { USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */ { USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */ { USB_DEVICE(0x1FB9, 0x0100) }, /* Lake Shore Model 121 Current Source */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 44ab12986805..a523adad6380 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -145,12 +145,14 @@ static struct ftdi_sio_quirk ftdi_8u2232c_quirk = { * /sys/bus/usb-serial/drivers/ftdi_sio/new_id and send a patch or report. */ static const struct usb_device_id id_table_combined[] = { + { USB_DEVICE(FTDI_VID, FTDI_BRICK_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ZEITCONTROL_TAGTRACE_MIFARE_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CTI_MINI_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CTI_NANO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_BM_ATOM_NANO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) }, { USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) }, @@ -580,6 +582,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_TAVIR_STK500_PID) }, { USB_DEVICE(FTDI_VID, FTDI_TIAO_UMPA_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID), + .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, /* * ELV devices: */ @@ -671,6 +675,10 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_MTW_PID) }, { USB_DEVICE(FTDI_VID, FTDI_OMNI1509) }, { USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) }, @@ -718,7 +726,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) }, { USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) }, { USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) }, - { USB_DEVICE(TESTO_VID, TESTO_USB_INTERFACE_PID) }, + { USB_DEVICE(TESTO_VID, TESTO_1_PID) }, + { USB_DEVICE(TESTO_VID, TESTO_3_PID) }, { USB_DEVICE(FTDI_VID, FTDI_GAMMA_SCOUT_PID) }, { USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13M_PID) }, { USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13S_PID) }, @@ -735,6 +744,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID), .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, { USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) }, + { USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S03_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_59_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_57A_PID) }, @@ -909,6 +919,45 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) }, /* Cressi Devices */ { USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) }, + /* Brainboxes Devices */ + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_001_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_012_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_023_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_034_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_101_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_1_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_2_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_3_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_4_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_5_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_6_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_7_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_8_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_257_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_1_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_2_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_3_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_4_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_313_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_324_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_1_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_2_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_357_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_1_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_2_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_3_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_1_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_2_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_1_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) }, + /* ekey Devices */ + { USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) }, + /* Infineon Devices */ + { USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) }, + /* GE Healthcare devices */ + { USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) }, { } /* Terminating entry */ }; @@ -1531,14 +1580,17 @@ static void ftdi_set_max_packet_size(struct usb_serial_port *port) struct usb_device *udev = serial->dev; struct usb_interface *interface = serial->interface; - struct usb_endpoint_descriptor *ep_desc = &interface->cur_altsetting->endpoint[1].desc; + struct usb_endpoint_descriptor *ep_desc; unsigned num_endpoints; - int i; + unsigned i; num_endpoints = interface->cur_altsetting->desc.bNumEndpoints; dev_info(&udev->dev, "Number of endpoints %d\n", num_endpoints); + if (!num_endpoints) + return; + /* NOTE: some customers have programmed FT232R/FT245R devices * with an endpoint size of 0 - not good. In this case, we * want to override the endpoint descriptor setting and use a diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index e599fbfcde5f..6786b705ccf6 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -30,6 +30,12 @@ /*** third-party PIDs (using FTDI_VID) ***/ +/* + * Certain versions of the official Windows FTDI driver reprogrammed + * counterfeit FTDI devices to PID 0. Support these devices anyway. + */ +#define FTDI_BRICK_PID 0x0000 + #define FTDI_LUMEL_PD12_PID 0x6002 /* @@ -42,6 +48,8 @@ /* www.candapter.com Ewert Energy Systems CANdapter device */ #define FTDI_CANDAPTER_PID 0x9F80 /* Product Id */ +#define FTDI_BM_ATOM_NANO_PID 0xa559 /* Basic Micro ATOM Nano USB2Serial */ + /* * Texas Instruments XDS100v2 JTAG / BeagleBone A3 * http://processors.wiki.ti.com/index.php/XDS100 @@ -140,12 +148,19 @@ /* * Xsens Technologies BV products (http://www.xsens.com). */ -#define XSENS_CONVERTER_0_PID 0xD388 -#define XSENS_CONVERTER_1_PID 0xD389 +#define XSENS_VID 0x2639 +#define XSENS_AWINDA_STATION_PID 0x0101 +#define XSENS_AWINDA_DONGLE_PID 0x0102 +#define XSENS_MTW_PID 0x0200 /* Xsens MTw */ +#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */ + +/* Xsens devices using FTDI VID */ +#define XSENS_CONVERTER_0_PID 0xD388 /* Xsens USB converter */ +#define XSENS_CONVERTER_1_PID 0xD389 /* Xsens Wireless Receiver */ #define XSENS_CONVERTER_2_PID 0xD38A -#define XSENS_CONVERTER_3_PID 0xD38B -#define XSENS_CONVERTER_4_PID 0xD38C -#define XSENS_CONVERTER_5_PID 0xD38D +#define XSENS_CONVERTER_3_PID 0xD38B /* Xsens USB-serial converter */ +#define XSENS_CONVERTER_4_PID 0xD38C /* Xsens Wireless Receiver */ +#define XSENS_CONVERTER_5_PID 0xD38D /* Xsens Awinda Station */ #define XSENS_CONVERTER_6_PID 0xD38E #define XSENS_CONVERTER_7_PID 0xD38F @@ -538,6 +553,11 @@ */ #define FTDI_TIAO_UMPA_PID 0x8a98 /* TIAO/DIYGADGET USB Multi-Protocol Adapter */ +/* + * NovaTech product ids (FTDI_VID) + */ +#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ + /********************************/ /** third-party VID/PID combos **/ @@ -579,6 +599,12 @@ #define RATOC_PRODUCT_ID_USB60F 0xb020 /* + * Infineon Technologies + */ +#define INFINEON_VID 0x058b +#define INFINEON_TRIBOARD_PID 0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */ + +/* * Acton Research Corp. */ #define ACTON_VID 0x0647 /* Vendor ID */ @@ -793,7 +819,8 @@ * Submitted by Colin Leroy */ #define TESTO_VID 0x128D -#define TESTO_USB_INTERFACE_PID 0x0001 +#define TESTO_1_PID 0x0001 +#define TESTO_3_PID 0x0003 /* * Mobility Electronics products. @@ -820,6 +847,12 @@ #define TELLDUS_TELLSTICK_PID 0x0C30 /* RF control dongle 433 MHz using FT232RL */ /* + * NOVITUS printers + */ +#define NOVITUS_VID 0x1a28 +#define NOVITUS_BONO_E_PID 0x6010 + +/* * RT Systems programming cables for various ham radios */ #define RTSYSTEMS_VID 0x2100 /* Vendor ID */ @@ -1326,3 +1359,51 @@ * Manufacturer: Cressi */ #define FTDI_CRESSI_PID 0x87d0 + +/* + * Brainboxes devices + */ +#define BRAINBOXES_VID 0x05d1 +#define BRAINBOXES_VX_001_PID 0x1001 /* VX-001 ExpressCard 1 Port RS232 */ +#define BRAINBOXES_VX_012_PID 0x1002 /* VX-012 ExpressCard 2 Port RS232 */ +#define BRAINBOXES_VX_023_PID 0x1003 /* VX-023 ExpressCard 1 Port RS422/485 */ +#define BRAINBOXES_VX_034_PID 0x1004 /* VX-034 ExpressCard 2 Port RS422/485 */ +#define BRAINBOXES_US_101_PID 0x1011 /* US-101 1xRS232 */ +#define BRAINBOXES_US_324_PID 0x1013 /* US-324 1xRS422/485 1Mbaud */ +#define BRAINBOXES_US_606_1_PID 0x2001 /* US-606 6 Port RS232 Serial Port 1 and 2 */ +#define BRAINBOXES_US_606_2_PID 0x2002 /* US-606 6 Port RS232 Serial Port 3 and 4 */ +#define BRAINBOXES_US_606_3_PID 0x2003 /* US-606 6 Port RS232 Serial Port 4 and 6 */ +#define BRAINBOXES_US_701_1_PID 0x2011 /* US-701 4xRS232 1Mbaud Port 1 and 2 */ +#define BRAINBOXES_US_701_2_PID 0x2012 /* US-701 4xRS422 1Mbaud Port 3 and 4 */ +#define BRAINBOXES_US_279_1_PID 0x2021 /* US-279 8xRS422 1Mbaud Port 1 and 2 */ +#define BRAINBOXES_US_279_2_PID 0x2022 /* US-279 8xRS422 1Mbaud Port 3 and 4 */ +#define BRAINBOXES_US_279_3_PID 0x2023 /* US-279 8xRS422 1Mbaud Port 5 and 6 */ +#define BRAINBOXES_US_279_4_PID 0x2024 /* US-279 8xRS422 1Mbaud Port 7 and 8 */ +#define BRAINBOXES_US_346_1_PID 0x3011 /* US-346 4xRS422/485 1Mbaud Port 1 and 2 */ +#define BRAINBOXES_US_346_2_PID 0x3012 /* US-346 4xRS422/485 1Mbaud Port 3 and 4 */ +#define BRAINBOXES_US_257_PID 0x5001 /* US-257 2xRS232 1Mbaud */ +#define BRAINBOXES_US_313_PID 0x6001 /* US-313 2xRS422/485 1Mbaud */ +#define BRAINBOXES_US_357_PID 0x7001 /* US_357 1xRS232/422/485 */ +#define BRAINBOXES_US_842_1_PID 0x8001 /* US-842 8xRS422/485 1Mbaud Port 1 and 2 */ +#define BRAINBOXES_US_842_2_PID 0x8002 /* US-842 8xRS422/485 1Mbaud Port 3 and 4 */ +#define BRAINBOXES_US_842_3_PID 0x8003 /* US-842 8xRS422/485 1Mbaud Port 5 and 6 */ +#define BRAINBOXES_US_842_4_PID 0x8004 /* US-842 8xRS422/485 1Mbaud Port 7 and 8 */ +#define BRAINBOXES_US_160_1_PID 0x9001 /* US-160 16xRS232 1Mbaud Port 1 and 2 */ +#define BRAINBOXES_US_160_2_PID 0x9002 /* US-160 16xRS232 1Mbaud Port 3 and 4 */ +#define BRAINBOXES_US_160_3_PID 0x9003 /* US-160 16xRS232 1Mbaud Port 5 and 6 */ +#define BRAINBOXES_US_160_4_PID 0x9004 /* US-160 16xRS232 1Mbaud Port 7 and 8 */ +#define BRAINBOXES_US_160_5_PID 0x9005 /* US-160 16xRS232 1Mbaud Port 9 and 10 */ +#define BRAINBOXES_US_160_6_PID 0x9006 /* US-160 16xRS232 1Mbaud Port 11 and 12 */ +#define BRAINBOXES_US_160_7_PID 0x9007 /* US-160 16xRS232 1Mbaud Port 13 and 14 */ +#define BRAINBOXES_US_160_8_PID 0x9008 /* US-160 16xRS232 1Mbaud Port 15 and 16 */ + +/* + * ekey biometric systems GmbH (http://ekey.net/) + */ +#define FTDI_EKEY_CONV_USB_PID 0xCB08 /* Converter USB */ + +/* + * GE Healthcare devices + */ +#define GE_HEALTHCARE_VID 0x1901 +#define GE_HEALTHCARE_NEMO_TRACKER_PID 0x0015 diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c index a2db5be9c305..c0a42e9e6777 100644 --- a/drivers/usb/serial/io_ti.c +++ b/drivers/usb/serial/io_ti.c @@ -28,6 +28,7 @@ #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/serial.h> +#include <linux/swab.h> #include <linux/kfifo.h> #include <linux/ioctl.h> #include <linux/firmware.h> @@ -280,7 +281,7 @@ static int read_download_mem(struct usb_device *dev, int start_address, { int status = 0; __u8 read_length; - __be16 be_start_address; + u16 be_start_address; dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, length); @@ -296,10 +297,14 @@ static int read_download_mem(struct usb_device *dev, int start_address, if (read_length > 1) { dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, read_length); } - be_start_address = cpu_to_be16(start_address); + /* + * NOTE: Must use swab as wIndex is sent in little-endian + * byte order regardless of host byte order. + */ + be_start_address = swab16((u16)start_address); status = ti_vread_sync(dev, UMPC_MEMORY_READ, (__u16)address_type, - (__force __u16)be_start_address, + be_start_address, buffer, read_length); if (status) { @@ -394,7 +399,7 @@ static int write_i2c_mem(struct edgeport_serial *serial, struct device *dev = &serial->serial->dev->dev; int status = 0; int write_length; - __be16 be_start_address; + u16 be_start_address; /* We can only send a maximum of 1 aligned byte page at a time */ @@ -409,11 +414,16 @@ static int write_i2c_mem(struct edgeport_serial *serial, __func__, start_address, write_length); usb_serial_debug_data(dev, __func__, write_length, buffer); - /* Write first page */ - be_start_address = cpu_to_be16(start_address); + /* + * Write first page. + * + * NOTE: Must use swab as wIndex is sent in little-endian byte order + * regardless of host byte order. + */ + be_start_address = swab16((u16)start_address); status = ti_vsend_sync(serial->serial->dev, UMPC_MEMORY_WRITE, (__u16)address_type, - (__force __u16)be_start_address, + be_start_address, buffer, write_length); if (status) { dev_dbg(dev, "%s - ERROR %d\n", __func__, status); @@ -436,11 +446,16 @@ static int write_i2c_mem(struct edgeport_serial *serial, __func__, start_address, write_length); usb_serial_debug_data(dev, __func__, write_length, buffer); - /* Write next page */ - be_start_address = cpu_to_be16(start_address); + /* + * Write next page. + * + * NOTE: Must use swab as wIndex is sent in little-endian byte + * order regardless of host byte order. + */ + be_start_address = swab16((u16)start_address); status = ti_vsend_sync(serial->serial->dev, UMPC_MEMORY_WRITE, (__u16)address_type, - (__force __u16)be_start_address, + be_start_address, buffer, write_length); if (status) { dev_err(dev, "%s - ERROR %d\n", __func__, status); @@ -585,8 +600,8 @@ static int get_descriptor_addr(struct edgeport_serial *serial, if (rom_desc->Type == desc_type) return start_address; - start_address = start_address + sizeof(struct ti_i2c_desc) - + rom_desc->Size; + start_address = start_address + sizeof(struct ti_i2c_desc) + + le16_to_cpu(rom_desc->Size); } while ((start_address < TI_MAX_I2C_SIZE) && rom_desc->Type); @@ -599,7 +614,7 @@ static int valid_csum(struct ti_i2c_desc *rom_desc, __u8 *buffer) __u16 i; __u8 cs = 0; - for (i = 0; i < rom_desc->Size; i++) + for (i = 0; i < le16_to_cpu(rom_desc->Size); i++) cs = (__u8)(cs + buffer[i]); if (cs != rom_desc->CheckSum) { @@ -650,7 +665,7 @@ static int check_i2c_image(struct edgeport_serial *serial) break; if ((start_address + sizeof(struct ti_i2c_desc) + - rom_desc->Size) > TI_MAX_I2C_SIZE) { + le16_to_cpu(rom_desc->Size)) > TI_MAX_I2C_SIZE) { status = -ENODEV; dev_dbg(dev, "%s - structure too big, erroring out.\n", __func__); break; @@ -665,7 +680,8 @@ static int check_i2c_image(struct edgeport_serial *serial) /* Read the descriptor data */ status = read_rom(serial, start_address + sizeof(struct ti_i2c_desc), - rom_desc->Size, buffer); + le16_to_cpu(rom_desc->Size), + buffer); if (status) break; @@ -674,7 +690,7 @@ static int check_i2c_image(struct edgeport_serial *serial) break; } start_address = start_address + sizeof(struct ti_i2c_desc) + - rom_desc->Size; + le16_to_cpu(rom_desc->Size); } while ((rom_desc->Type != I2C_DESC_TYPE_ION) && (start_address < TI_MAX_I2C_SIZE)); @@ -712,7 +728,7 @@ static int get_manuf_info(struct edgeport_serial *serial, __u8 *buffer) /* Read the descriptor data */ status = read_rom(serial, start_address+sizeof(struct ti_i2c_desc), - rom_desc->Size, buffer); + le16_to_cpu(rom_desc->Size), buffer); if (status) goto exit; @@ -805,7 +821,7 @@ static int build_i2c_fw_hdr(__u8 *header, struct device *dev) firmware_rec = (struct ti_i2c_firmware_rec*)i2c_header->Data; i2c_header->Type = I2C_DESC_TYPE_FIRMWARE_BLANK; - i2c_header->Size = (__u16)buffer_size; + i2c_header->Size = cpu_to_le16(buffer_size); i2c_header->CheckSum = cs; firmware_rec->Ver_Major = OperationalMajorVersion; firmware_rec->Ver_Minor = OperationalMinorVersion; diff --git a/drivers/usb/serial/io_usbvend.h b/drivers/usb/serial/io_usbvend.h index 51f83fbb73bb..6f6a856bc37c 100644 --- a/drivers/usb/serial/io_usbvend.h +++ b/drivers/usb/serial/io_usbvend.h @@ -594,7 +594,7 @@ struct edge_boot_descriptor { struct ti_i2c_desc { __u8 Type; // Type of descriptor - __u16 Size; // Size of data only not including header + __le16 Size; // Size of data only not including header __u8 CheckSum; // Checksum (8 bit sum of data only) __u8 Data[0]; // Data starts here } __attribute__((packed)); diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c index 618c1c1f227e..5cdb32b37e85 100644 --- a/drivers/usb/serial/kobil_sct.c +++ b/drivers/usb/serial/kobil_sct.c @@ -335,7 +335,8 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, port->interrupt_out_urb->transfer_buffer_length = length; priv->cur_pos = priv->cur_pos + length; - result = usb_submit_urb(port->interrupt_out_urb, GFP_NOIO); + result = usb_submit_urb(port->interrupt_out_urb, + GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send write URB returns: %i\n", __func__, result); todo = priv->filled - priv->cur_pos; @@ -350,7 +351,7 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID || priv->device_type == KOBIL_ADAPTER_K_PRODUCT_ID) { result = usb_submit_urb(port->interrupt_in_urb, - GFP_NOIO); + GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send read URB returns: %i\n", __func__, result); } } diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c index 4856fb7e637e..4b7bfb394a32 100644 --- a/drivers/usb/serial/opticon.c +++ b/drivers/usb/serial/opticon.c @@ -215,7 +215,7 @@ static int opticon_write(struct tty_struct *tty, struct usb_serial_port *port, /* The connected devices do not have a bulk write endpoint, * to transmit data to de barcode device the control endpoint is used */ - dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_NOIO); + dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC); if (!dr) { count = -ENOMEM; goto error_no_dr; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 68fc9fe65936..8b3484134ab0 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -161,6 +161,7 @@ static void option_instat_callback(struct urb *urb); #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_FULLSPEED 0x9000 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED 0x9001 #define NOVATELWIRELESS_PRODUCT_E362 0x9010 +#define NOVATELWIRELESS_PRODUCT_E371 0x9011 #define NOVATELWIRELESS_PRODUCT_G2 0xA010 #define NOVATELWIRELESS_PRODUCT_MC551 0xB001 @@ -234,8 +235,31 @@ static void option_instat_callback(struct urb *urb); #define QUALCOMM_VENDOR_ID 0x05C6 #define CMOTECH_VENDOR_ID 0x16d8 -#define CMOTECH_PRODUCT_6008 0x6008 -#define CMOTECH_PRODUCT_6280 0x6280 +#define CMOTECH_PRODUCT_6001 0x6001 +#define CMOTECH_PRODUCT_CMU_300 0x6002 +#define CMOTECH_PRODUCT_6003 0x6003 +#define CMOTECH_PRODUCT_6004 0x6004 +#define CMOTECH_PRODUCT_6005 0x6005 +#define CMOTECH_PRODUCT_CGU_628A 0x6006 +#define CMOTECH_PRODUCT_CHE_628S 0x6007 +#define CMOTECH_PRODUCT_CMU_301 0x6008 +#define CMOTECH_PRODUCT_CHU_628 0x6280 +#define CMOTECH_PRODUCT_CHU_628S 0x6281 +#define CMOTECH_PRODUCT_CDU_680 0x6803 +#define CMOTECH_PRODUCT_CDU_685A 0x6804 +#define CMOTECH_PRODUCT_CHU_720S 0x7001 +#define CMOTECH_PRODUCT_7002 0x7002 +#define CMOTECH_PRODUCT_CHU_629K 0x7003 +#define CMOTECH_PRODUCT_7004 0x7004 +#define CMOTECH_PRODUCT_7005 0x7005 +#define CMOTECH_PRODUCT_CGU_629 0x7006 +#define CMOTECH_PRODUCT_CHU_629S 0x700a +#define CMOTECH_PRODUCT_CHU_720I 0x7211 +#define CMOTECH_PRODUCT_7212 0x7212 +#define CMOTECH_PRODUCT_7213 0x7213 +#define CMOTECH_PRODUCT_7251 0x7251 +#define CMOTECH_PRODUCT_7252 0x7252 +#define CMOTECH_PRODUCT_7253 0x7253 #define TELIT_VENDOR_ID 0x1bc7 #define TELIT_PRODUCT_UC864E 0x1003 @@ -243,15 +267,21 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_CC864_DUAL 0x1005 #define TELIT_PRODUCT_CC864_SINGLE 0x1006 #define TELIT_PRODUCT_DE910_DUAL 0x1010 +#define TELIT_PRODUCT_UE910_V2 0x1012 #define TELIT_PRODUCT_LE920 0x1200 +#define TELIT_PRODUCT_LE910 0x1201 /* ZTE PRODUCTS */ #define ZTE_VENDOR_ID 0x19d2 #define ZTE_PRODUCT_MF622 0x0001 #define ZTE_PRODUCT_MF628 0x0015 #define ZTE_PRODUCT_MF626 0x0031 -#define ZTE_PRODUCT_MC2718 0xffe8 #define ZTE_PRODUCT_AC2726 0xfff1 +#define ZTE_PRODUCT_CDMA_TECH 0xfffe +#define ZTE_PRODUCT_AC8710T 0xffff +#define ZTE_PRODUCT_MC2718 0xffe8 +#define ZTE_PRODUCT_AD3812 0xffeb +#define ZTE_PRODUCT_MC2716 0xffed #define BENQ_VENDOR_ID 0x04a5 #define BENQ_PRODUCT_H10 0x4068 @@ -286,6 +316,7 @@ static void option_instat_callback(struct urb *urb); #define ALCATEL_PRODUCT_X060S_X200 0x0000 #define ALCATEL_PRODUCT_X220_X500D 0x0017 #define ALCATEL_PRODUCT_L100V 0x011e +#define ALCATEL_PRODUCT_L800MA 0x0203 #define PIRELLI_VENDOR_ID 0x1266 #define PIRELLI_PRODUCT_C100_1 0x1002 @@ -326,8 +357,12 @@ static void option_instat_callback(struct urb *urb); /* Zoom */ #define ZOOM_PRODUCT_4597 0x9607 +/* SpeedUp SU9800 usb 3g modem */ +#define SPEEDUP_PRODUCT_SU9800 0x9800 + /* Haier products */ #define HAIER_VENDOR_ID 0x201e +#define HAIER_PRODUCT_CE81B 0x10f8 #define HAIER_PRODUCT_CE100 0x2009 /* Cinterion (formerly Siemens) products */ @@ -346,8 +381,13 @@ static void option_instat_callback(struct urb *urb); /* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c #define OLIVETTI_PRODUCT_OLICARD100 0xc000 +#define OLIVETTI_PRODUCT_OLICARD120 0xc001 +#define OLIVETTI_PRODUCT_OLICARD140 0xc002 #define OLIVETTI_PRODUCT_OLICARD145 0xc003 +#define OLIVETTI_PRODUCT_OLICARD155 0xc004 #define OLIVETTI_PRODUCT_OLICARD200 0xc005 +#define OLIVETTI_PRODUCT_OLICARD160 0xc00a +#define OLIVETTI_PRODUCT_OLICARD500 0xc00b /* Celot products */ #define CELOT_VENDOR_ID 0x211f @@ -460,6 +500,10 @@ static void option_instat_callback(struct urb *urb); #define INOVIA_VENDOR_ID 0x20a6 #define INOVIA_SEW858 0x1105 +/* VIA Telecom */ +#define VIATELECOM_VENDOR_ID 0x15eb +#define VIATELECOM_PRODUCT_CDS7 0x0001 + /* some devices interfaces need special handling due to a number of reasons */ enum option_blacklist_reason { OPTION_BLACKLIST_NONE = 0, @@ -493,14 +537,26 @@ static const struct option_blacklist_info zte_k3765_z_blacklist = { .reserved = BIT(4), }; +static const struct option_blacklist_info zte_ad3812_z_blacklist = { + .sendsetup = BIT(0) | BIT(1) | BIT(2), +}; + static const struct option_blacklist_info zte_mc2718_z_blacklist = { .sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4), }; +static const struct option_blacklist_info zte_mc2716_z_blacklist = { + .sendsetup = BIT(1) | BIT(2) | BIT(3), +}; + static const struct option_blacklist_info huawei_cdc12_blacklist = { .reserved = BIT(1) | BIT(2), }; +static const struct option_blacklist_info net_intf0_blacklist = { + .reserved = BIT(0), +}; + static const struct option_blacklist_info net_intf1_blacklist = { .reserved = BIT(1), }; @@ -534,6 +590,11 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info telit_le910_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(2), +}; + static const struct option_blacklist_info telit_le920_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(5), @@ -982,6 +1043,7 @@ static const struct usb_device_id option_ids[] = { /* Novatel Ovation MC551 a.k.a. Verizon USB551L */ { USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC551, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E362, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E371, 0xff, 0xff, 0xff) }, { USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) }, { USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) }, @@ -1031,16 +1093,59 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(BANDRICH_VENDOR_ID, BANDRICH_PRODUCT_1012, 0xff) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) }, + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */ { 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(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6280) }, /* BP3-USB & BP3-EXT HSDPA */ - { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6008) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6004) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6005) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_628A) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHE_628S), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_301), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628S) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_680) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_685A) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720S), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7002), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629K), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7004), + .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7005) }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_629), + .driver_info = (kernel_ulong_t)&net_intf5_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629S), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720I), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7212), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7213), + .driver_info = (kernel_ulong_t)&net_intf0_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7251), + .driver_info = (kernel_ulong_t)&net_intf1_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7252), + .driver_info = (kernel_ulong_t)&net_intf1_blacklist }, + { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7253), + .driver_info = (kernel_ulong_t)&net_intf1_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864E) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864G) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), + .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), .driver_info = (kernel_ulong_t)&telit_le920_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ @@ -1408,6 +1513,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&net_intf2_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1426, 0xff, 0xff, 0xff), /* ZTE MF91 */ .driver_info = (kernel_ulong_t)&net_intf2_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff), /* Telewell TW-LTE 4G v2 */ + .driver_info = (kernel_ulong_t)&net_intf2_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) }, @@ -1463,13 +1570,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) }, - /* NOTE: most ZTE CDMA devices should be driven by zte_ev, not option */ + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) }, - { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) }, { USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) }, { USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) }, @@ -1498,14 +1610,18 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&net_intf5_blacklist }, { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L100V), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L800MA), + .driver_info = (kernel_ulong_t)&net_intf2_blacklist }, { USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) }, { USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14), .driver_info = (kernel_ulong_t)&four_g_w14_blacklist }, + { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) }, { 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) }, + { USB_DEVICE_AND_INTERFACE_INFO(HAIER_VENDOR_ID, HAIER_PRODUCT_CE81B, 0xff, 0xff, 0xff) }, /* Pirelli */ { USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_1, 0xff) }, { USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_2, 0xff) }, @@ -1537,12 +1653,21 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) }, { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */ { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, - - { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD140), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD155), + .driver_info = (kernel_ulong_t)&net_intf6_blacklist }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200), - .driver_info = (kernel_ulong_t)&net_intf6_blacklist - }, + .driver_info = (kernel_ulong_t)&net_intf6_blacklist }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD160), + .driver_info = (kernel_ulong_t)&net_intf6_blacklist }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD500), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */ { USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/ { USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM600) }, @@ -1631,6 +1756,7 @@ static const struct usb_device_id option_ids[] = { { 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(INOVIA_VENDOR_ID, INOVIA_SEW858) }, + { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); @@ -1824,6 +1950,8 @@ static void option_instat_callback(struct urb *urb) dev_dbg(dev, "%s: type %x req %x\n", __func__, req_pkt->bRequestType, req_pkt->bRequest); } + } else if (status == -ENOENT || status == -ESHUTDOWN) { + dev_dbg(dev, "%s: urb stopped: %d\n", __func__, status); } else dev_err(dev, "%s: error %d\n", __func__, status); @@ -1848,6 +1976,7 @@ static int option_send_setup(struct usb_serial_port *port) struct option_private *priv = intfdata->private; struct usb_wwan_port_private *portdata; int val = 0; + int res; portdata = usb_get_serial_port_data(port); @@ -1856,9 +1985,17 @@ static int option_send_setup(struct usb_serial_port *port) if (portdata->rts_state) val |= 0x02; - return usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0), + res = usb_autopm_get_interface(serial->interface); + if (res) + return res; + + res = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0), 0x22, 0x21, val, priv->bInterfaceNumber, NULL, 0, USB_CTRL_SET_TIMEOUT); + + usb_autopm_put_interface(serial->interface); + + return res; } MODULE_AUTHOR(DRIVER_AUTHOR); diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 2e22fc22c382..e9bad928039f 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -45,6 +45,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ZTEK) }, { 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) }, @@ -83,6 +84,9 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(YCCABLE_VENDOR_ID, YCCABLE_PRODUCT_ID) }, { USB_DEVICE(SUPERIAL_VENDOR_ID, SUPERIAL_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) }, + { USB_DEVICE(HP_VENDOR_ID, HP_LD960_PRODUCT_ID) }, + { USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) }, + { USB_DEVICE(HP_VENDOR_ID, HP_LCM960_PRODUCT_ID) }, { USB_DEVICE(CRESSI_VENDOR_ID, CRESSI_EDY_PRODUCT_ID) }, { USB_DEVICE(ZEAGLE_VENDOR_ID, ZEAGLE_N2ITION3_PRODUCT_ID) }, { USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index c38b8c00c06f..71fd9da1d6e7 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -22,6 +22,7 @@ #define PL2303_PRODUCT_ID_GPRS 0x0609 #define PL2303_PRODUCT_ID_HCR331 0x331a #define PL2303_PRODUCT_ID_MOTOROLA 0x0307 +#define PL2303_PRODUCT_ID_ZTEK 0xe1f1 #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 @@ -121,8 +122,11 @@ #define SUPERIAL_VENDOR_ID 0x5372 #define SUPERIAL_PRODUCT_ID 0x2303 -/* Hewlett-Packard LD220-HP POS Pole Display */ +/* Hewlett-Packard POS Pole Displays */ #define HP_VENDOR_ID 0x03f0 +#define HP_LD960_PRODUCT_ID 0x0b39 +#define HP_LCM220_PRODUCT_ID 0x3139 +#define HP_LCM960_PRODUCT_ID 0x3239 #define HP_LD220_PRODUCT_ID 0x3524 /* Cressi Edy (diving computer) PC interface */ diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 968a40201e5f..43d93dbf7d71 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -136,12 +136,57 @@ static const struct usb_device_id id_table[] = { {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 0)}, /* Sierra Wireless MC7710 Device Management */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 2)}, /* Sierra Wireless MC7710 NMEA */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 3)}, /* Sierra Wireless MC7710 Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 0)}, /* Sierra Wireless MC73xx Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 2)}, /* Sierra Wireless MC73xx NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 3)}, /* Sierra Wireless MC73xx Modem */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)}, /* Sierra Wireless EM7700 Device Management */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)}, /* Sierra Wireless EM7700 NMEA */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)}, /* Sierra Wireless EM7700 Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 0)}, /* Sierra Wireless EM7355 Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 2)}, /* Sierra Wireless EM7355 NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 3)}, /* Sierra Wireless EM7355 Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 0)}, /* Sierra Wireless Modem Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 2)}, /* Sierra Wireless Modem NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 3)}, /* Sierra Wireless Modem Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 0)}, /* Sierra Wireless MC7305/MC7355 Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 2)}, /* Sierra Wireless MC7305/MC7355 NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 3)}, /* Sierra Wireless MC7305/MC7355 Modem */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)}, /* Netgear AirCard 340U Device Management */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)}, /* Netgear AirCard 340U NMEA */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)}, /* Netgear AirCard 340U Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 0)}, /* Sierra Wireless Modem Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 2)}, /* Sierra Wireless Modem NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 3)}, /* Sierra Wireless Modem Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 0)}, /* Sierra Wireless Modem Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 2)}, /* Sierra Wireless Modem NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 3)}, /* Sierra Wireless Modem Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 0)}, /* Netgear AirCard 341U Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 2)}, /* Netgear AirCard 341U NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 3)}, /* Netgear AirCard 341U Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 0)}, /* Sierra Wireless Modem Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 2)}, /* Sierra Wireless Modem NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 3)}, /* Sierra Wireless Modem Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 0)}, /* Sierra Wireless Modem Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 2)}, /* Sierra Wireless Modem NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 3)}, /* Sierra Wireless Modem Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 0)}, /* Sierra Wireless Modem Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 2)}, /* Sierra Wireless Modem NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 3)}, /* Sierra Wireless Modem Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 0)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 2)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 0)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 2)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 3)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 0)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 2)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 3)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 0)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 2)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 3)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Modem */ { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c index a9eb6221a815..74a9375a9bb5 100644 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -58,6 +58,7 @@ struct sierra_intf_private { spinlock_t susp_lock; unsigned int suspended:1; int in_flight; + unsigned int open_ports; }; static int sierra_set_power_state(struct usb_device *udev, __u16 swiState) @@ -281,17 +282,21 @@ static const struct usb_device_id id_table[] = { /* Sierra Wireless HSPA Non-Composite Device */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6892, 0xFF, 0xFF, 0xFF)}, { USB_DEVICE(0x1199, 0x6893) }, /* Sierra Wireless Device */ - { USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */ + /* Sierra Wireless Direct IP modems */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68A3, 0xFF, 0xFF, 0xFF), + .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist + }, + { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, /* AT&T Direct IP LTE modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, - { USB_DEVICE(0x0f3d, 0x68A3), /* Airprime/Sierra Wireless Direct IP modems */ + /* Airprime/Sierra Wireless Direct IP modems */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68A3, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, - { USB_DEVICE(0x413C, 0x08133) }, /* Dell Computer Corp. Wireless 5720 VZW Mobile Broadband (EVDO Rev-A) Minicard GPS Port */ { } }; @@ -760,6 +765,7 @@ static void sierra_close(struct usb_serial_port *port) struct usb_serial *serial = port->serial; struct sierra_port_private *portdata; struct sierra_intf_private *intfdata = port->serial->private; + struct urb *urb; portdata = usb_get_serial_port_data(port); @@ -768,7 +774,6 @@ static void sierra_close(struct usb_serial_port *port) mutex_lock(&serial->disc_mutex); if (!serial->disconnected) { - serial->interface->needs_remote_wakeup = 0; /* odd error handling due to pm counters */ if (!usb_autopm_get_interface(serial->interface)) sierra_send_setup(port); @@ -779,8 +784,22 @@ static void sierra_close(struct usb_serial_port *port) mutex_unlock(&serial->disc_mutex); spin_lock_irq(&intfdata->susp_lock); portdata->opened = 0; + if (--intfdata->open_ports == 0) + serial->interface->needs_remote_wakeup = 0; spin_unlock_irq(&intfdata->susp_lock); + for (;;) { + urb = usb_get_from_anchor(&portdata->delayed); + if (!urb) + break; + kfree(urb->transfer_buffer); + usb_free_urb(urb); + usb_autopm_put_interface_async(serial->interface); + spin_lock(&portdata->lock); + portdata->outstanding_urbs--; + spin_unlock(&portdata->lock); + } + sierra_stop_rx_urbs(port); for (i = 0; i < portdata->num_in_urbs; i++) { sierra_release_urb(portdata->in_urbs[i]); @@ -817,23 +836,29 @@ static int sierra_open(struct tty_struct *tty, struct usb_serial_port *port) usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN); err = sierra_submit_rx_urbs(port, GFP_KERNEL); - if (err) { - /* get rid of everything as in close */ - sierra_close(port); - /* restore balance for autopm */ - if (!serial->disconnected) - usb_autopm_put_interface(serial->interface); - return err; - } + if (err) + goto err_submit; + sierra_send_setup(port); - serial->interface->needs_remote_wakeup = 1; spin_lock_irq(&intfdata->susp_lock); portdata->opened = 1; + if (++intfdata->open_ports == 1) + serial->interface->needs_remote_wakeup = 1; spin_unlock_irq(&intfdata->susp_lock); usb_autopm_put_interface(serial->interface); return 0; + +err_submit: + sierra_stop_rx_urbs(port); + + for (i = 0; i < portdata->num_in_urbs; i++) { + sierra_release_urb(portdata->in_urbs[i]); + portdata->in_urbs[i] = NULL; + } + + return err; } @@ -929,6 +954,7 @@ static int sierra_port_remove(struct usb_serial_port *port) struct sierra_port_private *portdata; portdata = usb_get_serial_port_data(port); + usb_set_serial_port_data(port, NULL); kfree(portdata); return 0; @@ -945,6 +971,8 @@ static void stop_read_write_urbs(struct usb_serial *serial) for (i = 0; i < serial->num_ports; ++i) { port = serial->port[i]; portdata = usb_get_serial_port_data(port); + if (!portdata) + continue; sierra_stop_rx_urbs(port); usb_kill_anchored_urbs(&portdata->active); } @@ -987,6 +1015,9 @@ static int sierra_resume(struct usb_serial *serial) port = serial->port[i]; portdata = usb_get_serial_port_data(port); + if (!portdata) + continue; + while ((urb = usb_get_from_anchor(&portdata->delayed))) { usb_anchor_urb(urb, &portdata->active); intfdata->in_flight++; @@ -994,8 +1025,12 @@ static int sierra_resume(struct usb_serial *serial) if (err < 0) { intfdata->in_flight--; usb_unanchor_urb(urb); - usb_scuttle_anchored_urbs(&portdata->delayed); - break; + kfree(urb->transfer_buffer); + usb_free_urb(urb); + spin_lock(&portdata->lock); + portdata->outstanding_urbs--; + spin_unlock(&portdata->lock); + continue; } } diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 7c9dc28640bb..9a08e18e09b9 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -764,29 +764,39 @@ static int usb_serial_probe(struct usb_interface *interface, if (usb_endpoint_is_bulk_in(endpoint)) { /* we found a bulk in endpoint */ dev_dbg(ddev, "found bulk in on endpoint %d\n", i); - bulk_in_endpoint[num_bulk_in] = endpoint; - ++num_bulk_in; + if (num_bulk_in < MAX_NUM_PORTS) { + bulk_in_endpoint[num_bulk_in] = endpoint; + ++num_bulk_in; + } } if (usb_endpoint_is_bulk_out(endpoint)) { /* we found a bulk out endpoint */ dev_dbg(ddev, "found bulk out on endpoint %d\n", i); - bulk_out_endpoint[num_bulk_out] = endpoint; - ++num_bulk_out; + if (num_bulk_out < MAX_NUM_PORTS) { + bulk_out_endpoint[num_bulk_out] = endpoint; + ++num_bulk_out; + } } if (usb_endpoint_is_int_in(endpoint)) { /* we found a interrupt in endpoint */ dev_dbg(ddev, "found interrupt in on endpoint %d\n", i); - interrupt_in_endpoint[num_interrupt_in] = endpoint; - ++num_interrupt_in; + if (num_interrupt_in < MAX_NUM_PORTS) { + interrupt_in_endpoint[num_interrupt_in] = + endpoint; + ++num_interrupt_in; + } } if (usb_endpoint_is_int_out(endpoint)) { /* we found an interrupt out endpoint */ dev_dbg(ddev, "found interrupt out on endpoint %d\n", i); - interrupt_out_endpoint[num_interrupt_out] = endpoint; - ++num_interrupt_out; + if (num_interrupt_out < MAX_NUM_PORTS) { + interrupt_out_endpoint[num_interrupt_out] = + endpoint; + ++num_interrupt_out; + } } } @@ -809,8 +819,10 @@ static int usb_serial_probe(struct usb_interface *interface, if (usb_endpoint_is_int_in(endpoint)) { /* we found a interrupt in endpoint */ dev_dbg(ddev, "found interrupt in for Prolific device on separate interface\n"); - interrupt_in_endpoint[num_interrupt_in] = endpoint; - ++num_interrupt_in; + if (num_interrupt_in < MAX_NUM_PORTS) { + interrupt_in_endpoint[num_interrupt_in] = endpoint; + ++num_interrupt_in; + } } } } @@ -850,6 +862,11 @@ static int usb_serial_probe(struct usb_interface *interface, num_ports = type->num_ports; } + if (num_ports > MAX_NUM_PORTS) { + dev_warn(ddev, "too many ports requested: %d\n", num_ports); + num_ports = MAX_NUM_PORTS; + } + serial->num_ports = num_ports; serial->num_bulk_in = num_bulk_in; serial->num_bulk_out = num_bulk_out; @@ -1348,10 +1365,12 @@ static int usb_serial_register(struct usb_serial_driver *driver) static void usb_serial_deregister(struct usb_serial_driver *device) { pr_info("USB Serial deregistering driver %s\n", device->description); + mutex_lock(&table_lock); list_del(&device->driver_list); - usb_serial_bus_deregister(device); mutex_unlock(&table_lock); + + usb_serial_bus_deregister(device); } /** diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c index 640fe0173236..d91a9883e869 100644 --- a/drivers/usb/serial/usb_wwan.c +++ b/drivers/usb/serial/usb_wwan.c @@ -228,8 +228,10 @@ int usb_wwan_write(struct tty_struct *tty, struct usb_serial_port *port, usb_pipeendpoint(this_urb->pipe), i); err = usb_autopm_get_interface_async(port->serial->interface); - if (err < 0) + if (err < 0) { + clear_bit(i, &portdata->out_busy); break; + } /* send the data */ memcpy(this_urb->transfer_buffer, buf, todo); @@ -386,6 +388,14 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port) portdata = usb_get_serial_port_data(port); intfdata = serial->private; + if (port->interrupt_in_urb) { + err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); + if (err) { + dev_dbg(&port->dev, "%s: submit int urb failed: %d\n", + __func__, err); + } + } + /* Start reading from the IN endpoint */ for (i = 0; i < N_IN_URB; i++) { urb = portdata->in_urbs[i]; @@ -412,12 +422,26 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port) } EXPORT_SYMBOL(usb_wwan_open); +static void unbusy_queued_urb(struct urb *urb, + struct usb_wwan_port_private *portdata) +{ + int i; + + for (i = 0; i < N_OUT_URB; i++) { + if (urb == portdata->out_urbs[i]) { + clear_bit(i, &portdata->out_busy); + break; + } + } +} + void usb_wwan_close(struct usb_serial_port *port) { int i; struct usb_serial *serial = port->serial; struct usb_wwan_port_private *portdata; struct usb_wwan_intf_private *intfdata = port->serial->private; + struct urb *urb; portdata = usb_get_serial_port_data(port); @@ -426,10 +450,19 @@ void usb_wwan_close(struct usb_serial_port *port) portdata->opened = 0; spin_unlock_irq(&intfdata->susp_lock); + for (;;) { + urb = usb_get_from_anchor(&portdata->delayed); + if (!urb) + break; + unbusy_queued_urb(urb, portdata); + usb_autopm_put_interface_async(serial->interface); + } + for (i = 0; i < N_IN_URB; i++) usb_kill_urb(portdata->in_urbs[i]); for (i = 0; i < N_OUT_URB; i++) usb_kill_urb(portdata->out_urbs[i]); + usb_kill_urb(port->interrupt_in_urb); /* balancing - important as an error cannot be handled*/ usb_autopm_get_interface_no_resume(serial->interface); @@ -463,9 +496,11 @@ int usb_wwan_port_probe(struct usb_serial_port *port) struct usb_wwan_port_private *portdata; struct urb *urb; u8 *buffer; - int err; int i; + if (!port->bulk_in_size || !port->bulk_out_size) + return -ENODEV; + portdata = kzalloc(sizeof(*portdata), GFP_KERNEL); if (!portdata) return -ENOMEM; @@ -473,9 +508,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port) init_usb_anchor(&portdata->delayed); for (i = 0; i < N_IN_URB; i++) { - if (!port->bulk_in_size) - break; - buffer = (u8 *)__get_free_page(GFP_KERNEL); if (!buffer) goto bail_out_error; @@ -489,9 +521,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port) } for (i = 0; i < N_OUT_URB; i++) { - if (!port->bulk_out_size) - break; - buffer = kmalloc(OUT_BUFLEN, GFP_KERNEL); if (!buffer) goto bail_out_error2; @@ -506,13 +535,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port) usb_set_serial_port_data(port, portdata); - if (port->interrupt_in_urb) { - err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); - if (err) - dev_dbg(&port->dev, "%s: submit irq_in urb failed %d\n", - __func__, err); - } - return 0; bail_out_error2: @@ -580,44 +602,29 @@ static void stop_read_write_urbs(struct usb_serial *serial) int usb_wwan_suspend(struct usb_serial *serial, pm_message_t message) { struct usb_wwan_intf_private *intfdata = serial->private; - int b; + spin_lock_irq(&intfdata->susp_lock); if (PMSG_IS_AUTO(message)) { - spin_lock_irq(&intfdata->susp_lock); - b = intfdata->in_flight; - spin_unlock_irq(&intfdata->susp_lock); - - if (b) + if (intfdata->in_flight) { + spin_unlock_irq(&intfdata->susp_lock); return -EBUSY; + } } - - spin_lock_irq(&intfdata->susp_lock); intfdata->suspended = 1; spin_unlock_irq(&intfdata->susp_lock); + stop_read_write_urbs(serial); return 0; } EXPORT_SYMBOL(usb_wwan_suspend); -static void unbusy_queued_urb(struct urb *urb, struct usb_wwan_port_private *portdata) -{ - int i; - - for (i = 0; i < N_OUT_URB; i++) { - if (urb == portdata->out_urbs[i]) { - clear_bit(i, &portdata->out_busy); - break; - } - } -} - -static void play_delayed(struct usb_serial_port *port) +static int play_delayed(struct usb_serial_port *port) { struct usb_wwan_intf_private *data; struct usb_wwan_port_private *portdata; struct urb *urb; - int err; + int err = 0; portdata = usb_get_serial_port_data(port); data = port->serial->private; @@ -634,6 +641,8 @@ static void play_delayed(struct usb_serial_port *port) break; } } + + return err; } int usb_wwan_resume(struct usb_serial *serial) @@ -643,54 +652,51 @@ int usb_wwan_resume(struct usb_serial *serial) struct usb_wwan_intf_private *intfdata = serial->private; struct usb_wwan_port_private *portdata; struct urb *urb; - int err = 0; - - /* get the interrupt URBs resubmitted unconditionally */ - for (i = 0; i < serial->num_ports; i++) { - port = serial->port[i]; - if (!port->interrupt_in_urb) { - dev_dbg(&port->dev, "%s: No interrupt URB for port\n", __func__); - continue; - } - err = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO); - dev_dbg(&port->dev, "Submitted interrupt URB for port (result %d)\n", err); - if (err < 0) { - dev_err(&port->dev, "%s: Error %d for interrupt URB\n", - __func__, err); - goto err_out; - } - } + int err; + int err_count = 0; + spin_lock_irq(&intfdata->susp_lock); for (i = 0; i < serial->num_ports; i++) { /* walk all ports */ port = serial->port[i]; portdata = usb_get_serial_port_data(port); /* skip closed ports */ - spin_lock_irq(&intfdata->susp_lock); - if (!portdata || !portdata->opened) { - spin_unlock_irq(&intfdata->susp_lock); + if (!portdata || !portdata->opened) continue; + + if (port->interrupt_in_urb) { + err = usb_submit_urb(port->interrupt_in_urb, + GFP_ATOMIC); + if (err) { + dev_err(&port->dev, + "%s: submit int urb failed: %d\n", + __func__, err); + err_count++; + } } + err = play_delayed(port); + if (err) + err_count++; + for (j = 0; j < N_IN_URB; j++) { urb = portdata->in_urbs[j]; err = usb_submit_urb(urb, GFP_ATOMIC); if (err < 0) { dev_err(&port->dev, "%s: Error %d for bulk URB %d\n", __func__, err, i); - spin_unlock_irq(&intfdata->susp_lock); - goto err_out; + err_count++; } } - play_delayed(port); - spin_unlock_irq(&intfdata->susp_lock); } - spin_lock_irq(&intfdata->susp_lock); intfdata->suspended = 0; spin_unlock_irq(&intfdata->susp_lock); -err_out: - return err; + + if (err_count) + return -EIO; + + return 0; } EXPORT_SYMBOL(usb_wwan_resume); #endif diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c index e62f2dff8b7d..6c3734d2b45a 100644 --- a/drivers/usb/serial/whiteheat.c +++ b/drivers/usb/serial/whiteheat.c @@ -514,6 +514,10 @@ static void command_port_read_callback(struct urb *urb) dev_dbg(&urb->dev->dev, "%s - command_info is NULL, exiting.\n", __func__); return; } + if (!urb->actual_length) { + dev_dbg(&urb->dev->dev, "%s - empty response, exiting.\n", __func__); + return; + } if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero urb status: %d\n", __func__, status); if (status != -ENOENT) @@ -534,7 +538,8 @@ static void command_port_read_callback(struct urb *urb) /* These are unsolicited reports from the firmware, hence no waiting command to wakeup */ dev_dbg(&urb->dev->dev, "%s - event received\n", __func__); - } else if (data[0] == WHITEHEAT_GET_DTR_RTS) { + } else if ((data[0] == WHITEHEAT_GET_DTR_RTS) && + (urb->actual_length - 1 <= sizeof(command_info->result_buffer))) { memcpy(command_info->result_buffer, &data[1], urb->actual_length - 1); command_info->command_finished = WHITEHEAT_CMD_COMPLETE; diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c index e40ab739c4a6..c9bb107d5e5c 100644 --- a/drivers/usb/serial/zte_ev.c +++ b/drivers/usb/serial/zte_ev.c @@ -272,28 +272,16 @@ static void zte_ev_usb_serial_close(struct usb_serial_port *port) } static const struct usb_device_id id_table[] = { - /* AC8710, AC8710T */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffff, 0xff, 0xff, 0xff) }, - /* AC8700 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfffe, 0xff, 0xff, 0xff) }, - /* MG880 */ - { USB_DEVICE(0x19d2, 0xfffd) }, - { USB_DEVICE(0x19d2, 0xfffc) }, - { USB_DEVICE(0x19d2, 0xfffb) }, - /* AC8710_V3 */ + { USB_DEVICE(0x19d2, 0xffec) }, + { USB_DEVICE(0x19d2, 0xffee) }, { USB_DEVICE(0x19d2, 0xfff6) }, { USB_DEVICE(0x19d2, 0xfff7) }, { USB_DEVICE(0x19d2, 0xfff8) }, { USB_DEVICE(0x19d2, 0xfff9) }, - { USB_DEVICE(0x19d2, 0xffee) }, - /* AC2716, MC2716 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffed, 0xff, 0xff, 0xff) }, - /* AD3812 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffeb, 0xff, 0xff, 0xff) }, - { USB_DEVICE(0x19d2, 0xffec) }, - { USB_DEVICE(0x05C6, 0x3197) }, - { USB_DEVICE(0x05C6, 0x6000) }, - { USB_DEVICE(0x05C6, 0x9008) }, + { USB_DEVICE(0x19d2, 0xfffb) }, + { USB_DEVICE(0x19d2, 0xfffc) }, + /* MG880 */ + { USB_DEVICE(0x19d2, 0xfffd) }, { }, }; MODULE_DEVICE_TABLE(usb, id_table); diff --git a/drivers/usb/storage/shuttle_usbat.c b/drivers/usb/storage/shuttle_usbat.c index 4ef2a80728f7..008d805c3d21 100644 --- a/drivers/usb/storage/shuttle_usbat.c +++ b/drivers/usb/storage/shuttle_usbat.c @@ -1851,7 +1851,7 @@ static int usbat_probe(struct usb_interface *intf, us->transport_name = "Shuttle USBAT"; us->transport = usbat_flash_transport; us->transport_reset = usb_stor_CB_reset; - us->max_lun = 1; + us->max_lun = 0; result = usb_stor_probe2(us); return result; diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 22c7d4360fa2..b1d815eb6d0b 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -1118,6 +1118,31 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) */ if (result == USB_STOR_XFER_LONG) fake_sense = 1; + + /* + * Sometimes a device will mistakenly skip the data phase + * and go directly to the status phase without sending a + * zero-length packet. If we get a 13-byte response here, + * check whether it really is a CSW. + */ + if (result == USB_STOR_XFER_SHORT && + srb->sc_data_direction == DMA_FROM_DEVICE && + transfer_length - scsi_get_resid(srb) == + US_BULK_CS_WRAP_LEN) { + struct scatterlist *sg = NULL; + unsigned int offset = 0; + + if (usb_stor_access_xfer_buf((unsigned char *) bcs, + US_BULK_CS_WRAP_LEN, srb, &sg, + &offset, FROM_XFER_BUF) == + US_BULK_CS_WRAP_LEN && + bcs->Signature == + cpu_to_le32(US_BULK_CS_SIGN)) { + usb_stor_dbg(us, "Device skipped data phase\n"); + scsi_set_resid(srb, transfer_length); + goto skipped_data_phase; + } + } } /* See flow chart on pg 15 of the Bulk Only Transport spec for @@ -1153,6 +1178,7 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; + skipped_data_phase: /* check bulk status */ residue = le32_to_cpu(bcs->Residue); usb_stor_dbg(us, "Bulk Status S 0x%x T 0x%x R %u Stat 0x%x\n", diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index adbeb255616a..7f625306ea80 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -101,6 +101,12 @@ UNUSUAL_DEV( 0x03f0, 0x4002, 0x0001, 0x0001, "PhotoSmart R707", USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_FIX_CAPACITY), +UNUSUAL_DEV( 0x03f3, 0x0001, 0x0000, 0x9999, + "Adaptec", + "USBConnect 2000", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Sebastian Kapfer <sebastian_kapfer@gmx.net> * and Olaf Hering <olh@suse.de> (different bcd's, same vendor/product) * for USB floppies that need the SINGLE_LUN enforcement. @@ -234,6 +240,20 @@ UNUSUAL_DEV( 0x0421, 0x0495, 0x0370, 0x0370, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_MAX_SECTORS_64 ), +/* Reported by Daniele Forsi <dforsi@gmail.com> */ +UNUSUAL_DEV( 0x0421, 0x04b9, 0x0350, 0x0350, + "Nokia", + "5300", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64 ), + +/* Patch submitted by Victor A. Santos <victoraur.santos@gmail.com> */ +UNUSUAL_DEV( 0x0421, 0x05af, 0x0742, 0x0742, + "Nokia", + "305", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64), + /* Patch submitted by Mikhail Zolotaryov <lebon@lebon.org.ua> */ UNUSUAL_DEV( 0x0421, 0x06aa, 0x1110, 0x1110, "Nokia", @@ -727,6 +747,12 @@ UNUSUAL_DEV( 0x059b, 0x0001, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_SINGLE_LUN ), +UNUSUAL_DEV( 0x059b, 0x0040, 0x0100, 0x0100, + "Iomega", + "Jaz USB Adapter", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_SINGLE_LUN ), + /* Reported by <Hendryk.Pfeiffer@gmx.de> */ UNUSUAL_DEV( 0x059f, 0x0643, 0x0000, 0x0000, "LaCie", @@ -1099,6 +1125,18 @@ UNUSUAL_DEV( 0x0851, 0x1543, 0x0200, 0x0200, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NOT_LOCKABLE), +UNUSUAL_DEV( 0x085a, 0x0026, 0x0100, 0x0133, + "Xircom", + "PortGear USB-SCSI (Mac USB Dock)", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + +UNUSUAL_DEV( 0x085a, 0x0028, 0x0100, 0x0133, + "Xircom", + "PortGear USB to SCSI Converter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Submitted by Jan De Luyck <lkml@kcore.org> */ UNUSUAL_DEV( 0x08bd, 0x1100, 0x0000, 0x0000, "CITIZEN", @@ -1931,6 +1969,14 @@ UNUSUAL_DEV( 0x152d, 0x2329, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ), +/* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI) + * and Mac USB Dock USB-SCSI */ +UNUSUAL_DEV( 0x1645, 0x0007, 0x0100, 0x0133, + "Entrega Technologies", + "USB to SCSI Converter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Robert Schedel <r.schedel@yahoo.de> * Note: this is a 'super top' device like the above 14cd/6600 device */ UNUSUAL_DEV( 0x1652, 0x6600, 0x0201, 0x0201, @@ -1953,6 +1999,12 @@ UNUSUAL_DEV( 0x177f, 0x0400, 0x0000, 0x0000, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ), +UNUSUAL_DEV( 0x1822, 0x0001, 0x0000, 0x9999, + "Ariston Technologies", + "iConnect USB to SCSI adapter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Hans de Goede <hdegoede@redhat.com> * These Appotech controllers are found in Picture Frames, they provide a * (buggy) emulation of a cdrom drive which contains the windows software diff --git a/drivers/uwb/lc-dev.c b/drivers/uwb/lc-dev.c index 80079b8fed15..d0303f0dbe15 100644 --- a/drivers/uwb/lc-dev.c +++ b/drivers/uwb/lc-dev.c @@ -431,16 +431,19 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce) uwb_dev->mac_addr = *bce->mac_addr; uwb_dev->dev_addr = bce->dev_addr; dev_set_name(&uwb_dev->dev, "%s", macbuf); + + /* plug the beacon cache */ + bce->uwb_dev = uwb_dev; + uwb_dev->bce = bce; + uwb_bce_get(bce); /* released in uwb_dev_sys_release() */ + result = uwb_dev_add(uwb_dev, &rc->uwb_dev.dev, rc); if (result < 0) { dev_err(dev, "new device %s: cannot instantiate device\n", macbuf); goto error_dev_add; } - /* plug the beacon cache */ - bce->uwb_dev = uwb_dev; - uwb_dev->bce = bce; - uwb_bce_get(bce); /* released in uwb_dev_sys_release() */ + dev_info(dev, "uwb device (mac %s dev %s) connected to %s %s\n", macbuf, devbuf, rc->uwb_dev.dev.parent->bus->name, dev_name(rc->uwb_dev.dev.parent)); @@ -448,6 +451,8 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce) return; error_dev_add: + bce->uwb_dev = NULL; + uwb_bce_put(bce); kfree(uwb_dev); return; } diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c index cd961622f9c1..b74e5f5ddac8 100644 --- a/drivers/video/atmel_lcdfb.c +++ b/drivers/video/atmel_lcdfb.c @@ -1298,6 +1298,12 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev) goto unregister_irqs; } + ret = atmel_lcdfb_set_par(info); + if (ret < 0) { + dev_err(dev, "set par failed: %d\n", ret); + goto unregister_irqs; + } + dev_set_drvdata(dev, info); /* diff --git a/drivers/video/aty/mach64_accel.c b/drivers/video/aty/mach64_accel.c index e45833ce975b..182bd680141f 100644 --- a/drivers/video/aty/mach64_accel.c +++ b/drivers/video/aty/mach64_accel.c @@ -4,6 +4,7 @@ */ #include <linux/delay.h> +#include <asm/unaligned.h> #include <linux/fb.h> #include <video/mach64.h> #include "atyfb.h" @@ -419,7 +420,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image) u32 *pbitmap, dwords = (src_bytes + 3) / 4; for (pbitmap = (u32*)(image->data); dwords; dwords--, pbitmap++) { wait_for_fifo(1, par); - aty_st_le32(HOST_DATA0, le32_to_cpup(pbitmap), par); + aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par); } } diff --git a/drivers/video/aty/mach64_cursor.c b/drivers/video/aty/mach64_cursor.c index 95ec042ddbf8..0fe02e22d9a4 100644 --- a/drivers/video/aty/mach64_cursor.c +++ b/drivers/video/aty/mach64_cursor.c @@ -5,6 +5,7 @@ #include <linux/fb.h> #include <linux/init.h> #include <linux/string.h> +#include "../fb_draw.h" #include <asm/io.h> @@ -157,24 +158,33 @@ static int atyfb_cursor(struct fb_info *info, struct fb_cursor *cursor) for (i = 0; i < height; i++) { for (j = 0; j < width; j++) { + u16 l = 0xaaaa; b = *src++; m = *msk++; switch (cursor->rop) { case ROP_XOR: // Upper 4 bits of mask data - fb_writeb(cursor_bits_lookup[(b ^ m) >> 4], dst++); + l = cursor_bits_lookup[(b ^ m) >> 4] | // Lower 4 bits of mask - fb_writeb(cursor_bits_lookup[(b ^ m) & 0x0f], - dst++); + (cursor_bits_lookup[(b ^ m) & 0x0f] << 8); break; case ROP_COPY: // Upper 4 bits of mask data - fb_writeb(cursor_bits_lookup[(b & m) >> 4], dst++); + l = cursor_bits_lookup[(b & m) >> 4] | // Lower 4 bits of mask - fb_writeb(cursor_bits_lookup[(b & m) & 0x0f], - dst++); + (cursor_bits_lookup[(b & m) & 0x0f] << 8); break; } + /* + * If cursor size is not a multiple of 8 characters + * we must pad it with transparent pattern (0xaaaa). + */ + if ((j + 1) * 8 > cursor->image.width) { + l = comp(l, 0xaaaa, + (1 << ((cursor->image.width & 7) * 2)) - 1); + } + fb_writeb(l & 0xff, dst++); + fb_writeb(l >> 8, dst++); } dst += offset; } diff --git a/drivers/video/cfbcopyarea.c b/drivers/video/cfbcopyarea.c index bb5a96b1645d..bcb57235fcc7 100644 --- a/drivers/video/cfbcopyarea.c +++ b/drivers/video/cfbcopyarea.c @@ -43,13 +43,22 @@ */ static void -bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, - const unsigned long __iomem *src, int src_idx, int bits, +bitcpy(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx, + const unsigned long __iomem *src, unsigned src_idx, int bits, unsigned n, u32 bswapmask) { unsigned long first, last; int const shift = dst_idx-src_idx; - int left, right; + +#if 0 + /* + * If you suspect bug in this function, compare it with this simple + * memmove implementation. + */ + fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8, + (char *)src + ((src_idx & (bits - 1))) / 8, n / 8); + return; +#endif first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask); last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask); @@ -98,9 +107,8 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, unsigned long d0, d1; int m; - right = shift & (bits - 1); - left = -shift & (bits - 1); - bswapmask &= shift; + int const left = shift & (bits - 1); + int const right = -shift & (bits - 1); if (dst_idx+n <= bits) { // Single destination word @@ -110,15 +118,15 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, d0 = fb_rev_pixels_in_long(d0, bswapmask); if (shift > 0) { // Single source word - d0 >>= right; + d0 <<= left; } else if (src_idx+n <= bits) { // Single source word - d0 <<= left; + d0 >>= right; } else { // 2 source words d1 = FB_READL(src + 1); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0<<left | d1>>right; + d0 = d0 >> right | d1 << left; } d0 = fb_rev_pixels_in_long(d0, bswapmask); FB_WRITEL(comp(d0, FB_READL(dst), first), dst); @@ -135,60 +143,59 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, if (shift > 0) { // Single source word d1 = d0; - d0 >>= right; - dst++; + d0 <<= left; n -= bits - dst_idx; } else { // 2 source words d1 = FB_READL(src++); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0<<left | d1>>right; - dst++; + d0 = d0 >> right | d1 << left; n -= bits - dst_idx; } d0 = fb_rev_pixels_in_long(d0, bswapmask); FB_WRITEL(comp(d0, FB_READL(dst), first), dst); d0 = d1; + dst++; // Main chunk m = n % bits; n /= bits; while ((n >= 4) && !bswapmask) { d1 = FB_READL(src++); - FB_WRITEL(d0 << left | d1 >> right, dst++); + FB_WRITEL(d0 >> right | d1 << left, dst++); d0 = d1; d1 = FB_READL(src++); - FB_WRITEL(d0 << left | d1 >> right, dst++); + FB_WRITEL(d0 >> right | d1 << left, dst++); d0 = d1; d1 = FB_READL(src++); - FB_WRITEL(d0 << left | d1 >> right, dst++); + FB_WRITEL(d0 >> right | d1 << left, dst++); d0 = d1; d1 = FB_READL(src++); - FB_WRITEL(d0 << left | d1 >> right, dst++); + FB_WRITEL(d0 >> right | d1 << left, dst++); d0 = d1; n -= 4; } while (n--) { d1 = FB_READL(src++); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0 << left | d1 >> right; + d0 = d0 >> right | d1 << left; d0 = fb_rev_pixels_in_long(d0, bswapmask); FB_WRITEL(d0, dst++); d0 = d1; } // Trailing bits - if (last) { - if (m <= right) { + if (m) { + if (m <= bits - right) { // Single source word - d0 <<= left; + d0 >>= right; } else { // 2 source words d1 = FB_READL(src); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0<<left | d1>>right; + d0 = d0 >> right | d1 << left; } d0 = fb_rev_pixels_in_long(d0, bswapmask); FB_WRITEL(comp(d0, FB_READL(dst), last), dst); @@ -202,43 +209,46 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, */ static void -bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, - const unsigned long __iomem *src, int src_idx, int bits, +bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx, + const unsigned long __iomem *src, unsigned src_idx, int bits, unsigned n, u32 bswapmask) { unsigned long first, last; int shift; - dst += (n-1)/bits; - src += (n-1)/bits; - if ((n-1) % bits) { - dst_idx += (n-1) % bits; - dst += dst_idx >> (ffs(bits) - 1); - dst_idx &= bits - 1; - src_idx += (n-1) % bits; - src += src_idx >> (ffs(bits) - 1); - src_idx &= bits - 1; - } +#if 0 + /* + * If you suspect bug in this function, compare it with this simple + * memmove implementation. + */ + fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8, + (char *)src + ((src_idx & (bits - 1))) / 8, n / 8); + return; +#endif + + dst += (dst_idx + n - 1) / bits; + src += (src_idx + n - 1) / bits; + dst_idx = (dst_idx + n - 1) % bits; + src_idx = (src_idx + n - 1) % bits; shift = dst_idx-src_idx; - first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask); - last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits), - bswapmask); + first = ~fb_shifted_pixels_mask_long(p, (dst_idx + 1) % bits, bswapmask); + last = fb_shifted_pixels_mask_long(p, (bits + dst_idx + 1 - n) % bits, bswapmask); if (!shift) { // Same alignment for source and dest if ((unsigned long)dst_idx+1 >= n) { // Single word - if (last) - first &= last; - FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst); + if (first) + last &= first; + FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst); } else { // Multiple destination words // Leading bits - if (first != ~0UL) { + if (first) { FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst); dst--; src--; @@ -262,7 +272,7 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, FB_WRITEL(FB_READL(src--), dst--); // Trailing bits - if (last) + if (last != -1UL) FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst); } } else { @@ -270,29 +280,28 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, unsigned long d0, d1; int m; - int const left = -shift & (bits-1); - int const right = shift & (bits-1); - bswapmask &= shift; + int const left = shift & (bits-1); + int const right = -shift & (bits-1); if ((unsigned long)dst_idx+1 >= n) { // Single destination word - if (last) - first &= last; + if (first) + last &= first; d0 = FB_READL(src); if (shift < 0) { // Single source word - d0 <<= left; + d0 >>= right; } else if (1+(unsigned long)src_idx >= n) { // Single source word - d0 >>= right; + d0 <<= left; } else { // 2 source words d1 = FB_READL(src - 1); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0>>right | d1<<left; + d0 = d0 << left | d1 >> right; } d0 = fb_rev_pixels_in_long(d0, bswapmask); - FB_WRITEL(comp(d0, FB_READL(dst), first), dst); + FB_WRITEL(comp(d0, FB_READL(dst), last), dst); } else { // Multiple destination words /** We must always remember the last value read, because in case @@ -307,12 +316,12 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, if (shift < 0) { // Single source word d1 = d0; - d0 <<= left; + d0 >>= right; } else { // 2 source words d1 = FB_READL(src--); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0>>right | d1<<left; + d0 = d0 << left | d1 >> right; } d0 = fb_rev_pixels_in_long(d0, bswapmask); FB_WRITEL(comp(d0, FB_READL(dst), first), dst); @@ -325,39 +334,39 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx, n /= bits; while ((n >= 4) && !bswapmask) { d1 = FB_READL(src--); - FB_WRITEL(d0 >> right | d1 << left, dst--); + FB_WRITEL(d0 << left | d1 >> right, dst--); d0 = d1; d1 = FB_READL(src--); - FB_WRITEL(d0 >> right | d1 << left, dst--); + FB_WRITEL(d0 << left | d1 >> right, dst--); d0 = d1; d1 = FB_READL(src--); - FB_WRITEL(d0 >> right | d1 << left, dst--); + FB_WRITEL(d0 << left | d1 >> right, dst--); d0 = d1; d1 = FB_READL(src--); - FB_WRITEL(d0 >> right | d1 << left, dst--); + FB_WRITEL(d0 << left | d1 >> right, dst--); d0 = d1; n -= 4; } while (n--) { d1 = FB_READL(src--); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0 >> right | d1 << left; + d0 = d0 << left | d1 >> right; d0 = fb_rev_pixels_in_long(d0, bswapmask); FB_WRITEL(d0, dst--); d0 = d1; } // Trailing bits - if (last) { - if (m <= left) { + if (m) { + if (m <= bits - left) { // Single source word - d0 >>= right; + d0 <<= left; } else { // 2 source words d1 = FB_READL(src); d1 = fb_rev_pixels_in_long(d1, bswapmask); - d0 = d0>>right | d1<<left; + d0 = d0 << left | d1 >> right; } d0 = fb_rev_pixels_in_long(d0, bswapmask); FB_WRITEL(comp(d0, FB_READL(dst), last), dst); @@ -371,9 +380,9 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy; u32 height = area->height, width = area->width; unsigned long const bits_per_line = p->fix.line_length*8u; - unsigned long __iomem *dst = NULL, *src = NULL; + unsigned long __iomem *base = NULL; int bits = BITS_PER_LONG, bytes = bits >> 3; - int dst_idx = 0, src_idx = 0, rev_copy = 0; + unsigned dst_idx = 0, src_idx = 0, rev_copy = 0; u32 bswapmask = fb_compute_bswapmask(p); if (p->state != FBINFO_STATE_RUNNING) @@ -389,7 +398,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) // split the base of the framebuffer into a long-aligned address and the // index of the first bit - dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1)); + base = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1)); dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1)); // add offset of source and target area dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel; @@ -402,20 +411,14 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) while (height--) { dst_idx -= bits_per_line; src_idx -= bits_per_line; - dst += dst_idx >> (ffs(bits) - 1); - dst_idx &= (bytes - 1); - src += src_idx >> (ffs(bits) - 1); - src_idx &= (bytes - 1); - bitcpy_rev(p, dst, dst_idx, src, src_idx, bits, + bitcpy_rev(p, base + (dst_idx / bits), dst_idx % bits, + base + (src_idx / bits), src_idx % bits, bits, width*p->var.bits_per_pixel, bswapmask); } } else { while (height--) { - dst += dst_idx >> (ffs(bits) - 1); - dst_idx &= (bytes - 1); - src += src_idx >> (ffs(bits) - 1); - src_idx &= (bytes - 1); - bitcpy(p, dst, dst_idx, src, src_idx, bits, + bitcpy(p, base + (dst_idx / bits), dst_idx % bits, + base + (src_idx / bits), src_idx % bits, bits, width*p->var.bits_per_pixel, bswapmask); dst_idx += bits_per_line; src_idx += bits_per_line; diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c index 61b182bf32a2..dbfe4eecf12e 100644 --- a/drivers/video/console/bitblit.c +++ b/drivers/video/console/bitblit.c @@ -205,7 +205,6 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info, static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, int bottom_only) { - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; unsigned int cw = vc->vc_font.width; unsigned int ch = vc->vc_font.height; unsigned int rw = info->var.xres - (vc->vc_cols*cw); @@ -214,7 +213,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bs = info->var.yres - bh; struct fb_fillrect region; - region.color = attr_bgcol_ec(bgshift, vc, info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c index 41b32ae23dac..5a3cbf6dff4d 100644 --- a/drivers/video/console/fbcon_ccw.c +++ b/drivers/video/console/fbcon_ccw.c @@ -197,9 +197,8 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bh = info->var.xres - (vc->vc_rows*ch); unsigned int bs = vc->vc_rows*ch; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_cw.c b/drivers/video/console/fbcon_cw.c index a93670ef7f89..e7ee44db4e98 100644 --- a/drivers/video/console/fbcon_cw.c +++ b/drivers/video/console/fbcon_cw.c @@ -180,9 +180,8 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bh = info->var.xres - (vc->vc_rows*ch); unsigned int rs = info->var.yres - rw; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_ud.c b/drivers/video/console/fbcon_ud.c index ff0872c0498b..19e3714abfe8 100644 --- a/drivers/video/console/fbcon_ud.c +++ b/drivers/video/console/fbcon_ud.c @@ -227,9 +227,8 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int rw = info->var.xres - (vc->vc_cols*cw); unsigned int bh = info->var.yres - (vc->vc_rows*ch); struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/fb-puv3.c b/drivers/video/fb-puv3.c index 6db9ebd042a3..88fa2e70a0bb 100644 --- a/drivers/video/fb-puv3.c +++ b/drivers/video/fb-puv3.c @@ -18,8 +18,10 @@ #include <linux/fb.h> #include <linux/init.h> #include <linux/console.h> +#include <linux/mm.h> #include <asm/sizes.h> +#include <asm/pgtable.h> #include <mach/hardware.h> /* Platform_data reserved for unifb registers. */ diff --git a/drivers/video/matrox/matroxfb_accel.c b/drivers/video/matrox/matroxfb_accel.c index 8335a6fe303e..0d5cb85d071a 100644 --- a/drivers/video/matrox/matroxfb_accel.c +++ b/drivers/video/matrox/matroxfb_accel.c @@ -192,10 +192,18 @@ void matrox_cfbX_init(struct matrox_fb_info *minfo) minfo->accel.m_dwg_rect = M_DWG_TRAP | M_DWG_SOLID | M_DWG_ARZERO | M_DWG_SGNZERO | M_DWG_SHIFTZERO; if (isMilleniumII(minfo)) minfo->accel.m_dwg_rect |= M_DWG_TRANSC; minfo->accel.m_opmode = mopmode; + minfo->accel.m_access = maccess; + minfo->accel.m_pitch = mpitch; } EXPORT_SYMBOL(matrox_cfbX_init); +static void matrox_accel_restore_maccess(struct matrox_fb_info *minfo) +{ + mga_outl(M_MACCESS, minfo->accel.m_access); + mga_outl(M_PITCH, minfo->accel.m_pitch); +} + static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy, int sx, int dy, int dx, int height, int width) { @@ -207,7 +215,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy, CRITBEGIN if ((dy < sy) || ((dy == sy) && (dx <= sx))) { - mga_fifo(2); + mga_fifo(4); + matrox_accel_restore_maccess(minfo); mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO | M_DWG_BFCOL | M_DWG_REPLACE); mga_outl(M_AR5, vxres); @@ -215,7 +224,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy, start = sy*vxres+sx+curr_ydstorg(minfo); end = start+width; } else { - mga_fifo(3); + mga_fifo(5); + matrox_accel_restore_maccess(minfo); mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE); mga_outl(M_SGN, 5); mga_outl(M_AR5, -vxres); @@ -224,7 +234,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy, start = end+width; dy += height-1; } - mga_fifo(4); + mga_fifo(6); + matrox_accel_restore_maccess(minfo); mga_outl(M_AR0, end); mga_outl(M_AR3, start); mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx); @@ -246,7 +257,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres, CRITBEGIN if ((dy < sy) || ((dy == sy) && (dx <= sx))) { - mga_fifo(2); + mga_fifo(4); + matrox_accel_restore_maccess(minfo); mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO | M_DWG_BFCOL | M_DWG_REPLACE); mga_outl(M_AR5, vxres); @@ -254,7 +266,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres, start = sy*vxres+sx+curr_ydstorg(minfo); end = start+width; } else { - mga_fifo(3); + mga_fifo(5); + matrox_accel_restore_maccess(minfo); mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE); mga_outl(M_SGN, 5); mga_outl(M_AR5, -vxres); @@ -263,7 +276,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres, start = end+width; dy += height-1; } - mga_fifo(5); + mga_fifo(7); + matrox_accel_restore_maccess(minfo); mga_outl(M_AR0, end); mga_outl(M_AR3, start); mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx); @@ -298,7 +312,8 @@ static void matroxfb_accel_clear(struct matrox_fb_info *minfo, u_int32_t color, CRITBEGIN - mga_fifo(5); + mga_fifo(7); + matrox_accel_restore_maccess(minfo); mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE); mga_outl(M_FCOL, color); mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx); @@ -341,7 +356,8 @@ static void matroxfb_cfb4_clear(struct matrox_fb_info *minfo, u_int32_t bgx, width >>= 1; sx >>= 1; if (width) { - mga_fifo(5); + mga_fifo(7); + matrox_accel_restore_maccess(minfo); mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE2); mga_outl(M_FCOL, bgx); mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx); @@ -415,7 +431,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx, CRITBEGIN - mga_fifo(3); + mga_fifo(5); + matrox_accel_restore_maccess(minfo); if (easy) mga_outl(M_DWGCTL, M_DWG_ILOAD | M_DWG_SGNZERO | M_DWG_SHIFTZERO | M_DWG_BMONOWF | M_DWG_LINEAR | M_DWG_REPLACE); else @@ -425,7 +442,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx, fxbndry = ((xx + width - 1) << 16) | xx; mmio = minfo->mmio.vbase; - mga_fifo(6); + mga_fifo(8); + matrox_accel_restore_maccess(minfo); mga_writel(mmio, M_FXBNDRY, fxbndry); mga_writel(mmio, M_AR0, ar0); mga_writel(mmio, M_AR3, 0); diff --git a/drivers/video/matrox/matroxfb_base.h b/drivers/video/matrox/matroxfb_base.h index 11ed57bb704e..89a8a89a5eb2 100644 --- a/drivers/video/matrox/matroxfb_base.h +++ b/drivers/video/matrox/matroxfb_base.h @@ -307,6 +307,8 @@ struct matrox_accel_data { #endif u_int32_t m_dwg_rect; u_int32_t m_opmode; + u_int32_t m_access; + u_int32_t m_pitch; }; struct v4l2_queryctrl; @@ -696,7 +698,7 @@ void matroxfb_unregister_driver(struct matroxfb_driver* drv); #define mga_fifo(n) do {} while ((mga_inl(M_FIFOSTATUS) & 0xFF) < (n)) -#define WaitTillIdle() do {} while (mga_inl(M_STATUS) & 0x10000) +#define WaitTillIdle() do { mga_inl(M_STATUS); do {} while (mga_inl(M_STATUS) & 0x10000); } while (0) /* code speedup */ #ifdef CONFIG_FB_MATROX_MILLENIUM diff --git a/drivers/video/tgafb.c b/drivers/video/tgafb.c index 07c7df9ee77b..3d5bce517d8e 100644 --- a/drivers/video/tgafb.c +++ b/drivers/video/tgafb.c @@ -182,6 +182,8 @@ tgafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) if (var->xres_virtual != var->xres || var->yres_virtual != var->yres) return -EINVAL; + if (var->xres * var->yres * (var->bits_per_pixel >> 3) > info->fix.smem_len) + return -EINVAL; if (var->nonstd) return -EINVAL; if (1000000000 / var->pixclock > TGA_PLL_MAX_FREQ) @@ -262,6 +264,7 @@ tgafb_set_par(struct fb_info *info) par->yres = info->var.yres; par->pll_freq = pll_freq = 1000000000 / info->var.pixclock; par->bits_per_pixel = info->var.bits_per_pixel; + info->fix.line_length = par->xres * (par->bits_per_pixel >> 3); tga_type = par->tga_type; @@ -1136,222 +1139,57 @@ copyarea_line_32bpp(struct fb_info *info, u32 dy, u32 sy, __raw_writel(TGA_MODE_SBM_24BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG); } -/* The general case of forward copy in 8bpp mode. */ +/* The (almost) general case of backward copy in 8bpp mode. */ static inline void -copyarea_foreward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy, - u32 height, u32 width, u32 line_length) +copyarea_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy, + u32 height, u32 width, u32 line_length, + const struct fb_copyarea *area) { struct tga_par *par = (struct tga_par *) info->par; - unsigned long i, copied, left; - unsigned long dpos, spos, dalign, salign, yincr; - u32 smask_first, dmask_first, dmask_last; - int pixel_shift, need_prime, need_second; - unsigned long n64, n32, xincr_first; + unsigned i, yincr; + int depos, sepos, backward, last_step, step; + u32 mask_last; + unsigned n32; void __iomem *tga_regs; void __iomem *tga_fb; - yincr = line_length; - if (dy > sy) { - dy += height - 1; - sy += height - 1; - yincr = -yincr; - } - - /* Compute the offsets and alignments in the frame buffer. - More than anything else, these control how we do copies. */ - dpos = dy * line_length + dx; - spos = sy * line_length + sx; - dalign = dpos & 7; - salign = spos & 7; - dpos &= -8; - spos &= -8; - - /* Compute the value for the PIXELSHIFT register. This controls - both non-co-aligned source and destination and copy direction. */ - if (dalign >= salign) - pixel_shift = dalign - salign; - else - pixel_shift = 8 - (salign - dalign); - - /* Figure out if we need an additional priming step for the - residue register. */ - need_prime = (salign > dalign); - if (need_prime) - dpos -= 8; - - /* Begin by copying the leading unaligned destination. Copy enough - to make the next destination address 32-byte aligned. */ - copied = 32 - (dalign + (dpos & 31)); - if (copied == 32) - copied = 0; - xincr_first = (copied + 7) & -8; - smask_first = dmask_first = (1ul << copied) - 1; - smask_first <<= salign; - dmask_first <<= dalign + need_prime*8; - if (need_prime && copied > 24) - copied -= 8; - left = width - copied; - - /* Care for small copies. */ - if (copied > width) { - u32 t; - t = (1ul << width) - 1; - t <<= dalign + need_prime*8; - dmask_first &= t; - left = 0; - } - - /* Attempt to use 64-byte copies. This is only possible if the - source and destination are co-aligned at 64 bytes. */ - n64 = need_second = 0; - if ((dpos & 63) == (spos & 63) - && (height == 1 || line_length % 64 == 0)) { - /* We may need a 32-byte copy to ensure 64 byte alignment. */ - need_second = (dpos + xincr_first) & 63; - if ((need_second & 32) != need_second) - printk(KERN_ERR "tgafb: need_second wrong\n"); - if (left >= need_second + 64) { - left -= need_second; - n64 = left / 64; - left %= 64; - } else - need_second = 0; - } - - /* Copy trailing full 32-byte sections. This will be the main - loop if the 64 byte loop can't be used. */ - n32 = left / 32; - left %= 32; - - /* Copy the trailing unaligned destination. */ - dmask_last = (1ul << left) - 1; - - tga_regs = par->tga_regs_base; - tga_fb = par->tga_fb_base; - - /* Set up the MODE and PIXELSHIFT registers. */ - __raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_COPY, tga_regs+TGA_MODE_REG); - __raw_writel(pixel_shift, tga_regs+TGA_PIXELSHIFT_REG); - wmb(); - - for (i = 0; i < height; ++i) { - unsigned long j; - void __iomem *sfb; - void __iomem *dfb; - - sfb = tga_fb + spos; - dfb = tga_fb + dpos; - if (dmask_first) { - __raw_writel(smask_first, sfb); - wmb(); - __raw_writel(dmask_first, dfb); - wmb(); - sfb += xincr_first; - dfb += xincr_first; - } - - if (need_second) { - __raw_writel(0xffffffff, sfb); - wmb(); - __raw_writel(0xffffffff, dfb); - wmb(); - sfb += 32; - dfb += 32; - } - - if (n64 && (((unsigned long)sfb | (unsigned long)dfb) & 63)) - printk(KERN_ERR - "tgafb: misaligned copy64 (s:%p, d:%p)\n", - sfb, dfb); - - for (j = 0; j < n64; ++j) { - __raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC); - wmb(); - __raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST); - wmb(); - sfb += 64; - dfb += 64; - } - - for (j = 0; j < n32; ++j) { - __raw_writel(0xffffffff, sfb); - wmb(); - __raw_writel(0xffffffff, dfb); - wmb(); - sfb += 32; - dfb += 32; - } - - if (dmask_last) { - __raw_writel(0xffffffff, sfb); - wmb(); - __raw_writel(dmask_last, dfb); - wmb(); - } - - spos += yincr; - dpos += yincr; + /* Do acceleration only if we are aligned on 8 pixels */ + if ((dx | sx | width) & 7) { + cfb_copyarea(info, area); + return; } - /* Reset the MODE register to normal. */ - __raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG); -} - -/* The (almost) general case of backward copy in 8bpp mode. */ -static inline void -copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy, - u32 height, u32 width, u32 line_length, - const struct fb_copyarea *area) -{ - struct tga_par *par = (struct tga_par *) info->par; - unsigned long i, left, yincr; - unsigned long depos, sepos, dealign, sealign; - u32 mask_first, mask_last; - unsigned long n32; - void __iomem *tga_regs; - void __iomem *tga_fb; - yincr = line_length; if (dy > sy) { dy += height - 1; sy += height - 1; yincr = -yincr; } + backward = dy == sy && dx > sx && dx < sx + width; /* Compute the offsets and alignments in the frame buffer. More than anything else, these control how we do copies. */ - depos = dy * line_length + dx + width; - sepos = sy * line_length + sx + width; - dealign = depos & 7; - sealign = sepos & 7; - - /* ??? The documentation appears to be incorrect (or very - misleading) wrt how pixel shifting works in backward copy - mode, i.e. when PIXELSHIFT is negative. I give up for now. - Do handle the common case of co-aligned backward copies, - but frob everything else back on generic code. */ - if (dealign != sealign) { - cfb_copyarea(info, area); - return; - } - - /* We begin the copy with the trailing pixels of the - unaligned destination. */ - mask_first = (1ul << dealign) - 1; - left = width - dealign; - - /* Care for small copies. */ - if (dealign > width) { - mask_first ^= (1ul << (dealign - width)) - 1; - left = 0; - } + depos = dy * line_length + dx; + sepos = sy * line_length + sx; + if (backward) + depos += width, sepos += width; /* Next copy full words at a time. */ - n32 = left / 32; - left %= 32; + n32 = width / 32; + last_step = width % 32; /* Finally copy the unaligned head of the span. */ - mask_last = -1 << (32 - left); + mask_last = (1ul << last_step) - 1; + + if (!backward) { + step = 32; + last_step = 32; + } else { + step = -32; + last_step = -last_step; + sepos -= 32; + depos -= 32; + } tga_regs = par->tga_regs_base; tga_fb = par->tga_fb_base; @@ -1368,25 +1206,33 @@ copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy, sfb = tga_fb + sepos; dfb = tga_fb + depos; - if (mask_first) { - __raw_writel(mask_first, sfb); - wmb(); - __raw_writel(mask_first, dfb); - wmb(); - } - for (j = 0; j < n32; ++j) { - sfb -= 32; - dfb -= 32; + for (j = 0; j < n32; j++) { + if (j < 2 && j + 1 < n32 && !backward && + !(((unsigned long)sfb | (unsigned long)dfb) & 63)) { + do { + __raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC); + wmb(); + __raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST); + wmb(); + sfb += 64; + dfb += 64; + j += 2; + } while (j + 1 < n32); + j--; + continue; + } __raw_writel(0xffffffff, sfb); wmb(); __raw_writel(0xffffffff, dfb); wmb(); + sfb += step; + dfb += step; } if (mask_last) { - sfb -= 32; - dfb -= 32; + sfb += last_step - step; + dfb += last_step - step; __raw_writel(mask_last, sfb); wmb(); __raw_writel(mask_last, dfb); @@ -1447,14 +1293,9 @@ tgafb_copyarea(struct fb_info *info, const struct fb_copyarea *area) else if (bpp == 32) cfb_copyarea(info, area); - /* Detect overlapping source and destination that requires - a backward copy. */ - else if (dy == sy && dx > sx && dx < sx + width) - copyarea_backward_8bpp(info, dx, dy, sx, sy, height, - width, line_length, area); else - copyarea_foreward_8bpp(info, dx, dy, sx, sy, height, - width, line_length); + copyarea_8bpp(info, dx, dy, sx, sy, height, + width, line_length, area); } @@ -1470,6 +1311,7 @@ tgafb_init_fix(struct fb_info *info) int tga_bus_tc = TGA_BUS_TC(par->dev); u8 tga_type = par->tga_type; const char *tga_type_name = NULL; + unsigned memory_size; switch (tga_type) { case TGA_TYPE_8PLANE: @@ -1477,22 +1319,27 @@ tgafb_init_fix(struct fb_info *info) tga_type_name = "Digital ZLXp-E1"; if (tga_bus_tc) tga_type_name = "Digital ZLX-E1"; + memory_size = 2097152; break; case TGA_TYPE_24PLANE: if (tga_bus_pci) tga_type_name = "Digital ZLXp-E2"; if (tga_bus_tc) tga_type_name = "Digital ZLX-E2"; + memory_size = 8388608; break; case TGA_TYPE_24PLUSZ: if (tga_bus_pci) tga_type_name = "Digital ZLXp-E3"; if (tga_bus_tc) tga_type_name = "Digital ZLX-E3"; + memory_size = 16777216; break; } - if (!tga_type_name) + if (!tga_type_name) { tga_type_name = "Unknown"; + memory_size = 16777216; + } strlcpy(info->fix.id, tga_type_name, sizeof(info->fix.id)); @@ -1502,9 +1349,8 @@ tgafb_init_fix(struct fb_info *info) ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_DIRECTCOLOR); - info->fix.line_length = par->xres * (par->bits_per_pixel >> 3); info->fix.smem_start = (size_t) par->tga_fb_base; - info->fix.smem_len = info->fix.line_length * par->yres; + info->fix.smem_len = memory_size; info->fix.mmio_start = (size_t) par->tga_regs_base; info->fix.mmio_len = 512; @@ -1628,6 +1474,9 @@ static int tgafb_register(struct device *dev) modedb_tga = &modedb_tc; modedbsize_tga = 1; } + + tgafb_init_fix(info); + ret = fb_find_mode(&info->var, info, mode_option ? mode_option : mode_option_tga, modedb_tga, modedbsize_tga, NULL, @@ -1645,7 +1494,6 @@ static int tgafb_register(struct device *dev) } tgafb_set_par(info); - tgafb_init_fix(info); if (register_framebuffer(info) < 0) { printk(KERN_ERR "tgafb: Could not register framebuffer\n"); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 34bdabaecbd6..36e7859a31aa 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -310,6 +310,12 @@ static int balloon(void *_vballoon) else if (diff < 0) leak_balloon(vb, -diff); update_balloon_size(vb); + + /* + * For large balloon changes, we could spend a lot of time + * and always have work to do. Be nice if preempt disabled. + */ + cond_resched(); } return 0; } diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index a416f9b2a7f6..827b5f8e6297 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -791,6 +791,7 @@ static int virtio_pci_restore(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct virtio_driver *drv; + unsigned status = 0; int ret; drv = container_of(vp_dev->vdev.dev.driver, @@ -801,14 +802,40 @@ static int virtio_pci_restore(struct device *dev) return ret; pci_set_master(pci_dev); + /* We always start by resetting the device, in case a previous + * driver messed it up. */ + vp_reset(&vp_dev->vdev); + + /* Acknowledge that we've seen the device. */ + status |= VIRTIO_CONFIG_S_ACKNOWLEDGE; + vp_set_status(&vp_dev->vdev, status); + + /* Maybe driver failed before freeze. + * Restore the failed status, for debugging. */ + status |= vp_dev->saved_status & VIRTIO_CONFIG_S_FAILED; + vp_set_status(&vp_dev->vdev, status); + + if (!drv) + return 0; + + /* We have a driver! */ + status |= VIRTIO_CONFIG_S_DRIVER; + vp_set_status(&vp_dev->vdev, status); + vp_finalize_features(&vp_dev->vdev); - if (drv && drv->restore) + if (drv->restore) { ret = drv->restore(&vp_dev->vdev); + if (ret) { + status |= VIRTIO_CONFIG_S_FAILED; + vp_set_status(&vp_dev->vdev, status); + return ret; + } + } /* Finally, tell the device we're all set */ - if (!ret) - vp_set_status(&vp_dev->vdev, vp_dev->saved_status); + status |= VIRTIO_CONFIG_S_DRIVER_OK; + vp_set_status(&vp_dev->vdev, status); return ret; } diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c index 40788c925d1c..73705aff53cb 100644 --- a/drivers/w1/w1_netlink.c +++ b/drivers/w1/w1_netlink.c @@ -54,28 +54,29 @@ static void w1_send_slave(struct w1_master *dev, u64 rn) struct w1_netlink_msg *hdr = (struct w1_netlink_msg *)(msg + 1); struct w1_netlink_cmd *cmd = (struct w1_netlink_cmd *)(hdr + 1); int avail; + u64 *data; /* update kernel slave list */ w1_slave_found(dev, rn); avail = dev->priv_size - cmd->len; - if (avail > 8) { - u64 *data = (void *)(cmd + 1) + cmd->len; + if (avail < 8) { + msg->ack++; + cn_netlink_send(msg, 0, GFP_KERNEL); - *data = rn; - cmd->len += 8; - hdr->len += 8; - msg->len += 8; - return; + msg->len = sizeof(struct w1_netlink_msg) + + sizeof(struct w1_netlink_cmd); + hdr->len = sizeof(struct w1_netlink_cmd); + cmd->len = 0; } - msg->ack++; - cn_netlink_send(msg, 0, GFP_KERNEL); + data = (void *)(cmd + 1) + cmd->len; - msg->len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd); - hdr->len = sizeof(struct w1_netlink_cmd); - cmd->len = 0; + *data = rn; + cmd->len += 8; + hdr->len += 8; + msg->len += 8; } static int w1_process_search_command(struct w1_master *dev, struct cn_msg *msg, diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c index 9fa1f69dac13..61098cd5439e 100644 --- a/drivers/watchdog/ath79_wdt.c +++ b/drivers/watchdog/ath79_wdt.c @@ -20,6 +20,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitops.h> +#include <linux/delay.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/init.h> @@ -91,6 +92,15 @@ static inline void ath79_wdt_keepalive(void) static inline void ath79_wdt_enable(void) { ath79_wdt_keepalive(); + + /* + * Updating the TIMER register requires a few microseconds + * on the AR934x SoCs at least. Use a small delay to ensure + * that the TIMER register is updated within the hardware + * before enabling the watchdog. + */ + udelay(2); + ath79_wdt_wr(WDOG_REG_CTRL, WDOG_CTRL_ACTION_FCR); /* flush write */ ath79_wdt_rr(WDOG_REG_CTRL); diff --git a/drivers/watchdog/kempld_wdt.c b/drivers/watchdog/kempld_wdt.c index 20dc73844737..d9c1a1601926 100644 --- a/drivers/watchdog/kempld_wdt.c +++ b/drivers/watchdog/kempld_wdt.c @@ -162,7 +162,7 @@ static int kempld_wdt_set_stage_timeout(struct kempld_wdt_data *wdt_data, kempld_get_mutex(pld); stage_cfg = kempld_read8(pld, KEMPLD_WDT_STAGE_CFG(stage->id)); stage_cfg &= ~STAGE_CFG_PRESCALER_MASK; - stage_cfg |= STAGE_CFG_SET_PRESCALER(prescaler); + stage_cfg |= STAGE_CFG_SET_PRESCALER(PRESCALER_21); kempld_write8(pld, KEMPLD_WDT_STAGE_CFG(stage->id), stage_cfg); kempld_write32(pld, KEMPLD_WDT_STAGE_TIMEOUT(stage->id), stage_timeout); diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c index 3f786ce0a6f2..88bcdfb9f68f 100644 --- a/drivers/watchdog/sp805_wdt.c +++ b/drivers/watchdog/sp805_wdt.c @@ -60,7 +60,6 @@ * @adev: amba device structure of wdt * @status: current status of wdt * @load_val: load value to be set for current timeout - * @timeout: current programmed timeout */ struct sp805_wdt { struct watchdog_device wdd; @@ -69,7 +68,6 @@ struct sp805_wdt { struct clk *clk; struct amba_device *adev; unsigned int load_val; - unsigned int timeout; }; static bool nowayout = WATCHDOG_NOWAYOUT; @@ -99,7 +97,7 @@ static int wdt_setload(struct watchdog_device *wdd, unsigned int timeout) spin_lock(&wdt->lock); wdt->load_val = load; /* roundup timeout to closest positive integer value */ - wdt->timeout = div_u64((load + 1) * 2 + (rate / 2), rate); + wdd->timeout = div_u64((load + 1) * 2 + (rate / 2), rate); spin_unlock(&wdt->lock); return 0; diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 61a6ac8fa8fc..08834b565aab 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -426,20 +426,18 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) * p2m are consistent. */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { - unsigned long p; - struct page *scratch_page = get_balloon_scratch_page(); - if (!PageHighMem(page)) { + struct page *scratch_page = get_balloon_scratch_page(); + ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), pfn_pte(page_to_pfn(scratch_page), PAGE_KERNEL_RO), 0); BUG_ON(ret); - } - p = page_to_pfn(scratch_page); - __set_phys_to_machine(pfn, pfn_to_mfn(p)); - put_balloon_scratch_page(); + put_balloon_scratch_page(); + } + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } #endif diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 1de2a191b395..ef7d446e07ee 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -66,7 +66,21 @@ static DEFINE_PER_CPU(struct evtchn_fifo_queue, cpu_queue); static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly; static unsigned event_array_pages __read_mostly; +/* + * sync_set_bit() and friends must be unsigned long aligned. + */ +#if BITS_PER_LONG > 32 + +#define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL) +#define EVTCHN_FIFO_BIT(b, w) \ + (((unsigned long)w & 0x4UL) ? (EVTCHN_FIFO_ ##b + 32) : EVTCHN_FIFO_ ##b) + +#else + #define BM(w) ((unsigned long *)(w)) +#define EVTCHN_FIFO_BIT(b, w) EVTCHN_FIFO_ ##b + +#endif static inline event_word_t *event_word_from_port(unsigned port) { @@ -85,6 +99,25 @@ static unsigned evtchn_fifo_nr_channels(void) return event_array_pages * EVENT_WORDS_PER_PAGE; } +static int init_control_block(int cpu, + struct evtchn_fifo_control_block *control_block) +{ + struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); + struct evtchn_init_control init_control; + unsigned int i; + + /* Reset the control block and the local HEADs. */ + clear_page(control_block); + for (i = 0; i < EVTCHN_FIFO_MAX_QUEUES; i++) + q->head[i] = 0; + + init_control.control_gfn = virt_to_mfn(control_block); + init_control.offset = 0; + init_control.vcpu = cpu; + + return HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control); +} + static void free_unused_array_pages(void) { unsigned i; @@ -161,33 +194,38 @@ static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu) static void evtchn_fifo_clear_pending(unsigned port) { event_word_t *word = event_word_from_port(port); - sync_clear_bit(EVTCHN_FIFO_PENDING, BM(word)); + sync_clear_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } static void evtchn_fifo_set_pending(unsigned port) { event_word_t *word = event_word_from_port(port); - sync_set_bit(EVTCHN_FIFO_PENDING, BM(word)); + sync_set_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } static bool evtchn_fifo_is_pending(unsigned port) { event_word_t *word = event_word_from_port(port); - return sync_test_bit(EVTCHN_FIFO_PENDING, BM(word)); + return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } static bool evtchn_fifo_test_and_set_mask(unsigned port) { event_word_t *word = event_word_from_port(port); - return sync_test_and_set_bit(EVTCHN_FIFO_MASKED, BM(word)); + return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); } static void evtchn_fifo_mask(unsigned port) { event_word_t *word = event_word_from_port(port); - sync_set_bit(EVTCHN_FIFO_MASKED, BM(word)); + sync_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); } +static bool evtchn_fifo_is_masked(unsigned port) +{ + event_word_t *word = event_word_from_port(port); + return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); +} /* * Clear MASKED, spinning if BUSY is set. */ @@ -211,7 +249,7 @@ static void evtchn_fifo_unmask(unsigned port) BUG_ON(!irqs_disabled()); clear_masked(word); - if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))) { + if (evtchn_fifo_is_pending(port)) { struct evtchn_unmask unmask = { .port = port }; (void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask); } @@ -247,7 +285,7 @@ static void handle_irq_for_port(unsigned port) static void consume_one_event(unsigned cpu, struct evtchn_fifo_control_block *control_block, - unsigned priority, uint32_t *ready) + unsigned priority, unsigned long *ready) { struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); uint32_t head; @@ -277,10 +315,9 @@ static void consume_one_event(unsigned cpu, * copy of the ready word. */ if (head == 0) - clear_bit(priority, BM(ready)); + clear_bit(priority, ready); - if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word)) - && !sync_test_bit(EVTCHN_FIFO_MASKED, BM(word))) + if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) handle_irq_for_port(port); q->head[priority] = head; @@ -289,7 +326,7 @@ static void consume_one_event(unsigned cpu, static void evtchn_fifo_handle_events(unsigned cpu) { struct evtchn_fifo_control_block *control_block; - uint32_t ready; + unsigned long ready; unsigned q; control_block = per_cpu(cpu_control_block, cpu); @@ -309,7 +346,6 @@ static void evtchn_fifo_resume(void) for_each_possible_cpu(cpu) { void *control_block = per_cpu(cpu_control_block, cpu); - struct evtchn_init_control init_control; int ret; if (!control_block) @@ -326,12 +362,7 @@ static void evtchn_fifo_resume(void) continue; } - init_control.control_gfn = virt_to_mfn(control_block); - init_control.offset = 0; - init_control.vcpu = cpu; - - ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control, - &init_control); + ret = init_control_block(cpu, control_block); if (ret < 0) BUG(); } @@ -359,30 +390,25 @@ static const struct evtchn_ops evtchn_ops_fifo = { .resume = evtchn_fifo_resume, }; -static int evtchn_fifo_init_control_block(unsigned cpu) +static int evtchn_fifo_alloc_control_block(unsigned cpu) { - struct page *control_block = NULL; - struct evtchn_init_control init_control; + void *control_block = NULL; int ret = -ENOMEM; - control_block = alloc_page(GFP_KERNEL|__GFP_ZERO); + control_block = (void *)__get_free_page(GFP_KERNEL); if (control_block == NULL) goto error; - init_control.control_gfn = virt_to_mfn(page_address(control_block)); - init_control.offset = 0; - init_control.vcpu = cpu; - - ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control); + ret = init_control_block(cpu, control_block); if (ret < 0) goto error; - per_cpu(cpu_control_block, cpu) = page_address(control_block); + per_cpu(cpu_control_block, cpu) = control_block; return 0; error: - __free_page(control_block); + free_page((unsigned long)control_block); return ret; } @@ -396,7 +422,7 @@ static int evtchn_fifo_cpu_notification(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: if (!per_cpu(cpu_control_block, cpu)) - ret = evtchn_fifo_init_control_block(cpu); + ret = evtchn_fifo_alloc_control_block(cpu); break; default: break; @@ -413,7 +439,7 @@ int __init xen_evtchn_fifo_init(void) int cpu = get_cpu(); int ret; - ret = evtchn_fifo_init_control_block(cpu); + ret = evtchn_fifo_alloc_control_block(cpu); if (ret < 0) goto out; diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 624e8dc24532..602913d7ae03 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -111,16 +111,11 @@ static void do_suspend(void) shutting_down = SHUTDOWN_SUSPEND; -#ifdef CONFIG_PREEMPT - /* If the kernel is preemptible, we need to freeze all the processes - to prevent them from being in the middle of a pagetable update - during suspend. */ err = freeze_processes(); if (err) { pr_err("%s: freeze failed %d\n", __func__, err); goto out; } -#endif err = dpm_suspend_start(PMSG_FREEZE); if (err) { @@ -169,10 +164,8 @@ out_resume: dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE); out_thaw: -#ifdef CONFIG_PREEMPT thaw_processes(); out: -#endif shutting_down = SHUTDOWN_INVALID; } #endif /* CONFIG_HIBERNATE_CALLBACKS */ diff --git a/fs/affs/super.c b/fs/affs/super.c index d098731b82ff..9a5b19dc899d 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -336,8 +336,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) &blocksize,&sbi->s_prefix, sbi->s_volume, &mount_flags)) { printk(KERN_ERR "AFFS: Error parsing options\n"); - kfree(sbi->s_prefix); - kfree(sbi); return -EINVAL; } /* N.B. after this point s_prefix must be released */ @@ -52,7 +52,8 @@ struct aio_ring { unsigned id; /* kernel internal index number */ unsigned nr; /* number of io_events */ - unsigned head; + unsigned head; /* Written to by userland or under ring_lock + * mutex by aio_read_events_ring(). */ unsigned tail; unsigned magic; @@ -111,6 +112,11 @@ struct kioctx { struct work_struct free_work; + /* + * signals when all in-flight requests are done + */ + struct completion *requests_done; + struct { /* * This counts the number of available slots in the ringbuffer, @@ -135,6 +141,7 @@ struct kioctx { struct { unsigned tail; + unsigned completed_events; spinlock_t completion_lock; } ____cacheline_aligned_in_smp; @@ -243,6 +250,11 @@ static void aio_free_ring(struct kioctx *ctx) { int i; + /* Disconnect the kiotx from the ring file. This prevents future + * accesses to the kioctx from page migration. + */ + put_aio_ring_file(ctx); + for (i = 0; i < ctx->nr_pages; i++) { struct page *page; pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i, @@ -254,8 +266,6 @@ static void aio_free_ring(struct kioctx *ctx) put_page(page); } - put_aio_ring_file(ctx); - if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) { kfree(ctx->ring_pages); ctx->ring_pages = NULL; @@ -283,29 +293,38 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, { struct kioctx *ctx; unsigned long flags; + pgoff_t idx; int rc; rc = 0; - /* Make sure the old page hasn't already been changed */ + /* mapping->private_lock here protects against the kioctx teardown. */ spin_lock(&mapping->private_lock); ctx = mapping->private_data; - if (ctx) { - pgoff_t idx; - spin_lock_irqsave(&ctx->completion_lock, flags); - idx = old->index; - if (idx < (pgoff_t)ctx->nr_pages) { - if (ctx->ring_pages[idx] != old) - rc = -EAGAIN; - } else - rc = -EINVAL; - spin_unlock_irqrestore(&ctx->completion_lock, flags); + if (!ctx) { + rc = -EINVAL; + goto out; + } + + /* The ring_lock mutex. The prevents aio_read_events() from writing + * to the ring's head, and prevents page migration from mucking in + * a partially initialized kiotx. + */ + if (!mutex_trylock(&ctx->ring_lock)) { + rc = -EAGAIN; + goto out; + } + + idx = old->index; + if (idx < (pgoff_t)ctx->nr_pages) { + /* Make sure the old page hasn't already been changed */ + if (ctx->ring_pages[idx] != old) + rc = -EAGAIN; } else rc = -EINVAL; - spin_unlock(&mapping->private_lock); if (rc != 0) - return rc; + goto out_unlock; /* Writeback must be complete */ BUG_ON(PageWriteback(old)); @@ -314,38 +333,26 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1); if (rc != MIGRATEPAGE_SUCCESS) { put_page(new); - return rc; + goto out_unlock; } - /* We can potentially race against kioctx teardown here. Use the - * address_space's private data lock to protect the mapping's - * private_data. + /* Take completion_lock to prevent other writes to the ring buffer + * while the old page is copied to the new. This prevents new + * events from being lost. */ - spin_lock(&mapping->private_lock); - ctx = mapping->private_data; - if (ctx) { - pgoff_t idx; - spin_lock_irqsave(&ctx->completion_lock, flags); - migrate_page_copy(new, old); - idx = old->index; - if (idx < (pgoff_t)ctx->nr_pages) { - /* And only do the move if things haven't changed */ - if (ctx->ring_pages[idx] == old) - ctx->ring_pages[idx] = new; - else - rc = -EAGAIN; - } else - rc = -EINVAL; - spin_unlock_irqrestore(&ctx->completion_lock, flags); - } else - rc = -EBUSY; - spin_unlock(&mapping->private_lock); + spin_lock_irqsave(&ctx->completion_lock, flags); + migrate_page_copy(new, old); + BUG_ON(ctx->ring_pages[idx] != old); + ctx->ring_pages[idx] = new; + spin_unlock_irqrestore(&ctx->completion_lock, flags); - if (rc == MIGRATEPAGE_SUCCESS) - put_page(old); - else - put_page(new); + /* The old page is no longer accessible. */ + put_page(old); +out_unlock: + mutex_unlock(&ctx->ring_lock); +out: + spin_unlock(&mapping->private_lock); return rc; } #endif @@ -380,7 +387,7 @@ static int aio_setup_ring(struct kioctx *ctx) file = aio_private_file(ctx, nr_pages); if (IS_ERR(file)) { ctx->aio_ring_file = NULL; - return -EAGAIN; + return -ENOMEM; } ctx->aio_ring_file = file; @@ -415,7 +422,7 @@ static int aio_setup_ring(struct kioctx *ctx) if (unlikely(i != nr_pages)) { aio_free_ring(ctx); - return -EAGAIN; + return -ENOMEM; } ctx->mmap_size = nr_pages * PAGE_SIZE; @@ -429,7 +436,7 @@ static int aio_setup_ring(struct kioctx *ctx) if (IS_ERR((void *)ctx->mmap_base)) { ctx->mmap_size = 0; aio_free_ring(ctx); - return -EAGAIN; + return -ENOMEM; } pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); @@ -507,6 +514,10 @@ static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); + /* At this point we know that there are no any in-flight requests */ + if (ctx->requests_done) + complete(ctx->requests_done); + INIT_WORK(&ctx->free_work, free_ioctx); schedule_work(&ctx->free_work); } @@ -556,6 +567,10 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); + /* While kioctx setup is in progress, + * we are protected from page migration + * changes ring_pages by ->ring_lock. + */ ring = kmap_atomic(ctx->ring_pages[0]); ring->id = ctx->id; kunmap_atomic(ring); @@ -640,24 +655,28 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) ctx->max_reqs = nr_events; - if (percpu_ref_init(&ctx->users, free_ioctx_users)) - goto err; - - if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs)) - goto err; - spin_lock_init(&ctx->ctx_lock); spin_lock_init(&ctx->completion_lock); mutex_init(&ctx->ring_lock); + /* Protect against page migration throughout kiotx setup by keeping + * the ring_lock mutex held until setup is complete. */ + mutex_lock(&ctx->ring_lock); init_waitqueue_head(&ctx->wait); INIT_LIST_HEAD(&ctx->active_reqs); + if (percpu_ref_init(&ctx->users, free_ioctx_users)) + goto err; + + if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs)) + goto err; + ctx->cpu = alloc_percpu(struct kioctx_cpu); if (!ctx->cpu) goto err; - if (aio_setup_ring(ctx) < 0) + err = aio_setup_ring(ctx); + if (err < 0) goto err; atomic_set(&ctx->reqs_available, ctx->nr_events - 1); @@ -683,6 +702,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) if (err) goto err_cleanup; + /* Release the ring_lock mutex now that all setup is complete. */ + mutex_unlock(&ctx->ring_lock); + pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", ctx, ctx->user_id, mm, ctx->nr_events); return ctx; @@ -692,6 +714,7 @@ err_cleanup: err_ctx: aio_free_ring(ctx); err: + mutex_unlock(&ctx->ring_lock); free_percpu(ctx->cpu); free_percpu(ctx->reqs.pcpu_count); free_percpu(ctx->users.pcpu_count); @@ -705,7 +728,8 @@ err: * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ -static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) +static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, + struct completion *requests_done) { if (!atomic_xchg(&ctx->dead, 1)) { struct kioctx_table *table; @@ -734,7 +758,11 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); + ctx->requests_done = requests_done; percpu_ref_kill(&ctx->users); + } else { + if (requests_done) + complete(requests_done); } } @@ -769,6 +797,9 @@ void exit_aio(struct mm_struct *mm) unsigned i = 0; while (1) { + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); @@ -796,23 +827,30 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx); + kill_ioctx(mm, ctx, &requests_done); + + /* Wait until all IO for the context are done. */ + wait_for_completion(&requests_done); } } static void put_reqs_available(struct kioctx *ctx, unsigned nr) { struct kioctx_cpu *kcpu; + unsigned long flags; preempt_disable(); kcpu = this_cpu_ptr(ctx->cpu); + local_irq_save(flags); kcpu->reqs_available += nr; + while (kcpu->reqs_available >= ctx->req_batch * 2) { kcpu->reqs_available -= ctx->req_batch; atomic_add(ctx->req_batch, &ctx->reqs_available); } + local_irq_restore(flags); preempt_enable(); } @@ -820,10 +858,12 @@ static bool get_reqs_available(struct kioctx *ctx) { struct kioctx_cpu *kcpu; bool ret = false; + unsigned long flags; preempt_disable(); kcpu = this_cpu_ptr(ctx->cpu); + local_irq_save(flags); if (!kcpu->reqs_available) { int old, avail = atomic_read(&ctx->reqs_available); @@ -842,10 +882,73 @@ static bool get_reqs_available(struct kioctx *ctx) ret = true; kcpu->reqs_available--; out: + local_irq_restore(flags); preempt_enable(); return ret; } +/* refill_reqs_available + * Updates the reqs_available reference counts used for tracking the + * number of free slots in the completion ring. This can be called + * from aio_complete() (to optimistically update reqs_available) or + * from aio_get_req() (the we're out of events case). It must be + * called holding ctx->completion_lock. + */ +static void refill_reqs_available(struct kioctx *ctx, unsigned head, + unsigned tail) +{ + unsigned events_in_ring, completed; + + /* Clamp head since userland can write to it. */ + head %= ctx->nr_events; + if (head <= tail) + events_in_ring = tail - head; + else + events_in_ring = ctx->nr_events - (head - tail); + + completed = ctx->completed_events; + if (events_in_ring < completed) + completed -= events_in_ring; + else + completed = 0; + + if (!completed) + return; + + ctx->completed_events -= completed; + put_reqs_available(ctx, completed); +} + +/* user_refill_reqs_available + * Called to refill reqs_available when aio_get_req() encounters an + * out of space in the completion ring. + */ +static void user_refill_reqs_available(struct kioctx *ctx) +{ + spin_lock_irq(&ctx->completion_lock); + if (ctx->completed_events) { + struct aio_ring *ring; + unsigned head; + + /* Access of ring->head may race with aio_read_events_ring() + * here, but that's okay since whether we read the old version + * or the new version, and either will be valid. The important + * part is that head cannot pass tail since we prevent + * aio_complete() from updating tail by holding + * ctx->completion_lock. Even if head is invalid, the check + * against ctx->completed_events below will make sure we do the + * safe/right thing. + */ + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; + kunmap_atomic(ring); + + refill_reqs_available(ctx, head, ctx->tail); + } + + spin_unlock_irq(&ctx->completion_lock); +} + /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. @@ -854,8 +957,11 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx) { struct kiocb *req; - if (!get_reqs_available(ctx)) - return NULL; + if (!get_reqs_available(ctx)) { + user_refill_reqs_available(ctx); + if (!get_reqs_available(ctx)) + return NULL; + } req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO); if (unlikely(!req)) @@ -914,8 +1020,8 @@ void aio_complete(struct kiocb *iocb, long res, long res2) struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; + unsigned tail, pos, head; unsigned long flags; - unsigned tail, pos; /* * Special case handling for sync iocbs: @@ -976,10 +1082,14 @@ void aio_complete(struct kiocb *iocb, long res, long res2) ctx->tail = tail; ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; ring->tail = tail; kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); + ctx->completed_events++; + if (ctx->completed_events > 1) + refill_reqs_available(ctx, head, tail); spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); @@ -1024,16 +1134,26 @@ static long aio_read_events_ring(struct kioctx *ctx, mutex_lock(&ctx->ring_lock); + /* Access to ->ring_pages here is protected by ctx->ring_lock. */ ring = kmap_atomic(ctx->ring_pages[0]); head = ring->head; tail = ring->tail; kunmap_atomic(ring); + /* + * Ensure that once we've read the current tail pointer, that + * we also see the events that were stored up to the tail. + */ + smp_rmb(); + pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events); if (head == tail) goto out; + head %= ctx->nr_events; + tail %= ctx->nr_events; + while (ret < nr) { long avail; struct io_event *ev; @@ -1072,8 +1192,6 @@ static long aio_read_events_ring(struct kioctx *ctx, flush_dcache_page(ctx->ring_pages[0]); pr_debug("%li h%u t%u\n", ret, head, tail); - - put_reqs_available(ctx, ret); out: mutex_unlock(&ctx->ring_lock); @@ -1171,7 +1289,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) - kill_ioctx(current->mm, ioctx); + kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } @@ -1189,8 +1307,22 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { - kill_ioctx(current->mm, ioctx); + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + + /* Pass requests_done to kill_ioctx() where it can be set + * in a thread-safe way. If we try to set it here then we have + * a race condition if two io_destroy() called simultaneously. + */ + kill_ioctx(current->mm, ioctx, &requests_done); percpu_ref_put(&ioctx->users); + + /* Wait until all IO for the context are done. Otherwise kernel + * keep using user-space buffers even if user thinks the context + * is destroyed. + */ + wait_for_completion(&requests_done); + return 0; } pr_debug("EINVAL: io_destroy: invalid context id\n"); @@ -1285,10 +1417,8 @@ rw_common: &iovec, compat) : aio_setup_single_vector(req, rw, buf, &nr_segs, iovec); - if (ret) - return ret; - - ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); + if (!ret) + ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); if (ret < 0) { if (iovec != &inline_vec) kfree(iovec); diff --git a/fs/attr.c b/fs/attr.c index 5d4e59d56e85..6530ced19697 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -50,14 +50,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) if ((ia_valid & ATTR_UID) && (!uid_eq(current_fsuid(), inode->i_uid) || !uid_eq(attr->ia_uid, inode->i_uid)) && - !inode_capable(inode, CAP_CHOWN)) + !capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && (!uid_eq(current_fsuid(), inode->i_uid) || (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) && - !inode_capable(inode, CAP_CHOWN)) + !capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return -EPERM; /* Make sure a caller can chmod. */ @@ -67,7 +67,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* Also check the setgid bit! */ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : inode->i_gid) && - !inode_capable(inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) attr->ia_mode &= ~S_ISGID; } @@ -160,7 +160,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr) umode_t mode = attr->ia_mode; if (!in_group_p(inode->i_gid) && - !inode_capable(inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 2caf36ac3e93..cc87c1abac97 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -179,7 +179,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry) spin_lock(&active->d_lock); /* Already gone? */ - if (!d_count(active)) + if ((int) d_count(active) <= 0) goto next; qstr = &active->d_name; @@ -230,7 +230,7 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry) spin_lock(&expiring->d_lock); - /* Bad luck, we've already been dentry_iput */ + /* We've already been dentry_iput or unlinked */ if (!expiring->d_inode) goto next; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index aded3ef3d3d4..6244f9cf8ae3 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -275,9 +275,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, } if (ret > 0) goto next; - ret = ulist_add_merge(parents, eb->start, - (uintptr_t)eie, - (u64 *)&old, GFP_NOFS); + ret = ulist_add_merge_ptr(parents, eb->start, + eie, (void **)&old, GFP_NOFS); if (ret < 0) break; if (!ret && extent_item_pos) { @@ -972,11 +971,12 @@ again: goto out; } if (ref->count && ref->parent) { - if (extent_item_pos && !ref->inode_list) { + if (extent_item_pos && !ref->inode_list && + ref->level == 0) { u32 bsz; struct extent_buffer *eb; bsz = btrfs_level_size(fs_info->extent_root, - info_level); + ref->level); eb = read_tree_block(fs_info->extent_root, ref->parent, bsz, 0); if (!eb || !extent_buffer_uptodate(eb)) { @@ -984,16 +984,19 @@ again: ret = -EIO; goto out; } + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); ret = find_extent_in_eb(eb, bytenr, *extent_item_pos, &eie); + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); if (ret < 0) goto out; ref->inode_list = eie; } - ret = ulist_add_merge(refs, ref->parent, - (uintptr_t)ref->inode_list, - (u64 *)&eie, GFP_NOFS); + ret = ulist_add_merge_ptr(refs, ref->parent, + ref->inode_list, + (void **)&eie, GFP_NOFS); if (ret < 0) goto out; if (!ret && extent_item_pos) { @@ -1411,9 +1414,10 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, * returns <0 on error */ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, - struct btrfs_extent_item *ei, u32 item_size, - struct btrfs_extent_inline_ref **out_eiref, - int *out_type) + struct btrfs_key *key, + struct btrfs_extent_item *ei, u32 item_size, + struct btrfs_extent_inline_ref **out_eiref, + int *out_type) { unsigned long end; u64 flags; @@ -1423,19 +1427,26 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, /* first call */ flags = btrfs_extent_flags(eb, ei); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { - info = (struct btrfs_tree_block_info *)(ei + 1); - *out_eiref = - (struct btrfs_extent_inline_ref *)(info + 1); + if (key->type == BTRFS_METADATA_ITEM_KEY) { + /* a skinny metadata extent */ + *out_eiref = + (struct btrfs_extent_inline_ref *)(ei + 1); + } else { + WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY); + info = (struct btrfs_tree_block_info *)(ei + 1); + *out_eiref = + (struct btrfs_extent_inline_ref *)(info + 1); + } } else { *out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1); } *ptr = (unsigned long)*out_eiref; - if ((void *)*ptr >= (void *)ei + item_size) + if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size) return -ENOENT; } end = (unsigned long)ei + item_size; - *out_eiref = (struct btrfs_extent_inline_ref *)*ptr; + *out_eiref = (struct btrfs_extent_inline_ref *)(*ptr); *out_type = btrfs_extent_inline_ref_type(eb, *out_eiref); *ptr += btrfs_extent_inline_ref_size(*out_type); @@ -1454,8 +1465,8 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, * <0 on error. */ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, - struct btrfs_extent_item *ei, u32 item_size, - u64 *out_root, u8 *out_level) + struct btrfs_key *key, struct btrfs_extent_item *ei, + u32 item_size, u64 *out_root, u8 *out_level) { int ret; int type; @@ -1466,8 +1477,8 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, return 1; while (1) { - ret = __get_extent_inline_ref(ptr, eb, ei, item_size, - &eiref, &type); + ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size, + &eiref, &type); if (ret < 0) return ret; diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index a910b27a8ad9..519b49e51f57 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -40,8 +40,8 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, u64 *flags); int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, - struct btrfs_extent_item *ei, u32 item_size, - u64 *out_root, u8 *out_level); + struct btrfs_key *key, struct btrfs_extent_item *ei, + u32 item_size, u64 *out_root, u8 *out_level); int iterate_extent_inodes(struct btrfs_fs_info *fs_info, u64 extent_item_objectid, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2c1a42ca519f..d3511cc17091 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1104,6 +1104,12 @@ struct btrfs_qgroup_limit_item { __le64 rsv_excl; } __attribute__ ((__packed__)); +/* For raid type sysfs entries */ +struct raid_kobject { + int raid_type; + struct kobject kobj; +}; + struct btrfs_space_info { spinlock_t lock; @@ -1154,7 +1160,7 @@ struct btrfs_space_info { wait_queue_head_t wait; struct kobject kobj; - struct kobject block_group_kobjs[BTRFS_NR_RAID_TYPES]; + struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES]; }; #define BTRFS_BLOCK_RSV_GLOBAL 1 diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 81ea55314b1f..370ef7450157 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3244,6 +3244,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info) /* send down all the barriers */ head = &info->fs_devices->devices; list_for_each_entry_rcu(dev, head, dev_list) { + if (dev->missing) + continue; if (!dev->bdev) { errors_send++; continue; @@ -3258,6 +3260,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info) /* wait for all the barriers */ list_for_each_entry_rcu(dev, head, dev_list) { + if (dev->missing) + continue; if (!dev->bdev) { errors_wait++; continue; @@ -3594,6 +3598,11 @@ int close_ctree(struct btrfs_root *root) btrfs_free_block_groups(fs_info); + /* + * we must make sure there is not any read request to + * submit after we stopping all workers. + */ + invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); free_root_pointers(fs_info, 1); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 32312e09f0f5..3ff98e23f651 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2444,7 +2444,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, spin_unlock(&locked_ref->lock); spin_lock(&delayed_refs->lock); spin_lock(&locked_ref->lock); - if (rb_first(&locked_ref->ref_root)) { + if (rb_first(&locked_ref->ref_root) || + locked_ref->extent_op) { spin_unlock(&locked_ref->lock); spin_unlock(&delayed_refs->lock); continue; @@ -3399,10 +3400,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, return ret; } - for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) { + for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) INIT_LIST_HEAD(&found->block_groups[i]); - kobject_init(&found->block_group_kobjs[i], &btrfs_raid_ktype); - } init_rwsem(&found->groups_sem); spin_lock_init(&found->lock); found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; @@ -8327,8 +8326,9 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) list_del(&space_info->list); for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) { struct kobject *kobj; - kobj = &space_info->block_group_kobjs[i]; - if (kobj->parent) { + kobj = space_info->block_group_kobjs[i]; + space_info->block_group_kobjs[i] = NULL; + if (kobj) { kobject_del(kobj); kobject_put(kobj); } @@ -8343,22 +8343,35 @@ static void __link_block_group(struct btrfs_space_info *space_info, struct btrfs_block_group_cache *cache) { int index = get_block_group_index(cache); + bool first = false; down_write(&space_info->groups_sem); - if (list_empty(&space_info->block_groups[index])) { - struct kobject *kobj = &space_info->block_group_kobjs[index]; + if (list_empty(&space_info->block_groups[index])) + first = true; + list_add_tail(&cache->list, &space_info->block_groups[index]); + up_write(&space_info->groups_sem); + + if (first) { + struct raid_kobject *rkobj; int ret; - kobject_get(&space_info->kobj); /* put in release */ - ret = kobject_add(kobj, &space_info->kobj, "%s", - get_raid_name(index)); + rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS); + if (!rkobj) + goto out_err; + rkobj->raid_type = index; + kobject_init(&rkobj->kobj, &btrfs_raid_ktype); + ret = kobject_add(&rkobj->kobj, &space_info->kobj, + "%s", get_raid_name(index)); if (ret) { - pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n"); - kobject_put(&space_info->kobj); + kobject_put(&rkobj->kobj); + goto out_err; } + space_info->block_group_kobjs[index] = &rkobj->kobj; } - list_add_tail(&cache->list, &space_info->block_groups[index]); - up_write(&space_info->groups_sem); + + return; +out_err: + pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n"); } static struct btrfs_block_group_cache * @@ -8693,6 +8706,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *tree_root = root->fs_info->tree_root; struct btrfs_key key; struct inode *inode; + struct kobject *kobj = NULL; int ret; int index; int factor; @@ -8792,11 +8806,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, */ list_del_init(&block_group->list); if (list_empty(&block_group->space_info->block_groups[index])) { - kobject_del(&block_group->space_info->block_group_kobjs[index]); - kobject_put(&block_group->space_info->block_group_kobjs[index]); + kobj = block_group->space_info->block_group_kobjs[index]; + block_group->space_info->block_group_kobjs[index] = NULL; clear_avail_alloc_bits(root->fs_info, block_group->flags); } up_write(&block_group->space_info->groups_sem); + if (kobj) { + kobject_del(kobj); + kobject_put(kobj); + } if (block_group->cached == BTRFS_CACHE_STARTED) wait_block_group_cache_done(block_group); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 85bbd01f1271..1a858947006e 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1686,6 +1686,7 @@ again: * shortening the size of the delalloc range we're searching */ free_extent_state(cached_state); + cached_state = NULL; if (!loops) { max_bytes = PAGE_CACHE_SIZE; loops = 1; @@ -2346,7 +2347,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end) { int uptodate = (err == 0); struct extent_io_tree *tree; - int ret; + int ret = 0; tree = &BTRFS_I(page->mapping->host)->io_tree; @@ -2360,6 +2361,8 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end) if (!uptodate) { ClearPageUptodate(page); SetPageError(page); + ret = ret < 0 ? ret : -EIO; + mapping_set_error(page->mapping, ret); } return 0; } @@ -2522,6 +2525,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) test_bit(BIO_UPTODATE, &bio->bi_flags); if (err) uptodate = 0; + offset += len; continue; } } diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 127555b29f58..196b089b0052 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -423,7 +423,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, ret = 0; fail: while (ret < 0 && !list_empty(&tmplist)) { - sums = list_entry(&tmplist, struct btrfs_ordered_sum, list); + sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list); list_del(&sums->list); kfree(sums); } @@ -756,7 +756,7 @@ again: found_next = 1; if (ret != 0) goto insert; - slot = 0; + slot = path->slots[0]; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0165b8672f09..a9a881ed8cbe 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2510,23 +2510,28 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_map *em = NULL; struct extent_state *cached_state = NULL; - u64 lockstart = *offset; - u64 lockend = i_size_read(inode); - u64 start = *offset; - u64 len = i_size_read(inode); + u64 lockstart; + u64 lockend; + u64 start; + u64 len; int ret = 0; - lockend = max_t(u64, root->sectorsize, lockend); + if (inode->i_size == 0) + return -ENXIO; + + /* + * *offset can be negative, in this case we start finding DATA/HOLE from + * the very start of the file. + */ + start = max_t(loff_t, 0, *offset); + + lockstart = round_down(start, root->sectorsize); + lockend = round_up(i_size_read(inode), root->sectorsize); if (lockend <= lockstart) lockend = lockstart + root->sectorsize; - lockend--; len = lockend - lockstart + 1; - len = max_t(u64, len, root->sectorsize); - if (inode->i_size == 0) - return -ENXIO; - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0, &cached_state); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 73f3de7a083c..a6bd654dcd47 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -831,7 +831,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, if (!matched) { __btrfs_remove_free_space_cache(ctl); - btrfs_err(fs_info, "block group %llu has wrong amount of free space", + btrfs_warn(fs_info, "block group %llu has wrong amount of free space", block_group->key.objectid); ret = -1; } @@ -843,7 +843,7 @@ out: spin_unlock(&block_group->lock); ret = 0; - btrfs_err(fs_info, "failed to load free space cache for block group %llu", + btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now", block_group->key.objectid); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d3d44486290b..d68a7250f00b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -701,6 +701,18 @@ retry: unlock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); + + /* + * we need to redirty the pages if we decide to + * fallback to uncompressed IO, otherwise we + * will not submit these pages down to lower + * layers. + */ + extent_range_redirty_for_io(inode, + async_extent->start, + async_extent->start + + async_extent->ram_size - 1); + goto retry; } goto out_free; @@ -3584,7 +3596,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, * without delay */ if (!btrfs_is_free_space_inode(inode) - && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { + && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID + && !root->fs_info->log_root_recovering) { btrfs_update_root_times(trans, root); ret = btrfs_delayed_update_inode(trans, root, inode); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a6d8efa46bfe..0b72006aecbe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -302,6 +302,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) goto out_drop; } else { + ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0); + if (ret && ret != -ENODATA) + goto out_drop; ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } @@ -4750,6 +4753,12 @@ long btrfs_ioctl(struct file *file, unsigned int if (ret) return ret; ret = btrfs_sync_fs(file->f_dentry->d_sb, 1); + /* + * The transaction thread may want to do more work, + * namely it pokes the cleaner ktread that will start + * processing uncleaned subvols. + */ + wake_up_process(root->fs_info->transaction_kthread); return ret; } case BTRFS_IOC_START_SYNC: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 07b3b36f40ee..01f977e3ce09 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -736,7 +736,8 @@ again: err = ret; goto out; } - BUG_ON(!ret || !path1->slots[0]); + ASSERT(ret); + ASSERT(path1->slots[0]); path1->slots[0]--; @@ -746,10 +747,10 @@ again: * the backref was added previously when processing * backref of type BTRFS_TREE_BLOCK_REF_KEY */ - BUG_ON(!list_is_singular(&cur->upper)); + ASSERT(list_is_singular(&cur->upper)); edge = list_entry(cur->upper.next, struct backref_edge, list[LOWER]); - BUG_ON(!list_empty(&edge->list[UPPER])); + ASSERT(list_empty(&edge->list[UPPER])); exist = edge->node[UPPER]; /* * add the upper level block to pending list if we need @@ -831,7 +832,7 @@ again: cur->cowonly = 1; } #else - BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY); + ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY); if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) { #endif if (key.objectid == key.offset) { @@ -840,7 +841,7 @@ again: * backref of this type. */ root = find_reloc_root(rc, cur->bytenr); - BUG_ON(!root); + ASSERT(root); cur->root = root; break; } @@ -868,7 +869,7 @@ again: } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); } list_add_tail(&edge->list[LOWER], &cur->upper); @@ -892,7 +893,7 @@ again: if (btrfs_root_level(&root->root_item) == cur->level) { /* tree root */ - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == cur->bytenr); if (should_ignore_root(root)) list_add(&cur->list, &useless); @@ -927,7 +928,7 @@ again: need_check = true; for (; level < BTRFS_MAX_LEVEL; level++) { if (!path2->nodes[level]) { - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == lower->bytenr); if (should_ignore_root(root)) list_add(&lower->list, &useless); @@ -976,12 +977,15 @@ again: need_check = false; list_add_tail(&edge->list[UPPER], &list); - } else + } else { + if (upper->checked) + need_check = true; INIT_LIST_HEAD(&edge->list[UPPER]); + } } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); if (!upper->owner) upper->owner = btrfs_header_owner(eb); @@ -1025,7 +1029,7 @@ next: * everything goes well, connect backref nodes and insert backref nodes * into the cache. */ - BUG_ON(!node->checked); + ASSERT(node->checked); cowonly = node->cowonly; if (!cowonly) { rb_node = tree_insert(&cache->rb_root, node->bytenr, @@ -1061,8 +1065,21 @@ next: continue; } - BUG_ON(!upper->checked); - BUG_ON(cowonly != upper->cowonly); + if (!upper->checked) { + /* + * Still want to blow up for developers since this is a + * logic bug. + */ + ASSERT(0); + err = -EINVAL; + goto out; + } + if (cowonly != upper->cowonly) { + ASSERT(0); + err = -EINVAL; + goto out; + } + if (!cowonly) { rb_node = tree_insert(&cache->rb_root, upper->bytenr, &upper->rb_node); @@ -1085,7 +1102,7 @@ next: while (!list_empty(&useless)) { upper = list_entry(useless.next, struct backref_node, list); list_del_init(&upper->list); - BUG_ON(!list_empty(&upper->upper)); + ASSERT(list_empty(&upper->upper)); if (upper == node) node = NULL; if (upper->lowest) { @@ -1118,29 +1135,45 @@ out: if (err) { while (!list_empty(&useless)) { lower = list_entry(useless.next, - struct backref_node, upper); - list_del_init(&lower->upper); + struct backref_node, list); + list_del_init(&lower->list); } - upper = node; - INIT_LIST_HEAD(&list); - while (upper) { - if (RB_EMPTY_NODE(&upper->rb_node)) { - list_splice_tail(&upper->upper, &list); - free_backref_node(cache, upper); - } - - if (list_empty(&list)) - break; - - edge = list_entry(list.next, struct backref_edge, - list[LOWER]); + while (!list_empty(&list)) { + edge = list_first_entry(&list, struct backref_edge, + list[UPPER]); + list_del(&edge->list[UPPER]); list_del(&edge->list[LOWER]); + lower = edge->node[LOWER]; upper = edge->node[UPPER]; free_backref_edge(cache, edge); + + /* + * Lower is no longer linked to any upper backref nodes + * and isn't in the cache, we can free it ourselves. + */ + if (list_empty(&lower->upper) && + RB_EMPTY_NODE(&lower->rb_node)) + list_add(&lower->list, &useless); + + if (!RB_EMPTY_NODE(&upper->rb_node)) + continue; + + /* Add this guy's upper edges to the list to proces */ + list_for_each_entry(edge, &upper->upper, list[LOWER]) + list_add_tail(&edge->list[UPPER], &list); + if (list_empty(&upper->upper)) + list_add(&upper->list, &useless); + } + + while (!list_empty(&useless)) { + lower = list_entry(useless.next, + struct backref_node, list); + list_del_init(&lower->list); + free_backref_node(cache, lower); } return ERR_PTR(err); } - BUG_ON(node && node->detached); + ASSERT(!node || !node->detached); return node; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index efba5d1282ee..f6666d9b41cf 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -577,8 +577,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { do { - ret = tree_backref_for_extent(&ptr, eb, ei, item_size, - &ref_root, &ref_level); + ret = tree_backref_for_extent(&ptr, eb, &found_key, ei, + item_size, &ref_root, + &ref_level); printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev %s, " "sector %llu: metadata %s (level %d) in tree " diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 9dde9717c1b9..20d793542096 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1589,6 +1589,10 @@ static int lookup_dir_item_inode(struct btrfs_root *root, goto out; } btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key); + if (key.type == BTRFS_ROOT_ITEM_KEY) { + ret = -ENOENT; + goto out; + } *found_inode = key.objectid; *found_type = btrfs_dir_type(path->nodes[0], di); @@ -4724,7 +4728,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (S_ISREG(sctx->cur_inode_mode)) { if (need_send_hole(sctx)) { - if (sctx->cur_inode_last_extent == (u64)-1) { + if (sctx->cur_inode_last_extent == (u64)-1 || + sctx->cur_inode_last_extent < + sctx->cur_inode_size) { ret = get_last_extent(sctx, (u64)-1); if (ret) goto out; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 865f4cf9a769..ff286f372ff4 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -253,6 +253,7 @@ static ssize_t global_rsv_reserved_show(struct kobject *kobj, BTRFS_ATTR(global_rsv_reserved, 0444, global_rsv_reserved_show); #define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj) +#define to_raid_kobj(_kobj) container_of(_kobj, struct raid_kobject, kobj) static ssize_t raid_bytes_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf); @@ -265,7 +266,7 @@ static ssize_t raid_bytes_show(struct kobject *kobj, { struct btrfs_space_info *sinfo = to_space_info(kobj->parent); struct btrfs_block_group_cache *block_group; - int index = kobj - sinfo->block_group_kobjs; + int index = to_raid_kobj(kobj)->raid_type; u64 val = 0; down_read(&sinfo->groups_sem); @@ -287,7 +288,7 @@ static struct attribute *raid_attributes[] = { static void release_raid_kobj(struct kobject *kobj) { - kobject_put(kobj->parent); + kfree(to_raid_kobj(kobj)); } struct kobj_type btrfs_raid_ktype = { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 34cd83184c4a..a0b65a01fed7 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -592,7 +592,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) if (transid <= root->fs_info->last_trans_committed) goto out; - ret = -EINVAL; /* find specified transaction */ spin_lock(&root->fs_info->trans_lock); list_for_each_entry(t, &root->fs_info->trans_list, list) { @@ -608,9 +607,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) } } spin_unlock(&root->fs_info->trans_lock); - /* The specified transaction doesn't exist */ - if (!cur_trans) + + /* + * The specified transaction doesn't exist, or we + * raced with btrfs_commit_transaction + */ + if (!cur_trans) { + if (transid > root->fs_info->last_trans_committed) + ret = -EINVAL; goto out; + } } else { /* find newest transaction that is committing | committed */ spin_lock(&root->fs_info->trans_lock); @@ -683,7 +689,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, int lock = (trans->type != TRANS_JOIN_NOLOCK); int err = 0; - if (--trans->use_count) { + if (trans->use_count > 1) { + trans->use_count--; trans->block_rsv = trans->orig_rsv; return 0; } @@ -731,17 +738,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, } if (lock && ACCESS_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { - if (throttle) { - /* - * We may race with somebody else here so end up having - * to call end_transaction on ourselves again, so inc - * our use_count. - */ - trans->use_count++; + if (throttle) return btrfs_commit_transaction(trans, root); - } else { + else wake_up_process(info->transaction_kthread); - } } if (trans->type & __TRANS_FREEZABLE) diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h index 7f78cbf5cf41..4c29db604bbe 100644 --- a/fs/btrfs/ulist.h +++ b/fs/btrfs/ulist.h @@ -57,6 +57,21 @@ void ulist_free(struct ulist *ulist); int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask); int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux, u64 *old_aux, gfp_t gfp_mask); + +/* just like ulist_add_merge() but take a pointer for the aux data */ +static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux, + void **old_aux, gfp_t gfp_mask) +{ +#if BITS_PER_LONG == 32 + u64 old64 = (uintptr_t)*old_aux; + int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask); + *old_aux = (void *)((uintptr_t)old64); + return ret; +#else + return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask); +#endif +} + struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_iterator *uiter); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bab0b84d8f80..e46d3d72a9c9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1438,6 +1438,22 @@ out: return ret; } +/* + * Function to update ctime/mtime for a given device path. + * Mainly used for ctime/mtime based probe like libblkid. + */ +static void update_dev_time(char *path_name) +{ + struct file *filp; + + filp = filp_open(path_name, O_RDWR, 0); + if (!filp) + return; + file_update_time(filp); + filp_close(filp, NULL); + return; +} + static int btrfs_rm_dev_item(struct btrfs_root *root, struct btrfs_device *device) { @@ -1660,11 +1676,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) struct btrfs_fs_devices *fs_devices; fs_devices = root->fs_info->fs_devices; while (fs_devices) { - if (fs_devices->seed == cur_devices) + if (fs_devices->seed == cur_devices) { + fs_devices->seed = cur_devices->seed; break; + } fs_devices = fs_devices->seed; } - fs_devices->seed = cur_devices->seed; cur_devices->seed = NULL; lock_chunks(root); __btrfs_close_devices(cur_devices); @@ -1690,10 +1707,14 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) ret = 0; - /* Notify udev that device has changed */ - if (bdev) + if (bdev) { + /* Notify udev that device has changed */ btrfs_kobject_uevent(bdev, KOBJ_CHANGE); + /* Update ctime/mtime for device path for libblkid */ + update_dev_time(device_path); + } + error_brelse: brelse(bh); if (bdev) @@ -1869,7 +1890,6 @@ static int btrfs_prepare_sprout(struct btrfs_root *root) fs_devices->seeding = 0; fs_devices->num_devices = 0; fs_devices->open_devices = 0; - fs_devices->total_devices = 0; fs_devices->seed = seed_devices; generate_random_uuid(fs_devices->fsid); @@ -2132,6 +2152,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_commit_transaction(trans, root); } + /* Update ctime/mtime for libblkid */ + update_dev_time(device_path); return ret; error_trans: @@ -6035,10 +6057,14 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info) struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; - mutex_lock(&fs_devices->device_list_mutex); - list_for_each_entry(device, &fs_devices->devices, dev_list) - device->dev_root = fs_info->dev_root; - mutex_unlock(&fs_devices->device_list_mutex); + while (fs_devices) { + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) + device->dev_root = fs_info->dev_root; + mutex_unlock(&fs_devices->device_list_mutex); + + fs_devices = fs_devices->seed; + } } static void __btrfs_reset_dev_stats(struct btrfs_device *dev) diff --git a/fs/buffer.c b/fs/buffer.c index 27265a8b43c1..4d06a573d199 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1029,7 +1029,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, - index << sizebits, size); + (sector_t)index << sizebits, + size); goto done; } if (!try_to_free_buffers(page)) @@ -1050,7 +1051,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); - end_block = init_page_buffers(page, bdev, index << sizebits, size); + end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, + size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; @@ -2075,6 +2077,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int i_size_changed = 0; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); @@ -2094,6 +2097,8 @@ int generic_write_end(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock @@ -2311,6 +2316,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, err = 0; balance_dirty_pages_ratelimited(mapping); + + if (unlikely(fatal_signal_pending(current))) { + err = -EINTR; + goto out; + } } /* page covers the boundary, find the boundary offset */ diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 45eda6d7a40c..5e0982aa7000 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -446,7 +446,6 @@ more: if (atomic_read(&ci->i_release_count) == fi->dir_release_count) { dout(" marking %p complete\n", inode); __ceph_dir_set_complete(ci, fi->dir_release_count); - ci->i_max_offset = ctx->pos; } spin_unlock(&ci->i_ceph_lock); @@ -932,14 +931,16 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, * to do it here. */ - /* d_move screws up d_subdirs order */ - ceph_dir_clear_complete(new_dir); - d_move(old_dentry, new_dentry); /* ensure target dentry is invalidated, despite rehashing bug in vfs_rename_dir */ ceph_invalidate_dentry_lease(new_dentry); + + /* d_move screws up sibling dentries' offsets */ + ceph_dir_clear_complete(old_dir); + ceph_dir_clear_complete(new_dir); + } ceph_mdsc_put_request(req); return err; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 32d519d8a2e2..6471f9c83428 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -752,7 +752,6 @@ static int fill_inode(struct inode *inode, !__ceph_dir_is_complete(ci)) { dout(" marking %p complete (empty)\n", inode); __ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count)); - ci->i_max_offset = 2; } no_change: spin_unlock(&ci->i_ceph_lock); @@ -890,41 +889,6 @@ out_unlock: } /* - * Set dentry's directory position based on the current dir's max, and - * order it in d_subdirs, so that dcache_readdir behaves. - * - * Always called under directory's i_mutex. - */ -static void ceph_set_dentry_offset(struct dentry *dn) -{ - struct dentry *dir = dn->d_parent; - struct inode *inode = dir->d_inode; - struct ceph_inode_info *ci; - struct ceph_dentry_info *di; - - BUG_ON(!inode); - - ci = ceph_inode(inode); - di = ceph_dentry(dn); - - spin_lock(&ci->i_ceph_lock); - if (!__ceph_dir_is_complete(ci)) { - spin_unlock(&ci->i_ceph_lock); - return; - } - di->offset = ceph_inode(inode)->i_max_offset++; - spin_unlock(&ci->i_ceph_lock); - - spin_lock(&dir->d_lock); - spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &dir->d_subdirs); - dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset, - dn->d_u.d_child.prev, dn->d_u.d_child.next); - spin_unlock(&dn->d_lock); - spin_unlock(&dir->d_lock); -} - -/* * splice a dentry to an inode. * caller must hold directory i_mutex for this to be safe. * @@ -933,7 +897,7 @@ static void ceph_set_dentry_offset(struct dentry *dn) * the caller) if we fail. */ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, - bool *prehash, bool set_offset) + bool *prehash) { struct dentry *realdn; @@ -965,8 +929,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, } if ((!prehash || *prehash) && d_unhashed(dn)) d_rehash(dn); - if (set_offset) - ceph_set_dentry_offset(dn); out: return dn; } @@ -987,7 +949,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, { struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info; struct inode *in = NULL; - struct ceph_mds_reply_inode *ininfo; struct ceph_vino vino; struct ceph_fs_client *fsc = ceph_sb_to_client(sb); int err = 0; @@ -1112,6 +1073,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, /* rename? */ if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) { + struct inode *olddir = req->r_old_dentry_dir; + BUG_ON(!olddir); + dout(" src %p '%.*s' dst %p '%.*s'\n", req->r_old_dentry, req->r_old_dentry->d_name.len, @@ -1131,13 +1095,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, rehashing bug in vfs_rename_dir */ ceph_invalidate_dentry_lease(dn); - /* - * d_move() puts the renamed dentry at the end of - * d_subdirs. We need to assign it an appropriate - * directory offset so we can behave when dir is - * complete. - */ - ceph_set_dentry_offset(req->r_old_dentry); + /* d_move screws up sibling dentries' offsets */ + ceph_dir_clear_complete(dir); + ceph_dir_clear_complete(olddir); + dout("dn %p gets new offset %lld\n", req->r_old_dentry, ceph_dentry(req->r_old_dentry)->offset); @@ -1164,8 +1125,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, /* attach proper inode */ if (!dn->d_inode) { + ceph_dir_clear_complete(dir); ihold(in); - dn = splice_dentry(dn, in, &have_lease, true); + dn = splice_dentry(dn, in, &have_lease); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1186,17 +1148,16 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, (req->r_op == CEPH_MDS_OP_LOOKUPSNAP || req->r_op == CEPH_MDS_OP_MKSNAP)) { struct dentry *dn = req->r_dentry; + struct inode *dir = req->r_locked_dir; /* fill out a snapdir LOOKUPSNAP dentry */ BUG_ON(!dn); - BUG_ON(!req->r_locked_dir); - BUG_ON(ceph_snap(req->r_locked_dir) != CEPH_SNAPDIR); - ininfo = rinfo->targeti.in; - vino.ino = le64_to_cpu(ininfo->ino); - vino.snap = le64_to_cpu(ininfo->snapid); + BUG_ON(!dir); + BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR); dout(" linking snapped dir %p to dn %p\n", in, dn); + ceph_dir_clear_complete(dir); ihold(in); - dn = splice_dentry(dn, in, NULL, true); + dn = splice_dentry(dn, in, NULL); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1358,7 +1319,7 @@ retry_lookup: } if (!dn->d_inode) { - dn = splice_dentry(dn, in, NULL, false); + dn = splice_dentry(dn, in, NULL); if (IS_ERR(dn)) { err = PTR_ERR(dn); dn = NULL; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index d8801a95b685..df2caa84b94f 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -266,7 +266,6 @@ struct ceph_inode_info { struct timespec i_rctime; u64 i_rbytes, i_rfiles, i_rsubdirs; u64 i_files, i_subdirs; - u64 i_max_offset; /* largest readdir offset, set with complete dir */ struct rb_root i_fragtree; struct mutex i_fragtree_mutex; diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 0227b45ef00a..15e9505aa35f 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -290,7 +290,8 @@ int cifsConvertToUTF16(__le16 *target, const char *source, int srclen, const struct nls_table *cp, int mapChars) { - int i, j, charlen; + int i, charlen; + int j = 0; char src_char; __le16 dst_char; wchar_t tmp; @@ -298,12 +299,11 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, if (!mapChars) return cifs_strtoUTF16(target, source, PATH_MAX, cp); - for (i = 0, j = 0; i < srclen; j++) { + for (i = 0; i < srclen; j++) { src_char = source[i]; charlen = 1; switch (src_char) { case 0: - put_unaligned(0, &target[j]); goto ctoUTF16_out; case ':': dst_char = cpu_to_le16(UNI_COLON); @@ -350,6 +350,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, } ctoUTF16_out: + put_unaligned(0, &target[j]); /* Null terminate target unicode string */ return j; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 849f6132b327..7c6b73c72210 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -253,6 +253,11 @@ cifs_alloc_inode(struct super_block *sb) cifs_set_oplock_level(cifs_inode, 0); cifs_inode->delete_pending = false; cifs_inode->invalid_mapping = false; + clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cifs_inode->flags); + clear_bit(CIFS_INODE_PENDING_WRITERS, &cifs_inode->flags); + clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cifs_inode->flags); + spin_lock_init(&cifs_inode->writers_lock); + cifs_inode->writers = 0; cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ cifs_inode->server_eof = 0; cifs_inode->uniqueid = 0; @@ -731,19 +736,26 @@ static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = file_inode(iocb->ki_filp); + struct cifsInodeInfo *cinode = CIFS_I(inode); ssize_t written; int rc; + written = cifs_get_writer(cinode); + if (written) + return written; + written = generic_file_aio_write(iocb, iov, nr_segs, pos); if (CIFS_CACHE_WRITE(CIFS_I(inode))) - return written; + goto out; rc = filemap_fdatawrite(inode->i_mapping); if (rc) cifs_dbg(FYI, "cifs_file_aio_write: %d rc on %p inode\n", rc, inode); +out: + cifs_put_writer(cinode); return written; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index c0f3718b77a8..5d12d69e2045 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -70,11 +70,6 @@ #define SERVER_NAME_LENGTH 40 #define SERVER_NAME_LEN_WITH_NULL (SERVER_NAME_LENGTH + 1) -/* used to define string lengths for reversing unicode strings */ -/* (256+1)*2 = 514 */ -/* (max path length + 1 for null) * 2 for unicode */ -#define MAX_NAME 514 - /* SMB echo "timeout" -- FIXME: tunable? */ #define SMB_ECHO_INTERVAL (60 * HZ) @@ -228,6 +223,8 @@ struct smb_version_operations { /* verify the message */ int (*check_message)(char *, unsigned int); bool (*is_oplock_break)(char *, struct TCP_Server_Info *); + void (*downgrade_oplock)(struct TCP_Server_Info *, + struct cifsInodeInfo *, bool); /* process transaction2 response */ bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *, char *, int); @@ -402,6 +399,8 @@ struct smb_version_operations { const struct cifs_fid *, u32 *); int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, int); + /* check if we need to issue closedir */ + bool (*dir_needs_close)(struct cifsFileInfo *); }; struct smb_version_values { @@ -1113,6 +1112,12 @@ struct cifsInodeInfo { unsigned int epoch; /* used to track lease state changes */ bool delete_pending; /* DELETE_ON_CLOSE is set */ bool invalid_mapping; /* pagecache is invalid */ + unsigned long flags; +#define CIFS_INODE_PENDING_OPLOCK_BREAK (0) /* oplock break in progress */ +#define CIFS_INODE_PENDING_WRITERS (1) /* Writes in progress */ +#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */ + spinlock_t writers_lock; + unsigned int writers; /* Number of writers on this inode */ unsigned long time; /* jiffies of last update of inode */ u64 server_eof; /* current file size on server -- protected by i_lock */ u64 uniqueid; /* server inode number */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index acc4ee8ed075..ca7980a1e303 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -127,6 +127,9 @@ extern u64 cifs_UnixTimeToNT(struct timespec); extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset); extern void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock); +extern int cifs_get_writer(struct cifsInodeInfo *cinode); +extern void cifs_put_writer(struct cifsInodeInfo *cinode); +extern void cifs_done_oplock_break(struct cifsInodeInfo *cinode); extern int cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 834fce759d80..d375322b6cec 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -762,7 +762,7 @@ int cifs_closedir(struct inode *inode, struct file *file) cifs_dbg(FYI, "Freeing private data in close dir\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); if (server->ops->close_dir) @@ -2608,12 +2608,20 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); ssize_t written; + written = cifs_get_writer(cinode); + if (written) + return written; + if (CIFS_CACHE_WRITE(cinode)) { if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) - && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) - return generic_file_aio_write(iocb, iov, nr_segs, pos); - return cifs_writev(iocb, iov, nr_segs, pos); + && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { + written = generic_file_aio_write( + iocb, iov, nr_segs, pos); + goto out; + } + written = cifs_writev(iocb, iov, nr_segs, pos); + goto out; } /* * For non-oplocked files in strict cache mode we need to write the data @@ -2633,6 +2641,8 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, inode); cinode->oplock = 0; } +out: + cifs_put_writer(cinode); return written; } @@ -2834,7 +2844,7 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server, total_read += result; } - return total_read > 0 ? total_read : result; + return total_read > 0 && result != -EAGAIN ? total_read : result; } static ssize_t @@ -3257,7 +3267,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, total_read += result; } - return total_read > 0 ? total_read : result; + return total_read > 0 && result != -EAGAIN ? total_read : result; } static int cifs_readpages(struct file *file, struct address_space *mapping, @@ -3644,6 +3654,13 @@ static int cifs_launder_page(struct page *page) return rc; } +static int +cifs_pending_writers_wait(void *unused) +{ + schedule(); + return 0; +} + void cifs_oplock_break(struct work_struct *work) { struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, @@ -3651,8 +3668,15 @@ void cifs_oplock_break(struct work_struct *work) struct inode *inode = cfile->dentry->d_inode; struct cifsInodeInfo *cinode = CIFS_I(inode); struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); + struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; + wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, + cifs_pending_writers_wait, TASK_UNINTERRUPTIBLE); + + server->ops->downgrade_oplock(server, cinode, + test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags)); + if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) && cifs_has_mand_locks(cinode)) { cifs_dbg(FYI, "Reset oplock to None for inode=%p due to mand locks\n", @@ -3689,6 +3713,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + cifs_done_oplock_break(cinode); } /* diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index aadc2b68678b..f2ddcf7ac9c3 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1706,13 +1706,22 @@ cifs_rename(struct inode *source_dir, struct dentry *source_dentry, unlink_target: /* Try unlinking the target dentry if it's not negative */ if (target_dentry->d_inode && (rc == -EACCES || rc == -EEXIST)) { - tmprc = cifs_unlink(target_dir, target_dentry); + if (d_is_dir(target_dentry)) + tmprc = cifs_rmdir(target_dir, target_dentry); + else + tmprc = cifs_unlink(target_dir, target_dentry); if (tmprc) goto cifs_rename_exit; rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); } + /* force revalidate to go get info when needed */ + CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0; + + source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime = + target_dir->i_mtime = current_fs_time(source_dir->i_sb); + cifs_rename_exit: kfree(info_buf_source); kfree(from_name); diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 264ece71bdb2..a5c2812ead68 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -213,8 +213,12 @@ create_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon, if (rc) goto out; - rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, cifs_sb, - fromName, buf, &bytes_written); + if (tcon->ses->server->ops->create_mf_symlink) + rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, + cifs_sb, fromName, buf, &bytes_written); + else + rc = -EOPNOTSUPP; + if (rc) goto out; @@ -374,7 +378,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; oparms.create_options = create_options; - oparms.disposition = FILE_OPEN; + oparms.disposition = FILE_CREATE; oparms.path = path; oparms.fid = &fid; oparms.reconnect = false; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 2f9f3790679d..3b0c62e622da 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -466,8 +466,22 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) cifs_dbg(FYI, "file id match, oplock break\n"); pCifsInode = CIFS_I(netfile->dentry->d_inode); - cifs_set_oplock_level(pCifsInode, - pSMB->OplockLevel ? OPLOCK_READ : 0); + set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, + &pCifsInode->flags); + + /* + * Set flag if the server downgrades the oplock + * to L2 else clear. + */ + if (pSMB->OplockLevel) + set_bit( + CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &pCifsInode->flags); + else + clear_bit( + CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &pCifsInode->flags); + queue_work(cifsiod_wq, &netfile->oplock_break); netfile->oplock_break_cancelled = false; @@ -551,6 +565,62 @@ void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock) cinode->oplock = 0; } +static int +cifs_oplock_break_wait(void *unused) +{ + schedule(); + return signal_pending(current) ? -ERESTARTSYS : 0; +} + +/* + * We wait for oplock breaks to be processed before we attempt to perform + * writes. + */ +int cifs_get_writer(struct cifsInodeInfo *cinode) +{ + int rc; + +start: + rc = wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK, + cifs_oplock_break_wait, TASK_KILLABLE); + if (rc) + return rc; + + spin_lock(&cinode->writers_lock); + if (!cinode->writers) + set_bit(CIFS_INODE_PENDING_WRITERS, &cinode->flags); + cinode->writers++; + /* Check to see if we have started servicing an oplock break */ + if (test_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags)) { + cinode->writers--; + if (cinode->writers == 0) { + clear_bit(CIFS_INODE_PENDING_WRITERS, &cinode->flags); + wake_up_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS); + } + spin_unlock(&cinode->writers_lock); + goto start; + } + spin_unlock(&cinode->writers_lock); + return 0; +} + +void cifs_put_writer(struct cifsInodeInfo *cinode) +{ + spin_lock(&cinode->writers_lock); + cinode->writers--; + if (cinode->writers == 0) { + clear_bit(CIFS_INODE_PENDING_WRITERS, &cinode->flags); + wake_up_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS); + } + spin_unlock(&cinode->writers_lock); +} + +void cifs_done_oplock_break(struct cifsInodeInfo *cinode) +{ + clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); + wake_up_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK); +} + bool backup_cred(struct cifs_sb_info *cifs_sb) { diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index b15862e0f68c..b334a89d6a66 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -593,11 +593,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, /* close and restart search */ cifs_dbg(FYI, "search backing up - close and restart search\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); - if (server->ops->close) - server->ops->close(xid, tcon, &cfile->fid); + if (server->ops->close_dir) + server->ops->close_dir(xid, tcon, &cfile->fid); } else spin_unlock(&cifs_file_list_lock); if (cfile->srch_inf.ntwrk_buf_start) { diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 526fb89f9230..e9ad8d37bb00 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -372,6 +372,16 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr) return 0; } +static void +cifs_downgrade_oplock(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, bool set_level2) +{ + if (set_level2) + cifs_set_oplock_level(cinode, OPLOCK_READ); + else + cifs_set_oplock_level(cinode, 0); +} + static bool cifs_check_trans2(struct mid_q_entry *mid, struct TCP_Server_Info *server, char *buf, int malformed) @@ -576,7 +586,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, tmprc = CIFS_open(xid, &oparms, &oplock, NULL); if (tmprc == -EOPNOTSUPP) *symlink = true; - else + else if (tmprc == 0) CIFSSMBClose(xid, tcon, fid.netfid); } @@ -999,6 +1009,12 @@ cifs_is_read_op(__u32 oplock) return oplock == OPLOCK_READ; } +static bool +cifs_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1019,6 +1035,7 @@ struct smb_version_operations smb1_operations = { .clear_stats = cifs_clear_stats, .print_stats = cifs_print_stats, .is_oplock_break = is_valid_oplock_break, + .downgrade_oplock = cifs_downgrade_oplock, .check_trans2 = cifs_check_trans2, .need_neg = cifs_need_neg, .negotiate = cifs_negotiate, @@ -1067,6 +1084,7 @@ struct smb_version_operations smb1_operations = { .query_mf_symlink = cifs_query_mf_symlink, .create_mf_symlink = cifs_create_mf_symlink, .is_read_op = cifs_is_read_op, + .dir_needs_close = cifs_dir_needs_close, #ifdef CONFIG_CIFS_XATTR .query_all_EAs = CIFSSMBQAllEAs, .set_EA = CIFSSMBSetEA, diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 3f17b4550831..45992944e238 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -50,7 +50,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, goto out; } - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, GFP_KERNEL); if (smb2_data == NULL) { rc = -ENOMEM; diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 84c012a6aba0..215f8d3e3e53 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -131,7 +131,7 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, *adjust_tz = false; *symlink = false; - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, GFP_KERNEL); if (smb2_data == NULL) return -ENOMEM; diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 94bd4fbb13d3..a491814cb2c0 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -214,7 +214,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"}, {STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"}, {STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"}, - {STATUS_NO_MORE_FILES, -EIO, "STATUS_NO_MORE_FILES"}, + {STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"}, {STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"}, {STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"}, {STATUS_NO_INHERITANCE, -EIO, "STATUS_NO_INHERITANCE"}, @@ -256,6 +256,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_DLL_MIGHT_BE_INCOMPATIBLE, -EIO, "STATUS_DLL_MIGHT_BE_INCOMPATIBLE"}, {STATUS_STOPPED_ON_SYMLINK, -EOPNOTSUPP, "STATUS_STOPPED_ON_SYMLINK"}, + {STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EOPNOTSUPP, + "STATUS_REPARSE_NOT_HANDLED"}, {STATUS_DEVICE_REQUIRES_CLEANING, -EIO, "STATUS_DEVICE_REQUIRES_CLEANING"}, {STATUS_DEVICE_DOOR_OPEN, -EIO, "STATUS_DEVICE_DOOR_OPEN"}, @@ -605,7 +607,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_MAPPED_FILE_SIZE_ZERO, -EIO, "STATUS_MAPPED_FILE_SIZE_ZERO"}, {STATUS_TOO_MANY_OPENED_FILES, -EMFILE, "STATUS_TOO_MANY_OPENED_FILES"}, {STATUS_CANCELLED, -EIO, "STATUS_CANCELLED"}, - {STATUS_CANNOT_DELETE, -EIO, "STATUS_CANNOT_DELETE"}, + {STATUS_CANNOT_DELETE, -EACCES, "STATUS_CANNOT_DELETE"}, {STATUS_INVALID_COMPUTER_NAME, -EIO, "STATUS_INVALID_COMPUTER_NAME"}, {STATUS_FILE_DELETED, -EIO, "STATUS_FILE_DELETED"}, {STATUS_SPECIAL_ACCOUNT, -EIO, "STATUS_SPECIAL_ACCOUNT"}, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index fb3966265b6e..b8021fde987d 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -575,9 +575,21 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) else cfile->oplock_break_cancelled = false; - server->ops->set_oplock_level(cinode, - rsp->OplockLevel ? SMB2_OPLOCK_LEVEL_II : 0, - 0, NULL); + set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, + &cinode->flags); + + /* + * Set flag if the server downgrades the oplock + * to L2 else clear. + */ + if (rsp->OplockLevel) + set_bit( + CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &cinode->flags); + else + clear_bit( + CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &cinode->flags); queue_work(cifsiod_wq, &cfile->oplock_break); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 192f51a12cf1..34a17d425be6 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -339,7 +339,7 @@ smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, int rc; struct smb2_file_all_info *smb2_data; - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, GFP_KERNEL); if (smb2_data == NULL) return -ENOMEM; @@ -905,6 +905,17 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, } static void +smb2_downgrade_oplock(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, bool set_level2) +{ + if (set_level2) + server->ops->set_oplock_level(cinode, SMB2_OPLOCK_LEVEL_II, + 0, NULL); + else + server->ops->set_oplock_level(cinode, 0, 0, NULL); +} + +static void smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int epoch, bool *purge_cache) { @@ -1091,6 +1102,12 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch) return le32_to_cpu(lc->lcontext.LeaseState); } +static bool +smb2_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->invalidHandle; +} + struct smb_version_operations smb20_operations = { .compare_fids = smb2_compare_fids, .setup_request = smb2_setup_request, @@ -1110,6 +1127,7 @@ struct smb_version_operations smb20_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -1163,6 +1181,7 @@ struct smb_version_operations smb20_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb21_operations = { @@ -1184,6 +1203,7 @@ struct smb_version_operations smb21_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -1237,6 +1257,7 @@ struct smb_version_operations smb21_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb30_operations = { @@ -1259,6 +1280,7 @@ 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, + .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -1314,6 +1336,7 @@ struct smb_version_operations smb30_operations = { .parse_lease_buf = smb3_parse_lease_buf, .clone_range = smb2_clone_range, .validate_negotiate = smb3_validate_negotiate, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 860344701067..348792911e1f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -916,7 +916,8 @@ tcon_exit: tcon_error_exit: if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) { cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); - tcon->bad_network_name = true; + if (tcon) + tcon->bad_network_name = true; } goto tcon_exit; } @@ -1089,6 +1090,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, int rc = 0; unsigned int num_iovecs = 2; __u32 file_attributes = 0; + char *dhc_buf = NULL, *lc_buf = NULL; cifs_dbg(FYI, "create/open\n"); @@ -1155,6 +1157,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, kfree(copy_path); return rc; } + lc_buf = iov[num_iovecs-1].iov_base; } if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) { @@ -1169,9 +1172,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, if (rc) { cifs_small_buf_release(req); kfree(copy_path); - kfree(iov[num_iovecs-1].iov_base); + kfree(lc_buf); return rc; } + dhc_buf = iov[num_iovecs-1].iov_base; } rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0); @@ -1203,6 +1207,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, *oplock = rsp->OplockLevel; creat_exit: kfree(copy_path); + kfree(lc_buf); + kfree(dhc_buf); free_rsp_buf(resp_buftype, rsp); return rc; } @@ -1534,7 +1540,7 @@ SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, { return query_info(xid, tcon, persistent_fid, volatile_fid, FILE_ALL_INFORMATION, - sizeof(struct smb2_file_all_info) + MAX_NAME * 2, + sizeof(struct smb2_file_all_info) + PATH_MAX * 2, sizeof(struct smb2_file_all_info), data); } @@ -2130,6 +2136,10 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base; if (rc) { + if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) { + srch_inf->endOfSearch = true; + rc = 0; + } cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } @@ -2167,11 +2177,6 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, else cifs_dbg(VFS, "illegal search buffer type\n"); - if (rsp->hdr.Status == STATUS_NO_MORE_FILES) - srch_inf->endOfSearch = 1; - else - srch_inf->endOfSearch = 0; - return rc; qdir_exit: diff --git a/fs/coredump.c b/fs/coredump.c index e3ad709a4232..a93f7e6ea4cf 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -73,10 +73,15 @@ static int expand_corename(struct core_name *cn, int size) static int cn_vprintf(struct core_name *cn, const char *fmt, va_list arg) { int free, need; + va_list arg_copy; again: free = cn->size - cn->used; - need = vsnprintf(cn->corename + cn->used, free, fmt, arg); + + va_copy(arg_copy, arg); + need = vsnprintf(cn->corename + cn->used, free, fmt, arg_copy); + va_end(arg_copy); + if (need < free) { cn->used += need; return 0; @@ -301,7 +306,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (unlikely(nr < 0)) return nr; - tsk->flags = PF_DUMPCORE; + tsk->flags |= PF_DUMPCORE; if (atomic_read(&mm->mm_users) == nr + 1) goto done; /* diff --git a/fs/dcache.c b/fs/dcache.c index ca02c13a84aa..436612777203 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -106,8 +106,7 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; - hash = hash + (hash >> d_hash_shift); - return dentry_hashtable + (hash & d_hash_mask); + return dentry_hashtable + hash_32(hash, d_hash_shift); } /* Statistics gathering. */ @@ -1647,8 +1646,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) unsigned add_flags = d_flags_for_inode(inode); spin_lock(&dentry->d_lock); - dentry->d_flags &= ~DCACHE_ENTRY_TYPE; - dentry->d_flags |= add_flags; + __d_set_type(dentry, add_flags); if (inode) hlist_add_head(&dentry->d_alias, &inode->i_dentry); dentry->d_inode = inode; @@ -2826,6 +2824,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen) * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. + * + * Data dependency barrier is needed to make sure that we see that terminating + * NUL. Alpha strikes again, film at 11... */ static int prepend_name(char **buffer, int *buflen, struct qstr *name) { @@ -2833,6 +2834,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name) u32 dlen = ACCESS_ONCE(name->len); char *p; + smp_read_barrier_depends(); + *buflen -= dlen + 1; if (*buflen < 0) return -ENAMETOOLONG; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 9c0444cccbe1..15761957cc3f 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -533,7 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove); */ void debugfs_remove_recursive(struct dentry *dentry) { - struct dentry *child, *next, *parent; + struct dentry *child, *parent; if (IS_ERR_OR_NULL(dentry)) return; @@ -545,30 +545,49 @@ void debugfs_remove_recursive(struct dentry *dentry) parent = dentry; down: mutex_lock(&parent->d_inode->i_mutex); - list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { + loop: + /* + * The parent->d_subdirs is protected by the d_lock. Outside that + * lock, the child can be unlinked and set to be freed which can + * use the d_u.d_child as the rcu head and corrupt this list. + */ + spin_lock(&parent->d_lock); + list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) { if (!debugfs_positive(child)) continue; /* perhaps simple_empty(child) makes more sense */ if (!list_empty(&child->d_subdirs)) { + spin_unlock(&parent->d_lock); mutex_unlock(&parent->d_inode->i_mutex); parent = child; goto down; } - up: + + spin_unlock(&parent->d_lock); + if (!__debugfs_remove(child, parent)) simple_release_fs(&debugfs_mount, &debugfs_mount_count); + + /* + * The parent->d_lock protects agaist child from unlinking + * from d_subdirs. When releasing the parent->d_lock we can + * no longer trust that the next pointer is valid. + * Restart the loop. We'll skip this one with the + * debugfs_positive() check. + */ + goto loop; } + spin_unlock(&parent->d_lock); mutex_unlock(&parent->d_inode->i_mutex); child = parent; parent = parent->d_parent; mutex_lock(&parent->d_inode->i_mutex); - if (child != dentry) { - next = list_next_entry(child, d_u.d_child); - goto up; - } + if (child != dentry) + /* go up */ + goto loop; if (!__debugfs_remove(child, parent)) simple_release_fs(&debugfs_mount, &debugfs_mount_count); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index b167ca48b8ee..a85ceb7c91bc 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1039,7 +1039,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value, } rc = vfs_setxattr(lower_dentry, name, value, size, flags); - if (!rc) + if (!rc && dentry->d_inode) fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode); out: return rc; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index af903128891c..f50d79eb52db 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -910,7 +910,7 @@ static const struct file_operations eventpoll_fops = { void eventpoll_release_file(struct file *file) { struct eventpoll *ep; - struct epitem *epi; + struct epitem *epi, *next; /* * We don't want to get "file->f_lock" because it is not @@ -926,7 +926,7 @@ void eventpoll_release_file(struct file *file) * Besides, ep_remove() acquires the lock, so we can't hold it here. */ mutex_lock(&epmutex); - list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) { + list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) { ep = epi->ep; mutex_lock_nested(&ep->mtx, 0); ep_remove(ep, epi); @@ -1852,7 +1852,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - ep_take_care_of_epollwakeup(&epds); + if (ep_op_has_event(op)) + ep_take_care_of_epollwakeup(&epds); /* * We have to check that the file structure underneath the file descriptor diff --git a/fs/exec.c b/fs/exec.c index 3d78fccdd723..ea4449d0536a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -26,6 +26,7 @@ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> @@ -654,10 +655,10 @@ int setup_arg_pages(struct linux_binprm *bprm, unsigned long rlim_stack; #ifdef CONFIG_STACK_GROWSUP - /* Limit stack size to 1GB */ + /* Limit stack size */ stack_base = rlimit_max(RLIMIT_STACK); - if (stack_base > (1 << 30)) - stack_base = 1 << 30; + if (stack_base > STACK_SIZE_MAX) + stack_base = STACK_SIZE_MAX; /* Make sure we didn't let the argument array grow too large. */ if (vma->vm_end - vma->vm_start > stack_base) @@ -820,7 +821,7 @@ EXPORT_SYMBOL(read_code); static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; - struct mm_struct * old_mm, *active_mm; + struct mm_struct *old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; @@ -846,6 +847,8 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); task_unlock(tsk); if (old_mm) { up_read(&old_mm->mmap_sem); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 37fd31ed16e7..0498390f309e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1354,13 +1354,6 @@ set_qf_format: "not specified."); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext3_msg(sb, KERN_ERR, "error: journaled quota format " - "specified with no journaling " - "enabled."); - return 0; - } } #endif return 1; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index 3285aa5a706a..b610779a958c 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -24,8 +24,7 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); @@ -46,8 +45,7 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); @@ -65,8 +63,7 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); @@ -91,8 +88,7 @@ void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d3a534fdc5ff..2a6830a7af33 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2110,6 +2110,7 @@ int do_journal_get_write_access(handle_t *handle, #define CONVERT_INLINE_DATA 2 extern struct inode *ext4_iget(struct super_block *, unsigned long); +extern struct inode *ext4_iget_normal(struct super_block *, unsigned long); extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, @@ -2340,10 +2341,18 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_group_desc_csum(struct super_block *sb) { return EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM | - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM); + EXT4_FEATURE_RO_COMPAT_GDT_CSUM) || + (EXT4_SB(sb)->s_chksum_driver != NULL); } +static inline int ext4_has_metadata_csum(struct super_block *sb) +{ + WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + !EXT4_SB(sb)->s_chksum_driver); + + return (EXT4_SB(sb)->s_chksum_driver != NULL); +} static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | @@ -2462,23 +2471,6 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) up_write(&EXT4_I(inode)->i_data_sem); } -/* - * Update i_disksize after writeback has been started. Races with truncate - * are avoided by checking i_size under i_data_sem. - */ -static inline void ext4_wb_update_i_disksize(struct inode *inode, loff_t newsize) -{ - loff_t i_size; - - down_write(&EXT4_I(inode)->i_data_sem); - i_size = i_size_read(inode); - if (newsize > i_size) - newsize = i_size; - if (newsize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = newsize; - up_write(&EXT4_I(inode)->i_data_sem); -} - struct ext4_group_info { unsigned long bb_state; struct rb_root bb_free_root; @@ -2781,7 +2773,8 @@ extern void ext4_io_submit(struct ext4_io_submit *io); extern int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, int len, - struct writeback_control *wbc); + struct writeback_control *wbc, + bool keep_towrite); /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 74bc2d549c58..96a1ce159f51 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -74,8 +74,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); @@ -89,8 +88,7 @@ static void ext4_extent_block_csum_set(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); @@ -2585,6 +2583,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); + /* + * If we're starting with an extent other than the last one in the + * node, we need to see if it shares a cluster with the extent to + * the right (towards the end of the file). If its leftmost cluster + * is this extent's rightmost cluster and it is not cluster aligned, + * we'll mark it as a partial that is not to be deallocated. + */ + + if (ex != EXT_LAST_EXTENT(eh)) { + ext4_fsblk_t current_pblk, right_pblk; + long long current_cluster, right_cluster; + + current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1; + current_cluster = (long long)EXT4_B2C(sbi, current_pblk); + right_pblk = ext4_ext_pblock(ex + 1); + right_cluster = (long long)EXT4_B2C(sbi, right_pblk); + if (current_cluster == right_cluster && + EXT4_PBLK_COFF(sbi, right_pblk)) + *partial_cluster = -right_cluster; + } + trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster); while (ex >= EXT_FIRST_EXTENT(eh) && @@ -2710,10 +2729,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, err = ext4_ext_correct_indexes(handle, inode, path); /* - * Free the partial cluster only if the current extent does not - * reference it. Otherwise we might free used cluster. + * If there's a partial cluster and at least one extent remains in + * the leaf, free the partial cluster if it isn't shared with the + * current extent. If there's a partial cluster and no extents + * remain in the leaf, it can't be freed here. It can only be + * freed when it's possible to determine if it's not shared with + * any other extent - when the next leaf is processed or when space + * removal is complete. */ - if (*partial_cluster > 0 && + if (*partial_cluster > 0 && eh->eh_entries && (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) != *partial_cluster)) { int flags = get_default_free_blocks_flags(inode); @@ -4128,7 +4152,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_extent newex, *ex, *ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0; - int free_on_err = 0, err = 0, depth; + int free_on_err = 0, err = 0, depth, ret; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; @@ -4189,9 +4213,13 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, if (!ext4_ext_is_uninitialized(ex)) goto out; - allocated = ext4_ext_handle_uninitialized_extents( + ret = ext4_ext_handle_uninitialized_extents( handle, inode, map, path, flags, allocated, newblock); + if (ret < 0) + err = ret; + else + allocated = ret; goto out3; } } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 3981ff783950..171b9fa0f27a 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -962,10 +962,10 @@ retry: continue; } - if (ei->i_es_lru_nr == 0 || ei == locked_ei) + if (ei->i_es_lru_nr == 0 || ei == locked_ei || + !write_trylock(&ei->i_es_lock)) continue; - write_lock(&ei->i_es_lock); shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan); if (ei->i_es_lru_nr == 0) list_del_init(&ei->i_es_lru); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 1a5073959f32..2a8b2e15dcc4 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -82,7 +82,7 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov, size_t count = iov_length(iov, nr_segs); loff_t final_size = pos + count; - if (pos >= inode->i_size) + if (pos >= i_size_read(inode)) return 0; if ((pos & blockmask) || (final_size & blockmask)) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 0ee59a6644e2..a8d1a64d8cb0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -851,12 +851,23 @@ got: goto out; } + BUFFER_TRACE(group_desc_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, group_desc_bh); + if (err) { + ext4_std_error(sb, err); + goto out; + } + /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { struct buffer_head *block_bitmap_bh; block_bitmap_bh = ext4_read_block_bitmap(sb, group); + if (!block_bitmap_bh) { + err = -EIO; + goto out; + } BUFFER_TRACE(block_bitmap_bh, "get block bitmap access"); err = ext4_journal_get_write_access(handle, block_bitmap_bh); if (err) { @@ -887,13 +898,6 @@ got: } } - BUFFER_TRACE(group_desc_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, group_desc_bh); - if (err) { - ext4_std_error(sb, err); - goto out; - } - /* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { int free; @@ -988,8 +992,7 @@ got: spin_unlock(&sbi->s_next_gen_lock); /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 594009f5f523..e6574d7b6642 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -389,7 +389,13 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, return 0; failed: for (; i >= 0; i--) { - if (i != indirect_blks && branch[i].bh) + /* + * We want to ext4_forget() only freshly allocated indirect + * blocks. Buffer for new_blocks[i-1] is at branch[i].bh and + * buffer at branch[0].bh is indirect block / inode already + * existing before ext4_alloc_branch() was called. + */ + if (i > 0 && i != indirect_blks && branch[i].bh) ext4_forget(handle, 1, inode, branch[i].bh, branch[i].bh->b_blocknr); ext4_free_blocks(handle, inode, NULL, new_blocks[i], @@ -1312,16 +1318,24 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode, blk = *i_data; if (level > 0) { ext4_lblk_t first2; + ext4_lblk_t count2; + bh = sb_bread(inode->i_sb, le32_to_cpu(blk)); if (!bh) { EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk), "Read failure"); return -EIO; } - first2 = (first > offset) ? first - offset : 0; + if (first > offset) { + first2 = first - offset; + count2 = count; + } else { + first2 = 0; + count2 = count - (offset - first); + } ret = free_hole_blocks(handle, inode, bh, (__le32 *)bh->b_data, level - 1, - first2, count - offset, + first2, count2, inode->i_sb->s_blocksize >> 2); if (ret) { brelse(bh); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 82edf5b93352..8c03b747021b 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1128,8 +1128,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); inode->i_size = inode->i_sb->s_blocksize; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 24bfd7ff3049..3a7e0341447f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -83,8 +83,7 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); @@ -105,8 +104,7 @@ static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return; csum = ext4_inode_csum(inode, raw, ei); @@ -515,6 +513,10 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, "logical block %lu\n", inode->i_ino, flags, map->m_len, (unsigned long) map->m_lblk); + /* We can handle the block number less than EXT_MAX_BLOCKS */ + if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS)) + return -EIO; + /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { ext4_es_lru_add(inode); @@ -1831,6 +1833,7 @@ static int ext4_writepage(struct page *page, struct buffer_head *page_bufs = NULL; struct inode *inode = page->mapping->host; struct ext4_io_submit io_submit; + bool keep_towrite = false; trace_ext4_writepage(page); size = i_size_read(inode); @@ -1861,6 +1864,7 @@ static int ext4_writepage(struct page *page, unlock_page(page); return 0; } + keep_towrite = true; } if (PageChecked(page) && ext4_should_journal_data(inode)) @@ -1877,7 +1881,7 @@ static int ext4_writepage(struct page *page, unlock_page(page); return -ENOMEM; } - ret = ext4_bio_write_page(&io_submit, page, len, wbc); + ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite); ext4_io_submit(&io_submit); /* Drop io_end reference we got from init */ ext4_put_io_end_defer(io_submit.io_end); @@ -1896,7 +1900,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) else len = PAGE_CACHE_SIZE; clear_page_dirty_for_io(page); - err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc); + err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false); if (!err) mpd->wbc->nr_to_write--; mpd->first_page++; @@ -2189,6 +2193,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, struct ext4_map_blocks *map = &mpd->map; int err; loff_t disksize; + int progress = 0; mpd->io_submit.io_end->offset = ((loff_t)map->m_lblk) << inode->i_blkbits; @@ -2205,8 +2210,11 @@ static int mpage_map_and_submit_extent(handle_t *handle, * is non-zero, a commit should free up blocks. */ if ((err == -ENOMEM) || - (err == -ENOSPC && ext4_count_free_clusters(sb))) + (err == -ENOSPC && ext4_count_free_clusters(sb))) { + if (progress) + goto update_disksize; return err; + } ext4_msg(sb, KERN_CRIT, "Delayed block allocation failed for " "inode %lu at logical offset %llu with" @@ -2223,22 +2231,34 @@ static int mpage_map_and_submit_extent(handle_t *handle, *give_up_on_write = true; return err; } + progress = 1; /* * Update buffer state, submit mapped pages, and get us new * extent to map */ err = mpage_map_and_submit_buffers(mpd); if (err < 0) - return err; + goto update_disksize; } while (map->m_len); - /* Update on-disk size after IO is submitted */ +update_disksize: + /* + * Update on-disk size after IO is submitted. Races with + * truncate are avoided by checking i_size under i_data_sem. + */ disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT; if (disksize > EXT4_I(inode)->i_disksize) { int err2; - - ext4_wb_update_i_disksize(inode, disksize); + loff_t i_size; + + down_write(&EXT4_I(inode)->i_data_sem); + i_size = i_size_read(inode); + if (disksize > i_size) + disksize = i_size; + if (disksize > EXT4_I(inode)->i_disksize) + EXT4_I(inode)->i_disksize = disksize; err2 = ext4_mark_inode_dirty(handle, inode); + up_write(&EXT4_I(inode)->i_data_sem); if (err2) ext4_error(inode->i_sb, "Failed to mark inode %lu dirty", @@ -2611,6 +2631,20 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } +/* We always reserve for an inode update; the superblock could be there too */ +static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) +{ + if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_LARGE_FILE))) + return 1; + + if (pos + len <= 0x7fffffffULL) + return 1; + + /* We might need to update the superblock to set LARGE_FILE */ + return 2; +} + static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2661,7 +2695,8 @@ retry_grab: * of file which has an already mapped buffer. */ retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1); + handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, + ext4_da_write_credits(inode, pos, len)); if (IS_ERR(handle)) { page_cache_release(page); return PTR_ERR(handle); @@ -4039,8 +4074,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_extra_isize = 0; /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); @@ -4228,6 +4262,13 @@ bad_inode: return ERR_PTR(ret); } +struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino) +{ + if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) + return ERR_PTR(-EIO); + return ext4_iget(sb, ino); +} + static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) @@ -4623,8 +4664,12 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) ext4_orphan_del(NULL, inode); goto err_out; } - } else + } else { + loff_t oldsize = inode->i_size; + i_size_write(inode, attr->ia_size); + pagecache_isize_extended(inode, oldsize, inode->i_size); + } /* * Blocks are going to be removed from the inode. Wait diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a2a837f00407..dfe982dee0b3 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -343,8 +343,7 @@ flags_out: if (!inode_owner_or_capable(inode)) return -EPERM; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(inode->i_sb)) { ext4_warning(sb, "Setting inode version is not " "supported with metadata_csum enabled."); return -ENOTTY; @@ -544,9 +543,17 @@ group_add_out: } case EXT4_IOC_SWAP_BOOT: + { + int err; if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; - return swap_inode_boot_loader(sb, inode); + err = mnt_want_write_file(filp); + if (err) + return err; + err = swap_inode_boot_loader(sb, inode); + mnt_drop_write_file(filp); + return err; + } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 04a5c7504be9..242226a87be7 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -751,8 +751,8 @@ void ext4_mb_generate_buddy(struct super_block *sb, if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, - "%u clusters in bitmap, %u in gd; " - "block bitmap corrupt.", + "block bitmap and bg descriptor " + "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor @@ -1398,6 +1398,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, int last = first + count - 1; struct super_block *sb = e4b->bd_sb; + if (WARN_ON(count == 0)) + return; BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); /* Don't bother if the block group is corrupt. */ @@ -3135,7 +3137,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, } BUG_ON(start + size <= ac->ac_o_ex.fe_logical && start > ac->ac_o_ex.fe_logical); - BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); + BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ @@ -3196,8 +3198,30 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; + struct ext4_buddy e4b; + int err; - if (pa && pa->pa_type == MB_INODE_PA) + if (pa == NULL) { + if (ac->ac_f_ex.fe_len == 0) + return; + err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); + if (err) { + /* + * This should never happen since we pin the + * pages in the ext4_allocation_context so + * ext4_mb_load_buddy() should never fail. + */ + WARN(1, "mb_load_buddy failed (%d)", err); + return; + } + ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); + mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, + ac->ac_f_ex.fe_len); + ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); + ext4_mb_unload_buddy(&e4b); + return; + } + if (pa->pa_type == MB_INODE_PA) pa->pa_free += ac->ac_b_ex.fe_len; } diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 04434ad3e8e0..1268a1b5afa9 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -20,8 +20,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp); @@ -29,8 +28,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; mmp->mmp_checksum = ext4_mmp_csum(sb, mmp); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d050e043e884..2dcbfb6245d8 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -123,8 +123,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, "directory leaf block found instead of index block"); return ERR_PTR(-EIO); } - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) || + if (!ext4_has_metadata_csum(inode->i_sb) || buffer_verified(bh)) return bh; @@ -339,8 +338,7 @@ int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; t = get_dirent_tail(inode, dirent); @@ -361,8 +359,7 @@ static void ext4_dirent_csum_set(struct inode *inode, { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; t = get_dirent_tail(inode, dirent); @@ -437,8 +434,7 @@ static int ext4_dx_csum_verify(struct inode *inode, struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -467,8 +463,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -556,8 +551,7 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - EXT4_DIR_REC_LEN(2) - infosize; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -566,8 +560,7 @@ static inline unsigned dx_node_limit(struct inode *dir) { unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -1429,7 +1422,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi dentry); return ERR_PTR(-EIO); } - inode = ext4_iget(dir->i_sb, ino); + inode = ext4_iget_normal(dir->i_sb, ino); if (inode == ERR_PTR(-ESTALE)) { EXT4_ERROR_INODE(dir, "deleted inode referenced: %u", @@ -1460,7 +1453,7 @@ struct dentry *ext4_get_parent(struct dentry *child) return ERR_PTR(-EIO); } - return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino)); + return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino)); } /* @@ -1534,8 +1527,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, int csum_size = 0; int err = 0, i; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); bh2 = ext4_append(handle, dir, &newblock); @@ -1704,8 +1696,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (!de) { @@ -1772,8 +1763,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct fake_dirent *fde; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); blocksize = dir->i_sb->s_blocksize; @@ -1889,8 +1879,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, ext4_lblk_t block, blocks; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; @@ -2152,8 +2141,7 @@ static int ext4_delete_entry(handle_t *handle, return err; } - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); BUFFER_TRACE(bh, "get_write_access"); @@ -2372,8 +2360,7 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index ab95508e3d40..b6a3804a9855 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -308,13 +308,14 @@ static void ext4_end_bio(struct bio *bio, int error) if (error) { struct inode *inode = io_end->inode; - ext4_warning(inode->i_sb, "I/O error writing to inode %lu " + ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu " "(offset %llu size %ld starting block %llu)", - inode->i_ino, + error, inode->i_ino, (unsigned long long) io_end->offset, (long) io_end->size, (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); + mapping_set_error(inode->i_mapping, error); } if (io_end->flag & EXT4_IO_END_UNWRITTEN) { @@ -400,7 +401,8 @@ submit_and_retry: int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, int len, - struct writeback_control *wbc) + struct writeback_control *wbc, + bool keep_towrite) { struct inode *inode = page->mapping->host; unsigned block_start, blocksize; @@ -413,10 +415,24 @@ int ext4_bio_write_page(struct ext4_io_submit *io, BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); - set_page_writeback(page); + if (keep_towrite) + set_page_writeback_keepwrite(page); + else + set_page_writeback(page); ClearPageError(page); /* + * Comments copied from block_write_full_page_endio: + * + * The page straddles i_size. It must be zeroed out on each and every + * writepage invocation because it may be mmapped. "A file is mapped + * in multiples of the page size. For a file that is not a multiple of + * the page size, the remaining memory is zeroed when mapped, and + * writes to that region are not written out to the file." + */ + if (len < PAGE_CACHE_SIZE) + zero_user_segment(page, len, PAGE_CACHE_SIZE); + /* * In the first loop we prepare and mark buffers to submit. We have to * mark all buffers in the page before submitting so that * end_page_writeback() cannot be called from ext4_bio_end_io() when IO @@ -427,19 +443,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { block_start = bh_offset(bh); if (block_start >= len) { - /* - * Comments copied from block_write_full_page_endio: - * - * The page straddles i_size. It must be zeroed out on - * each and every writepage invocation because it may - * be mmapped. "A file is mapped in multiples of the - * page size. For a file that is not a multiple of - * the page size, the remaining memory is zeroed when - * mapped, and writes to that region are not written - * out to the file." - */ - zero_user_segment(page, block_start, - block_start + blocksize); clear_buffer_dirty(bh); set_buffer_uptodate(bh); continue; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index f3b84cd9de56..2400ad1c3d12 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1071,7 +1071,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data, break; if (meta_bg == 0) - backup_block = group * bpg + blk_off; + backup_block = ((ext4_fsblk_t)group) * bpg + blk_off; else backup_block = (ext4_group_first_block_no(sb, group) + ext4_bg_has_super(sb, group)); @@ -1200,8 +1200,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb, { struct buffer_head *bh; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 0; bh = ext4_get_bitmap(sb, group_data->inode_bitmap); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 710fed2377d4..9fb3e6c0c578 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -140,8 +140,7 @@ static __le32 ext4_superblock_csum(struct super_block *sb, int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); @@ -151,8 +150,7 @@ void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(sb, es); @@ -996,7 +994,7 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb, * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ - inode = ext4_iget(sb, ino); + inode = ext4_iget_normal(sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { @@ -1519,8 +1517,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, arg = JBD2_DEFAULT_MAX_COMMIT_AGE; sbi->s_commit_interval = HZ * arg; } else if (token == Opt_max_batch_time) { - if (arg == 0) - arg = EXT4_DEF_MAX_BATCH_TIME; sbi->s_max_batch_time = arg; } else if (token == Opt_min_batch_time) { sbi->s_min_batch_time = arg; @@ -1708,13 +1704,6 @@ static int parse_options(char *options, struct super_block *sb, "not specified"); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext4_msg(sb, KERN_ERR, "journaled quota format " - "specified with no journaling " - "enabled"); - return 0; - } } #endif if (test_opt(sb, DIOREAD_NOLOCK)) { @@ -2012,8 +2001,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); - if ((sbi->s_es->s_feature_ro_compat & - cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { + if (ext4_has_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __le16 save_csum; __u32 csum32; @@ -2031,6 +2019,10 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, } /* old crc16 code */ + if (!(sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM))) + return 0; + offset = offsetof(struct ext4_group_desc, bg_checksum); crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); @@ -2793,10 +2785,11 @@ static void print_daily_error_info(unsigned long arg) es = sbi->s_es; if (es->s_error_count) - ext4_msg(sb, KERN_NOTICE, "error count: %u", + /* fsck newer than v1.41.13 is needed to clean this condition. */ + ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u", le32_to_cpu(es->s_error_count)); if (es->s_first_error_time) { - printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d", + printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d", sb->s_id, le32_to_cpu(es->s_first_error_time), (int) sizeof(es->s_first_error_func), es->s_first_error_func, @@ -2810,7 +2803,7 @@ static void print_daily_error_info(unsigned long arg) printk("\n"); } if (es->s_last_error_time) { - printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d", + printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d", sb->s_id, le32_to_cpu(es->s_last_error_time), (int) sizeof(es->s_last_error_func), es->s_last_error_func, @@ -3168,11 +3161,10 @@ static int set_journal_csum_feature_set(struct super_block *sb) int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { - /* journal checksum v2 */ + if (ext4_has_metadata_csum(sb)) { + /* journal checksum v3 */ compat = 0; - incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2; + incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; } else { /* journal checksum v1 */ compat = JBD2_FEATURE_COMPAT_CHECKSUM; @@ -3194,6 +3186,7 @@ static int set_journal_csum_feature_set(struct super_block *sb) jbd2_journal_clear_features(sbi->s_journal, JBD2_FEATURE_COMPAT_CHECKSUM, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | + JBD2_FEATURE_INCOMPAT_CSUM_V3 | JBD2_FEATURE_INCOMPAT_CSUM_V2); } @@ -3475,8 +3468,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } /* Precompute checksum seed for all metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); @@ -3494,6 +3486,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif + /* don't forget to enable journal_csum when metadata_csum is enabled. */ + if (ext4_has_metadata_csum(sb)) + set_opt(sb, JOURNAL_CHECKSUM); + if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index e175e94116ac..8825154b20b6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -141,8 +141,7 @@ static int ext4_xattr_block_csum_verify(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + if (ext4_has_metadata_csum(inode->i_sb) && (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr))) return 0; return 1; @@ -152,8 +151,7 @@ static void ext4_xattr_block_csum_set(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr); @@ -189,14 +187,28 @@ ext4_listxattr(struct dentry *dentry, char *buffer, size_t size) } static int -ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end) +ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end, + void *value_start) { - while (!IS_LAST_ENTRY(entry)) { - struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry); + struct ext4_xattr_entry *e = entry; + + while (!IS_LAST_ENTRY(e)) { + struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next >= end) return -EIO; - entry = next; + e = next; + } + + while (!IS_LAST_ENTRY(entry)) { + if (entry->e_value_size != 0 && + (value_start + le16_to_cpu(entry->e_value_offs) < + (void *)e + sizeof(__u32) || + value_start + le16_to_cpu(entry->e_value_offs) + + le32_to_cpu(entry->e_value_size) > end)) + return -EIO; + entry = EXT4_XATTR_NEXT(entry); } + return 0; } @@ -213,7 +225,8 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) return -EIO; if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) return -EIO; - error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size); + error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, + bh->b_data); if (!error) set_buffer_verified(bh); return error; @@ -329,7 +342,7 @@ 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); + error = ext4_xattr_check_names(entry, end, entry); if (error) goto cleanup; error = ext4_xattr_find_entry(&entry, name_index, name, @@ -457,7 +470,7 @@ 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); + error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header)); if (error) goto cleanup; error = ext4_xattr_list_entries(dentry, IFIRST(header), @@ -517,8 +530,8 @@ static void ext4_xattr_update_super_block(handle_t *handle, } /* - * Release the xattr block BH: If the reference count is > 1, decrement - * it; otherwise free the block. + * Release the xattr block BH: If the reference count is > 1, decrement it; + * otherwise free the block. */ static void ext4_xattr_release_block(handle_t *handle, struct inode *inode, @@ -538,16 +551,31 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (ce) mb_cache_entry_free(ce); get_bh(bh); + unlock_buffer(bh); ext4_free_blocks(handle, inode, bh, 0, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); - unlock_buffer(bh); } 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 + * from a race where someone else frees the block (and releases + * its journal_head) before we are done dirtying the buffer. In + * nojournal mode this race is harmless and we actually cannot + * call ext4_handle_dirty_xattr_block() with locked buffer as + * that function can call sync_dirty_buffer() so for that case + * we handle the dirtying after unlocking the buffer. + */ + if (ext4_handle_valid(handle)) + error = ext4_handle_dirty_xattr_block(handle, inode, + bh); unlock_buffer(bh); - error = ext4_handle_dirty_xattr_block(handle, inode, bh); + if (!ext4_handle_valid(handle)) + error = ext4_handle_dirty_xattr_block(handle, inode, + bh); if (IS_SYNC(inode)) ext4_handle_sync(handle); dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1)); @@ -957,7 +985,8 @@ 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); + error = ext4_xattr_check_names(IFIRST(header), is->s.end, + IFIRST(header)); if (error) return error; /* Find the named attribute. */ diff --git a/fs/file_table.c b/fs/file_table.c index 5b24008ea4f6..79ecae62209a 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -209,10 +209,10 @@ static void drop_file_write_access(struct file *file) struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; - put_write_access(inode); - if (special_file(inode->i_mode)) return; + + put_write_access(inode); if (file_check_writeable(file) != 0) return; __mnt_drop_write(mnt); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index d754e3cf99a8..a16315957ef3 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -89,16 +89,29 @@ static inline struct inode *wb_inode(struct list_head *head) #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> +static void bdi_wakeup_thread(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi->wb_lock); + if (test_bit(BDI_registered, &bdi->state)) + mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + spin_unlock_bh(&bdi->wb_lock); +} + static void bdi_queue_work(struct backing_dev_info *bdi, struct wb_writeback_work *work) { trace_writeback_queue(bdi, work); spin_lock_bh(&bdi->wb_lock); + if (!test_bit(BDI_registered, &bdi->state)) { + if (work->done) + complete(work->done); + goto out_unlock; + } list_add_tail(&work->list, &bdi->work_list); - spin_unlock_bh(&bdi->wb_lock); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); +out_unlock: + spin_unlock_bh(&bdi->wb_lock); } static void @@ -114,7 +127,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) { trace_writeback_nowork(bdi); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + bdi_wakeup_thread(bdi); return; } @@ -161,7 +174,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi) * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(bdi); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + bdi_wakeup_thread(bdi); } /* @@ -1017,7 +1030,7 @@ void bdi_writeback_workfn(struct work_struct *work) current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || - list_empty(&bdi->bdi_list))) { + !test_bit(BDI_registered, &bdi->state))) { /* * The normal path. Keep writing back @bdi until its * work_list is empty. Note that this path is also taken @@ -1039,10 +1052,10 @@ void bdi_writeback_workfn(struct work_struct *work) trace_writeback_pages_written(pages_written); } - if (!list_empty(&bdi->work_list) || - (wb_has_dirty_io(wb) && dirty_writeback_interval)) - queue_delayed_work(bdi_wq, &wb->dwork, - msecs_to_jiffies(dirty_writeback_interval * 10)); + if (!list_empty(&bdi->work_list)) + mod_delayed_work(bdi_wq, &wb->dwork, 0); + else if (wb_has_dirty_io(wb) && dirty_writeback_interval) + bdi_wakeup_thread_delayed(bdi); current->flags &= ~PF_SWAPWRITE; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 1d1292c581c3..342f0239fcbf 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -198,7 +198,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) inode = ACCESS_ONCE(entry->d_inode); if (inode && is_bad_inode(inode)) goto invalid; - else if (fuse_dentry_time(entry) < get_jiffies_64()) { + else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) || + (flags & LOOKUP_REVAL)) { int err; struct fuse_entry_out outarg; struct fuse_req *req; @@ -925,7 +926,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, int err; bool r; - if (fi->i_time < get_jiffies_64()) { + if (time_before64(fi->i_time, get_jiffies_64())) { r = true; err = fuse_do_getattr(inode, stat, file); } else { @@ -1111,7 +1112,7 @@ static int fuse_permission(struct inode *inode, int mask) ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) { struct fuse_inode *fi = get_fuse_inode(inode); - if (fi->i_time < get_jiffies_64()) { + if (time_before64(fi->i_time, get_jiffies_64())) { refreshed = true; err = fuse_perm_getattr(inode, mask); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d468643a68b2..73f6bcb44ea8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -461,6 +461,17 @@ static const match_table_t tokens = { {OPT_ERR, NULL} }; +static int fuse_match_uint(substring_t *s, unsigned int *res) +{ + int err = -ENOMEM; + char *buf = match_strdup(s); + if (buf) { + err = kstrtouint(buf, 10, res); + kfree(buf); + } + return err; +} + static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) { char *p; @@ -471,6 +482,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) while ((p = strsep(&opt, ",")) != NULL) { int token; int value; + unsigned uv; substring_t args[MAX_OPT_ARGS]; if (!*p) continue; @@ -494,18 +506,18 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) break; case OPT_USER_ID: - if (match_int(&args[0], &value)) + if (fuse_match_uint(&args[0], &uv)) return 0; - d->user_id = make_kuid(current_user_ns(), value); + d->user_id = make_kuid(current_user_ns(), uv); if (!uid_valid(d->user_id)) return 0; d->user_id_present = 1; break; case OPT_GROUP_ID: - if (match_int(&args[0], &value)) + if (fuse_match_uint(&args[0], &uv)) return 0; - d->group_id = make_kgid(current_user_ns(), value); + d->group_id = make_kgid(current_user_ns(), uv); if (!gid_valid(d->group_id)) return 0; d->group_id_present = 1; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5c524180c98e..bc643b97423c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -606,8 +606,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (!IS_ERR(inode)) { d = d_splice_alias(inode, dentry); error = PTR_ERR(d); - if (IS_ERR(d)) + if (IS_ERR(d)) { + inode = ERR_CAST(d); goto fail_gunlock; + } error = 0; if (file) { if (S_ISREG(inode->i_mode)) { @@ -823,7 +825,6 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry, d = d_splice_alias(inode, dentry); if (IS_ERR(d)) { - iput(inode); gfs2_glock_dq_uninit(&gh); return d; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d19b30ababf1..a4a8ed56e438 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1017,6 +1017,11 @@ static int __init init_hugetlbfs_fs(void) int error; int i; + if (!hugepages_supported()) { + pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n"); + return -ENOTSUPP; + } + error = bdi_init(&hugetlbfs_backing_dev_info); if (error) return error; diff --git a/fs/inode.c b/fs/inode.c index 4bcdad3c9361..e846a32e8d6e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1840,14 +1840,18 @@ EXPORT_SYMBOL(inode_init_owner); * inode_owner_or_capable - check current task permissions to inode * @inode: inode being checked * - * Return true if current either has CAP_FOWNER to the inode, or - * owns the file. + * Return true if current either has CAP_FOWNER in a namespace with the + * inode owner uid mapped, or owns the file. */ bool inode_owner_or_capable(const struct inode *inode) { + struct user_namespace *ns; + if (uid_eq(current_fsuid(), inode->i_uid)) return true; - if (inode_capable(inode, CAP_FOWNER)) + + ns = current_user_ns(); + if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid)) return true; return false; } diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 4a9e10ea13f2..a9daccbd8fe7 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -61,7 +61,7 @@ static void isofs_put_super(struct super_block *sb) return; } -static int isofs_read_inode(struct inode *); +static int isofs_read_inode(struct inode *, int relocated); static int isofs_statfs (struct dentry *, struct kstatfs *); static struct kmem_cache *isofs_inode_cachep; @@ -1258,7 +1258,7 @@ out_toomany: goto out; } -static int isofs_read_inode(struct inode *inode) +static int isofs_read_inode(struct inode *inode, int relocated) { struct super_block *sb = inode->i_sb; struct isofs_sb_info *sbi = ISOFS_SB(sb); @@ -1403,7 +1403,7 @@ static int isofs_read_inode(struct inode *inode) */ if (!high_sierra) { - parse_rock_ridge_inode(de, inode); + parse_rock_ridge_inode(de, inode, relocated); /* if we want uid/gid set, override the rock ridge setting */ if (sbi->s_uid_set) inode->i_uid = sbi->s_uid; @@ -1482,9 +1482,10 @@ static int isofs_iget5_set(struct inode *ino, void *data) * offset that point to the underlying meta-data for the inode. The * code below is otherwise similar to the iget() code in * include/linux/fs.h */ -struct inode *isofs_iget(struct super_block *sb, - unsigned long block, - unsigned long offset) +struct inode *__isofs_iget(struct super_block *sb, + unsigned long block, + unsigned long offset, + int relocated) { unsigned long hashval; struct inode *inode; @@ -1506,7 +1507,7 @@ struct inode *isofs_iget(struct super_block *sb, return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { - ret = isofs_read_inode(inode); + ret = isofs_read_inode(inode, relocated); if (ret < 0) { iget_failed(inode); inode = ERR_PTR(ret); diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 99167238518d..0ac4c1f73fbd 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -107,7 +107,7 @@ extern int iso_date(char *, int); struct inode; /* To make gcc happy */ -extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *); +extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated); extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *); extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *); @@ -118,9 +118,24 @@ extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int extern struct buffer_head *isofs_bread(struct inode *, sector_t); extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long); -extern struct inode *isofs_iget(struct super_block *sb, - unsigned long block, - unsigned long offset); +struct inode *__isofs_iget(struct super_block *sb, + unsigned long block, + unsigned long offset, + int relocated); + +static inline struct inode *isofs_iget(struct super_block *sb, + unsigned long block, + unsigned long offset) +{ + return __isofs_iget(sb, block, offset, 0); +} + +static inline struct inode *isofs_iget_reloc(struct super_block *sb, + unsigned long block, + unsigned long offset) +{ + return __isofs_iget(sb, block, offset, 1); +} /* Because the inode number is no longer relevant to finding the * underlying meta-data for an inode, we are free to choose a more diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index c0bf42472e40..f488bbae541a 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -288,12 +288,16 @@ eio: goto out; } +#define RR_REGARD_XA 1 +#define RR_RELOC_DE 2 + static int parse_rock_ridge_inode_internal(struct iso_directory_record *de, - struct inode *inode, int regard_xa) + struct inode *inode, int flags) { int symlink_len = 0; int cnt, sig; + unsigned int reloc_block; struct inode *reloc; struct rock_ridge *rr; int rootflag; @@ -305,7 +309,7 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de, init_rock_state(&rs, inode); setup_rock_ridge(de, inode, &rs); - if (regard_xa) { + if (flags & RR_REGARD_XA) { rs.chr += 14; rs.len -= 14; if (rs.len < 0) @@ -485,12 +489,22 @@ repeat: "relocated directory\n"); goto out; case SIG('C', 'L'): - ISOFS_I(inode)->i_first_extent = - isonum_733(rr->u.CL.location); - reloc = - isofs_iget(inode->i_sb, - ISOFS_I(inode)->i_first_extent, - 0); + if (flags & RR_RELOC_DE) { + printk(KERN_ERR + "ISOFS: Recursive directory relocation " + "is not supported\n"); + goto eio; + } + reloc_block = isonum_733(rr->u.CL.location); + if (reloc_block == ISOFS_I(inode)->i_iget5_block && + ISOFS_I(inode)->i_iget5_offset == 0) { + printk(KERN_ERR + "ISOFS: Directory relocation points to " + "itself\n"); + goto eio; + } + ISOFS_I(inode)->i_first_extent = reloc_block; + reloc = isofs_iget_reloc(inode->i_sb, reloc_block, 0); if (IS_ERR(reloc)) { ret = PTR_ERR(reloc); goto out; @@ -637,9 +651,11 @@ static char *get_symlink_chunk(char *rpnt, struct rock_ridge *rr, char *plimit) return rpnt; } -int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode) +int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode, + int relocated) { - int result = parse_rock_ridge_inode_internal(de, inode, 0); + int flags = relocated ? RR_RELOC_DE : 0; + int result = parse_rock_ridge_inode_internal(de, inode, flags); /* * if rockridge flag was reset and we didn't look for attributes @@ -647,7 +663,8 @@ int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode) */ if ((ISOFS_SB(inode->i_sb)->s_rock_offset == -1) && (ISOFS_SB(inode->i_sb)->s_rock == 2)) { - result = parse_rock_ridge_inode_internal(de, inode, 14); + result = parse_rock_ridge_inode_internal(de, inode, + flags | RR_REGARD_XA); } return result; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index cf2fc0594063..9181c2b22b3c 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -97,7 +97,7 @@ static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh) struct commit_header *h; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; h = (struct commit_header *)(bh->b_data); @@ -313,11 +313,11 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh) return checksum; } -static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, +static void write_tag_block(journal_t *j, journal_block_tag_t *tag, unsigned long long block) { tag->t_blocknr = cpu_to_be32(block & (u32)~0); - if (tag_bytes > JBD2_TAG_SIZE32) + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT)) tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } @@ -327,7 +327,7 @@ static void jbd2_descr_block_csum_set(journal_t *j, struct jbd2_journal_block_tail *tail; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - @@ -340,12 +340,13 @@ static void jbd2_descr_block_csum_set(journal_t *j, static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, struct buffer_head *bh, __u32 sequence) { + journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag; struct page *page = bh->b_page; __u8 *addr; __u32 csum32; __be32 seq; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; seq = cpu_to_be32(sequence); @@ -355,8 +356,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, bh->b_size); kunmap_atomic(addr); - /* We only have space to store the lower 16 bits of the crc32c. */ - tag->t_checksum = cpu_to_be16(csum32); + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + tag3->t_checksum = cpu_to_be32(csum32); + else + tag->t_checksum = cpu_to_be16(csum32); } /* * jbd2_journal_commit_transaction @@ -396,7 +399,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) LIST_HEAD(io_bufs); LIST_HEAD(log_bufs); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_block_tail); /* @@ -692,7 +695,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) tag_flag |= JBD2_FLAG_SAME_UUID; tag = (journal_block_tag_t *) tagp; - write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr); + write_tag_block(journal, tag, jh2bh(jh)->b_blocknr); tag->t_flags = cpu_to_be16(tag_flag); jbd2_block_tag_csum_set(journal, tag, wbuf[bufs], commit_transaction->t_tid); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 5fa344afb49a..f2d78a3dae43 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug); /* Checksumming functions */ int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; @@ -145,7 +145,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; return sb->s_checksum == jbd2_superblock_csum(j, sb); @@ -153,7 +153,7 @@ int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb) { - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; sb->s_checksum = jbd2_superblock_csum(j, sb); @@ -1522,21 +1522,29 @@ static int journal_get_superblock(journal_t *journal) goto out; } - if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) && - JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + if (jbd2_journal_has_csum_v2or3(journal) && + JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) { /* Can't have checksum v1 and v2 on at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 " "at the same time!\n"); goto out; } + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) && + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) { + /* Can't have checksum v2 and v3 at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " + "at the same time!\n"); + goto out; + } + if (!jbd2_verify_csum_type(journal, sb)) { printk(KERN_ERR "JBD2: Unknown checksum type\n"); goto out; } /* Load the checksum driver */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + if (jbd2_journal_has_csum_v2or3(journal)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); @@ -1553,7 +1561,7 @@ static int journal_get_superblock(journal_t *journal) } /* Precompute checksum seed for all metadata */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); @@ -1813,8 +1821,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) return 0; - /* Asking for checksumming v2 and v1? Only give them v2. */ - if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 && + /* If enabling v2 checksums, turn on v3 instead */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) { + incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2; + incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3; + } + + /* Asking for checksumming v3 and v1? Only give them v3. */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 && compat & JBD2_FEATURE_COMPAT_CHECKSUM) compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; @@ -1823,8 +1837,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, sb = journal->j_superblock; - /* If enabling v2 checksums, update superblock */ - if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + /* If enabling v3 checksums, update superblock */ + if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); @@ -1842,8 +1856,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, } /* Precompute checksum seed for all metadata */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); @@ -1852,7 +1865,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, /* If enabling v1 checksums, downgrade superblock */ if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) sb->s_feature_incompat &= - ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2); + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 | + JBD2_FEATURE_INCOMPAT_CSUM_V3); sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); @@ -2165,16 +2179,20 @@ int jbd2_journal_blocks_per_page(struct inode *inode) */ size_t journal_tag_bytes(journal_t *journal) { - journal_block_tag_t tag; - size_t x = 0; + size_t sz; + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return sizeof(journal_block_tag3_t); + + sz = sizeof(journal_block_tag_t); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) - x += sizeof(tag.t_checksum); + sz += sizeof(__u16); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - return x + JBD2_TAG_SIZE64; + return sz; else - return x + JBD2_TAG_SIZE32; + return sz - sizeof(__u32); } /* diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 3b6bb19d60b1..bcbef08a4d8f 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -181,7 +181,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j, __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize - @@ -205,7 +205,7 @@ static int count_tags(journal_t *journal, struct buffer_head *bh) int nr = 0, size = journal->j_blocksize; int tag_bytes = journal_tag_bytes(journal); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) size -= sizeof(struct jbd2_journal_block_tail); tagp = &bh->b_data[sizeof(journal_header_t)]; @@ -338,10 +338,11 @@ int jbd2_journal_skip_recovery(journal_t *journal) return err; } -static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag) +static inline unsigned long long read_tag_block(journal_t *journal, + journal_block_tag_t *tag) { unsigned long long block = be32_to_cpu(tag->t_blocknr); - if (tag_bytes > JBD2_TAG_SIZE32) + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; return block; } @@ -384,7 +385,7 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; h = buf; @@ -399,17 +400,21 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, void *buf, __u32 sequence) { + journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag; __u32 csum32; __be32 seq; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; seq = cpu_to_be32(sequence); csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize); - return tag->t_checksum == cpu_to_be16(csum32); + if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return tag3->t_checksum == cpu_to_be32(csum32); + else + return tag->t_checksum == cpu_to_be16(csum32); } static int do_one_pass(journal_t *journal, @@ -426,6 +431,7 @@ static int do_one_pass(journal_t *journal, int tag_bytes = journal_tag_bytes(journal); __u32 crc32_sum = ~0; /* Transactional Checksums */ int descr_csum_size = 0; + int block_error = 0; /* * First thing is to establish what we expect to find in the log @@ -512,14 +518,14 @@ static int do_one_pass(journal_t *journal, switch(blocktype) { case JBD2_DESCRIPTOR_BLOCK: /* Verify checksum first */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) descr_csum_size = sizeof(struct jbd2_journal_block_tail); if (descr_csum_size > 0 && !jbd2_descr_block_csum_verify(journal, bh->b_data)) { err = -EIO; + brelse(bh); goto failed; } @@ -574,7 +580,7 @@ static int do_one_pass(journal_t *journal, unsigned long long blocknr; J_ASSERT(obh != NULL); - blocknr = read_tag_block(tag_bytes, + blocknr = read_tag_block(journal, tag); /* If the block has been @@ -598,7 +604,8 @@ static int do_one_pass(journal_t *journal, "checksum recovering " "block %llu in log\n", blocknr); - continue; + block_error = 1; + goto skip_write; } /* Find a buffer for the new @@ -797,7 +804,8 @@ static int do_one_pass(journal_t *journal, success = -EIO; } } - + if (block_error && success == 0) + success = -EIO; return success; failed: @@ -811,7 +819,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j, __be32 provided; __u32 calculated; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return 1; tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize - diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 198c9c10276d..d5e95a175c92 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -91,8 +91,8 @@ #include <linux/list.h> #include <linux/init.h> #include <linux/bio.h> -#endif #include <linux/log2.h> +#endif static struct kmem_cache *jbd2_revoke_record_cache; static struct kmem_cache *jbd2_revoke_table_cache; @@ -597,7 +597,7 @@ static void write_one_revoke_record(journal_t *journal, offset = *offsetp; /* Do we need to leave space at the end for a checksum? */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_revoke_tail); /* Make sure we have a descriptor with space left for the record */ @@ -644,7 +644,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh) struct jbd2_journal_revoke_tail *tail; __u32 csum; - if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize - diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 60bb365f54a5..f8a5d6a166fb 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1590,9 +1590,12 @@ int jbd2_journal_stop(handle_t *handle) * to perform a synchronous write. We do this to detect the * case where a single process is doing a stream of sync * writes. No point in waiting for joiners in that case. + * + * Setting max_batch_time to 0 disables this completely. */ pid = current->pid; - if (handle->h_sync && journal->j_last_sync_writer != pid) { + if (handle->h_sync && journal->j_last_sync_writer != pid && + journal->j_max_batch_time) { u64 commit_time, trans_time; journal->j_last_sync_writer = pid; diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c index 16a5047903a6..406d9cc84ba8 100644 --- a/fs/jffs2/compr_rtime.c +++ b/fs/jffs2/compr_rtime.c @@ -33,7 +33,7 @@ static int jffs2_rtime_compress(unsigned char *data_in, unsigned char *cpage_out, uint32_t *sourcelen, uint32_t *dstlen) { - short positions[256]; + unsigned short positions[256]; int outpos = 0; int pos=0; @@ -74,7 +74,7 @@ static int jffs2_rtime_decompress(unsigned char *data_in, unsigned char *cpage_out, uint32_t srclen, uint32_t destlen) { - short positions[256]; + unsigned short positions[256]; int outpos = 0; int pos=0; diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h index 413ef89c2d1b..046fee8b6e9b 100644 --- a/fs/jffs2/jffs2_fs_sb.h +++ b/fs/jffs2/jffs2_fs_sb.h @@ -134,8 +134,6 @@ struct jffs2_sb_info { struct rw_semaphore wbuf_sem; /* Protects the write buffer */ struct delayed_work wbuf_dwork; /* write-buffer write-out work */ - int wbuf_queued; /* non-zero delayed work is queued */ - spinlock_t wbuf_dwork_lock; /* protects wbuf_dwork and and wbuf_queued */ unsigned char *oobbuf; int oobavail; /* How many bytes are available for JFFS2 in OOB */ diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index e4619b00f7c5..fa35ff79ab35 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -231,7 +231,7 @@ struct jffs2_tmp_dnode_info uint32_t version; uint32_t data_crc; uint32_t partial_crc; - uint16_t csize; + uint32_t csize; uint16_t overlapped; }; diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c index 03310721712f..b6bd4affd9ad 100644 --- a/fs/jffs2/nodemgmt.c +++ b/fs/jffs2/nodemgmt.c @@ -179,6 +179,7 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize, spin_unlock(&c->erase_completion_lock); schedule(); + remove_wait_queue(&c->erase_wait, &wait); } else spin_unlock(&c->erase_completion_lock); } else if (ret) @@ -211,20 +212,25 @@ out: int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize, uint32_t *len, uint32_t sumsize) { - int ret = -EAGAIN; + int ret; minsize = PAD(minsize); jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize); - spin_lock(&c->erase_completion_lock); - while(ret == -EAGAIN) { + while (true) { + spin_lock(&c->erase_completion_lock); ret = jffs2_do_reserve_space(c, minsize, len, sumsize); if (ret) { jffs2_dbg(1, "%s(): looping, ret is %d\n", __func__, ret); } + spin_unlock(&c->erase_completion_lock); + + if (ret == -EAGAIN) + cond_resched(); + else + break; } - spin_unlock(&c->erase_completion_lock); if (!ret) ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1); diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index a6597d60d76d..09ed55190ee2 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work) struct jffs2_sb_info *c = work_to_sb(work); struct super_block *sb = OFNI_BS_2SFFJ(c); - spin_lock(&c->wbuf_dwork_lock); - c->wbuf_queued = 0; - spin_unlock(&c->wbuf_dwork_lock); - if (!(sb->s_flags & MS_RDONLY)) { jffs2_dbg(1, "%s()\n", __func__); jffs2_flush_wbuf_gc(c, 0); @@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c) if (sb->s_flags & MS_RDONLY) return; - spin_lock(&c->wbuf_dwork_lock); - if (!c->wbuf_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay)) jffs2_dbg(1, "%s()\n", __func__); - delay = msecs_to_jiffies(dirty_writeback_interval * 10); - queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay); - c->wbuf_queued = 1; - } - spin_unlock(&c->wbuf_dwork_lock); } int jffs2_nand_flash_setup(struct jffs2_sb_info *c) @@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c) /* Initialise write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; c->wbuf_ofs = 0xFFFFFFFF; @@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->erasesize; @@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; @@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) { return 0; init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index bd6e18be6e1a..39c0143fb3af 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -37,7 +37,7 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns) hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31)); hash &= 0x7fffffffU; /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ - if (hash < 1) + if (hash < 2) hash += 2; if (hash >= INT_MAX) hash = INT_MAX - 1; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index dbf397bfdff2..d29640b49be3 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -476,6 +476,8 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); + if (rc) + goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index e55126f85bd2..553946c9d952 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -48,14 +48,18 @@ void __init kernfs_inode_init(void) static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) { + static DEFINE_MUTEX(iattr_mutex); + struct kernfs_iattrs *ret; struct iattr *iattrs; + mutex_lock(&iattr_mutex); + if (kn->iattr) - return kn->iattr; + goto out_unlock; kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL); if (!kn->iattr) - return NULL; + goto out_unlock; iattrs = &kn->iattr->ia_iattr; /* assign default attributes */ @@ -65,8 +69,10 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME; simple_xattrs_init(&kn->iattr->xattrs); - - return kn->iattr; +out_unlock: + ret = kn->iattr; + mutex_unlock(&iattr_mutex); + return ret; } static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1812f026960c..6ae664b489af 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, msg.rpc_proc = &clnt->cl_procinfo[proc]; status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + if (status == -ECONNREFUSED) { + dprintk("lockd: NSM upcall RPC failed, status=%d, forcing rebind\n", + status); + rpc_force_rebind(clnt); + status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + } if (status < 0) dprintk("lockd: NSM upcall RPC failed, status=%d\n", status); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 10d6c41aecad..223e1cb14345 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -235,6 +235,7 @@ out_err: if (warned++ == 0) printk(KERN_WARNING "lockd_up: makesock failed, error=%d\n", err); + svc_shutdown_net(serv, net); return err; } @@ -252,13 +253,11 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net) error = make_socks(serv, net); if (error < 0) - goto err_socks; + goto err_bind; set_grace_period(net); dprintk("lockd_up_net: per-net data created; net=%p\n", net); return 0; -err_socks: - svc_rpcb_cleanup(serv, net); err_bind: ln->nlmsvc_users--; return error; diff --git a/fs/locks.c b/fs/locks.c index 92a0f0a52b06..4dd39b98a6a3 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1376,11 +1376,10 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) restart: break_time = flock->fl_break_time; - if (break_time != 0) { + if (break_time != 0) break_time -= jiffies; - if (break_time == 0) - break_time++; - } + if (break_time == 0) + break_time++; locks_insert_block(flock, new_fl); spin_unlock(&inode->i_lock); error = wait_event_interruptible_timeout(new_fl->fl_wait, diff --git a/fs/namei.c b/fs/namei.c index 4b491b431990..0dd72c8e65fd 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -34,6 +34,7 @@ #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> +#include <linux/hash.h> #include <asm/uaccess.h> #include "internal.h" @@ -332,10 +333,11 @@ int generic_permission(struct inode *inode, int mask) if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ - if (inode_capable(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; if (!(mask & MAY_WRITE)) - if (inode_capable(inode, CAP_DAC_READ_SEARCH)) + if (capable_wrt_inode_uidgid(inode, + CAP_DAC_READ_SEARCH)) return 0; return -EACCES; } @@ -345,7 +347,7 @@ int generic_permission(struct inode *inode, int mask) * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (inode_capable(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; /* @@ -353,7 +355,7 @@ int generic_permission(struct inode *inode, int mask) */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (inode_capable(inode, CAP_DAC_READ_SEARCH)) + if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; return -EACCES; @@ -640,24 +642,22 @@ static int complete_walk(struct nameidata *nd) static __always_inline void set_root(struct nameidata *nd) { - if (!nd->root.mnt) - get_fs_root(current->fs, &nd->root); + get_fs_root(current->fs, &nd->root); } static int link_path_walk(const char *, struct nameidata *); -static __always_inline void set_root_rcu(struct nameidata *nd) +static __always_inline unsigned set_root_rcu(struct nameidata *nd) { - if (!nd->root.mnt) { - struct fs_struct *fs = current->fs; - unsigned seq; + struct fs_struct *fs = current->fs; + unsigned seq, res; - do { - seq = read_seqcount_begin(&fs->seq); - nd->root = fs->root; - nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); - } + do { + seq = read_seqcount_begin(&fs->seq); + nd->root = fs->root; + res = __read_seqcount_begin(&nd->root.dentry->d_seq); + } while (read_seqcount_retry(&fs->seq, seq)); + return res; } static void path_put_conditional(struct path *path, struct nameidata *nd) @@ -857,7 +857,8 @@ follow_link(struct path *link, struct nameidata *nd, void **p) return PTR_ERR(s); } if (*s == '/') { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); path_put(&nd->path); nd->path = nd->root; path_get(&nd->root); @@ -1130,7 +1131,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, static int follow_dotdot_rcu(struct nameidata *nd) { - set_root_rcu(nd); + if (!nd->root.mnt) + set_root_rcu(nd); while (1) { if (nd->path.dentry == nd->root.dentry && @@ -1242,7 +1244,8 @@ static void follow_mount(struct path *path) static void follow_dotdot(struct nameidata *nd) { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); while(1) { struct dentry *old = nd->path.dentry; @@ -1537,7 +1540,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path, inode = path->dentry->d_inode; } err = -ENOENT; - if (!inode) + if (!inode || d_is_negative(path->dentry)) goto out_path_put; if (should_follow_link(path->dentry, follow)) { @@ -1623,8 +1626,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd) static inline unsigned int fold_hash(unsigned long hash) { - hash += hash >> (8*sizeof(int)); - return hash; + return hash_64(hash, 32); } #else /* 32-bit case */ @@ -1796,7 +1798,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) if (err) return err; } - if (!d_is_directory(nd->path.dentry)) { + if (!d_can_lookup(nd->path.dentry)) { err = -ENOTDIR; break; } @@ -1817,7 +1819,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*name) { - if (!d_is_directory(root)) + if (!d_can_lookup(root)) return -ENOTDIR; retval = inode_permission(inode, MAY_EXEC); if (retval) @@ -1841,7 +1843,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (*name=='/') { if (flags & LOOKUP_RCU) { rcu_read_lock(); - set_root_rcu(nd); + nd->seq = set_root_rcu(nd); } else { set_root(nd); path_get(&nd->root); @@ -1873,7 +1875,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, dentry = f.file->f_path.dentry; if (*name) { - if (!d_is_directory(dentry)) { + if (!d_can_lookup(dentry)) { fdput(f); return -ENOTDIR; } @@ -1955,7 +1957,7 @@ static int path_lookupat(int dfd, const char *name, err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) { - if (!d_is_directory(nd->path.dentry)) { + if (!d_can_lookup(nd->path.dentry)) { path_put(&nd->path); err = -ENOTDIR; } @@ -2240,15 +2242,16 @@ mountpoint_last(struct nameidata *nd, struct path *path) mutex_unlock(&dir->d_inode->i_mutex); done: - if (!dentry->d_inode) { + if (!dentry->d_inode || d_is_negative(dentry)) { error = -ENOENT; dput(dentry); goto out; } path->dentry = dentry; - path->mnt = mntget(nd->path.mnt); + path->mnt = nd->path.mnt; if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW)) return 1; + mntget(path->mnt); follow_mount(path); error = 0; out: @@ -2370,7 +2373,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; - return !inode_capable(inode, CAP_FOWNER); + return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } /* @@ -2414,11 +2417,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) IS_IMMUTABLE(inode) || IS_SWAPFILE(inode)) return -EPERM; if (isdir) { - if (!d_is_directory(victim) && !d_is_autodir(victim)) + if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; - } else if (d_is_directory(victim) || d_is_autodir(victim)) + } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; @@ -2982,7 +2985,7 @@ retry_lookup: finish_lookup: /* we _can_ be in RCU mode here */ error = -ENOENT; - if (d_is_negative(path->dentry)) { + if (!inode || d_is_negative(path->dentry)) { path_to_nameidata(path, nd); goto out; } @@ -3016,11 +3019,10 @@ finish_open: } audit_inode(name, nd->path.dentry, 0); error = -EISDIR; - if ((open_flag & O_CREAT) && - (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry))) + if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; error = -ENOTDIR; - if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry)) + if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) goto out; if (!S_ISREG(nd->inode->i_mode)) will_truncate = false; @@ -3126,7 +3128,8 @@ static int do_tmpfile(int dfd, struct filename *pathname, if (error) goto out2; audit_inode(pathname, nd->path.dentry, 0); - error = may_open(&nd->path, op->acc_mode, op->open_flag); + /* Don't check for other permissions, the inode was just created */ + error = may_open(&nd->path, MAY_OPEN, op->open_flag); if (error) goto out2; file->f_path.mnt = nd->path.mnt; @@ -3744,7 +3747,7 @@ exit1: slashes: if (d_is_negative(dentry)) error = -ENOENT; - else if (d_is_directory(dentry) || d_is_autodir(dentry)) + else if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; @@ -4123,7 +4126,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode **delegated_inode) { int error; - int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry); + int is_dir = d_is_dir(old_dentry); const unsigned char *old_name; if (old_dentry->d_inode == new_dentry->d_inode) @@ -4216,7 +4219,7 @@ retry_deleg: if (d_is_negative(old_dentry)) goto exit4; /* unless the source is a directory trailing slashes give -ENOTDIR */ - if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) { + if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (oldnd.last.name[oldnd.last.len]) goto exit4; diff --git a/fs/namespace.c b/fs/namespace.c index 2ffc5a2905d4..d9bf3efbf040 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -777,6 +777,20 @@ static void attach_mnt(struct mount *mnt, list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } +static void attach_shadowed(struct mount *mnt, + struct mount *parent, + struct mount *shadows) +{ + if (shadows) { + hlist_add_after_rcu(&shadows->mnt_hash, &mnt->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); + } +} + /* * vfsmount lock must be held for write */ @@ -795,12 +809,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) list_splice(&head, n->list.prev); - if (shadows) - hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash); - else - hlist_add_head_rcu(&mnt->mnt_hash, - m_hash(&parent->mnt, mnt->mnt_mountpoint)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + attach_shadowed(mnt, parent, shadows); touch_mnt_namespace(n); } @@ -885,10 +894,23 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, goto out_free; } - mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD; + mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED); /* Don't allow unprivileged users to change mount flags */ - if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY)) - mnt->mnt.mnt_flags |= MNT_LOCK_READONLY; + if (flag & CL_UNPRIVILEGED) { + mnt->mnt.mnt_flags |= MNT_LOCK_ATIME; + + if (mnt->mnt.mnt_flags & MNT_READONLY) + mnt->mnt.mnt_flags |= MNT_LOCK_READONLY; + + if (mnt->mnt.mnt_flags & MNT_NODEV) + mnt->mnt.mnt_flags |= MNT_LOCK_NODEV; + + if (mnt->mnt.mnt_flags & MNT_NOSUID) + mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID; + + if (mnt->mnt.mnt_flags & MNT_NOEXEC) + mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC; + } /* Don't allow unprivileged users to reveal what is under a mount */ if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire)) @@ -1204,6 +1226,11 @@ static void namespace_unlock(void) head.first->pprev = &head.first; INIT_HLIST_HEAD(&unmounted); + /* undo decrements we'd done in umount_tree() */ + hlist_for_each_entry(mnt, &head, mnt_hash) + if (mnt->mnt_ex_mountpoint.mnt) + mntget(mnt->mnt_ex_mountpoint.mnt); + up_write(&namespace_sem); synchronize_rcu(); @@ -1240,6 +1267,9 @@ void umount_tree(struct mount *mnt, int how) hlist_add_head(&p->mnt_hash, &tmp_list); } + hlist_for_each_entry(p, &tmp_list, mnt_hash) + list_del_init(&p->mnt_child); + if (how) propagate_umount(&tmp_list); @@ -1250,9 +1280,9 @@ void umount_tree(struct mount *mnt, int how) p->mnt_ns = NULL; if (how < 2) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; - list_del_init(&p->mnt_child); if (mnt_has_parent(p)) { put_mountpoint(p->mnt_mp); + mnt_add_count(p->mnt_parent, -1); /* move the reference to mountpoint into ->mnt_ex_mountpoint */ p->mnt_ex_mountpoint.dentry = p->mnt_mountpoint; p->mnt_ex_mountpoint.mnt = &p->mnt_parent->mnt; @@ -1335,6 +1365,8 @@ static int do_umount(struct mount *mnt, int flags) * Special case for "unmounting" root ... * we just try to remount it readonly. */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; down_write(&sb->s_umount); if (!(sb->s_flags & MS_RDONLY)) retval = do_remount_sb(sb, MS_RDONLY, NULL, 0); @@ -1483,6 +1515,7 @@ 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); @@ -1504,7 +1537,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - attach_mnt(q, parent, p->mnt_mp); + 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); unlock_mount_hash(); } } @@ -1661,9 +1701,9 @@ static int attach_recursive_mnt(struct mount *source_mnt, if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); + lock_mount_hash(); if (err) goto out_cleanup_ids; - lock_mount_hash(); for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } else { @@ -1690,6 +1730,11 @@ static int attach_recursive_mnt(struct mount *source_mnt, return 0; out_cleanup_ids: + while (!hlist_empty(&tree_list)) { + child = hlist_entry(tree_list.first, struct mount, mnt_hash); + umount_tree(child, 0); + } + unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: return err; @@ -1882,9 +1927,6 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags) if (readonly_request == __mnt_is_readonly(mnt)) return 0; - if (mnt->mnt_flags & MNT_LOCK_READONLY) - return -EPERM; - if (readonly_request) error = mnt_make_readonly(real_mount(mnt)); else @@ -1910,6 +1952,33 @@ static int do_remount(struct path *path, int flags, int mnt_flags, if (path->dentry != path->mnt->mnt_root) return -EINVAL; + /* Don't allow changing of locked mnt flags. + * + * No locks need to be held here while testing the various + * MNT_LOCK flags because those flags can never be cleared + * once they are set. + */ + if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) && + !(mnt_flags & MNT_READONLY)) { + return -EPERM; + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && + !(mnt_flags & MNT_NODEV)) { + return -EPERM; + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) && + !(mnt_flags & MNT_NOSUID)) { + return -EPERM; + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) && + !(mnt_flags & MNT_NOEXEC)) { + return -EPERM; + } + if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) && + ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) { + return -EPERM; + } + err = security_sb_remount(sb, data); if (err) return err; @@ -1923,7 +1992,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags, err = do_remount_sb(sb, flags, data, 0); if (!err) { lock_mount_hash(); - mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK; + mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); unlock_mount_hash(); @@ -2044,7 +2113,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags) struct mount *parent; int err; - mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT); + mnt_flags &= ~MNT_INTERNAL_FLAGS; mp = lock_mount(path); if (IS_ERR(mp)) @@ -2108,7 +2177,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, */ if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) { flags |= MS_NODEV; - mnt_flags |= MNT_NODEV; + mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV; } } @@ -2422,6 +2491,14 @@ long do_mount(const char *dev_name, const char *dir_name, if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; + /* The default atime for remount is preservation */ + if ((flags & MS_REMOUNT) && + ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | + MS_STRICTATIME)) == 0)) { + mnt_flags &= ~MNT_ATIME_MASK; + mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK; + } + flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | MS_STRICTATIME); @@ -2754,6 +2831,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; + /* make certain new is below the root */ + if (!is_path_reachable(new_mnt, new.dentry, &root)) + goto out4; root_mp->m_count++; /* pin it so it won't go away */ lock_mount_hash(); detach_mnt(new_mnt, &parent_path); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 360114ae8b82..15f9d98627a4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1555,18 +1555,20 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_version = fattr->change_attr; } } else if (server->caps & NFS_CAP_CHANGE_ATTR) - invalid |= save_cache_validity; + nfsi->cache_validity |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); } else if (server->caps & NFS_CAP_MTIME) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); } else if (server->caps & NFS_CAP_CTIME) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); /* Check if our cached file size is stale */ @@ -1588,7 +1590,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)new_isize); } } else - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); @@ -1596,7 +1599,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); else if (server->caps & NFS_CAP_ATIME) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_MODE) { @@ -1607,7 +1611,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } } else if (server->caps & NFS_CAP_MODE) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); @@ -1618,7 +1623,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_uid = fattr->uid; } } else if (server->caps & NFS_CAP_OWNER) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); @@ -1629,7 +1635,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_gid = fattr->gid; } } else if (server->caps & NFS_CAP_OWNER_GROUP) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); @@ -1642,7 +1649,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) set_nlink(inode, fattr->nlink); } } else if (server->caps & NFS_CAP_NLINK) - invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + nfsi->cache_validity |= save_cache_validity & + (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 871d6eda8dba..24c6898159cc 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -129,7 +129,10 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, .rpc_argp = &args, .rpc_resp = &fattr, }; - int status; + int status = 0; + + if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL)) + goto out; status = -EOPNOTSUPP; if (!nfs_server_capable(inode, NFS_CAP_ACLS)) @@ -247,3 +250,46 @@ const struct xattr_handler *nfs3_xattr_handlers[] = { &posix_acl_default_xattr_handler, NULL, }; + +static int +nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data, + size_t size, ssize_t *result) +{ + struct posix_acl *acl; + char *p = data + *result; + + acl = get_acl(inode, type); + if (IS_ERR_OR_NULL(acl)) + return 0; + + posix_acl_release(acl); + + *result += strlen(name); + *result += 1; + if (!size) + return 0; + if (*result > size) + return -ERANGE; + + strcpy(p, name); + return 0; +} + +ssize_t +nfs3_listxattr(struct dentry *dentry, char *data, size_t size) +{ + struct inode *inode = dentry->d_inode; + ssize_t result = 0; + int error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, + POSIX_ACL_XATTR_ACCESS, data, size, &result); + if (error) + return error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, + POSIX_ACL_XATTR_DEFAULT, data, size, &result); + if (error) + return error; + return result; +} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index a462ef0fb5d6..8a18b4a0a4ee 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -926,7 +926,7 @@ static const struct inode_operations nfs3_dir_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, @@ -940,7 +940,7 @@ static const struct inode_operations nfs3_file_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0e46d3d1b6cc..1abe4f55dea2 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -482,6 +482,16 @@ int nfs40_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos" */ if (pos->cl_cons_state > NFS_CS_READY) { @@ -501,15 +511,6 @@ int nfs40_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (pos->cl_clientid != new->cl_clientid) continue; @@ -615,6 +616,16 @@ int nfs41_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos", especially the client * ID and serverowner fields. Wait for CREATE_SESSION @@ -640,15 +651,6 @@ int nfs41_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (!nfs4_match_clientids(pos, new)) continue; diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index b9a35c05b60f..5e992fc51e61 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -1330,7 +1330,7 @@ filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) struct nfs4_filelayout *flo; flo = kzalloc(sizeof(*flo), gfp_flags); - return &flo->generic_hdr; + return flo != NULL ? &flo->generic_hdr : NULL; } static void diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 450bfedbe2f4..da657b7804a5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1068,6 +1068,7 @@ static void nfs4_opendata_free(struct kref *kref) dput(p->dentry); nfs_sb_deactive(sb); nfs_fattr_free_names(&p->f_attr); + kfree(p->f_attr.mdsthreshold); kfree(p); } @@ -2244,10 +2245,12 @@ static int _nfs4_do_open(struct inode *dir, } } - if (ctx_th && server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { - opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); - if (!opendata->f_attr.mdsthreshold) - goto err_free_label; + if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { + if (!opendata->f_attr.mdsthreshold) { + opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); + if (!opendata->f_attr.mdsthreshold) + goto err_free_label; + } opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0]; } if (dentry->d_inode != NULL) @@ -2275,11 +2278,10 @@ static int _nfs4_do_open(struct inode *dir, if (opendata->file_created) *opened |= FILE_CREATED; - if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) + if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) { *ctx_th = opendata->f_attr.mdsthreshold; - else - kfree(opendata->f_attr.mdsthreshold); - opendata->f_attr.mdsthreshold = NULL; + opendata->f_attr.mdsthreshold = NULL; + } nfs4_label_free(olabel); @@ -2289,7 +2291,6 @@ static int _nfs4_do_open(struct inode *dir, err_free_label: nfs4_label_free(olabel); err_opendata_put: - kfree(opendata->f_attr.mdsthreshold); nfs4_opendata_put(opendata); err_put_state_owner: nfs4_put_state_owner(sp); @@ -2545,6 +2546,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) struct nfs4_closedata *calldata = data; struct nfs4_state *state = calldata->state; struct inode *inode = calldata->inode; + bool is_rdonly, is_wronly, is_rdwr; int call_close = 0; dprintk("%s: begin!\n", __func__); @@ -2552,21 +2554,27 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_wait; task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE]; - calldata->arg.fmode = FMODE_READ|FMODE_WRITE; spin_lock(&state->owner->so_lock); + is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); + is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); + is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); /* Calculate the change in open mode */ + calldata->arg.fmode = 0; if (state->n_rdwr == 0) { - if (state->n_rdonly == 0) { - call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags); - call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); - calldata->arg.fmode &= ~FMODE_READ; - } - if (state->n_wronly == 0) { - call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags); - call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); - calldata->arg.fmode &= ~FMODE_WRITE; - } - } + if (state->n_rdonly == 0) + call_close |= is_rdonly; + else if (is_rdonly) + calldata->arg.fmode |= FMODE_READ; + if (state->n_wronly == 0) + call_close |= is_wronly; + else if (is_wronly) + calldata->arg.fmode |= FMODE_WRITE; + } else if (is_rdwr) + calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; + + if (calldata->arg.fmode == 0) + call_close |= is_rdwr; + if (!nfs4_valid_open_stateid(state)) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -7234,7 +7242,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr int ret = 0; if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0) - return 0; + return -EAGAIN; task = _nfs41_proc_sequence(clp, cred, false); if (IS_ERR(task)) ret = PTR_ERR(task); diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 1720d32ffa54..e1ba58c3d1ad 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work) } nfs_expire_all_delegations(clp); } else { + int ret; + /* Queue an asynchronous RENEW. */ - ops->sched_state_renewal(clp, cred, renew_flags); + ret = ops->sched_state_renewal(clp, cred, renew_flags); put_rpccred(cred); - goto out_exp; + switch (ret) { + default: + goto out_exp; + case -EAGAIN: + case -ENOMEM: + break; + } } } else { dprintk("%s: failed to call renewd. Reason: lease not expired \n", diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0deb32105ccf..b4f177f1d405 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1456,7 +1456,7 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs * server that doesn't support a grace period. */ spin_lock(&sp->so_lock); - write_seqcount_begin(&sp->so_reclaim_seqcount); + raw_write_seqcount_begin(&sp->so_reclaim_seqcount); restart: list_for_each_entry(state, &sp->so_states, open_states) { if (!test_and_clear_bit(ops->state_flag_bit, &state->flags)) @@ -1519,13 +1519,13 @@ restart: spin_lock(&sp->so_lock); goto restart; } - write_seqcount_end(&sp->so_reclaim_seqcount); + raw_write_seqcount_end(&sp->so_reclaim_seqcount); spin_unlock(&sp->so_lock); return 0; out_err: nfs4_put_open_state(state); spin_lock(&sp->so_lock); - write_seqcount_end(&sp->so_reclaim_seqcount); + raw_write_seqcount_end(&sp->so_reclaim_seqcount); spin_unlock(&sp->so_lock); return status; } @@ -1732,7 +1732,8 @@ restart: if (status < 0) { set_bit(ops->owner_flag_bit, &sp->so_flags); nfs4_put_state_owner(sp); - return nfs4_recovery_handle_error(clp, status); + status = nfs4_recovery_handle_error(clp, status); + return (status != 0) ? status : -EAGAIN; } nfs4_put_state_owner(sp); @@ -1741,7 +1742,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); - return status; + return 0; } static int nfs4_check_lease(struct nfs_client *clp) @@ -1788,7 +1789,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) break; case -NFS4ERR_STALE_CLIENTID: clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); - nfs4_state_clear_reclaim_reboot(clp); nfs4_state_start_reclaim_reboot(clp); break; case -NFS4ERR_CLID_INUSE: @@ -2370,6 +2370,7 @@ static void nfs4_state_manager(struct nfs_client *clp) status = nfs4_check_lease(clp); if (status < 0) goto out_error; + continue; } if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) { @@ -2391,14 +2392,11 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim reboot"; status = nfs4_do_reclaim(clp, clp->cl_mvops->reboot_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) - continue; - nfs4_state_end_reclaim_reboot(clp); - if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; + nfs4_state_end_reclaim_reboot(clp); } /* Now recover expired state... */ @@ -2406,9 +2404,7 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim nograce"; status = nfs4_do_reclaim(clp, clp->cl_mvops->nograce_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) || - test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 910ed906eb82..05c3a6e6518d 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2246,6 +2246,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; data->version = nfsvers; data->minorversion = nfss->nfs_client->cl_minorversion; + data->net = current->nsproxy->net_ns; memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr, data->nfs_server.addrlen); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9a3b6a4cd6b9..aaa16b31e21e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -913,12 +913,14 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) if (nfs_have_delegated_attributes(inode)) goto out; - if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE)) + if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) return false; smp_rmb(); if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) return false; out: + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + return false; return PageUptodate(page) != 0; } diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index d190e33d0ec2..dea8c60954ba 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -402,8 +402,10 @@ sort_pacl(struct posix_acl *pacl) * by uid/gid. */ int i, j; - if (pacl->a_count <= 4) - return; /* no users or groups */ + /* no users or groups */ + if (!pacl || pacl->a_count <= 4) + return; + i = 1; while (pacl->a_entries[i].e_tag == ACL_USER) i++; @@ -530,13 +532,12 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags) /* * ACLs with no ACEs are treated differently in the inheritable - * and effective cases: when there are no inheritable ACEs, we - * set a zero-length default posix acl: + * and effective cases: when there are no inheritable ACEs, + * calls ->set_acl with a NULL ACL structure. */ - if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) { - pacl = posix_acl_alloc(0, GFP_KERNEL); - return pacl ? pacl : ERR_PTR(-ENOMEM); - } + if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) + return NULL; + /* * When there are no effective ACEs, the following will end * up setting a 3-element effective posix ACL with all diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7f05cd140de3..cc8c5b32043c 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -637,9 +637,11 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses) { + int maxtime = max_cb_time(clp->net); struct rpc_timeout timeparms = { - .to_initval = max_cb_time(clp->net), + .to_initval = maxtime, .to_retries = 0, + .to_maxval = maxtime, }; struct rpc_create_args args = { .net = clp->net, @@ -670,7 +672,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; args.prognumber = clp->cl_cb_session->se_cb_prog; - args.protocol = XPRT_TRANSPORT_BC_TCP; + args.protocol = conn->cb_xprt->xpt_class->xcl_ident | + XPRT_TRANSPORT_BC; args.authflavor = ses->se_cb_sec.flavor; } /* Create RPC client */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 82189b208af3..86f5d3e474bf 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -618,15 +618,6 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, switch (create->cr_type) { case NF4LNK: - /* ugh! we have to null-terminate the linktext, or - * vfs_symlink() will choke. it is always safe to - * null-terminate by brute force, since at worst we - * will overwrite the first byte of the create namelen - * in the XDR buffer, which has already been extracted - * during XDR decode. - */ - create->cr_linkname[create->cr_linklen] = 0; - status = nfsd_symlink(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, create->cr_linkname, create->cr_linklen, @@ -1252,7 +1243,8 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) */ if (argp->opcnt == resp->opcnt) return false; - + if (next->opnum == OP_ILLEGAL) + return false; nextd = OPDESC(next); /* * Rest of 2.6.3.1.1: certain operations will return WRONGSEC @@ -1359,6 +1351,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, /* If op is non-idempotent */ if (opdesc->op_flags & OP_MODIFIES_SOMETHING) { plen = opdesc->op_rsize_bop(rqstp, op); + /* + * If there's still another operation, make sure + * we'll have space to at least encode an error: + */ + if (resp->opcnt < args->opcnt) + plen += COMPOUND_ERR_SLACK_SPACE; op->status = nfsd4_check_resp_size(resp, plen); } @@ -1523,7 +1521,8 @@ static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *o static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { - return (op_encode_hdr_size + 2 + 1024) * sizeof(__be32); + return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) * + sizeof(__be32); } static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d5d070fbeb35..34d2a1f2f400 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1078,6 +1078,18 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) return NULL; } clp->cl_name.len = name.len; + INIT_LIST_HEAD(&clp->cl_sessions); + idr_init(&clp->cl_stateids); + atomic_set(&clp->cl_refcount, 0); + clp->cl_cb_state = NFSD4_CB_UNKNOWN; + INIT_LIST_HEAD(&clp->cl_idhash); + INIT_LIST_HEAD(&clp->cl_openowners); + INIT_LIST_HEAD(&clp->cl_delegations); + INIT_LIST_HEAD(&clp->cl_lru); + INIT_LIST_HEAD(&clp->cl_callbacks); + INIT_LIST_HEAD(&clp->cl_revoked); + spin_lock_init(&clp->cl_lock); + rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; } @@ -1095,6 +1107,7 @@ free_client(struct nfs4_client *clp) WARN_ON_ONCE(atomic_read(&ses->se_ref)); free_session(ses); } + rpc_destroy_wait_queue(&clp->cl_cb_waitq); free_svc_cred(&clp->cl_cred); kfree(clp->cl_name.data); idr_destroy(&clp->cl_stateids); @@ -1347,7 +1360,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name, if (clp == NULL) return NULL; - INIT_LIST_HEAD(&clp->cl_sessions); ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred); if (ret) { spin_lock(&nn->client_lock); @@ -1355,20 +1367,9 @@ static struct nfs4_client *create_client(struct xdr_netobj name, spin_unlock(&nn->client_lock); return NULL; } - idr_init(&clp->cl_stateids); - atomic_set(&clp->cl_refcount, 0); - clp->cl_cb_state = NFSD4_CB_UNKNOWN; - INIT_LIST_HEAD(&clp->cl_idhash); - INIT_LIST_HEAD(&clp->cl_openowners); - INIT_LIST_HEAD(&clp->cl_delegations); - INIT_LIST_HEAD(&clp->cl_lru); - INIT_LIST_HEAD(&clp->cl_callbacks); - INIT_LIST_HEAD(&clp->cl_revoked); - spin_lock_init(&clp->cl_lock); nfsd4_init_callback(&clp->cl_cb_null); clp->cl_time = get_seconds(); clear_bit(0, &clp->cl_cb_slot_busy); - rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); copy_verf(clp, verf); rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa); gen_confirm(clp); @@ -3713,9 +3714,16 @@ out: static __be32 nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp) { - if (check_for_locks(stp->st_file, lockowner(stp->st_stateowner))) + struct nfs4_lockowner *lo = lockowner(stp->st_stateowner); + + if (check_for_locks(stp->st_file, lo)) return nfserr_locks_held; - release_lock_stateid(stp); + /* + * Currently there's a 1-1 lock stateid<->lockowner + * correspondance, and we have to delete the lockowner when we + * delete the lock stateid: + */ + release_lockowner(lo); return nfs_ok; } @@ -4155,6 +4163,10 @@ static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, c if (!same_owner_str(&lo->lo_owner, owner, clid)) return false; + if (list_empty(&lo->lo_owner.so_stateids)) { + WARN_ON_ONCE(1); + return false; + } lst = list_first_entry(&lo->lo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); return lst->st_file->fi_inode == inode; @@ -5062,7 +5074,6 @@ nfs4_state_destroy_net(struct net *net) int i; struct nfs4_client *clp = NULL; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct rb_node *node, *tmp; for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->conf_id_hashtbl[i])) { @@ -5071,13 +5082,11 @@ nfs4_state_destroy_net(struct net *net) } } - node = rb_first(&nn->unconf_name_tree); - while (node != NULL) { - tmp = node; - node = rb_next(tmp); - clp = rb_entry(tmp, struct nfs4_client, cl_namenode); - rb_erase(tmp, &nn->unconf_name_tree); - destroy_client(clp); + for (i = 0; i < CLIENT_HASH_SIZE; i++) { + while (!list_empty(&nn->unconf_id_hashtbl[i])) { + clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); + destroy_client(clp); + } } kfree(nn->sessionid_hashtbl); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 63f2395c57ed..86573350350e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -602,7 +602,18 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create READ_BUF(4); READ32(create->cr_linklen); READ_BUF(create->cr_linklen); - SAVEMEM(create->cr_linkname, create->cr_linklen); + /* + * The VFS will want a null-terminated string, and + * null-terminating in place isn't safe since this might + * end on a page boundary: + */ + create->cr_linkname = + kmalloc(create->cr_linklen + 1, GFP_KERNEL); + if (!create->cr_linkname) + return nfserr_jukebox; + memcpy(create->cr_linkname, p, create->cr_linklen); + create->cr_linkname[create->cr_linklen] = '\0'; + defer_free(argp, kfree, create->cr_linkname); break; case NF4BLK: case NF4CHR: @@ -2096,8 +2107,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, err = vfs_getattr(&path, &stat); if (err) goto out_nfserr; - if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | - FATTR4_WORD0_MAXNAME)) || + if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { err = vfs_statfs(&path, &statfs); @@ -2483,6 +2494,8 @@ out_acl: goto out; } if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { + if ((buflen -= 16) < 0) + goto out_resource; WRITE32(3); WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0); WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1); @@ -2499,8 +2512,10 @@ out: security_release_secctx(context, contextlen); #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ kfree(acl); - if (tempfh) + if (tempfh) { fh_put(tempfh); + kfree(tempfh); + } return status; out_nfserr: status = nfserrno(err); @@ -3471,6 +3486,9 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_test_stateid_id *stateid, *next; __be32 *p; + if (nfserr) + return nfserr; + RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids)); *p++ = htonl(test_stateid->ts_num_ids); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7f555179bf81..f34d9de802ab 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -699,6 +699,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net) if (err != 0 || fd < 0) return -EINVAL; + if (svc_alien_sock(net, fd)) { + printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__); + return -EINVAL; + } + err = nfsd_create_serv(net); if (err != 0) return err; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 30f34ab02137..479eb681c27c 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -282,7 +282,7 @@ void nfsd_lockd_shutdown(void); * reason. */ #define COMPOUND_SLACK_SPACE 140 /* OP_GETFH */ -#define COMPOUND_ERR_SLACK_SPACE 12 /* OP_SETATTR */ +#define COMPOUND_ERR_SLACK_SPACE 16 /* OP_SETATTR */ #define NFSD_LAUNDROMAT_MINTIMEOUT 1 /* seconds */ diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 9a4a5f9e7468..c34e45d1539b 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -221,7 +221,8 @@ static int nfsd_startup_generic(int nrservs) */ ret = nfsd_racache_init(2*nrservs); if (ret) - return ret; + goto dec_users; + ret = nfs4_state_start(); if (ret) goto out_racache; @@ -229,6 +230,8 @@ static int nfsd_startup_generic(int nrservs) out_racache: nfsd_racache_shutdown(); +dec_users: + nfsd_users--; return ret; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index b17d93214d01..9c769a47ac5a 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -152,7 +152,7 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, type = (stat->mode & S_IFMT); *p++ = htonl(nfs_ftypes[type >> 12]); - *p++ = htonl((u32) (stat->mode & S_IALLUGO)); + *p++ = htonl((u32) stat->mode); *p++ = htonl((u32) stat->nlink); *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid)); *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid)); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 6d7be3f80356..eea5ad188984 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -404,6 +404,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, umode_t ftype = 0; __be32 err; int host_err; + bool get_write_count; int size_change = 0; if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) @@ -411,10 +412,18 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, if (iap->ia_valid & ATTR_SIZE) ftype = S_IFREG; + /* Callers that do fh_verify should do the fh_want_write: */ + get_write_count = !fhp->fh_dentry; + /* Get inode */ err = fh_verify(rqstp, fhp, ftype, accmode); if (err) goto out; + if (get_write_count) { + host_err = fh_want_write(fhp); + if (host_err) + return nfserrno(host_err); + } dentry = fhp->fh_dentry; inode = dentry->d_inode; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7e350c562e0e..1e0bbae06ee7 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -24,6 +24,7 @@ #include <linux/buffer_head.h> #include <linux/gfp.h> #include <linux/mpage.h> +#include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/aio.h> #include "nilfs.h" @@ -219,10 +220,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) static int nilfs_set_page_dirty(struct page *page) { + struct inode *inode = page->mapping->host; int ret = __set_page_dirty_nobuffers(page); if (page_has_buffers(page)) { - struct inode *inode = page->mapping->host; unsigned nr_dirty = 0; struct buffer_head *bh, *head; @@ -245,6 +246,10 @@ static int nilfs_set_page_dirty(struct page *page) if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); + } else if (ret) { + unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); + + nilfs_set_file_dirty(inode, nr_dirty); } return ret; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 287a22c04149..de6323eb0113 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -71,7 +71,7 @@ static int create_fd(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - client_fd = get_unused_fd(); + client_fd = get_unused_fd_flags(group->fanotify_data.f_flags); if (client_fd < 0) return client_fd; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 238a5930cb3c..9d7e2b9659cb 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -42,7 +42,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) { struct { struct file_handle handle; - u8 pad[64]; + u8 pad[MAX_HANDLE_SZ]; } f; int size, ret, i; @@ -50,7 +50,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f.handle.handle_bytes >> 2; ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0); - if ((ret == 255) || (ret == -ENOSPC)) { + if ((ret == FILEID_INVALID) || (ret < 0)) { WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); return 0; } diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 5b704c63a103..1edcb141f639 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -90,7 +90,6 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, * information for this bh as it's not marked locally * uptodate. */ ret = -EIO; - put_bh(bh); mlog_errno(ret); } @@ -420,7 +419,6 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb, if (!buffer_uptodate(bh)) { ret = -EIO; - put_bh(bh); mlog_errno(ret); } diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index af3f7aa73e13..1be3398c96f6 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -650,12 +650,9 @@ void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm, clear_bit(bit, res->refmap); } - -void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, +static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { - assert_spin_locked(&res->spinlock); - res->inflight_locks++; mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name, @@ -663,6 +660,13 @@ void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, __builtin_return_address(0)); } +void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + assert_spin_locked(&res->spinlock); + __dlm_lockres_grab_inflight_ref(dlm, res); +} + void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { @@ -852,10 +856,8 @@ lookup: /* finally add the lockres to its hash bucket */ __dlm_insert_lockres(dlm, res); - /* Grab inflight ref to pin the resource */ - spin_lock(&res->spinlock); - dlm_lockres_grab_inflight_ref(dlm, res); - spin_unlock(&res->spinlock); + /* since this lockres is new it doesn't not require the spinlock */ + __dlm_lockres_grab_inflight_ref(dlm, res); /* get an extra ref on the mle in case this is a BLOCK * if so, the creator of the BLOCK may try to put the last diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 7035af09cc03..fe29f7978f81 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -537,7 +537,10 @@ master_here: /* success! see if any other nodes need recovery */ mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n", dlm->name, dlm->reco.dead_node, dlm->node_num); - dlm_reset_recovery(dlm); + spin_lock(&dlm->spinlock); + __dlm_reset_recovery(dlm); + dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE; + spin_unlock(&dlm->spinlock); } dlm_end_recovery(dlm); @@ -695,6 +698,14 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) if (all_nodes_done) { int ret; + /* Set this flag on recovery master to avoid + * a new recovery for another dead node start + * before the recovery is not done. That may + * cause recovery hung.*/ + spin_lock(&dlm->spinlock); + dlm->reco.state |= DLM_RECO_STATE_FINALIZE; + spin_unlock(&dlm->spinlock); + /* all nodes are now in DLM_RECO_NODE_DATA_DONE state * just send a finalize message to everyone and * clean up */ @@ -1750,13 +1761,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, struct dlm_migratable_lockres *mres) { struct dlm_migratable_lock *ml; - struct list_head *queue; + struct list_head *queue, *iter; struct list_head *tmpq = NULL; struct dlm_lock *newlock = NULL; struct dlm_lockstatus *lksb = NULL; int ret = 0; int i, j, bad; - struct dlm_lock *lock = NULL; + struct dlm_lock *lock; u8 from = O2NM_MAX_NODES; unsigned int added = 0; __be64 c; @@ -1791,14 +1802,16 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, /* MIGRATION ONLY! */ BUG_ON(!(mres->flags & DLM_MRES_MIGRATION)); + lock = NULL; spin_lock(&res->spinlock); for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) { tmpq = dlm_list_idx_to_ptr(res, j); - list_for_each_entry(lock, tmpq, list) { - if (lock->ml.cookie != ml->cookie) - lock = NULL; - else + list_for_each(iter, tmpq) { + lock = list_entry(iter, + struct dlm_lock, list); + if (lock->ml.cookie == ml->cookie) break; + lock = NULL; } if (lock) break; @@ -2882,8 +2895,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data, BUG(); } dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE; + __dlm_reset_recovery(dlm); spin_unlock(&dlm->spinlock); - dlm_reset_recovery(dlm); dlm_kick_recovery_thread(dlm); break; default: diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3683643f3f0e..feed025fe064 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -450,7 +450,6 @@ leave: brelse(new_fe_bh); brelse(parent_fe_bh); - kfree(si.name); kfree(si.value); ocfs2_free_dir_lookup_result(&lookup); @@ -1855,7 +1854,6 @@ bail: brelse(new_fe_bh); brelse(parent_fe_bh); - kfree(si.name); kfree(si.value); ocfs2_free_dir_lookup_result(&lookup); if (inode_ac) diff --git a/fs/open.c b/fs/open.c index b9ed8b25c108..2ed7325f713e 100644 --- a/fs/open.c +++ b/fs/open.c @@ -641,23 +641,12 @@ out: static inline int __get_file_write_access(struct inode *inode, struct vfsmount *mnt) { - int error; - error = get_write_access(inode); + int error = get_write_access(inode); if (error) return error; - /* - * Do not take mount writer counts on - * special files since no writes to - * the mount itself will occur. - */ - if (!special_file(inode->i_mode)) { - /* - * Balanced in __fput() - */ - error = __mnt_want_write(mnt); - if (error) - put_write_access(inode); - } + error = __mnt_want_write(mnt); + if (error) + put_write_access(inode); return error; } @@ -690,12 +679,11 @@ static int do_dentry_open(struct file *f, path_get(&f->f_path); inode = f->f_inode = f->f_path.dentry->d_inode; - if (f->f_mode & FMODE_WRITE) { + if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = __get_file_write_access(inode, f->f_path.mnt); if (error) goto cleanup_file; - if (!special_file(inode->i_mode)) - file_take_write(f); + file_take_write(f); } f->f_mapping = inode->i_mapping; @@ -742,7 +730,6 @@ static int do_dentry_open(struct file *f, cleanup_all: fops_put(f->f_op); if (f->f_mode & FMODE_WRITE) { - put_write_access(inode); if (!special_file(inode->i_mode)) { /* * We don't consider this a real @@ -750,6 +737,7 @@ cleanup_all: * because it all happenend right * here, so just reset the state. */ + put_write_access(inode); file_reset_write(f); __mnt_drop_write(f->f_path.mnt); } diff --git a/fs/pnode.c b/fs/pnode.c index 88396df725b4..b7f831089500 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -164,46 +164,94 @@ static struct mount *propagation_next(struct mount *m, } } -/* - * return the source mount to be used for cloning - * - * @dest the current destination mount - * @last_dest the last seen destination mount - * @last_src the last seen source mount - * @type return CL_SLAVE if the new mount has to be - * cloned as a slave. - */ -static struct mount *get_source(struct mount *dest, - struct mount *last_dest, - struct mount *last_src, - int *type) +static struct mount *next_group(struct mount *m, struct mount *origin) { - struct mount *p_last_src = NULL; - struct mount *p_last_dest = NULL; - - while (last_dest != dest->mnt_master) { - p_last_dest = last_dest; - p_last_src = last_src; - last_dest = last_dest->mnt_master; - last_src = last_src->mnt_master; + while (1) { + while (1) { + struct mount *next; + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + return first_slave(m); + next = next_peer(m); + if (m->mnt_group_id == origin->mnt_group_id) { + if (next == origin) + return NULL; + } else if (m->mnt_slave.next != &next->mnt_slave) + break; + m = next; + } + /* m is the last peer */ + while (1) { + struct mount *master = m->mnt_master; + if (m->mnt_slave.next != &master->mnt_slave_list) + return next_slave(m); + m = next_peer(master); + if (master->mnt_group_id == origin->mnt_group_id) + break; + if (master->mnt_slave.next == &m->mnt_slave) + break; + m = master; + } + if (m == origin) + return NULL; } +} - if (p_last_dest) { - do { - p_last_dest = next_peer(p_last_dest); - } while (IS_MNT_NEW(p_last_dest)); - /* is that a peer of the earlier? */ - if (dest == p_last_dest) { - *type = CL_MAKE_SHARED; - return p_last_src; +/* all accesses are serialized by namespace_sem */ +static struct user_namespace *user_ns; +static struct mount *last_dest, *last_source, *dest_master; +static struct mountpoint *mp; +static struct hlist_head *list; + +static int propagate_one(struct mount *m) +{ + struct mount *child; + int type; + /* skip ones added by this propagate_mnt() */ + if (IS_MNT_NEW(m)) + return 0; + /* skip if mountpoint isn't covered by it */ + if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) + return 0; + if (m->mnt_group_id == last_dest->mnt_group_id) { + type = CL_MAKE_SHARED; + } else { + struct mount *n, *p; + for (n = m; ; n = p) { + p = n->mnt_master; + if (p == dest_master || IS_MNT_MARKED(p)) { + while (last_dest->mnt_master != p) { + last_source = last_source->mnt_master; + last_dest = last_source->mnt_parent; + } + if (n->mnt_group_id != last_dest->mnt_group_id) { + last_source = last_source->mnt_master; + last_dest = last_source->mnt_parent; + } + break; + } } + type = CL_SLAVE; + /* beginning of peer group among the slaves? */ + if (IS_MNT_SHARED(m)) + type |= CL_MAKE_SHARED; } - /* slave of the earlier, then */ - *type = CL_SLAVE; - /* beginning of peer group among the slaves? */ - if (IS_MNT_SHARED(dest)) - *type |= CL_MAKE_SHARED; - return last_src; + + /* Notice when we are propagating across user namespaces */ + if (m->mnt_ns->user_ns != user_ns) + type |= CL_UNPRIVILEGED; + child = copy_tree(last_source, last_source->mnt.mnt_root, type); + if (IS_ERR(child)) + return PTR_ERR(child); + mnt_set_mountpoint(m, mp, child); + last_dest = m; + last_source = child; + if (m->mnt_master != dest_master) { + read_seqlock_excl(&mount_lock); + SET_MNT_MARK(m->mnt_master); + read_sequnlock_excl(&mount_lock); + } + hlist_add_head(&child->mnt_hash, list); + return 0; } /* @@ -222,56 +270,48 @@ static struct mount *get_source(struct mount *dest, int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, struct mount *source_mnt, struct hlist_head *tree_list) { - struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; - struct mount *m, *child; + struct mount *m, *n; int ret = 0; - struct mount *prev_dest_mnt = dest_mnt; - struct mount *prev_src_mnt = source_mnt; - HLIST_HEAD(tmp_list); - - for (m = propagation_next(dest_mnt, dest_mnt); m; - m = propagation_next(m, dest_mnt)) { - int type; - struct mount *source; - - if (IS_MNT_NEW(m)) - continue; - - source = get_source(m, prev_dest_mnt, prev_src_mnt, &type); - - /* Notice when we are propagating across user namespaces */ - if (m->mnt_ns->user_ns != user_ns) - type |= CL_UNPRIVILEGED; - - child = copy_tree(source, source->mnt.mnt_root, type); - if (IS_ERR(child)) { - ret = PTR_ERR(child); - tmp_list = *tree_list; - tmp_list.first->pprev = &tmp_list.first; - INIT_HLIST_HEAD(tree_list); + + /* + * we don't want to bother passing tons of arguments to + * propagate_one(); everything is serialized by namespace_sem, + * so globals will do just fine. + */ + user_ns = current->nsproxy->mnt_ns->user_ns; + last_dest = dest_mnt; + last_source = source_mnt; + mp = dest_mp; + list = tree_list; + dest_master = dest_mnt->mnt_master; + + /* all peers of dest_mnt, except dest_mnt itself */ + for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { + ret = propagate_one(n); + if (ret) goto out; - } + } - if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) { - mnt_set_mountpoint(m, dest_mp, child); - hlist_add_head(&child->mnt_hash, tree_list); - } else { - /* - * This can happen if the parent mount was bind mounted - * on some subdirectory of a shared/slave mount. - */ - hlist_add_head(&child->mnt_hash, &tmp_list); - } - prev_dest_mnt = m; - prev_src_mnt = child; + /* all slave groups */ + for (m = next_group(dest_mnt, dest_mnt); m; + m = next_group(m, dest_mnt)) { + /* everything in that slave group */ + n = m; + do { + ret = propagate_one(n); + if (ret) + goto out; + n = next_peer(n); + } while (n != m); } out: - lock_mount_hash(); - while (!hlist_empty(&tmp_list)) { - child = hlist_entry(tmp_list.first, struct mount, mnt_hash); - umount_tree(child, 0); + read_seqlock_excl(&mount_lock); + hlist_for_each_entry(n, tree_list, mnt_hash) { + m = n->mnt_parent; + if (m->mnt_master != dest_mnt->mnt_master) + CLEAR_MNT_MARK(m->mnt_master); } - unlock_mount_hash(); + read_sequnlock_excl(&mount_lock); return ret; } @@ -341,6 +381,7 @@ static void __propagate_umount(struct mount *mnt) * other children */ if (child && list_empty(&child->mnt_mounts)) { + list_del_init(&child->mnt_child); hlist_del_init_rcu(&child->mnt_hash); hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash); } diff --git a/fs/pnode.h b/fs/pnode.h index fc28a27fa892..4a246358b031 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -16,6 +16,9 @@ #define IS_MNT_NEW(m) (!(m)->mnt_ns) #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED) #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE) +#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED) +#define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED) +#define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED) #define CL_EXPIRE 0x01 #define CL_SLAVE 0x02 diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 11c54fd51e16..0855f772cd41 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -246,6 +246,12 @@ posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) umode_t mode = 0; int not_equiv = 0; + /* + * A null ACL can always be presented as mode bits. + */ + if (!acl) + return 0; + FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: @@ -723,7 +729,7 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size) { posix_acl_xattr_header *ext_acl = (posix_acl_xattr_header *)buffer; - posix_acl_xattr_entry *ext_entry = ext_acl->a_entries; + posix_acl_xattr_entry *ext_entry; int real_size, n; real_size = posix_acl_xattr_size(acl->a_count); @@ -731,7 +737,8 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, return real_size; if (real_size > size) return -ERANGE; - + + ext_entry = ext_acl->a_entries; ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); for (n=0; n < acl->a_count; n++, ext_entry++) { diff --git a/fs/proc/array.c b/fs/proc/array.c index 656e401794de..baf3464bbce0 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -297,15 +297,11 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_puts(m, header); CAP_FOR_EACH_U32(__capi) { seq_printf(m, "%08x", - a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]); + a->cap[CAP_LAST_U32 - __capi]); } seq_putc(m, '\n'); } -/* Remove non-existent capabilities */ -#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \ - CAP_TO_MASK(CAP_LAST_CAP + 1) - 1) - static inline void task_cap(struct seq_file *m, struct task_struct *p) { const struct cred *cred; @@ -319,11 +315,6 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p) cap_bset = cred->cap_bset; rcu_read_unlock(); - NORM_CAPS(cap_inheritable); - NORM_CAPS(cap_permitted); - NORM_CAPS(cap_effective); - NORM_CAPS(cap_bset); - render_cap_t(m, "CapInh:\t", &cap_inheritable); render_cap_t(m, "CapPrm:\t", &cap_permitted); render_cap_t(m, "CapEff:\t", &cap_effective); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fb52b548080d..c4b2646b6d7c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,4 +1,5 @@ #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/mount.h> @@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) /* * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at + * vmacache most of the time. We have zero last_addr at * the beginning and also after lseek. We will have -1 last_addr * after the end of the vmas. */ @@ -1350,7 +1351,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, struct numa_maps *md; struct page *page; - if (pte_none(*pte)) + if (!pte_present(*pte)) return 0; page = pte_page(*pte); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 12823845d324..14120a3c6195 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -319,10 +319,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - sprintf(name, "console-%s", psname); + sprintf(name, "console-%s-%lld", psname, id); break; case PSTORE_TYPE_FTRACE: - sprintf(name, "ftrace-%s", psname); + sprintf(name, "ftrace-%s-%lld", psname, id); break; case PSTORE_TYPE_MCE: sprintf(name, "mce-%s-%lld", psname, id); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index cfc8dcc16043..89da95700c69 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -637,7 +637,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dqstats_inc(DQST_LOOKUPS); err = sb->dq_op->write_dquot(dquot); if (!ret && err) - err = ret; + ret = err; dqput(dquot); spin_lock(&dq_list_lock); } @@ -702,6 +702,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) struct dquot *dquot; unsigned long freed = 0; + spin_lock(&dq_list_lock); head = free_dquots.prev; while (head != &free_dquots && sc->nr_to_scan) { dquot = list_entry(head, struct dquot, dq_free); @@ -713,6 +714,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) freed++; head = free_dquots.prev; } + spin_unlock(&dq_list_lock); return freed; } diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 1fd2051109a3..af677353a3f5 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -125,6 +125,7 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx) int d_reclen; char *d_name; ino_t d_ino; + loff_t cur_pos = deh_offset(deh); if (!de_visible(deh)) /* it is hidden entry */ @@ -196,8 +197,9 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx) if (local_buf != small_buf) { kfree(local_buf); } - // next entry should be looked for with such offset - next_pos = deh_offset(deh) + 1; + + /* deh_offset(deh) may be invalid now. */ + next_pos = cur_pos + 1; if (item_moved(&tmp_ih, &path_to_entry)) { set_cpu_key_k_offset(&pos_key, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index ad62bdbb451e..1e4cf9d73130 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3220,8 +3220,14 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_size != i_size_read(inode)) { error = inode_newsize_ok(inode, attr->ia_size); if (!error) { + /* + * Could race against reiserfs_file_release + * if called from NFS, so take tailpack mutex. + */ + mutex_lock(&REISERFS_I(inode)->tailpack); truncate_setsize(inode, attr->ia_size); - reiserfs_vfs_truncate_file(inode); + reiserfs_truncate_file(inode, 1); + mutex_unlock(&REISERFS_I(inode)->tailpack); } } diff --git a/fs/super.c b/fs/super.c index 80d5cf2ca765..88a6bc6e3cc9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -81,6 +81,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink, inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid); dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid); total_objects = dentries + inodes + fs_objects + 1; + if (!total_objects) + total_objects = 1; /* proportion the scan between the caches */ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); @@ -802,7 +804,10 @@ void emergency_remount(void) static DEFINE_IDA(unnamed_dev_ida); static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */ -static int unnamed_dev_start = 0; /* don't bother trying below it */ +/* Many userspace utilities consider an FSID of 0 invalid. + * Always return at least 1 from get_anon_bdev. + */ +static int unnamed_dev_start = 1; int get_anon_bdev(dev_t *p) { diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 810cf6e613e5..5fd2bf18e27d 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -47,12 +47,13 @@ static int sysfs_kf_seq_show(struct seq_file *sf, void *v) ssize_t count; char *buf; - /* acquire buffer and ensure that it's >= PAGE_SIZE */ + /* acquire buffer and ensure that it's >= PAGE_SIZE and clear */ count = seq_get_buf(sf, &buf); if (count < PAGE_SIZE) { seq_commit(sf, -1); return 0; } + memset(buf, 0, PAGE_SIZE); /* * Invoke show(). Control may reach here via seq file lseek even diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index ff8229340cd5..26b69b2d4a45 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -166,15 +166,10 @@ static int do_commit(struct ubifs_info *c) err = ubifs_orphan_end_commit(c); if (err) goto out; - old_ltail_lnum = c->ltail_lnum; - err = ubifs_log_end_commit(c, new_ltail_lnum); - if (err) - goto out; err = dbg_check_old_index(c, &zroot); if (err) goto out; - mutex_lock(&c->mst_mutex); c->mst_node->cmt_no = cpu_to_le64(c->cmt_no); c->mst_node->log_lnum = cpu_to_le32(new_ltail_lnum); c->mst_node->root_lnum = cpu_to_le32(zroot.lnum); @@ -203,8 +198,9 @@ static int do_commit(struct ubifs_info *c) c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); else c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS); - err = ubifs_write_master(c); - mutex_unlock(&c->mst_mutex); + + old_ltail_lnum = c->ltail_lnum; + err = ubifs_log_end_commit(c, new_ltail_lnum); if (err) goto out; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 123c79b7261e..b56eb6275744 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1525,8 +1525,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma, } wait_for_stable_page(page); - unlock_page(page); - return 0; + return VM_FAULT_LOCKED; out_unlock: unlock_page(page); diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index a902c5919e42..8d59de86dc9a 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -106,10 +106,14 @@ static inline long long empty_log_bytes(const struct ubifs_info *c) h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs; t = (long long)c->ltail_lnum * c->leb_size; - if (h >= t) + if (h > t) return c->log_bytes - h + t; - else + else if (h != t) return t - h; + else if (c->lhead_lnum != c->ltail_lnum) + return 0; + else + return c->log_bytes; } /** @@ -447,9 +451,9 @@ out: * @ltail_lnum: new log tail LEB number * * This function is called on when the commit operation was finished. It - * moves log tail to new position and unmaps LEBs which contain obsolete data. - * Returns zero in case of success and a negative error code in case of - * failure. + * moves log tail to new position and updates the master node so that it stores + * the new log tail LEB number. Returns zero in case of success and a negative + * error code in case of failure. */ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) { @@ -477,7 +481,12 @@ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) spin_unlock(&c->buds_lock); err = dbg_check_bud_bytes(c); + if (err) + goto out; + err = ubifs_write_master(c); + +out: mutex_unlock(&c->log_mutex); return err; } diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index ab83ace9910a..1a4bb9e8b3b8 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -352,10 +352,9 @@ int ubifs_read_master(struct ubifs_info *c) * ubifs_write_master - write master node. * @c: UBIFS file-system description object * - * This function writes the master node. The caller has to take the - * @c->mst_mutex lock before calling this function. Returns zero in case of - * success and a negative error code in case of failure. The master node is - * written twice to enable recovery. + * This function writes the master node. Returns zero in case of success and a + * negative error code in case of failure. The master node is written twice to + * enable recovery. */ int ubifs_write_master(struct ubifs_info *c) { diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c index f35135e28e96..9a9fb94a41c6 100644 --- a/fs/ubifs/shrinker.c +++ b/fs/ubifs/shrinker.c @@ -128,7 +128,6 @@ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention) freed = ubifs_destroy_tnc_subtree(znode); atomic_long_sub(freed, &ubifs_clean_zn_cnt); atomic_long_sub(freed, &c->clean_zn_cnt); - ubifs_assert(atomic_long_read(&c->clean_zn_cnt) >= 0); total_freed += freed; znode = zprev; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5ded8490c0c6..94d9a64287b7 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1957,7 +1957,6 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi) mutex_init(&c->lp_mutex); mutex_init(&c->tnc_mutex); mutex_init(&c->log_mutex); - mutex_init(&c->mst_mutex); mutex_init(&c->umount_mutex); mutex_init(&c->bu_mutex); mutex_init(&c->write_reserve_mutex); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index e8c8cfe1435c..7ab9c710c749 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1042,7 +1042,6 @@ struct ubifs_debug_info; * * @mst_node: master node * @mst_offs: offset of valid master node - * @mst_mutex: protects the master node area, @mst_node, and @mst_offs * * @max_bu_buf_len: maximum bulk-read buffer length * @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu @@ -1282,7 +1281,6 @@ struct ubifs_info { struct ubifs_mst_node *mst_node; int mst_offs; - struct mutex mst_mutex; int max_bu_buf_len; struct mutex bu_mutex; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 982ce05c87ed..287cd5f23421 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1271,13 +1271,22 @@ update_time: return 0; } +/* + * Maximum length of linked list formed by ICB hierarchy. The chosen number is + * arbitrary - just that we hopefully don't limit any real use of rewritten + * inode on write-once media but avoid looping for too long on corrupted media. + */ +#define UDF_MAX_ICB_NESTING 1024 + static void __udf_read_inode(struct inode *inode) { struct buffer_head *bh = NULL; struct fileEntry *fe; uint16_t ident; struct udf_inode_info *iinfo = UDF_I(inode); + unsigned int indirections = 0; +reread: /* * Set defaults, but the inode is still incomplete! * Note: get_new_inode() sets the following on a new inode: @@ -1314,28 +1323,26 @@ static void __udf_read_inode(struct inode *inode) ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1, &ident); if (ident == TAG_IDENT_IE && ibh) { - struct buffer_head *nbh = NULL; struct kernel_lb_addr loc; struct indirectEntry *ie; ie = (struct indirectEntry *)ibh->b_data; loc = lelb_to_cpu(ie->indirectICB.extLocation); - if (ie->indirectICB.extLength && - (nbh = udf_read_ptagged(inode->i_sb, &loc, 0, - &ident))) { - if (ident == TAG_IDENT_FE || - ident == TAG_IDENT_EFE) { - memcpy(&iinfo->i_location, - &loc, - sizeof(struct kernel_lb_addr)); - brelse(bh); - brelse(ibh); - brelse(nbh); - __udf_read_inode(inode); + if (ie->indirectICB.extLength) { + brelse(bh); + brelse(ibh); + memcpy(&iinfo->i_location, &loc, + sizeof(struct kernel_lb_addr)); + if (++indirections > UDF_MAX_ICB_NESTING) { + udf_err(inode->i_sb, + "too many ICBs in ICB hierarchy" + " (max %d supported)\n", + UDF_MAX_ICB_NESTING); + make_bad_inode(inode); return; } - brelse(nbh); + goto reread; } } brelse(ibh); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index db2cfb067d0b..0461fbe405b7 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -434,10 +434,22 @@ xfs_start_page_writeback( { ASSERT(PageLocked(page)); ASSERT(!PageWriteback(page)); - if (clear_dirty) + + /* + * if the page was not fully cleaned, we need to ensure that the higher + * layers come back to it correctly. That means we need to keep the page + * dirty, and for WB_SYNC_ALL writeback we need to ensure the + * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to + * write this page in this writeback sweep will be made. + */ + if (clear_dirty) { clear_page_dirty_for_io(page); - set_page_writeback(page); + set_page_writeback(page); + } else + set_page_writeback_keepwrite(page); + unlock_page(page); + /* If no buffers on the page are to be written, finish it here */ if (!buffers) end_page_writeback(page); @@ -1660,11 +1672,72 @@ xfs_vm_readpages( return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks); } +/* + * This is basically a copy of __set_page_dirty_buffers() with one + * small tweak: buffers beyond EOF do not get marked dirty. If we mark them + * dirty, we'll never be able to clean them because we don't write buffers + * beyond EOF, and that means we can't invalidate pages that span EOF + * that have been marked dirty. Further, the dirty state can leak into + * the file interior if the file is extended, resulting in all sorts of + * bad things happening as the state does not match the underlying data. + * + * XXX: this really indicates that bufferheads in XFS need to die. Warts like + * this only exist because of bufferheads and how the generic code manages them. + */ +STATIC int +xfs_vm_set_page_dirty( + struct page *page) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + loff_t end_offset; + loff_t offset; + int newly_dirty; + + if (unlikely(!mapping)) + return !TestSetPageDirty(page); + + end_offset = i_size_read(inode); + offset = page_offset(page); + + spin_lock(&mapping->private_lock); + if (page_has_buffers(page)) { + struct buffer_head *head = page_buffers(page); + struct buffer_head *bh = head; + + do { + if (offset < end_offset) + set_buffer_dirty(bh); + bh = bh->b_this_page; + offset += 1 << inode->i_blkbits; + } while (bh != head); + } + newly_dirty = !TestSetPageDirty(page); + spin_unlock(&mapping->private_lock); + + if (newly_dirty) { + /* sigh - __set_page_dirty() is static, so copy it here, too */ + unsigned long flags; + + spin_lock_irqsave(&mapping->tree_lock, flags); + if (page->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(!PageUptodate(page)); + account_page_dirtied(page, mapping); + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); + } + spin_unlock_irqrestore(&mapping->tree_lock, flags); + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + } + return newly_dirty; +} + const struct address_space_operations xfs_address_space_operations = { .readpage = xfs_vm_readpage, .readpages = xfs_vm_readpages, .writepage = xfs_vm_writepage, .writepages = xfs_vm_writepages, + .set_page_dirty = xfs_vm_set_page_dirty, .releasepage = xfs_vm_releasepage, .invalidatepage = xfs_vm_invalidatepage, .write_begin = xfs_vm_write_begin, diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 796272a2e129..e69d57be866b 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -1295,7 +1295,7 @@ xfs_da3_fixhashpath( node = blk->bp->b_addr; dp->d_ops->node_hdr_from_disk(&nodehdr, node); btree = dp->d_ops->node_tree_p(node); - if (be32_to_cpu(btree->hashval) == lasthash) + if (be32_to_cpu(btree[blk->index].hashval) == lasthash) break; blk->hashval = lasthash; btree[blk->index].hashval = cpu_to_be32(lasthash); diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 7aeb4c895b32..95f94483c3d7 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1011,7 +1011,8 @@ xfs_qm_dqflush( * Get the buffer containing the on-disk dquot */ error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL); + mp->m_quotainfo->qi_dqchunklen, 0, &bp, + &xfs_dquot_buf_ops); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 64b48eade91d..f50def6018a9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -302,7 +302,16 @@ xfs_file_aio_read( xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } - truncate_pagecache_range(VFS_I(ip), pos, -1); + + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, -1); + WARN_ON_ONCE(ret); + ret = 0; } xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); } @@ -683,7 +692,15 @@ xfs_file_dio_aio_write( pos, -1); if (ret) goto out; - truncate_pagecache_range(VFS_I(ip), pos, -1); + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, -1); + WARN_ON_ONCE(ret); + ret = 0; } /* diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index bcfe61202115..78e62cc471c5 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1241,7 +1241,7 @@ xfs_ioctl_setattr( * cleared upon successful return from chown() */ if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && - !inode_capable(VFS_I(ip), CAP_FSETID)) + !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); /* diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index b0f4ef77fa70..bf9781e9fd92 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -24,7 +24,8 @@ struct xfs_log_vec { struct xfs_log_iovec *lv_iovecp; /* iovec array */ struct xfs_log_item *lv_item; /* owner */ char *lv_buf; /* formatted buffer */ - int lv_buf_len; /* size of formatted buffer */ + int lv_bytes; /* accounted space in buffer */ + int lv_buf_len; /* aligned size of buffer */ int lv_size; /* size of allocated lv */ }; @@ -52,15 +53,21 @@ xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp, return vec->i_addr; } +/* + * We need to make sure the next buffer is naturally aligned for the biggest + * basic data type we put into it. We already accounted for this padding when + * sizing the buffer. + * + * However, this padding does not get written into the log, and hence we have to + * track the space used by the log vectors separately to prevent log space hangs + * due to inaccurate accounting (i.e. a leak) of the used log space through the + * CIL context ticket. + */ static inline void xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len) { - /* - * We need to make sure the next buffer is naturally aligned for the - * biggest basic data type we put into it. We already accounted for - * this when sizing the buffer. - */ lv->lv_buf_len += round_up(len, sizeof(uint64_t)); + lv->lv_bytes += len; vec->i_len = len; } diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 4ef6fdbced78..bcfbaae4702c 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -97,7 +97,7 @@ xfs_cil_prepare_item( { /* Account for the new LV being passed in */ if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) { - *diff_len += lv->lv_buf_len; + *diff_len += lv->lv_bytes; *diff_iovecs += lv->lv_niovecs; } @@ -111,7 +111,7 @@ xfs_cil_prepare_item( else if (old_lv != lv) { ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED); - *diff_len -= old_lv->lv_buf_len; + *diff_len -= old_lv->lv_bytes; *diff_iovecs -= old_lv->lv_niovecs; kmem_free(old_lv); } @@ -239,7 +239,7 @@ xlog_cil_insert_format_items( * that the space reservation accounting is correct. */ *diff_iovecs -= lv->lv_niovecs; - *diff_len -= lv->lv_buf_len; + *diff_len -= lv->lv_bytes; } else { /* allocate new data chunk */ lv = kmem_zalloc(buf_size, KM_SLEEP|KM_NOFS); @@ -259,6 +259,7 @@ xlog_cil_insert_format_items( /* The allocated data region lies beyond the iovec region */ lv->lv_buf_len = 0; + lv->lv_bytes = 0; lv->lv_buf = (char *)lv + buf_size - nbytes; ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t))); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index bce53ac81096..eb26418814fe 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2125,6 +2125,17 @@ xlog_recover_validate_buf_type( __uint16_t magic16; __uint16_t magicda; + /* + * We can only do post recovery validation on items on CRC enabled + * fielsystems as we need to know when the buffer was written to be able + * to determine if we should have replayed the item. If we replay old + * metadata over a newer buffer, then it will enter a temporarily + * inconsistent state resulting in verification failures. Hence for now + * just avoid the verification stage for non-crc filesystems + */ + if (!xfs_sb_version_hascrc(&mp->m_sb)) + return; + magic32 = be32_to_cpu(*(__be32 *)bp->b_addr); magic16 = be16_to_cpu(*(__be16*)bp->b_addr); magicda = be16_to_cpu(info->magic); @@ -2160,8 +2171,6 @@ xlog_recover_validate_buf_type( bp->b_ops = &xfs_agf_buf_ops; break; case XFS_BLFT_AGFL_BUF: - if (!xfs_sb_version_hascrc(&mp->m_sb)) - break; if (magic32 != XFS_AGFL_MAGIC) { xfs_warn(mp, "Bad AGFL block magic!"); ASSERT(0); @@ -2194,10 +2203,6 @@ xlog_recover_validate_buf_type( #endif break; case XFS_BLFT_DINO_BUF: - /* - * we get here with inode allocation buffers, not buffers that - * track unlinked list changes. - */ if (magic16 != XFS_DINODE_MAGIC) { xfs_warn(mp, "Bad INODE block magic!"); ASSERT(0); @@ -2277,8 +2282,6 @@ xlog_recover_validate_buf_type( bp->b_ops = &xfs_attr3_leaf_buf_ops; break; case XFS_BLFT_ATTR_RMT_BUF: - if (!xfs_sb_version_hascrc(&mp->m_sb)) - break; if (magic32 != XFS_ATTR3_RMT_MAGIC) { xfs_warn(mp, "Bad attr remote magic!"); ASSERT(0); @@ -2385,16 +2388,7 @@ xlog_recover_do_reg_buffer( /* Shouldn't be any more regions */ ASSERT(i == item->ri_total); - /* - * We can only do post recovery validation on items on CRC enabled - * fielsystems as we need to know when the buffer was written to be able - * to determine if we should have replayed the item. If we replay old - * metadata over a newer buffer, then it will enter a temporarily - * inconsistent state resulting in verification failures. Hence for now - * just avoid the verification stage for non-crc filesystems - */ - if (xfs_sb_version_hascrc(&mp->m_sb)) - xlog_recover_validate_buf_type(mp, bp, buf_f); + xlog_recover_validate_buf_type(mp, bp, buf_f); } /* @@ -2502,12 +2496,29 @@ xlog_recover_buffer_pass2( } /* - * recover the buffer only if we get an LSN from it and it's less than + * Recover the buffer only if we get an LSN from it and it's less than * the lsn of the transaction we are replaying. + * + * Note that we have to be extremely careful of readahead here. + * Readahead does not attach verfiers to the buffers so if we don't + * actually do any replay after readahead because of the LSN we found + * in the buffer if more recent than that current transaction then we + * need to attach the verifier directly. Failure to do so can lead to + * future recovery actions (e.g. EFI and unlinked list recovery) can + * operate on the buffers and they won't get the verifier attached. This + * can lead to blocks on disk having the correct content but a stale + * CRC. + * + * It is safe to assume these clean buffers are currently up to date. + * If the buffer is dirtied by a later transaction being replayed, then + * the verifier will be reset to match whatever recover turns that + * buffer into. */ lsn = xlog_recover_get_buf_lsn(mp, bp); - if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) + if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { + xlog_recover_validate_buf_type(mp, bp, buf_f); goto out_release; + } if (buf_f->blf_flags & XFS_BLF_INODE_BUF) { error = xlog_recover_do_inode_buffer(mp, item, bp, buf_f); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index f96c05669a9e..0eaaa2d296f0 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -320,8 +320,18 @@ reread: /* * Initialize the mount structure from the superblock. */ - xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp)); - xfs_sb_quota_from_disk(&mp->m_sb); + xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp)); + + /* + * If we haven't validated the superblock, do so now before we try + * to check the sector size and reread the superblock appropriately. + */ + if (sbp->sb_magicnum != XFS_SB_MAGIC) { + if (loud) + xfs_warn(mp, "Invalid superblock magic number"); + error = EINVAL; + goto release_buf; + } /* * We must be able to do sector-sized and sector-aligned IO. @@ -334,11 +344,11 @@ reread: goto release_buf; } - /* - * Re-read the superblock so the buffer is correctly sized, - * and properly verified. - */ if (buf_ops == NULL) { + /* + * Re-read the superblock so the buffer is correctly sized, + * and properly verified. + */ xfs_buf_relse(bp); sector_size = sbp->sb_sectsize; buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 348e4d2ed6e6..6d7d1de13403 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1176,6 +1176,12 @@ xfs_qm_dqiter_bufs( if (error) break; + /* + * A corrupt buffer might not have a verifier attached, so + * make sure we have the correct one attached before writeback + * occurs. + */ + bp->b_ops = &xfs_dquot_buf_ops; xfs_qm_reset_dqcounts(mp, bp, firstid, type); xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); @@ -1261,7 +1267,7 @@ xfs_qm_dqiterate( xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, rablkno), mp->m_quotainfo->qi_dqchunklen, - NULL); + &xfs_dquot_buf_ops); rablkno++; } } diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index 1e116794bb66..4afd393846d3 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -397,10 +397,11 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp) } } -void -xfs_sb_from_disk( +static void +__xfs_sb_from_disk( struct xfs_sb *to, - xfs_dsb_t *from) + xfs_dsb_t *from, + bool convert_xquota) { to->sb_magicnum = be32_to_cpu(from->sb_magicnum); to->sb_blocksize = be32_to_cpu(from->sb_blocksize); @@ -456,6 +457,17 @@ xfs_sb_from_disk( to->sb_pad = 0; to->sb_pquotino = be64_to_cpu(from->sb_pquotino); to->sb_lsn = be64_to_cpu(from->sb_lsn); + /* Convert on-disk flags to in-memory flags? */ + if (convert_xquota) + xfs_sb_quota_from_disk(to); +} + +void +xfs_sb_from_disk( + struct xfs_sb *to, + xfs_dsb_t *from) +{ + __xfs_sb_from_disk(to, from, true); } static inline void @@ -571,7 +583,11 @@ xfs_sb_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_sb sb; - xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp)); + /* + * Use call variant which doesn't convert quota flags from disk + * format, because xfs_mount_validate_sb checks the on-disk flags. + */ + __xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false); /* * Only check the in progress field for the primary superblock as diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 8256eb4ad057..ac46782c10d3 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -118,6 +118,7 @@ struct acpi_device; struct acpi_hotplug_profile { struct kobject kobj; int (*scan_dependent)(struct acpi_device *adev); + void (*notify_online)(struct acpi_device *adev); bool enabled:1; bool demand_offline:1; }; @@ -228,7 +229,6 @@ struct acpi_device_pnp { acpi_device_name device_name; /* Driver-determined */ acpi_device_class device_class; /* " */ union acpi_object *str_obj; /* unicode string for _STR method */ - unsigned long sun; /* _SUN */ }; #define acpi_device_bid(d) ((d)->pnp.bus_id) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 34c7bdc06014..38a743705cc6 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -680,24 +680,35 @@ static inline int pmd_numa(pmd_t pmd) #ifndef pte_mknonnuma static inline pte_t pte_mknonnuma(pte_t pte) { - pte = pte_clear_flags(pte, _PAGE_NUMA); - return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED); + pteval_t val = pte_val(pte); + + val &= ~_PAGE_NUMA; + val |= (_PAGE_PRESENT|_PAGE_ACCESSED); + return __pte(val); } #endif #ifndef pmd_mknonnuma static inline pmd_t pmd_mknonnuma(pmd_t pmd) { - pmd = pmd_clear_flags(pmd, _PAGE_NUMA); - return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED); + pmdval_t val = pmd_val(pmd); + + val &= ~_PAGE_NUMA; + val |= (_PAGE_PRESENT|_PAGE_ACCESSED); + + return __pmd(val); } #endif #ifndef pte_mknuma static inline pte_t pte_mknuma(pte_t pte) { - pte = pte_set_flags(pte, _PAGE_NUMA); - return pte_clear_flags(pte, _PAGE_PRESENT); + pteval_t val = pte_val(pte); + + val &= ~_PAGE_PRESENT; + val |= _PAGE_NUMA; + + return __pte(val); } #endif @@ -716,8 +727,12 @@ static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, #ifndef pmd_mknuma static inline pmd_t pmd_mknuma(pmd_t pmd) { - pmd = pmd_set_flags(pmd, _PAGE_NUMA); - return pmd_clear_flags(pmd, _PAGE_PRESENT); + pmdval_t val = pmd_val(pmd); + + val &= ~_PAGE_PRESENT; + val |= _PAGE_NUMA; + + return __pmd(val); } #endif diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h index d3909effd725..d96deb443f18 100644 --- a/include/asm-generic/word-at-a-time.h +++ b/include/asm-generic/word-at-a-time.h @@ -50,11 +50,7 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct } #ifndef zero_bytemask -#ifdef CONFIG_64BIT -#define zero_bytemask(mask) (~0ul << fls64(mask)) -#else -#define zero_bytemask(mask) (~0ul << fls(mask)) -#endif /* CONFIG_64BIT */ -#endif /* zero_bytemask */ +#define zero_bytemask(mask) (~0ul << __fls(mask) << 1) +#endif #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 49376aec2fbb..ca52de5a5c97 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -17,6 +17,7 @@ {0x1002, 0x1315, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x1316, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x1317, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x1318, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x131B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x131C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x131D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ @@ -73,7 +74,6 @@ {0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ {0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ {0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ - {0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \ {0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ {0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ {0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ @@ -164,8 +164,11 @@ {0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6604, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6605, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6608, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ @@ -175,6 +178,8 @@ {0x1002, 0x6631, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6640, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6641, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6646, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6650, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6651, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ @@ -297,6 +302,7 @@ {0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x682C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h index 8c1603b10665..433528ab5161 100644 --- a/include/dt-bindings/clock/tegra124-car.h +++ b/include/dt-bindings/clock/tegra124-car.h @@ -29,7 +29,7 @@ /* 10 (register bit affects spdif_in and spdif_out) */ #define TEGRA124_CLK_I2S1 11 #define TEGRA124_CLK_I2C1 12 -#define TEGRA124_CLK_NDFLASH 13 +/* 13 */ #define TEGRA124_CLK_SDMMC1 14 #define TEGRA124_CLK_SDMMC4 15 /* 16 */ @@ -83,7 +83,7 @@ /* 64 */ #define TEGRA124_CLK_UARTD 65 -#define TEGRA124_CLK_UARTE 66 +/* 66 */ #define TEGRA124_CLK_I2C3 67 #define TEGRA124_CLK_SBC4 68 #define TEGRA124_CLK_SDMMC3 69 @@ -97,7 +97,7 @@ #define TEGRA124_CLK_TRACE 77 #define TEGRA124_CLK_SOC_THERM 78 #define TEGRA124_CLK_DTV 79 -#define TEGRA124_CLK_NDSPEED 80 +/* 80 */ #define TEGRA124_CLK_I2CSLOW 81 #define TEGRA124_CLK_DSIB 82 #define TEGRA124_CLK_TSEC 83 diff --git a/include/dt-bindings/pinctrl/dra.h b/include/dt-bindings/pinctrl/dra.h index 002a2855c046..3d33794e4f3e 100644 --- a/include/dt-bindings/pinctrl/dra.h +++ b/include/dt-bindings/pinctrl/dra.h @@ -30,7 +30,8 @@ #define MUX_MODE14 0xe #define MUX_MODE15 0xf -#define PULL_ENA (1 << 16) +#define PULL_ENA (0 << 16) +#define PULL_DIS (1 << 16) #define PULL_UP (1 << 17) #define INPUT_EN (1 << 18) #define SLEWCONTROL (1 << 19) @@ -38,10 +39,10 @@ #define WAKEUP_EVENT (1 << 25) /* Active pin states */ -#define PIN_OUTPUT 0 +#define PIN_OUTPUT (0 | PULL_DIS) #define PIN_OUTPUT_PULLUP (PIN_OUTPUT | PULL_ENA | PULL_UP) #define PIN_OUTPUT_PULLDOWN (PIN_OUTPUT | PULL_ENA) -#define PIN_INPUT INPUT_EN +#define PIN_INPUT (INPUT_EN | PULL_DIS) #define PIN_INPUT_SLEW (INPUT_EN | SLEWCONTROL) #define PIN_INPUT_PULLUP (PULL_ENA | INPUT_EN | PULL_UP) #define PIN_INPUT_PULLDOWN (PULL_ENA | INPUT_EN) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1151a1dcfe41..cd80aa80d03e 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -37,6 +37,7 @@ #include <linux/list.h> #include <linux/mod_devicetable.h> +#include <linux/dynamic_debug.h> #include <acpi/acpi.h> #include <acpi/acpi_bus.h> @@ -590,6 +591,14 @@ static inline __printf(3, 4) void acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} #endif /* !CONFIG_ACPI */ +#if defined(CONFIG_ACPI) && defined(CONFIG_DYNAMIC_DEBUG) +__printf(3, 4) +void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const char *fmt, ...); +#else +#define __acpi_handle_debug(descriptor, handle, fmt, ...) \ + acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__); +#endif + /* * acpi_handle_<level>: Print message with ACPI prefix and object path * @@ -611,11 +620,19 @@ acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} #define acpi_handle_info(handle, fmt, ...) \ acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__) -/* REVISIT: Support CONFIG_DYNAMIC_DEBUG when necessary */ -#if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) +#if defined(DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__) #else +#if defined(CONFIG_DYNAMIC_DEBUG) +#define acpi_handle_debug(handle, fmt, ...) \ +do { \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + __acpi_handle_debug(&descriptor, handle, pr_fmt(fmt), \ + ##__VA_ARGS__); \ +} while (0) +#else #define acpi_handle_debug(handle, fmt, ...) \ ({ \ if (0) \ @@ -623,5 +640,6 @@ acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} 0; \ }) #endif +#endif #endif /*_LINUX_ACPI_H*/ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 24819001f5c8..e488e9459a93 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -95,7 +95,7 @@ struct backing_dev_info { unsigned int max_ratio, max_prop_frac; struct bdi_writeback wb; /* default writeback info for this bdi */ - spinlock_t wb_lock; /* protects work_list */ + spinlock_t wb_lock; /* protects work_list & wb.dwork scheduling */ struct list_head work_list; diff --git a/include/linux/bio.h b/include/linux/bio.h index 5a4d39b4686b..5aa372a7380c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -216,9 +216,9 @@ static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter, } #define for_each_bvec(bvl, bio_vec, iter, start) \ - for ((iter) = start; \ - (bvl) = bvec_iter_bvec((bio_vec), (iter)), \ - (iter).bi_size; \ + for (iter = (start); \ + (iter).bi_size && \ + ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4afa4f8f6090..a693c6d29328 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1232,10 +1232,9 @@ static inline int queue_alignment_offset(struct request_queue *q) static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = (sector << 9) & (granularity - 1); + unsigned int alignment = sector_div(sector, granularity >> 9) << 9; - return (granularity + lim->alignment_offset - alignment) - & (granularity - 1); + return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) diff --git a/include/linux/capability.h b/include/linux/capability.h index a6ee1f9a5018..aa93e5ef594c 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -78,8 +78,11 @@ extern const kernel_cap_t __cap_init_eff_set; # error Fix up hand-coded capability macro initializers #else /* HAND-CODED capability initializers */ +#define CAP_LAST_U32 ((_KERNEL_CAPABILITY_U32S) - 1) +#define CAP_LAST_U32_VALID_MASK (CAP_TO_MASK(CAP_LAST_CAP + 1) -1) + # define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }}) -# define CAP_FULL_SET ((kernel_cap_t){{ ~0, ~0 }}) +# define CAP_FULL_SET ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }}) # define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \ | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \ CAP_FS_MASK_B1 } }) @@ -210,7 +213,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); -extern bool inode_capable(const struct inode *inode, int cap); +extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); /* audit system wants to get cap info from files as well */ diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h new file mode 100644 index 000000000000..cdd1cc202d51 --- /dev/null +++ b/include/linux/compiler-gcc5.h @@ -0,0 +1,66 @@ +#ifndef __LINUX_COMPILER_H +#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead." +#endif + +#define __used __attribute__((__used__)) +#define __must_check __attribute__((warn_unused_result)) +#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) + +/* Mark functions as cold. gcc will assume any path leading to a call + to them will be unlikely. This means a lot of manual unlikely()s + are unnecessary now for any paths leading to the usual suspects + like BUG(), printk(), panic() etc. [but let's keep them for now for + older compilers] + + Early snapshots of gcc 4.3 don't support this and we can't detect this + in the preprocessor, but we can live with this because they're unreleased. + Maketime probing would be overkill here. + + gcc also has a __attribute__((__hot__)) to move hot functions into + a special section, but I don't see any sense in this right now in + the kernel context */ +#define __cold __attribute__((__cold__)) + +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) + +#ifndef __CHECKER__ +# define __compiletime_warning(message) __attribute__((warning(message))) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* __CHECKER__ */ + +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + * + * Early snapshots of gcc 4.5 don't support this and we can't detect + * this in the preprocessor, but we can live with this because they're + * unreleased. Really, we need to have autoconf for the kernel. + */ +#define unreachable() __builtin_unreachable() + +/* Mark a function definition as prohibited from being cloned. */ +#define __noclone __attribute__((__noclone__)) + +/* + * Tell the optimizer that something else uses this function or variable. + */ +#define __visible __attribute__((externally_visible)) + +/* + * GCC 'asm goto' miscompiles certain code sequences: + * + * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. + * Fixed in GCC 4.8.2 and later versions. + * + * (asm goto is automatically volatile - the naming reflects this.) + */ +#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#define __HAVE_BUILTIN_BSWAP16__ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 3fe661fe96d1..b19d3dc2e651 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -87,25 +87,26 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); /* - * get_mems_allowed is required when making decisions involving mems_allowed - * such as during page allocation. mems_allowed can be updated in parallel - * and depending on the new value an operation can fail potentially causing - * process failure. A retry loop with get_mems_allowed and put_mems_allowed - * prevents these artificial failures. + * read_mems_allowed_begin is required when making decisions involving + * mems_allowed such as during page allocation. mems_allowed can be updated in + * parallel and depending on the new value an operation can fail potentially + * causing process failure. A retry loop with read_mems_allowed_begin and + * read_mems_allowed_retry prevents these artificial failures. */ -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return read_seqcount_begin(¤t->mems_allowed_seq); } /* - * If this returns false, the operation that took place after get_mems_allowed - * may have failed. It is up to the caller to retry the operation if + * If this returns true, the operation that took place after + * read_mems_allowed_begin may have failed artificially due to a concurrent + * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return !read_seqcount_retry(¤t->mems_allowed_seq, seq); + return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) @@ -225,14 +226,14 @@ static inline void set_mems_allowed(nodemask_t nodemask) { } -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return 0; } -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return true; + return false; } #endif /* !CONFIG_CPUSETS */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bf72e9ac6de0..3b50cac7ccb3 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -429,7 +429,7 @@ static inline unsigned __d_entry_type(const struct dentry *dentry) return dentry->d_flags & DCACHE_ENTRY_TYPE; } -static inline bool d_is_directory(const struct dentry *dentry) +static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } @@ -439,6 +439,11 @@ static inline bool d_is_autodir(const struct dentry *dentry) return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } +static inline bool d_is_dir(const struct dentry *dentry) +{ + return d_can_lookup(dentry) || d_is_autodir(dentry); +} + static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c5c92d59e531..0a5f55272672 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -433,6 +433,7 @@ typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param); typedef void (*dma_async_tx_callback)(void *dma_async_param); struct dmaengine_unmap_data { + u8 map_cnt; u8 to_cnt; u8 from_cnt; u8 bidi_cnt; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f4233b195dab..2068dff8a2cc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -524,6 +524,7 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); +extern void ftrace_module_init(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); @@ -533,6 +534,7 @@ static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } static inline void ftrace_release_mod(struct module *mod) {} +static inline void ftrace_module_init(struct module *mod) {} static inline __init int register_ftrace_command(struct ftrace_func_command *cmd) { return -EINVAL; diff --git a/include/linux/futex.h b/include/linux/futex.h index b0d95cac826e..6435f46d6e13 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -55,7 +55,11 @@ union futex_key { #ifdef CONFIG_FUTEX extern void exit_robust_list(struct task_struct *curr); extern void exit_pi_state_list(struct task_struct *curr); +#ifdef CONFIG_HAVE_FUTEX_CMPXCHG +#define futex_cmpxchg_enabled 1 +#else extern int futex_cmpxchg_enabled; +#endif #else static inline void exit_robust_list(struct task_struct *curr) { diff --git a/include/linux/hid.h b/include/linux/hid.h index 31b9d299ef6c..00c88fccd162 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -286,6 +286,7 @@ struct hid_item { #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 #define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 #define HID_QUIRK_NO_INIT_INPUT_REPORTS 0x00000200 +#define HID_QUIRK_ALWAYS_POLL 0x00000400 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8c43cc469d78..42b05c4c53e5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -382,15 +382,13 @@ static inline pgoff_t basepage_index(struct page *page) extern void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); -int pmd_huge_support(void); -/* - * Currently hugepage migration is enabled only for pmd-based hugepage. - * This function will be updated when hugepage migration is more widely - * supported. - */ static inline int hugepage_migration_support(struct hstate *h) { - return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT); +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + return huge_page_shift(h) == PMD_SHIFT; +#else + return 0; +#endif } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, @@ -402,6 +400,16 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } +static inline bool hugepages_supported(void) +{ + /* + * Some platform decide whether they support huge pages at boot + * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when + * there is no such support + */ + return HPAGE_SHIFT != 0; +} + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL @@ -430,7 +438,6 @@ static inline pgoff_t basepage_index(struct page *page) return page->index; } #define dissolve_free_huge_pages(s, e) do {} while (0) -#define pmd_huge_support() 0 #define hugepage_migration_support(h) 0 static inline spinlock_t *huge_pte_lockptr(struct hstate *h, diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 344883dce584..6088058a3e00 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -464,15 +464,17 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, * 0 . 13 (Windows Server 2008) * 1 . 1 (Windows 7) * 2 . 4 (Windows 8) + * 3 . 0 (Windows 8 R2) */ #define VERSION_WS2008 ((0 << 16) | (13)) #define VERSION_WIN7 ((1 << 16) | (1)) #define VERSION_WIN8 ((2 << 16) | (4)) +#define VERSION_WIN8_1 ((3 << 16) | (0)) #define VERSION_INVAL -1 -#define VERSION_CURRENT VERSION_WIN8 +#define VERSION_CURRENT VERSION_WIN8_1 /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 7c8b20b120ea..a9a53b12397b 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -56,6 +56,7 @@ struct macvlan_dev { int numqueues; netdev_features_t tap_features; int minor; + int nest_level; }; static inline void macvlan_count_rx(const struct macvlan_dev *vlan, diff --git a/include/linux/if_team.h b/include/linux/if_team.h index a899dc24be15..a6aa970758a2 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -194,6 +194,7 @@ struct team { bool user_carrier_enabled; bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ + bool port_mtu_change_allowed; struct { unsigned int count; unsigned int interval; /* in ms */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index bbedfb56bd66..2abe67bd4df8 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -73,7 +73,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); -static inline int is_vlan_dev(struct net_device *dev) +static inline bool is_vlan_dev(struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } @@ -158,6 +158,7 @@ struct vlan_dev_priv { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif + unsigned int nest_level; }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) @@ -185,7 +186,6 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) } extern bool vlan_do_receive(struct sk_buff **skb); -extern struct sk_buff *vlan_untag(struct sk_buff *skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); @@ -227,11 +227,6 @@ static inline bool vlan_do_receive(struct sk_buff **skb) return false; } -static inline struct sk_buff *vlan_untag(struct sk_buff *skb) -{ - return skb; -} - static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 369cf2cd5144..68f46cd5d514 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -84,10 +84,12 @@ static inline void iio_trigger_put(struct iio_trigger *trig) put_device(&trig->dev); } -static inline void iio_trigger_get(struct iio_trigger *trig) +static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig) { get_device(&trig->dev); __module_get(trig->ops->owner); + + return trig; } /** diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a2678d35b5a2..203c43d3e1b8 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -202,7 +202,40 @@ static inline int check_wakeup_irqs(void) { return 0; } extern cpumask_var_t irq_default_affinity; -extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask); +/* Internal implementation. Use the helpers below */ +extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask, + bool force); + +/** + * irq_set_affinity - Set the irq affinity of a given irq + * @irq: Interrupt to set affinity + * @mask: cpumask + * + * Fails if cpumask does not contain an online CPU + */ +static inline int +irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) +{ + return __irq_set_affinity(irq, cpumask, false); +} + +/** + * irq_force_affinity - Force the irq affinity of a given irq + * @irq: Interrupt to set affinity + * @mask: cpumask + * + * Same as irq_set_affinity, but without checking the mask against + * online cpus. + * + * Solely for low level cpu hotplug code, where we need to make per + * cpu interrupts affine before the cpu becomes online. + */ +static inline int +irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) +{ + return __irq_set_affinity(irq, cpumask, true); +} + extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); @@ -238,6 +271,11 @@ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) return -EINVAL; } +static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) +{ + return 0; +} + static inline int irq_can_set_affinity(unsigned int irq) { return 0; diff --git a/include/linux/irq.h b/include/linux/irq.h index 7dc10036eff5..ef1ac9feff56 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -385,7 +385,8 @@ extern void remove_percpu_irq(unsigned int irq, struct irqaction *act); extern void irq_cpu_online(void); extern void irq_cpu_offline(void); -extern int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask); +extern int irq_set_affinity_locked(struct irq_data *data, + const struct cpumask *cpumask, bool force); #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) void irq_move_irq(struct irq_data *data); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 26e2661d3935..472c021a2d4f 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -27,6 +27,8 @@ struct irq_desc; * @irq_count: stats field to detect stalled irqs * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts + * @threads_handled: stats field for deferred spurious detection of threaded handlers + * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers * @lock: locking for SMP * @affinity_hint: hint to user space for preferred irq affinity * @affinity_notify: context for notification of affinity changes @@ -52,6 +54,8 @@ struct irq_desc { unsigned int irq_count; /* For detecting broken IRQs */ unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; + atomic_t threads_handled; + int threads_handled_last; raw_spinlock_t lock; struct cpumask *percpu_enabled; #ifdef CONFIG_SMP diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d5b50a19463c..0dae71e9971c 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -159,7 +159,11 @@ typedef struct journal_header_s * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * - * Checksum v1 and v2 are mutually exclusive features. + * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses + * journal_block_tag3_t to store a full 32-bit checksum. Everything else + * is the same as v2. + * + * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; @@ -179,6 +183,14 @@ struct commit_header { * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ +typedef struct journal_block_tag3_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ + __be32 t_checksum; /* crc32c(uuid+seq+block) */ +} journal_block_tag3_t; + typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ @@ -187,9 +199,6 @@ typedef struct journal_block_tag_s __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; -#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) -#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t)) - /* Tail of descriptor block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ @@ -284,6 +293,7 @@ typedef struct journal_superblock_s #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 +#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM @@ -291,7 +301,8 @@ typedef struct journal_superblock_s #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ - JBD2_FEATURE_INCOMPAT_CSUM_V2) + JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ + JBD2_FEATURE_INCOMPAT_CSUM_V3) #ifdef __KERNEL__ @@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y) extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); +static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) +{ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) || + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + return 1; + + return 0; +} + /* * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for * transaction control blocks. diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1f44466c1e9d..c367cbdf73ab 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -258,23 +258,11 @@ extern unsigned long preset_lpj; #define SEC_JIFFIE_SC (32 - SHIFT_HZ) #endif #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) -#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19) #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) -#define USEC_CONVERSION \ - ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\ - TICK_NSEC -1) / (u64)TICK_NSEC)) -/* - * USEC_ROUND is used in the timeval to jiffie conversion. See there - * for more details. It is the scaled resolution rounding value. Note - * that it is a 64-bit value. Since, when it is applied, we are already - * in jiffies (albit scaled), it is nothing but the bits we will shift - * off. - */ -#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1) /* * The maximum jiffie value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, diff --git a/include/linux/libata.h b/include/linux/libata.h index bec6dbe939a0..e13b3aef0b0c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -593,6 +593,7 @@ struct ata_host { struct device *dev; void __iomem * const *iomap; unsigned int n_ports; + unsigned int n_tags; /* nr of NCQ tags */ void *private_data; struct ata_port_operations *ops; unsigned long flags; @@ -822,6 +823,7 @@ struct ata_port { unsigned long qc_allocated; unsigned int qc_active; int nr_active_links; /* #links with active qcs */ + unsigned int last_tag; /* track next tag hw expects */ struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5f1ea756aace..5bba088bd239 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -176,6 +176,12 @@ static inline int vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return 0; + +#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + if (vma->vm_flags & VM_HUGETLB) + return 0; +#endif + /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not diff --git a/include/linux/mm.h b/include/linux/mm.h index c1b7414c7bef..0a0b024ec7e8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1123,6 +1123,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 290901a8c1de..2b58d192ea24 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,9 +342,9 @@ struct mm_rss_stat { struct kioctx_table; struct mm_struct { - struct vm_area_struct * mmap; /* list of VMAs */ + struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - struct vm_area_struct * mmap_cache; /* last find_vma result */ + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9b61b9bf81ac..e6800f0c0d7b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -75,9 +75,13 @@ enum { extern int page_group_by_mobility_disabled; +#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) +#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) + static inline int get_pageblock_migratetype(struct page *page) { - return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end); + BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2); + return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK); } struct free_area { diff --git a/include/linux/mount.h b/include/linux/mount.h index 371d346fa270..b0c1e6574e7f 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -42,15 +42,25 @@ struct mnt_namespace; * flag, consider how it interacts with shared mounts. */ #define MNT_SHARED_MASK (MNT_UNBINDABLE) -#define MNT_PROPAGATION_MASK (MNT_SHARED | MNT_UNBINDABLE) +#define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ + | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ + | MNT_READONLY) +#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) +#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) #define MNT_INTERNAL 0x4000 +#define MNT_LOCK_ATIME 0x040000 +#define MNT_LOCK_NOEXEC 0x080000 +#define MNT_LOCK_NOSUID 0x100000 +#define MNT_LOCK_NODEV 0x200000 #define MNT_LOCK_READONLY 0x400000 #define MNT_LOCKED 0x800000 #define MNT_DOOMED 0x1000000 #define MNT_SYNC_UMOUNT 0x2000000 +#define MNT_MARKED 0x4000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ diff --git a/include/linux/net.h b/include/linux/net.h index 94734a6259a4..17d83393afcc 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -248,24 +248,17 @@ do { \ bool __net_get_random_once(void *buf, int nbytes, bool *done, struct static_key *done_key); -#ifdef HAVE_JUMP_LABEL -#define ___NET_RANDOM_STATIC_KEY_INIT ((struct static_key) \ - { .enabled = ATOMIC_INIT(0), .entries = (void *)1 }) -#else /* !HAVE_JUMP_LABEL */ -#define ___NET_RANDOM_STATIC_KEY_INIT STATIC_KEY_INIT_FALSE -#endif /* HAVE_JUMP_LABEL */ - #define net_get_random_once(buf, nbytes) \ ({ \ bool ___ret = false; \ static bool ___done = false; \ - static struct static_key ___done_key = \ - ___NET_RANDOM_STATIC_KEY_INIT; \ - if (!static_key_true(&___done_key)) \ + static struct static_key ___once_key = \ + STATIC_KEY_INIT_TRUE; \ + if (static_key_true(&___once_key)) \ ___ret = __net_get_random_once(buf, \ nbytes, \ &___done, \ - &___done_key); \ + &___once_key); \ ___ret; \ }) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index daafd9561cbc..911718fa92ed 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1145,6 +1145,7 @@ struct net_device_ops { netdev_tx_t (*ndo_dfwd_start_xmit) (struct sk_buff *skb, struct net_device *dev, void *priv); + int (*ndo_get_lock_subclass)(struct net_device *dev); }; /* @@ -2861,7 +2862,12 @@ static inline void netif_addr_lock(struct net_device *dev) static inline void netif_addr_lock_nested(struct net_device *dev) { - spin_lock_nested(&dev->addr_list_lock, SINGLE_DEPTH_NESTING); + int subclass = SINGLE_DEPTH_NESTING; + + if (dev->netdev_ops->ndo_get_lock_subclass) + subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); + + spin_lock_nested(&dev->addr_list_lock, subclass); } static inline void netif_addr_lock_bh(struct net_device *dev) @@ -2988,6 +2994,14 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, priv; \ priv = netdev_lower_get_next_private_rcu(dev, &(iter))) +void *netdev_lower_get_next(struct net_device *dev, + struct list_head **iter); +#define netdev_for_each_lower_dev(dev, ldev, iter) \ + for (iter = &(dev)->adj_list.lower, \ + ldev = netdev_lower_get_next(dev, &(iter)); \ + ldev; \ + ldev = netdev_lower_get_next(dev, &(iter))) + void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); @@ -3003,6 +3017,8 @@ void netdev_upper_dev_unlink(struct net_device *dev, void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)); int skb_checksum_help(struct sk_buff *skb); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); diff --git a/include/linux/netlink.h b/include/linux/netlink.h index aad8eeaf416d..034cda789a15 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -16,9 +16,10 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) } enum netlink_skb_flags { - NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ - NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ - NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ + NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ + NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */ }; struct netlink_skb_parms { @@ -169,4 +170,11 @@ struct netlink_tap { extern int netlink_add_tap(struct netlink_tap *nt); extern int netlink_remove_tap(struct netlink_tap *nt); +bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, + struct user_namespace *ns, int cap); +bool netlink_ns_capable(const struct sk_buff *skb, + struct user_namespace *ns, int cap); +bool netlink_capable(const struct sk_buff *skb, int cap); +bool netlink_net_capable(const struct sk_buff *skb, int cap); + #endif /* __LINUX_NETLINK_H */ diff --git a/include/linux/of.h b/include/linux/of.h index 435cb995904d..3f8144dadaef 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -215,14 +215,12 @@ extern int of_property_read_u64(const struct device_node *np, extern int of_property_read_string(struct device_node *np, const char *propname, const char **out_string); -extern int of_property_read_string_index(struct device_node *np, - const char *propname, - int index, const char **output); extern int of_property_match_string(struct device_node *np, const char *propname, const char *string); -extern int of_property_count_strings(struct device_node *np, - const char *propname); +extern int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); @@ -422,15 +420,9 @@ static inline int of_property_read_string(struct device_node *np, return -ENOSYS; } -static inline int of_property_read_string_index(struct device_node *np, - const char *propname, int index, - const char **out_string) -{ - return -ENOSYS; -} - -static inline int of_property_count_strings(struct device_node *np, - const char *propname) +static inline int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index) { return -ENOSYS; } @@ -536,6 +528,70 @@ static inline struct device_node *of_find_matching_node( } /** + * of_property_read_string_array() - Read an array of strings from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_strs: output array of string pointers. + * @sz: number of array elements to read. + * + * Search for a property in a device tree node and retrieve a list of + * terminated string values (pointer to data, not a copy) in that property. + * + * If @out_strs is NULL, the number of strings in the property is returned. + */ +static inline int of_property_read_string_array(struct device_node *np, + const char *propname, const char **out_strs, + size_t sz) +{ + return of_property_read_string_helper(np, propname, out_strs, sz, 0); +} + +/** + * of_property_count_strings() - Find and return the number of strings from a + * multiple strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device tree node and retrieve the number of null + * terminated string contain in it. Returns the number of strings on + * success, -EINVAL if the property does not exist, -ENODATA if property + * does not have a value, and -EILSEQ if the string is not null-terminated + * within the length of the property data. + */ +static inline int of_property_count_strings(struct device_node *np, + const char *propname) +{ + return of_property_read_string_helper(np, propname, NULL, 0, 0); +} + +/** + * of_property_read_string_index() - Find and read a string from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @index: index of the string in the list of strings + * @out_string: pointer to null terminated return string, modified only if + * return value is 0. + * + * Search for a property in a device tree node and retrieve a null + * terminated string value (pointer to data, not a copy) in the list of strings + * contained in that property. + * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if + * property does not have a value, and -EILSEQ if the string is not + * null-terminated within the length of the property data. + * + * The out_string pointer is modified only if a valid string can be decoded. + */ +static inline int of_property_read_string_index(struct device_node *np, + const char *propname, + int index, const char **output) +{ + int rc = of_property_read_string_helper(np, propname, output, 1, index); + return rc < 0 ? rc : 0; +} + +/** * of_property_read_bool - Findfrom a property * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 3f23b4472c31..6404253d810d 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -44,11 +44,16 @@ extern void of_irq_init(const struct of_device_id *matches); #ifdef CONFIG_OF_IRQ extern int of_irq_count(struct device_node *dev); +extern int of_irq_get(struct device_node *dev, int index); #else static inline int of_irq_count(struct device_node *dev) { return 0; } +static inline int of_irq_get(struct device_node *dev, int index) +{ + return 0; +} #endif #if defined(CONFIG_OF) diff --git a/include/linux/oom.h b/include/linux/oom.h index 4cd62677feb9..17f0949bd822 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -50,6 +50,9 @@ static inline bool oom_task_origin(const struct task_struct *p) extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); + +extern int oom_kills_count(void); +extern void note_oom_kill(void); extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned int points, unsigned long totalpages, struct mem_cgroup *memcg, nodemask_t *nodemask, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d1fe1a761047..ca71a1d347a0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -317,13 +317,23 @@ CLEARPAGEFLAG(Uptodate, uptodate) extern void cancel_dirty_page(struct page *page, unsigned int account_size); int test_clear_page_writeback(struct page *page); -int test_set_page_writeback(struct page *page); +int __test_set_page_writeback(struct page *page, bool keep_write); + +#define test_set_page_writeback(page) \ + __test_set_page_writeback(page, false) +#define test_set_page_writeback_keepwrite(page) \ + __test_set_page_writeback(page, true) static inline void set_page_writeback(struct page *page) { test_set_page_writeback(page); } +static inline void set_page_writeback_keepwrite(struct page *page) +{ + test_set_page_writeback_keepwrite(page); +} + #ifdef CONFIG_PAGEFLAGS_EXTENDED /* * System with lots of page flags available. This allows separate diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 2ee8cd2466b5..c08730c10c7a 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -30,9 +30,12 @@ enum pageblock_bits { PB_migrate, PB_migrate_end = PB_migrate + 3 - 1, /* 3 bits required for migrate types */ -#ifdef CONFIG_COMPACTION PB_migrate_skip,/* If set the block is skipped by compaction */ -#endif /* CONFIG_COMPACTION */ + + /* + * Assume the bits will always align on a word. If this assumption + * changes then get/set pageblock needs updating. + */ NR_PAGEBLOCK_BITS }; @@ -62,11 +65,33 @@ extern int pageblock_order; /* Forward declaration */ struct page; +unsigned long get_pageblock_flags_mask(struct page *page, + unsigned long end_bitidx, + unsigned long mask); +void set_pageblock_flags_mask(struct page *page, + unsigned long flags, + unsigned long end_bitidx, + unsigned long mask); + /* Declarations for getting and setting flags. See mm/page_alloc.c */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx); -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx); +static inline unsigned long get_pageblock_flags_group(struct page *page, + int start_bitidx, int end_bitidx) +{ + unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; + unsigned long mask = (1 << nr_flag_bits) - 1; + + return get_pageblock_flags_mask(page, end_bitidx, mask); +} + +static inline void set_pageblock_flags_group(struct page *page, + unsigned long flags, + int start_bitidx, int end_bitidx) +{ + unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; + unsigned long mask = (1 << nr_flag_bits) - 1; + + set_pageblock_flags_mask(page, flags, end_bitidx, mask); +} #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 97fbecdd7a40..057c1d8c77e5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2551,6 +2551,7 @@ #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 #define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095E #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 95961f0bf62d..0afb48fd449d 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -110,7 +110,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref) pcpu_count = ACCESS_ONCE(ref->pcpu_count); if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) - __this_cpu_inc(*pcpu_count); + this_cpu_inc(*pcpu_count); else atomic_inc(&ref->count); @@ -139,7 +139,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) pcpu_count = ACCESS_ONCE(ref->pcpu_count); if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) { - __this_cpu_inc(*pcpu_count); + this_cpu_inc(*pcpu_count); ret = true; } @@ -164,7 +164,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref) pcpu_count = ACCESS_ONCE(ref->pcpu_count); if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) - __this_cpu_dec(*pcpu_count); + this_cpu_dec(*pcpu_count); else if (unlikely(atomic_dec_and_test(&ref->count))) ref->release(ref); diff --git a/include/linux/plist.h b/include/linux/plist.h index aa0fb390bd29..8b6c970cff6c 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -98,6 +98,13 @@ struct plist_node { } /** + * PLIST_HEAD - declare and init plist_head + * @head: name for struct plist_head variable + */ +#define PLIST_HEAD(head) \ + struct plist_head head = PLIST_HEAD_INIT(head) + +/** * PLIST_NODE_INIT - static struct plist_node initializer * @node: struct plist_node variable name * @__prio: initial node priority @@ -134,6 +141,8 @@ static inline void plist_node_init(struct plist_node *node, int prio) extern void plist_add(struct plist_node *node, struct plist_head *head); extern void plist_del(struct plist_node *node, struct plist_head *head); +extern void plist_requeue(struct plist_node *node, struct plist_head *head); + /** * plist_for_each - iterate over the plist * @pos: the type * to use as a loop counter @@ -143,6 +152,16 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, node_list) /** + * plist_for_each_continue - continue iteration over the plist + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * + * Continue to iterate over plist, continuing after the current position. + */ +#define plist_for_each_continue(pos, head) \ + list_for_each_entry_continue(pos, &(head)->node_list, node_list) + +/** * plist_for_each_safe - iterate safely over a plist of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -163,6 +182,18 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, mem.node_list) /** + * plist_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * @m: the name of the list_struct within the struct + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define plist_for_each_entry_continue(pos, head, m) \ + list_for_each_entry_continue(pos, &(head)->node_list, m.node_list) + +/** * plist_for_each_entry_safe - iterate safely over list of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -229,6 +260,20 @@ static inline int plist_node_empty(const struct plist_node *node) #endif /** + * plist_next - get the next entry in list + * @pos: the type * to cursor + */ +#define plist_next(pos) \ + list_next_entry(pos, node_list) + +/** + * plist_prev - get the prev entry in list + * @pos: the type * to cursor + */ +#define plist_prev(pos) \ + list_prev_entry(pos, node_list) + +/** * plist_first - return the first node (and thus, highest priority) * @head: the &struct plist_head pointer * diff --git a/include/linux/preempt.h b/include/linux/preempt.h index de83b4eb1642..1841b58cf173 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -15,6 +15,8 @@ */ #define PREEMPT_NEED_RESCHED 0x80000000 +#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) + #include <asm/preempt.h> #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER) diff --git a/include/linux/printk.h b/include/linux/printk.h index fa47e2708c01..cbf094f993f4 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -132,9 +132,9 @@ asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* - * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ -__printf(1, 2) __cold int printk_sched(const char *fmt, ...); +__printf(1, 2) __cold int printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -169,7 +169,7 @@ int printk(const char *s, ...) return 0; } static inline __printf(1, 2) __cold -int printk_sched(const char *s, ...) +int printk_deferred(const char *s, ...) { return 0; } diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 07d0df6bf768..cc79eff4a1ad 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -5,6 +5,7 @@ #include <linux/sched.h> /* For struct task_struct. */ #include <linux/err.h> /* for IS_ERR_VALUE */ #include <linux/bug.h> /* For BUG_ON. */ +#include <linux/pid_namespace.h> /* For task_active_pid_ns. */ #include <uapi/linux/ptrace.h> /* @@ -129,6 +130,37 @@ static inline void ptrace_event(int event, unsigned long message) } /** + * ptrace_event_pid - possibly stop for a ptrace event notification + * @event: %PTRACE_EVENT_* value to report + * @pid: process identifier for %PTRACE_GETEVENTMSG to return + * + * Check whether @event is enabled and, if so, report @event and @pid + * to the ptrace parent. @pid is reported as the pid_t seen from the + * the ptrace parent's pid namespace. + * + * Called without locks. + */ +static inline void ptrace_event_pid(int event, struct pid *pid) +{ + /* + * FIXME: There's a potential race if a ptracer in a different pid + * namespace than parent attaches between computing message below and + * when we acquire tasklist_lock in ptrace_stop(). If this happens, + * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG. + */ + unsigned long message = 0; + struct pid_namespace *ns; + + rcu_read_lock(); + ns = task_active_pid_ns(rcu_dereference(current->parent)); + if (ns) + message = pid_nr_ns(pid, ns); + rcu_read_unlock(); + + ptrace_event(event, message); +} + +/** * ptrace_init_task - initialize ptrace state for a new child * @child: new child task * @ptrace: true if child should be ptrace'd by parent's tracer @@ -302,6 +334,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, * calling arch_ptrace_stop() when it would be superfluous. For example, * if the thread has not been back to user mode since the last stop, the * thread state might indicate that nothing needs to be done. + * + * This is guaranteed to be invoked once before a task stops for ptrace and + * may include arch-specific operations necessary prior to a ptrace stop. */ #define arch_ptrace_stop_needed(code, info) (0) #endif diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index d69cf637a15a..49a4d6f59108 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) -void ring_buffer_wait(struct ring_buffer *buffer, int cpu); +int ring_buffer_wait(struct ring_buffer *buffer, int cpu); int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 8e3e66ac0a52..953937ea5233 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -4,6 +4,7 @@ #include <linux/mutex.h> #include <linux/netdevice.h> +#include <linux/wait.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -22,6 +23,10 @@ extern void rtnl_lock(void); extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); + +extern wait_queue_head_t netdev_unregistering_wq; +extern struct mutex net_mutex; + #ifdef CONFIG_PROVE_LOCKING extern int lockdep_rtnl_is_held(void); #else diff --git a/include/linux/sched.h b/include/linux/sched.h index a781dec1cd0b..218b058060f1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -59,6 +59,10 @@ struct sched_param { #define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ +#define VMACACHE_BITS 2 +#define VMACACHE_SIZE (1U << VMACACHE_BITS) +#define VMACACHE_MASK (VMACACHE_SIZE - 1) + /* * Extended scheduling parameters data structure. * @@ -1228,6 +1232,9 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif + /* per-thread vma caching */ + u32 vmacache_seqnum; + struct vm_area_struct *vmacache[VMACACHE_SIZE]; #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif @@ -1688,6 +1695,24 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk) } +static 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) { @@ -1727,7 +1752,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) * * Return: 1 if the process is alive. 0 otherwise. */ -static inline int pid_alive(struct task_struct *p) +static inline int pid_alive(const struct task_struct *p) { return p->pids[PIDTYPE_PID].pid != NULL; } @@ -1851,11 +1876,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */ +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags + * __GFP_FS is also cleared as it implies __GFP_IO. + */ static inline gfp_t memalloc_noio_flags(gfp_t flags) { if (unlikely(current->flags & PF_MEMALLOC_NOIO)) - flags &= ~__GFP_IO; + flags &= ~(__GFP_IO | __GFP_FS); return flags; } diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 535f158977b9..8cf350325dc6 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -164,8 +164,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) static inline unsigned raw_seqcount_begin(const seqcount_t *s) { unsigned ret = ACCESS_ONCE(s->sequence); - - seqcount_lockdep_reader_access(s); smp_rmb(); return ret & ~1; } diff --git a/include/linux/serio.h b/include/linux/serio.h index 36aac733840a..9f779c7a2da4 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -23,6 +23,7 @@ struct serio { char name[32]; char phys[32]; + char firmware_id[128]; bool manual_bind; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 15ede6a823a6..ad8f85908a56 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2458,6 +2458,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); +struct sk_buff *skb_vlan_untag(struct sk_buff *skb); struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 54f91d35e5fd..46cca4c06848 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -23,7 +23,7 @@ int sock_diag_check_cookie(void *sk, __u32 *cookie); void sock_diag_save_cookie(void *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); #endif diff --git a/include/linux/string.h b/include/linux/string.h index ac889c5ea11b..0ed878d0465c 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -129,7 +129,7 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, - const void *from, size_t available); + const void *from, size_t available); /** * strstarts - does @str start with @prefix? @@ -141,7 +141,8 @@ static inline bool strstarts(const char *str, const char *prefix) return strncmp(str, prefix, strlen(prefix)) == 0; } -extern size_t memweight(const void *ptr, size_t bytes); +size_t memweight(const void *ptr, size_t bytes); +void memzero_explicit(void *s, size_t count); /** * kbasename - return the last part of a pathname. diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index b05963f09ebf..f5bfb1a80abe 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -32,6 +32,7 @@ struct svc_xprt_class { struct svc_xprt_ops *xcl_ops; struct list_head xcl_list; u32 xcl_max_payload; + int xcl_ident; }; /* diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 62fd1b756e99..947009ed5996 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -56,6 +56,7 @@ int svc_recv(struct svc_rqst *, long); int svc_send(struct svc_rqst *); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); +bool svc_alien_sock(struct net *net, int fd); int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, const size_t len); void svc_init_xprt_sock(void); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 8097b9df6773..51009d280ac7 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -340,6 +340,7 @@ int xs_swapper(struct rpc_xprt *xprt, int enable); #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) +#define XPRT_CONNECTION_REUSE (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 46ba0c6c219f..789324976801 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,8 +214,9 @@ struct percpu_cluster { struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ + struct plist_node list; /* entry in swap_active_head */ + struct plist_node avail_list; /* entry in swap_avail_head */ signed char type; /* strange name for an index */ - signed char next; /* next type on the swap list */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ @@ -255,11 +256,6 @@ struct swap_info_struct { struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ }; -struct swap_list_t { - int head; /* head of priority-ordered swapfile list */ - int next; /* swapfile to be used next */ -}; - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e282624e8c10..388293a91e8c 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,7 +6,7 @@ * want to expose them to the dozens of source files that include swap.h */ extern spinlock_t swap_lock; -extern struct swap_list_t swap_list; +extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index fddbe2023a5d..a629e4b23217 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -118,8 +118,6 @@ static inline __deprecated void set_need_resched(void) */ } -#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) - #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK /* * An arch can define its own version of set_restore_sigmask() to get the diff --git a/include/linux/tpm.h b/include/linux/tpm.h index fff1d0976f80..8350c538b486 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -39,6 +39,9 @@ struct tpm_class_ops { int (*send) (struct tpm_chip *chip, u8 *buf, size_t len); void (*cancel) (struct tpm_chip *chip); u8 (*status) (struct tpm_chip *chip); + bool (*update_timeouts)(struct tpm_chip *chip, + unsigned long *timeout_cap); + }; #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) diff --git a/include/linux/tty.h b/include/linux/tty.h index 90b4fdc8a61f..b90b5c221ff0 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -208,7 +208,7 @@ struct tty_port { wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ unsigned char console:1, /* port is a console */ - low_latency:1; /* direct buffer flush */ + low_latency:1; /* optional: tune for latency */ struct mutex mutex; /* Locking */ struct mutex buf_mutex; /* Buffer alloc lock */ unsigned char *xmit_buf; /* Optional buffer */ diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 52f944dfe2fd..8b96ae2a38fe 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -30,4 +30,10 @@ descriptor */ #define USB_QUIRK_DELAY_INIT 0x00000040 +/* device generates spurious wakeup, ignore remote wakeup capability */ +#define USB_QUIRK_IGNORE_REMOTE_WAKEUP 0x00000200 + +/* device can't handle device_qualifier descriptor requests */ +#define USB_QUIRK_DEVICE_QUALIFIER 0x00000100 + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 502073a53dd3..b483abd34493 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -64,6 +64,7 @@ int vga_switcheroo_get_client_state(struct pci_dev *dev); void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic); int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain); +void vga_switcheroo_fini_domain_pm_ops(struct device *dev); int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain); #else @@ -82,6 +83,7 @@ static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {} static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } +static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {} static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } #endif diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h new file mode 100644 index 000000000000..c3fa0fd43949 --- /dev/null +++ b/include/linux/vmacache.h @@ -0,0 +1,38 @@ +#ifndef __LINUX_VMACACHE_H +#define __LINUX_VMACACHE_H + +#include <linux/sched.h> +#include <linux/mm.h> + +/* + * Hash based on the page number. Provides a good hit rate for + * workloads with good locality and those with random accesses as well. + */ +#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK) + +static inline void vmacache_flush(struct task_struct *tsk) +{ + memset(tsk->vmacache, 0, sizeof(tsk->vmacache)); +} + +extern void vmacache_flush_all(struct mm_struct *mm); +extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); +extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, + unsigned long addr); + +#ifndef CONFIG_MMU +extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end); +#endif + +static inline void vmacache_invalidate(struct mm_struct *mm) +{ + mm->vmacache_seqnum++; + + /* deal with overflows */ + if (unlikely(mm->vmacache_seqnum == 0)) + vmacache_flush_all(mm); +} + +#endif /* __LINUX_VMACACHE_H */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 704f4f652d0a..6c62cfa25f1a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -452,7 +452,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \ 1, (name)) #define create_singlethread_workqueue(name) \ - alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name)) + alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index bef53ce555d2..b10682cb138c 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -329,6 +329,9 @@ struct v4l2_fh; * @retry_start_streaming: start_streaming() was called, but there were not enough * buffers queued. If set, then retry calling start_streaming when * queuing a new buffer. + * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for + * buffers. Only set for capture queues if qbuf has not yet been + * called since poll() needs to return POLLERR in that situation. * @fileio: file io emulator internal data, used only if emulator is active */ struct vb2_queue { @@ -362,6 +365,7 @@ struct vb2_queue { unsigned int streaming:1; unsigned int retry_start_streaming:1; + unsigned int waiting_for_buffers:1; struct vb2_fileio_data *fileio; }; diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 7d64d3609ec9..428277869400 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -155,7 +155,11 @@ struct vsock_transport { /**** CORE ****/ -int vsock_core_init(const struct vsock_transport *t); +int __vsock_core_init(const struct vsock_transport *t, struct module *owner); +static inline int vsock_core_init(const struct vsock_transport *t) +{ + return __vsock_core_init(t, THIS_MODULE); +} void vsock_core_exit(void); /**** UTILS ****/ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b1f84b05c67e..37123eb1f093 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3637,6 +3637,18 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy); void cfg80211_sched_scan_stopped(struct wiphy *wiphy); /** + * cfg80211_sched_scan_stopped_rtnl - notify that the scheduled scan has stopped + * + * @wiphy: the wiphy on which the scheduled scan stopped + * + * The driver can call this function to inform cfg80211 that the + * scheduled scan had to be stopped, for whatever reason. The driver + * is then called back via the sched_scan_stop operation when done. + * This function should be called with rtnl locked. + */ +void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); + +/** * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame * * @wiphy: the wiphy reporting the BSS diff --git a/include/net/dst.h b/include/net/dst.h index 77eb53fabfb0..909032821c37 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -466,6 +466,7 @@ void dst_init(void); /* Flags for xfrm_lookup flags argument. */ enum { XFRM_LOOKUP_ICMP = 1 << 0, + XFRM_LOOKUP_QUEUE = 1 << 1, }; struct flowi; @@ -476,7 +477,16 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, int flags) { return dst_orig; -} +} + +static inline struct dst_entry *xfrm_lookup_route(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + struct sock *sk, + int flags) +{ + return dst_orig; +} static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { @@ -488,6 +498,10 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, struct sock *sk, int flags); +struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, struct sock *sk, + int flags); + /* skb attached with this dst needs transformation if dst->xfrm is valid */ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c55aeed41ace..cf9272807788 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -62,6 +62,7 @@ struct inet_connection_sock_af_ops { void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); int (*bind_conflict)(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); + void (*mtu_reduced)(struct sock *sk); }; /** inet_connection_sock - INET connection oriented sock diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 6efe73c79c52..823ec7bb9c67 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -41,14 +41,13 @@ struct inet_peer { struct rcu_head gc_rcu; }; /* - * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count + * Once inet_peer is queued for deletion (refcnt == -1), following field + * is not available: rid * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { atomic_t rid; /* Frag reception counter */ - atomic_t ip_id_count; /* IP ID for the next packet */ }; struct rcu_head rcu; struct inet_peer *gc_next; @@ -165,7 +164,7 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); void inetpeer_invalidate_tree(struct inet_peer_base *); /* - * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, + * temporary check to make sure we dont access rid, tcp_ts, * tcp_ts_stamp if no refcount is taken on inet_peer */ static inline void inet_peer_refcheck(const struct inet_peer *p) @@ -173,20 +172,4 @@ static inline void inet_peer_refcheck(const struct inet_peer *p) WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0); } - -/* can be called with or without local BH being disabled */ -static inline int inet_getid(struct inet_peer *p, int more) -{ - int old, new; - more++; - inet_peer_refcheck(p); - do { - old = atomic_read(&p->ip_id_count); - new = old + more; - if (!new) - new = 1; - } while (atomic_cmpxchg(&p->ip_id_count, old, new) != old); - return new; -} - #endif /* _NET_INETPEER_H */ diff --git a/include/net/ip.h b/include/net/ip.h index 23be0fd37937..937f19681426 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -297,9 +297,10 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) } } -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); +u32 ip_idents_reserve(u32 hash, int segs); +void __ip_select_ident(struct iphdr *iph, int segs); -static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk) +static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); @@ -309,24 +310,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s * does not change, they drop every other packet in * a TCP stream using header compression. */ - iph->id = (sk && inet_sk(sk)->inet_daddr) ? - htons(inet_sk(sk)->inet_id++) : 0; - } else - __ip_select_ident(iph, dst, 0); -} - -static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more) -{ - struct iphdr *iph = ip_hdr(skb); - - if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { if (sk && inet_sk(sk)->inet_daddr) { iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += 1 + more; - } else + inet_sk(sk)->inet_id += segs; + } else { iph->id = 0; - } else - __ip_select_ident(iph, dst, more); + } + } else { + __ip_select_ident(iph, segs); + } +} + +static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) +{ + ip_select_ident_segs(skb, sk, 1); } /* diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 017badb1aec7..2e74c6cfa612 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -32,6 +32,11 @@ struct route_info { #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 +/* We do not (yet ?) support IPv6 jumbograms (RFC 2675) + * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header + */ +#define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr)) + /* * rt6_srcprefs2flags() and rt6_flags2srcprefs() translate * between IPV6_ADDR_PREFERENCES socket option values diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index e77c10405d51..7b9ec5837496 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -40,6 +40,7 @@ struct ip_tunnel_prl_entry { struct ip_tunnel_dst { struct dst_entry __rcu *dst; + __be32 saddr; }; struct ip_tunnel { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4f541f11ce63..a60948d7bcea 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -660,7 +660,7 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt); +void ipv6_proxy_select_ident(struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 956b175523ff..55d15049ab2f 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -47,8 +47,8 @@ enum nf_ct_ext_id { /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { struct rcu_head rcu; - u8 offset[NF_CT_EXT_NUM]; - u8 len; + u16 offset[NF_CT_EXT_NUM]; + u16 len; char data[0]; }; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index cf2b7ae2b9d8..a75fc8e27cd6 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -13,6 +13,16 @@ struct nft_cmp_fast_expr { u8 len; }; +/* Calculate the mask for the nft_cmp_fast expression. On big endian the + * mask needs to include the *upper* bytes when interpreting that data as + * something smaller than the full u32, therefore a cpu_to_le32 is done. + */ +static inline u32 nft_cmp_fast_mask(unsigned int len) +{ + return cpu_to_le32(~0U >> (FIELD_SIZEOF(struct nft_cmp_fast_expr, + data) * BITS_PER_BYTE - len)); +} + extern const struct nft_expr_ops nft_cmp_fast_ops; int nft_cmp_module_init(void); diff --git a/include/net/regulatory.h b/include/net/regulatory.h index b07cdc9fa454..f103f30122a1 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -160,7 +160,7 @@ struct ieee80211_reg_rule { struct ieee80211_regdomain { struct rcu_head rcu_head; u32 n_reg_rules; - char alpha2[2]; + char alpha2[3]; enum nl80211_dfs_regions dfs_region; struct ieee80211_reg_rule reg_rules[]; }; diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 4b7cd695e431..cfcbc3f627bd 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -115,7 +115,7 @@ typedef enum { * analysis of the state functions, but in reality just taken from * thin air in the hopes othat we don't trigger a kernel panic. */ -#define SCTP_MAX_NUM_COMMANDS 14 +#define SCTP_MAX_NUM_COMMANDS 20 typedef union { __s32 i32; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6ee76c804893..0dfcc92600e8 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1241,6 +1241,7 @@ struct sctp_endpoint { /* SCTP-AUTH: endpoint shared keys */ struct list_head endpoint_shared_keys; __u16 active_key_id; + __u8 auth_enable; }; /* Recover the outter endpoint structure. */ @@ -1269,7 +1270,8 @@ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *, int sctp_has_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr); -int sctp_verify_init(struct net *net, const struct sctp_association *asoc, +int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, sctp_cid_t, sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **err_chunk); int sctp_process_init(struct sctp_association *, struct sctp_chunk *chunk, @@ -1653,6 +1655,17 @@ struct sctp_association { /* This is the last advertised value of rwnd over a SACK chunk. */ __u32 a_rwnd; + /* Number of bytes by which the rwnd has slopped. The rwnd is allowed + * to slop over a maximum of the association's frag_point. + */ + __u32 rwnd_over; + + /* Keeps treack of rwnd pressure. This happens when we have + * a window, but not recevie buffer (i.e small packets). This one + * is releases slowly (1 PMTU at a time ). + */ + __u32 rwnd_press; + /* This is the sndbuf size in use for the association. * This corresponds to the sndbuf size for the association, * as specified in the sk->sndbuf. @@ -1881,7 +1894,8 @@ void sctp_assoc_update(struct sctp_association *old, __u32 sctp_association_get_next_tsn(struct sctp_association *); void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *); -void sctp_assoc_rwnd_update(struct sctp_association *, bool); +void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); +void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); void sctp_assoc_set_primary(struct sctp_association *, struct sctp_transport *); void sctp_assoc_del_nonprimary_peers(struct sctp_association *, diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index f257486f17be..3f36d45b714a 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -3,8 +3,6 @@ #include <linux/types.h> -__u32 secure_ip_id(__be32 daddr); -__u32 secure_ipv6_id(const __be32 daddr[4]); u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); diff --git a/include/net/sock.h b/include/net/sock.h index b9586a137cad..f66b2b19a6e4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -969,7 +969,6 @@ struct proto { struct sk_buff *skb); void (*release_cb)(struct sock *sk); - void (*mtu_reduced)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); @@ -1755,8 +1754,8 @@ sk_dst_get(struct sock *sk) rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); - if (dst) - dst_hold(dst); + if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + dst = NULL; rcu_read_unlock(); return dst; } @@ -1793,9 +1792,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { - spin_lock(&sk->sk_dst_lock); - __sk_dst_set(sk, dst); - spin_unlock(&sk->sk_dst_lock); + struct dst_entry *old_dst; + + sk_tx_queue_clear(sk); + old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); + dst_release(old_dst); } static inline void @@ -1807,9 +1808,7 @@ __sk_dst_reset(struct sock *sk) static inline void sk_dst_reset(struct sock *sk) { - spin_lock(&sk->sk_dst_lock); - __sk_dst_reset(sk); - spin_unlock(&sk->sk_dst_lock); + sk_dst_set(sk, NULL); } struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); @@ -2278,6 +2277,11 @@ int sock_get_timestampns(struct sock *, struct timespec __user *); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap); +bool sk_capable(const struct sock *sk, int cap); +bool sk_net_capable(const struct sock *sk, int cap); + /* * Enable debug/info messages */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 743accec6c76..1f0d8479e15f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -453,6 +453,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); +void tcp_v4_mtu_reduced(struct sock *sk); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, @@ -720,8 +721,10 @@ struct tcp_skb_cb { #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ +#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ -#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS) +#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ + TCPCB_REPAIRED) __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ /* 1 byte hole */ diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h index f29e3a27c2cc..0e3ff30647d5 100644 --- a/include/rdma/ib_cm.h +++ b/include/rdma/ib_cm.h @@ -601,5 +601,4 @@ struct ib_cm_sidr_rep_param { int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id, struct ib_cm_sidr_rep_param *param); -int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac); #endif /* IB_CM_H */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index d65fbec2533d..409fafb63f63 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -149,6 +149,7 @@ struct scsi_device { unsigned skip_ms_page_8:1; /* do not use MODE SENSE page 0x08 */ unsigned skip_ms_page_3f:1; /* do not use MODE SENSE page 0x3f */ unsigned skip_vpd_pages:1; /* do not read VPD pages */ + unsigned try_vpd_pages:1; /* attempt to read VPD pages */ unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */ unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ @@ -257,7 +258,7 @@ struct scsi_target { struct list_head siblings; struct list_head devices; struct device dev; - unsigned int reap_ref; /* protected by the host lock */ + struct kref reap_ref; /* last put renders target invisible */ unsigned int channel; unsigned int id; /* target id ... replace * scsi_device.id eventually */ @@ -284,7 +285,6 @@ struct scsi_target { #define SCSI_DEFAULT_TARGET_BLOCKED 3 char scsi_level; - struct execute_work ew; enum scsi_target_state state; void *hostdata; /* available to low-level driver */ unsigned long starget_data[0]; /* for the transport */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 447d2d7466fc..183eaab7c380 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -32,4 +32,9 @@ #define BLIST_ATTACH_PQ3 0x1000000 /* Scan: Attach to PQ3 devices */ #define BLIST_NO_DIF 0x2000000 /* Disable T10 PI (DIF) */ #define BLIST_SKIP_VPD_PAGES 0x4000000 /* Ignore SBC-3 VPD pages */ +#define BLIST_SCSI3LUN 0x8000000 /* Scan more than 256 LUNs + for sequential scan */ +#define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */ +#define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */ + #endif diff --git a/include/sound/core.h b/include/sound/core.h index 2a14f1f02d4f..d6bc9616058b 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -121,6 +121,8 @@ struct snd_card { int user_ctl_count; /* count of all user controls */ struct list_head controls; /* all controls for this card */ struct list_head ctl_files; /* active control files */ + struct mutex user_ctl_lock; /* protects user controls against + concurrent access */ struct snd_info_entry *proc_root; /* root for soundcard specific files */ struct snd_info_entry *proc_id; /* the card id */ diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 4483fadfa68d..d1fb912740f3 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -68,7 +68,8 @@ extern void iscsit_build_nopin_rsp(struct iscsi_cmd *, struct iscsi_conn *, extern void iscsit_build_task_mgt_rsp(struct iscsi_cmd *, struct iscsi_conn *, struct iscsi_tm_rsp *); extern int iscsit_build_text_rsp(struct iscsi_cmd *, struct iscsi_conn *, - struct iscsi_text_rsp *); + struct iscsi_text_rsp *, + enum iscsit_transport_type); extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *, struct iscsi_reject *); extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *, diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 7020e33e742e..f5915b39386a 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -59,6 +59,7 @@ int transport_subsystem_register(struct se_subsystem_api *); void transport_subsystem_release(struct se_subsystem_api *); void target_complete_cmd(struct se_cmd *, u8); +void target_complete_cmd_with_length(struct se_cmd *, u8, int); sense_reason_t spc_parse_cdb(struct se_cmd *cmd, unsigned int *size); sense_reason_t spc_emulate_report_luns(struct se_cmd *cmd); diff --git a/include/trace/events/block.h b/include/trace/events/block.h index e76ae19a8d6f..e8a5eca1dbe5 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -132,6 +132,7 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue, * block_rq_complete - block IO operation completed by device driver * @q: queue containing the block operation request * @rq: block operations request + * @nr_bytes: number of completed bytes * * The block_rq_complete tracepoint event indicates that some portion * of operation request has been completed by the device driver. If @@ -139,11 +140,37 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue, * do for the request. If @rq->bio is non-NULL then there is * additional work required to complete the request. */ -DEFINE_EVENT(block_rq_with_error, block_rq_complete, +TRACE_EVENT(block_rq_complete, - TP_PROTO(struct request_queue *q, struct request *rq), + TP_PROTO(struct request_queue *q, struct request *rq, + unsigned int nr_bytes), - TP_ARGS(q, rq) + TP_ARGS(q, rq, nr_bytes), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( unsigned int, nr_sector ) + __field( int, errors ) + __array( char, rwbs, RWBS_LEN ) + __dynamic_array( char, cmd, blk_cmd_buf_len(rq) ) + ), + + TP_fast_assign( + __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; + __entry->sector = blk_rq_pos(rq); + __entry->nr_sector = nr_bytes >> 9; + __entry->errors = rq->errors; + + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes); + blk_dump_cmd(__get_str(cmd), rq); + ), + + TP_printk("%d,%d %s (%s) %llu + %u [%d]", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rwbs, __get_str(cmd), + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->errors) ); DECLARE_EVENT_CLASS(block_rq, diff --git a/include/trace/events/module.h b/include/trace/events/module.h index 161932737416..ca298c7157ae 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -78,7 +78,7 @@ DECLARE_EVENT_CLASS(module_refcnt, TP_fast_assign( __entry->ip = ip; - __entry->refcnt = __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs); + __entry->refcnt = __this_cpu_read(mod->refptr->incs) - __this_cpu_read(mod->refptr->decs); __assign_str(name, mod->name); ), diff --git a/include/trace/syscall.h b/include/trace/syscall.h index fed853f3d7aa..9674145e2f6a 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -4,6 +4,7 @@ #include <linux/tracepoint.h> #include <linux/unistd.h> #include <linux/ftrace_event.h> +#include <linux/thread_info.h> #include <asm/ptrace.h> @@ -32,4 +33,18 @@ struct syscall_metadata { struct ftrace_event_call *exit_event; }; +#if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS) +static inline void syscall_tracepoint_update(struct task_struct *p) +{ + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT); + else + clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT); +} +#else +static inline void syscall_tracepoint_update(struct task_struct *p) +{ +} +#endif + #endif /* _TRACE_SYSCALL_H */ diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h index 5e1ab552cbed..c28de1afd684 100644 --- a/include/uapi/drm/tegra_drm.h +++ b/include/uapi/drm/tegra_drm.h @@ -114,7 +114,6 @@ struct drm_tegra_submit { __u32 num_waitchks; __u32 waitchk_mask; __u32 timeout; - __u32 pad; __u64 syncpts; __u64 cmdbufs; __u64 relocs; diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 87792a5fee3b..33b739522840 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -29,7 +29,7 @@ #define __VMWGFX_DRM_H__ #ifndef __KERNEL__ -#include <drm.h> +#include <drm/drm.h> #endif #define DRM_VMW_MAX_SURFACE_FACES 6 diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index bd24470d24a2..f4849525519c 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -164,6 +164,7 @@ struct input_keymap_entry { #define INPUT_PROP_DIRECT 0x01 /* direct input devices */ #define INPUT_PROP_BUTTONPAD 0x02 /* has button(s) under pad */ #define INPUT_PROP_SEMI_MT 0x03 /* touch rectangle only */ +#define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ #define INPUT_PROP_MAX 0x1f #define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index 335e8a7cad39..c140620dad92 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -85,6 +85,12 @@ #endif /* _NETINET_IN_H */ +/* Definitions for xattr.h */ +#if defined(_SYS_XATTR_H) +#define __UAPI_DEF_XATTR 0 +#else +#define __UAPI_DEF_XATTR 1 +#endif /* If we did not see any headers from any supported C libraries, * or we are being included in the kernel, then define everything @@ -98,6 +104,9 @@ #define __UAPI_DEF_IPV6_MREQ 1 #define __UAPI_DEF_IPPROTO_V6 1 +/* Definitions for xattr.h */ +#define __UAPI_DEF_XATTR 1 + #endif /* __GLIBC__ */ #endif /* _UAPI_LIBC_COMPAT_H */ diff --git a/include/uapi/linux/usb/Kbuild b/include/uapi/linux/usb/Kbuild index 6cb4ea826834..4cc4d6e7e523 100644 --- a/include/uapi/linux/usb/Kbuild +++ b/include/uapi/linux/usb/Kbuild @@ -1,6 +1,7 @@ # UAPI Header export list header-y += audio.h header-y += cdc.h +header-y += cdc-wdm.h header-y += ch11.h header-y += ch9.h header-y += functionfs.h diff --git a/include/uapi/linux/usb/cdc-wdm.h b/include/uapi/linux/usb/cdc-wdm.h index f03134feebd6..0dc132e75030 100644 --- a/include/uapi/linux/usb/cdc-wdm.h +++ b/include/uapi/linux/usb/cdc-wdm.h @@ -9,6 +9,8 @@ #ifndef _UAPI__LINUX_USB_CDC_WDM_H #define _UAPI__LINUX_USB_CDC_WDM_H +#include <linux/types.h> + /* * This IOCTL is used to retrieve the wMaxCommand for the device, * defining the message limit for both reading and writing. diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index d6b01283f85c..f279394aafb0 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -32,12 +32,13 @@ struct usb_endpoint_descriptor_no_audio { * All numbers must be in little endian order. */ +/* Legacy format, deprecated as of 3.14. */ struct usb_functionfs_descs_head { __le32 magic; __le32 length; __le32 fs_count; __le32 hs_count; -} __attribute__((packed)); +} __attribute__((packed, deprecated)); /* * Descriptors format: diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 6ae7bbe988cc..fe94bb90582e 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1059,14 +1059,14 @@ struct v4l2_bt_timings { /* A few useful defines to calculate the total blanking and frame sizes */ #define V4L2_DV_BT_BLANKING_WIDTH(bt) \ - (bt->hfrontporch + bt->hsync + bt->hbackporch) + ((bt)->hfrontporch + (bt)->hsync + (bt)->hbackporch) #define V4L2_DV_BT_FRAME_WIDTH(bt) \ - (bt->width + V4L2_DV_BT_BLANKING_WIDTH(bt)) + ((bt)->width + V4L2_DV_BT_BLANKING_WIDTH(bt)) #define V4L2_DV_BT_BLANKING_HEIGHT(bt) \ - (bt->vfrontporch + bt->vsync + bt->vbackporch + \ - bt->il_vfrontporch + bt->il_vsync + bt->il_vbackporch) + ((bt)->vfrontporch + (bt)->vsync + (bt)->vbackporch + \ + (bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) #define V4L2_DV_BT_FRAME_HEIGHT(bt) \ - (bt->height + V4L2_DV_BT_BLANKING_HEIGHT(bt)) + ((bt)->height + V4L2_DV_BT_BLANKING_HEIGHT(bt)) /** struct v4l2_dv_timings - DV timings * @type: the type of the timings diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index 40bbc04b6f81..1590c49cae57 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -7,11 +7,18 @@ Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ + +#include <linux/libc-compat.h> + #ifndef _UAPI_LINUX_XATTR_H #define _UAPI_LINUX_XATTR_H +#if __UAPI_DEF_XATTR +#define __USE_KERNEL_XATTR_DEFS + #define XATTR_CREATE 0x1 /* set value, fail if attr already exists */ #define XATTR_REPLACE 0x2 /* set value, fail if attr does not exist */ +#endif /* Namespaces */ #define XATTR_OS2_PREFIX "os2." diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h index 99b80abf360a..3066718eb120 100644 --- a/include/uapi/rdma/rdma_user_cm.h +++ b/include/uapi/rdma/rdma_user_cm.h @@ -34,6 +34,7 @@ #define RDMA_USER_CM_H #include <linux/types.h> +#include <linux/socket.h> #include <linux/in6.h> #include <rdma/ib_user_verbs.h> #include <rdma/ib_user_sa.h> diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h index 5759810e1c1b..21eed488783f 100644 --- a/include/uapi/sound/compress_offload.h +++ b/include/uapi/sound/compress_offload.h @@ -80,7 +80,7 @@ struct snd_compr_tstamp { struct snd_compr_avail { __u64 avail; struct snd_compr_tstamp tstamp; -}; +} __attribute__((packed)); enum snd_compr_direction { SND_COMPRESS_PLAYBACK = 0, diff --git a/init/Kconfig b/init/Kconfig index 009a797dd242..8b9521a2d2c1 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1387,6 +1387,14 @@ config FUTEX support for "fast userspace mutexes". The resulting kernel may not run glibc-based applications correctly. +config HAVE_FUTEX_CMPXCHG + bool + depends on FUTEX + help + Architectures should select this if futex_atomic_cmpxchg_inatomic() + is implemented and always working. This removes a couple of runtime + checks. + config EPOLL bool "Enable eventpoll support" if EXPERT default y @@ -1614,6 +1622,18 @@ config MMAP_ALLOW_UNINITIALIZED See Documentation/nommu-mmap.txt for more information. +config SYSTEM_TRUSTED_KEYRING + bool "Provide system-wide ring of trusted keys" + depends on KEYS + help + Provide a system keyring to which trusted keys can be added. Keys in + the keyring are considered to be trusted. Keys may be added at will + by the kernel from compiled-in data and from hardware key stores, but + userspace may only add extra keys if those keys can be verified by + keys already in the keyring. + + Keys in this keyring are used by module signature checking. + config PROFILING bool "Profiling support" help @@ -1649,18 +1669,6 @@ config BASE_SMALL default 0 if BASE_FULL default 1 if !BASE_FULL -config SYSTEM_TRUSTED_KEYRING - bool "Provide system-wide ring of trusted keys" - depends on KEYS - help - Provide a system keyring to which trusted keys can be added. Keys in - the keyring are considered to be trusted. Keys may be added at will - by the kernel from compiled-in data and from hardware key stores, but - userspace may only add extra keys if those keys can be verified by - keys already in the keyring. - - Keys in this keyring are used by module signature checking. - menuconfig MODULES bool "Enable loadable module support" option modules diff --git a/init/main.c b/init/main.c index 9c7fd4c9249f..58c132d7de4b 100644 --- a/init/main.c +++ b/init/main.c @@ -617,6 +617,10 @@ asmlinkage void __init start_kernel(void) if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); #endif +#ifdef CONFIG_X86_ESPFIX64 + /* Should be run before the first non-init thread is created */ + init_espfix_bsp(); +#endif thread_info_cache_init(); cred_init(); fork_init(totalram_pages); diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index d2b32ac27a39..ecee67a00f5f 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -220,6 +220,9 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE endif +config ARCH_SUPPORTS_ATOMIC_RMW + bool + config MUTEX_SPIN_ON_OWNER def_bool y - depends on SMP && !DEBUG_MUTEXES + depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW diff --git a/kernel/audit.c b/kernel/audit.c index 95a20f3f52f1..2c0ecd1753de 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -639,13 +639,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: - if (!capable(CAP_AUDIT_CONTROL)) + if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: - if (!capable(CAP_AUDIT_WRITE)) + if (!netlink_capable(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ @@ -1628,7 +1628,7 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) audit_log_format(ab, " %s=", prefix); CAP_FOR_EACH_U32(i) { audit_log_format(ab, "%08x", - cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]); + cap->cap[CAP_LAST_U32 - i]); } } @@ -1829,10 +1829,10 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) spin_unlock_irq(&tsk->sighand->siglock); audit_log_format(ab, - " ppid=%ld pid=%d auid=%u uid=%u gid=%u" + " ppid=%d pid=%d auid=%u uid=%u gid=%u" " euid=%u suid=%u fsuid=%u" " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", - sys_getppid(), + task_ppid_nr(tsk), tsk->pid, from_kuid(&init_user_ns, audit_get_loginuid(tsk)), from_kuid(&init_user_ns, cred->uid), diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 7aef2f4b6c64..619b58d3fcdf 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -459,7 +459,7 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_PPID: if (ctx) { if (!ctx->ppid) - ctx->ppid = sys_getppid(); + ctx->ppid = task_ppid_nr(tsk); result = audit_comparator(ctx->ppid, f->op, f->val); } break; @@ -720,6 +720,22 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key) return AUDIT_BUILD_CONTEXT; } +static int audit_in_mask(const struct audit_krule *rule, unsigned long val) +{ + int word, bit; + + if (val > 0xffffffff) + return false; + + word = AUDIT_WORD(val); + if (word >= AUDIT_BITMASK_SIZE) + return false; + + bit = AUDIT_BIT(val); + + return rule->mask[word] & bit; +} + /* At syscall entry and exit time, this filter is called if the * audit_state is not low enough that auditing cannot take place, but is * also not high enough that we already know we have to write an audit @@ -737,11 +753,8 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, rcu_read_lock(); if (!list_empty(list)) { - int word = AUDIT_WORD(ctx->major); - int bit = AUDIT_BIT(ctx->major); - list_for_each_entry_rcu(e, list, list) { - if ((e->rule.mask[word] & bit) == bit && + if (audit_in_mask(&e->rule, ctx->major) && audit_filter_rules(tsk, &e->rule, ctx, NULL, &state, false)) { rcu_read_unlock(); @@ -761,20 +774,16 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, static int audit_filter_inode_name(struct task_struct *tsk, struct audit_names *n, struct audit_context *ctx) { - int word, bit; int h = audit_hash_ino((u32)n->ino); struct list_head *list = &audit_inode_hash[h]; struct audit_entry *e; enum audit_state state; - word = AUDIT_WORD(ctx->major); - bit = AUDIT_BIT(ctx->major); - if (list_empty(list)) return 0; list_for_each_entry_rcu(e, list, list) { - if ((e->rule.mask[word] & bit) == bit && + if (audit_in_mask(&e->rule, ctx->major) && audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) { ctx->current_state = state; return 1; @@ -1982,7 +1991,7 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, if (!ab) return; audit_log_format(ab, "pid=%d uid=%u" - " old-auid=%u new-auid=%u old-ses=%u new-ses=%u" + " old-auid=%u auid=%u old-ses=%u ses=%u" " res=%d", current->pid, uid, oldloginuid, loginuid, oldsessionid, sessionid, diff --git a/kernel/capability.c b/kernel/capability.c index 34019c57888d..00adb2193d01 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -268,6 +268,10 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) i++; } + effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + new = prepare_creds(); if (!new) return -ENOMEM; @@ -433,23 +437,19 @@ bool capable(int cap) EXPORT_SYMBOL(capable); /** - * inode_capable - Check superior capability over inode + * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @inode: The inode in question * @cap: The capability in question * - * Return true if the current task has the given superior capability - * targeted at it's own user namespace and that the given inode is owned - * by the current user namespace or a child namespace. - * - * Currently we check to see if an inode is owned by the current - * user namespace by seeing if the inode's owner maps into the - * current user namespace. - * + * Return true if the current task has the given capability targeted at + * its own user namespace and that the given inode's uid and gid are + * mapped into the current user namespace. */ -bool inode_capable(const struct inode *inode, int cap) +bool capable_wrt_inode_uidgid(const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); - return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid); + return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) && + kgid_has_mapping(ns, inode->i_gid); } -EXPORT_SYMBOL(inode_capable); +EXPORT_SYMBOL(capable_wrt_inode_uidgid); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0c753ddd223b..550e2050d778 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3663,7 +3663,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, l = cgroup_pidlist_find_create(cgrp, type); if (!l) { - mutex_unlock(&cgrp->pidlist_mutex); pidlist_free(array); return -ENOMEM; } diff --git a/kernel/cpu.c b/kernel/cpu.c index deff2e693766..9a1ba77d6a50 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -692,10 +692,12 @@ void set_cpu_present(unsigned int cpu, bool present) void set_cpu_online(unsigned int cpu, bool online) { - if (online) + if (online) { cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits)); - else + cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits)); + } else { cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits)); + } } void set_cpu_active(unsigned int cpu, bool active) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index e6b1b66afe52..15b3ea693225 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1022,7 +1022,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, task_lock(tsk); /* * Determine if a loop is necessary if another thread is doing - * get_mems_allowed(). If at least one node remains unchanged and + * read_mems_allowed_begin(). If at least one node remains unchanged and * tsk does not have a mempolicy, then an empty nodemask will not be * possible when mems_allowed is larger than a word. */ @@ -1236,7 +1236,13 @@ done: int current_cpuset_is_being_rebound(void) { - return task_cs(current) == cpuset_being_rebound; + int ret; + + rcu_read_lock(); + ret = task_cs(current) == cpuset_being_rebound; + rcu_read_unlock(); + + return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 334b3980ffc1..8865caec45fb 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -49,6 +49,7 @@ #include <linux/pid.h> #include <linux/smp.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/rcupdate.h> #include <asm/cacheflush.h> @@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) if (!CACHE_FLUSH_IS_SAFE) return; - if (current->mm && current->mm->mmap_cache) { - flush_cache_range(current->mm->mmap_cache, - addr, addr + BREAK_INSTR_SIZE); + if (current->mm) { + int i; + + for (i = 0; i < VMACACHE_SIZE; i++) { + if (!current->vmacache[i]) + continue; + flush_cache_range(current->vmacache[i], + addr, addr + BREAK_INSTR_SIZE); + } } + /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } diff --git a/kernel/events/core.c b/kernel/events/core.c index fa0b2d4ad83c..4ced342f1ba9 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1439,6 +1439,11 @@ group_sched_out(struct perf_event *group_event, cpuctx->exclusive = 0; } +struct remove_event { + struct perf_event *event; + bool detach_group; +}; + /* * Cross CPU call to remove a performance event * @@ -1447,12 +1452,15 @@ group_sched_out(struct perf_event *group_event, */ static int __perf_remove_from_context(void *info) { - struct perf_event *event = info; + struct remove_event *re = info; + struct perf_event *event = re->event; struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); raw_spin_lock(&ctx->lock); event_sched_out(event, cpuctx, ctx); + if (re->detach_group) + perf_group_detach(event); list_del_event(event, ctx); if (!ctx->nr_events && cpuctx->task_ctx == ctx) { ctx->is_active = 0; @@ -1477,10 +1485,14 @@ static int __perf_remove_from_context(void *info) * When called from perf_event_exit_task, it's OK because the * context has been detached from its task. */ -static void perf_remove_from_context(struct perf_event *event) +static void perf_remove_from_context(struct perf_event *event, bool detach_group) { struct perf_event_context *ctx = event->ctx; struct task_struct *task = ctx->task; + struct remove_event re = { + .event = event, + .detach_group = detach_group, + }; lockdep_assert_held(&ctx->mutex); @@ -1489,12 +1501,12 @@ static void perf_remove_from_context(struct perf_event *event) * Per cpu events are removed via an smp call and * the removal is always successful. */ - cpu_function_call(event->cpu, __perf_remove_from_context, event); + cpu_function_call(event->cpu, __perf_remove_from_context, &re); return; } retry: - if (!task_function_call(task, __perf_remove_from_context, event)) + if (!task_function_call(task, __perf_remove_from_context, &re)) return; raw_spin_lock_irq(&ctx->lock); @@ -1504,6 +1516,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -1511,6 +1528,8 @@ retry: * Since the task isn't running, its safe to remove the event, us * holding the ctx->lock ensures the task won't get scheduled in. */ + if (detach_group) + perf_group_detach(event); list_del_event(event, ctx); raw_spin_unlock_irq(&ctx->lock); } @@ -1943,6 +1962,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -2297,7 +2321,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, next_parent = rcu_dereference(next_ctx->parent_ctx); /* If neither context have a parent context; they cannot be clones. */ - if (!parent && !next_parent) + if (!parent || !next_parent) goto unlock; if (next_parent == ctx || next_ctx == parent || next_parent == parent) { @@ -3279,10 +3303,7 @@ int perf_event_release_kernel(struct perf_event *event) * to trigger the AB-BA case. */ mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING); - raw_spin_lock_irq(&ctx->lock); - perf_group_detach(event); - raw_spin_unlock_irq(&ctx->lock); - perf_remove_from_context(event); + perf_remove_from_context(event, true); mutex_unlock(&ctx->mutex); free_event(event); @@ -5406,6 +5427,9 @@ struct swevent_htable { /* Recursion avoidance in each contexts */ int recursion[PERF_NR_CONTEXTS]; + + /* Keeps track of cpu being initialized/exited */ + bool online; }; static DEFINE_PER_CPU(struct swevent_htable, swevent_htable); @@ -5652,8 +5676,14 @@ static int perf_swevent_add(struct perf_event *event, int flags) hwc->state = !(flags & PERF_EF_START); head = find_swevent_head(swhash, event); - if (WARN_ON_ONCE(!head)) + if (!head) { + /* + * We can race with cpu hotplug code. Do not + * WARN if the cpu just got unplugged. + */ + WARN_ON_ONCE(swhash->online); return -EINVAL; + } hlist_add_head_rcu(&event->hlist_entry, head); @@ -7016,6 +7046,9 @@ SYSCALL_DEFINE5(perf_event_open, if (attr.freq) { if (attr.sample_freq > sysctl_perf_event_sample_rate) return -EINVAL; + } else { + if (attr.sample_period & (1ULL << 63)) + return -EINVAL; } /* @@ -7163,7 +7196,7 @@ SYSCALL_DEFINE5(perf_event_open, struct perf_event_context *gctx = group_leader->ctx; mutex_lock(&gctx->mutex); - perf_remove_from_context(group_leader); + perf_remove_from_context(group_leader, false); /* * Removing from the context ends up with disabled @@ -7173,7 +7206,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_event__state_init(group_leader); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_remove_from_context(sibling); + perf_remove_from_context(sibling, false); perf_event__state_init(sibling); put_ctx(gctx); } @@ -7303,7 +7336,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) mutex_lock(&src_ctx->mutex); list_for_each_entry_safe(event, tmp, &src_ctx->event_list, event_entry) { - perf_remove_from_context(event); + perf_remove_from_context(event, false); unaccount_event_cpu(event, src_cpu); put_ctx(src_ctx); list_add(&event->migrate_entry, &events); @@ -7365,13 +7398,7 @@ __perf_event_exit_task(struct perf_event *child_event, struct perf_event_context *child_ctx, struct task_struct *child) { - if (child_event->parent) { - raw_spin_lock_irq(&child_ctx->lock); - perf_group_detach(child_event); - raw_spin_unlock_irq(&child_ctx->lock); - } - - perf_remove_from_context(child_event); + perf_remove_from_context(child_event, !!child_event->parent); /* * It can happen that the parent exits first, and has events @@ -7809,8 +7836,10 @@ int perf_event_init_task(struct task_struct *child) for_each_task_context_nr(ctxn) { ret = perf_event_init_context(child, ctxn); - if (ret) + if (ret) { + perf_event_free_task(child); return ret; + } } return 0; @@ -7833,6 +7862,7 @@ static void perf_event_init_cpu(int cpu) struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); mutex_lock(&swhash->hlist_mutex); + swhash->online = true; if (swhash->hlist_refcount > 0) { struct swevent_hlist *hlist; @@ -7855,14 +7885,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu) static void __perf_event_exit_context(void *__info) { + struct remove_event re = { .detach_group = false }; struct perf_event_context *ctx = __info; - struct perf_event *event; perf_pmu_rotate_stop(ctx->pmu); rcu_read_lock(); - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) - __perf_remove_from_context(event); + list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry) + __perf_remove_from_context(&re); rcu_read_unlock(); } @@ -7890,6 +7920,7 @@ static void perf_event_exit_cpu(int cpu) perf_event_exit_cpu_context(cpu); mutex_lock(&swhash->hlist_mutex); + swhash->online = false; swevent_hlist_release(swhash); mutex_unlock(&swhash->hlist_mutex); } diff --git a/kernel/exit.c b/kernel/exit.c index 1e77fc645317..81b3d6789ee8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -560,9 +560,6 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p, struct list_head *dead) { list_move_tail(&p->sibling, &p->real_parent->children); - - if (p->exit_state == EXIT_DEAD) - return; /* * If this is a threaded reparent there is no need to * notify anyone anything has happened. @@ -570,9 +567,19 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p, if (same_thread_group(p->real_parent, father)) return; - /* We don't want people slaying init. */ + /* + * We don't want people slaying init. + * + * Note: we do this even if it is EXIT_DEAD, wait_task_zombie() + * can change ->exit_state to EXIT_ZOMBIE. If this is the final + * state, do_notify_parent() was already called and ->exit_signal + * doesn't matter. + */ p->exit_signal = SIGCHLD; + if (p->exit_state == EXIT_DEAD) + return; + /* If it has exited notify the new parent about this child's death. */ if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { @@ -784,6 +791,8 @@ void do_exit(long code) exit_shm(tsk); exit_files(tsk); exit_fs(tsk); + if (group_dead) + disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); check_stack_usage(); @@ -799,13 +808,9 @@ void do_exit(long code) cgroup_exit(tsk, 1); - if (group_dead) - disassociate_ctty(1); - module_put(task_thread_info(tsk)->exec_domain->module); proc_exit_connector(tsk); - /* * FIXME: do that only when needed, using sched_exit tracepoint */ diff --git a/kernel/fork.c b/kernel/fork.c index a17621c6cd42..e2c685396295 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -28,6 +28,8 @@ #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> +#include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> @@ -363,7 +365,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; - mm->mmap_cache = NULL; + mm->vmacache_seqnum = 0; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -876,6 +878,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (!oldmm) return 0; + /* initialize the new vmacache entries */ + vmacache_flush(tsk); + if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; @@ -1323,7 +1328,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) - goto bad_fork_cleanup_policy; + goto bad_fork_cleanup_perf; /* copy all the process information */ retval = copy_semundo(clone_flags, p); if (retval) @@ -1484,7 +1489,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, total_forks++; spin_unlock(¤t->sighand->siglock); + syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); + proc_fork_connector(p); cgroup_post_fork(p); if (clone_flags & CLONE_THREAD) @@ -1520,8 +1527,9 @@ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); -bad_fork_cleanup_policy: +bad_fork_cleanup_perf: perf_event_free_task(p); +bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_cgroup: @@ -1604,10 +1612,12 @@ long do_fork(unsigned long clone_flags, */ if (!IS_ERR(p)) { struct completion vfork; + struct pid *pid; trace_sched_process_fork(current, p); - nr = task_pid_vnr(p); + pid = get_task_pid(p, PIDTYPE_PID); + nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, parent_tidptr); @@ -1622,12 +1632,14 @@ long do_fork(unsigned long clone_flags, /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) - ptrace_event(trace, nr); + ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) - ptrace_event(PTRACE_EVENT_VFORK_DONE, nr); + ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } + + put_pid(pid); } else { nr = PTR_ERR(p); } diff --git a/kernel/freezer.c b/kernel/freezer.c index aa6a8aadb911..8f9279b9c6d7 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -42,6 +42,9 @@ bool freezing_slow_path(struct task_struct *p) if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; + if (test_thread_flag(TIF_MEMDIE)) + return false; + if (pm_nosig_freezing || cgroup_freezing(p)) return true; diff --git a/kernel/futex.c b/kernel/futex.c index 08ec814ad9d2..fda2950f2ce4 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -157,7 +157,9 @@ * enqueue. */ +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG int __read_mostly futex_cmpxchg_enabled; +#endif /* * Futex flags used to encode options to functions and preserve them across @@ -327,6 +329,8 @@ static void get_futex_key_refs(union futex_key *key) case FUT_OFF_MMSHARED: futex_get_mm(key); /* implies MB (B) */ break; + default: + smp_mb(); /* explicit MB (B) */ } } @@ -727,6 +731,55 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); } +/* + * We need to check the following states: + * + * Waiter | pi_state | pi->owner | uTID | uODIED | ? + * + * [1] NULL | --- | --- | 0 | 0/1 | Valid + * [2] NULL | --- | --- | >0 | 0/1 | Valid + * + * [3] Found | NULL | -- | Any | 0/1 | Invalid + * + * [4] Found | Found | NULL | 0 | 1 | Valid + * [5] Found | Found | NULL | >0 | 1 | Invalid + * + * [6] Found | Found | task | 0 | 1 | Valid + * + * [7] Found | Found | NULL | Any | 0 | Invalid + * + * [8] Found | Found | task | ==taskTID | 0/1 | Valid + * [9] Found | Found | task | 0 | 0 | Invalid + * [10] Found | Found | task | !=taskTID | 0/1 | Invalid + * + * [1] Indicates that the kernel can acquire the futex atomically. We + * came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit. + * + * [2] Valid, if TID does not belong to a kernel thread. If no matching + * thread is found then it indicates that the owner TID has died. + * + * [3] Invalid. The waiter is queued on a non PI futex + * + * [4] Valid state after exit_robust_list(), which sets the user space + * value to FUTEX_WAITERS | FUTEX_OWNER_DIED. + * + * [5] The user space value got manipulated between exit_robust_list() + * and exit_pi_state_list() + * + * [6] Valid state after exit_pi_state_list() which sets the new owner in + * the pi_state but cannot access the user space value. + * + * [7] pi_state->owner can only be NULL when the OWNER_DIED bit is set. + * + * [8] Owner and user space value match + * + * [9] There is no transient state which sets the user space TID to 0 + * except exit_robust_list(), but this is indicated by the + * FUTEX_OWNER_DIED bit. See [4] + * + * [10] There is no transient state which leaves owner and user space + * TID out of sync. + */ static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, union futex_key *key, struct futex_pi_state **ps) @@ -739,12 +792,13 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, plist_for_each_entry_safe(this, next, &hb->chain, list) { if (match_futex(&this->key, key)) { /* - * Another waiter already exists - bump up - * the refcount and return its pi_state: + * Sanity check the waiter before increasing + * the refcount and attaching to it. */ pi_state = this->pi_state; /* - * Userspace might have messed up non-PI and PI futexes + * Userspace might have messed up non-PI and + * PI futexes [3] */ if (unlikely(!pi_state)) return -EINVAL; @@ -752,34 +806,70 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, WARN_ON(!atomic_read(&pi_state->refcount)); /* - * When pi_state->owner is NULL then the owner died - * and another waiter is on the fly. pi_state->owner - * is fixed up by the task which acquires - * pi_state->rt_mutex. - * - * We do not check for pid == 0 which can happen when - * the owner died and robust_list_exit() cleared the - * TID. + * Handle the owner died case: */ - if (pid && pi_state->owner) { + if (uval & FUTEX_OWNER_DIED) { + /* + * exit_pi_state_list sets owner to NULL and + * wakes the topmost waiter. The task which + * acquires the pi_state->rt_mutex will fixup + * owner. + */ + if (!pi_state->owner) { + /* + * No pi state owner, but the user + * space TID is not 0. Inconsistent + * state. [5] + */ + if (pid) + return -EINVAL; + /* + * Take a ref on the state and + * return. [4] + */ + goto out_state; + } + + /* + * If TID is 0, then either the dying owner + * has not yet executed exit_pi_state_list() + * or some waiter acquired the rtmutex in the + * pi state, but did not yet fixup the TID in + * user space. + * + * Take a ref on the state and return. [6] + */ + if (!pid) + goto out_state; + } else { /* - * Bail out if user space manipulated the - * futex value. + * If the owner died bit is not set, + * then the pi_state must have an + * owner. [7] */ - if (pid != task_pid_vnr(pi_state->owner)) + if (!pi_state->owner) return -EINVAL; } + /* + * Bail out if user space manipulated the + * futex value. If pi state exists then the + * owner TID must be the same as the user + * space TID. [9/10] + */ + if (pid != task_pid_vnr(pi_state->owner)) + return -EINVAL; + + out_state: atomic_inc(&pi_state->refcount); *ps = pi_state; - return 0; } } /* * We are the first waiter - try to look up the real owner and attach - * the new pi_state to it, but bail out when TID = 0 + * the new pi_state to it, but bail out when TID = 0 [1] */ if (!pid) return -ESRCH; @@ -787,6 +877,11 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, if (!p) return -ESRCH; + if (!p->mm) { + put_task_struct(p); + return -EPERM; + } + /* * We need to look at the task state flags to figure out, * whether the task is exiting. To protect against the do_exit @@ -807,6 +902,9 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, return ret; } + /* + * No existing pi state. First waiter. [2] + */ pi_state = alloc_pi_state(); /* @@ -878,10 +976,18 @@ retry: return -EDEADLK; /* - * Surprise - we got the lock. Just return to userspace: + * Surprise - we got the lock, but we do not trust user space at all. */ - if (unlikely(!curval)) - return 1; + if (unlikely(!curval)) { + /* + * We verify whether there is kernel state for this + * futex. If not, we can safely assume, that the 0 -> + * TID transition is correct. If state exists, we do + * not bother to fixup the user space state as it was + * corrupted already. + */ + return futex_top_waiter(hb, key) ? -EINVAL : 1; + } uval = curval; @@ -1012,6 +1118,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) struct task_struct *new_owner; struct futex_pi_state *pi_state = this->pi_state; u32 uninitialized_var(curval), newval; + int ret = 0; if (!pi_state) return -EINVAL; @@ -1035,23 +1142,19 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) new_owner = this->task; /* - * We pass it to the next owner. (The WAITERS bit is always - * kept enabled while there is PI state around. We must also - * preserve the owner died bit.) + * We pass it to the next owner. The WAITERS bit is always + * kept enabled while there is PI state around. We cleanup the + * owner died bit, because we are the owner. */ - if (!(uval & FUTEX_OWNER_DIED)) { - int ret = 0; - - newval = FUTEX_WAITERS | task_pid_vnr(new_owner); + newval = FUTEX_WAITERS | task_pid_vnr(new_owner); - if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) - ret = -EFAULT; - else if (curval != uval) - ret = -EINVAL; - if (ret) { - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); - return ret; - } + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) + ret = -EFAULT; + else if (curval != uval) + ret = -EINVAL; + if (ret) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + return ret; } raw_spin_lock_irq(&pi_state->owner->pi_lock); @@ -1331,7 +1434,7 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, * * Return: * 0 - failed to acquire the lock atomically; - * 1 - acquired the lock; + * >0 - acquired the lock, return value is vpid of the top_waiter * <0 - error */ static int futex_proxy_trylock_atomic(u32 __user *pifutex, @@ -1342,7 +1445,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex, { struct futex_q *top_waiter = NULL; u32 curval; - int ret; + int ret, vpid; if (get_futex_value_locked(&curval, pifutex)) return -EFAULT; @@ -1370,11 +1473,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex, * the contended case or if set_waiters is 1. The pi_state is returned * in ps in contended cases. */ + vpid = task_pid_vnr(top_waiter->task); ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, set_waiters); - if (ret == 1) + if (ret == 1) { requeue_pi_wake_futex(top_waiter, key2, hb2); - + return vpid; + } return ret; } @@ -1405,10 +1510,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, struct futex_pi_state *pi_state = NULL; struct futex_hash_bucket *hb1, *hb2; struct futex_q *this, *next; - u32 curval2; if (requeue_pi) { /* + * Requeue PI only works on two distinct uaddrs. This + * check is only valid for private futexes. See below. + */ + if (uaddr1 == uaddr2) + return -EINVAL; + + /* * requeue_pi requires a pi_state, try to allocate it now * without any locks in case it fails. */ @@ -1446,10 +1557,20 @@ retry: if (unlikely(ret != 0)) goto out_put_key1; + /* + * The check above which compares uaddrs is not sufficient for + * shared futexes. We need to compare the keys: + */ + if (requeue_pi && match_futex(&key1, &key2)) { + ret = -EINVAL; + goto out_put_keys; + } + hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); retry_private: + hb_waiters_inc(hb2); double_lock_hb(hb1, hb2); if (likely(cmpval != NULL)) { @@ -1459,6 +1580,7 @@ retry_private: if (unlikely(ret)) { double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); ret = get_user(curval, uaddr1); if (ret) @@ -1491,16 +1613,25 @@ retry_private: * At this point the top_waiter has either taken uaddr2 or is * waiting on it. If the former, then the pi_state will not * exist yet, look it up one more time to ensure we have a - * reference to it. + * reference to it. If the lock was taken, ret contains the + * vpid of the top waiter task. */ - if (ret == 1) { + if (ret > 0) { WARN_ON(pi_state); drop_count++; task_count++; - ret = get_futex_value_locked(&curval2, uaddr2); - if (!ret) - ret = lookup_pi_state(curval2, hb2, &key2, - &pi_state); + /* + * If we acquired the lock, then the user + * space value of uaddr2 should be vpid. It + * cannot be changed by the top waiter as it + * is blocked on hb2 lock if it tries to do + * so. If something fiddled with it behind our + * back the pi state lookup might unearth + * it. So we rather use the known value than + * rereading and handing potential crap to + * lookup_pi_state. + */ + ret = lookup_pi_state(ret, hb2, &key2, &pi_state); } switch (ret) { @@ -1508,6 +1639,7 @@ retry_private: break; case -EFAULT: double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); put_futex_key(&key2); put_futex_key(&key1); ret = fault_in_user_writeable(uaddr2); @@ -1517,6 +1649,7 @@ retry_private: case -EAGAIN: /* The owner was exiting, try again. */ double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); put_futex_key(&key2); put_futex_key(&key1); cond_resched(); @@ -1592,6 +1725,7 @@ retry_private: out_unlock: double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); /* * drop_futex_key_refs() must be called outside the spinlocks. During @@ -2280,9 +2414,10 @@ retry: /* * To avoid races, try to do the TID -> 0 atomic transition * again. If it succeeds then we can return without waking - * anyone else up: + * anyone else up. We only try this if neither the waiters nor + * the owner died bit are set. */ - if (!(uval & FUTEX_OWNER_DIED) && + if (!(uval & ~FUTEX_TID_MASK) && cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0)) goto pi_faulted; /* @@ -2312,11 +2447,9 @@ retry: /* * No waiters - kernel unlocks the futex: */ - if (!(uval & FUTEX_OWNER_DIED)) { - ret = unlock_futex_pi(uaddr, uval); - if (ret == -EFAULT) - goto pi_faulted; - } + ret = unlock_futex_pi(uaddr, uval); + if (ret == -EFAULT) + goto pi_faulted; out_unlock: spin_unlock(&hb->lock); @@ -2478,6 +2611,16 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (ret) goto out_key2; + /* + * The check above which compares uaddrs is not sufficient for + * shared futexes. We need to compare the keys: + */ + if (match_futex(&q.key, &key2)) { + queue_unlock(hb); + ret = -EINVAL; + goto out_put_keys; + } + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ futex_wait_queue_me(hb, &q, to); @@ -2875,9 +3018,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); } -static int __init futex_init(void) +static void __init futex_detect_cmpxchg(void) { +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG u32 curval; + + /* + * This will fail and we want it. Some arch implementations do + * runtime detection of the futex_atomic_cmpxchg_inatomic() + * functionality. We want to know that before we call in any + * of the complex code paths. Also we want to prevent + * registration of robust lists in that case. NULL is + * guaranteed to fault and we get -EFAULT on functional + * implementation, the non-functional ones will return + * -ENOSYS. + */ + if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT) + futex_cmpxchg_enabled = 1; +#endif +} + +static int __init futex_init(void) +{ unsigned int futex_shift; unsigned long i; @@ -2893,18 +3055,8 @@ static int __init futex_init(void) &futex_shift, NULL, futex_hashsize, futex_hashsize); futex_hashsize = 1UL << futex_shift; - /* - * This will fail and we want it. Some arch implementations do - * runtime detection of the futex_atomic_cmpxchg_inatomic() - * functionality. We want to know that before we call in any - * of the complex code paths. Also we want to prevent - * registration of robust lists in that case. NULL is - * guaranteed to fault and we get -EFAULT on functional - * implementation, the non-functional ones will return - * -ENOSYS. - */ - if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT) - futex_cmpxchg_enabled = 1; + + futex_detect_cmpxchg(); for (i = 0; i < futex_hashsize; i++) { atomic_set(&futex_queues[i].waiters, 0); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 09094361dce5..04d03745fb98 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -247,6 +247,11 @@ again: goto again; } timer->base = new_base; + } else { + if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { + cpu = this_cpu; + goto again; + } } return new_base; } @@ -582,6 +587,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) cpu_base->expires_next.tv64 = expires_next.tv64; + /* + * If a hang was detected in the last timer interrupt then we + * leave the hang delay active in the hardware. We want the + * system to make progress. That also prevents the following + * scenario: + * T1 expires 50ms from now + * T2 expires 5s from now + * + * T1 is removed, so this code is called and would reprogram + * the hardware to 5s from now. Any hrtimer_start after that + * will not reprogram the hardware due to hang_detected being + * set. So we'd effectivly block all timers until the T2 event + * fires. + */ + if (cpu_base->hang_detected) + return; + if (cpu_base->expires_next.tv64 != KTIME_MAX) tick_program_event(cpu_base->expires_next, 1); } @@ -981,11 +1003,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Remove an active timer from the queue: */ ret = remove_hrtimer(timer, base); - /* Switch the timer base, if necessary: */ - new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); - if (mode & HRTIMER_MODE_REL) { - tim = ktime_add_safe(tim, new_base->get_time()); + tim = ktime_add_safe(tim, base->get_time()); /* * CONFIG_TIME_LOW_RES is a temporary way for architectures * to signal that they simply return xtime in @@ -1000,6 +1019,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, hrtimer_set_expires_range_ns(timer, tim, delta_ns); + /* Switch the timer base, if necessary: */ + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + timer_stats_hrtimer_set_start_info(timer); leftmost = enqueue_hrtimer(timer, new_base); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index d3bf660cb57f..ebb8a9e937fa 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -150,7 +150,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_chip *chip = irq_data_get_irq_chip(data); int ret; - ret = chip->irq_set_affinity(data, mask, false); + ret = chip->irq_set_affinity(data, mask, force); switch (ret) { case IRQ_SET_MASK_OK: cpumask_copy(data->affinity, mask); @@ -162,7 +162,8 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } -int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) +int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, + bool force) { struct irq_chip *chip = irq_data_get_irq_chip(data); struct irq_desc *desc = irq_data_to_desc(data); @@ -172,7 +173,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) return -EINVAL; if (irq_can_move_pcntxt(data)) { - ret = irq_do_set_affinity(data, mask, false); + ret = irq_do_set_affinity(data, mask, force); } else { irqd_set_move_pending(data); irq_copy_pending(desc, mask); @@ -187,13 +188,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) return ret; } -/** - * irq_set_affinity - Set the irq affinity of a given irq - * @irq: Interrupt to set affinity - * @mask: cpumask - * - */ -int irq_set_affinity(unsigned int irq, const struct cpumask *mask) +int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; @@ -203,7 +198,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask) return -EINVAL; raw_spin_lock_irqsave(&desc->lock, flags); - ret = __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask); + ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force); raw_spin_unlock_irqrestore(&desc->lock, flags); return ret; } @@ -861,8 +856,8 @@ static int irq_thread(void *data) irq_thread_check_affinity(desc, action); action_ret = handler_fn(desc, action); - if (!noirqdebug) - note_interrupt(action->irq, desc, action_ret); + if (action_ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); wake_threads_waitq(desc); } diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index a1d8cc63b56e..e2514b0e439e 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -270,6 +270,8 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc, return action && (action->flags & IRQF_IRQPOLL); } +#define SPURIOUS_DEFERRED 0x80000000 + void note_interrupt(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret) { @@ -277,15 +279,111 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, irq_settings_is_polled(desc)) return; - /* we get here again via the threaded handler */ - if (action_ret == IRQ_WAKE_THREAD) - return; - if (bad_action_ret(action_ret)) { report_bad_irq(irq, desc, action_ret); return; } + /* + * We cannot call note_interrupt from the threaded handler + * because we need to look at the compound of all handlers + * (primary and threaded). Aside of that in the threaded + * shared case we have no serialization against an incoming + * hardware interrupt while we are dealing with a threaded + * result. + * + * So in case a thread is woken, we just note the fact and + * defer the analysis to the next hardware interrupt. + * + * The threaded handlers store whether they sucessfully + * handled an interrupt and we check whether that number + * changed versus the last invocation. + * + * We could handle all interrupts with the delayed by one + * mechanism, but for the non forced threaded case we'd just + * add pointless overhead to the straight hardirq interrupts + * for the sake of a few lines less code. + */ + if (action_ret & IRQ_WAKE_THREAD) { + /* + * There is a thread woken. Check whether one of the + * shared primary handlers returned IRQ_HANDLED. If + * not we defer the spurious detection to the next + * interrupt. + */ + if (action_ret == IRQ_WAKE_THREAD) { + int handled; + /* + * We use bit 31 of thread_handled_last to + * denote the deferred spurious detection + * active. No locking necessary as + * thread_handled_last is only accessed here + * and we have the guarantee that hard + * interrupts are not reentrant. + */ + if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) { + desc->threads_handled_last |= SPURIOUS_DEFERRED; + return; + } + /* + * Check whether one of the threaded handlers + * returned IRQ_HANDLED since the last + * interrupt happened. + * + * For simplicity we just set bit 31, as it is + * set in threads_handled_last as well. So we + * avoid extra masking. And we really do not + * care about the high bits of the handled + * count. We just care about the count being + * different than the one we saw before. + */ + handled = atomic_read(&desc->threads_handled); + handled |= SPURIOUS_DEFERRED; + if (handled != desc->threads_handled_last) { + action_ret = IRQ_HANDLED; + /* + * Note: We keep the SPURIOUS_DEFERRED + * bit set. We are handling the + * previous invocation right now. + * Keep it for the current one, so the + * next hardware interrupt will + * account for it. + */ + desc->threads_handled_last = handled; + } else { + /* + * None of the threaded handlers felt + * responsible for the last interrupt + * + * We keep the SPURIOUS_DEFERRED bit + * set in threads_handled_last as we + * need to account for the current + * interrupt as well. + */ + action_ret = IRQ_NONE; + } + } else { + /* + * One of the primary handlers returned + * IRQ_HANDLED. So we don't care about the + * threaded handlers on the same line. Clear + * the deferred detection bit. + * + * In theory we could/should check whether the + * deferred bit is set and take the result of + * the previous run into account here as + * well. But it's really not worth the + * trouble. If every other interrupt is + * handled we never trigger the spurious + * detector. And if this is just the one out + * of 100k unhandled ones which is handled + * then we merily delay the spurious detection + * by one hard interrupt. Not a real problem. + */ + desc->threads_handled_last &= ~SPURIOUS_DEFERRED; + } + } + if (unlikely(action_ret == IRQ_NONE)) { /* * If we are seeing only the odd spurious IRQ caused by diff --git a/kernel/kcmp.c b/kernel/kcmp.c index e30ac0fe61c3..0aa69ea1d8fd 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type) */ static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type) { - long ret; + long t1, t2; - ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type); + t1 = kptr_obfuscate((long)v1, type); + t2 = kptr_obfuscate((long)v2, type); - return (ret < 0) | ((ret > 0) << 1); + return (t1 < t2) | ((t1 > t2) << 1); } /* The caller must have pinned the task */ diff --git a/kernel/kexec.c b/kernel/kexec.c index 60bafbed06ab..18ff0b91d6d2 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1682,6 +1682,14 @@ int kernel_kexec(void) kexec_in_progress = true; kernel_restart_prepare(NULL); migrate_to_reboot_cpu(); + + /* + * migrate_to_reboot_cpu() disables CPU hotplug assuming that + * no further code needs to use CPU hotplug (which is true in + * the reboot case). However, the kexec path depends on using + * CPU hotplug again; so re-enable it here. + */ + cpu_hotplug_enable(); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); } diff --git a/kernel/kthread.c b/kernel/kthread.c index b5ae3ee860a9..f6249f9ab33e 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -262,7 +262,7 @@ static void create_kthread(struct kthread_create_info *create) * kthread_stop() has been called). The return value should be zero * or a negative error number; it will be passed to kthread_stop(). * - * Returns a task_struct or ERR_PTR(-ENOMEM). + * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). */ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, @@ -298,7 +298,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), * that thread. */ if (xchg(&create->done, NULL)) - return ERR_PTR(-ENOMEM); + return ERR_PTR(-EINTR); /* * kthreadd (or new kernel thread) will call complete() * shortly. diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index 14193d596d78..ab29b6a22669 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -31,3 +31,8 @@ static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, { return (waiter != NULL); } + +static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) +{ + debug_rt_mutex_print_deadlock(w); +} diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 2e960a2bab81..1ce0f6c6eb01 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -83,6 +83,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) owner = *p; } while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); } + +/* + * Safe fastpath aware unlock: + * 1) Clear the waiters bit + * 2) Drop lock->wait_lock + * 3) Try to unlock the lock with cmpxchg + */ +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) + __releases(lock->wait_lock) +{ + struct task_struct *owner = rt_mutex_owner(lock); + + clear_rt_mutex_waiters(lock); + raw_spin_unlock(&lock->wait_lock); + /* + * If a new waiter comes in between the unlock and the cmpxchg + * we have two situations: + * + * unlock(wait_lock); + * lock(wait_lock); + * cmpxchg(p, owner, 0) == owner + * mark_rt_mutex_waiters(lock); + * acquire(lock); + * or: + * + * unlock(wait_lock); + * lock(wait_lock); + * mark_rt_mutex_waiters(lock); + * + * cmpxchg(p, owner, 0) != owner + * enqueue_waiter(); + * unlock(wait_lock); + * lock(wait_lock); + * wake waiter(); + * unlock(wait_lock); + * lock(wait_lock); + * acquire(lock); + */ + return rt_mutex_cmpxchg(lock, owner, NULL); +} + #else # define rt_mutex_cmpxchg(l,c,n) (0) static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) @@ -90,6 +131,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) lock->owner = (struct task_struct *) ((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS); } + +/* + * Simple slow path only version: lock->owner is protected by lock->wait_lock. + */ +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) + __releases(lock->wait_lock) +{ + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return true; +} #endif static inline int @@ -248,27 +300,36 @@ static void rt_mutex_adjust_prio(struct task_struct *task) */ int max_lock_depth = 1024; +static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) +{ + return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; +} + /* * Adjust the priority chain. Also used for deadlock detection. * Decreases task's usage by one - may thus free the task. * - * @task: the task owning the mutex (owner) for which a chain walk is probably - * needed + * @task: the task owning the mutex (owner) for which a chain walk is + * probably needed * @deadlock_detect: do we have to carry out deadlock detection? - * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck - * things for a task that has just got its priority adjusted, and - * is waiting on a mutex) + * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck + * things for a task that has just got its priority adjusted, and + * is waiting on a mutex) + * @next_lock: the mutex on which the owner of @orig_lock was blocked before + * we dropped its pi_lock. Is never dereferenced, only used for + * comparison to detect lock chain changes. * @orig_waiter: rt_mutex_waiter struct for the task that has just donated - * its priority to the mutex owner (can be NULL in the case - * depicted above or if the top waiter is gone away and we are - * actually deboosting the owner) - * @top_task: the current top waiter + * its priority to the mutex owner (can be NULL in the case + * depicted above or if the top waiter is gone away and we are + * actually deboosting the owner) + * @top_task: the current top waiter * * Returns 0 or -EDEADLK. */ static int rt_mutex_adjust_prio_chain(struct task_struct *task, int deadlock_detect, struct rt_mutex *orig_lock, + struct rt_mutex *next_lock, struct rt_mutex_waiter *orig_waiter, struct task_struct *top_task) { @@ -302,7 +363,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } put_task_struct(task); - return deadlock_detect ? -EDEADLK : 0; + return -EDEADLK; } retry: /* @@ -327,13 +388,32 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, goto out_unlock_pi; /* + * We dropped all locks after taking a refcount on @task, so + * the task might have moved on in the lock chain or even left + * the chain completely and blocks now on an unrelated lock or + * on @orig_lock. + * + * We stored the lock on which @task was blocked in @next_lock, + * so we can detect the chain change. + */ + if (next_lock != waiter->lock) + goto out_unlock_pi; + + /* * Drop out, when the task has no waiters. Note, * top_waiter can be NULL, when we are in the deboosting * mode! */ - if (top_waiter && (!task_has_pi_waiters(task) || - top_waiter != task_top_pi_waiter(task))) - goto out_unlock_pi; + if (top_waiter) { + if (!task_has_pi_waiters(task)) + goto out_unlock_pi; + /* + * If deadlock detection is off, we stop here if we + * are not the top pi waiter of the task. + */ + if (!detect_deadlock && top_waiter != task_top_pi_waiter(task)) + goto out_unlock_pi; + } /* * When deadlock detection is off then we check, if further @@ -349,11 +429,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, goto retry; } - /* Deadlock detection */ + /* + * Deadlock detection. If the lock is the same as the original + * lock which caused us to walk the lock chain or if the + * current lock is owned by the task which initiated the chain + * walk, we detected a deadlock. + */ if (lock == orig_lock || rt_mutex_owner(lock) == top_task) { debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock); raw_spin_unlock(&lock->wait_lock); - ret = deadlock_detect ? -EDEADLK : 0; + ret = -EDEADLK; goto out_unlock_pi; } @@ -398,11 +483,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, __rt_mutex_adjust_prio(task); } + /* + * Check whether the task which owns the current lock is pi + * blocked itself. If yes we store a pointer to the lock for + * the lock chain change detection above. After we dropped + * task->pi_lock next_lock cannot be dereferenced anymore. + */ + next_lock = task_blocked_on_lock(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); top_waiter = rt_mutex_top_waiter(lock); raw_spin_unlock(&lock->wait_lock); + /* + * We reached the end of the lock chain. Stop right here. No + * point to go back just to figure that out. + */ + if (!next_lock) + goto out_put_task; + if (!detect_deadlock && waiter != top_waiter) goto out_put_task; @@ -512,8 +612,21 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, { struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex_waiter *top_waiter = waiter; - unsigned long flags; + struct rt_mutex *next_lock; int chain_walk = 0, res; + unsigned long flags; + + /* + * Early deadlock detection. We really don't want the task to + * enqueue on itself just to untangle the mess later. It's not + * only an optimization. We drop the locks, so another waiter + * can come in before the chain walk detects the deadlock. So + * the other will detect the deadlock and return -EDEADLOCK, + * which is wrong, as the other waiter is not in a deadlock + * situation. + */ + if (owner == task) + return -EDEADLK; raw_spin_lock_irqsave(&task->pi_lock, flags); __rt_mutex_adjust_prio(task); @@ -533,20 +646,28 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, if (!owner) return 0; + raw_spin_lock_irqsave(&owner->pi_lock, flags); if (waiter == rt_mutex_top_waiter(lock)) { - raw_spin_lock_irqsave(&owner->pi_lock, flags); rt_mutex_dequeue_pi(owner, top_waiter); rt_mutex_enqueue_pi(owner, waiter); __rt_mutex_adjust_prio(owner); if (owner->pi_blocked_on) chain_walk = 1; - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); - } - else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) + } else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) { chain_walk = 1; + } + + /* Store the lock on which owner is blocked or NULL */ + next_lock = task_blocked_on_lock(owner); - if (!chain_walk) + raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + /* + * Even if full deadlock detection is on, if the owner is not + * blocked itself, we can avoid finding this out in the chain + * walk. + */ + if (!chain_walk || !next_lock) return 0; /* @@ -558,8 +679,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, raw_spin_unlock(&lock->wait_lock); - res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter, - task); + res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, + next_lock, waiter, task); raw_spin_lock(&lock->wait_lock); @@ -569,7 +690,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, /* * Wake up the next waiter on the lock. * - * Remove the top waiter from the current tasks waiter list and wake it up. + * Remove the top waiter from the current tasks pi waiter list and + * wake it up. * * Called with lock->wait_lock held. */ @@ -590,10 +712,23 @@ static void wakeup_next_waiter(struct rt_mutex *lock) */ rt_mutex_dequeue_pi(current, waiter); - rt_mutex_set_owner(lock, NULL); + /* + * As we are waking up the top waiter, and the waiter stays + * queued on the lock until it gets the lock, this lock + * obviously has waiters. Just set the bit here and this has + * the added benefit of forcing all new tasks into the + * slow path making sure no task of lower priority than + * the top waiter can steal this lock. + */ + lock->owner = (void *) RT_MUTEX_HAS_WAITERS; raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + /* + * It's safe to dereference waiter as it cannot go away as + * long as we hold lock->wait_lock. The waiter task needs to + * acquire it in order to dequeue the waiter. + */ wake_up_process(waiter->task); } @@ -608,8 +743,8 @@ static void remove_waiter(struct rt_mutex *lock, { int first = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); + struct rt_mutex *next_lock = NULL; unsigned long flags; - int chain_walk = 0; raw_spin_lock_irqsave(¤t->pi_lock, flags); rt_mutex_dequeue(lock, waiter); @@ -633,13 +768,13 @@ static void remove_waiter(struct rt_mutex *lock, } __rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) - chain_walk = 1; + /* Store the lock on which owner is blocked or NULL */ + next_lock = task_blocked_on_lock(owner); raw_spin_unlock_irqrestore(&owner->pi_lock, flags); } - if (!chain_walk) + if (!next_lock) return; /* gets dropped in rt_mutex_adjust_prio_chain()! */ @@ -647,7 +782,7 @@ static void remove_waiter(struct rt_mutex *lock, raw_spin_unlock(&lock->wait_lock); - rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current); + rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current); raw_spin_lock(&lock->wait_lock); } @@ -660,6 +795,7 @@ static void remove_waiter(struct rt_mutex *lock, void rt_mutex_adjust_pi(struct task_struct *task) { struct rt_mutex_waiter *waiter; + struct rt_mutex *next_lock; unsigned long flags; raw_spin_lock_irqsave(&task->pi_lock, flags); @@ -670,12 +806,13 @@ void rt_mutex_adjust_pi(struct task_struct *task) raw_spin_unlock_irqrestore(&task->pi_lock, flags); return; } - + next_lock = waiter->lock; raw_spin_unlock_irqrestore(&task->pi_lock, flags); /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(task); - rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task); + + rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task); } /** @@ -727,6 +864,26 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static void rt_mutex_handle_deadlock(int res, int detect_deadlock, + struct rt_mutex_waiter *w) +{ + /* + * If the result is not -EDEADLOCK or the caller requested + * deadlock detection, nothing to do here. + */ + if (res != -EDEADLOCK || detect_deadlock) + return; + + /* + * Yell lowdly and stop the task right here. + */ + rt_mutex_print_deadlock(w); + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } +} + /* * Slow path lock function: */ @@ -766,8 +923,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, set_current_state(TASK_RUNNING); - if (unlikely(ret)) + if (unlikely(ret)) { remove_waiter(lock, &waiter); + rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter); + } /* * try_to_take_rt_mutex() sets the waiter bit @@ -823,12 +982,49 @@ rt_mutex_slowunlock(struct rt_mutex *lock) rt_mutex_deadlock_account_unlock(current); - if (!rt_mutex_has_waiters(lock)) { - lock->owner = NULL; - raw_spin_unlock(&lock->wait_lock); - return; + /* + * We must be careful here if the fast path is enabled. If we + * have no waiters queued we cannot set owner to NULL here + * because of: + * + * foo->lock->owner = NULL; + * rtmutex_lock(foo->lock); <- fast path + * free = atomic_dec_and_test(foo->refcnt); + * rtmutex_unlock(foo->lock); <- fast path + * if (free) + * kfree(foo); + * raw_spin_unlock(foo->lock->wait_lock); + * + * So for the fastpath enabled kernel: + * + * Nothing can set the waiters bit as long as we hold + * lock->wait_lock. So we do the following sequence: + * + * owner = rt_mutex_owner(lock); + * clear_rt_mutex_waiters(lock); + * raw_spin_unlock(&lock->wait_lock); + * if (cmpxchg(&lock->owner, owner, 0) == owner) + * return; + * goto retry; + * + * The fastpath disabled variant is simple as all access to + * lock->owner is serialized by lock->wait_lock: + * + * lock->owner = NULL; + * raw_spin_unlock(&lock->wait_lock); + */ + while (!rt_mutex_has_waiters(lock)) { + /* Drops lock->wait_lock ! */ + if (unlock_rt_mutex_safe(lock) == true) + return; + /* Relock the rtmutex and try again */ + raw_spin_lock(&lock->wait_lock); } + /* + * The wakeup next waiter path does not suffer from the above + * race. See the comments there. + */ wakeup_next_waiter(lock); raw_spin_unlock(&lock->wait_lock); @@ -1076,7 +1272,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, return 1; } - ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, 1); if (ret && !rt_mutex_owner(lock)) { /* diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index a1a1dd06421d..f6a1f3c133b1 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -24,3 +24,8 @@ #define debug_rt_mutex_print_deadlock(w) do { } while (0) #define debug_rt_mutex_detect_deadlock(w,d) (d) #define debug_rt_mutex_reset_waiter(w) do { } while (0) + +static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) +{ + WARN(1, "rtmutex deadlock detected\n"); +} diff --git a/kernel/module.c b/kernel/module.c index d24fcf29cb64..1d679a6c942f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -815,9 +815,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; - if (!(flags & O_NONBLOCK)) - pr_warn("waiting module removal not supported: please upgrade\n"); - if (mutex_lock_interruptible(&module_mutex) != 0) return -EINTR; @@ -1844,7 +1841,9 @@ static void free_module(struct module *mod) /* We leave it in list to prevent duplicate loads, but make sure * that noone uses it while it's being deconstructed. */ + mutex_lock(&module_mutex); mod->state = MODULE_STATE_UNFORMED; + mutex_unlock(&module_mutex); /* Remove dynamic debug info */ ddebug_remove_module(mod->name); @@ -3265,6 +3264,9 @@ static int load_module(struct load_info *info, const char __user *uargs, dynamic_debug_setup(info->debug, info->num_debug); + /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */ + ftrace_module_init(mod); + /* Finally it's fully formed, ready to start executing. */ err = complete_formation(mod, info); if (err) diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 06c62de9c711..db95d8eb761b 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -318,7 +318,9 @@ static void *pidns_get(struct task_struct *task) struct pid_namespace *ns; rcu_read_lock(); - ns = get_pid_ns(task_active_pid_ns(task)); + ns = task_active_pid_ns(task); + if (ns) + get_pid_ns(ns); rcu_read_unlock(); return ns; diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 424c2d4265c9..77e6b83c0431 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -634,6 +634,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, goto out; } } else { + memset(&event.sigev_value, 0, sizeof(event.sigev_value)); event.sigev_notify = SIGEV_SIGNAL; event.sigev_signo = SIGALRM; event.sigev_value.sival_int = new_timer->it_id; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 37170d4dd9a6..126586a31408 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -492,8 +492,14 @@ int hibernation_restore(int platform_mode) error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); - dpm_resume_end(PMSG_RECOVER); + /* + * The above should either succeed and jump to the new kernel, + * or return with an error. Otherwise things are just + * undefined, so let's be paranoid. + */ + BUG_ON(!error); } + dpm_resume_end(PMSG_RECOVER); pm_restore_gfp_mask(); ftrace_start(); resume_console(); diff --git a/kernel/power/main.c b/kernel/power/main.c index 1d1bf630e6e9..3ae41cdd804a 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -293,12 +293,12 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, { char *s = buf; #ifdef CONFIG_SUSPEND - int i; + suspend_state_t i; + + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (pm_states[i].state) + s += sprintf(s,"%s ", pm_states[i].label); - for (i = 0; i < PM_SUSPEND_MAX; i++) { - if (pm_states[i] && valid_state(i)) - s += sprintf(s,"%s ", pm_states[i]); - } #endif #ifdef CONFIG_HIBERNATION s += sprintf(s, "%s\n", "disk"); @@ -314,7 +314,7 @@ static suspend_state_t decode_state(const char *buf, size_t n) { #ifdef CONFIG_SUSPEND suspend_state_t state = PM_SUSPEND_MIN; - const char * const *s; + struct pm_sleep_state *s; #endif char *p; int len; @@ -328,8 +328,9 @@ static suspend_state_t decode_state(const char *buf, size_t n) #ifdef CONFIG_SUSPEND for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) - if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) - return state; + if (s->state && len == strlen(s->label) + && !strncmp(buf, s->label, len)) + return s->state; #endif return PM_SUSPEND_ON; @@ -447,8 +448,8 @@ static ssize_t autosleep_show(struct kobject *kobj, #ifdef CONFIG_SUSPEND if (state < PM_SUSPEND_MAX) - return sprintf(buf, "%s\n", valid_state(state) ? - pm_states[state] : "error"); + return sprintf(buf, "%s\n", pm_states[state].state ? + pm_states[state].label : "error"); #endif #ifdef CONFIG_HIBERNATION return sprintf(buf, "disk\n"); diff --git a/kernel/power/power.h b/kernel/power/power.h index 7d4b7ffb3c1d..f770cad3666c 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -175,17 +175,20 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *, unsigned int, char *); #ifdef CONFIG_SUSPEND +struct pm_sleep_state { + const char *label; + suspend_state_t state; +}; + /* kernel/power/suspend.c */ -extern const char *const pm_states[]; +extern struct pm_sleep_state pm_states[]; -extern bool valid_state(suspend_state_t state); extern int suspend_devices_and_enter(suspend_state_t state); #else /* !CONFIG_SUSPEND */ static inline int suspend_devices_and_enter(suspend_state_t state) { return -ENOSYS; } -static inline bool valid_state(suspend_state_t state) { return false; } #endif /* !CONFIG_SUSPEND */ #ifdef CONFIG_PM_TEST_SUSPEND diff --git a/kernel/power/process.c b/kernel/power/process.c index 06ec8869dbf1..f1fe7ec110bb 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -107,6 +107,28 @@ static int try_to_freeze_tasks(bool user_only) return todo ? -EBUSY : 0; } +/* + * Returns true if all freezable tasks (except for current) are frozen already + */ +static bool check_frozen_processes(void) +{ + struct task_struct *g, *p; + bool ret = true; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (p != current && !freezer_should_skip(p) && + !frozen(p)) { + ret = false; + goto done; + } + } +done: + read_unlock(&tasklist_lock); + + return ret; +} + /** * freeze_processes - Signal user space processes to enter the refrigerator. * The current thread will not be frozen. The same process that calls @@ -117,6 +139,7 @@ static int try_to_freeze_tasks(bool user_only) int freeze_processes(void) { int error; + int oom_kills_saved; error = __usermodehelper_disable(UMH_FREEZING); if (error) @@ -130,12 +153,27 @@ int freeze_processes(void) printk("Freezing user space processes ... "); pm_freezing = true; + oom_kills_saved = oom_kills_count(); error = try_to_freeze_tasks(true); if (!error) { - printk("done."); __usermodehelper_set_disable_depth(UMH_DISABLED); oom_killer_disable(); + + /* + * There might have been an OOM kill while we were + * freezing tasks and the killed task might be still + * on the way out so we have to double check for race. + */ + if (oom_kills_count() != oom_kills_saved && + !check_frozen_processes()) { + __usermodehelper_set_disable_depth(UMH_ENABLED); + printk("OOM in progress."); + error = -EBUSY; + goto done; + } + printk("done."); } +done: printk("\n"); BUG_ON(in_atomic()); @@ -184,6 +222,7 @@ void thaw_processes(void) printk("Restarting tasks ... "); + __usermodehelper_set_disable_depth(UMH_FREEZING); thaw_workqueues(); read_lock(&tasklist_lock); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 62ee437b5c7e..5455d5c3c149 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -29,10 +29,10 @@ #include "power.h" -const char *const pm_states[PM_SUSPEND_MAX] = { - [PM_SUSPEND_FREEZE] = "freeze", - [PM_SUSPEND_STANDBY] = "standby", - [PM_SUSPEND_MEM] = "mem", +struct pm_sleep_state pm_states[PM_SUSPEND_MAX] = { + [PM_SUSPEND_FREEZE] = { .label = "freeze", .state = PM_SUSPEND_FREEZE }, + [PM_SUSPEND_STANDBY] = { .label = "standby", }, + [PM_SUSPEND_MEM] = { .label = "mem", }, }; static const struct platform_suspend_ops *suspend_ops; @@ -62,42 +62,34 @@ void freeze_wake(void) } EXPORT_SYMBOL_GPL(freeze_wake); +static bool valid_state(suspend_state_t state) +{ + /* + * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level + * support and need to be valid to the low level + * implementation, no valid callback implies that none are valid. + */ + return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); +} + /** * suspend_set_ops - Set the global suspend method table. * @ops: Suspend operations to use. */ void suspend_set_ops(const struct platform_suspend_ops *ops) { + suspend_state_t i; + lock_system_sleep(); + suspend_ops = ops; + for (i = PM_SUSPEND_STANDBY; i <= PM_SUSPEND_MEM; i++) + pm_states[i].state = valid_state(i) ? i : 0; + unlock_system_sleep(); } EXPORT_SYMBOL_GPL(suspend_set_ops); -bool valid_state(suspend_state_t state) -{ - if (state == PM_SUSPEND_FREEZE) { -#ifdef CONFIG_PM_DEBUG - if (pm_test_level != TEST_NONE && - pm_test_level != TEST_FREEZER && - pm_test_level != TEST_DEVICES && - pm_test_level != TEST_PLATFORM) { - printk(KERN_WARNING "Unsupported pm_test mode for " - "freeze state, please choose " - "none/freezer/devices/platform.\n"); - return false; - } -#endif - return true; - } - /* - * PM_SUSPEND_STANDBY and PM_SUSPEND_MEMORY states need lowlevel - * support and need to be valid to the lowlevel - * implementation, no valid callback implies that none are valid. - */ - return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); -} - /** * suspend_valid_only_mem - Generic memory-only valid callback. * @@ -324,9 +316,17 @@ static int enter_state(suspend_state_t state) { int error; - if (!valid_state(state)) - return -ENODEV; - + if (state == PM_SUSPEND_FREEZE) { +#ifdef CONFIG_PM_DEBUG + if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { + pr_warning("PM: Unsupported test mode for freeze state," + "please choose none/freezer/devices/platform.\n"); + return -EAGAIN; + } +#endif + } else if (!valid_state(state)) { + return -EINVAL; + } if (!mutex_trylock(&pm_mutex)) return -EBUSY; @@ -337,7 +337,7 @@ static int enter_state(suspend_state_t state) sys_sync(); printk("done.\n"); - pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]); + pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label); error = suspend_prepare(state); if (error) goto Unlock; @@ -345,7 +345,7 @@ static int enter_state(suspend_state_t state) if (suspend_test(TEST_FREEZER)) goto Finish; - pr_debug("PM: Entering %s sleep\n", pm_states[state]); + pr_debug("PM: Entering %s sleep\n", pm_states[state].label); pm_restrict_gfp_mask(); error = suspend_devices_and_enter(state); pm_restore_gfp_mask(); diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index 9b2a1d58558d..269b097e78ea 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -92,13 +92,13 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) } if (state == PM_SUSPEND_MEM) { - printk(info_test, pm_states[state]); + printk(info_test, pm_states[state].label); status = pm_suspend(state); if (status == -ENODEV) state = PM_SUSPEND_STANDBY; } if (state == PM_SUSPEND_STANDBY) { - printk(info_test, pm_states[state]); + printk(info_test, pm_states[state].label); status = pm_suspend(state); } if (status < 0) @@ -136,18 +136,16 @@ static char warn_bad_state[] __initdata = static int __init setup_test_suspend(char *value) { - unsigned i; + suspend_state_t i; /* "=mem" ==> "mem" */ value++; - for (i = 0; i < PM_SUSPEND_MAX; i++) { - if (!pm_states[i]) - continue; - if (strcmp(pm_states[i], value) != 0) - continue; - test_state = (__force suspend_state_t) i; - return 0; - } + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (!strcmp(pm_states[i].label, value)) { + test_state = pm_states[i].state; + return 0; + } + printk(warn_bad_state, value); return 0; } @@ -164,8 +162,8 @@ static int __init test_suspend(void) /* PM is initialized by now; is that state testable? */ if (test_state == PM_SUSPEND_ON) goto done; - if (!valid_state(test_state)) { - printk(warn_bad_state, pm_states[test_state]); + if (!pm_states[test_state].state) { + printk(warn_bad_state, pm_states[test_state].label); goto done; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 4dae9cbe9259..8c086e6049b9 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2468,7 +2468,7 @@ void wake_up_klogd(void) preempt_enable(); } -int printk_sched(const char *fmt, ...) +int printk_deferred(const char *fmt, ...) { unsigned long flags; va_list args; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f5c6635b806c..9a3f3c4e1f5a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1322,7 +1322,7 @@ out: * leave kernel. */ if (p->mm && printk_ratelimit()) { - printk_sched("process %d (%s) no longer affine to cpu%d\n", + printk_deferred("process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } } @@ -1895,6 +1895,8 @@ unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_SMP inline struct dl_bw *dl_bw_of(int i) { + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); return &cpu_rq(i)->rd->dl_bw; } @@ -1903,6 +1905,8 @@ static inline int dl_bw_cpus(int i) struct root_domain *rd = cpu_rq(i)->rd; int cpus = 0; + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); for_each_cpu_and(i, rd->span, cpu_active_mask) cpus++; @@ -3242,17 +3246,40 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr) * We ask for the deadline not being zero, and greater or equal * than the runtime, as well as the period of being zero or * greater than deadline. Furthermore, we have to be sure that - * user parameters are above the internal resolution (1us); we - * check sched_runtime only since it is always the smaller one. + * user parameters are above the internal resolution of 1us (we + * check sched_runtime only since it is always the smaller one) and + * below 2^63 ns (we have to check both sched_deadline and + * sched_period, as the latter can be zero). */ static bool __checkparam_dl(const struct sched_attr *attr) { - return attr && attr->sched_deadline != 0 && - (attr->sched_period == 0 || - (s64)(attr->sched_period - attr->sched_deadline) >= 0) && - (s64)(attr->sched_deadline - attr->sched_runtime ) >= 0 && - attr->sched_runtime >= (2 << (DL_SCALE - 1)); + /* deadline != 0 */ + if (attr->sched_deadline == 0) + return false; + + /* + * Since we truncate DL_SCALE bits, make sure we're at least + * that big. + */ + if (attr->sched_runtime < (1ULL << DL_SCALE)) + return false; + + /* + * Since we use the MSB for wrap-around and sign issues, make + * sure it's not set (mind that period can be equal to zero). + */ + if (attr->sched_deadline & (1ULL << 63) || + attr->sched_period & (1ULL << 63)) + return false; + + /* runtime <= deadline <= period (if period != 0) */ + if ((attr->sched_period != 0 && + attr->sched_period < attr->sched_deadline) || + attr->sched_deadline < attr->sched_runtime) + return false; + + return true; } /* @@ -3488,9 +3515,10 @@ static int _sched_setscheduler(struct task_struct *p, int policy, }; /* - * Fixup the legacy SCHED_RESET_ON_FORK hack + * Fixup the legacy SCHED_RESET_ON_FORK hack, except if + * the policy=-1 was passed by sched_setparam(). */ - if (policy & SCHED_RESET_ON_FORK) { + if ((policy != -1) && (policy & SCHED_RESET_ON_FORK)) { attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; policy &= ~SCHED_RESET_ON_FORK; attr.sched_policy = policy; @@ -3680,8 +3708,12 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, if (!uattr || pid < 0 || flags) return -EINVAL; - if (sched_copy_attr(uattr, &attr)) - return -EFAULT; + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; rcu_read_lock(); retval = -ESRCH; @@ -3731,7 +3763,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) */ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) { - struct sched_param lp; + struct sched_param lp = { .sched_priority = 0 }; struct task_struct *p; int retval; @@ -3748,11 +3780,8 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) if (retval) goto out_unlock; - if (task_has_dl_policy(p)) { - retval = -EINVAL; - goto out_unlock; - } - lp.sched_priority = p->rt_priority; + if (task_has_rt_policy(p)) + lp.sched_priority = p->rt_priority; rcu_read_unlock(); /* @@ -3912,13 +3941,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) * root_domain. */ #ifdef CONFIG_SMP - if (task_has_dl_policy(p)) { - const struct cpumask *span = task_rq(p)->rd->span; - - if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) { + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + rcu_read_lock(); + if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { retval = -EBUSY; + rcu_read_unlock(); goto out_unlock; } + rcu_read_unlock(); } #endif again: @@ -5051,7 +5081,6 @@ static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { - case CPU_STARTING: case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -7434,6 +7463,8 @@ static int sched_dl_global_constraints(void) int cpu, ret = 0; unsigned long flags; + rcu_read_lock(); + /* * Here we want to check the bandwidth not being set to some * value smaller than the currently allocated bandwidth in @@ -7455,6 +7486,8 @@ static int sched_dl_global_constraints(void) break; } + rcu_read_unlock(); + return ret; } @@ -7470,6 +7503,7 @@ static void sched_dl_do_global(void) if (global_rt_runtime() != RUNTIME_INF) new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + rcu_read_lock(); /* * FIXME: As above... */ @@ -7480,6 +7514,7 @@ static void sched_dl_do_global(void) dl_b->bw = new_bw; raw_spin_unlock_irqrestore(&dl_b->lock, flags); } + rcu_read_unlock(); } static int sched_rt_global_validate(void) diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 5b9bb42b2d47..ab001b5d5048 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -210,7 +210,5 @@ int cpudl_init(struct cpudl *cp) */ void cpudl_cleanup(struct cpudl *cp) { - /* - * nothing to do for the moment - */ + free_cpumask_var(cp->free_cpus); } diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 8b836b376d91..3031bac8aa3e 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -70,8 +70,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, int idx = 0; int task_pri = convert_prio(p->prio); - if (task_pri >= MAX_RT_PRIO) - return 0; + BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES); for (idx = 0; idx < task_pri; idx++) { struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 99947919e30b..cfe2f268afaa 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -326,50 +326,50 @@ out: * softirq as those do not count in task exec_runtime any more. */ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) + struct rq *rq, int ticks) { - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + cputime_t scaled = cputime_to_scaled(cputime_one_jiffy); + u64 cputime = (__force u64) cputime_one_jiffy; u64 *cpustat = kcpustat_this_cpu->cpustat; if (steal_account_process_tick()) return; + cputime *= ticks; + scaled *= ticks; + if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_IRQ] += cputime; } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_SOFTIRQ] += cputime; } else if (this_cpu_ksoftirqd() == p) { /* * ksoftirqd time do not get accounted in cpu_softirq_time. * So, we have to handle it separately here. * Also, p->stime needs to be updated for ksoftirqd. */ - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SOFTIRQ); + __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ); } else if (user_tick) { - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_user_time(p, cputime, scaled); } else if (p == rq->idle) { - account_idle_time(cputime_one_jiffy); + account_idle_time(cputime); } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_guest_time(p, cputime, scaled); } else { - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SYSTEM); + __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM); } } static void irqtime_account_idle_ticks(int ticks) { - int i; struct rq *rq = this_rq(); - for (i = 0; i < ticks; i++) - irqtime_account_process_tick(current, 0, rq); + irqtime_account_process_tick(current, 0, rq, ticks); } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ static inline void irqtime_account_idle_ticks(int ticks) {} static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) {} + struct rq *rq, int nr_ticks) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ /* @@ -458,7 +458,7 @@ void account_process_tick(struct task_struct *p, int user_tick) return; if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); + irqtime_account_process_tick(p, user_tick, rq, 1); return; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6e79b3faa4cd..37dac98c0749 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -329,7 +329,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, if (!lag_once) { lag_once = true; - printk_sched("sched: DL replenish lagged to much\n"); + printk_deferred("sched: DL replenish lagged to much\n"); } dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; @@ -490,9 +490,17 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) struct sched_dl_entity, dl_timer); struct task_struct *p = dl_task_of(dl_se); - struct rq *rq = task_rq(p); + struct rq *rq; +again: + rq = task_rq(p); raw_spin_lock(&rq->lock); + if (rq != task_rq(p)) { + /* Task was moved, retrying. */ + raw_spin_unlock(&rq->lock); + goto again; + } + /* * We need to take care of a possible races here. In fact, the * task might have changed its scheduling policy to something diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index dd52e7ffb10e..183e8e5c38ba 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -608,7 +608,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) avg_atom = p->se.sum_exec_runtime; if (nr_switches) - do_div(avg_atom, nr_switches); + avg_atom = div64_ul(avg_atom, nr_switches); else avg_atom = -1LL; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 1999021042c7..27b8e836307f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -837,7 +837,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) if (!once) { once = true; - printk_sched("sched: RT throttling activated\n"); + printk_deferred("sched: RT throttling activated\n"); } } else { /* diff --git a/kernel/smp.c b/kernel/smp.c index ffee35bef179..ff87d4479558 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -617,7 +617,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), if (cond_func(cpu, info)) { ret = smp_call_function_single(cpu, func, info, wait); - WARN_ON_ONCE(!ret); + WARN_ON_ONCE(ret); } preempt_enable(); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 49e13e1f8fe6..c1b26e176aa6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -139,11 +139,15 @@ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ static int maxolduid = 65535; static int minolduid; -static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; +/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */ +#ifdef CONFIG_DETECT_HUNG_TASK +static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); +#endif + #ifdef CONFIG_INOTIFY_USER #include <linux/inotify.h> #endif @@ -995,6 +999,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = &hung_task_timeout_max, }, { .procname = "hung_task_warnings", @@ -1318,7 +1323,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(percpu_pagelist_fraction), .mode = 0644, .proc_handler = percpu_pagelist_fraction_sysctl_handler, - .extra1 = &min_percpu_pagelist_fract, + .extra1 = &zero, }, #ifdef CONFIG_MMU { diff --git a/kernel/time.c b/kernel/time.c index 7c7964c33ae7..3c49ab45f822 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -496,17 +496,20 @@ EXPORT_SYMBOL(usecs_to_jiffies); * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. + * Note that due to the small error in the multiplier here, this + * rounding is incorrect for sufficiently large values of tv_nsec, but + * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're + * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. */ -unsigned long -timespec_to_jiffies(const struct timespec *value) +static unsigned long +__timespec_to_jiffies(unsigned long sec, long nsec) { - unsigned long sec = value->tv_sec; - long nsec = value->tv_nsec + TICK_NSEC - 1; + nsec = nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; @@ -517,6 +520,13 @@ timespec_to_jiffies(const struct timespec *value) (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } + +unsigned long +timespec_to_jiffies(const struct timespec *value) +{ + return __timespec_to_jiffies(value->tv_sec, value->tv_nsec); +} + EXPORT_SYMBOL(timespec_to_jiffies); void @@ -533,31 +543,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) } EXPORT_SYMBOL(jiffies_to_timespec); -/* Same for "timeval" +/* + * We could use a similar algorithm to timespec_to_jiffies (with a + * different multiplier for usec instead of nsec). But this has a + * problem with rounding: we can't exactly add TICK_NSEC - 1 to the + * usec value, since it's not necessarily integral. * - * Well, almost. The problem here is that the real system resolution is - * in nanoseconds and the value being converted is in micro seconds. - * Also for some machines (those that use HZ = 1024, in-particular), - * there is a LARGE error in the tick size in microseconds. - - * The solution we use is to do the rounding AFTER we convert the - * microsecond part. Thus the USEC_ROUND, the bits to be shifted off. - * Instruction wise, this should cost only an additional add with carry - * instruction above the way it was done above. + * We could instead round in the intermediate scaled representation + * (i.e. in units of 1/2^(large scale) jiffies) but that's also + * perilous: the scaling introduces a small positive error, which + * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1 + * units to the intermediate before shifting) leads to accidental + * overflow and overestimates. + * + * At the cost of one additional multiplication by a constant, just + * use the timespec implementation. */ unsigned long timeval_to_jiffies(const struct timeval *value) { - unsigned long sec = value->tv_sec; - long usec = value->tv_usec; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - usec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)usec * USEC_CONVERSION + USEC_ROUND) >> - (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; + return __timespec_to_jiffies(value->tv_sec, + value->tv_usec * NSEC_PER_USEC); } EXPORT_SYMBOL(timeval_to_jiffies); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 88c9c65a430d..cd45a0727a16 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, ktime_t now) { + unsigned long flags; struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); - if (posix_timer_event(ptr, 0) != 0) - ptr->it_overrun++; + enum alarmtimer_restart result = ALARMTIMER_NORESTART; + + spin_lock_irqsave(&ptr->it_lock, flags); + if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) { + if (posix_timer_event(ptr, 0) != 0) + ptr->it_overrun++; + } /* Re-add periodic timers */ if (ptr->it.alarm.interval.tv64) { ptr->it_overrun += alarm_forward(alarm, now, ptr->it.alarm.interval); - return ALARMTIMER_RESTART; + result = ALARMTIMER_RESTART; } - return ALARMTIMER_NORESTART; + spin_unlock_irqrestore(&ptr->it_lock, flags); + + return result; } /** @@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer) * @new_timer: k_itimer pointer * @cur_setting: itimerspec data to fill * - * Copies the itimerspec data out from the k_itimer + * Copies out the current itimerspec data */ static void alarm_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) { - memset(cur_setting, 0, sizeof(struct itimerspec)); + ktime_t relative_expiry_time = + alarm_expires_remaining(&(timr->it.alarm.alarmtimer)); - cur_setting->it_interval = - ktime_to_timespec(timr->it.alarm.interval); - cur_setting->it_value = - ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires); - return; + if (ktime_to_ns(relative_expiry_time) > 0) { + cur_setting->it_value = ktime_to_timespec(relative_expiry_time); + } else { + cur_setting->it_value.tv_sec = 0; + cur_setting->it_value.tv_nsec = 0; + } + + cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval); } /** @@ -585,9 +597,14 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, struct itimerspec *new_setting, struct itimerspec *old_setting) { + ktime_t exp; + if (!rtcdev) return -ENOTSUPP; + if (flags & ~TIMER_ABSTIME) + return -EINVAL; + if (old_setting) alarm_timer_get(timr, old_setting); @@ -597,8 +614,16 @@ 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); - alarm_start(&timr->it.alarm.alarmtimer, - timespec_to_ktime(new_setting->it_value)); + 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); + } + + alarm_start(&timr->it.alarm.alarmtimer, exp); return 0; } @@ -730,6 +755,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, if (!alarmtimer_get_rtcdev()) return -ENOTSUPP; + if (flags & ~TIMER_ABSTIME) + return -EINVAL; + if (!capable(CAP_WAKE_ALARM)) return -EPERM; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 086ad6043bcb..60ba1af801c3 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -146,7 +146,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) { /* Nothing to do if we already reached the limit */ if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { - printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); + printk_deferred(KERN_WARNING + "CE: Reprogramming failure. Giving up\n"); dev->next_event.tv64 = KTIME_MAX; return -ETIME; } @@ -159,9 +160,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) if (dev->min_delta_ns > MIN_DELTA_LIMIT) dev->min_delta_ns = MIN_DELTA_LIMIT; - printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", - dev->name ? dev->name : "?", - (unsigned long long) dev->min_delta_ns); + printk_deferred(KERN_WARNING + "CE: %s increased min_delta_ns to %llu nsec\n", + dev->name ? dev->name : "?", + (unsigned long long) dev->min_delta_ns); return 0; } diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 4d23dc4d8139..313a662911b1 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -204,7 +204,8 @@ void __init sched_clock_postinit(void) static int sched_clock_suspend(void) { - sched_clock_poll(&sched_clock_timer); + update_sched_clock(); + hrtimer_cancel(&sched_clock_timer); cd.suspended = true; return 0; } @@ -212,6 +213,7 @@ static int sched_clock_suspend(void) static void sched_clock_resume(void) { cd.epoch_cyc = read_sched_clock(); + hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); cd.suspended = false; } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 20b2fe37d105..0de9d7f5045c 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -276,7 +276,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev, bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev) { - if (tick_check_percpu(curdev, newdev, smp_processor_id())) + if (!tick_check_percpu(curdev, newdev, smp_processor_id())) return false; return tick_check_preferred(curdev, newdev); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9f8af69c67ec..6558b7ac112d 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -84,6 +84,9 @@ static void tick_do_update_jiffies64(ktime_t now) /* Keep the tick_next_period variable up to date */ tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { + write_sequnlock(&jiffies_lock); + return; } write_sequnlock(&jiffies_lock); update_wall_time(); @@ -967,7 +970,7 @@ static void tick_nohz_switch_to_nohz(void) struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); ktime_t next; - if (!tick_nohz_active) + if (!tick_nohz_enabled) return; local_irq_disable(); diff --git a/kernel/timer.c b/kernel/timer.c index accfd241b9e5..38f0d40fca13 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -822,7 +822,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires) bit = find_last_bit(&mask, BITS_PER_LONG); - mask = (1 << bit) - 1; + mask = (1UL << bit) - 1; expires_limit = expires_limit & ~(mask); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index b418cb0d7242..4f3a3c03eadb 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -702,6 +702,7 @@ void blk_trace_shutdown(struct request_queue *q) * blk_add_trace_rq - Add a trace for a request oriented action * @q: queue the io is for * @rq: the source request + * @nr_bytes: number of completed bytes * @what: the action * * Description: @@ -709,7 +710,7 @@ void blk_trace_shutdown(struct request_queue *q) * **/ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, - u32 what) + unsigned int nr_bytes, u32 what) { struct blk_trace *bt = q->blk_trace; @@ -718,11 +719,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); - __blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags, + __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags, what, rq->errors, rq->cmd_len, rq->cmd); } else { what |= BLK_TC_ACT(BLK_TC_FS); - __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), + __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, rq->cmd_flags, what, rq->errors, 0, NULL); } } @@ -730,33 +731,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, static void blk_add_trace_rq_abort(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_ABORT); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT); } static void blk_add_trace_rq_insert(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_INSERT); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT); } static void blk_add_trace_rq_issue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_ISSUE); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE); } static void blk_add_trace_rq_requeue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_REQUEUE); + blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE); } static void blk_add_trace_rq_complete(void *ignore, struct request_queue *q, - struct request *rq) + struct request *rq, + unsigned int nr_bytes) { - blk_add_trace_rq(q, rq, BLK_TA_COMPLETE); + blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE); } /** diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index cd7f76d1eb86..e3be87edde33 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -331,12 +331,12 @@ static void update_ftrace_function(void) func = ftrace_ops_list_func; } + update_function_graph_func(); + /* If there's no change, then do nothing more here */ if (ftrace_trace_function == func) return; - update_function_graph_func(); - /* * If we are using the list function, it doesn't care * about the function_trace_ops. @@ -4315,16 +4315,11 @@ static void ftrace_init_module(struct module *mod, ftrace_process_locs(mod, start, end); } -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) +void ftrace_module_init(struct module *mod) { - struct module *mod = data; - - if (val == MODULE_STATE_COMING) - ftrace_init_module(mod, mod->ftrace_callsites, - mod->ftrace_callsites + - mod->num_ftrace_callsites); - return 0; + ftrace_init_module(mod, mod->ftrace_callsites, + mod->ftrace_callsites + + mod->num_ftrace_callsites); } static int ftrace_module_notify_exit(struct notifier_block *self, @@ -4338,11 +4333,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self, return 0; } #else -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) -{ - return 0; -} static int ftrace_module_notify_exit(struct notifier_block *self, unsigned long val, void *data) { @@ -4350,11 +4340,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self, } #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_enter_nb = { - .notifier_call = ftrace_module_notify_enter, - .priority = INT_MAX, /* Run before anything that can use kprobes */ -}; - struct notifier_block ftrace_module_exit_nb = { .notifier_call = ftrace_module_notify_exit, .priority = INT_MIN, /* Run after anything that can remove kprobes */ @@ -4391,10 +4376,6 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_enter_nb); - if (ret) - pr_warning("Failed to register trace ftrace module enter notifier\n"); - ret = register_module_notifier(&ftrace_module_exit_nb); if (ret) pr_warning("Failed to register trace ftrace module exit notifier\n"); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index fc4da2d97f9b..774a0807fe81 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -543,7 +543,7 @@ static void rb_wake_up_waiters(struct irq_work *work) * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -void ring_buffer_wait(struct ring_buffer *buffer, int cpu) +int ring_buffer_wait(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); @@ -557,6 +557,8 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu) if (cpu == RING_BUFFER_ALL_CPUS) work = &buffer->irq_work; else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -ENODEV; cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; } @@ -591,6 +593,7 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu) schedule(); finish_wait(&work->waiters, &wait); + return 0; } /** @@ -613,10 +616,6 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *work; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || - (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) - return POLLIN | POLLRDNORM; - if (cpu == RING_BUFFER_ALL_CPUS) work = &buffer->irq_work; else { @@ -627,8 +626,22 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, work = &cpu_buffer->irq_work; } - work->waiters_pending = true; poll_wait(filp, &work->waiters, poll_table); + work->waiters_pending = true; + /* + * There's a tight race between setting the waiters_pending and + * checking if the ring buffer is empty. Once the waiters_pending bit + * is set, the next event will wake the task up, but we can get stuck + * if there's only a single event in. + * + * FIXME: Ideally, we need a memory barrier on the writer side as well, + * but adding a memory barrier to all events will cause too much of a + * performance hit in the fast path. We only need a memory barrier when + * the buffer goes from empty to having content. But as this race is + * extremely small, and it's not a problem if another event comes in, we + * will fix it later. + */ + smp_mb(); if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) @@ -1982,7 +1995,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta) /** * rb_update_event - update event type and data - * @event: the even to update + * @event: the event to update * @type: the type of event * @length: the size of the event field in the ring buffer * @@ -3355,21 +3368,16 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; /* Iterator usage is expected to have record disabled */ - if (list_empty(&cpu_buffer->reader_page->list)) { - iter->head_page = rb_set_head_page(cpu_buffer); - if (unlikely(!iter->head_page)) - return; - iter->head = iter->head_page->read; - } else { - iter->head_page = cpu_buffer->reader_page; - iter->head = cpu_buffer->reader_page->read; - } + iter->head_page = cpu_buffer->reader_page; + iter->head = cpu_buffer->reader_page->read; + + iter->cache_reader_page = iter->head_page; + iter->cache_read = cpu_buffer->read; + if (iter->head) iter->read_stamp = cpu_buffer->read_stamp; else iter->read_stamp = iter->head_page->page->time_stamp; - iter->cache_reader_page = cpu_buffer->reader_page; - iter->cache_read = cpu_buffer->read; } /** @@ -3762,12 +3770,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return NULL; /* - * We repeat when a time extend is encountered. - * Since the time extend is always attached to a data event, - * we should never loop more than once. - * (We never hit the following condition more than twice). + * We repeat when a time extend is encountered or we hit + * the end of the page. Since the time extend is always attached + * to a data event, we should never loop more than three times. + * Once for going to next page, once on time extend, and + * finally once to get the event. + * (We never hit the following condition more than thrice). */ - if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2)) + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) return NULL; if (rb_per_cpu_empty(cpu_buffer)) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 24c1f2382557..71136720ffa1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -454,6 +454,12 @@ int __trace_puts(unsigned long ip, const char *str, int size) struct print_entry *entry; unsigned long irq_flags; int alloc; + int pc; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + pc = preempt_count(); if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -463,7 +469,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) local_save_flags(irq_flags); buffer = global_trace.trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, - irq_flags, preempt_count()); + irq_flags, pc); if (!event) return 0; @@ -480,6 +486,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, irq_flags, 4, pc); return size; } @@ -497,6 +504,12 @@ int __trace_bputs(unsigned long ip, const char *str) struct bputs_entry *entry; unsigned long irq_flags; int size = sizeof(struct bputs_entry); + int pc; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + pc = preempt_count(); if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -504,7 +517,7 @@ int __trace_bputs(unsigned long ip, const char *str) local_save_flags(irq_flags); buffer = global_trace.trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, - irq_flags, preempt_count()); + irq_flags, pc); if (!event) return 0; @@ -513,6 +526,7 @@ int __trace_bputs(unsigned long ip, const char *str) entry->str = str; __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(buffer, irq_flags, 4, pc); return 1; } @@ -797,7 +811,7 @@ static struct { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, - { trace_clock_jiffies, "uptime", 1 }, + { trace_clock_jiffies, "uptime", 0 }, { trace_clock, "perf", 1 }, ARCH_TRACE_CLOCKS }; @@ -1091,13 +1105,13 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) } #endif /* CONFIG_TRACER_MAX_TRACE */ -static void default_wait_pipe(struct trace_iterator *iter) +static int default_wait_pipe(struct trace_iterator *iter) { /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) - return; + return 0; - ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file); + return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file); } #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -1355,7 +1369,6 @@ void tracing_start(void) arch_spin_unlock(&ftrace_max_lock); - ftrace_start(); out: raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); } @@ -1402,7 +1415,6 @@ void tracing_stop(void) struct ring_buffer *buffer; unsigned long flags; - ftrace_stop(); raw_spin_lock_irqsave(&global_trace.start_lock, flags); if (global_trace.stop_count++) goto out; @@ -1449,12 +1461,12 @@ static void tracing_stop_tr(struct trace_array *tr) void trace_stop_cmdline_recording(void); -static void trace_save_cmdline(struct task_struct *tsk) +static int trace_save_cmdline(struct task_struct *tsk) { unsigned pid, idx; if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) - return; + return 0; /* * It's not the end of the world if we don't get @@ -1463,7 +1475,7 @@ static void trace_save_cmdline(struct task_struct *tsk) * so if we miss here, then better luck next time. */ if (!arch_spin_trylock(&trace_cmdline_lock)) - return; + return 0; idx = map_pid_to_cmdline[tsk->pid]; if (idx == NO_CMDLINE_MAP) { @@ -1488,6 +1500,8 @@ static void trace_save_cmdline(struct task_struct *tsk) memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN); arch_spin_unlock(&trace_cmdline_lock); + + return 1; } void trace_find_cmdline(int pid, char comm[]) @@ -1529,9 +1543,8 @@ void tracing_record_cmdline(struct task_struct *tsk) if (!__this_cpu_read(trace_cmdline_save)) return; - __this_cpu_write(trace_cmdline_save, false); - - trace_save_cmdline(tsk); + if (trace_save_cmdline(tsk)) + __this_cpu_write(trace_cmdline_save, false); } void @@ -4161,17 +4174,19 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) * * Anyway, this is really very primitive wakeup. */ -void poll_wait_pipe(struct trace_iterator *iter) +int poll_wait_pipe(struct trace_iterator *iter) { set_current_state(TASK_INTERRUPTIBLE); /* sleep for 100 msecs, and try again. */ schedule_timeout(HZ / 10); + return 0; } /* Must be called with trace_types_lock mutex held. */ static int tracing_wait_pipe(struct file *filp) { struct trace_iterator *iter = filp->private_data; + int ret; while (trace_empty(iter)) { @@ -4181,10 +4196,13 @@ static int tracing_wait_pipe(struct file *filp) mutex_unlock(&iter->mutex); - iter->trace->wait_pipe(iter); + ret = iter->trace->wait_pipe(iter); mutex_lock(&iter->mutex); + if (ret) + return ret; + if (signal_pending(current)) return -EINTR; @@ -5112,8 +5130,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, goto out_unlock; } mutex_unlock(&trace_types_lock); - iter->trace->wait_pipe(iter); + ret = iter->trace->wait_pipe(iter); mutex_lock(&trace_types_lock); + if (ret) { + size = ret; + goto out_unlock; + } if (signal_pending(current)) { size = -EINTR; goto out_unlock; @@ -5325,8 +5347,10 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, goto out; } mutex_unlock(&trace_types_lock); - iter->trace->wait_pipe(iter); + ret = iter->trace->wait_pipe(iter); mutex_lock(&trace_types_lock); + if (ret) + goto out; if (signal_pending(current)) { ret = -EINTR; goto out; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 02b592f2d4b7..c8bd809cbd1c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -336,7 +336,7 @@ struct tracer { void (*stop)(struct trace_array *tr); void (*open)(struct trace_iterator *iter); void (*pipe_open)(struct trace_iterator *iter); - void (*wait_pipe)(struct trace_iterator *iter); + int (*wait_pipe)(struct trace_iterator *iter); void (*close)(struct trace_iterator *iter); void (*pipe_close)(struct trace_iterator *iter); ssize_t (*read)(struct trace_iterator *iter, @@ -552,7 +552,7 @@ void trace_init_global_iter(struct trace_iterator *iter); void tracing_iter_reset(struct trace_iterator *iter, int cpu); -void poll_wait_pipe(struct trace_iterator *iter); +int poll_wait_pipe(struct trace_iterator *iter); void tracing_sched_switch_trace(struct trace_array *tr, struct task_struct *prev, diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 26dc348332b7..57b67b1f24d1 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -59,13 +59,14 @@ u64 notrace trace_clock(void) /* * trace_jiffy_clock(): Simply use jiffies as a clock counter. + * Note that this use of jiffies_64 is not completely safe on + * 32-bit systems. But the window is tiny, and the effect if + * we are affected is that we will have an obviously bogus + * timestamp on a trace event - i.e. not life threatening. */ u64 notrace trace_clock_jiffies(void) { - u64 jiffy = jiffies - INITIAL_JIFFIES; - - /* Return nsecs */ - return (u64)jiffies_to_usecs(jiffy) * 1000ULL; + return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES); } /* diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7b16d40bd64d..e4c4efc4ba0d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -439,6 +439,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file) list_del(&file->list); remove_subsystem(file->system); + free_event_filter(file->filter); kmem_cache_free(file_cachep, file); } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 8efbb69b04f0..6d6a789e579e 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec) data->ops->func(data); continue; } - filter = rcu_dereference(data->filter); + filter = rcu_dereference_sched(data->filter); if (filter && !filter_match_preds(filter, rec)) continue; if (data->cmd_ops->post_trigger) { diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 759d5e004517..7e3cd7aaec83 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -313,7 +313,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */ @@ -360,7 +360,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) int syscall_nr; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */ @@ -567,7 +567,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) return; @@ -641,7 +641,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) return; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 79e52d93860b..bd0c9b133b54 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -728,9 +728,15 @@ static int uprobe_buffer_enable(void) static void uprobe_buffer_disable(void) { + int cpu; + BUG_ON(!mutex_is_locked(&event_mutex)); if (--uprobe_buffer_refcnt == 0) { + for_each_possible_cpu(cpu) + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, + cpu)->buf); + free_percpu(uprobe_cpu_buffer); uprobe_cpu_buffer = NULL; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 031cc5655a51..63630aef3bd3 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -641,6 +641,9 @@ static int tracepoint_module_coming(struct module *mod) struct tp_module *tp_mod, *iter; int ret = 0; + if (!mod->num_tracepoints) + return 0; + /* * We skip modules that taint the kernel, especially those with different * module headers (for forced load), to make sure we don't cause a crash. @@ -684,6 +687,9 @@ static int tracepoint_module_going(struct module *mod) { struct tp_module *pos; + if (!mod->num_tracepoints) + return 0; + mutex_lock(&tracepoints_mutex); tracepoint_update_probe_range(mod->tracepoints_ptrs, mod->tracepoints_ptrs + mod->num_tracepoints); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index dd06439b9c84..80a57afd8647 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -152,7 +152,7 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) /* Find the matching extent */ extents = map->nr_extents; - smp_read_barrier_depends(); + smp_rmb(); for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; @@ -176,7 +176,7 @@ static u32 map_id_down(struct uid_gid_map *map, u32 id) /* Find the matching extent */ extents = map->nr_extents; - smp_read_barrier_depends(); + smp_rmb(); for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; @@ -199,7 +199,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id) /* Find the matching extent */ extents = map->nr_extents; - smp_read_barrier_depends(); + smp_rmb(); for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; @@ -615,9 +615,8 @@ static ssize_t map_write(struct file *file, const char __user *buf, * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write - * order and smp_read_barrier_depends() is guaranteed that we - * don't have crazy architectures returning stale data. - * + * order and smp_rmb() is guaranteed that we don't have crazy + * architectures returning stale data. */ mutex_lock(&id_map_mutex); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 4431610f049a..c9b6f01bf853 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -524,10 +524,8 @@ static void update_timers_all_cpus(void) int cpu; get_online_cpus(); - preempt_disable(); for_each_online_cpu(cpu) update_timers(cpu); - preempt_enable(); put_online_cpus(); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 193e977a10ea..b4defdecec8a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1909,6 +1909,12 @@ static void send_mayday(struct work_struct *work) /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { + /* + * If @pwq is for an unbound wq, its base ref may be put at + * any time due to an attribute change. Pin @pwq until the + * rescuer is done with it. + */ + get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); } @@ -2391,6 +2397,7 @@ static int rescuer_thread(void *__rescuer) struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; + bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); @@ -2402,11 +2409,15 @@ static int rescuer_thread(void *__rescuer) repeat: set_current_state(TASK_INTERRUPTIBLE); - if (kthread_should_stop()) { - __set_current_state(TASK_RUNNING); - rescuer->task->flags &= ~PF_WQ_WORKER; - return 0; - } + /* + * By the time the rescuer is requested to stop, the workqueue + * shouldn't have any work pending, but @wq->maydays may still have + * pwq(s) queued. This can happen by non-rescuer workers consuming + * all the work items before the rescuer got to them. Go through + * @wq->maydays processing before acting on should_stop so that the + * list is always empty on exit. + */ + should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ spin_lock_irq(&wq_mayday_lock); @@ -2438,6 +2449,12 @@ repeat: process_scheduled_works(rescuer); /* + * Put the reference grabbed by send_mayday(). @pool won't + * go away while we're holding its lock. + */ + put_pwq(pwq); + + /* * Leave this pool. If keep_working() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. @@ -2452,6 +2469,12 @@ repeat: spin_unlock_irq(&wq_mayday_lock); + if (should_stop) { + __set_current_state(TASK_RUNNING); + rescuer->task->flags &= ~PF_WQ_WORKER; + return 0; + } + /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); @@ -3392,6 +3415,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) } } + dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } @@ -4093,7 +4117,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, if (!pwq) { pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", wq->name); - goto out_unlock; + mutex_lock(&wq->mutex); + goto use_dfl_pwq; } /* @@ -5002,7 +5027,7 @@ static void __init wq_numa_init(void) BUG_ON(!tbl); for_each_node(node) - BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, + BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { diff --git a/lib/assoc_array.c b/lib/assoc_array.c index c0b1007011e1..2404d03e251a 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -1723,11 +1723,13 @@ ascend_old_tree: shortcut = assoc_array_ptr_to_shortcut(ptr); slot = shortcut->parent_slot; cursor = shortcut->back_pointer; + if (!cursor) + goto gc_complete; } else { slot = node->parent_slot; cursor = ptr; } - BUG_ON(!ptr); + BUG_ON(!cursor); node = assoc_array_ptr_to_node(cursor); slot++; goto continue_node; @@ -1735,7 +1737,7 @@ ascend_old_tree: gc_complete: edit->set[0].to = new_root; assoc_array_apply_edit(edit); - edit->array->nr_leaves_on_tree = nr_leaves_on_tree; + array->nr_leaves_on_tree = nr_leaves_on_tree; return 0; enomem: diff --git a/lib/bitmap.c b/lib/bitmap.c index 06f7e4fe8d2d..e5c4ebe586ba 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -131,7 +131,9 @@ void __bitmap_shift_right(unsigned long *dst, lower = src[off + k]; if (left && off + k == lim - 1) lower &= mask; - dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem; + dst[k] = lower >> rem; + if (rem) + dst[k] |= upper << (BITS_PER_LONG - rem); if (left && k == lim - 1) dst[k] &= mask; } @@ -172,7 +174,9 @@ void __bitmap_shift_left(unsigned long *dst, upper = src[k]; if (left && k == lim - 1) upper &= (1UL << left) - 1; - dst[k + off] = lower >> (BITS_PER_LONG - rem) | upper << rem; + dst[k + off] = upper << rem; + if (rem) + dst[k + off] |= lower >> (BITS_PER_LONG - rem); if (left && k + off == lim - 1) dst[k + off] &= (1UL << left) - 1; } diff --git a/lib/btree.c b/lib/btree.c index f9a484676cb6..4264871ea1a0 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -198,6 +198,7 @@ EXPORT_SYMBOL_GPL(btree_init); void btree_destroy(struct btree_head *head) { + mempool_free(head->node, head->mempool); mempool_destroy(head->mempool); head->mempool = NULL; } diff --git a/lib/idr.c b/lib/idr.c index bfe4db4e165f..674c30bc2ed0 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -250,7 +250,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa, id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1; /* if already at the top layer, we need to grow */ - if (id >= 1 << (idp->layers * IDR_BITS)) { + if (id > idr_max(idp->layers)) { *starting_id = id; return -EAGAIN; } @@ -827,12 +827,10 @@ void *idr_replace(struct idr *idp, void *ptr, int id) if (!p) return ERR_PTR(-EINVAL); - n = (p->layer+1) * IDR_BITS; - - if (id >= (1 << n)) + if (id > idr_max(p->layer + 1)) return ERR_PTR(-EINVAL); - n -= IDR_BITS; + n = p->layer * IDR_BITS; while ((n > 0) && p) { p = p->ary[(id >> n) & IDR_MASK]; n -= IDR_BITS; diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index df6839e3ce08..7a85967060a5 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -72,6 +72,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize) len = *ip++; for (; len == 255; length += 255) len = *ip++; + if (unlikely(length > (size_t)(length + len))) + goto _output_error; length += len; } @@ -106,6 +108,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize) if (length == ML_MASK) { for (; *ip == 255; length += 255) ip++; + if (unlikely(length > (size_t)(length + *ip))) + goto _output_error; length += *ip++; } @@ -155,7 +159,7 @@ static int lz4_uncompress(const char *source, char *dest, int osize) /* write overflow error detected */ _output_error: - return (int) (-(((char *)ip) - source)); + return -1; } static int lz4_uncompress_unknownoutputsize(const char *source, char *dest, @@ -188,6 +192,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest, int s = 255; while ((ip < iend) && (s == 255)) { s = *ip++; + if (unlikely(length > (size_t)(length + s))) + goto _output_error; length += s; } } @@ -228,6 +234,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest, if (length == ML_MASK) { while (ip < iend) { int s = *ip++; + if (unlikely(length > (size_t)(length + s))) + goto _output_error; length += s; if (s == 255) continue; @@ -280,7 +288,7 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest, /* write overflow error detected */ _output_error: - return (int) (-(((char *) ip) - source)); + return -1; } int lz4_decompress(const unsigned char *src, size_t *src_len, diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 569985d522d5..a1c387f6afba 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -25,6 +25,16 @@ #define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun #define TEST_LB(m_pos) if ((m_pos) < out) goto lookbehind_overrun +/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base + * count without overflowing an integer. The multiply will overflow when + * multiplying 255 by more than MAXINT/255. The sum will overflow earlier + * depending on the base count. Since the base count is taken from a u8 + * and a few bits, it is safe to assume that it will always be lower than + * or equal to 2*255, thus we can always prevent any overflow by accepting + * two less 255 steps. See Documentation/lzo.txt for more information. + */ +#define MAX_255_COUNT ((((size_t)~0) / 255) - 2) + int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, unsigned char *out, size_t *out_len) { @@ -55,12 +65,19 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, if (t < 16) { if (likely(state == 0)) { if (unlikely(t == 0)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; NEED_IP(1); } - t += 15 + *ip++; + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 15 + *ip++; } t += 3; copy_literal_run: @@ -116,12 +133,19 @@ copy_literal_run: } else if (t >= 32) { t = (t & 31) + (3 - 1); if (unlikely(t == 2)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; NEED_IP(1); } - t += 31 + *ip++; + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 31 + *ip++; NEED_IP(2); } m_pos = op - 1; @@ -134,12 +158,19 @@ copy_literal_run: m_pos -= (t & 8) << 11; t = (t & 7) + (3 - 1); if (unlikely(t == 2)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; NEED_IP(1); } - t += 7 + *ip++; + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 7 + *ip++; NEED_IP(2); } next = get_unaligned_le16(ip); diff --git a/lib/nlattr.c b/lib/nlattr.c index 18eca7809b08..10ad042d01be 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -201,8 +201,8 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, } if (unlikely(rem > 0)) - printk(KERN_WARNING "netlink: %d bytes leftover after parsing " - "attributes.\n", rem); + pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n", + rem, current->comm); err = 0; errout: @@ -303,9 +303,15 @@ int nla_memcmp(const struct nlattr *nla, const void *data, */ int nla_strcmp(const struct nlattr *nla, const char *str) { - int len = strlen(str) + 1; - int d = nla_len(nla) - len; + int len = strlen(str); + char *buf = nla_data(nla); + int attrlen = nla_len(nla); + int d; + if (attrlen > 0 && buf[attrlen - 1] == '\0') + attrlen--; + + d = attrlen - len; if (d == 0) d = memcmp(nla_data(nla), str, len); diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 8280a5dd1727..7dd33577b905 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -169,7 +169,7 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb, struct percpu_counter *fbc; compute_batch_value(); - if (action != CPU_DEAD) + if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) return NOTIFY_OK; cpu = (unsigned long)hcpu; diff --git a/lib/plist.c b/lib/plist.c index 1ebc95f7a46f..0f2084d30798 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -134,6 +134,46 @@ void plist_del(struct plist_node *node, struct plist_head *head) plist_check_head(head); } +/** + * plist_requeue - Requeue @node at end of same-prio entries. + * + * This is essentially an optimized plist_del() followed by + * plist_add(). It moves an entry already in the plist to + * after any other same-priority entries. + * + * @node: &struct plist_node pointer - entry to be moved + * @head: &struct plist_head pointer - list head + */ +void plist_requeue(struct plist_node *node, struct plist_head *head) +{ + struct plist_node *iter; + struct list_head *node_next = &head->node_list; + + plist_check_head(head); + BUG_ON(plist_head_empty(head)); + BUG_ON(plist_node_empty(node)); + + if (node == plist_last(head)) + return; + + iter = plist_next(node); + + if (node->prio != iter->prio) + return; + + plist_del(node, head); + + plist_for_each_continue(iter, head) { + if (node->prio != iter->prio) { + node_next = &iter->node_list; + break; + } + } + list_add_tail(&node->node_list, node_next); + + plist_check_head(head); +} + #ifdef CONFIG_DEBUG_PI_LIST #include <linux/sched.h> #include <linux/module.h> @@ -170,6 +210,14 @@ static void __init plist_test_check(int nr_expect) BUG_ON(prio_pos->prio_list.next != &first->prio_list); } +static void __init plist_test_requeue(struct plist_node *node) +{ + plist_requeue(node, &test_head); + + if (node != plist_last(&test_head)) + BUG_ON(node->prio == plist_next(node)->prio); +} + static int __init plist_test(void) { int nr_expect = 0, i, loop; @@ -193,6 +241,10 @@ static int __init plist_test(void) nr_expect--; } plist_test_check(nr_expect); + if (!plist_node_empty(test_node + i)) { + plist_test_requeue(test_node + i); + plist_test_check(nr_expect); + } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { diff --git a/lib/string.c b/lib/string.c index e5878de4f101..43d0781daf47 100644 --- a/lib/string.c +++ b/lib/string.c @@ -586,6 +586,22 @@ void *memset(void *s, int c, size_t count) EXPORT_SYMBOL(memset); #endif +/** + * memzero_explicit - Fill a region of memory (e.g. sensitive + * keying data) with 0s. + * @s: Pointer to the start of the area. + * @count: The size of the area. + * + * memzero_explicit() doesn't need an arch-specific version as + * it just invokes the one of memset() implicitly. + */ +void memzero_explicit(void *s, size_t count) +{ + memset(s, 0, count); + OPTIMIZER_HIDE_VAR(s); +} +EXPORT_SYMBOL(memzero_explicit); + #ifndef __HAVE_ARCH_MEMCPY /** * memcpy - Copy one area of memory to another diff --git a/mm/Kconfig b/mm/Kconfig index 2888024e0b0a..0862816bb455 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -263,6 +263,9 @@ config MIGRATION pages as migration can relocate pages to satisfy a huge page allocation instead of reclaiming. +config ARCH_ENABLE_HUGEPAGE_MIGRATION + boolean + config PHYS_ADDR_T_64BIT def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT @@ -577,3 +580,18 @@ config PGTABLE_MAPPING You can check speed with zsmalloc benchmark: https://github.com/spartacus06/zsmapbench + +config MAX_STACK_SIZE_MB + int "Maximum user stack size for 32-bit processes (MB)" + default 80 + range 8 256 if METAG + range 8 2048 + depends on STACK_GROWSUP && (!64BIT || COMPAT) + help + This is the maximum stack size in Megabytes in the VM layout of 32-bit + user processes when the stack grows upwards (currently only on parisc + and metag arch). The stack will be located at the highest memory + address minus the given value, unless the RLIMIT_STACK hard limit is + changed to a smaller value in which case that is used. + + A sane initial value is 80 MB. diff --git a/mm/Makefile b/mm/Makefile index 310c90a09264..c561f1f6bca0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,7 +16,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o balloon_compaction.o \ + compaction.o balloon_compaction.o vmacache.o \ interval_tree.o list_lru.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index ce682f7a4f29..09d9591b7708 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -288,13 +288,19 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. + * + * We have to be careful not to postpone flush work if it is scheduled for + * earlier. Thus we use queue_delayed_work(). */ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); + spin_lock_bh(&bdi->wb_lock); + if (test_bit(BDI_registered, &bdi->state)) + queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); + spin_unlock_bh(&bdi->wb_lock); } /* @@ -307,9 +313,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi) spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); - - /* bdi_list is now unused, clear it to mark @bdi dying */ - INIT_LIST_HEAD(&bdi->bdi_list); } int bdi_register(struct backing_dev_info *bdi, struct device *parent, @@ -360,6 +363,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) */ bdi_remove_from_list(bdi); + /* Make sure nobody queues further work */ + spin_lock_bh(&bdi->wb_lock); + clear_bit(BDI_registered, &bdi->state); + spin_unlock_bh(&bdi->wb_lock); + /* * Drain work list and shutdown the delayed_work. At this point, * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi diff --git a/mm/compaction.c b/mm/compaction.c index 918577595ea8..5e38e5706f62 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -217,21 +217,12 @@ static inline bool compact_trylock_irqsave(spinlock_t *lock, /* Returns true if the page is within a block suitable for migration to */ static bool suitable_migration_target(struct page *page) { - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_RESERVE) - return false; - - if (is_migrate_isolate(migratetype)) - return false; - - /* If the page is a large free page, then allow migration */ + /* If the page is a large free page, then disallow migration */ if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; + return false; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(migratetype)) + if (migrate_async_suitable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ @@ -253,6 +244,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, struct page *cursor, *valid_page = NULL; unsigned long flags; bool locked = false; + bool checked_pageblock = false; cursor = pfn_to_page(blockpfn); @@ -284,8 +276,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; /* Recheck this is a suitable migration target under lock */ - if (!strict && !suitable_migration_target(page)) - break; + if (!strict && !checked_pageblock) { + /* + * We need to check suitability of pageblock only once + * and this isolate_freepages_block() is called with + * pageblock range, so just check once is sufficient. + */ + checked_pageblock = true; + if (!suitable_migration_target(page)) + break; + } /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) @@ -460,12 +460,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; - isolate_mode_t mode = 0; struct lruvec *lruvec; unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; bool skipped_async_unsuitable = false; + const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) | + (unevictable ? ISOLATE_UNEVICTABLE : 0); /* * Ensure that there are not too many pages isolated from the LRU @@ -487,7 +488,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, cond_resched(); for (; low_pfn < end_pfn; low_pfn++) { /* give a chance to irqs before checking need_resched() */ - if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) { + if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) { if (should_release_lock(&zone->lru_lock)) { spin_unlock_irqrestore(&zone->lru_lock, flags); locked = false; @@ -526,8 +527,25 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, /* If isolation recently failed, do not retry */ pageblock_nr = low_pfn >> pageblock_order; - if (!isolation_suitable(cc, page)) - goto next_pageblock; + if (last_pageblock_nr != pageblock_nr) { + int mt; + + last_pageblock_nr = pageblock_nr; + if (!isolation_suitable(cc, page)) + goto next_pageblock; + + /* + * For async migration, also only scan in MOVABLE + * blocks. Async migration is optimistic to see if + * the minimum amount of work satisfies the allocation + */ + mt = get_pageblock_migratetype(page); + if (!cc->sync && !migrate_async_suitable(mt)) { + cc->finished_update_migrate = true; + skipped_async_unsuitable = true; + goto next_pageblock; + } + } /* * Skip if free. page_order cannot be used without zone->lock @@ -537,18 +555,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; /* - * For async migration, also only scan in MOVABLE blocks. Async - * migration is optimistic to see if the minimum amount of work - * satisfies the allocation - */ - if (!cc->sync && last_pageblock_nr != pageblock_nr && - !migrate_async_suitable(get_pageblock_migratetype(page))) { - cc->finished_update_migrate = true; - skipped_async_unsuitable = true; - goto next_pageblock; - } - - /* * Check may be lockless but that's ok as we recheck later. * It's possible to migrate LRU pages and balloon pages * Skip any other type of page @@ -557,11 +563,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, if (unlikely(balloon_page_movable(page))) { if (locked && balloon_page_isolate(page)) { /* Successfully isolated */ - cc->finished_update_migrate = true; - list_add(&page->lru, migratelist); - cc->nr_migratepages++; - nr_isolated++; - goto check_compact_cluster; + goto isolate_success; } } continue; @@ -584,6 +586,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } + /* + * Migration will fail if an anonymous page is pinned in memory, + * so avoid taking lru_lock and isolating it unnecessarily in an + * admittedly racy check. + */ + if (!page_mapping(page) && + page_count(page) > page_mapcount(page)) + continue; + /* Check if it is ok to still hold the lock */ locked = compact_checklock_irqsave(&zone->lru_lock, &flags, locked, cc); @@ -598,12 +609,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (!cc->sync) - mode |= ISOLATE_ASYNC_MIGRATE; - - if (unevictable) - mode |= ISOLATE_UNEVICTABLE; - lruvec = mem_cgroup_page_lruvec(page, zone); /* Try isolate the page */ @@ -613,13 +618,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, VM_BUG_ON_PAGE(PageTransCompound(page), page); /* Successfully isolated */ - cc->finished_update_migrate = true; del_page_from_lru_list(page, lruvec, page_lru(page)); + +isolate_success: + cc->finished_update_migrate = true; list_add(&page->lru, migratelist); cc->nr_migratepages++; nr_isolated++; -check_compact_cluster: /* Avoid isolating too much */ if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) { ++low_pfn; @@ -630,7 +636,6 @@ check_compact_cluster: next_pageblock: low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1; - last_pageblock_nr = pageblock_nr; } acct_isolated(zone, locked, cc); @@ -666,16 +671,20 @@ static void isolate_freepages(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn; + unsigned long high_pfn, low_pfn, pfn, z_end_pfn; int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; /* * Initialise the free scanner. The starting point is where we last - * scanned from (or the end of the zone if starting). The low point - * is the end of the pageblock the migration scanner is using. + * successfully isolated from, zone-cached value, or the end of the + * zone when isolating for the first time. We need this aligned to + * the pageblock boundary, because we do pfn -= pageblock_nr_pages + * in the for loop. + * The low boundary is the end of the pageblock the migration scanner + * is using. */ - pfn = cc->free_pfn; + pfn = cc->free_pfn & ~(pageblock_nr_pages-1); low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); /* @@ -695,6 +704,7 @@ static void isolate_freepages(struct zone *zone, for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages; pfn -= pageblock_nr_pages) { unsigned long isolated; + unsigned long end_pfn; /* * This can iterate a massively long zone without finding any @@ -729,13 +739,10 @@ static void isolate_freepages(struct zone *zone, isolated = 0; /* - * As pfn may not start aligned, pfn+pageblock_nr_page - * may cross a MAX_ORDER_NR_PAGES boundary and miss - * a pfn_valid check. Ensure isolate_freepages_block() - * only scans within a pageblock + * Take care when isolating in last pageblock of a zone which + * ends in the middle of a pageblock. */ - end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); - end_pfn = min(end_pfn, z_end_pfn); + end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn); isolated = isolate_freepages_block(cc, pfn, end_pfn, freelist, false); nr_freepages += isolated; @@ -1186,6 +1193,7 @@ static void compact_node(int nid) struct compact_control cc = { .order = -1, .sync = true, + .ignore_skip_hint = true, }; __compact_pgdat(NODE_DATA(nid), &cc); diff --git a/mm/filemap.c b/mm/filemap.c index 7a13f6ac5421..c2cc7c95eff1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -192,9 +192,11 @@ static int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + if (test_bit(AS_ENOSPC, &mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) + if (test_bit(AS_EIO, &mapping->flags) && + test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } @@ -520,10 +522,10 @@ struct page *__page_cache_alloc(gfp_t gfp) if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = alloc_pages_exact_node(n, gfp, 0); - } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } diff --git a/mm/frontswap.c b/mm/frontswap.c index 1b24bdcb3197..c30eec536f03 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -327,15 +327,12 @@ EXPORT_SYMBOL(__frontswap_invalidate_area); static unsigned long __frontswap_curr_pages(void) { - int type; unsigned long totalpages = 0; struct swap_info_struct *si = NULL; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) totalpages += atomic_read(&si->frontswap_pages); - } return totalpages; } @@ -347,11 +344,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, int si_frontswap_pages; unsigned long total_pages_to_unuse = total; unsigned long pages = 0, pages_to_unuse = 0; - int type; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) { si_frontswap_pages = atomic_read(&si->frontswap_pages); if (total_pages_to_unuse < si_frontswap_pages) { pages = pages_to_unuse = total_pages_to_unuse; @@ -366,7 +361,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, } vm_unacct_memory(pages); *unused = pages_to_unuse; - *swapid = type; + *swapid = si->type; ret = 0; break; } @@ -413,7 +408,7 @@ void frontswap_shrink(unsigned long target_pages) /* * we don't want to hold swap_lock while doing a very * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_list.head each time + * so restart scan from swap_active_head each time */ spin_lock(&swap_lock); ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1546655a2d78..331faa5c0d5e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -199,7 +199,7 @@ retry: preempt_disable(); if (cmpxchg(&huge_zero_page, NULL, zero_page)) { preempt_enable(); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); goto retry; } @@ -231,7 +231,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -1611,16 +1611,23 @@ pmd_t *page_check_address_pmd(struct page *page, enum page_check_address_pmd_flag flag, spinlock_t **ptl) { + pgd_t *pgd; + pud_t *pud; pmd_t *pmd; if (address & ~HPAGE_PMD_MASK) return NULL; - pmd = mm_find_pmd(mm, address); - if (!pmd) + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) return NULL; + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return NULL; + pmd = pmd_offset(pud, address); + *ptl = pmd_lock(mm, pmd); - if (pmd_none(*pmd)) + if (!pmd_present(*pmd)) goto unlock; if (pmd_page(*pmd) != page) goto unlock; @@ -1812,21 +1819,24 @@ static int __split_huge_page_map(struct page *page, if (pmd) { pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); + if (pmd_write(*pmd)) + BUG_ON(page_mapcount(page) != 1); haddr = address; for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { pte_t *pte, entry; BUG_ON(PageCompound(page+i)); + /* + * Note that pmd_numa is not transferred deliberately + * to avoid any possibility that pte_numa leaks to + * a PROT_NONE VMA by accident. + */ entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (!pmd_write(*pmd)) entry = pte_wrprotect(entry); - else - BUG_ON(page_mapcount(page) != 1); if (!pmd_young(*pmd)) entry = pte_mkold(entry); - if (pmd_numa(*pmd)) - entry = pte_mknuma(entry); pte = pte_offset_map(&_pmd, haddr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, haddr, pte, entry); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c01cb9fedb18..67d0c175efcf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -540,7 +540,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, goto err; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = huge_zonelist(vma, address, htlb_alloc_mask(h), &mpol, &nodemask); @@ -562,7 +562,7 @@ retry_cpuset: } mpol_cond_put(mpol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -1134,6 +1134,7 @@ static void return_unused_surplus_pages(struct hstate *h, while (nr_pages--) { if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) break; + cond_resched_lock(&hugetlb_lock); } } @@ -1509,6 +1510,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, while (min_count < persistent_huge_pages(h)) { if (!free_pool_huge_page(h, nodes_allowed, 0)) break; + cond_resched_lock(&hugetlb_lock); } while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) @@ -2069,6 +2071,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->max_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2122,6 +2127,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->nr_overcommit_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2147,6 +2155,8 @@ out: void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return; seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" @@ -2163,6 +2173,8 @@ void hugetlb_report_meminfo(struct seq_file *m) int hugetlb_report_node_meminfo(int nid, char *buf) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return 0; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" @@ -2177,6 +2189,9 @@ void hugetlb_show_meminfo(void) struct hstate *h; int nid; + if (!hugepages_supported()) + return; + for_each_node_state(nid, N_MEMORY) for_each_hstate(h) pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", @@ -2336,6 +2351,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, update_mmu_cache(vma, address, ptep); } +static int is_hugetlb_entry_migration(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_migration_entry(swp)) + return 1; + else + return 0; +} + +static int is_hugetlb_entry_hwpoisoned(pte_t pte) +{ + swp_entry_t swp; + + if (huge_pte_none(pte) || pte_present(pte)) + return 0; + swp = pte_to_swp_entry(pte); + if (non_swap_entry(swp) && is_hwpoison_entry(swp)) + return 1; + else + return 0; +} int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) @@ -2375,7 +2415,24 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); - if (!huge_pte_none(huge_ptep_get(src_pte))) { + entry = huge_ptep_get(src_pte); + if (huge_pte_none(entry)) { /* skip none entry */ + ; + } else if (unlikely(is_hugetlb_entry_migration(entry) || + is_hugetlb_entry_hwpoisoned(entry))) { + swp_entry_t swp_entry = pte_to_swp_entry(entry); + + if (is_write_migration_entry(swp_entry) && cow) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&swp_entry); + entry = swp_entry_to_pte(swp_entry); + set_huge_pte_at(src, addr, src_pte, entry); + } + set_huge_pte_at(dst, addr, dst_pte, entry); + } else { if (cow) huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_ptep_get(src_pte); @@ -2394,32 +2451,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, return ret; } -static int is_hugetlb_entry_migration(pte_t pte) -{ - swp_entry_t swp; - - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_migration_entry(swp)) - return 1; - else - return 0; -} - -static int is_hugetlb_entry_hwpoisoned(pte_t pte) -{ - swp_entry_t swp; - - if (huge_pte_none(pte) || pte_present(pte)) - return 0; - swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_hwpoison_entry(swp)) - return 1; - else - return 0; -} - void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) diff --git a/mm/internal.h b/mm/internal.h index 29e1e761f9eb..3e910000fda4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -370,5 +370,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ +#define ALLOC_FAIR 0x100 /* fair zone allocation */ #endif /* __MM_INTERNAL_H */ diff --git a/mm/memblock.c b/mm/memblock.c index 39a31e7f0045..0739dc1b4095 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -183,8 +183,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid) { - int ret; - phys_addr_t kernel_end; + phys_addr_t kernel_end, ret; /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5b6b0039f725..b58d4fbe6c48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -292,6 +292,9 @@ struct mem_cgroup { /* vmpressure notifications */ struct vmpressure vmpressure; + /* css_online() has been completed */ + int initialized; + /* * the counter to account for mem+swap usage. */ @@ -1127,9 +1130,21 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) - return mem_cgroup_from_css(next_css); + struct mem_cgroup *memcg = mem_cgroup_from_css(next_css); + + if (next_css == &root->css) + return memcg; + + if (css_tryget(next_css)) { + /* + * Make sure the memcg is initialized: + * mem_cgroup_css_online() orders the the + * initialization against setting the flag. + */ + if (smp_load_acquire(&memcg->initialized)) + return memcg; + css_put(next_css); + } prev_css = next_css; goto skip_node; @@ -5670,8 +5685,12 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) { struct mem_cgroup_eventfd_list *ev; + spin_lock(&memcg_oom_lock); + list_for_each_entry(ev, &memcg->oom_notify, list) eventfd_signal(ev->eventfd, 1); + + spin_unlock(&memcg_oom_lock); return 0; } @@ -6534,6 +6553,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); + int ret; if (css->cgroup->id > MEM_CGROUP_ID_MAX) return -ENOSPC; @@ -6570,7 +6590,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) } mutex_unlock(&memcg_create_mutex); - return memcg_init_kmem(memcg, &mem_cgroup_subsys); + ret = memcg_init_kmem(memcg, &mem_cgroup_subsys); + if (ret) + return ret; + + /* + * Make sure the memcg is initialized: mem_cgroup_iter() + * orders reading memcg->initialized against its callers + * reading the memcg members. + */ + smp_store_release(&memcg->initialized, 1); + + return 0; } /* diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 90002ea43638..33365e9ce6a7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, #endif si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; - if ((flags & MF_ACTION_REQUIRED) && t == current) { + if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { si.si_code = BUS_MCEERR_AR; - ret = force_sig_info(SIGBUS, &si, t); + ret = force_sig_info(SIGBUS, &si, current); } else { /* * Don't use force here, it's convenient if the signal @@ -384,20 +384,51 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, } } -static int task_early_kill(struct task_struct *tsk) +/* + * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO) + * on behalf of the thread group. Return task_struct of the (first found) + * dedicated thread if found, and return NULL otherwise. + * + * We already hold read_lock(&tasklist_lock) in the caller, so we don't + * have to call rcu_read_lock/unlock() in this function. + */ +static struct task_struct *find_early_kill_thread(struct task_struct *tsk) { + struct task_struct *t; + + for_each_thread(tsk, t) + if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY)) + return t; + return NULL; +} + +/* + * Determine whether a given process is "early kill" process which expects + * to be signaled when some page under the process is hwpoisoned. + * Return task_struct of the dedicated thread (main thread unless explicitly + * specified) if the process is "early kill," and otherwise returns NULL. + */ +static struct task_struct *task_early_kill(struct task_struct *tsk, + int force_early) +{ + struct task_struct *t; if (!tsk->mm) - return 0; - if (tsk->flags & PF_MCE_PROCESS) - return !!(tsk->flags & PF_MCE_EARLY); - return sysctl_memory_failure_early_kill; + return NULL; + if (force_early) + return tsk; + t = find_early_kill_thread(tsk); + if (t) + return t; + if (sysctl_memory_failure_early_kill) + return tsk; + return NULL; } /* * Collect processes when the error hit an anonymous page. */ static void collect_procs_anon(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -412,16 +443,17 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; if (!page_mapped_in_vma(page, vma)) continue; - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -432,7 +464,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, * Collect processes when the error hit a file mapped page. */ static void collect_procs_file(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -442,10 +474,10 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, read_lock(&tasklist_lock); for_each_process(tsk) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* @@ -455,8 +487,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * Assume applications who requested early kill want * to be informed of all such data corruptions. */ - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -469,7 +501,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * First preallocate one tokill structure outside the spin locks, * so that we can kill at least one process reasonably reliable. */ -static void collect_procs(struct page *page, struct list_head *tokill) +static void collect_procs(struct page *page, struct list_head *tokill, + int force_early) { struct to_kill *tk; @@ -480,9 +513,9 @@ static void collect_procs(struct page *page, struct list_head *tokill) if (!tk) return; if (PageAnon(page)) - collect_procs_anon(page, tokill, &tk); + collect_procs_anon(page, tokill, &tk, force_early); else - collect_procs_file(page, tokill, &tk); + collect_procs_file(page, tokill, &tk, force_early); kfree(tk); } @@ -967,7 +1000,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(ppage, &tokill); + collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED); ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) @@ -1085,15 +1118,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags) return 0; } else if (PageHuge(hpage)) { /* - * Check "just unpoisoned", "filter hit", and - * "race with other subpage." + * Check "filter hit" and "race with other subpage." */ lock_page(hpage); - if (!PageHWPoison(hpage) - || (hwpoison_filter(p) && TestClearPageHWPoison(p)) - || (p != hpage && TestSetPageHWPoison(hpage))) { - atomic_long_sub(nr_pages, &num_poisoned_pages); - return 0; + if (PageHWPoison(hpage)) { + if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) + || (p != hpage && TestSetPageHWPoison(hpage))) { + atomic_long_sub(nr_pages, &num_poisoned_pages); + unlock_page(hpage); + return 0; + } } set_page_hwpoison_huge_page(hpage); res = dequeue_hwpoisoned_huge_page(hpage); @@ -1156,6 +1190,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (!PageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); + atomic_long_sub(nr_pages, &num_poisoned_pages); + put_page(hpage); res = 0; goto out; } diff --git a/mm/memory.c b/mm/memory.c index 22dfa617bddb..492e36f27f43 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1120,7 +1120,7 @@ again: addr) != page->index) { pte_t ptfile = pgoff_to_pte(page->index); if (pte_soft_dirty(ptent)) - pte_file_mksoft_dirty(ptfile); + ptfile = pte_file_mksoft_dirty(ptfile); set_pte_at(mm, addr, pte, ptfile); } if (PageAnon(page)) @@ -1929,12 +1929,17 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags) { struct vm_area_struct *vma; + vm_flags_t vm_flags; int ret; vma = find_extend_vma(mm, address); if (!vma || address < vma->vm_start) return -EFAULT; + vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ; + if (!(vm_flags & vma->vm_flags)) + return -EFAULT; + ret = handle_mm_fault(mm, vma, address, fault_flags); if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) @@ -3751,9 +3756,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, } } - /* THP should already have been handled */ - BUG_ON(pmd_numa(*pmd)); - /* * Use __pte_alloc instead of pte_alloc_map, because we can't * run pte_offset_map on the pmd, if an huge pmd could diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ae3c8f3595d4..796c7e6cf93b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -526,9 +526,13 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, int nid; struct page *page; spinlock_t *ptl; + pte_t entry; ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd); - page = pte_page(huge_ptep_get((pte_t *)pmd)); + entry = huge_ptep_get((pte_t *)pmd); + if (!pte_present(entry)) + goto unlock; + page = pte_page(entry); nid = page_to_nid(page); if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) goto unlock; @@ -649,19 +653,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, * @nodes and @flags,) it's isolated and queued to the pagelist which is * passed via @private.) */ -static struct vm_area_struct * +static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) { - int err; - struct vm_area_struct *first, *vma, *prev; - + int err = 0; + struct vm_area_struct *vma, *prev; - first = find_vma(mm, start); - if (!first) - return ERR_PTR(-EFAULT); + vma = find_vma(mm, start); + if (!vma) + return -EFAULT; prev = NULL; - for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { + for (; vma && vma->vm_start < end; vma = vma->vm_next) { unsigned long endvma = vma->vm_end; if (endvma > end) @@ -671,9 +674,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, if (!(flags & MPOL_MF_DISCONTIG_OK)) { if (!vma->vm_next && vma->vm_end < end) - return ERR_PTR(-EFAULT); + return -EFAULT; if (prev && prev->vm_end < vma->vm_start) - return ERR_PTR(-EFAULT); + return -EFAULT; } if (flags & MPOL_MF_LAZY) { @@ -687,15 +690,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, err = queue_pages_pgd_range(vma, start, endvma, nodes, flags, private); - if (err) { - first = ERR_PTR(err); + if (err) break; - } } next: prev = vma; } - return first; + return err; } /* @@ -1180,16 +1181,17 @@ out: /* * Allocate a new page for page migration based on vma policy. - * Start assuming that page is mapped by vma pointed to by @private. + * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { - struct vm_area_struct *vma = (struct vm_area_struct *)private; + struct vm_area_struct *vma; unsigned long uninitialized_var(address); + vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) @@ -1219,7 +1221,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { return NULL; } @@ -1229,7 +1231,6 @@ static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { - struct vm_area_struct *vma; struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; @@ -1295,11 +1296,9 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - vma = queue_pages_range(mm, start, end, nmask, + err = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - - err = PTR_ERR(vma); /* maybe ... */ - if (!IS_ERR(vma)) + if (!err) err = mbind_range(mm, start, end, new); if (!err) { @@ -1307,9 +1306,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, - MIGRATE_SYNC, MR_MEMPOLICY_MBIND); + nr_failed = migrate_pages(&pagelist, new_page, + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); } @@ -1899,7 +1897,7 @@ int node_random(const nodemask_t *maskp) * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * - * Must be protected by get_mems_allowed() + * Must be protected by read_mems_allowed_begin() */ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, @@ -2063,7 +2061,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, retry_cpuset: pol = get_vma_policy(current, vma, addr); - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; @@ -2071,7 +2069,7 @@ retry_cpuset: nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2081,7 +2079,7 @@ retry_cpuset: policy_nodemask(gfp, pol)); if (unlikely(mpol_needs_cond_ref(pol))) __mpol_put(pol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } @@ -2115,7 +2113,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) pol = &default_policy; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* * No reference counting needed for current->mempolicy @@ -2128,7 +2126,7 @@ retry_cpuset: policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2172,7 +2170,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) } else *new = *old; - rcu_read_lock(); if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); if (new->flags & MPOL_F_REBINDING) @@ -2180,7 +2177,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) else mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE); } - rcu_read_unlock(); atomic_set(&new->refcnt, 1); return new; } diff --git a/mm/migrate.c b/mm/migrate.c index bed48809e5d0..13f47fbe3550 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -148,8 +148,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); if (pte_swp_soft_dirty(*ptep)) pte = pte_mksoft_dirty(pte); + + /* Recheck VMA as permissions can change since migration started */ if (is_write_migration_entry(entry)) - pte = pte_mkwrite(pte); + pte = maybe_mkwrite(pte, vma); + #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { pte = pte_mkhuge(pte); diff --git a/mm/mlock.c b/mm/mlock.c index 4e1a68162285..b1eb53634005 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -79,6 +79,7 @@ void clear_page_mlock(struct page *page) */ void mlock_vma_page(struct page *page) { + /* Serialize with page migration */ BUG_ON(!PageLocked(page)); if (!TestSetPageMlocked(page)) { @@ -174,6 +175,7 @@ unsigned int munlock_vma_page(struct page *page) unsigned int nr_pages; struct zone *zone = page_zone(page); + /* For try_to_munlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); /* diff --git a/mm/mmap.c b/mm/mmap.c index 20ff0c33274c..dfe90657a6db 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> @@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, prev->vm_next = next = vma->vm_next; if (next) next->vm_prev = prev; - if (mm->mmap_cache == vma) - mm->mmap_cache = prev; + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -1989,34 +1991,33 @@ EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = NULL; + struct rb_node *rb_node; + struct vm_area_struct *vma; /* Check the cache first. */ - /* (Cache hit rate is typically around 35%.) */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { - struct rb_node *rb_node; + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; - rb_node = mm->mm_rb.rb_node; - vma = NULL; + rb_node = mm->mm_rb.rb_node; + vma = NULL; - while (rb_node) { - struct vm_area_struct *vma_tmp; - - vma_tmp = rb_entry(rb_node, - struct vm_area_struct, vm_rb); - - if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - break; - rb_node = rb_node->rb_left; - } else - rb_node = rb_node->rb_right; - } - if (vma) - mm->mmap_cache = vma; + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; } + + if (vma) + vmacache_update(addr, vma); return vma; } @@ -2388,7 +2389,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - mm->mmap_cache = NULL; /* Kill the cache. */ + + /* Kill the cache */ + vmacache_invalidate(mm); } /* diff --git a/mm/mremap.c b/mm/mremap.c index 0843feb66f3d..05f1180e9f21 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma, break; if (pmd_trans_huge(*old_pmd)) { int err = 0; - if (extent == HPAGE_PMD_SIZE) + if (extent == HPAGE_PMD_SIZE) { + VM_BUG_ON(vma->vm_file || !vma->anon_vma); + /* See comment in move_ptes() */ + if (need_rmap_locks) + anon_vma_lock_write(vma->anon_vma); err = move_huge_pmd(vma, new_vma, old_addr, new_addr, old_end, old_pmd, new_pmd); + if (need_rmap_locks) + anon_vma_unlock_write(vma->anon_vma); + } if (err > 0) { need_flush = true; continue; diff --git a/mm/nommu.c b/mm/nommu.c index 8740213b1647..3ee4f74fbfbe 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -15,6 +15,7 @@ #include <linux/export.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/file.h> @@ -768,16 +769,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) */ static void delete_vma_from_mm(struct vm_area_struct *vma) { + int i; struct address_space *mapping; struct mm_struct *mm = vma->vm_mm; + struct task_struct *curr = current; kenter("%p", vma); protect_vma(vma, 0); mm->map_count--; - if (mm->mmap_cache == vma) - mm->mmap_cache = NULL; + for (i = 0; i < VMACACHE_SIZE; i++) { + /* if the vma is cached, invalidate the entire cache */ + if (curr->vmacache[i] == vma) { + vmacache_invalidate(curr->mm); + break; + } + } /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -825,8 +833,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma; /* check the cache first */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (vma && vma->vm_start <= addr && vma->vm_end > addr) + vma = vmacache_find(mm, addr); + if (likely(vma)) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -835,7 +843,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) if (vma->vm_start > addr) return NULL; if (vma->vm_end > addr) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -874,8 +882,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, unsigned long end = addr + len; /* check the cache first */ - vma = mm->mmap_cache; - if (vma && vma->vm_start == addr && vma->vm_end == end) + vma = vmacache_find_exact(mm, addr, end); + if (vma) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -886,7 +894,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, if (vma->vm_start > addr) return NULL; if (vma->vm_end == end) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 3291e82d4352..171c00f2e495 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -406,6 +406,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, dump_tasks(memcg, nodemask); } +/* + * Number of OOM killer invocations (including memcg OOM killer). + * Primarily used by PM freezer to check for potential races with + * OOM killed frozen task. + */ +static atomic_t oom_kills = ATOMIC_INIT(0); + +int oom_kills_count(void) +{ + return atomic_read(&oom_kills); +} + +void note_oom_kill(void) +{ + atomic_inc(&oom_kills); +} + #define K(x) ((x) << (PAGE_SHIFT-10)) /* * Must be called while holding a reference to p, which will be released upon diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7106cb1aca8e..9f45f87a5859 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -593,14 +593,14 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ -static inline long long pos_ratio_polynom(unsigned long setpoint, +static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; - x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, + x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, limit - setpoint + 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; @@ -842,7 +842,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, x_intercept = bdi_setpoint + span; if (bdi_dirty < x_intercept - span / 4) { - pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty), + pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty), x_intercept - bdi_setpoint + 1); } else pos_ratio /= 4; @@ -1324,9 +1324,9 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); if (bdi_bg_thresh) - *bdi_bg_thresh = div_u64((u64)*bdi_thresh * - background_thresh, - dirty_thresh); + *bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh * + background_thresh, + dirty_thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need @@ -2398,7 +2398,7 @@ int test_clear_page_writeback(struct page *page) return ret; } -int test_set_page_writeback(struct page *page) +int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); int ret; @@ -2423,9 +2423,10 @@ int test_set_page_writeback(struct page *page) radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_TOWRITE); + if (!keep_write) + radix_tree_tag_clear(&mapping->page_tree, + page_index(page), + PAGECACHE_TAG_TOWRITE); spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestSetPageWriteback(page); @@ -2436,7 +2437,7 @@ int test_set_page_writeback(struct page *page) return ret; } -EXPORT_SYMBOL(test_set_page_writeback); +EXPORT_SYMBOL(__test_set_page_writeback); /* * Return true if any of the pages in the mapping are marked with the diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3bac76ae4b30..7b2611a055a7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -69,6 +69,7 @@ /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); +#define MIN_PERCPU_PAGELIST_FRACTION (8) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); @@ -798,9 +799,21 @@ void __init init_cma_reserved_pageblock(struct page *page) set_page_count(p, 0); } while (++p, --i); - set_page_refcounted(page); set_pageblock_migratetype(page, MIGRATE_CMA); - __free_pages(page, pageblock_order); + + if (pageblock_order >= MAX_ORDER) { + i = pageblock_nr_pages; + p = page; + do { + set_page_refcounted(p); + __free_pages(p, MAX_ORDER - 1); + p += MAX_ORDER_NR_PAGES; + } while (i -= MAX_ORDER_NR_PAGES); + } else { + set_page_refcounted(page); + __free_pages(page, pageblock_order); + } + adjust_managed_page_count(page, pageblock_nr_pages); } #endif @@ -1238,15 +1251,6 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) } local_irq_restore(flags); } -static bool gfp_thisnode_allocation(gfp_t gfp_mask) -{ - return (gfp_mask & GFP_THISNODE) == GFP_THISNODE; -} -#else -static bool gfp_thisnode_allocation(gfp_t gfp_mask) -{ - return false; -} #endif /* @@ -1583,12 +1587,7 @@ again: get_pageblock_migratetype(page)); } - /* - * NOTE: GFP_THISNODE allocations do not partake in the kswapd - * aging protocol, so they can't be fair. - */ - if (!gfp_thisnode_allocation(gfp_flags)) - __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); @@ -1870,7 +1869,7 @@ static void __paginginit init_zone_allows_reclaim(int nid) { int i; - for_each_online_node(i) + for_each_node_state(i, N_MEMORY) if (node_distance(nid, i) <= RECLAIM_DISTANCE) node_set(i, NODE_DATA(nid)->reclaim_nodes); else @@ -1954,23 +1953,12 @@ zonelist_scan: * zone size to ensure fair page aging. The zone a * page was allocated in should have no effect on the * time the page has in memory before being reclaimed. - * - * Try to stay in local zones in the fastpath. If - * that fails, the slowpath is entered, which will do - * another pass starting with the local zones, but - * ultimately fall back to remote zones that do not - * partake in the fairness round-robin cycle of this - * zonelist. - * - * NOTE: GFP_THISNODE allocations do not partake in - * the kswapd aging protocol, so they can't be fair. */ - if ((alloc_flags & ALLOC_WMARK_LOW) && - !gfp_thisnode_allocation(gfp_mask)) { - if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) - continue; + if (alloc_flags & ALLOC_FAIR) { if (!zone_local(preferred_zone, zone)) continue; + if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0) + continue; } /* * When allocating a page cache page for writing, we @@ -2208,6 +2196,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, } /* + * PM-freezer should be notified that there might be an OOM killer on + * its way to kill and wake somebody up. This is too early and we might + * end up not killing anything but false positives are acceptable. + * See freeze_processes. + */ + note_oom_kill(); + + /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if * we're still under heavy pressure. @@ -2408,37 +2404,45 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static void prepare_slowpath(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, - enum zone_type high_zoneidx, - struct zone *preferred_zone) +static void reset_alloc_batches(struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) { struct zoneref *z; struct zone *zone; for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { - if (!(gfp_mask & __GFP_NO_KSWAPD)) - wakeup_kswapd(zone, order, zone_idx(preferred_zone)); /* * Only reset the batches of zones that were actually - * considered in the fast path, we don't want to - * thrash fairness information for zones that are not + * considered in the fairness pass, we don't want to + * trash fairness information for zones that are not * actually part of this zonelist's round-robin cycle. */ if (!zone_local(preferred_zone, zone)) continue; mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - - low_wmark_pages(zone) - - zone_page_state(zone, NR_ALLOC_BATCH)); + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); } } +static void wake_all_kswapds(unsigned int order, + struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) +{ + struct zoneref *z; + struct zone *zone; + + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) + wakeup_kswapd(zone, order, zone_idx(preferred_zone)); +} + static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2447,20 +2451,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (!wait) { + if (atomic) { /* - * Not worth trying to allocate harder for - * __GFP_NOMEMALLOC even if it can't schedule. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (!(gfp_mask & __GFP_NOMEMALLOC)) alloc_flags |= ALLOC_HARDER; /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed_softwall(). */ alloc_flags &= ~ALLOC_CPUSET; } else if (unlikely(rt_task(current)) && !in_interrupt()) @@ -2522,12 +2526,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, * allowed per node queues are empty and that nodes are * over allocated. */ - if (gfp_thisnode_allocation(gfp_mask)) + if (IS_ENABLED(CONFIG_NUMA) && + (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; restart: - prepare_slowpath(gfp_mask, order, zonelist, - high_zoneidx, preferred_zone); + if (!(gfp_mask & __GFP_NO_KSWAPD)) + wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone); /* * OK, we're below the kswapd watermark and have kicked background @@ -2711,7 +2716,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); unsigned int cpuset_mems_cookie; - int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET; + int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; struct mem_cgroup *memcg = NULL; gfp_mask &= gfp_allowed_mask; @@ -2739,7 +2744,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, return NULL; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* The preferred zone is used for statistics later */ first_zones_zonelist(zonelist, high_zoneidx, @@ -2752,12 +2757,29 @@ retry_cpuset: if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; #endif +retry: /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, alloc_flags, preferred_zone, migratetype); if (unlikely(!page)) { /* + * The first pass makes sure allocations are spread + * fairly within the local node. However, the local + * node might have free pages left after the fairness + * batches are exhausted, and remote zones haven't + * even been considered yet. Try once more without + * fairness, and include remote zones now, before + * entering the slowpath and waking kswapd: prefer + * spilling to a remote zone over swapping locally. + */ + if (alloc_flags & ALLOC_FAIR) { + reset_alloc_batches(zonelist, high_zoneidx, + preferred_zone); + alloc_flags &= ~ALLOC_FAIR; + goto retry; + } + /* * Runtime PM, block IO and its error handling path * can deadlock because I/O on the device might not * complete. @@ -2777,7 +2799,7 @@ out: * the mask is being updated. If a page allocation is about to fail, * check if the cpuset changed during allocation and if so, retry. */ - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; memcg_kmem_commit_charge(page, memcg, order); @@ -3045,9 +3067,9 @@ bool skip_free_areas_node(unsigned int flags, int nid) goto out; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); out: return ret; } @@ -4105,7 +4127,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) #endif -static int __meminit zone_batchsize(struct zone *zone) +static int zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU int batch; @@ -4221,8 +4243,8 @@ static void pageset_set_high(struct per_cpu_pageset *p, pageset_update(&p->pcp, high, batch); } -static void __meminit pageset_set_high_and_batch(struct zone *zone, - struct per_cpu_pageset *pcp) +static void pageset_set_high_and_batch(struct zone *zone, + struct per_cpu_pageset *pcp) { if (percpu_pagelist_fraction) pageset_set_high(pcp, @@ -4919,7 +4941,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - init_zone_allows_reclaim(nid); + if (node_state(nid, N_MEMORY)) + init_zone_allows_reclaim(nid); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #endif @@ -5647,9 +5670,8 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); __mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - - low_wmark_pages(zone) - - zone_page_state(zone, NR_ALLOC_BATCH)); + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); @@ -5847,23 +5869,38 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - unsigned int cpu; + int old_percpu_pagelist_fraction; int ret; + mutex_lock(&pcp_batch_high_lock); + old_percpu_pagelist_fraction = percpu_pagelist_fraction; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || (ret < 0)) - return ret; + if (!write || ret < 0) + goto out; + + /* Sanity checking to avoid pcp imbalance */ + if (percpu_pagelist_fraction && + percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { + percpu_pagelist_fraction = old_percpu_pagelist_fraction; + ret = -EINVAL; + goto out; + } + + /* No change? */ + if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + goto out; - mutex_lock(&pcp_batch_high_lock); for_each_populated_zone(zone) { - unsigned long high; - high = zone->managed_pages / percpu_pagelist_fraction; + unsigned int cpu; + for_each_possible_cpu(cpu) - pageset_set_high(per_cpu_ptr(zone->pageset, cpu), - high); + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); } +out: mutex_unlock(&pcp_batch_high_lock); - return 0; + return ret; } int hashdist = HASHDIST_DEFAULT; @@ -6006,53 +6043,65 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) * @end_bitidx: The last bit of interest * returns pageblock_bits flags */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) +unsigned long get_pageblock_flags_mask(struct page *page, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long flags = 0; - unsigned long value = 1; + unsigned long pfn, bitidx, word_bitidx; + unsigned long word; zone = page_zone(page); pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (test_bit(bitidx + start_bitidx, bitmap)) - flags |= value; - - return flags; + word = bitmap[word_bitidx]; + bitidx += end_bitidx; + return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; } /** - * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest * @start_bitidx: The first bit of interest * @end_bitidx: The last bit of interest * @flags: The flags to set */ -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx) +void set_pageblock_flags_mask(struct page *page, unsigned long flags, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long value = 1; + unsigned long pfn, bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (flags & value) - __set_bit(bitidx + start_bitidx, bitmap); - else - __clear_bit(bitidx + start_bitidx, bitmap); + bitidx += end_bitidx; + mask <<= (BITS_PER_LONG - bitidx - 1); + flags <<= (BITS_PER_LONG - bitidx - 1); + + word = ACCESS_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } } /* diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index cfd162882c00..0e9a319d5f8d 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -171,6 +171,7 @@ static void free_page_cgroup(void *addr) sizeof(struct page_cgroup) * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); + kmemleak_free(addr); free_pages_exact(addr, table_size); } } diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 3707c71ae4cd..51108165f829 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, int page_start, int page_end) { const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; - unsigned int cpu; + unsigned int cpu, tcpu; int i; for_each_possible_cpu(cpu) { @@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); - if (!*pagep) { - pcpu_free_pages(chunk, pages, populated, - page_start, page_end); - return -ENOMEM; - } + if (!*pagep) + goto err; } } return 0; + +err: + while (--i >= page_start) + __free_page(pages[pcpu_page_idx(cpu, i)]); + + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + for (i = page_start; i < page_end; i++) + __free_page(pages[pcpu_page_idx(tcpu, i)]); + } + return -ENOMEM; } /** @@ -263,6 +272,7 @@ err: __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); } + pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } diff --git a/mm/percpu.c b/mm/percpu.c index 036cfe07050f..a2a54a85f691 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -612,7 +612,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); if (!chunk->map) { - kfree(chunk); + pcpu_mem_free(chunk, pcpu_chunk_struct_size); return NULL; } diff --git a/mm/readahead.c b/mm/readahead.c index 0de2360d65f3..1fa0d6fca556 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -233,14 +233,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, return 0; } +#define MAX_READAHEAD ((512*4096)/PAGE_CACHE_SIZE) /* * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a * sensible upper limit. */ unsigned long max_sane_readahead(unsigned long nr) { - return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE) - + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); + return min(nr, MAX_READAHEAD); } /* diff --git a/mm/rmap.c b/mm/rmap.c index 8fc049f9a5a6..cdbd31285cf6 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma) * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ + might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); @@ -426,8 +427,9 @@ struct anon_vma *page_get_anon_vma(struct page *page) * above cannot corrupt). */ if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; + return NULL; } out: rcu_read_unlock(); @@ -477,9 +479,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page) } if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; - goto out; + return NULL; } /* we pinned the anon_vma, its safe to sleep */ @@ -1322,9 +1324,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, BUG_ON(!page || PageAnon(page)); if (locked_vma) { - mlock_vma_page(page); /* no-op if already mlocked */ - if (page == check_page) + if (page == check_page) { + /* we know we have check_page locked */ + mlock_vma_page(page); ret = SWAP_MLOCK; + } else if (trylock_page(page)) { + /* + * If we can lock the page, perform mlock. + * Otherwise leave the page alone, it will be + * eventually encountered again later. + */ + mlock_vma_page(page); + unlock_page(page); + } continue; /* don't unmap */ } @@ -1544,10 +1556,9 @@ void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; + anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); - - anon_vma_free(anon_vma); } static struct anon_vma *rmap_walk_anon_lock(struct page *page, diff --git a/mm/shmem.c b/mm/shmem.c index 1f18c9d0d93e..f0d698ba7d0f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -80,11 +80,12 @@ static struct vfsmount *shm_mnt; #define SHORT_SYMLINK_LEN 128 /* - * shmem_fallocate and shmem_writepage communicate via inode->i_private - * (with i_mutex making sure that it has only one user at a time): - * we would prefer not to enlarge the shmem inode just for that. + * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * inode->i_private (with i_mutex making sure that it has only one user at + * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { + wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ @@ -533,22 +534,19 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, return; index = start; - for ( ; ; ) { + while (index < end) { cond_resched(); pvec.nr = shmem_find_get_pages_and_swap(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), pvec.pages, indices); if (!pvec.nr) { - if (index == start || unfalloc) + /* If all gone or hole-punch or unfalloc, we're done */ + if (index == start || end != -1) break; + /* But if truncating, restart to make sure all gone */ index = start; continue; } - if ((index == start || unfalloc) && indices[0] >= end) { - shmem_deswap_pagevec(&pvec); - pagevec_release(&pvec); - break; - } mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; @@ -560,8 +558,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (radix_tree_exceptional_entry(page)) { if (unfalloc) continue; - nr_swaps_freed += !shmem_free_swap(mapping, - index, page); + if (shmem_free_swap(mapping, index, page)) { + /* Swap was replaced by page: retry */ + index--; + break; + } + nr_swaps_freed++; continue; } @@ -570,6 +572,11 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (page->mapping == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); + } else { + /* Page was replaced by swap: retry */ + unlock_page(page); + index--; + break; } } unlock_page(page); @@ -824,6 +831,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && + !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; @@ -1298,6 +1306,64 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) int error; int ret = VM_FAULT_LOCKED; + /* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_mutex. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_mutex in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ + if (unlikely(inode->i_private)) { + struct shmem_falloc *shmem_falloc; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT(shmem_fault_wait); + + ret = VM_FAULT_NOPAGE; + if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && + !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + /* It's polite to up mmap_sem if we can */ + up_read(&vma->vm_mm->mmap_sem); + ret = VM_FAULT_RETRY; + } + + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); + + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + spin_unlock(&inode->i_lock); + return ret; + } + spin_unlock(&inode->i_lock); + } + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); @@ -1817,12 +1883,25 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); + + shmem_falloc.waitq = &shmem_falloc_waitq; + shmem_falloc.start = unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ + + spin_lock(&inode->i_lock); + inode->i_private = NULL; + wake_up_all(&shmem_falloc_waitq); + spin_unlock(&inode->i_lock); error = 0; goto out; } @@ -1840,6 +1919,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, goto out; } + shmem_falloc.waitq = NULL; shmem_falloc.start = start; shmem_falloc.next = start; shmem_falloc.nr_falloced = 0; @@ -2063,8 +2143,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); - if (they_are_dirs) + if (they_are_dirs) { + drop_nlink(new_dentry->d_inode); drop_nlink(old_dir); + } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); diff --git a/mm/slab.c b/mm/slab.c index b264214c77ea..0b1c2a58559d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -375,6 +375,39 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #endif +#define OBJECT_FREE (0) +#define OBJECT_ACTIVE (1) + +#ifdef CONFIG_DEBUG_SLAB_LEAK + +static void set_obj_status(struct page *page, int idx, int val) +{ + int freelist_size; + char *status; + struct kmem_cache *cachep = page->slab_cache; + + freelist_size = cachep->num * sizeof(unsigned int); + status = (char *)page->freelist + freelist_size; + status[idx] = val; +} + +static inline unsigned int get_obj_status(struct page *page, int idx) +{ + int freelist_size; + char *status; + struct kmem_cache *cachep = page->slab_cache; + + freelist_size = cachep->num * sizeof(unsigned int); + status = (char *)page->freelist + freelist_size; + + return status[idx]; +} + +#else +static inline void set_obj_status(struct page *page, int idx, int val) {} + +#endif + /* * Do not go above this order unless 0 objects fit into the slab or * overridden on the command line. @@ -565,9 +598,18 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) return cachep->array[smp_processor_id()]; } -static size_t slab_mgmt_size(size_t nr_objs, size_t align) +static size_t calculate_freelist_size(int nr_objs, size_t align) { - return ALIGN(nr_objs * sizeof(unsigned int), align); + size_t freelist_size; + + freelist_size = nr_objs * sizeof(unsigned int); + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + freelist_size += nr_objs * sizeof(char); + + if (align) + freelist_size = ALIGN(freelist_size, align); + + return freelist_size; } /* @@ -600,6 +642,10 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size, nr_objs = slab_size / buffer_size; } else { + int extra_space = 0; + + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + extra_space = sizeof(char); /* * Ignore padding for the initial guess. The padding * is at most @align-1 bytes, and @buffer_size is at @@ -608,17 +654,18 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size, * into the memory allocation when taking the padding * into account. */ - nr_objs = (slab_size) / (buffer_size + sizeof(unsigned int)); + nr_objs = (slab_size) / + (buffer_size + sizeof(unsigned int) + extra_space); /* * This calculated number will be either the right * amount, or one greater than what we want. */ - if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size - > slab_size) + if (calculate_freelist_size(nr_objs, align) > + slab_size - nr_objs * buffer_size) nr_objs--; - mgmt_size = slab_mgmt_size(nr_objs, align); + mgmt_size = calculate_freelist_size(nr_objs, align); } *num = nr_objs; *left_over = slab_size - nr_objs*buffer_size - mgmt_size; @@ -2011,13 +2058,16 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, continue; if (flags & CFLGS_OFF_SLAB) { + size_t freelist_size_per_obj = sizeof(unsigned int); /* * Max number of objs-per-slab for caches which * use off-slab slabs. Needed to avoid a possible * looping condition in cache_grow(). */ + if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK)) + freelist_size_per_obj += sizeof(char); offslab_limit = size; - offslab_limit /= sizeof(unsigned int); + offslab_limit /= freelist_size_per_obj; if (num > offslab_limit) break; @@ -2139,7 +2189,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) int __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { - size_t left_over, freelist_size, ralign; + size_t left_over, freelist_size; + size_t ralign = BYTES_PER_WORD; gfp_t gfp; int err; size_t size = cachep->size; @@ -2172,14 +2223,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) size &= ~(BYTES_PER_WORD - 1); } - /* - * Redzoning and user store require word alignment or possibly larger. - * Note this will be overridden by architecture or caller mandated - * alignment if either is greater than BYTES_PER_WORD. - */ - if (flags & SLAB_STORE_USER) - ralign = BYTES_PER_WORD; - if (flags & SLAB_RED_ZONE) { ralign = REDZONE_ALIGN; /* If redzoning, ensure that the second redzone is suitably @@ -2258,8 +2301,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) if (!cachep->num) return -E2BIG; - freelist_size = - ALIGN(cachep->num * sizeof(unsigned int), cachep->align); + freelist_size = calculate_freelist_size(cachep->num, cachep->align); /* * If the slab has been placed off-slab, and we have enough space then @@ -2272,7 +2314,7 @@ __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 = cachep->num * sizeof(unsigned int); + freelist_size = calculate_freelist_size(cachep->num, 0); #ifdef CONFIG_PAGE_POISONING /* If we're going to use the generic kernel_map_pages() @@ -2589,6 +2631,7 @@ static void cache_init_objs(struct kmem_cache *cachep, if (cachep->ctor) cachep->ctor(objp); #endif + set_obj_status(page, i, OBJECT_FREE); slab_freelist(page)[i] = i; } } @@ -2797,6 +2840,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, BUG_ON(objnr >= cachep->num); BUG_ON(objp != index_to_obj(cachep, page, objnr)); + 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)) { @@ -2930,6 +2974,8 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags, void *objp, unsigned long caller) { + struct page *page; + if (!objp) return objp; if (cachep->flags & SLAB_POISON) { @@ -2960,6 +3006,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, *dbg_redzone1(cachep, objp) = RED_ACTIVE; *dbg_redzone2(cachep, objp) = RED_ACTIVE; } + + page = virt_to_head_page(objp); + set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE); objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); @@ -3073,7 +3122,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); retry: @@ -3131,7 +3180,7 @@ retry: } } - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return obj; } @@ -4201,21 +4250,12 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct page *page) { void *p; - int i, j; + int i; if (n[0] == n[1]) return; for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) { - bool active = true; - - for (j = page->active; j < c->num; j++) { - /* Skip freed item */ - if (slab_freelist(page)[j] == i) { - active = false; - break; - } - } - if (!active) + if (get_obj_status(page, i) != OBJECT_ACTIVE) continue; if (!add_caller(n, (unsigned long)*dbg_userword(c, p))) diff --git a/mm/slab_common.c b/mm/slab_common.c index 1ec3c619ba04..f149e6724411 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -56,7 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, continue; } -#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) +#if !defined(CONFIG_SLUB) /* * For simplicity, we won't check this in the list of memcg * caches. We have control over memcg naming, and if there diff --git a/mm/slub.c b/mm/slub.c index 25f14ad8f817..7611f148ee81 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1684,7 +1684,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1696,19 +1696,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, object = get_partial_node(s, n, c, flags); if (object) { /* - * Return the object even if - * put_mems_allowed indicated that - * the cpuset mems_allowed was - * updated in parallel. It's a - * harmless race between the alloc - * and the cpuset update. + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update */ - put_mems_allowed(cpuset_mems_cookie); return object; } } } - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); #endif return NULL; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 4a7f7e6992b6..beeeef8a1b2d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -51,14 +51,32 @@ atomic_long_t nr_swap_pages; /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; -static atomic_t highest_priority_index = ATOMIC_INIT(-1); static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -struct swap_list_t swap_list = {-1, -1}; +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by get_swap_page() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static PLIST_HEAD(swap_avail_head); +static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -591,6 +609,9 @@ checks: if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; + spin_lock(&swap_avail_lock); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } si->swap_map[offset] = usage; inc_cluster_info_page(si, si->cluster_info, offset); @@ -640,71 +661,65 @@ no_page: swp_entry_t get_swap_page(void) { - struct swap_info_struct *si; + struct swap_info_struct *si, *next; pgoff_t offset; - int type, next; - int wrapped = 0; - int hp_index; - spin_lock(&swap_lock); if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; atomic_long_dec(&nr_swap_pages); - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - hp_index = atomic_xchg(&highest_priority_index, -1); - /* - * highest_priority_index records current highest priority swap - * type which just frees swap entries. If its priority is - * higher than that of swap_list.next swap type, we use it. It - * isn't protected by swap_lock, so it can be an invalid value - * if the corresponding swap type is swapoff. We double check - * the flags here. It's even possible the swap type is swapoff - * and swapon again and its priority is changed. In such rare - * case, low prority swap type might be used, but eventually - * high priority swap will be used after several rounds of - * swap. - */ - if (hp_index != -1 && hp_index != type && - swap_info[type]->prio < swap_info[hp_index]->prio && - (swap_info[hp_index]->flags & SWP_WRITEOK)) { - type = hp_index; - swap_list.next = type; - } - - si = swap_info[type]; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next]->prio)) { - next = swap_list.head; - wrapped++; - } + spin_lock(&swap_avail_lock); +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&si->lock); - if (!si->highest_bit) { + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_list)) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + plist_del(&si->avail_list, &swap_avail_head); spin_unlock(&si->lock); - continue; + goto nextsi; } - if (!(si->flags & SWP_WRITEOK)) { - spin_unlock(&si->lock); - continue; - } - - swap_list.next = next; - spin_unlock(&swap_lock); /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); spin_unlock(&si->lock); if (offset) - return swp_entry(type, offset); - spin_lock(&swap_lock); - next = swap_list.next; + return swp_entry(si->type, offset); + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + spin_lock(&swap_avail_lock); +nextsi: + /* + * if we got here, it's likely that si was almost full before, + * and since scan_swap_map() can drop the si->lock, multiple + * callers probably all tried to get a page from the same si + * and it filled up before we could get one; or, the si filled + * up between us dropping swap_avail_lock and taking si->lock. + * Since we dropped the swap_avail_lock, the swap_avail_head + * list may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over. + */ + if (plist_node_empty(&next->avail_list)) + goto start_over; } + spin_unlock(&swap_avail_lock); + atomic_long_inc(&nr_swap_pages); noswap: - spin_unlock(&swap_lock); return (swp_entry_t) {0}; } @@ -766,27 +781,6 @@ out: return NULL; } -/* - * This swap type frees swap entry, check if it is the highest priority swap - * type which just frees swap entry. get_swap_page() uses - * highest_priority_index to search highest priority swap type. The - * swap_info_struct.lock can't protect us if there are multiple swap types - * active, so we use atomic_cmpxchg. - */ -static void set_highest_priority_index(int type) -{ - int old_hp_index, new_hp_index; - - do { - old_hp_index = atomic_read(&highest_priority_index); - if (old_hp_index != -1 && - swap_info[old_hp_index]->prio >= swap_info[type]->prio) - break; - new_hp_index = type; - } while (atomic_cmpxchg(&highest_priority_index, - old_hp_index, new_hp_index) != old_hp_index); -} - static unsigned char swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -828,9 +822,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; - if (offset > p->highest_bit) + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; p->highest_bit = offset; - set_highest_priority_index(p->type); + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + } atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); @@ -1765,30 +1768,37 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { - int i, prev; - if (prio >= 0) p->prio = prio; else p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + p->avail_list.prio = -p->prio; p->swap_map = swap_map; p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; - /* insert swap space into swap_list: */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { - if (p->prio >= swap_info[i]->prio) - break; - prev = i; - } - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p->type; - else - swap_info[prev]->next = p->type; + assert_spin_locked(&swap_lock); + /* + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * which on removal of any swap_info_struct with an auto-assigned + * (i.e. negative) priority increments the auto-assigned priority + * of any lower-priority swap_info_structs. + * swap_avail_head needs to be priority ordered for get_swap_page(), + * which allocates swap pages from the highest available priority + * swap_info_struct. + */ + plist_add(&p->list, &swap_active_head); + spin_lock(&swap_avail_lock); + plist_add(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -1823,8 +1833,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct address_space *mapping; struct inode *inode; struct filename *pathname; - int i, type, prev; - int err; + int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) @@ -1842,17 +1851,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out; mapping = victim->f_mapping; - prev = -1; spin_lock(&swap_lock); - for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { - p = swap_info[type]; + plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) + if (p->swap_file->f_mapping == mapping) { + found = 1; break; + } } - prev = type; } - if (type < 0) { + if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; @@ -1864,20 +1872,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) - swap_list.head = p->next; - else - swap_info[prev]->next = p->next; - if (type == swap_list.next) { - /* just pick something that's safe... */ - swap_list.next = swap_list.head; - } + spin_lock(&swap_avail_lock); + plist_del(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&p->lock); if (p->prio < 0) { - for (i = p->next; i >= 0; i = swap_info[i]->next) - swap_info[i]->prio = p->prio--; + struct swap_info_struct *si = p; + + plist_for_each_entry_continue(si, &swap_active_head, list) { + si->prio++; + si->list.prio--; + si->avail_list.prio--; + } least_priority++; } + plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; @@ -1885,7 +1894,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); set_current_oom_origin(); - err = try_to_unuse(type, false, 0); /* force all pages to be unused */ + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { @@ -1926,7 +1935,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); - frontswap_invalidate_area(type); + frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); @@ -1935,7 +1944,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account information */ - swap_cgroup_swapoff(type); + swap_cgroup_swapoff(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2142,8 +2151,9 @@ static struct swap_info_struct *alloc_swap_info(void) */ } INIT_LIST_HEAD(&p->first_swap_extent.list); + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; - p->next = -1; spin_unlock(&swap_lock); spin_lock_init(&p->lock); diff --git a/mm/truncate.c b/mm/truncate.c index 353b683afd6e..ac18edc30649 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -20,6 +20,7 @@ #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ #include <linux/cleancache.h> +#include <linux/rmap.h> #include "internal.h" @@ -613,12 +614,67 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { + loff_t oldsize = inode->i_size; + i_size_write(inode, newsize); + if (newsize > oldsize) + pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** + * pagecache_isize_extended - update pagecache after extension of i_size + * @inode: inode for which i_size was extended + * @from: original inode size + * @to: new inode size + * + * Handle extension of inode size either caused by extending truncate or by + * write starting after current i_size. We mark the page straddling current + * i_size RO so that page_mkwrite() is called on the nearest write access to + * the page. This way filesystem can be sure that page_mkwrite() is called on + * the page before user writes to the page via mmap after the i_size has been + * changed. + * + * The function must be called after i_size is updated so that page fault + * coming after we unlock the page will already see the new i_size. + * The function must be called while we still hold i_mutex - this not only + * makes sure i_size is stable but also that userspace cannot observe new + * i_size value before we are prepared to store mmap writes at new inode size. + */ +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) +{ + int bsize = 1 << inode->i_blkbits; + loff_t rounded_from; + struct page *page; + pgoff_t index; + + WARN_ON(to > inode->i_size); + + if (from >= to || bsize == PAGE_CACHE_SIZE) + return; + /* Page straddling @from will not have any hole block created? */ + rounded_from = round_up(from, bsize); + if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1))) + return; + + index = from >> PAGE_CACHE_SHIFT; + page = find_lock_page(inode->i_mapping, index); + /* Page not cached? Nothing to do */ + if (!page) + return; + /* + * See clear_page_dirty_for_io() for details why set_page_dirty() + * is needed. + */ + if (page_mkclean(page)) + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); +} +EXPORT_SYMBOL(pagecache_isize_extended); + +/** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole diff --git a/mm/util.c b/mm/util.c index a24aa22f2473..c1010cb7ca0c 100644 --- a/mm/util.c +++ b/mm/util.c @@ -275,17 +275,14 @@ pid_t vm_is_stack(struct task_struct *task, if (in_group) { struct task_struct *t; - rcu_read_lock(); - if (!pid_alive(task)) - goto done; - t = task; - do { + rcu_read_lock(); + for_each_thread(task, t) { if (vm_is_stack_for_task(t, vma)) { ret = t->pid; goto done; } - } while_each_thread(task, t); + } done: rcu_read_unlock(); } diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 000000000000..1037a3bab505 --- /dev/null +++ b/mm/vmacache.c @@ -0,0 +1,114 @@ +/* + * Copyright (C) 2014 Davidlohr Bueso. + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmacache.h> + +/* + * Flush vma caches for threads that share a given mm. + * + * The operation is safe because the caller holds the mmap_sem + * exclusively and other threads accessing the vma cache will + * have mmap_sem held at least for read, so no extra locking + * is required to maintain the vma cache. + */ +void vmacache_flush_all(struct mm_struct *mm) +{ + struct task_struct *g, *p; + + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * Only flush the vmacache pointers as the + * mm seqnum is already set and curr's will + * be set upon invalidation when the next + * lookup is done. + */ + if (mm == p->mm) + vmacache_flush(p); + } + rcu_read_unlock(); +} + +/* + * This task may be accessing a foreign mm via (for example) + * get_user_pages()->find_vma(). The vmacache is task-local and this + * task's vmacache pertains to a different mm (ie, its own). There is + * nothing we can do here. + * + * Also handle the case where a kernel thread has adopted this mm via use_mm(). + * That kernel thread's vmacache is not applicable to this mm. + */ +static bool vmacache_valid_mm(struct mm_struct *mm) +{ + return current->mm == mm && !(current->flags & PF_KTHREAD); +} + +void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) +{ + if (vmacache_valid_mm(newvma->vm_mm)) + current->vmacache[VMACACHE_HASH(addr)] = newvma; +} + +static bool vmacache_valid(struct mm_struct *mm) +{ + struct task_struct *curr; + + if (!vmacache_valid_mm(mm)) + return false; + + curr = current; + if (mm->vmacache_seqnum != curr->vmacache_seqnum) { + /* + * First attempt will always be invalid, initialize + * the new cache for this task here. + */ + curr->vmacache_seqnum = mm->vmacache_seqnum; + vmacache_flush(curr); + return false; + } + return true; +} + +struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (!vma) + continue; + if (WARN_ON_ONCE(vma->vm_mm != mm)) + break; + if (vma->vm_start <= addr && vma->vm_end > addr) + return vma; + } + + return NULL; +} + +#ifndef CONFIG_MMU +struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (vma && vma->vm_start == start && vma->vm_end == end) + return vma; + } + + return NULL; +} +#endif diff --git a/mm/vmscan.c b/mm/vmscan.c index a9c74b409681..0c0b36e5b4f8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -224,15 +224,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, unsigned long freed = 0; unsigned long long delta; long total_scan; - long max_pass; + long freeable; long nr; long new_nr; int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; - max_pass = shrinker->count_objects(shrinker, shrinkctl); - if (max_pass == 0) + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0) return 0; /* @@ -244,14 +244,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, total_scan = nr; delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; + delta *= freeable; do_div(delta, lru_pages + 1); total_scan += delta; if (total_scan < 0) { printk(KERN_ERR "shrink_slab: %pF negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); - total_scan = max_pass; + total_scan = freeable; } /* @@ -260,26 +260,26 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * shrinkers to return -1 all the time. This results in a large * nr being built up so when a shrink that can do some work * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in + * freeable. This is bad for sustaining a working set in * memory. * * Hence only allow the shrinker to scan the entire cache when * a large delta change is calculated directly. */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); + if (delta < freeable / 4) + total_scan = min(total_scan, freeable / 2); /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; + if (total_scan > freeable * 2) + total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); + freeable, delta, total_scan); /* * Normally, we should not scan less than batch_size objects in one @@ -292,12 +292,12 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater - * than the total number of objects on slab (max_pass), we must be + * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || - total_scan >= max_pass) { + total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); @@ -1144,7 +1144,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, TTU_UNMAP|TTU_IGNORE_ACCESS, &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); return ret; } @@ -1540,19 +1540,18 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * If dirty pages are scanned that are not queued for IO, it * implies that flushers are not keeping up. In this case, flag * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing - * pages from reclaim context. It will forcibly stall in the - * next check. + * pages from reclaim context. */ if (nr_unqueued_dirty == nr_taken) zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY); /* - * In addition, if kswapd scans pages marked marked for - * immediate reclaim and under writeback (nr_immediate), it - * implies that pages are cycling through the LRU faster than + * If kswapd scans pages marked marked for immediate + * reclaim and under writeback (nr_immediate), it implies + * that pages are cycling through the LRU faster than * they are written so also forcibly stall. */ - if (nr_unqueued_dirty == nr_taken || nr_immediate) + if (nr_immediate) congestion_wait(BLK_RW_ASYNC, HZ/10); } @@ -2425,8 +2424,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, unsigned long lru_pages = 0; nodes_clear(shrink->nodes_to_scan); - for_each_zone_zonelist(zone, z, zonelist, - gfp_zone(sc->gfp_mask)) { + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(sc->gfp_mask), sc->nodemask) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; @@ -2502,10 +2501,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; + if (!populated_zone(zone)) + continue; + pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } + /* If there are no reserves (unexpected config) then do not throttle */ + if (!pfmemalloc_reserve) + return true; + wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ @@ -2530,9 +2536,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { + struct zoneref *z; struct zone *zone; - int high_zoneidx = gfp_zone(gfp_mask); - pg_data_t *pgdat; + pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly @@ -2551,10 +2557,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, if (fatal_signal_pending(current)) goto out; - /* Check if the pfmemalloc reserves are ok */ - first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone); - pgdat = zone->zone_pgdat; - if (pfmemalloc_watermark_ok(pgdat)) + /* + * Check if the pfmemalloc reserves are ok by finding the first node + * with a usable ZONE_NORMAL or lower zone. The expectation is that + * GFP_KERNEL will be required for allocating network buffers when + * swapping over the network so ZONE_HIGHMEM is unusable. + * + * Throttling is based on the first usable node and throttled processes + * wait on a queue until kswapd makes progress and wakes them. There + * is an affinity then between processes waking up and where reclaim + * progress has been made assuming the process wakes on the same node. + * More importantly, processes running on remote nodes will not compete + * for remote pfmemalloc reserves and processes on different nodes + * should make reasonable progress. + */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_mask, nodemask) { + if (zone_idx(zone) > ZONE_NORMAL) + continue; + + /* Throttle based on the first usable node */ + pgdat = zone->zone_pgdat; + if (pfmemalloc_watermark_ok(pgdat)) + goto out; + break; + } + + /* If no zone was usable by the allocation flags then do not throttle */ + if (!pgdat) goto out; /* Account for the throttling */ @@ -3285,7 +3315,10 @@ static int kswapd(void *p) } } + tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); current->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + return 0; } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 175273f38cb1..44ebd5c2cd4a 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; + vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 6ee48aac776f..5d56e05d83dd 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -106,56 +106,6 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); -static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) -{ - if (skb_cow(skb, skb_headroom(skb)) < 0) - return NULL; - memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); - skb->mac_header += VLAN_HLEN; - return skb; -} - -struct sk_buff *vlan_untag(struct sk_buff *skb) -{ - struct vlan_hdr *vhdr; - u16 vlan_tci; - - if (unlikely(vlan_tx_tag_present(skb))) { - /* vlan_tci is already set-up so leave this for another time */ - return skb; - } - - skb = skb_share_check(skb, GFP_ATOMIC); - if (unlikely(!skb)) - goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) - goto err_free; - - vhdr = (struct vlan_hdr *) skb->data; - vlan_tci = ntohs(vhdr->h_vlan_TCI); - __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); - - skb_pull_rcsum(skb, VLAN_HLEN); - vlan_set_encap_proto(skb, vhdr); - - skb = vlan_reorder_header(skb); - if (unlikely(!skb)) - goto err_free; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb_reset_mac_len(skb); - - return skb; - -err_free: - kfree_skb(skb); - return NULL; -} -EXPORT_SYMBOL(vlan_untag); - - /* * vlan info and vid list */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 27bfe2f8e2de..1f26a1b8c576 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -524,6 +524,11 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); } +static int vlan_dev_get_lock_subclass(struct net_device *dev) +{ + return vlan_dev_priv(dev)->nest_level; +} + static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .rebuild = vlan_dev_rebuild_header, @@ -559,7 +564,7 @@ static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - int subclass = 0, i; + int i; netif_carrier_off(dev); @@ -608,10 +613,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - if (is_vlan_dev(real_dev)) - subclass = 1; - - vlan_dev_set_lockdep_class(dev, subclass); + vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev)); vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats); if (!vlan_dev_priv(dev)->vlan_pcpu_stats) @@ -633,8 +635,6 @@ static void vlan_dev_uninit(struct net_device *dev) struct vlan_dev_priv *vlan = vlan_dev_priv(dev); int i; - free_percpu(vlan->vlan_pcpu_stats); - vlan->vlan_pcpu_stats = NULL; for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) { while ((pm = vlan->egress_priority_map[i]) != NULL) { vlan->egress_priority_map[i] = pm->next; @@ -791,8 +791,18 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, + .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, }; +static void vlan_dev_free(struct net_device *dev) +{ + struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + + free_percpu(vlan->vlan_pcpu_stats); + vlan->vlan_pcpu_stats = NULL; + free_netdev(dev); +} + void vlan_setup(struct net_device *dev) { ether_setup(dev); @@ -802,7 +812,7 @@ void vlan_setup(struct net_device *dev) dev->tx_queue_len = 0; dev->netdev_ops = &vlan_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = vlan_dev_free; dev->ethtool_ops = &vlan_ethtool_ops; memset(dev->broadcast, 0, ETH_ALEN); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 02806c6b2ff3..0c769cc65f25 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1489,8 +1489,6 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; /* Queue packet (standard) */ - skb->sk = sock; - if (sock_queue_rcv_skb(sock, skb) < 0) goto drop; @@ -1644,7 +1642,6 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr if (!skb) goto out; - skb->sk = sk; skb_reserve(skb, ddp_dl->header_length); skb_reserve(skb, dev->hard_header_len); skb->dev = dev; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 8323bced8e5b..d074d06ce094 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1545,6 +1545,8 @@ out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) batadv_orig_node_free_ref(orig_neigh_node); out: + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); if (router) batadv_neigh_node_free_ref(router); if (router_router) diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index edee50411892..bd8219a7dddf 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -940,8 +940,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, * additional DAT answer may trigger kernel warnings about * a packet coming from the wrong port. */ - if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, - BATADV_NO_FLAGS)) { + if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) { ret = true; goto out; } diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 88df9b1d552d..c46387a46535 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -128,6 +128,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, { struct batadv_frag_table_entry *chain; struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr; + struct batadv_frag_list_entry *frag_entry_last = NULL; struct batadv_frag_packet *frag_packet; uint8_t bucket; uint16_t seqno, hdr_size = sizeof(struct batadv_frag_packet); @@ -180,11 +181,14 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, ret = true; goto out; } + + /* store current entry because it could be the last in list */ + frag_entry_last = frag_entry_curr; } - /* Reached the end of the list, so insert after 'frag_entry_curr'. */ - if (likely(frag_entry_curr)) { - hlist_add_after(&frag_entry_curr->list, &frag_entry_new->list); + /* Reached the end of the list, so insert after 'frag_entry_last'. */ + if (likely(frag_entry_last)) { + hlist_add_after(&frag_entry_last->list, &frag_entry_new->list); chain->size += skb->len - hdr_size; chain->timestamp = jiffies; ret = true; @@ -418,12 +422,13 @@ bool batadv_frag_send_packet(struct sk_buff *skb, struct batadv_neigh_node *neigh_node) { struct batadv_priv *bat_priv; - struct batadv_hard_iface *primary_if; + struct batadv_hard_iface *primary_if = NULL; struct batadv_frag_packet frag_header; struct sk_buff *skb_fragment; unsigned mtu = neigh_node->if_incoming->net_dev->mtu; unsigned header_size = sizeof(frag_header); unsigned max_fragment_size, max_packet_size; + bool ret = false; /* To avoid merge and refragmentation at next-hops we never send * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE @@ -483,7 +488,11 @@ bool batadv_frag_send_packet(struct sk_buff *skb, skb->len + ETH_HLEN); batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - return true; + ret = true; + out_err: - return false; + if (primary_if) + batadv_hardif_free_ref(primary_if); + + return ret; } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 55cf2260d295..36b9ae61f5e8 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -42,8 +42,10 @@ static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node) { - if (atomic_dec_and_test(&gw_node->refcount)) + if (atomic_dec_and_test(&gw_node->refcount)) { + batadv_orig_node_free_ref(gw_node->orig_node); kfree_rcu(gw_node, rcu); + } } static struct batadv_gw_node * @@ -408,9 +410,14 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, if (gateway->bandwidth_down == 0) return; + if (!atomic_inc_not_zero(&orig_node->refcount)) + return; + gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC); - if (!gw_node) + if (!gw_node) { + batadv_orig_node_free_ref(orig_node); return; + } INIT_HLIST_NODE(&gw_node->list); gw_node->orig_node = orig_node; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 853941629dc1..abf612d7d0ae 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -500,12 +500,17 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node, static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) { struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_neigh_node *router; orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + /* this is the last reference to this object */ + router = rcu_dereference_protected(orig_ifinfo->router, true); + if (router) + batadv_neigh_node_free_ref_now(router); kfree(orig_ifinfo); } @@ -697,6 +702,47 @@ free_orig_node: } /** + * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor + * @bat_priv: the bat priv with all the soft interface information + * @neigh: orig node which is to be checked + */ +static void +batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, + struct batadv_neigh_node *neigh) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo; + struct batadv_hard_iface *if_outgoing; + struct hlist_node *node_tmp; + + spin_lock_bh(&neigh->ifinfo_lock); + + /* for all ifinfo objects for this neighinator */ + hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, + &neigh->ifinfo_list, list) { + if_outgoing = neigh_ifinfo->if_outgoing; + + /* always keep the default interface */ + if (if_outgoing == BATADV_IF_DEFAULT) + continue; + + /* don't purge if the interface is not (going) down */ + if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && + (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && + (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + continue; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "neighbor/ifinfo purge: neighbor %pM, iface: %s\n", + neigh->addr, if_outgoing->net_dev->name); + + hlist_del_rcu(&neigh_ifinfo->list); + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + } + + spin_unlock_bh(&neigh->ifinfo_lock); +} + +/** * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which is to be checked @@ -795,6 +841,11 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, hlist_del_rcu(&neigh_node->list); batadv_neigh_node_free_ref(neigh_node); + } else { + /* only necessary if not the whole neighbor is to be + * deleted, but some interface has been removed. + */ + batadv_purge_neigh_ifinfo(bat_priv, neigh_node); } } @@ -852,7 +903,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, { struct batadv_neigh_node *best_neigh_node; struct batadv_hard_iface *hard_iface; - bool changed; + bool changed_ifinfo, changed_neigh; if (batadv_has_timed_out(orig_node->last_seen, 2 * BATADV_PURGE_TIMEOUT)) { @@ -862,10 +913,10 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, jiffies_to_msecs(orig_node->last_seen)); return true; } - changed = batadv_purge_orig_ifinfo(bat_priv, orig_node); - changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node); + changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node); + changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node); - if (!changed) + if (!changed_ifinfo && !changed_neigh) return false; /* first for NULL ... */ @@ -1023,7 +1074,8 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset) bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface); out: - batadv_hardif_free_ref(hard_iface); + if (hard_iface) + batadv_hardif_free_ref(hard_iface); return 0; } diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index adb3ea04adaa..d906016f3c6b 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -420,12 +420,18 @@ static int conn_send(struct l2cap_conn *conn, return 0; } -static void get_dest_bdaddr(struct in6_addr *ip6_daddr, - bdaddr_t *addr, u8 *addr_type) +static u8 get_addr_type_from_eui64(u8 byte) { - u8 *eui64; + /* Is universal(0) or local(1) bit, */ + if (byte & 0x02) + return ADDR_LE_DEV_RANDOM; - eui64 = ip6_daddr->s6_addr + 8; + return ADDR_LE_DEV_PUBLIC; +} + +static void copy_to_bdaddr(struct in6_addr *ip6_daddr, bdaddr_t *addr) +{ + u8 *eui64 = ip6_daddr->s6_addr + 8; addr->b[0] = eui64[7]; addr->b[1] = eui64[6]; @@ -433,16 +439,19 @@ static void get_dest_bdaddr(struct in6_addr *ip6_daddr, addr->b[3] = eui64[2]; addr->b[4] = eui64[1]; addr->b[5] = eui64[0]; +} - addr->b[5] ^= 2; +static void convert_dest_bdaddr(struct in6_addr *ip6_daddr, + bdaddr_t *addr, u8 *addr_type) +{ + copy_to_bdaddr(ip6_daddr, addr); - /* Set universal/local bit to 0 */ - if (addr->b[5] & 1) { - addr->b[5] &= ~1; - *addr_type = ADDR_LE_DEV_PUBLIC; - } else { - *addr_type = ADDR_LE_DEV_RANDOM; - } + /* We need to toggle the U/L bit that we got from IPv6 address + * so that we get the proper address and type of the BD address. + */ + addr->b[5] ^= 0x02; + + *addr_type = get_addr_type_from_eui64(addr->b[5]); } static int header_create(struct sk_buff *skb, struct net_device *netdev, @@ -473,9 +482,11 @@ static int header_create(struct sk_buff *skb, struct net_device *netdev, /* Get destination BT device from skb. * If there is no such peer then discard the packet. */ - get_dest_bdaddr(&hdr->daddr, &addr, &addr_type); + convert_dest_bdaddr(&hdr->daddr, &addr, &addr_type); - BT_DBG("dest addr %pMR type %d", &addr, addr_type); + BT_DBG("dest addr %pMR type %s IP %pI6c", &addr, + addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM", + &hdr->daddr); read_lock_irqsave(&devices_lock, flags); peer = peer_lookup_ba(dev, &addr, addr_type); @@ -556,7 +567,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) } else { unsigned long flags; - get_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type); + convert_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type); eui64_addr = lowpan_cb(skb)->addr.s6_addr + 8; dev = lowpan_dev(netdev); @@ -564,8 +575,10 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) peer = peer_lookup_ba(dev, &addr, addr_type); read_unlock_irqrestore(&devices_lock, flags); - BT_DBG("xmit from %s to %pMR (%pI6c) peer %p", netdev->name, - &addr, &lowpan_cb(skb)->addr, peer); + BT_DBG("xmit %s to %pMR type %s IP %pI6c peer %p", + netdev->name, &addr, + addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM", + &lowpan_cb(skb)->addr, peer); if (peer && peer->conn) err = send_pkt(peer->conn, netdev->dev_addr, @@ -620,13 +633,13 @@ static void set_addr(u8 *eui, u8 *addr, u8 addr_type) eui[6] = addr[1]; eui[7] = addr[0]; - eui[0] ^= 2; - - /* Universal/local bit set, RFC 4291 */ + /* Universal/local bit set, BT 6lowpan draft ch. 3.2.1 */ if (addr_type == ADDR_LE_DEV_PUBLIC) - eui[0] |= 1; + eui[0] &= ~0x02; else - eui[0] &= ~1; + eui[0] |= 0x02; + + BT_DBG("type %d addr %*phC", addr_type, 8, eui); } static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr, @@ -634,7 +647,6 @@ static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr, { netdev->addr_assign_type = NET_ADDR_PERM; set_addr(netdev->dev_addr, addr->b, addr_type); - netdev->dev_addr[0] ^= 2; } static void ifup(struct net_device *netdev) @@ -684,13 +696,6 @@ static int add_peer_conn(struct l2cap_conn *conn, struct lowpan_dev *dev) memcpy(&peer->eui64_addr, (u8 *)&peer->peer_addr.s6_addr + 8, EUI64_ADDR_LEN); - peer->eui64_addr[0] ^= 2; /* second bit-flip (Universe/Local) - * is done according RFC2464 - */ - - raw_dump_inline(__func__, "peer IPv6 address", - (unsigned char *)&peer->peer_addr, 16); - raw_dump_inline(__func__, "peer EUI64 address", peer->eui64_addr, 8); write_lock_irqsave(&devices_lock, flags); INIT_LIST_HEAD(&peer->list); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ba5366c320da..1c6e950b9ae7 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -752,14 +752,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; - /* encrypt must be pending if auth is also pending */ - set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); - if (conn->key_type != 0xff) + + /* If we're already encrypted set the REAUTH_PEND flag, + * otherwise set the ENCRYPT_PEND. + */ + if (conn->link_mode & HCI_LM_ENCRYPT) set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); + else + set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 5f812455a450..2e8c5765e5ea 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -48,6 +48,10 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */ wake_up_bit(&hdev->flags, HCI_INQUIRY); + hci_dev_lock(hdev); + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + hci_dev_unlock(hdev); + hci_conn_check_pending(hdev); } @@ -3006,6 +3010,12 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev, if (!conn) goto unlock; + /* For BR/EDR the necessary steps are taken through the + * auth_complete event. + */ + if (conn->type != LE_LINK) + goto unlock; + if (!ev->status) conn->sec_level = conn->pending_sec_level; @@ -3171,8 +3181,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev, /* If we're not the initiators request authorization to * proceed from user space (mgmt_user_confirm with - * confirm_hint set to 1). */ - if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { + * confirm_hint set to 1). The exception is if neither + * side had MITM in which case we do auto-accept. + */ + if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) && + (loc_mitm || rem_mitm)) { BT_DBG("Confirming auto-accept as acceptor"); confirm_hint = 1; goto confirm; @@ -3593,7 +3606,13 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); - if (ltk->type & HCI_SMP_STK) { + /* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a + * temporary key used to encrypt a connection following + * pairing. It is used during the Encrypted Session Setup to + * distribute the keys. Later, security can be re-established + * using a distributed LTK. + */ + if (ltk->type == HCI_SMP_STK_SLAVE) { list_del(<k->list); kfree(ltk); } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b0ad2c752d73..0007c9e9853a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2608,12 +2608,8 @@ static int l2cap_segment_le_sdu(struct l2cap_chan *chan, BT_DBG("chan %p, msg %p, len %zu", chan, msg, len); - pdu_len = chan->conn->mtu - L2CAP_HDR_SIZE; - - pdu_len = min_t(size_t, pdu_len, chan->remote_mps); - sdu_len = len; - pdu_len -= L2CAP_SDULEN_SIZE; + pdu_len = chan->remote_mps - L2CAP_SDULEN_SIZE; while (len > 0) { if (len <= pdu_len) @@ -7471,9 +7467,9 @@ int __init l2cap_init(void) l2cap_debugfs = debugfs_create_file("l2cap", 0444, bt_debugfs, NULL, &l2cap_debugfs_fops); - debugfs_create_u16("l2cap_le_max_credits", 0466, bt_debugfs, + debugfs_create_u16("l2cap_le_max_credits", 0644, bt_debugfs, &le_max_credits); - debugfs_create_u16("l2cap_le_default_mps", 0466, bt_debugfs, + debugfs_create_u16("l2cap_le_default_mps", 0644, bt_debugfs, &le_default_mps); bt_6lowpan_init(); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d58f76bcebd1..06a7a769737f 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -778,11 +778,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, /*change security for LE channels */ if (chan->scid == L2CAP_CID_ATT) { - if (!conn->hcon->out) { - err = -EINVAL; - break; - } - if (smp_conn_security(conn->hcon, sec.level)) break; sk->sk_state = BT_CONFIG; @@ -1117,7 +1112,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) l2cap_chan_close(chan, 0); lock_sock(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } @@ -1181,13 +1177,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) /* Check for backlog size */ if (sk_acceptq_is_full(parent)) { BT_DBG("backlog full %d", parent->sk_ack_backlog); + release_sock(parent); return NULL; } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC); - if (!sk) + if (!sk) { + release_sock(parent); return NULL; + } bt_sock_reclassify_lock(sk, BTPROTO_L2CAP); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index a03ca3ca91bf..f1ac2a754acc 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2826,8 +2826,13 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev, } if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) { - /* Continue with pairing via SMP */ + /* Continue with pairing via SMP. The hdev lock must be + * released as SMP may try to recquire it for crypto + * purposes. + */ + hci_dev_unlock(hdev); err = smp_user_confirm_reply(conn, mgmt_op, passkey); + hci_dev_lock(hdev); if (!err) err = cmd_complete(sk, hdev->id, mgmt_op, diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index facd8a79c038..b08865111024 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1859,10 +1859,13 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) + if (!skb_linearize(skb)) { s = rfcomm_recv_frame(s, skb); - else + if (!s) + break; + } else { kfree_skb(skb); + } } if (s && (sk->sk_state == BT_CLOSED)) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 3c2d3e4aa2f5..a0050de6f1f1 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -898,7 +898,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how) sk->sk_shutdown = SHUTDOWN_MASK; __rfcomm_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 24fa3964b3c8..316dd4e0af39 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -909,7 +909,8 @@ static int sco_sock_shutdown(struct socket *sock, int how) sco_sock_clear_timer(sk); __sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } @@ -929,7 +930,8 @@ static int sco_sock_release(struct socket *sock) sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) { + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index d0cca3c65f01..04d6348fd530 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -73,7 +73,7 @@ int br_handle_frame_finish(struct sk_buff *skb) goto drop; if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) - goto drop; + goto out; /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; @@ -147,8 +147,8 @@ static int br_handle_local_finish(struct sk_buff *skb) struct net_bridge_port *p = br_port_get_rcu(skb->dev); u16 vid = 0; - br_vlan_get_tag(skb, &vid); - if (p->flags & BR_LEARNING) + /* check if vlan is allowed, to avoid spoofing */ + if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid)) br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false); return 0; /* process further */ } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e74b6d530cb6..e8844d975b32 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -445,6 +445,20 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) 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 (tb[IFLA_ADDRESS]) { + spin_lock_bh(&br->lock); + br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); + spin_unlock_bh(&br->lock); + } + + return register_netdevice(dev); +} + static size_t br_get_link_af_size(const struct net_device *dev) { struct net_port_vlans *pv; @@ -473,6 +487,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = { .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .validate = br_validate, + .newlink = br_dev_newlink, .dellink = br_dev_delete, }; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3ba11bc99b65..4acfc3eef56a 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -302,6 +302,9 @@ struct br_input_skb_cb { int igmp; int mrouters_only; #endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + bool vlan_filtered; +#endif }; #define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb) @@ -581,6 +584,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, struct sk_buff *skb, u16 *vid); bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v, const struct sk_buff *skb); +bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_port_vlans *v, struct sk_buff *skb); @@ -648,6 +652,12 @@ static inline bool br_allowed_egress(struct net_bridge *br, return true; } +static inline bool br_should_learn(struct net_bridge_port *p, + struct sk_buff *skb, u16 *vid) +{ + return true; +} + static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_port_vlans *v, struct sk_buff *skb) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index f23c74b3a953..e1bd2539f9dc 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -125,7 +125,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, { u16 vid; - if (!br->vlan_enabled) + /* If this packet was not filtered at input, let it pass */ + if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* Vlan filter table must be configured at this point. The @@ -163,14 +164,18 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ - if (!br->vlan_enabled) + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; + } /* If there are no vlan in the permitted list, all packets are * rejected. */ if (!v) - return false; + goto drop; + + BR_INPUT_SKB_CB(skb)->vlan_filtered = true; /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have @@ -179,7 +184,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (unlikely(!vlan_tx_tag_present(skb) && (skb->protocol == htons(ETH_P_8021Q) || skb->protocol == htons(ETH_P_8021AD)))) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } @@ -193,7 +198,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, * vlan untagged or priority-tagged traffic belongs to. */ if (pvid == VLAN_N_VID) - return false; + goto drop; /* PVID is set on this port. Any untagged or priority-tagged * ingress frame is considered to belong to this vlan. @@ -216,7 +221,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, /* Frame had a valid vlan tag. See if vlan is allowed */ if (test_bit(*vid, v->vlan_bitmap)) return true; - +drop: + kfree_skb(skb); return false; } @@ -227,7 +233,8 @@ bool br_allowed_egress(struct net_bridge *br, { u16 vid; - if (!br->vlan_enabled) + /* If this packet was not filtered at input, let it pass */ + if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; if (!v) @@ -240,6 +247,35 @@ bool br_allowed_egress(struct net_bridge *br, return false; } +/* Called under RCU */ +bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) +{ + struct net_bridge *br = p->br; + struct net_port_vlans *v; + + /* If filtering was disabled at input, let it pass. */ + if (!br->vlan_enabled) + return true; + + v = rcu_dereference(p->vlan_info); + if (!v) + return false; + + br_vlan_get_tag(skb, vid); + if (!*vid) { + *vid = br_get_pvid(v); + if (*vid == VLAN_N_VID) + return false; + + return true; + } + + if (test_bit(*vid, v->vlan_bitmap)) + return true; + + return false; +} + /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 0e474b13463b..1059ed3bc255 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1044,10 +1044,9 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, if (repl->num_counters && copy_to_user(repl->counters, counterstmp, repl->num_counters * sizeof(struct ebt_counter))) { - ret = -EFAULT; + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ebtables: counters copy to user failed while replacing table\n"); } - else - ret = 0; /* decrease module count and free resources */ EBT_ENTRY_ITERATE(table->entries, table->entries_size, diff --git a/net/can/gw.c b/net/can/gw.c index ac31891967da..050a2110d43f 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -804,7 +804,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh) u8 limhops = 0; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) @@ -893,7 +893,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh) u8 limhops = 0; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 96238ba95f2b..de6662b14e1f 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -13,8 +13,6 @@ #include "auth_x.h" #include "auth_x_protocol.h" -#define TEMP_TICKET_BUF_LEN 256 - static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed); static int ceph_x_is_authenticated(struct ceph_auth_client *ac) @@ -64,7 +62,7 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret, } static int ceph_x_decrypt(struct ceph_crypto_key *secret, - void **p, void *end, void *obuf, size_t olen) + void **p, void *end, void **obuf, size_t olen) { struct ceph_x_encrypt_header head; size_t head_len = sizeof(head); @@ -75,8 +73,14 @@ static int ceph_x_decrypt(struct ceph_crypto_key *secret, return -EINVAL; dout("ceph_x_decrypt len %d\n", len); - ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen, - *p, len); + if (*obuf == NULL) { + *obuf = kmalloc(len, GFP_NOFS); + if (!*obuf) + return -ENOMEM; + olen = len; + } + + ret = ceph_decrypt2(secret, &head, &head_len, *obuf, &olen, *p, len); if (ret) return ret; if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC) @@ -129,139 +133,120 @@ static void remove_ticket_handler(struct ceph_auth_client *ac, kfree(th); } -static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, - struct ceph_crypto_key *secret, - void *buf, void *end) +static int process_one_ticket(struct ceph_auth_client *ac, + struct ceph_crypto_key *secret, + void **p, void *end) { struct ceph_x_info *xi = ac->private; - int num; - void *p = buf; + int type; + u8 tkt_struct_v, blob_struct_v; + struct ceph_x_ticket_handler *th; + void *dbuf = NULL; + void *dp, *dend; + int dlen; + char is_enc; + struct timespec validity; + struct ceph_crypto_key old_key; + void *ticket_buf = NULL; + void *tp, *tpend; + struct ceph_timespec new_validity; + struct ceph_crypto_key new_session_key; + struct ceph_buffer *new_ticket_blob; + unsigned long new_expires, new_renew_after; + u64 new_secret_id; int ret; - char *dbuf; - char *ticket_buf; - u8 reply_struct_v; - dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!dbuf) - return -ENOMEM; + ceph_decode_need(p, end, sizeof(u32) + 1, bad); - ret = -ENOMEM; - ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!ticket_buf) - goto out_dbuf; + type = ceph_decode_32(p); + dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); - ceph_decode_need(&p, end, 1 + sizeof(u32), bad); - reply_struct_v = ceph_decode_8(&p); - if (reply_struct_v != 1) + tkt_struct_v = ceph_decode_8(p); + if (tkt_struct_v != 1) goto bad; - num = ceph_decode_32(&p); - dout("%d tickets\n", num); - while (num--) { - int type; - u8 tkt_struct_v, blob_struct_v; - struct ceph_x_ticket_handler *th; - void *dp, *dend; - int dlen; - char is_enc; - struct timespec validity; - struct ceph_crypto_key old_key; - void *tp, *tpend; - struct ceph_timespec new_validity; - struct ceph_crypto_key new_session_key; - struct ceph_buffer *new_ticket_blob; - unsigned long new_expires, new_renew_after; - u64 new_secret_id; - - ceph_decode_need(&p, end, sizeof(u32) + 1, bad); - - type = ceph_decode_32(&p); - dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); - - tkt_struct_v = ceph_decode_8(&p); - if (tkt_struct_v != 1) - goto bad; - - th = get_ticket_handler(ac, type); - if (IS_ERR(th)) { - ret = PTR_ERR(th); - goto out; - } - /* blob for me */ - dlen = ceph_x_decrypt(secret, &p, end, dbuf, - TEMP_TICKET_BUF_LEN); - if (dlen <= 0) { - ret = dlen; - goto out; - } - dout(" decrypted %d bytes\n", dlen); - dend = dbuf + dlen; - dp = dbuf; + th = get_ticket_handler(ac, type); + if (IS_ERR(th)) { + ret = PTR_ERR(th); + goto out; + } - tkt_struct_v = ceph_decode_8(&dp); - if (tkt_struct_v != 1) - goto bad; + /* blob for me */ + dlen = ceph_x_decrypt(secret, p, end, &dbuf, 0); + if (dlen <= 0) { + ret = dlen; + goto out; + } + dout(" decrypted %d bytes\n", dlen); + dp = dbuf; + dend = dp + dlen; - memcpy(&old_key, &th->session_key, sizeof(old_key)); - ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); - if (ret) - goto out; + tkt_struct_v = ceph_decode_8(&dp); + if (tkt_struct_v != 1) + goto bad; - ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); - ceph_decode_timespec(&validity, &new_validity); - new_expires = get_seconds() + validity.tv_sec; - new_renew_after = new_expires - (validity.tv_sec / 4); - dout(" expires=%lu renew_after=%lu\n", new_expires, - new_renew_after); + memcpy(&old_key, &th->session_key, sizeof(old_key)); + ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); + if (ret) + goto out; - /* ticket blob for service */ - ceph_decode_8_safe(&p, end, is_enc, bad); - tp = ticket_buf; - if (is_enc) { - /* encrypted */ - dout(" encrypted ticket\n"); - dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf, - TEMP_TICKET_BUF_LEN); - if (dlen < 0) { - ret = dlen; - goto out; - } - dlen = ceph_decode_32(&tp); - } else { - /* unencrypted */ - ceph_decode_32_safe(&p, end, dlen, bad); - ceph_decode_need(&p, end, dlen, bad); - ceph_decode_copy(&p, ticket_buf, dlen); + ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); + ceph_decode_timespec(&validity, &new_validity); + new_expires = get_seconds() + validity.tv_sec; + new_renew_after = new_expires - (validity.tv_sec / 4); + dout(" expires=%lu renew_after=%lu\n", new_expires, + new_renew_after); + + /* ticket blob for service */ + ceph_decode_8_safe(p, end, is_enc, bad); + if (is_enc) { + /* encrypted */ + dout(" encrypted ticket\n"); + dlen = ceph_x_decrypt(&old_key, p, end, &ticket_buf, 0); + if (dlen < 0) { + ret = dlen; + goto out; } - tpend = tp + dlen; - dout(" ticket blob is %d bytes\n", dlen); - ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); - blob_struct_v = ceph_decode_8(&tp); - new_secret_id = ceph_decode_64(&tp); - ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); - if (ret) + tp = ticket_buf; + dlen = ceph_decode_32(&tp); + } else { + /* unencrypted */ + ceph_decode_32_safe(p, end, dlen, bad); + ticket_buf = kmalloc(dlen, GFP_NOFS); + if (!ticket_buf) { + ret = -ENOMEM; goto out; - - /* all is well, update our ticket */ - ceph_crypto_key_destroy(&th->session_key); - if (th->ticket_blob) - ceph_buffer_put(th->ticket_blob); - th->session_key = new_session_key; - th->ticket_blob = new_ticket_blob; - th->validity = new_validity; - th->secret_id = new_secret_id; - th->expires = new_expires; - th->renew_after = new_renew_after; - dout(" got ticket service %d (%s) secret_id %lld len %d\n", - type, ceph_entity_type_name(type), th->secret_id, - (int)th->ticket_blob->vec.iov_len); - xi->have_keys |= th->service; + } + tp = ticket_buf; + ceph_decode_need(p, end, dlen, bad); + ceph_decode_copy(p, ticket_buf, dlen); } + tpend = tp + dlen; + dout(" ticket blob is %d bytes\n", dlen); + ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); + blob_struct_v = ceph_decode_8(&tp); + new_secret_id = ceph_decode_64(&tp); + ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); + if (ret) + goto out; + + /* all is well, update our ticket */ + ceph_crypto_key_destroy(&th->session_key); + if (th->ticket_blob) + ceph_buffer_put(th->ticket_blob); + th->session_key = new_session_key; + th->ticket_blob = new_ticket_blob; + th->validity = new_validity; + th->secret_id = new_secret_id; + th->expires = new_expires; + th->renew_after = new_renew_after; + dout(" got ticket service %d (%s) secret_id %lld len %d\n", + type, ceph_entity_type_name(type), th->secret_id, + (int)th->ticket_blob->vec.iov_len); + xi->have_keys |= th->service; - ret = 0; out: kfree(ticket_buf); -out_dbuf: kfree(dbuf); return ret; @@ -270,6 +255,34 @@ bad: goto out; } +static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, + struct ceph_crypto_key *secret, + void *buf, void *end) +{ + void *p = buf; + u8 reply_struct_v; + u32 num; + int ret; + + ceph_decode_8_safe(&p, end, reply_struct_v, bad); + if (reply_struct_v != 1) + return -EINVAL; + + ceph_decode_32_safe(&p, end, num, bad); + dout("%d tickets\n", num); + + while (num--) { + ret = process_one_ticket(ac, secret, &p, end); + if (ret) + return ret; + } + + return 0; + +bad: + return -EINVAL; +} + static int ceph_x_build_authorizer(struct ceph_auth_client *ac, struct ceph_x_ticket_handler *th, struct ceph_x_authorizer *au) @@ -583,13 +596,14 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_x_ticket_handler *th; int ret = 0; struct ceph_x_authorize_reply reply; + void *preply = &reply; void *p = au->reply_buf; void *end = p + sizeof(au->reply_buf); th = get_ticket_handler(ac, au->service); if (IS_ERR(th)) return PTR_ERR(th); - ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply)); + ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply)); if (ret < 0) return ret; if (ret != sizeof(reply)) diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index b703790b4e44..074bb2a5e675 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -292,8 +292,8 @@ static int is_out(const struct crush_map *map, * @outpos: our position in that vector * @tries: number of attempts to make * @recurse_tries: number of attempts to have recursive chooseleaf make - * @local_tries: localized retries - * @local_fallback_tries: localized fallback retries + * @local_retries: localized retries + * @local_fallback_retries: localized fallback retries * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose) * @out2: second output vector for leaf items (if @recurse_to_leaf) */ @@ -304,8 +304,8 @@ static int crush_choose_firstn(const struct crush_map *map, int *out, int outpos, unsigned int tries, unsigned int recurse_tries, - unsigned int local_tries, - unsigned int local_fallback_tries, + unsigned int local_retries, + unsigned int local_fallback_retries, int recurse_to_leaf, int *out2) { @@ -344,9 +344,9 @@ static int crush_choose_firstn(const struct crush_map *map, reject = 1; goto reject; } - if (local_fallback_tries > 0 && + if (local_fallback_retries > 0 && flocal >= (in->size>>1) && - flocal > local_fallback_tries) + flocal > local_fallback_retries) item = bucket_perm_choose(in, x, r); else item = crush_bucket_choose(in, x, r); @@ -393,8 +393,8 @@ static int crush_choose_firstn(const struct crush_map *map, x, outpos+1, 0, out2, outpos, recurse_tries, 0, - local_tries, - local_fallback_tries, + local_retries, + local_fallback_retries, 0, NULL) <= outpos) /* didn't get leaf */ @@ -420,14 +420,14 @@ reject: ftotal++; flocal++; - if (collide && flocal <= local_tries) + if (collide && flocal <= local_retries) /* retry locally a few times */ retry_bucket = 1; - else if (local_fallback_tries > 0 && - flocal <= in->size + local_fallback_tries) + else if (local_fallback_retries > 0 && + flocal <= in->size + local_fallback_retries) /* exhaustive bucket search */ retry_bucket = 1; - else if (ftotal <= tries) + else if (ftotal < tries) /* then retry descent */ retry_descent = 1; else @@ -640,10 +640,18 @@ int crush_do_rule(const struct crush_map *map, __u32 step; int i, j; int numrep; - int choose_tries = map->choose_total_tries; - int choose_local_tries = map->choose_local_tries; - int choose_local_fallback_tries = map->choose_local_fallback_tries; + /* + * the original choose_total_tries value was off by one (it + * counted "retries" and not "tries"). add one. + */ + int choose_tries = map->choose_total_tries + 1; int choose_leaf_tries = 0; + /* + * the local tries values were counted as "retries", though, + * and need no adjustment + */ + int choose_local_retries = map->choose_local_tries; + int choose_local_fallback_retries = map->choose_local_fallback_tries; if ((__u32)ruleno >= map->max_rules) { dprintk(" bad ruleno %d\n", ruleno); @@ -677,12 +685,12 @@ int crush_do_rule(const struct crush_map *map, case CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES: if (curstep->arg1 > 0) - choose_local_tries = curstep->arg1; + choose_local_retries = curstep->arg1; break; case CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES: if (curstep->arg1 > 0) - choose_local_fallback_tries = curstep->arg1; + choose_local_fallback_retries = curstep->arg1; break; case CRUSH_RULE_CHOOSELEAF_FIRSTN: @@ -734,8 +742,8 @@ int crush_do_rule(const struct crush_map *map, o+osize, j, choose_tries, recurse_tries, - choose_local_tries, - choose_local_fallback_tries, + choose_local_retries, + choose_local_fallback_retries, recurse_to_leaf, c+osize); } else { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 30efc5c18622..2e87eecec8f6 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -291,7 +291,11 @@ int ceph_msgr_init(void) if (ceph_msgr_slab_init()) return -ENOMEM; - ceph_msgr_wq = alloc_workqueue("ceph-msgr", 0, 0); + /* + * The number of active work items is limited by the number of + * connections, so leave @max_active at default. + */ + ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_MEM_RECLAIM, 0); if (ceph_msgr_wq) return 0; @@ -557,7 +561,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, return r; } -static int ceph_tcp_sendpage(struct socket *sock, struct page *page, +static int __ceph_tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, bool more) { int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR); @@ -570,6 +574,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, return ret; } +static int ceph_tcp_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, bool more) +{ + int ret; + struct kvec iov; + + /* sendpage cannot properly handle pages with page_count == 0, + * we need to fallback to sendmsg if that's the case */ + if (page_count(page) >= 1) + return __ceph_tcp_sendpage(sock, page, offset, size, more); + + iov.iov_base = kmap(page) + offset; + iov.iov_len = size; + ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more); + kunmap(page); + + return ret; +} /* * Shutdown/close the socket for the given connection. @@ -882,7 +904,7 @@ static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor, BUG_ON(page_count > (int)USHRT_MAX); cursor->page_count = (unsigned short)page_count; BUG_ON(length > SIZE_MAX - cursor->page_offset); - cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE; + cursor->last_piece = cursor->page_offset + cursor->resid <= PAGE_SIZE; } static struct page * diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 2ac9ef35110b..dbcbf5a4707f 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1041,7 +1041,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, if (!m) { pr_info("alloc_msg unknown type %d\n", type); *skip = 1; + } else if (front_len > m->front_alloc_len) { + pr_warning("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n", + front_len, m->front_alloc_len, + (unsigned int)con->peer_name.type, + le64_to_cpu(con->peer_name.num)); + ceph_msg_put(m); + m = ceph_msg_new(type, front_len, GFP_NOFS, false); } + return m; } diff --git a/net/compat.c b/net/compat.c index f50161fb812e..cbc1a2a26587 100644 --- a/net/compat.c +++ b/net/compat.c @@ -85,7 +85,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, { int tot_len; - if (kern_msg->msg_namelen) { + if (kern_msg->msg_name && kern_msg->msg_namelen) { if (mode == VERIFY_READ) { int err = move_addr_to_kernel(kern_msg->msg_name, kern_msg->msg_namelen, @@ -93,10 +93,11 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, if (err < 0) return err; } - if (kern_msg->msg_name) - kern_msg->msg_name = kern_address; - } else + kern_msg->msg_name = kern_address; + } else { kern_msg->msg_name = NULL; + kern_msg->msg_namelen = 0; + } tot_len = iov_from_user_compat_to_kern(kern_iov, (struct compat_iovec __user *)kern_msg->msg_iov, diff --git a/net/core/dev.c b/net/core/dev.c index 45fa2f11f84d..3ed11a555834 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -148,6 +148,9 @@ struct list_head ptype_all __read_mostly; /* Taps */ static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -1207,7 +1210,11 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - call_netdevice_notifiers(NETDEV_CHANGE, dev); + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = 0; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } } @@ -2289,7 +2296,7 @@ EXPORT_SYMBOL(skb_checksum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; + int vlan_depth = skb->mac_len; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { @@ -3547,7 +3554,7 @@ another_round: if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || skb->protocol == cpu_to_be16(ETH_P_8021AD)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto unlock; } @@ -3944,6 +3951,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; + NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); skb->next = napi->gro_list; napi->gro_list = skb; @@ -4050,6 +4058,9 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->vlan_tci = 0; skb->dev = napi->dev; skb->skb_iif = 0; + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); napi->skb = skb; } @@ -4605,6 +4616,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** + * netdev_lower_get_next - Get the next device from the lower neighbour + * list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent from the dev's lower neighbour + * list, starting from iter position. The caller must hold RTNL lock or + * its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + + return lower->dev; +} +EXPORT_SYMBOL(netdev_lower_get_next); + +/** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant @@ -5054,6 +5091,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev, } EXPORT_SYMBOL(netdev_lower_dev_get_private); + +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)) +{ + struct net_device *lower = NULL; + struct list_head *iter; + int max_nest = -1; + int nest; + + ASSERT_RTNL(); + + netdev_for_each_lower_dev(dev, lower, iter) { + nest = dev_get_nest_level(lower, type_check); + if (max_nest < nest) + max_nest = nest; + } + + if (type_check(dev)) + max_nest++; + + return max_nest; +} +EXPORT_SYMBOL(dev_get_nest_level); + static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -5523,7 +5584,7 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); -static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { @@ -6496,6 +6557,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -6505,6 +6569,7 @@ void unregister_netdevice_many(struct list_head *head) rollback_registered_many(head); list_for_each_entry(dev, head, unreg_list) net_set_todo(dev); + list_del(head); } } EXPORT_SYMBOL(unregister_netdevice_many); @@ -6960,7 +7025,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } } unregister_netdevice_many(&dev_kill_list); - list_del(&dev_kill_list); rtnl_unlock(); } diff --git a/net/core/dst.c b/net/core/dst.c index ca4231ec7347..15b6792e6ebb 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -267,6 +267,15 @@ again: } EXPORT_SYMBOL(dst_destroy); +static void dst_destroy_rcu(struct rcu_head *head) +{ + struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); + + dst = dst_destroy(dst); + if (dst) + __dst_free(dst); +} + void dst_release(struct dst_entry *dst) { if (dst) { @@ -274,11 +283,8 @@ void dst_release(struct dst_entry *dst) newrefcnt = atomic_dec_return(&dst->__refcnt); WARN_ON(newrefcnt < 0); - if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) { - dst = dst_destroy(dst); - if (dst) - __dst_free(dst); - } + if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) + call_rcu(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); diff --git a/net/core/filter.c b/net/core/filter.c index ad30d626a5bd..ebce437678fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -355,6 +355,8 @@ load_b: if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; if (A > skb->len - sizeof(struct nlattr)) return 0; @@ -371,11 +373,13 @@ load_b: if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; if (A > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *)&skb->data[A]; - if (nla->nla_len > A - skb->len) + if (nla->nla_len > skb->len - A) return 0; nla = nla_find_nested(nla, X); diff --git a/net/core/iovec.c b/net/core/iovec.c index b61869429f4c..26dc0062652f 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a { int size, ct, err; - if (m->msg_namelen) { + if (m->msg_name && m->msg_namelen) { if (mode == VERIFY_READ) { void __user *namep; namep = (void __user __force *) m->msg_name; @@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a if (err < 0) return err; } - if (m->msg_name) - m->msg_name = address; + m->msg_name = address; } else { m->msg_name = NULL; + m->msg_namelen = 0; } size = m->msg_iovlen * sizeof(struct iovec); @@ -107,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend); int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len) { + /* No data? Done! */ + if (len == 0) + return 0; + /* Skip over the finished iovecs */ while (offset >= iov->iov_len) { offset -= iov->iov_len; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e16129019c66..7d95f69635c6 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1247,8 +1247,8 @@ void __neigh_set_probe_once(struct neighbour *neigh) neigh->updated = jiffies; if (!(neigh->nud_state & NUD_FAILED)) return; - neigh->nud_state = NUD_PROBE; - atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh->nud_state = NUD_INCOMPLETE; + atomic_set(&neigh->probes, neigh_max_probes(neigh)); neigh_add_timer(neigh, jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 81d3a9a08453..7c8ffd974961 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -24,7 +24,7 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -static DEFINE_MUTEX(net_mutex); +DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index df9e6b1a9759..723fa7da8025 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -788,7 +788,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) } if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 120eecc0f5a4..b0db904f083d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); +/* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace. + */ +static void rtnl_lock_unregistering_all(void) +{ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + for_each_net(net) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + /** * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { - rtnl_lock(); + /* Close the race with cleanup_net() */ + mutex_lock(&net_mutex); + rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); + mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); @@ -768,13 +799,15 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + - nla_total_size(sizeof(struct ifla_vf_spoofchk))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_link_state))); return size; } else return 0; } -static size_t rtnl_port_size(const struct net_device *dev) +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ @@ -790,7 +823,8 @@ static size_t rtnl_port_size(const struct net_device *dev) size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + port_size; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; if (dev_num_vf(dev->dev.parent)) return port_self_size + vf_ports_size + @@ -825,7 +859,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ - + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ @@ -887,11 +921,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) return 0; } -static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { int err; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; err = rtnl_port_self_fill(skb, dev); @@ -1076,7 +1112,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, vfinfo); } - if (rtnl_port_fill(skb, dev)) + if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { @@ -1130,6 +1166,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_head *head; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; + int err; + int hdrlen; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1137,8 +1175,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; - if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + /* A hack to preserve kernel<->userspace interface. + * The correct header is ifinfomsg. It is consistent with rtnl_getlink. + * However, before Linux v3.9 the code here assumed rtgenmsg and that's + * what iproute2 < v3.9.0 used. + * We can detect the old iproute2. Even including the IFLA_EXT_MASK + * attribute, its netlink message is shorter than struct ifinfomsg. + */ + hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -1150,11 +1197,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + 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; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1386,7 +1439,8 @@ static int do_set_master(struct net_device *dev, int ifindex) return 0; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1398,7 +1452,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { err = -EPERM; goto errout; } @@ -1652,7 +1706,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } @@ -1692,7 +1746,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) ops->dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); - list_del(&list_kill); return 0; } @@ -1769,7 +1822,8 @@ err: } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_group_changelink(struct net *net, int group, +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, struct ifinfomsg *ifm, struct nlattr **tb) { @@ -1778,7 +1832,7 @@ static int rtnl_group_changelink(struct net *net, int group, for_each_netdev(net, dev) { if (dev->group == group) { - err = do_setlink(dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) return err; } @@ -1920,12 +1974,12 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + return do_setlink(skb, dev, ifm, tb, ifname, modified); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) - return rtnl_group_changelink(net, + return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), ifm, tb); return -ENODEV; @@ -2042,9 +2096,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0; + int hdrlen; + + /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ + hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); - if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); } @@ -2312,7 +2370,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2764,7 +2822,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 897da56f3aff..ba71212f0251 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -__u32 secure_ip_id(__be32 daddr) -{ - u32 hash[MD5_DIGEST_WORDS]; - - net_secret_init(); - hash[0] = (__force __u32) daddr; - hash[1] = net_secret[13]; - hash[2] = net_secret[14]; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - return hash[0]; -} - -__u32 secure_ipv6_id(const __be32 daddr[4]) -{ - __u32 hash[4]; - - net_secret_init(); - memcpy(hash, daddr, 16); - md5_transform(hash, net_secret); - - return hash[0]; -} __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 90b96a11b974..baf6fc457df9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -62,6 +62,7 @@ #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> +#include <linux/if_vlan.h> #include <net/protocol.h> #include <net/dst.h> @@ -2881,12 +2882,13 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, int pos; int dummy; + __skb_push(head_skb, doffset); proto = skb_network_protocol(head_skb, &dummy); if (unlikely(!proto)) return ERR_PTR(-EINVAL); csum = !!can_checksum_protocol(features, proto); - __skb_push(head_skb, doffset); + headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); @@ -2967,9 +2969,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, tail = nskb; __copy_skb_header(nskb, head_skb); - nskb->mac_len = head_skb->mac_len; skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); + skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, @@ -3076,7 +3078,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) if (unlikely(p->len + len >= 65536)) return -E2BIG; - lp = NAPI_GRO_CB(p)->last ?: p; + lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp); if (headlen <= offset) { @@ -3138,6 +3140,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } + /* switch back to head shinfo */ + pinfo = skb_shinfo(p); + if (pinfo->frag_list) goto merge; if (skb_gro_len(p) != pinfo->gso_size) @@ -3192,7 +3197,7 @@ merge: __skb_pull(skb, offset); - if (!NAPI_GRO_CB(p)->last) + if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; @@ -3951,12 +3956,66 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); - unsigned int hdr_len; if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) - hdr_len = tcp_hdrlen(skb); - else - hdr_len = sizeof(struct udphdr); - return hdr_len + shinfo->gso_size; + return tcp_hdrlen(skb) + shinfo->gso_size; + + /* UFO sets gso_size to the size of the fragmentation + * payload, i.e. the size of the L4 (UDP) header is already + * accounted for. + */ + return shinfo->gso_size; } EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) +{ + if (skb_cow(skb, skb_headroom(skb)) < 0) { + kfree_skb(skb); + return NULL; + } + + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + skb->mac_header += VLAN_HLEN; + return skb; +} + +struct sk_buff *skb_vlan_untag(struct sk_buff *skb) +{ + struct vlan_hdr *vhdr; + u16 vlan_tci; + + if (unlikely(vlan_tx_tag_present(skb))) { + /* vlan_tci is already set-up so leave this for another time */ + return skb; + } + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + goto err_free; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + goto err_free; + + vhdr = (struct vlan_hdr *)skb->data; + vlan_tci = ntohs(vhdr->h_vlan_TCI); + __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); + + skb_pull_rcsum(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vhdr); + + skb = skb_reorder_vlan_header(skb); + if (unlikely(!skb)) + goto err_free; + + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb_reset_mac_len(skb); + + return skb; + +err_free: + kfree_skb(skb); + return NULL; +} +EXPORT_SYMBOL(skb_vlan_untag); diff --git a/net/core/sock.c b/net/core/sock.c index c0fc6bdad1e3..c8069561bdb7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -145,6 +145,55 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + #ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index a0e9cf6379de..c38e7a2b5a8e 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct nlattr *attr; @@ -57,7 +57,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, unsigned int len; int err = 0; - if (!ns_capable(user_ns, CAP_NET_ADMIN)) { + if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } diff --git a/net/core/utils.c b/net/core/utils.c index 2f737bf90b3f..eed34338736c 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w) { struct __net_random_once_work *work = container_of(w, struct __net_random_once_work, work); - if (!static_key_enabled(work->key)) - static_key_slow_inc(work->key); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); kfree(work); } @@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key) } bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key) + struct static_key *once_key) { static DEFINE_SPINLOCK(lock); unsigned long flags; @@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done, *done = true; spin_unlock_irqrestore(&lock, flags); - __net_random_once_disable_jump(done_key); + __net_random_once_disable_jump(once_key); return true; } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 553644402670..f8b98d89c285 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1669,7 +1669,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlmsghdr *reply_nlh = NULL; const struct reply_func *fn; - if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN)) + if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index a603823a3e27..3b726f31c64c 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -574,7 +574,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr __rcu **ifap; int err = -EINVAL; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -618,7 +618,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr *ifa; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 57dc159245ec..d332aefb0846 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index e83015cecfa7..e4d9560a910b 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) return; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) RCV_SKB_FAIL(-EPERM); /* Eventually we might send routing messages too */ diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index e7b6d53eef88..f005cc760535 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -149,7 +149,9 @@ int dns_query(const char *type, const char *name, size_t namelen, if (!*_result) goto put; - memcpy(*_result, upayload->data, len + 1); + memcpy(*_result, upayload->data, len); + (*_result)[len] = '\0'; + if (_expiry) *_expiry = rkey->expiry; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 19ab78aca547..07bd8edef417 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1434,6 +1434,9 @@ static int inet_gro_complete(struct sk_buff *skb, int nhoff) int proto = iph->protocol; int err = -ENOSYS; + if (skb->encapsulation) + skb_set_inner_network_header(skb, nhoff); + csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 8b5134c582f1..a3095fdefbed 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -86,18 +86,26 @@ out: } EXPORT_SYMBOL(ip4_datagram_connect); +/* Because UDP xmit path can manipulate sk_dst_cache without holding + * socket lock, we need to use sk_dst_set() here, + * even if we own the socket lock. + */ void ip4_datagram_release_cb(struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; + struct dst_entry *dst; struct flowi4 fl4; struct rtable *rt; - if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) - return; - rcu_read_lock(); + + dst = __sk_dst_get(sk); + if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) { + rcu_read_unlock(); + return; + } inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; @@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk) inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); - if (!IS_ERR(rt)) - __sk_dst_set(sk, &rt->dst); + + dst = !IS_ERR(rt) ? &rt->dst : NULL; + sk_dst_set(sk, dst); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b53f0bf84dca..017fa5e17594 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -535,7 +535,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; attrlen = rtnh_attrlen(rtnh); - if (attrlen < 0) { + if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); @@ -820,13 +820,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (fi == NULL) goto failure; + fib_info_cnt++; if (cfg->fc_mx) { fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); if (!fi->fib_metrics) goto failure; } else fi->fib_metrics = (u32 *) dst_default_metrics; - fib_info_cnt++; fi->fib_net = hold_net(net); fi->fib_protocol = cfg->fc_protocol; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index f1d32280cb54..8c8493ea6b1c 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -50,7 +50,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); - ghl = skb_inner_network_header(skb) - skb_transport_header(skb); + ghl = skb_inner_mac_header(skb) - skb_transport_header(skb); if (unlikely(ghl < sizeof(*greh))) goto out; @@ -255,6 +255,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) int err = -ENOENT; __be16 type; + skb->encapsulation = 1; + skb_shinfo(skb)->gso_type = SKB_GSO_GRE; + type = greh->protocol; if (greh->flags & GRE_KEY) grehlen += GRE_HEADER_SECTION; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 0134663fdbce..1e4aa8354f93 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -732,8 +732,6 @@ static void icmp_unreach(struct sk_buff *skb) /* fall through */ case 0: info = ntohs(icmph->un.frag.mtu); - if (!info) - goto out; } break; case ICMP_SR_FAILED: diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 97e4d1655d26..0ffcd4d64e0a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -1952,6 +1952,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_lock(); in_dev = ip_mc_find_dev(net, imr); + if (!in_dev) { + ret = -ENODEV; + goto out; + } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; @@ -1969,16 +1973,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) *imlp = iml->next_rcu; - if (in_dev) - ip_mc_dec_group(in_dev, group); + ip_mc_dec_group(in_dev, group); rtnl_unlock(); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } - if (!in_dev) - ret = -ENODEV; +out: rtnl_unlock(); return ret; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 48f424465112..bf2cb4a4714b 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -26,20 +26,7 @@ * Theory of operations. * We keep one entry for each peer IP address. The nodes contains long-living * information about the peer which doesn't depend on routes. - * At this moment this information consists only of ID field for the next - * outgoing IP packet. This field is incremented with each packet as encoded - * in inet_getid() function (include/net/inetpeer.h). - * At the moment of writing this notes identifier of IP packets is generated - * to be unpredictable using this code only for packets subjected - * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size when local fragmentation is disabled use a constant ID and do - * not use this code (see ip_select_ident() in include/net/ip.h). * - * Route cache entries hold references to our nodes. - * New cache entries get references via lookup by destination IP address in - * the avl tree. The reference is grabbed only when it's needed i.e. only - * when we try to output IP packet which needs an unpredictable ID (see - * __ip_select_ident() in net/ipv4/route.c). * Nodes are removed only when reference counter goes to 0. * When it's happened the node may be removed when a sufficient amount of * time has been passed since its last use. The less-recently-used entry can @@ -62,7 +49,6 @@ * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing * daddr: unchangeable - * ip_id_count: atomic value (no lock needed) */ static struct kmem_cache *peer_cachep __read_mostly; @@ -497,10 +483,6 @@ relookup: p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, - (daddr->family == AF_INET) ? - secure_ip_id(daddr->addr.a4) : - secure_ipv6_id(daddr->addr.a6)); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index f3869c186d97..1c6bd4359cbd 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -42,12 +42,12 @@ static bool ip_may_fragment(const struct sk_buff *skb) { return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || - !skb->local_df; + skb->local_df; } static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) { - if (skb->len <= mtu || skb->local_df) + if (skb->len <= mtu) return false; if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ec4f762efda5..94213c891565 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -463,6 +463,7 @@ static const struct net_device_ops ipgre_netdev_ops = { static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; + dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } @@ -501,7 +502,6 @@ static int ipgre_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->type = ARPHRD_IPGRE; dev->flags = IFF_NOARP; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->addr_len = 4; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index f4ab72e19af9..96f90b89df32 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -288,6 +288,10 @@ int ip_options_compile(struct net *net, optptr++; continue; } + if (unlikely(l < 2)) { + pp_ptr = optptr; + goto error; + } optlen = optptr[1]; if (optlen < 2 || optlen > l) { pp_ptr = optptr; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 73c6b63bba74..844323b6cfb9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -386,8 +386,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(skb, &rt->dst, sk, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); + ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -1338,7 +1337,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(skb, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt) { iph->ihl += opt->optlen>>2; @@ -1488,6 +1487,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, struct sk_buff *nskb; struct sock *sk; struct inet_sock *inet; + int err; if (ip_options_echo(&replyopts.opt.opt, skb)) return; @@ -1526,8 +1526,13 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, sock_net_set(sk, net); __skb_queue_head_init(&sk->sk_write_queue); sk->sk_sndbuf = sysctl_wmem_default; - ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, - &ipc, &rt, MSG_DONTWAIT); + err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, + len, 0, &ipc, &rt, MSG_DONTWAIT); + if (unlikely(err)) { + ip_flush_pending_frames(sk); + goto out; + } + nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) @@ -1539,7 +1544,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } - +out: put_cpu_var(unicast_sock); ip_rt_put(rt); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index a82a22d8f77f..0a4af0920af3 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -69,28 +69,25 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) } static void __tunnel_dst_set(struct ip_tunnel_dst *idst, - struct dst_entry *dst) + struct dst_entry *dst, __be32 saddr) { struct dst_entry *old_dst; - if (dst) { - if (dst->flags & DST_NOCACHE) - dst = NULL; - else - dst_clone(dst); - } + dst_clone(dst); old_dst = xchg((__force struct dst_entry **)&idst->dst, dst); dst_release(old_dst); + idst->saddr = saddr; } -static void tunnel_dst_set(struct ip_tunnel *t, struct dst_entry *dst) +static void tunnel_dst_set(struct ip_tunnel *t, + struct dst_entry *dst, __be32 saddr) { - __tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst); + __tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst, saddr); } static void tunnel_dst_reset(struct ip_tunnel *t) { - tunnel_dst_set(t, NULL); + tunnel_dst_set(t, NULL, 0); } void ip_tunnel_dst_reset_all(struct ip_tunnel *t) @@ -98,23 +95,29 @@ void ip_tunnel_dst_reset_all(struct ip_tunnel *t) int i; for_each_possible_cpu(i) - __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); + __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0); } EXPORT_SYMBOL(ip_tunnel_dst_reset_all); -static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) +static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, + u32 cookie, __be32 *saddr) { + struct ip_tunnel_dst *idst; struct dst_entry *dst; rcu_read_lock(); - dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst); + idst = this_cpu_ptr(t->dst_cache); + dst = rcu_dereference(idst->dst); + if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + dst = NULL; if (dst) { - if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) { - rcu_read_unlock(); + if (!dst->obsolete || dst->ops->check(dst, cookie)) { + *saddr = idst->saddr; + } else { tunnel_dst_reset(t); - return NULL; + dst_release(dst); + dst = NULL; } - dst_hold(dst); } rcu_read_unlock(); return (struct rtable *)dst; @@ -173,6 +176,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (remote != t->parms.iph.daddr || + t->parms.iph.saddr != 0 || !(t->dev->flags & IFF_UP)) continue; @@ -189,10 +193,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { - if ((local != t->parms.iph.saddr && - (local != t->parms.iph.daddr || - !ipv4_is_multicast(local))) || - !(t->dev->flags & IFF_UP)) + if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) && + (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) + continue; + + if (!(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) @@ -209,6 +214,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (t->parms.i_key != key || + t->parms.iph.saddr != 0 || + t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) continue; @@ -362,7 +369,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (!IS_ERR(rt)) { tdev = rt->dst.dev; - tunnel_dst_set(tunnel, &rt->dst); + tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) @@ -438,6 +445,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + skb_reset_network_header(skb); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -534,9 +543,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, unsigned int max_headroom; /* The extra header space needed */ __be32 dst; int err; - bool connected = true; + bool connected; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); + connected = (tunnel->parms.iph.daddr != 0); dst = tnl_params->daddr; if (dst == 0) { @@ -603,7 +613,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); - rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL; + rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); @@ -613,7 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } if (connected) - tunnel_dst_set(tunnel, &rt->dst); + tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { @@ -872,6 +882,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, */ if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); } rtnl_unlock(); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 8d69626f2206..791a419f0699 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -74,7 +74,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1); + __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1); err = ip_local_out(skb); if (unlikely(net_xmit_eval(err))) @@ -91,11 +91,12 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) skb_pull_rcsum(skb, hdr_len); if (inner_proto == htons(ETH_P_TEB)) { - struct ethhdr *eh = (struct ethhdr *)skb->data; + struct ethhdr *eh; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) return -ENOMEM; + eh = (struct ethhdr *)skb->data; if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN)) skb->protocol = eh->h_proto; else diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 48eafae51769..e4a8f76c8995 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -207,6 +207,7 @@ static const struct net_device_ops vti_netdev_ops = { static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; + dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } @@ -218,7 +219,6 @@ static int vti_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->type = ARPHRD_TUNNEL; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 812b18351462..62eaa005e146 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPIP, 0); + t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; @@ -486,4 +486,5 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 28863570dd60..1149fc2290e2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1663,7 +1663,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(skb, skb_dst(skb), NULL); + ip_select_ident(skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 59da7cde0724..f95b6f93814b 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1044,8 +1044,10 @@ static int __do_replace(struct net *net, const char *name, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 718dfbd30cbe..99e810f84671 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1231,8 +1231,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 12e13bd82b5b..f40f321b41fc 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -22,7 +22,6 @@ #endif #include <net/netfilter/nf_conntrack_zones.h> -/* Returns new sk_buff, or NULL */ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) { int err; @@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) err = ip_defrag(skb, user); local_bh_enable(); - if (!err) + if (!err) { ip_send_check(ip_hdr(skb)); + skb->local_df = 1; + } return err; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2d11c094296e..e21934b06d4c 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -252,26 +252,33 @@ int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); - struct group_info *group_info = get_current_groups(); - int i, j, count = group_info->ngroups; + struct group_info *group_info; + int i, j, count; kgid_t low, high; + int ret = 0; inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; + group_info = get_current_groups(); + count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); for (j = 0; j < cp_count; j++) { kgid_t gid = group_info->blocks[i][j]; if (gid_lte(low, gid) && gid_lte(gid, high)) - return 0; + goto out_release_group; } count -= cp_count; } - return -EACCES; + ret = -EACCES; + +out_release_group: + put_group_info(group_info); + return ret; } EXPORT_SYMBOL_GPL(ping_init_sock); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c04518f4850a..11c8d81fdc59 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4c011ec69ed4..487bb6252520 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -89,6 +89,7 @@ #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/jhash.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -462,39 +463,45 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, return neigh_create(&arp_tbl, pkey, dev); } -/* - * Peer allocation may fail only in serious out-of-memory conditions. However - * we still can generate some output. - * Random ID selection looks a bit dangerous because we have no chances to - * select ID being unique in a reasonable period of time. - * But broken packet identifier may be better than no packet at all. +#define IP_IDENTS_SZ 2048u +struct ip_ident_bucket { + atomic_t id; + u32 stamp32; +}; + +static struct ip_ident_bucket *ip_idents __read_mostly; + +/* In order to protect privacy, we add a perturbation to identifiers + * if one generator is seldom used. This makes hard for an attacker + * to infer how many packets were sent between two points in time. */ -static void ip_select_fb_ident(struct iphdr *iph) +u32 ip_idents_reserve(u32 hash, int segs) { - static DEFINE_SPINLOCK(ip_fb_id_lock); - static u32 ip_fallback_id; - u32 salt; + struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ; + u32 old = ACCESS_ONCE(bucket->stamp32); + u32 now = (u32)jiffies; + u32 delta = 0; - spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); - iph->id = htons(salt & 0xFFFF); - ip_fallback_id = salt; - spin_unlock_bh(&ip_fb_id_lock); + if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) + delta = prandom_u32_max(now - old); + + return atomic_add_return(segs + delta, &bucket->id) - segs; } +EXPORT_SYMBOL(ip_idents_reserve); -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) +void __ip_select_ident(struct iphdr *iph, int segs) { - struct net *net = dev_net(dst->dev); - struct inet_peer *peer; + static u32 ip_idents_hashrnd __read_mostly; + u32 hash, id; - peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1); - if (peer) { - iph->id = htons(inet_getid(peer, more)); - inet_putpeer(peer); - return; - } + net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); - ip_select_fb_ident(iph); + hash = jhash_3words((__force u32)iph->daddr, + (__force u32)iph->saddr, + iph->protocol, + ip_idents_hashrnd); + id = ip_idents_reserve(hash, segs); + iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); @@ -1029,7 +1036,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; - struct dst_entry *dst; + struct dst_entry *odst = NULL; bool new = false; bh_lock_sock(sk); @@ -1037,16 +1044,17 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) if (!ip_sk_accept_pmtu(sk)) goto out; - rt = (struct rtable *) __sk_dst_get(sk); + odst = sk_dst_get(sk); - if (sock_owned_by_user(sk) || !rt) { + if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); - if (!__sk_dst_check(sk, 0)) { + rt = (struct rtable *)odst; + if (odst->obsolete && odst->ops->check(odst, 0) == NULL) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; @@ -1056,8 +1064,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); - dst = dst_check(&rt->dst, 0); - if (!dst) { + if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); @@ -1069,10 +1076,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) } if (new) - __sk_dst_set(sk, &rt->dst); + sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); + dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); @@ -1526,7 +1534,7 @@ static int __mkroute_input(struct sk_buff *skb, struct in_device *out_dev; unsigned int flags = 0; bool do_cache; - u32 itag; + u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); @@ -2260,9 +2268,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, return rt; if (flp4->flowi4_proto) - rt = (struct rtable *) xfrm_lookup(net, &rt->dst, - flowi4_to_flowi(flp4), - sk, 0); + rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, + flowi4_to_flowi(flp4), + sk, 0); return rt; } @@ -2364,7 +2372,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, } } else #endif - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex)) goto nla_put_failure; } @@ -2717,6 +2725,12 @@ int __init ip_rt_init(void) { int rc = 0; + ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); + if (!ip_idents) + panic("IP: failed to allocate ip_idents\n"); + + prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 97c8f5620c43..29d240b87af1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1108,7 +1108,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); - goto out; + goto out_nopush; } err = -EINVAL; @@ -1175,13 +1175,6 @@ new_segment: goto wait_for_memory; /* - * All packets are restored as if they have - * already been sent. - */ - if (tp->repair) - TCP_SKB_CB(skb)->when = tcp_time_stamp; - - /* * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) @@ -1190,6 +1183,13 @@ new_segment: skb_entail(sk, skb); copy = size_goal; max = size_goal; + + /* All packets are restored as if they have + * already been sent. skb_mstamp isn't set to + * avoid wrong rtt estimation. + */ + if (tp->repair) + TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ @@ -1282,6 +1282,7 @@ wait_for_memory: out: if (copied) tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); +out_nopush: release_sock(sk); return copied + copied_syn; @@ -2953,61 +2954,42 @@ EXPORT_SYMBOL(compat_tcp_getsockopt); #endif #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly; +static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool); static DEFINE_MUTEX(tcp_md5sig_mutex); - -static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu); - - if (p->md5_desc.tfm) - crypto_free_hash(p->md5_desc.tfm); - } - free_percpu(pool); -} +static bool tcp_md5sig_pool_populated = false; static void __tcp_alloc_md5sig_pool(void) { int cpu; - struct tcp_md5sig_pool __percpu *pool; - - pool = alloc_percpu(struct tcp_md5sig_pool); - if (!pool) - return; for_each_possible_cpu(cpu) { - struct crypto_hash *hash; - - hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(hash)) - goto out_free; + if (!per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm) { + struct crypto_hash *hash; - per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; + hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR_OR_NULL(hash)) + return; + per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash; + } } - /* before setting tcp_md5sig_pool, we must commit all writes - * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool() + /* before setting tcp_md5sig_pool_populated, we must commit all writes + * to memory. See smp_rmb() in tcp_get_md5sig_pool() */ smp_wmb(); - tcp_md5sig_pool = pool; - return; -out_free: - __tcp_free_md5sig_pool(pool); + tcp_md5sig_pool_populated = true; } bool tcp_alloc_md5sig_pool(void) { - if (unlikely(!tcp_md5sig_pool)) { + if (unlikely(!tcp_md5sig_pool_populated)) { mutex_lock(&tcp_md5sig_mutex); - if (!tcp_md5sig_pool) + if (!tcp_md5sig_pool_populated) __tcp_alloc_md5sig_pool(); mutex_unlock(&tcp_md5sig_mutex); } - return tcp_md5sig_pool != NULL; + return tcp_md5sig_pool_populated; } EXPORT_SYMBOL(tcp_alloc_md5sig_pool); @@ -3021,13 +3003,13 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool); */ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { - struct tcp_md5sig_pool __percpu *p; - local_bh_disable(); - p = ACCESS_ONCE(tcp_md5sig_pool); - if (p) - return __this_cpu_ptr(p); + if (tcp_md5sig_pool_populated) { + /* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */ + smp_rmb(); + return this_cpu_ptr(&tcp_md5sig_pool); + } local_bh_enable(); return NULL; } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 828e4c3ffbaf..121a9a22dc98 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -409,7 +409,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; ratio += cnt; - ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT); + ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT); } /* Some calls are for duplicates without timetamps */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eeaac399420d..22917918fa80 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1113,7 +1113,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } /* D-SACK for already forgotten data... Do dumb counting. */ - if (dup_sack && tp->undo_marker && tp->undo_retrans && + if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 && !after(end_seq_0, prior_snd_una) && after(end_seq_0, tp->undo_marker)) tp->undo_retrans--; @@ -1169,7 +1169,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, unsigned int new_len = (pkt_len / mss) * mss; if (!in_sack && new_len < pkt_len) { new_len += mss; - if (new_len > skb->len) + if (new_len >= skb->len) return 0; } pkt_len = new_len; @@ -1193,7 +1193,7 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { - if (tp->undo_marker && tp->undo_retrans && + if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) @@ -1894,7 +1894,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp) tp->lost_out = 0; tp->undo_marker = 0; - tp->undo_retrans = 0; + tp->undo_retrans = -1; } void tcp_clear_retrans(struct tcp_sock *tp) @@ -2663,7 +2663,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) tp->prior_ssthresh = 0; tp->undo_marker = tp->snd_una; - tp->undo_retrans = tp->retrans_out; + tp->undo_retrans = tp->retrans_out ? : -1; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { if (!ece_ack) @@ -2678,18 +2678,16 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) */ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) { - struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ - if (flag & FLAG_ORIG_SACK_ACKED) { - /* Step 3.b. A timeout is spurious if not all data are - * lost, i.e., never-retransmitted data are (s)acked. - */ - tcp_try_undo_loss(sk, true); + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) return; - } + if (after(tp->snd_nxt, tp->high_seq) && (flag & FLAG_DATA_SACKED || is_dupack)) { tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ @@ -2705,12 +2703,9 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) if (recovered) { /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */ - icsk->icsk_retransmits = 0; tcp_try_undo_recovery(sk); return; } - if (flag & FLAG_DATA_ACKED) - icsk->icsk_retransmits = 0; if (tcp_is_reno(tp)) { /* A Reno DUPACK means new data in F-RTO step 2.b above are * delivered. Lower inflight to clock out (re)tranmissions. @@ -3399,8 +3394,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); - if (after(ack, prior_snd_una)) + if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; + icsk->icsk_retransmits = 0; + } prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1e4eac779f51..a782d5be132e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -269,7 +269,7 @@ EXPORT_SYMBOL(tcp_v4_connect); * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ -static void tcp_v4_mtu_reduced(struct sock *sk) +void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); @@ -300,6 +300,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk) tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } +EXPORT_SYMBOL(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { @@ -2117,6 +2118,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .compat_setsockopt = compat_ip_setsockopt, .compat_getsockopt = compat_ip_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_SYMBOL(ipv4_specific); @@ -2736,7 +2738,6 @@ struct proto tcp_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index b92b81718ca4..c25953a386d0 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -310,7 +310,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; return tcp_gro_complete(skb); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 17a11e65e57f..91b98e5a17aa 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -787,7 +787,7 @@ void tcp_release_cb(struct sock *sk) __sock_put(sk); } if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { - sk->sk_prot->mtu_reduced(sk); + inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } @@ -1876,8 +1876,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); - if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { + /* "when" is used as a start point for the retransmit timer */ + TCP_SKB_CB(skb)->when = tcp_time_stamp; goto repair; /* Skip network transmission */ + } cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { @@ -2066,9 +2069,7 @@ void tcp_send_loss_probe(struct sock *sk) if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; - /* Probe with zero data doesn't trigger fast recovery. */ - if (skb->len > 0) - err = __tcp_retransmit_skb(sk, skb); + err = __tcp_retransmit_skb(sk, skb); /* Record snd_nxt for loss detection. */ if (likely(!err)) @@ -2448,8 +2449,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (!tp->retrans_stamp) tp->retrans_stamp = TCP_SKB_CB(skb)->when; - tp->undo_retrans += tcp_skb_pcount(skb); - /* snd_nxt is stored to detect loss of retransmitted segment, * see tcp_input.c tcp_sacktag_write_queue(). */ @@ -2457,6 +2456,10 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) } else { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } + + if (tp->undo_retrans < 0) + tp->undo_retrans = 0; + tp->undo_retrans += tcp_skb_pcount(skb); return err; } diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 06cae62bf208..6b1a5fd60598 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -219,7 +219,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked, * This is: * (actual rate in segments) * baseRTT */ - target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt; + target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT; + do_div(target_cwnd, rtt); /* Calculate the difference between the window we had, * and the window we would like to have. This quantity diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 326475a94865..603ad498e18a 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -145,7 +145,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked, rtt = veno->minrtt; - target_cwnd = (tp->snd_cwnd * veno->basertt); + target_cwnd = (u64)tp->snd_cwnd * veno->basertt; target_cwnd <<= V_PARAM_SHIFT; do_div(target_cwnd, rtt); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 77bd16fa9f34..b25e852625d8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1833,6 +1833,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask); struct udp_hslot *hslot = &udp_table.hash[slot]; + /* Do not bother scanning a too big list */ + if (hslot->count > 10) + return NULL; + rcu_read_lock(); begin: count = 0; diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 31b18152528f..1f564a1487a3 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -117,12 +117,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; + ip_select_ident(skb, NULL); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6c7fa0853fc7..3f0ec063d7f8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1684,14 +1684,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) addrconf_mod_dad_work(ifp, 0); } -/* Join to solicited addr multicast group. */ - +/* Join to solicited addr multicast group. + * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1699,12 +1697,11 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } +/* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1712,12 +1709,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &maddr); } +/* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -1726,12 +1722,11 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) ipv6_dev_ac_inc(ifp->idev->dev, &addr); } +/* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 210183244689..ff2de7d9d8e6 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -77,6 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -137,6 +138,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) error: rcu_read_unlock(); + rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -171,11 +173,13 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock_bh(&ipv6_sk_ac_lock); + rtnl_lock(); rcu_read_lock(); dev = dev_get_by_index_rcu(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; @@ -198,6 +202,7 @@ void ipv6_sock_ac_close(struct sock *sk) spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rtnl_lock(); rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; @@ -212,6 +217,7 @@ void ipv6_sock_ac_close(struct sock *sk) pac = next; } rcu_read_unlock(); + rtnl_unlock(); } static void aca_put(struct ifacaddr6 *ac) @@ -233,6 +239,8 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) struct rt6_info *rt; int err; + ASSERT_RTNL(); + idev = in6_dev_get(dev); if (idev == NULL) @@ -302,6 +310,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); prev_aca = NULL; for (aca = idev->ac_list; aca; aca = aca->aca_next) { diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f2610e157660..7b326529e6a2 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -520,7 +520,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) np->tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 075602fc6b6a..1e55f5eba185 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1418,7 +1418,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) if (w->skip) { w->skip--; - continue; + goto skip; } err = w->func(w); @@ -1428,6 +1428,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) w->count++; continue; } +skip: w->state = FWS_U; case FWS_U: if (fn == w->root) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f3ffb43f59c0..cb57aa862177 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -787,7 +787,7 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPIP; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv4_get_dsfield(iph); @@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPV6; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) @@ -1566,6 +1566,15 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], return 0; } +static void ip6gre_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + if (dev != ign->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6gre_get_size(const struct net_device *dev) { return @@ -1643,6 +1652,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { .validate = ip6gre_tunnel_validate, .newlink = ip6gre_newlink, .changelink = ip6gre_changelink, + .dellink = ip6gre_dellink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, }; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 59f95affceb0..b2f091566f88 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -196,7 +196,6 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, unsigned int off; u16 flush = 1; int proto; - __wsum csum; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); @@ -264,13 +263,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, NAPI_GRO_CB(skb)->flush |= flush; - csum = skb->csum; - skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + skb_gro_postpull_rcsum(skb, iph, nlen); pp = ops->callbacks.gro_receive(head, skb); - skb->csum = csum; - out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 64d6073731d3..12f7ef0f243a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -344,12 +344,16 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { - if (skb->len <= mtu || skb->local_df) + if (skb->len <= mtu) return false; + /* ipv6 conntrack defrag sets max_frag_size + local_df */ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) return true; + if (skb->local_df) + return false; + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) return false; @@ -533,6 +537,20 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static u32 ip6_idents_hashrnd __read_mostly; + u32 hash, id; + + net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); + hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash); + + id = ip_idents_reserve(hash, 1); + fhdr->identification = htonl(id); +} + int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -990,7 +1008,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1022,7 +1040,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); @@ -1225,7 +1243,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, unsigned int maxnonfragsize, headersize; headersize = sizeof(struct ipv6hdr) + - (opt ? opt->tot_len : 0) + + (opt ? opt->opt_flen + opt->opt_nflen : 0) + (dst_allfrag(&rt->dst) ? sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; @@ -1566,8 +1584,8 @@ int ip6_push_pending_frames(struct sock *sk) if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } err = ip6_local_out(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5db8d310f9c0..912033957ad3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -61,6 +61,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG @@ -1564,7 +1565,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) { u8 proto; - if (!data) + if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index e1e47350784b..761e4586ab5f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -172,6 +172,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = NULL; mc_lst->addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -185,6 +186,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (dev == NULL) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -202,6 +204,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (err) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } @@ -212,6 +215,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock(&ipv6_sk_mc_lock); rcu_read_unlock(); + rtnl_unlock(); return 0; } @@ -229,6 +233,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = rcu_dereference_protected(*lnk, @@ -252,12 +257,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); + rtnl_unlock(); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); return -EADDRNOTAVAIL; } @@ -302,6 +310,7 @@ void ipv6_sock_mc_close(struct sock *sk) if (!rcu_access_pointer(np->ipv6_mc_list)) return; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { @@ -328,6 +337,7 @@ void ipv6_sock_mc_close(struct sock *sk) spin_lock(&ipv6_sk_mc_lock); } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -845,6 +855,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) struct ifmcaddr6 *mc; struct inet6_dev *idev; + ASSERT_RTNL(); + /* we need to take a reference on idev */ idev = in6_dev_get(dev); @@ -916,6 +928,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, **map; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { @@ -1620,11 +1634,12 @@ static void mld_sendpack(struct sk_buff *skb) dst_output); out: if (!err) { - ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); - } else - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS); + ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); + } else { + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + } rcu_read_unlock(); return; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 95f3f1da0d7f..d38e6a8d8b9f 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb) .daddr = iph->daddr, .saddr = iph->saddr, }; + int err; dst = ip6_route_output(net, skb->sk, &fl6); - if (dst->error) { + err = dst->error; + if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); dst_release(dst); - return dst->error; + return err; } /* Drop old route. */ diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 710238f58aa9..e080fbbbc0e5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1241,8 +1241,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 827f795209cf..ae4a06be14df 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -3,38 +3,43 @@ * not configured or static. These functions are needed by GSO/GRO implementation. */ #include <linux/export.h> +#include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +/* This function exists only for tap drivers that must support broken + * clients requesting UFO without specifying an IPv6 fragment ID. + * + * This is similar to ipv6_select_ident() but we use an independent hash + * seed to limit information leakage. + * + * The network header must be set before calling this. + */ +void ipv6_proxy_select_ident(struct sk_buff *skb) { - static atomic_t ipv6_fragmentation_id; - int old, new; - -#if IS_ENABLED(CONFIG_IPV6) - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } - } -#endif - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); + static u32 ip6_proxy_idents_hashrnd __read_mostly; + struct in6_addr buf[2]; + struct in6_addr *addrs; + u32 hash, id; + + addrs = skb_header_pointer(skb, + skb_network_offset(skb) + + offsetof(struct ipv6hdr, saddr), + sizeof(buf), buf); + if (!addrs) + return; + + net_get_random_once(&ip6_proxy_idents_hashrnd, + sizeof(ip6_proxy_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd); + hash = __ipv6_addr_jhash(&addrs[0], hash); + + id = ip_idents_reserve(hash, 1); + skb_shinfo(skb)->ip6_frag_id = htonl(id); } -EXPORT_SYMBOL(ipv6_select_ident); +EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 587bbdcb22b4..bda74291c3e0 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -182,8 +182,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev, - ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fba54a407bb2..7cc1102e298c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1342,7 +1342,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = IPV6_MIN_MTU; @@ -1352,7 +1352,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) mtu = idev->cnf.mtu6; rcu_read_unlock(); - return mtu; +out: + return min_t(unsigned int, mtu, IP6_MAX_MTU); } static struct dst_entry *icmp6_dst_gc_list; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b4d74c86586c..b12b11b123ff 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -101,19 +101,19 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } @@ -560,12 +560,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPV6, 0); + t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; @@ -1850,4 +1850,5 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 889079b2ea85..a4f890dd223a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1668,6 +1668,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v6_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1699,6 +1700,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1935,7 +1937,6 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 0d78132ff18a..01b0ff9a0c2c 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, if (NAPI_GRO_CB(skb)->flush) goto skip_csum; - wsum = skb->csum; + wsum = NAPI_GRO_CB(skb)->csum; switch (skb->ip_summed) { case CHECKSUM_NONE: @@ -73,7 +73,7 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; return tcp_gro_complete(skb); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1e586d92260e..20b63d2ab70f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -716,15 +716,15 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, if (inet->inet_dport != rmt_port) continue; } - if (!ipv6_addr_any(&sk->sk_v6_daddr) && - !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) + if (!ipv6_addr_any(&s->sk_v6_daddr) && + !ipv6_addr_equal(&s->sk_v6_daddr, rmt_addr)) continue; if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) continue; - if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { - if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) + if (!ipv6_addr_any(&s->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&s->sk_v6_rcv_saddr, loc_addr)) continue; } if (!inet6_mc_check(s, loc_addr, rmt_addr)) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index c4b7218058b6..1465363a452b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1829,7 +1829,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { + if (msg->tag == IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5990919356a5..da8d067d6107 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -756,9 +756,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, session->deref = pppol2tp_session_sock_put; /* If PMTU discovery was enabled, use the MTU that was discovered */ - dst = sk_dst_get(sk); + dst = sk_dst_get(tunnel->sock); if (dst != NULL) { - u32 pmtu = dst_mtu(__sk_dst_get(sk)); + u32 pmtu = dst_mtu(dst); + if (pmtu != 0) session->mtu = session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; @@ -1368,7 +1369,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, int err; if (level != SOL_PPPOL2TP) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (optlen < sizeof(int)) return -EINVAL; @@ -1494,7 +1495,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, struct pppol2tp_session *ps; if (level != SOL_PPPOL2TP) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (get_user(len, optlen)) return -EFAULT; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index ebf80f3abd83..653ce5d9e6e0 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read( ssize_t ret = -EINVAL; read_lock(&dev_base_lock); - if (sdata->dev->reg_state == NETREG_REGISTERED) - ret = (*format)(sdata, buf, sizeof(buf)); + ret = (*format)(sdata, buf, sizeof(buf)); read_unlock(&dev_base_lock); if (ret >= 0) @@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write( ret = -ENODEV; rtnl_lock(); - if (sdata->dev->reg_state == NETREG_REGISTERED) - ret = (*write)(sdata, buf, count); + ret = (*write)(sdata, buf, count); rtnl_unlock(); return ret; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 2796a198728f..ea7013cb7e52 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1655,6 +1655,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, sdata->u.ibss.control_port = params->control_port; sdata->u.ibss.userspace_handles_dfs = params->userspace_handles_dfs; sdata->u.ibss.basic_rates = params->basic_rates; + sdata->u.ibss.last_scan_completed = jiffies; /* fix basic_rates if channel does not support these rates */ rate_flags = ieee80211_chandef_rate_flags(¶ms->chandef); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 5e44e3179e02..b127902361f4 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -317,6 +317,7 @@ struct ieee80211_roc_work { bool started, abort, hw_begun, notified; bool to_be_freed; + bool on_channel; unsigned long hw_start_time; @@ -1385,6 +1386,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata); void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata); void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata, __le16 fc, bool acked); +void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata); /* IBSS code */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index ce1c44370610..8f7fabc46c97 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1761,7 +1761,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) } mutex_unlock(&local->iflist_mtx); unregister_netdevice_many(&unreg_list); - list_del(&unreg_list); list_for_each_entry_safe(sdata, tmp, &wdev_list, list) { list_del(&sdata->list); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d767cfb9b45f..c7a7a86afdb8 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -148,6 +148,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (!rcu_access_pointer(sdata->vif.chanctx_conf)) continue; + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; power = min(power, sdata->vif.bss_conf.txpower); } rcu_read_unlock(); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 245dce969b31..189eef014c4f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2708,8 +2708,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems, channel); if (bss) { - ieee80211_rx_bss_put(local, bss); sdata->vif.bss_conf.beacon_rate = bss->beacon_rate; + ieee80211_rx_bss_put(local, bss); } } @@ -3504,6 +3504,38 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) } #ifdef CONFIG_PM +void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + sdata_lock(sdata); + + if (ifmgd->auth_data || ifmgd->assoc_data) { + const u8 *bssid = ifmgd->auth_data ? + ifmgd->auth_data->bss->bssid : + ifmgd->assoc_data->bss->bssid; + + /* + * If we are trying to authenticate / associate while suspending, + * cfg80211 won't know and won't actually abort those attempts, + * thus we need to do that ourselves. + */ + ieee80211_send_deauth_disassoc(sdata, bssid, + IEEE80211_STYPE_DEAUTH, + WLAN_REASON_DEAUTH_LEAVING, + false, frame_buf); + if (ifmgd->assoc_data) + ieee80211_destroy_assoc_data(sdata, false); + if (ifmgd->auth_data) + ieee80211_destroy_auth_data(sdata, false); + cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, + IEEE80211_DEAUTH_FRAME_LEN); + } + + sdata_unlock(sdata); +} + void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -4208,8 +4240,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (bss->wmm_used && bss->uapsd_supported && - (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) && - sdata->wmm_acm != 0xff) { + (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { assoc_data->uapsd = true; ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED; } else { diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 0c2a29484c07..7a17decd27f9 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) container_of(work, struct ieee80211_roc_work, work.work); struct ieee80211_sub_if_data *sdata = roc->sdata; struct ieee80211_local *local = sdata->local; - bool started; + bool started, on_channel; mutex_lock(&local->mtx); @@ -354,13 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work) if (!roc->started) { struct ieee80211_roc_work *dep; - /* start this ROC */ + WARN_ON(local->use_chanctx); + + /* If actually operating on the desired channel (with at least + * 20 MHz channel width) don't stop all the operations but still + * treat it as though the ROC operation started properly, so + * other ROC operations won't interfere with this one. + */ + roc->on_channel = roc->chan == local->_oper_chandef.chan && + local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 && + local->_oper_chandef.width != NL80211_CHAN_WIDTH_10; - /* switch channel etc */ + /* start this ROC */ ieee80211_recalc_idle(local); - local->tmp_channel = roc->chan; - ieee80211_hw_config(local, 0); + if (!roc->on_channel) { + ieee80211_offchannel_stop_vifs(local); + + local->tmp_channel = roc->chan; + ieee80211_hw_config(local, 0); + } /* tell userspace or send frame */ ieee80211_handle_roc_started(roc); @@ -379,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work) finish: list_del(&roc->list); started = roc->started; + on_channel = roc->on_channel; ieee80211_roc_notify_destroy(roc, !roc->abort); - if (started) { + if (started && !on_channel) { ieee80211_flush_queues(local, NULL); local->tmp_channel = NULL; diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index af64fb8e8add..d478b880a0af 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -100,10 +100,18 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) /* remove all interfaces that were created in the driver */ list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata) || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MONITOR) + if (!ieee80211_sdata_running(sdata)) continue; + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + continue; + case NL80211_IFTYPE_STATION: + ieee80211_mgd_quiesce(sdata); + break; + default: + break; + } drv_remove_interface(local, sdata); } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 22b223f13c9f..74350c3863b8 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -462,7 +462,7 @@ static void rate_fixup_ratelist(struct ieee80211_vif *vif, */ if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) { u32 basic_rates = vif->bss_conf.basic_rates; - s8 baserate = basic_rates ? ffs(basic_rates - 1) : 0; + s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0; rate = &sband->bitrates[rates[0].idx]; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 137a192e64bc..bedaeecdab97 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -240,6 +240,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); + kfree(rcu_dereference_raw(sta->sta.rates)); kfree(sta); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 4080c615636f..e5a7ac2f3687 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -414,6 +414,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (ieee80211_has_order(hdr->frame_control)) return TX_CONTINUE; + if (ieee80211_is_probe_req(hdr->frame_control)) + return TX_CONTINUE; + if (tx->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) info->hw_queue = tx->sdata->vif.cab_queue; @@ -464,6 +467,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) { struct sta_info *sta = tx->sta; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; struct ieee80211_local *local = tx->local; if (unlikely(!sta)) @@ -474,6 +478,15 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) { int ac = skb_get_queue_mapping(tx->skb); + /* only deauth, disassoc and action are bufferable MMPDUs */ + if (ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_is_deauth(hdr->frame_control) && + !ieee80211_is_disassoc(hdr->frame_control) && + !ieee80211_is_action(hdr->frame_control)) { + info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; + return TX_CONTINUE; + } + ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n", sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) @@ -532,22 +545,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED)) return TX_CONTINUE; - - /* only deauth, disassoc and action are bufferable MMPDUs */ - if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_deauth(hdr->frame_control) && - !ieee80211_is_disassoc(hdr->frame_control) && - !ieee80211_is_action(hdr->frame_control)) { - if (tx->flags & IEEE80211_TX_UNICAST) - info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; - return TX_CONTINUE; - } - if (tx->flags & IEEE80211_TX_UNICAST) return ieee80211_tx_h_unicast_ps_buf(tx); else @@ -2909,7 +2908,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, cpu_to_le16(IEEE80211_FCTL_MOREDATA); } - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + if (sdata->vif.type == NL80211_IFTYPE_AP) sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); if (!ieee80211_tx_prepare(sdata, &tx, skb)) break; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index b8700d417a9c..642762518213 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1754,7 +1754,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_unlock(&local->mtx); if (sched_scan_stopped) - cfg80211_sched_scan_stopped(local->hw.wiphy); + cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy); /* * If this is for hw restart things are still running. diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a8eb0a89326a..610e19c0e13f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data) ip_vs_control_del(cp); if (cp->flags & IP_VS_CONN_F_NFCT) { - ip_vs_conn_drop_conntrack(cp); /* Do not access conntracks during subsys cleanup * because nf_conntrack_find_get can not be used after * conntrack cleanup for the net. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f26ee46b51f..27d3f40de3cd 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1392,15 +1392,19 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) if (ipip) { __be32 info = ic->un.gateway; + __u8 type = ic->type; + __u8 code = ic->code; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); + __be16 frag_off = cih->frag_off; /* Strip outer IP and ICMP, go to IPIP header */ - __skb_pull(skb, ihl + sizeof(_icmph)); + if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) + goto ignore_ipip; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", @@ -1408,7 +1412,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ipv4_update_pmtu(skb, dev_net(skb->dev), mtu, 0, 0, 0, 0); /* Client uses PMTUD? */ - if (!(cih->frag_off & htons(IP_DF))) + if (!(frag_off & htons(IP_DF))) goto ignore_ipip; /* Prefer the resulting PMTU */ if (dest) { @@ -1427,12 +1431,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) /* Strip outer IP, ICMP and IPIP, go to IP header of * original request. */ - __skb_pull(skb, offset2); + if (pskb_pull(skb, offset2) == NULL) + goto ignore_ipip; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, - ic->type, ic->code, ntohl(info)); - icmp_send(skb, ic->type, ic->code, info); + type, code, ntohl(info)); + icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb); @@ -1901,7 +1906,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_reply6, .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index c47444e4cf8c..1692e7534759 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(skb, &rt->dst, NULL); + ip_select_ident(skb, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, iph->nexthdr = IPPROTO_IPV6; iph->payload_len = old_iph->payload_len; be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); - iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); + ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph)); iph->daddr = cp->daddr.in6; iph->saddr = saddr; iph->hop_limit = old_iph->hop_limit; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 52ca952b802c..23247a0d2b69 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -517,6 +517,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data) return i->status & IPS_NAT_MASK ? 1 : 0; } +static int nf_nat_proto_clean(struct nf_conn *ct, void *data) +{ + struct nf_conn_nat *nat = nfct_nat(ct); + + if (nf_nat_proto_remove(ct, data)) + return 1; + + if (!nat || !nat->ct) + return 0; + + /* This netns is being destroyed, and conntrack has nat null binding. + * Remove it from bysource hash, as the table will be freed soon. + * + * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack() + * will delete entry from already-freed table. + */ + if (!del_timer(&ct->timeout)) + return 1; + + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + ct->status &= ~IPS_NAT_DONE_MASK; + nat->ct = NULL; + spin_unlock_bh(&nf_nat_lock); + + add_timer(&ct->timeout); + + /* don't delete conntrack. Although that would make things a lot + * simpler, we'd end up flushing all conntracks on nat rmmod. + */ + return 0; +} + static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) { struct nf_nat_proto_clean clean = { @@ -787,7 +820,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0); + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index adce01e8bb57..c68e5e0628df 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1934,7 +1934,8 @@ static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_TABLE] = { .type = NLA_STRING }, - [NFTA_SET_NAME] = { .type = NLA_STRING }, + [NFTA_SET_NAME] = { .type = NLA_STRING, + .len = IFNAMSIZ - 1 }, [NFTA_SET_FLAGS] = { .type = NLA_U32 }, [NFTA_SET_KEY_TYPE] = { .type = NLA_U32 }, [NFTA_SET_KEY_LEN] = { .type = NLA_U32 }, diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 90998a6ff8b9..804105391b9a 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -25,9 +25,8 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr, struct nft_data data[NFT_REG_MAX + 1]) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); - u32 mask; + u32 mask = nft_cmp_fast_mask(priv->len); - mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - priv->len); if ((data[priv->sreg].data[0] & mask) == priv->data) return; data[NFT_REG_VERDICT].verdict = NFT_BREAK; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 046aa13b4fea..bf8a108b46e2 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -248,15 +248,15 @@ replay: #endif { nfnl_unlock(subsys_id); - kfree_skb(nskb); - return netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(skb, nlh, -EOPNOTSUPP); + return kfree_skb(nskb); } } if (!ss->commit || !ss->abort) { nfnl_unlock(subsys_id); - kfree_skb(nskb); - return netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(skb, nlh, -EOPNOTSUPP); + return kfree_skb(skb); } while (skb->len >= nlmsg_total_size(0)) { @@ -367,7 +367,7 @@ static void nfnetlink_rcv(struct sk_buff *skb) skb->len < nlh->nlmsg_len) return; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) { netlink_ack(skb, nlh, -EPERM); return; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 954925db414d..e2b3f51c81f1 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -128,7 +128,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, BUG_ON(err < 0); desc.len *= BITS_PER_BYTE; - mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - desc.len); + mask = nft_cmp_fast_mask(desc.len); priv->data = data.data[0] & mask; priv->len = desc.len; return 0; diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 9a8e77e7f8d4..ef5c75a5b200 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -31,7 +31,7 @@ static int cgroup_mt_check(const struct xt_mtchk_param *par) if (info->invert & ~1) return -EINVAL; - return info->id ? 0 : -EINVAL; + return 0; } static bool diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index a3910fc2122b..47dc6836830a 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -104,7 +104,7 @@ struct xt_hashlimit_htable { spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ unsigned int count; /* number entries in table */ - struct timer_list timer; /* timer for gc */ + struct delayed_work gc_work; /* seq_file stuff */ struct proc_dir_entry *pde; @@ -213,7 +213,7 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) call_rcu_bh(&ent->rcu, dsthash_free_rcu); ht->count--; } -static void htable_gc(unsigned long htlong); +static void htable_gc(struct work_struct *work); static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) @@ -273,9 +273,9 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, } hinfo->net = net; - setup_timer(&hinfo->timer, htable_gc, (unsigned long)hinfo); - hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); - add_timer(&hinfo->timer); + INIT_DEFERRABLE_WORK(&hinfo->gc_work, htable_gc); + queue_delayed_work(system_power_efficient_wq, &hinfo->gc_work, + msecs_to_jiffies(hinfo->cfg.gc_interval)); hlist_add_head(&hinfo->node, &hashlimit_net->htables); @@ -300,29 +300,30 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, { unsigned int i; - /* lock hash table and iterate over it */ - spin_lock_bh(&ht->lock); for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; struct hlist_node *n; + + spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if ((*select)(ht, dh)) dsthash_free(ht, dh); } + spin_unlock_bh(&ht->lock); + cond_resched(); } - spin_unlock_bh(&ht->lock); } -/* hash table garbage collector, run by timer */ -static void htable_gc(unsigned long htlong) +static void htable_gc(struct work_struct *work) { - struct xt_hashlimit_htable *ht = (struct xt_hashlimit_htable *)htlong; + struct xt_hashlimit_htable *ht; + + ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); htable_selective_cleanup(ht, select_gc); - /* re-add the timer accordingly */ - ht->timer.expires = jiffies + msecs_to_jiffies(ht->cfg.gc_interval); - add_timer(&ht->timer); + queue_delayed_work(system_power_efficient_wq, + &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); } static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) @@ -341,7 +342,7 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) static void htable_destroy(struct xt_hashlimit_htable *hinfo) { - del_timer_sync(&hinfo->timer); + cancel_delayed_work_sync(&hinfo->gc_work); htable_remove_proc_entry(hinfo); htable_selective_cleanup(hinfo, select_all); kfree(hinfo->name); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 04748ab649c2..7c177bc43806 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -205,7 +205,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; - + skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); @@ -636,7 +636,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock, while (nlk->cb_running && netlink_dump_space(nlk)) { err = netlink_dump(sk); if (err < 0) { - sk->sk_err = err; + sk->sk_err = -err; sk->sk_error_report(sk); break; } @@ -707,7 +707,7 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, * after validation, the socket and the ring may only be used by a * single process, otherwise we fall back to copying. */ - if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 || + if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 || atomic_read(&nlk->mapped) > 1) excl = false; @@ -1360,7 +1360,74 @@ retry: return err; } -static inline int netlink_capable(const struct socket *sock, unsigned int flag) +/** + * __netlink_ns_capable - General netlink message capability test + * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, + struct user_namespace *user_ns, int cap) +{ + return ((nsp->flags & NETLINK_SKB_DST) || + file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(__netlink_ns_capable); + +/** + * netlink_ns_capable - General netlink message capability test + * @skb: socket buffer holding a netlink command from userspace + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool netlink_ns_capable(const struct sk_buff *skb, + struct user_namespace *user_ns, int cap) +{ + return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); +} +EXPORT_SYMBOL(netlink_ns_capable); + +/** + * netlink_capable - Netlink global message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in all user namespaces. + */ +bool netlink_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, &init_user_ns, cap); +} +EXPORT_SYMBOL(netlink_capable); + +/** + * netlink_net_capable - Netlink network namespace message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap over the network namespace of + * the socket we received the message from. + */ +bool netlink_net_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); +} +EXPORT_SYMBOL(netlink_net_capable); + +static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); @@ -1428,7 +1495,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, /* Only superuser is allowed to listen multicasts */ if (nladdr->nl_groups) { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -1490,7 +1557,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if ((nladdr->nl_groups || nladdr->nl_pid) && - !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; if (!nlk->portid) @@ -2096,7 +2163,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -2228,6 +2295,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sk_buff *skb; int err; struct scm_cookie scm; + u32 netlink_skb_flags = 0; if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP; @@ -2247,8 +2315,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && - !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; + netlink_skb_flags |= NETLINK_SKB_DST; } else { dst_portid = nlk->dst_portid; dst_group = nlk->dst_group; @@ -2278,6 +2347,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = siocb->scm->creds; + NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { @@ -2378,7 +2448,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { - sk->sk_err = ret; + sk->sk_err = -ret; sk->sk_error_report(sk); } } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index b1dcdb932a86..a3ba3ca0ff92 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -561,7 +561,7 @@ static int genl_family_rcv_msg(struct genl_family *family, return -EOPNOTSUPP; if ((ops->flags & GENL_ADMIN_PERM) && - !capable(CAP_NET_ADMIN)) + !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2c77e7b1a913..600c7646b3d3 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -42,6 +42,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, static int make_writable(struct sk_buff *skb, int write_len) { + if (!pskb_may_pull(skb, write_len)) + return -ENOMEM; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; @@ -70,6 +73,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci) vlan_set_encap_proto(skb, vhdr); skb->mac_header += VLAN_HLEN; + if (skb_network_offset(skb) < ETH_HLEN) + skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return 0; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 48a6a93db296..48b181797d7b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -635,6 +635,7 @@ static void init_prb_bdqc(struct packet_sock *po, p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; + p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po, tx_ring); prb_open_block(p1, pbd); @@ -1946,6 +1947,18 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if ((int)snaplen < 0) snaplen = 0; } + } else if (unlikely(macoff + snaplen > + GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { + u32 nval; + + nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; + pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", + snaplen, nval, macoff); + snaplen = nval; + if (unlikely((int)snaplen < 0)) { + snaplen = 0; + macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; + } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, @@ -3779,6 +3792,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) goto out; + if (po->tp_version >= TPACKET_V3 && + (int)(req->tp_block_size - + BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0) + goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + po->tp_reserve)) goto out; diff --git a/net/packet/diag.c b/net/packet/diag.c index 533ce4ff108a..92f2c7107eec 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -128,6 +128,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb) static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, + bool may_report_filterinfo, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, int sk_ino) { @@ -172,7 +173,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_FILTER) && - sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER)) + sock_diag_put_filterinfo(may_report_filterinfo, sk, skb, + PACKET_DIAG_FILTER)) goto out_nlmsg_trim; return nlmsg_end(skb, nlh); @@ -188,9 +190,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct packet_diag_req *req; struct net *net; struct sock *sk; + bool may_report_filterinfo; net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); + may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN); mutex_lock(&net->packet.sklist_lock); sk_for_each(sk, &net->packet.sklist) { @@ -200,6 +204,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (sk_diag_fill(sk, skb, req, + may_report_filterinfo, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, diff --git a/net/packet/internal.h b/net/packet/internal.h index eb9580a6b25f..cdddf6a30399 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -29,6 +29,7 @@ struct tpacket_kbdq_core { char *pkblk_start; char *pkblk_end; int kblk_size; + unsigned int max_frame_len; unsigned int knum_blocks; uint64_t knxt_seq_num; char *prev; diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index dc15f4300808..b64151ade6b3 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 pnaddr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); @@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 dst; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); diff --git a/net/rds/iw.c b/net/rds/iw.c index 7826d46baa70..589935661d66 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr) ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); /* due to this, we will claim to support IB devices unless we check node_type. */ - if (ret || cm_id->device->node_type != RDMA_NODE_RNIC) + if (ret || !cm_id->device || + cm_id->device->node_type != RDMA_NODE_RNIC) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI4 ret %d node type %d\n", diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 72bdc7166345..3b2265523552 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -908,7 +908,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; - if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 29a30a14c315..bdbdb1a7920a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -134,7 +134,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n) int err; int tp_created = 0; - if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index eed8404443d8..f435a88d899a 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -188,6 +188,12 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, }; +static void tcindex_filter_result_init(struct tcindex_filter_result *r) +{ + memset(r, 0, sizeof(*r)); + tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); +} + static int tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_data *p, @@ -207,15 +213,11 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, return err; memcpy(&cp, p, sizeof(cp)); - memset(&new_filter_result, 0, sizeof(new_filter_result)); - tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); + tcindex_filter_result_init(&new_filter_result); + tcindex_filter_result_init(&cr); if (old_r) - memcpy(&cr, r, sizeof(cr)); - else { - memset(&cr, 0, sizeof(cr)); - tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - } + cr.res = r->res; if (tb[TCA_TCINDEX_HASH]) cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -267,9 +269,14 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp.perfect && !cp.h) { if (valid_perfect_hash(&cp)) { + int i; + cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL); if (!cp.perfect) goto errout; + for (i = 0; i < cp.hash; i++) + tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT, + TCA_TCINDEX_POLICE); balloc = 1; } else { cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL); @@ -295,14 +302,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, tcf_bind_filter(tp, &cr.res, base); } - tcf_exts_change(tp, &cr.exts, &e); + if (old_r) + tcf_exts_change(tp, &r->exts, &e); + else + tcf_exts_change(tp, &cr.exts, &e); tcf_tree_lock(tp); if (old_r && old_r != r) - memset(old_r, 0, sizeof(*old_r)); + tcindex_filter_result_init(old_r); memcpy(p, &cp, sizeof(cp)); - memcpy(r, &cr, sizeof(cr)); + r->res = cr.res; if (r == &new_filter_result) { struct tcindex_filter **fp; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a07d55e75698..98532cfa7823 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1084,7 +1084,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *p = NULL; int err; - if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1151,7 +1151,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *q, *p; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: @@ -1491,7 +1491,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n) u32 qid; int err; - if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 647680b1c625..039977830783 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -553,11 +553,6 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) if (err < 0) return err; - sch_tree_lock(sch); - - if (tb[TCA_HHF_BACKLOG_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]); - if (tb[TCA_HHF_QUANTUM]) new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]); @@ -567,6 +562,12 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight; if (non_hh_quantum > INT_MAX) return -EINVAL; + + sch_tree_lock(sch); + + if (tb[TCA_HHF_BACKLOG_LIMIT]) + sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]); + q->quantum = new_quantum; q->hhf_non_hh_weight = new_hhf_non_hh_weight; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index ee13d28d39d1..5d97d8fe4be7 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -330,7 +330,7 @@ void sctp_association_free(struct sctp_association *asoc) /* Only real associations count against the endpoint, so * don't bother for if this is a temporary association. */ - if (!asoc->temp) { + if (!list_empty(&asoc->asocs)) { list_del(&asoc->asocs); /* Decrement the backlog value for a TCP-style listening @@ -1151,6 +1151,7 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->c = new->c; asoc->peer.rwnd = new->peer.rwnd; asoc->peer.sack_needed = new->peer.sack_needed; + asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, asoc->peer.i.initial_tsn, GFP_ATOMIC); @@ -1396,35 +1397,44 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) return false; } -/* Update asoc's rwnd for the approximated state in the buffer, - * and check whether SACK needs to be sent. - */ -void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) +/* Increase asoc's rwnd by len and send any window update SACK if needed. */ +void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) { - int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); + if (asoc->rwnd_over) { + if (asoc->rwnd_over >= len) { + asoc->rwnd_over -= len; + } else { + asoc->rwnd += (len - asoc->rwnd_over); + asoc->rwnd_over = 0; + } + } else { + asoc->rwnd += len; + } - if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) - asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; - else - asoc->rwnd = 0; + /* If we had window pressure, start recovering it + * once our rwnd had reached the accumulated pressure + * threshold. The idea is to recover slowly, but up + * to the initial advertised window. + */ + if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { + int change = min(asoc->pathmtu, asoc->rwnd_press); + asoc->rwnd += change; + asoc->rwnd_press -= change; + } - pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", - __func__, asoc, asoc->rwnd, rx_count, - asoc->base.sk->sk_rcvbuf); + pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", + __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, + asoc->a_rwnd); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (update_peer && sctp_peer_needs_update(asoc)) { + if (sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1446,6 +1456,45 @@ void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) } } +/* Decrease asoc's rwnd by len. */ +void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) +{ + int rx_count; + int over = 0; + + if (unlikely(!asoc->rwnd || asoc->rwnd_over)) + pr_debug("%s: association:%p has asoc->rwnd:%u, " + "asoc->rwnd_over:%u!\n", __func__, asoc, + asoc->rwnd, asoc->rwnd_over); + + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); + + /* If we've reached or overflowed our receive buffer, announce + * a 0 rwnd if rwnd would still be positive. Store the + * the potential pressure overflow so that the window can be restored + * back to original value. + */ + if (rx_count >= asoc->base.sk->sk_rcvbuf) + over = 1; + + if (asoc->rwnd >= len) { + asoc->rwnd -= len; + if (over) { + asoc->rwnd_press += asoc->rwnd; + asoc->rwnd = 0; + } + } else { + asoc->rwnd_over = len - asoc->rwnd; + asoc->rwnd = 0; + } + + pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", + __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, + asoc->rwnd_press); +} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 683c7d1b1306..0e8529113dc5 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -386,14 +386,13 @@ nomem: */ int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp) { - struct net *net = sock_net(asoc->base.sk); struct sctp_auth_bytes *secret; struct sctp_shared_key *ep_key; /* If we don't support AUTH, or peer is not capable * we don't need to do anything. */ - if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + if (!asoc->ep->auth_enable || !asoc->peer.auth_capable) return 0; /* If the key_id is non-zero and we couldn't find an @@ -440,16 +439,16 @@ struct sctp_shared_key *sctp_auth_get_shkey( */ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) { - struct net *net = sock_net(ep->base.sk); struct crypto_hash *tfm = NULL; __u16 id; - /* if the transforms are already allocted, we are done */ - if (!net->sctp.auth_enable) { + /* If AUTH extension is disabled, we are done */ + if (!ep->auth_enable) { ep->auth_hmacs = NULL; return 0; } + /* If the transforms are already allocated, we are done */ if (ep->auth_hmacs) return 0; @@ -665,12 +664,10 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) /* Check if peer requested that this chunk is authenticated */ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) { - struct net *net; if (!asoc) return 0; - net = sock_net(asoc->base.sk); - if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + if (!asoc->ep->auth_enable || !asoc->peer.auth_capable) return 0; return __sctp_auth_cid(chunk, asoc->peer.peer_chunks); @@ -679,12 +676,10 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) /* Check if we requested that peer authenticate this chunk. */ int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc) { - struct net *net; if (!asoc) return 0; - net = sock_net(asoc->base.sk); - if (!net->sctp.auth_enable) + if (!asoc->ep->auth_enable) return 0; return __sctp_auth_cid(chunk, diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 8e5fdea05216..3d9f429858dc 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -68,7 +68,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, if (!ep->digest) return NULL; - if (net->sctp.auth_enable) { + ep->auth_enable = net->sctp.auth_enable; + if (ep->auth_enable) { /* Allocate space for HMACS and CHUNKS authentication * variables. There are arrays that we encode directly * into parameters to make the rest of the operations easier. diff --git a/net/sctp/output.c b/net/sctp/output.c index 0f4d15fc2627..8267b06c3646 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -599,7 +599,7 @@ out: return err; no_route: kfree_skb(nskb); - IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); /* FIXME: Returning the 'err' will effect all the associations * associated with a socket, although only one of the paths of the diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 4e1d0fcb028e..a62a215dd22e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -491,8 +491,13 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, continue; if ((laddr->state == SCTP_ADDR_SRC) && (AF_INET == laddr->a.sa.sa_family)) { - fl4->saddr = laddr->a.v4.sin_addr.s_addr; fl4->fl4_sport = laddr->a.v4.sin_port; + flowi4_update_output(fl4, + asoc->base.sk->sk_bound_dev_if, + RT_CONN_FLAGS(asoc->base.sk), + daddr->v4.sin_addr.s_addr, + laddr->a.v4.sin_addr.s_addr); + rt = ip_route_output_key(sock_net(sk), fl4); if (!IS_ERR(rt)) { dst = &rt->dst; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 3a1767ef3201..fee5552ddf92 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -219,6 +219,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, gfp_t gfp, int vparam_len) { struct net *net = sock_net(asoc->base.sk); + struct sctp_endpoint *ep = asoc->ep; sctp_inithdr_t init; union sctp_params addrs; size_t chunksize; @@ -278,7 +279,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, chunksize += vparam_len; /* Account for AUTH related parameters */ - if (net->sctp.auth_enable) { + if (ep->auth_enable) { /* Add random parameter length*/ chunksize += sizeof(asoc->c.auth_random); @@ -363,7 +364,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, } /* Add SCTP-AUTH chunks to the parameter list */ - if (net->sctp.auth_enable) { + if (ep->auth_enable) { sctp_addto_chunk(retval, sizeof(asoc->c.auth_random), asoc->c.auth_random); if (auth_hmacs) @@ -2010,7 +2011,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc, /* if the peer reports AUTH, assume that he * supports AUTH. */ - if (net->sctp.auth_enable) + if (asoc->ep->auth_enable) asoc->peer.auth_capable = 1; break; case SCTP_CID_ASCONF: @@ -2102,6 +2103,7 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, * SCTP_IERROR_NO_ERROR - continue with the chunk */ static sctp_ierror_t sctp_verify_param(struct net *net, + const struct sctp_endpoint *ep, const struct sctp_association *asoc, union sctp_params param, sctp_cid_t cid, @@ -2152,7 +2154,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, goto fallthrough; case SCTP_PARAM_RANDOM: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; /* SCTP-AUTH: Secion 6.1 @@ -2169,7 +2171,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, break; case SCTP_PARAM_CHUNKS: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; /* SCTP-AUTH: Section 3.2 @@ -2185,7 +2187,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, break; case SCTP_PARAM_HMAC_ALGO: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; hmacs = (struct sctp_hmac_algo_param *)param.p; @@ -2220,10 +2222,9 @@ fallthrough: } /* Verify the INIT packet before we process it. */ -int sctp_verify_init(struct net *net, const struct sctp_association *asoc, - sctp_cid_t cid, - sctp_init_chunk_t *peer_init, - struct sctp_chunk *chunk, +int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, sctp_cid_t cid, + sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **errp) { union sctp_params param; @@ -2264,8 +2265,8 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc, /* Verify all the variable length parameters */ sctp_walk_params(param, peer_init, init_hdr.params) { - - result = sctp_verify_param(net, asoc, param, cid, chunk, errp); + result = sctp_verify_param(net, ep, asoc, param, cid, + chunk, errp); switch (result) { case SCTP_IERROR_ABORT: case SCTP_IERROR_NOMEM: @@ -2497,6 +2498,7 @@ static int sctp_process_param(struct sctp_association *asoc, struct sctp_af *af; union sctp_addr_param *addr_param; struct sctp_transport *t; + struct sctp_endpoint *ep = asoc->ep; /* We maintain all INIT parameters in network byte order all the * time. This allows us to not worry about whether the parameters @@ -2636,7 +2638,7 @@ do_addr_param: goto fall_through; case SCTP_PARAM_RANDOM: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; /* Save peer's random parameter */ @@ -2649,7 +2651,7 @@ do_addr_param: break; case SCTP_PARAM_HMAC_ALGO: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; /* Save peer's HMAC list */ @@ -2665,7 +2667,7 @@ do_addr_param: break; case SCTP_PARAM_CHUNKS: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; asoc->peer.peer_chunks = kmemdup(param.p, diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 5d6883ff00c3..fef2acdf4a2e 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -496,11 +496,10 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, /* If the transport error count is greater than the pf_retrans * threshold, and less than pathmaxrtx, and if the current state - * is not SCTP_UNCONFIRMED, then mark this transport as Partially - * Failed, see SCTP Quick Failover Draft, section 5.1 + * is SCTP_ACTIVE, then mark this transport as Partially Failed, + * see SCTP Quick Failover Draft, section 5.1 */ - if ((transport->state != SCTP_PF) && - (transport->state != SCTP_UNCONFIRMED) && + if ((transport->state == SCTP_ACTIVE) && (asoc->pf_retrans < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 01e002430c85..7194fe8589b0 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -357,7 +357,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. @@ -524,7 +524,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { @@ -1430,7 +1430,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. @@ -1775,9 +1775,22 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, - SCTP_STATE(SCTP_STATE_ESTABLISHED)); - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + if (sctp_state(asoc, SHUTDOWN_PENDING) && + (sctp_sstate(asoc->base.sk, CLOSING) || + sock_flag(asoc->base.sk, SOCK_DEAD))) { + /* if were currently in SHUTDOWN_PENDING, but the socket + * has been closed by user, don't transition to ESTABLISHED. + * Instead trigger SHUTDOWN bundled with COOKIE_ACK. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, + SCTP_ST_CHUNK(0), NULL, + commands); + } else { + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + } return SCTP_DISPOSITION_CONSUME; nomem_ev: @@ -6178,7 +6191,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || + if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 981aaf8b6ace..604a6acdf92e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2115,6 +2115,12 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); + /* When only partial message is copied to the user, increase + * rwnd by that amount. If all the data in the skb is read, + * rwnd is updated when the event is freed. + */ + if (!sctp_ulpevent_is_notification(event)) + sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) @@ -3315,10 +3321,10 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunk val; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authchunk)) @@ -3335,7 +3341,7 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, } /* add this chunk id to the endpoint */ - return sctp_auth_ep_add_chunkid(sctp_sk(sk)->ep, val.sauth_chunk); + return sctp_auth_ep_add_chunkid(ep, val.sauth_chunk); } /* @@ -3348,12 +3354,12 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo *hmacs; u32 idents; int err; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen < sizeof(struct sctp_hmacalgo)) @@ -3370,7 +3376,7 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, goto out; } - err = sctp_auth_ep_set_hmacs(sctp_sk(sk)->ep, hmacs); + err = sctp_auth_ep_set_hmacs(ep, hmacs); out: kfree(hmacs); return err; @@ -3386,12 +3392,12 @@ static int sctp_setsockopt_auth_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkey *authkey; struct sctp_association *asoc; int ret; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen <= sizeof(struct sctp_authkey)) @@ -3412,7 +3418,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, goto out; } - ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey); + ret = sctp_auth_set_key(ep, asoc, authkey); out: kzfree(authkey); return ret; @@ -3428,11 +3434,11 @@ static int sctp_setsockopt_active_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authkeyid)) @@ -3444,8 +3450,7 @@ static int sctp_setsockopt_active_key(struct sock *sk, if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_set_active_key(sctp_sk(sk)->ep, asoc, - val.scact_keynumber); + return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); } /* @@ -3457,11 +3462,11 @@ static int sctp_setsockopt_del_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authkeyid)) @@ -3473,8 +3478,7 @@ static int sctp_setsockopt_del_key(struct sock *sk, if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_del_key_id(sctp_sk(sk)->ep, asoc, - val.scact_keynumber); + return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); } @@ -5381,16 +5385,16 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo __user *p = (void __user *)optval; struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; - hmacs = sctp_sk(sk)->ep->auth_hmacs_list; + hmacs = ep->auth_hmacs_list; data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t); if (len < sizeof(struct sctp_hmacalgo) + data_len) @@ -5411,11 +5415,11 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, static int sctp_getsockopt_active_key(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authkeyid)) @@ -5430,7 +5434,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, if (asoc) val.scact_keynumber = asoc->active_key_id; else - val.scact_keynumber = sctp_sk(sk)->ep->active_key_id; + val.scact_keynumber = ep->active_key_id; len = sizeof(struct sctp_authkeyid); if (put_user(len, optlen)) @@ -5444,7 +5448,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; @@ -5452,7 +5456,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, u32 num_chunks = 0; char __user *to; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authchunks)) @@ -5489,7 +5493,7 @@ num: static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; @@ -5497,7 +5501,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, u32 num_chunks = 0; char __user *to; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authchunks)) @@ -5514,7 +5518,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, if (asoc) ch = (struct sctp_chunks_param *)asoc->c.auth_chunks; else - ch = sctp_sk(sk)->ep->auth_chunk_list; + ch = ep->auth_chunk_list; if (!ch) goto num; @@ -6593,6 +6597,46 @@ static void __sctp_write_space(struct sctp_association *asoc) } } +static void sctp_wake_up_waiters(struct sock *sk, + struct sctp_association *asoc) +{ + struct sctp_association *tmp = asoc; + + /* We do accounting for the sndbuf space per association, + * so we only need to wake our own association. + */ + if (asoc->ep->sndbuf_policy) + return __sctp_write_space(asoc); + + /* If association goes down and is just flushing its + * outq, then just normally notify others. + */ + if (asoc->base.dead) + return sctp_write_space(sk); + + /* Accounting for the sndbuf space is per socket, so we + * need to wake up others, try to be fair and in case of + * other associations, let them have a go first instead + * of just doing a sctp_write_space() call. + * + * Note that we reach sctp_wake_up_waiters() only when + * associations free up queued chunks, thus we are under + * lock and the list of associations on a socket is + * guaranteed not to change. + */ + for (tmp = list_next_entry(tmp, asocs); 1; + tmp = list_next_entry(tmp, asocs)) { + /* Manually skip the head element. */ + if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs)) + continue; + /* Wake up association. */ + __sctp_write_space(tmp); + /* We've reached the end. */ + if (tmp == asoc) + break; + } +} + /* Do accounting for the sndbuf space. * Decrement the used sndbuf space of the corresponding association by the * data size which was just transmitted(freed). @@ -6620,7 +6664,7 @@ static void sctp_wfree(struct sk_buff *skb) sk_mem_uncharge(sk, skb->truesize); sock_wfree(skb); - __sctp_write_space(asoc); + sctp_wake_up_waiters(sk, asoc); sctp_association_put(asoc); } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 35c8923b5554..dfa532f00d88 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -64,6 +64,9 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); static struct ctl_table sctp_table[] = { { @@ -266,7 +269,7 @@ static struct ctl_table sctp_net_table[] = { .data = &init_net.sctp.auth_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_sctp_do_auth, }, { .procname = "addr_scope_policy", @@ -304,41 +307,40 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; - char tmp[8]; struct ctl_table tbl; - int ret; - int changed = 0; + bool changed = false; char *none = "none"; + char tmp[8]; + int ret; memset(&tbl, 0, sizeof(struct ctl_table)); if (write) { tbl.data = tmp; - tbl.maxlen = 8; + tbl.maxlen = sizeof(tmp); } else { tbl.data = net->sctp.sctp_hmac_alg ? : none; tbl.maxlen = strlen(tbl.data); } - ret = proc_dostring(&tbl, write, buffer, lenp, ppos); - if (write) { + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { #ifdef CONFIG_CRYPTO_MD5 if (!strncmp(tmp, "md5", 3)) { net->sctp.sctp_hmac_alg = "md5"; - changed = 1; + changed = true; } #endif #ifdef CONFIG_CRYPTO_SHA1 if (!strncmp(tmp, "sha1", 4)) { net->sctp.sctp_hmac_alg = "sha1"; - changed = 1; + changed = true; } #endif if (!strncmp(tmp, "none", 4)) { net->sctp.sctp_hmac_alg = NULL; - changed = 1; + changed = true; } - if (!changed) ret = -EINVAL; } @@ -351,11 +353,10 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; - int new_value; - struct ctl_table tbl; unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; - int ret; + struct ctl_table tbl; + int ret, new_value; memset(&tbl, 0, sizeof(struct ctl_table)); tbl.maxlen = sizeof(unsigned int); @@ -364,12 +365,15 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, tbl.data = &new_value; else tbl.data = &net->sctp.rto_min; + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); - if (write) { - if (ret || new_value > max || new_value < min) + if (write && ret == 0) { + if (new_value > max || new_value < min) return -EINVAL; + net->sctp.rto_min = new_value; } + return ret; } @@ -378,11 +382,10 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; - int new_value; - struct ctl_table tbl; unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; - int ret; + struct ctl_table tbl; + int ret, new_value; memset(&tbl, 0, sizeof(struct ctl_table)); tbl.maxlen = sizeof(unsigned int); @@ -391,12 +394,45 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, tbl.data = &new_value; else tbl.data = &net->sctp.rto_max; + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); - if (write) { - if (ret || new_value > max || new_value < min) + if (write && ret == 0) { + if (new_value > max || new_value < min) return -EINVAL; + net->sctp.rto_max = new_value; } + + return ret; +} + +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int new_value, ret; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.auth_enable; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + struct sock *sk = net->sctp.ctl_sock; + + net->sctp.auth_enable = new_value; + /* Update the value in the control socket */ + lock_sock(sk); + sctp_sk(sk)->ep->auth_enable = new_value; + release_sock(sk); + } + return ret; } diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 8d198ae03606..b6842fdb53d4 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -366,9 +366,10 @@ fail: * specification [SCTP] and any extensions for a list of possible * error formats. */ -struct sctp_ulpevent *sctp_ulpevent_make_remote_error( - const struct sctp_association *asoc, struct sctp_chunk *chunk, - __u16 flags, gfp_t gfp) +struct sctp_ulpevent * +sctp_ulpevent_make_remote_error(const struct sctp_association *asoc, + struct sctp_chunk *chunk, __u16 flags, + gfp_t gfp) { struct sctp_ulpevent *event; struct sctp_remote_error *sre; @@ -387,8 +388,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error( /* Copy the skb to a new skb with room for us to prepend * notification with. */ - skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error), - 0, gfp); + skb = skb_copy_expand(chunk->skb, sizeof(*sre), 0, gfp); /* Pull off the rest of the cause TLV from the chunk. */ skb_pull(chunk->skb, elen); @@ -399,62 +399,21 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error( event = sctp_skb2event(skb); sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize); - sre = (struct sctp_remote_error *) - skb_push(skb, sizeof(struct sctp_remote_error)); + sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre)); /* Trim the buffer to the right length. */ - skb_trim(skb, sizeof(struct sctp_remote_error) + elen); + skb_trim(skb, sizeof(*sre) + elen); - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_type: - * It should be SCTP_REMOTE_ERROR. - */ + /* RFC6458, Section 6.1.3. SCTP_REMOTE_ERROR */ + memset(sre, 0, sizeof(*sre)); sre->sre_type = SCTP_REMOTE_ERROR; - - /* - * Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_flags: 16 bits (unsigned integer) - * Currently unused. - */ sre->sre_flags = 0; - - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_length: sizeof (__u32) - * - * This field is the total length of the notification data, - * including the notification header. - */ sre->sre_length = skb->len; - - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_error: 16 bits (unsigned integer) - * This value represents one of the Operational Error causes defined in - * the SCTP specification, in network byte order. - */ sre->sre_error = cause; - - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_assoc_id: sizeof (sctp_assoc_t) - * - * The association id field, holds the identifier for the association. - * All notifications for a given association have the same association - * identifier. For TCP style socket, this field is ignored. - */ sctp_ulpevent_set_owner(event, asoc); sre->sre_assoc_id = sctp_assoc2id(asoc); return event; - fail: return NULL; } @@ -899,7 +858,9 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event) return notification->sn_header.sn_type; } -/* Copy out the sndrcvinfo into a msghdr. */ +/* RFC6458, Section 5.3.2. SCTP Header Information Structure + * (SCTP_SNDRCV, DEPRECATED) + */ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *msghdr) { @@ -908,74 +869,21 @@ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, if (sctp_ulpevent_is_notification(event)) return; - /* Sockets API Extensions for SCTP - * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV) - * - * sinfo_stream: 16 bits (unsigned integer) - * - * For recvmsg() the SCTP stack places the message's stream number in - * this value. - */ + memset(&sinfo, 0, sizeof(sinfo)); sinfo.sinfo_stream = event->stream; - /* sinfo_ssn: 16 bits (unsigned integer) - * - * For recvmsg() this value contains the stream sequence number that - * the remote endpoint placed in the DATA chunk. For fragmented - * messages this is the same number for all deliveries of the message - * (if more than one recvmsg() is needed to read the message). - */ sinfo.sinfo_ssn = event->ssn; - /* sinfo_ppid: 32 bits (unsigned integer) - * - * In recvmsg() this value is - * the same information that was passed by the upper layer in the peer - * application. Please note that byte order issues are NOT accounted - * for and this information is passed opaquely by the SCTP stack from - * one end to the other. - */ sinfo.sinfo_ppid = event->ppid; - /* sinfo_flags: 16 bits (unsigned integer) - * - * This field may contain any of the following flags and is composed of - * a bitwise OR of these values. - * - * recvmsg() flags: - * - * SCTP_UNORDERED - This flag is present when the message was sent - * non-ordered. - */ sinfo.sinfo_flags = event->flags; - /* sinfo_tsn: 32 bit (unsigned integer) - * - * For the receiving side, this field holds a TSN that was - * assigned to one of the SCTP Data Chunks. - */ sinfo.sinfo_tsn = event->tsn; - /* sinfo_cumtsn: 32 bit (unsigned integer) - * - * This field will hold the current cumulative TSN as - * known by the underlying SCTP layer. Note this field is - * ignored when sending and only valid for a receive - * operation when sinfo_flags are set to SCTP_UNORDERED. - */ sinfo.sinfo_cumtsn = event->cumtsn; - /* sinfo_assoc_id: sizeof (sctp_assoc_t) - * - * The association handle field, sinfo_assoc_id, holds the identifier - * for the association announced in the COMMUNICATION_UP notification. - * All notifications for a given association have the same identifier. - * Ignored for one-to-one style sockets. - */ sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc); - - /* context value that is set via SCTP_CONTEXT socket option. */ + /* Context value that is set via SCTP_CONTEXT socket option. */ sinfo.sinfo_context = event->asoc->default_rcv_context; - /* These fields are not used while receiving. */ sinfo.sinfo_timetolive = 0; put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV, - sizeof(struct sctp_sndrcvinfo), (void *)&sinfo); + sizeof(sinfo), &sinfo); } /* Do accounting for bytes received and hold a reference to the association @@ -989,7 +897,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_update(asoc, false); + sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); if (!skb->data_len) return; @@ -1011,7 +919,6 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; - struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1036,11 +943,8 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - asoc = event->asoc; - sctp_association_hold(asoc); + sctp_assoc_rwnd_increase(event->asoc, len); sctp_ulpevent_release_owner(event); - sctp_assoc_rwnd_update(asoc, true); - sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 0edada973434..5ff8b87c3d04 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -533,6 +533,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) if (args->flags & RPC_CLNT_CREATE_AUTOBIND) clnt->cl_autobind = 1; + if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT) + clnt->cl_noretranstimeo = 1; if (args->flags & RPC_CLNT_CREATE_DISCRTRY) clnt->cl_discrtry = 1; if (!(args->flags & RPC_CLNT_CREATE_QUIET)) @@ -571,6 +573,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, /* Turn off autobind on clones */ new->cl_autobind = 0; new->cl_softrtry = clnt->cl_softrtry; + new->cl_noretranstimeo = clnt->cl_noretranstimeo; new->cl_discrtry = clnt->cl_discrtry; new->cl_chatty = clnt->cl_chatty; return new; @@ -1798,21 +1801,19 @@ call_connect_status(struct rpc_task *task) trace_rpc_connect_status(task, status); task->tk_status = 0; switch (status) { - /* if soft mounted, test if we've timed out */ - case -ETIMEDOUT: - task->tk_action = call_timeout; - return; case -ECONNREFUSED: case -ECONNRESET: case -ECONNABORTED: case -ENETUNREACH: case -EHOSTUNREACH: - /* retry with existing socket, after a delay */ - rpc_delay(task, 3*HZ); if (RPC_IS_SOFTCONN(task)) break; + /* retry with existing socket, after a delay */ + rpc_delay(task, 3*HZ); case -EAGAIN: - task->tk_action = call_bind; + /* Check for timeouts before looping back to call_bind */ + case -ETIMEDOUT: + task->tk_action = call_timeout; return; case 0: clnt->cl_stats->netreconn++; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 06c6ff0cb911..a4acaf2bcf18 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -730,6 +730,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) newxpt = xprt->xpt_ops->xpo_accept(xprt); if (newxpt) svc_add_new_temp_xprt(serv, newxpt); + else + module_put(xprt->xpt_class->xcl_owner); } else if (xprt->xpt_ops->xpo_has_wspace(xprt)) { /* XPT_DATA|XPT_DEFERRED case: */ dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index b6e59f0a9475..5e8fe777772b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -685,6 +685,7 @@ static struct svc_xprt_class svc_udp_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_udp_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP, + .xcl_ident = XPRT_TRANSPORT_UDP, }; static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) @@ -1279,6 +1280,7 @@ static struct svc_xprt_class svc_tcp_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_tcp_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, + .xcl_ident = XPRT_TRANSPORT_TCP, }; void svc_init_xprt_sock(void) @@ -1397,6 +1399,22 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } +bool svc_alien_sock(struct net *net, int fd) +{ + int err; + struct socket *sock = sockfd_lookup(fd, &err); + bool ret = false; + + if (!sock) + goto out; + if (sock_net(sock->sk) != net) + ret = true; + sockfd_put(sock); +out: + return ret; +} +EXPORT_SYMBOL_GPL(svc_alien_sock); + /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 7d4df99f761f..03ac88431984 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1316,7 +1316,7 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) } } spin_unlock(&xprt_list_lock); - printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident); + dprintk("RPC: transport (%d) not supported\n", args->ident); return ERR_PTR(-EIO); found: diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 62e4f9bcc387..ed36cb52cd86 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -89,6 +89,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, + .xcl_ident = XPRT_TRANSPORT_RDMA, }; struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0addefca8e77..41c2f9d7a148 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -842,6 +842,8 @@ static void xs_error_report(struct sock *sk) dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -err); trace_rpc_socket_error(xprt, sk->sk_socket, err); + if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state)) + goto out; xprt_wake_pending_tasks(xprt, err); out: read_unlock_bh(&sk->sk_callback_lock); @@ -2251,7 +2253,9 @@ static void xs_tcp_setup_socket(struct work_struct *work) abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); /* "close" the socket, preserving the local port */ + set_bit(XPRT_CONNECTION_REUSE, &xprt->state); xs_tcp_reuse_connection(transport); + clear_bit(XPRT_CONNECTION_REUSE, &xprt->state); if (abort_and_exit) goto out_eagain; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index bf860d9e75af..3ca45bf5029f 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -537,6 +537,7 @@ receive: buf = node->bclink.deferred_head; node->bclink.deferred_head = buf->next; + buf->next = NULL; node->bclink.deferred_size--; goto receive; } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 3aaf73de9e2d..ad844d365340 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN); u16 cmd; - if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN))) + if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN))) cmd = TIPC_CMD_NOT_NET_ADMIN; else cmd = req_userhdr->cmd; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 5adfd94c5b85..85d232bed87d 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1925,9 +1925,23 @@ static struct miscdevice vsock_device = { .fops = &vsock_device_ops, }; -static int __vsock_core_init(void) +int __vsock_core_init(const struct vsock_transport *t, struct module *owner) { - int err; + int err = mutex_lock_interruptible(&vsock_register_mutex); + + if (err) + return err; + + if (transport) { + err = -EBUSY; + goto err_busy; + } + + /* Transport must be the owner of the protocol so that it can't + * unload while there are open sockets. + */ + vsock_proto.owner = owner; + transport = t; vsock_init_tables(); @@ -1951,36 +1965,19 @@ static int __vsock_core_init(void) goto err_unregister_proto; } + mutex_unlock(&vsock_register_mutex); return 0; err_unregister_proto: proto_unregister(&vsock_proto); err_misc_deregister: misc_deregister(&vsock_device); - return err; -} - -int vsock_core_init(const struct vsock_transport *t) -{ - int retval = mutex_lock_interruptible(&vsock_register_mutex); - if (retval) - return retval; - - if (transport) { - retval = -EBUSY; - goto out; - } - - transport = t; - retval = __vsock_core_init(); - if (retval) - transport = NULL; - -out: + transport = NULL; +err_busy: mutex_unlock(&vsock_register_mutex); - return retval; + return err; } -EXPORT_SYMBOL_GPL(vsock_core_init); +EXPORT_SYMBOL_GPL(__vsock_core_init); void vsock_core_exit(void) { @@ -2000,5 +1997,5 @@ EXPORT_SYMBOL_GPL(vsock_core_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); -MODULE_VERSION("1.0.0.0-k"); +MODULE_VERSION("1.0.1.0-k"); MODULE_LICENSE("GPL v2"); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4fe2e6e2bc76..df33156ecd2d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1450,18 +1450,17 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev, } CMD(start_p2p_device, START_P2P_DEVICE); CMD(set_mcast_rate, SET_MCAST_RATE); +#ifdef CONFIG_NL80211_TESTMODE + CMD(testmode_cmd, TESTMODE); +#endif if (state->split) { CMD(crit_proto_start, CRIT_PROTOCOL_START); CMD(crit_proto_stop, CRIT_PROTOCOL_STOP); if (dev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH) CMD(channel_switch, CHANNEL_SWITCH); + CMD(set_qos_map, SET_QOS_MAP); } - CMD(set_qos_map, SET_QOS_MAP); - -#ifdef CONFIG_NL80211_TESTMODE - CMD(testmode_cmd, TESTMODE); -#endif - + /* add into the if now */ #undef CMD if (dev->ops->connect || dev->ops->auth) { @@ -6797,6 +6796,9 @@ void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp) struct nlattr *data = ((void **)skb->cb)[2]; enum nl80211_multicast_groups mcgrp = NL80211_MCGRP_TESTMODE; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + nla_nest_end(skb, data); genlmsg_end(skb, hdr); @@ -9076,6 +9078,9 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb) void *hdr = ((void **)skb->cb)[1]; struct nlattr *data = ((void **)skb->cb)[2]; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + if (WARN_ON(!rdev->cur_cmd_info)) { kfree_skb(skb); return -EINVAL; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index f0541370e68e..338794ea44d1 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1683,17 +1683,9 @@ static void reg_process_hint(struct regulatory_request *reg_request) struct wiphy *wiphy = NULL; enum reg_request_treatment treatment; - if (WARN_ON(!reg_request->alpha2)) - return; - if (reg_request->wiphy_idx != WIPHY_IDX_INVALID) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx); - if (reg_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && !wiphy) { - kfree(reg_request); - return; - } - switch (reg_request->initiator) { case NL80211_REGDOM_SET_BY_CORE: reg_process_hint_core(reg_request); @@ -1706,20 +1698,29 @@ static void reg_process_hint(struct regulatory_request *reg_request) schedule_delayed_work(®_timeout, msecs_to_jiffies(3142)); return; case NL80211_REGDOM_SET_BY_DRIVER: + if (!wiphy) + goto out_free; treatment = reg_process_hint_driver(wiphy, reg_request); break; case NL80211_REGDOM_SET_BY_COUNTRY_IE: + if (!wiphy) + goto out_free; treatment = reg_process_hint_country_ie(wiphy, reg_request); break; default: WARN(1, "invalid initiator %d\n", reg_request->initiator); - return; + goto out_free; } /* This is required so that the orig_* parameters are saved */ if (treatment == REG_REQ_ALREADY_SET && wiphy && wiphy->regulatory_flags & REGULATORY_STRICT_REG) wiphy_update_regulatory(wiphy, reg_request->initiator); + + return; + +out_free: + kfree(reg_request); } /* diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d1ed4aebbbb7..38d6dd553770 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -284,14 +284,22 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy) } EXPORT_SYMBOL(cfg80211_sched_scan_results); -void cfg80211_sched_scan_stopped(struct wiphy *wiphy) +void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + ASSERT_RTNL(); + trace_cfg80211_sched_scan_stopped(wiphy); - rtnl_lock(); __cfg80211_stop_sched_scan(rdev, true); +} +EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl); + +void cfg80211_sched_scan_stopped(struct wiphy *wiphy) +{ + rtnl_lock(); + cfg80211_sched_scan_stopped_rtnl(wiphy); rtnl_unlock(); } EXPORT_SYMBOL(cfg80211_sched_scan_stopped); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f04d4c32e96e..760722f9126b 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -235,7 +235,6 @@ void cfg80211_conn_work(struct work_struct *work) NULL, 0, NULL, 0, WLAN_STATUS_UNSPECIFIED_FAILURE, false, NULL); - cfg80211_sme_free(wdev); } wdev_unlock(wdev); } @@ -649,6 +648,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, cfg80211_unhold_bss(bss_from_pub(bss)); cfg80211_put_bss(wdev->wiphy, bss); } + cfg80211_sme_free(wdev); return; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index fbcc23edee54..b89eb3990f0a 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2068,7 +2068,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure, MAC_ASSIGN(addr, addr); __entry->key_type = key_type; __entry->key_id = key_id; - memcpy(__entry->tsc, tsc, 6); + if (tsc) + memcpy(__entry->tsc, tsc, 6); ), TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm", NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1d5c7bf29938..59cf325f2772 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -41,6 +41,11 @@ static struct dst_entry *xfrm_policy_sk_bundles; +struct xfrm_flo { + struct dst_entry *dst_orig; + u8 flags; +}; + static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] __read_mostly; @@ -1889,13 +1894,14 @@ static int xdst_queue_output(struct sk_buff *skb) } static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, - struct dst_entry *dst, + struct xfrm_flo *xflo, const struct flowi *fl, int num_xfrms, u16 family) { int err; struct net_device *dev; + struct dst_entry *dst; struct dst_entry *dst1; struct xfrm_dst *xdst; @@ -1903,9 +1909,12 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, if (IS_ERR(xdst)) return xdst; - if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0) + if (!(xflo->flags & XFRM_LOOKUP_QUEUE) || + net->xfrm.sysctl_larval_drop || + num_xfrms <= 0) return xdst; + dst = xflo->dst_orig; dst1 = &xdst->u.dst; dst_hold(dst); xdst->route = dst; @@ -1947,7 +1956,7 @@ static struct flow_cache_object * xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct flow_cache_object *oldflo, void *ctx) { - struct dst_entry *dst_orig = (struct dst_entry *)ctx; + struct xfrm_flo *xflo = (struct xfrm_flo *)ctx; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst, *new_xdst; int num_pols = 0, num_xfrms = 0, i, err, pol_dead; @@ -1988,7 +1997,8 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, goto make_dummy_bundle; } - new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig); + new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, + xflo->dst_orig); if (IS_ERR(new_xdst)) { err = PTR_ERR(new_xdst); if (err != -EAGAIN) @@ -2022,7 +2032,7 @@ make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ - xdst = xfrm_create_dummy_bundle(net, dst_orig, fl, num_xfrms, family); + xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); @@ -2121,13 +2131,18 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, } if (xdst == NULL) { + struct xfrm_flo xflo; + + xflo.dst_orig = dst_orig; + xflo.flags = flags; + /* To accelerate a bit... */ if ((dst_orig->flags & DST_NOXFRM) || !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; flo = flow_cache_lookup(net, fl, family, dir, - xfrm_bundle_lookup, dst_orig); + xfrm_bundle_lookup, &xflo); if (flo == NULL) goto nopol; if (IS_ERR(flo)) { @@ -2155,7 +2170,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, xfrm_pols_put(pols, drop_pols); XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - return make_blackhole(net, family, dst_orig); + return ERR_PTR(-EREMOTE); } err = -EAGAIN; @@ -2212,6 +2227,23 @@ dropdst: } EXPORT_SYMBOL(xfrm_lookup); +/* Callers of xfrm_lookup_route() must ensure a call to dst_output(). + * Otherwise we may send out blackholed packets. + */ +struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, + struct sock *sk, int flags) +{ + struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, + flags | XFRM_LOOKUP_QUEUE); + + if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) + return make_blackhole(net, dst_orig->ops->family, dst_orig); + + return dst; +} +EXPORT_SYMBOL(xfrm_lookup_route); + static inline int xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { @@ -2477,7 +2509,7 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) skb_dst_force(skb); - dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0); + dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { res = 0; dst = NULL; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2f7ddc3a59b4..3bea4ddc699d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -176,9 +176,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ALG_COMP] || - attrs[XFRMA_TFCPAD] || - (ntohl(p->id.spi) >= 0x10000)) - + attrs[XFRMA_TFCPAD]) goto out; break; @@ -206,7 +204,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_AUTH] || attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_CRYPT] || - attrs[XFRMA_TFCPAD]) + attrs[XFRMA_TFCPAD] || + (ntohl(p->id.spi) >= 0x10000)) goto out; break; @@ -2350,7 +2349,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) link = &xfrm_dispatch[type]; /* All operations require privileges, even GET */ - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || diff --git a/scripts/package/builddeb b/scripts/package/builddeb index f46e4dd0558d..152d4d25ab7c 100644 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -155,11 +155,11 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then for module in $(find lib/modules/ -name *.ko); do mkdir -p $(dirname $dbg_dir/usr/lib/debug/$module) # only keep debug symbols in the debug file - objcopy --only-keep-debug $module $dbg_dir/usr/lib/debug/$module + $OBJCOPY --only-keep-debug $module $dbg_dir/usr/lib/debug/$module # strip original module from debug symbols - objcopy --strip-debug $module + $OBJCOPY --strip-debug $module # then add a link to those - objcopy --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module + $OBJCOPY --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module done ) fi diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h index 9d1421e63ff8..49b582a225b0 100644 --- a/scripts/recordmcount.h +++ b/scripts/recordmcount.h @@ -163,11 +163,11 @@ static int mcount_adjust = 0; static int MIPS_is_fake_mcount(Elf_Rel const *rp) { - static Elf_Addr old_r_offset; + static Elf_Addr old_r_offset = ~(Elf_Addr)0; Elf_Addr current_r_offset = _w(rp->r_offset); int is_fake; - is_fake = old_r_offset && + is_fake = (old_r_offset != ~(Elf_Addr)0) && (current_r_offset - old_r_offset == MIPS_FAKEMCOUNT_OFFSET); old_r_offset = current_r_offset; diff --git a/security/commoncap.c b/security/commoncap.c index b9d613e0ef14..963dc5981661 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -421,6 +421,9 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable); } + cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + return 0; } diff --git a/security/device_cgroup.c b/security/device_cgroup.c index d3b6d2cd3a06..6e4e6eb732fe 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -308,57 +308,139 @@ static int devcgroup_seq_show(struct seq_file *m, void *v) } /** - * may_access - verifies if a new exception is part of what is allowed - * by a dev cgroup based on the default policy + - * exceptions. This is used to make sure a child cgroup - * won't have more privileges than its parent or to - * verify if a certain access is allowed. - * @dev_cgroup: dev cgroup to be tested against - * @refex: new exception - * @behavior: behavior of the exception + * match_exception - iterates the exception list trying to match a rule + * based on type, major, minor and access type. It is + * considered a match if an exception is found that + * will contain the entire range of provided parameters. + * @exceptions: list of exceptions + * @type: device type (DEV_BLOCK or DEV_CHAR) + * @major: device file major number, ~0 to match all + * @minor: device file minor number, ~0 to match all + * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD) + * + * returns: true in case it matches an exception completely */ -static bool may_access(struct dev_cgroup *dev_cgroup, - struct dev_exception_item *refex, - enum devcg_behavior behavior) +static bool match_exception(struct list_head *exceptions, short type, + u32 major, u32 minor, short access) { struct dev_exception_item *ex; - bool match = false; - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&devcgroup_mutex), - "device_cgroup::may_access() called without proper synchronization"); + list_for_each_entry_rcu(ex, exceptions, list) { + if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK)) + continue; + if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR)) + continue; + if (ex->major != ~0 && ex->major != major) + continue; + if (ex->minor != ~0 && ex->minor != minor) + continue; + /* provided access cannot have more than the exception rule */ + if (access & (~ex->access)) + continue; + return true; + } + return false; +} + +/** + * match_exception_partial - iterates the exception list trying to match a rule + * based on type, major, minor and access type. It is + * considered a match if an exception's range is + * found to contain *any* of the devices specified by + * provided parameters. This is used to make sure no + * extra access is being granted that is forbidden by + * any of the exception list. + * @exceptions: list of exceptions + * @type: device type (DEV_BLOCK or DEV_CHAR) + * @major: device file major number, ~0 to match all + * @minor: device file minor number, ~0 to match all + * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD) + * + * returns: true in case the provided range mat matches an exception completely + */ +static bool match_exception_partial(struct list_head *exceptions, short type, + u32 major, u32 minor, short access) +{ + struct dev_exception_item *ex; - list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) { - if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK)) + list_for_each_entry_rcu(ex, exceptions, list) { + if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK)) continue; - if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR)) + if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR)) continue; - if (ex->major != ~0 && ex->major != refex->major) + /* + * We must be sure that both the exception and the provided + * range aren't masking all devices + */ + if (ex->major != ~0 && major != ~0 && ex->major != major) continue; - if (ex->minor != ~0 && ex->minor != refex->minor) + if (ex->minor != ~0 && minor != ~0 && ex->minor != minor) continue; - if (refex->access & (~ex->access)) + /* + * In order to make sure the provided range isn't matching + * an exception, all its access bits shouldn't match the + * exception's access bits + */ + if (!(access & ex->access)) continue; - match = true; - break; + return true; } + return false; +} + +/** + * verify_new_ex - verifies if a new exception is part of what is allowed + * by a dev cgroup based on the default policy + + * exceptions. This is used to make sure a child cgroup + * won't have more privileges than its parent + * @dev_cgroup: dev cgroup to be tested against + * @refex: new exception + * @behavior: behavior of the exception's dev_cgroup + */ +static bool verify_new_ex(struct dev_cgroup *dev_cgroup, + struct dev_exception_item *refex, + enum devcg_behavior behavior) +{ + bool match = false; + + rcu_lockdep_assert(rcu_read_lock_held() || + lockdep_is_held(&devcgroup_mutex), + "device_cgroup:verify_new_ex called without proper synchronization"); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { - /* the exception will deny access to certain devices */ + /* + * new exception in the child doesn't matter, only + * adding extra restrictions + */ return true; } else { - /* the exception will allow access to certain devices */ + /* + * new exception in the child will add more devices + * that can be acessed, so it can't match any of + * parent's exceptions, even slightly + */ + match = match_exception_partial(&dev_cgroup->exceptions, + refex->type, + refex->major, + refex->minor, + refex->access); + if (match) - /* - * a new exception allowing access shouldn't - * match an parent's exception - */ return false; return true; } } else { - /* only behavior == DEVCG_DEFAULT_DENY allowed here */ + /* + * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore + * the new exception will add access to more devices and must + * be contained completely in an parent's exception to be + * allowed + */ + match = match_exception(&dev_cgroup->exceptions, refex->type, + refex->major, refex->minor, + refex->access); + if (match) /* parent has an exception that matches the proposed */ return true; @@ -380,7 +462,38 @@ static int parent_has_perm(struct dev_cgroup *childcg, if (!parent) return 1; - return may_access(parent, ex, childcg->behavior); + return verify_new_ex(parent, ex, childcg->behavior); +} + +/** + * parent_allows_removal - verify if it's ok to remove an exception + * @childcg: child cgroup from where the exception will be removed + * @ex: exception being removed + * + * When removing an exception in cgroups with default ALLOW policy, it must + * be checked if removing it will give the child cgroup more access than the + * parent. + * + * Return: true if it's ok to remove exception, false otherwise + */ +static bool parent_allows_removal(struct dev_cgroup *childcg, + struct dev_exception_item *ex) +{ + struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css)); + + if (!parent) + return true; + + /* It's always allowed to remove access to devices */ + if (childcg->behavior == DEVCG_DEFAULT_DENY) + return true; + + /* + * Make sure you're not removing part or a whole exception existing in + * the parent cgroup + */ + return !match_exception_partial(&parent->exceptions, ex->type, + ex->major, ex->minor, ex->access); } /** @@ -618,17 +731,21 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup, switch (filetype) { case DEVCG_ALLOW: - if (!parent_has_perm(devcgroup, &ex)) - return -EPERM; /* * If the default policy is to allow by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { + /* Check if the parent allows removing it first */ + if (!parent_allows_removal(devcgroup, &ex)) + return -EPERM; dev_exception_rm(devcgroup, &ex); - return 0; + break; } + + if (!parent_has_perm(devcgroup, &ex)) + return -EPERM; rc = dev_exception_add(devcgroup, &ex); break; case DEVCG_DENY: @@ -708,18 +825,18 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor, short access) { struct dev_cgroup *dev_cgroup; - struct dev_exception_item ex; - int rc; - - memset(&ex, 0, sizeof(ex)); - ex.type = type; - ex.major = major; - ex.minor = minor; - ex.access = access; + bool rc; rcu_read_lock(); dev_cgroup = task_devcgroup(current); - rc = may_access(dev_cgroup, &ex, dev_cgroup->behavior); + if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) + /* Can't match any of the exceptions, even partially */ + rc = !match_exception_partial(&dev_cgroup->exceptions, + type, major, minor, access); + else + /* Need to match completely one exception to be allowed */ + rc = match_exception(&dev_cgroup->exceptions, type, major, + minor, access); rcu_read_unlock(); if (!rc) diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 336b3ddfe63f..7e71e066198f 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -269,6 +269,13 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name, goto out; } evm_status = evm_verify_current_integrity(dentry); + if (evm_status == INTEGRITY_NOXATTRS) { + struct integrity_iint_cache *iint; + + iint = integrity_iint_find(dentry->d_inode); + if (iint && (iint->flags & IMA_NEW_FILE)) + return 0; + } out: if (evm_status != INTEGRITY_PASS) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode, @@ -285,12 +292,23 @@ out: * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * - * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that - * the current value is valid. + * Before allowing the 'security.evm' protected xattr to be updated, + * verify the existing value is valid. As only the kernel should have + * access to the EVM encrypted key needed to calculate the HMAC, prevent + * userspace from writing HMAC value. Writing 'security.evm' requires + * requires CAP_SYS_ADMIN privileges. */ int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { + const struct evm_ima_xattr_data *xattr_data = xattr_value; + + if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { + if (!xattr_value_len) + return -EINVAL; + if (xattr_data->type != EVM_IMA_XATTR_DIGSIG) + return -EPERM; + } return evm_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); } diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 0356e1d437ca..f79fa8be203c 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -27,7 +27,7 @@ #include "../integrity.h" enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN, - IMA_SHOW_ASCII }; + IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII }; enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 }; /* digest size for IMA, fits SHA1 or MD5 */ diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index c38bbce8c6a6..025824af08e0 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -199,6 +199,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, struct evm_ima_xattr_data **xattr_value, int *xattr_len) { + const char *audit_cause = "failed"; struct inode *inode = file_inode(file); const char *filename = file->f_dentry->d_name.name; int result = 0; @@ -213,6 +214,12 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, if (!(iint->flags & IMA_COLLECTED)) { u64 i_version = file_inode(file)->i_version; + if (file->f_flags & O_DIRECT) { + audit_cause = "failed(directio)"; + result = -EACCES; + goto out; + } + /* use default hash algorithm */ hash.hdr.algo = ima_hash_algo; @@ -233,9 +240,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, result = -ENOMEM; } } +out: if (result) integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, - filename, "collect_data", "failed", + filename, "collect_data", audit_cause, result, 0); return result; } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 734e9468aca0..6df1b2527d02 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -194,8 +194,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint, goto out; cause = "missing-hash"; - status = - (inode->i_size == 0) ? INTEGRITY_PASS : INTEGRITY_NOLABEL; + status = INTEGRITY_NOLABEL; + if (inode->i_size == 0) { + iint->flags |= IMA_NEW_FILE; + status = INTEGRITY_PASS; + } goto out; } diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index fdf60def52e9..b5c126fe0bd9 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -25,6 +25,36 @@ static struct crypto_shash *ima_shash_tfm; +/** + * ima_kernel_read - read file content + * + * This is a function for reading file content instead of kernel_read(). + * It does not perform locking checks to ensure it cannot be blocked. + * It does not perform security checks because it is irrelevant for IMA. + * + */ +static int ima_kernel_read(struct file *file, loff_t offset, + char *addr, unsigned long count) +{ + mm_segment_t old_fs; + char __user *buf = addr; + ssize_t ret; + + if (!(file->f_mode & FMODE_READ)) + return -EBADF; + if (!file->f_op->read && !file->f_op->aio_read) + return -EINVAL; + + old_fs = get_fs(); + set_fs(get_ds()); + if (file->f_op->read) + ret = file->f_op->read(file, buf, count, &offset); + else + ret = do_sync_read(file, buf, count, &offset); + set_fs(old_fs); + return ret; +} + int ima_init_crypto(void) { long rc; @@ -98,7 +128,7 @@ static int ima_calc_file_hash_tfm(struct file *file, while (offset < i_size) { int rbuf_len; - rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE); + rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE); if (rbuf_len < 0) { rc = rbuf_len; break; diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index db01125926bd..468a3ba3c539 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -160,6 +160,8 @@ static int ima_measurements_show(struct seq_file *m, void *v) if (is_ima_template && strcmp(field->field_id, "d") == 0) show = IMA_SHOW_BINARY_NO_FIELD_LEN; + if (is_ima_template && strcmp(field->field_id, "n") == 0) + show = IMA_SHOW_BINARY_OLD_STRING_FMT; field->field_show(m, show, &e->template_data[i]); } return 0; diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 149ee1119f87..9f70efd08058 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -131,11 +131,13 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint, return; mutex_lock(&inode->i_mutex); - if (atomic_read(&inode->i_writecount) == 1 && - iint->version != inode->i_version) { - iint->flags &= ~IMA_DONE_MASK; - if (iint->flags & IMA_APPRAISE) - ima_update_xattr(iint, file); + if (atomic_read(&inode->i_writecount) == 1) { + if ((iint->version != inode->i_version) || + (iint->flags & IMA_NEW_FILE)) { + iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); + if (iint->flags & IMA_APPRAISE) + ima_update_xattr(iint, file); + } } mutex_unlock(&inode->i_mutex); } @@ -217,8 +219,11 @@ static int process_measurement(struct file *file, const char *filename, xattr_ptr = &xattr_value; rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len); - if (rc != 0) + if (rc != 0) { + if (file->f_flags & O_DIRECT) + rc = (iint->flags & IMA_PERMIT_DIRECTIO) ? 0 : -EACCES; goto out_digsig; + } pathname = !filename ? ima_d_path(&file->f_path, &pathbuf) : filename; if (!pathname) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index a9c3d3cd1990..085c4964be99 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -351,7 +351,7 @@ enum { Opt_obj_user, Opt_obj_role, Opt_obj_type, Opt_subj_user, Opt_subj_role, Opt_subj_type, Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner, - Opt_appraise_type, Opt_fsuuid + Opt_appraise_type, Opt_fsuuid, Opt_permit_directio }; static match_table_t policy_tokens = { @@ -373,6 +373,7 @@ static match_table_t policy_tokens = { {Opt_uid, "uid=%s"}, {Opt_fowner, "fowner=%s"}, {Opt_appraise_type, "appraise_type=%s"}, + {Opt_permit_directio, "permit_directio"}, {Opt_err, NULL} }; @@ -621,6 +622,9 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) else result = -EINVAL; break; + case Opt_permit_directio: + entry->flags |= IMA_PERMIT_DIRECTIO; + break; case Opt_err: ima_log_string(ab, "UNKNOWN", p); result = -EINVAL; diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 1683bbf289a4..e8592e7bfc21 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -109,13 +109,16 @@ static void ima_show_template_data_binary(struct seq_file *m, enum data_formats datafmt, struct ima_field_data *field_data) { + u32 len = (show == IMA_SHOW_BINARY_OLD_STRING_FMT) ? + strlen(field_data->data) : field_data->len; + if (show != IMA_SHOW_BINARY_NO_FIELD_LEN) - ima_putc(m, &field_data->len, sizeof(u32)); + ima_putc(m, &len, sizeof(len)); - if (!field_data->len) + if (!len) return; - ima_putc(m, field_data->data, field_data->len); + ima_putc(m, field_data->data, len); } static void ima_show_template_field_data(struct seq_file *m, @@ -129,6 +132,7 @@ static void ima_show_template_field_data(struct seq_file *m, break; case IMA_SHOW_BINARY: case IMA_SHOW_BINARY_NO_FIELD_LEN: + case IMA_SHOW_BINARY_OLD_STRING_FMT: ima_show_template_data_binary(m, show, datafmt, field_data); break; default: diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 2fb5e53e927f..2f8715d77a5a 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -30,6 +30,8 @@ #define IMA_ACTION_FLAGS 0xff000000 #define IMA_DIGSIG 0x01000000 #define IMA_DIGSIG_REQUIRED 0x02000000 +#define IMA_PERMIT_DIRECTIO 0x04000000 +#define IMA_NEW_FILE 0x08000000 #define IMA_DO_MASK (IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \ IMA_APPRAISE_SUBMASK) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index b332e2cc0954..47b5c69e4605 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -470,6 +470,7 @@ next_inode: list_entry(sbsec->isec_head.next, struct inode_security_struct, list); struct inode *inode = isec->inode; + list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { @@ -478,7 +479,6 @@ next_inode: iput(inode); } spin_lock(&sbsec->isec_lock); - list_del_init(&isec->list); goto next_inode; } spin_unlock(&sbsec->isec_lock); @@ -1418,15 +1418,33 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent isec->sid = sbsec->sid; if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) { - if (opt_dentry) { - isec->sclass = inode_mode_to_security_class(inode->i_mode); - rc = selinux_proc_get_sid(opt_dentry, - isec->sclass, - &sid); - if (rc) - goto out_unlock; - isec->sid = sid; - } + /* We must have a dentry to determine the label on + * procfs inodes */ + if (opt_dentry) + /* Called from d_instantiate or + * d_splice_alias. */ + dentry = dget(opt_dentry); + else + /* Called from selinux_complete_init, try to + * find a dentry. */ + dentry = d_find_alias(inode); + /* + * This can be hit on boot when a file is accessed + * before the policy is loaded. When we load policy we + * may find inodes that have no dentry on the + * sbsec->isec_head list. No reason to complain as + * these will get fixed up the next time we go through + * inode_doinit() with a dentry, before these inodes + * could be used again by userspace. + */ + if (!dentry) + goto out_unlock; + isec->sclass = inode_mode_to_security_class(inode->i_mode); + rc = selinux_proc_get_sid(dentry, isec->sclass, &sid); + dput(dentry); + if (rc) + goto out_unlock; + isec->sid = sid; } break; } diff --git a/sound/core/control.c b/sound/core/control.c index d8aa206e8bde..98a29b26c5f4 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -289,6 +289,10 @@ static bool snd_ctl_remove_numid_conflict(struct snd_card *card, { struct snd_kcontrol *kctl; + /* Make sure that the ids assigned to the control do not wrap around */ + if (card->last_numid >= UINT_MAX - count) + card->last_numid = 0; + list_for_each_entry(kctl, &card->controls, list) { if (kctl->id.numid < card->last_numid + 1 + count && kctl->id.numid + kctl->count > card->last_numid + 1) { @@ -331,6 +335,7 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) { struct snd_ctl_elem_id id; unsigned int idx; + unsigned int count; int err = -EINVAL; if (! kcontrol) @@ -338,6 +343,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) if (snd_BUG_ON(!card || !kcontrol->info)) goto error; id = kcontrol->id; + if (id.index > UINT_MAX - kcontrol->count) + goto error; + down_write(&card->controls_rwsem); if (snd_ctl_find_id(card, &id)) { up_write(&card->controls_rwsem); @@ -359,8 +367,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) card->controls_count += kcontrol->count; kcontrol->id.numid = card->last_numid + 1; card->last_numid += kcontrol->count; + count = kcontrol->count; up_write(&card->controls_rwsem); - for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++) + for (idx = 0; idx < count; idx++, id.index++, id.numid++) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); return 0; @@ -389,6 +398,7 @@ int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol, bool add_on_replace) { struct snd_ctl_elem_id id; + unsigned int count; unsigned int idx; struct snd_kcontrol *old; int ret; @@ -424,8 +434,9 @@ add: card->controls_count += kcontrol->count; kcontrol->id.numid = card->last_numid + 1; card->last_numid += kcontrol->count; + count = kcontrol->count; up_write(&card->controls_rwsem); - for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++) + for (idx = 0; idx < count; idx++, id.index++, id.numid++) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); return 0; @@ -898,9 +909,9 @@ static int snd_ctl_elem_write(struct snd_card *card, struct snd_ctl_file *file, result = kctl->put(kctl, control); } if (result > 0) { + struct snd_ctl_elem_id id = control->id; up_read(&card->controls_rwsem); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, - &control->id); + snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id); return 0; } } @@ -992,6 +1003,7 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file, struct user_element { struct snd_ctl_elem_info info; + struct snd_card *card; void *elem_data; /* element data */ unsigned long elem_data_size; /* size of element data in bytes */ void *tlv_data; /* TLV data */ @@ -1035,7 +1047,9 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol, { struct user_element *ue = kcontrol->private_data; + mutex_lock(&ue->card->user_ctl_lock); memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size); + mutex_unlock(&ue->card->user_ctl_lock); return 0; } @@ -1044,10 +1058,12 @@ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol, { int change; struct user_element *ue = kcontrol->private_data; - + + mutex_lock(&ue->card->user_ctl_lock); change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0; if (change) memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size); + mutex_unlock(&ue->card->user_ctl_lock); return change; } @@ -1067,19 +1083,32 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol, new_data = memdup_user(tlv, size); if (IS_ERR(new_data)) return PTR_ERR(new_data); + mutex_lock(&ue->card->user_ctl_lock); change = ue->tlv_data_size != size; if (!change) change = memcmp(ue->tlv_data, new_data, size); kfree(ue->tlv_data); ue->tlv_data = new_data; ue->tlv_data_size = size; + mutex_unlock(&ue->card->user_ctl_lock); } else { - if (! ue->tlv_data_size || ! ue->tlv_data) - return -ENXIO; - if (size < ue->tlv_data_size) - return -ENOSPC; + int ret = 0; + + mutex_lock(&ue->card->user_ctl_lock); + if (!ue->tlv_data_size || !ue->tlv_data) { + ret = -ENXIO; + goto err_unlock; + } + if (size < ue->tlv_data_size) { + ret = -ENOSPC; + goto err_unlock; + } if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size)) - return -EFAULT; + ret = -EFAULT; +err_unlock: + mutex_unlock(&ue->card->user_ctl_lock); + if (ret) + return ret; } return change; } @@ -1137,8 +1166,6 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, struct user_element *ue; int idx, err; - if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS) - return -ENOMEM; if (info->count < 1) return -EINVAL; access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE : @@ -1147,21 +1174,16 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE)); info->id.numid = 0; memset(&kctl, 0, sizeof(kctl)); - down_write(&card->controls_rwsem); - _kctl = snd_ctl_find_id(card, &info->id); - err = 0; - if (_kctl) { - if (replace) - err = snd_ctl_remove(card, _kctl); - else - err = -EBUSY; - } else { - if (replace) - err = -ENOENT; + + if (replace) { + err = snd_ctl_remove_user_ctl(file, &info->id); + if (err) + return err; } - up_write(&card->controls_rwsem); - if (err < 0) - return err; + + if (card->user_ctl_count >= MAX_USER_CONTROLS) + return -ENOMEM; + memcpy(&kctl.id, &info->id, sizeof(info->id)); kctl.count = info->owner ? info->owner : 1; access |= SNDRV_CTL_ELEM_ACCESS_USER; @@ -1211,6 +1233,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL); if (ue == NULL) return -ENOMEM; + ue->card = card; ue->info = *info; ue->info.access = 0; ue->elem_data = (char *)ue + sizeof(*ue); @@ -1322,8 +1345,9 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file, } err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv); if (err > 0) { + struct snd_ctl_elem_id id = kctl->id; up_read(&card->controls_rwsem); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id); + snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id); return 0; } } else { diff --git a/sound/core/info.c b/sound/core/info.c index e79baa11b60e..08070e1eefeb 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -679,7 +679,7 @@ int snd_info_card_free(struct snd_card *card) * snd_info_get_line - read one line from the procfs buffer * @buffer: the procfs buffer * @line: the buffer to store - * @len: the max. buffer size - 1 + * @len: the max. buffer size * * Reads one line from the buffer and stores the string. * @@ -699,7 +699,7 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len) buffer->stop = 1; if (c == '\n') break; - if (len) { + if (len > 1) { len--; *line++ = c; } diff --git a/sound/core/init.c b/sound/core/init.c index 0d42fcda0de2..39c25167add8 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -218,6 +218,7 @@ int snd_card_create(int idx, const char *xid, INIT_LIST_HEAD(&card->devices); init_rwsem(&card->controls_rwsem); rwlock_init(&card->ctl_files_rwlock); + mutex_init(&card->user_ctl_lock); INIT_LIST_HEAD(&card->controls); INIT_LIST_HEAD(&card->ctl_files); spin_lock_init(&card->files_lock); diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index af49721ba0e3..c4ac3c1e19af 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -206,6 +206,8 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream, if (err < 0) return err; + if (clear_user(src, sizeof(*src))) + return -EFAULT; if (put_user(status.state, &src->state) || compat_put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) || compat_put_timespec(&status.tstamp, &src->tstamp) || diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index a2104671f51d..e1ef106c8a6f 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1783,14 +1783,16 @@ static int snd_pcm_lib_ioctl_fifo_size(struct snd_pcm_substream *substream, { struct snd_pcm_hw_params *params = arg; snd_pcm_format_t format; - int channels, width; + int channels; + ssize_t frame_size; params->fifo_size = substream->runtime->hw.fifo_size; if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_FIFO_IN_FRAMES)) { format = params_format(params); channels = params_channels(params); - width = snd_pcm_format_physical_width(format); - params->fifo_size /= width * channels; + frame_size = snd_pcm_format_size(format, channels); + if (frame_size > 0) + params->fifo_size /= (unsigned)frame_size; } return 0; } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 01a5e05ede95..566b0f69d628 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3189,7 +3189,7 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = { #ifndef ARCH_HAS_DMA_MMAP_COHERENT /* This should be defined / handled globally! */ -#ifdef CONFIG_ARM +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) #define ARCH_HAS_DMA_MMAP_COHERENT #endif #endif diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig index 8756c8e32922..46e563046bfb 100644 --- a/sound/pci/Kconfig +++ b/sound/pci/Kconfig @@ -859,8 +859,8 @@ config SND_VIRTUOSO select SND_JACK if INPUT=y || INPUT=SND help Say Y here to include support for sound cards based on the - Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, - Essence ST (Deluxe), and Essence STX. + Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX, + Essence ST (Deluxe), and Essence STX (II). Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental; for the Xense, missing. diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c index cae36597aa71..0a34b5f1c475 100644 --- a/sound/pci/emu10k1/emu10k1_callback.c +++ b/sound/pci/emu10k1/emu10k1_callback.c @@ -85,6 +85,8 @@ snd_emu10k1_ops_setup(struct snd_emux *emux) * get more voice for pcm * * terminate most inactive voice and give it as a pcm voice. + * + * voice_lock is already held. */ int snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) @@ -92,12 +94,10 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) struct snd_emux *emu; struct snd_emux_voice *vp; struct best_voice best[V_END]; - unsigned long flags; int i; emu = hw->synth; - spin_lock_irqsave(&emu->voice_lock, flags); lookup_voices(emu, hw, best, 1); /* no OFF voices */ for (i = 0; i < V_END; i++) { if (best[i].voice >= 0) { @@ -113,11 +113,9 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) vp->emu->num_voices--; vp->ch = -1; vp->state = SNDRV_EMUX_ST_OFF; - spin_unlock_irqrestore(&emu->voice_lock, flags); return ch; } } - spin_unlock_irqrestore(&emu->voice_lock, flags); /* not found */ return -ENOMEM; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e354ab1ec20f..103e85a13f35 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -297,9 +297,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; #define ULI_NUM_CAPTURE 5 #define ULI_NUM_PLAYBACK 6 -/* ATI HDMI may have up to 8 playbacks and 0 capture */ +/* ATI HDMI has 1 playback and 0 capture */ #define ATIHDMI_NUM_CAPTURE 0 -#define ATIHDMI_NUM_PLAYBACK 8 +#define ATIHDMI_NUM_PLAYBACK 1 /* TERA has 4 playback and 3 capture */ #define TERA_NUM_CAPTURE 3 @@ -2930,7 +2930,7 @@ static int azx_suspend(struct device *dev) struct azx *chip = card->private_data; struct azx_pcm *p; - if (chip->disabled) + if (chip->disabled || chip->init_failed) return 0; snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); @@ -2961,7 +2961,7 @@ static int azx_resume(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip = card->private_data; - if (chip->disabled) + if (chip->disabled || chip->init_failed) return 0; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) @@ -2996,7 +2996,7 @@ static int azx_runtime_suspend(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip = card->private_data; - if (chip->disabled) + if (chip->disabled || chip->init_failed) return 0; if (!(chip->driver_caps & AZX_DCAPS_PM_RUNTIME)) @@ -3022,7 +3022,7 @@ static int azx_runtime_resume(struct device *dev) struct hda_codec *codec; int status; - if (chip->disabled) + if (chip->disabled || chip->init_failed) return 0; if (!(chip->driver_caps & AZX_DCAPS_PM_RUNTIME)) @@ -3057,7 +3057,7 @@ static int azx_runtime_idle(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip = card->private_data; - if (chip->disabled) + if (chip->disabled || chip->init_failed) return 0; if (!power_save_controller || @@ -3988,6 +3988,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = { /* Lynx Point */ { PCI_DEVICE(0x8086, 0x8c20), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, + /* 9 Series */ + { PCI_DEVICE(0x8086, 0x8ca0), + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, /* Wellsburg */ { PCI_DEVICE(0x8086, 0x8d20), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, @@ -4024,6 +4027,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = { /* BayTrail */ { PCI_DEVICE(0x8086, 0x0f04), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM }, + /* Braswell */ + { PCI_DEVICE(0x8086, 0x2284), + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, /* ICH */ { PCI_DEVICE(0x8086, 0x2668), .driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC | diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c index 8ed0bcc01386..eaf64ea2e1c1 100644 --- a/sound/pci/hda/patch_analog.c +++ b/sound/pci/hda/patch_analog.c @@ -333,6 +333,7 @@ static const struct hda_fixup ad1986a_fixups[] = { static const struct snd_pci_quirk ad1986a_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x30af, "HP B2800", AD1986A_FIXUP_LAPTOP_IMIC), + SND_PCI_QUIRK(0x1043, 0x1447, "ASUS A8JN", AD1986A_FIXUP_EAPD), SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8100, "ASUS P5", AD1986A_FIXUP_3STACK), SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8200, "ASUS M2", AD1986A_FIXUP_3STACK), SND_PCI_QUIRK(0x10de, 0xcb84, "ASUS A8N-VM", AD1986A_FIXUP_3STACK), diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 46ecdbb9053f..d5843da4ae19 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4379,6 +4379,9 @@ static void ca0132_download_dsp(struct hda_codec *codec) return; /* NOP */ #endif + if (spec->dsp_state == DSP_DOWNLOAD_FAILED) + return; /* don't retry failures */ + chipio_enable_clocks(codec); spec->dsp_state = DSP_DOWNLOADING; if (!ca0132_download_dsp_images(codec)) @@ -4555,7 +4558,8 @@ static int ca0132_init(struct hda_codec *codec) struct auto_pin_cfg *cfg = &spec->autocfg; int i; - spec->dsp_state = DSP_DOWNLOAD_INIT; + if (spec->dsp_state != DSP_DOWNLOAD_FAILED) + spec->dsp_state = DSP_DOWNLOAD_INIT; spec->curr_chip_addx = INVALID_CHIP_ADDRESS; snd_hda_power_up(codec); @@ -4666,6 +4670,7 @@ static int patch_ca0132(struct hda_codec *codec) codec->spec = spec; spec->codec = codec; + spec->dsp_state = DSP_DOWNLOAD_INIT; spec->num_mixers = 1; spec->mixers[0] = ca0132_mixer; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index bcf91bea3317..ffc19464b978 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -3237,6 +3237,7 @@ enum { CXT_FIXUP_HEADPHONE_MIC_PIN, CXT_FIXUP_HEADPHONE_MIC, CXT_FIXUP_GPIO1, + CXT_FIXUP_ASPIRE_DMIC, CXT_FIXUP_THINKPAD_ACPI, }; @@ -3397,6 +3398,12 @@ static const struct hda_fixup cxt_fixups[] = { { } }, }, + [CXT_FIXUP_ASPIRE_DMIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = cxt_fixup_stereo_dmic, + .chained = true, + .chain_id = CXT_FIXUP_GPIO1, + }, [CXT_FIXUP_THINKPAD_ACPI] = { .type = HDA_FIXUP_FUNC, .v.func = hda_fixup_thinkpad_acpi, @@ -3410,7 +3417,7 @@ static const struct snd_pci_quirk cxt5051_fixups[] = { static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_GPIO1), + SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 5ef95034d041..611110a3f1a4 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1062,6 +1062,7 @@ static void hdmi_pin_setup_infoframe(struct hda_codec *codec, { union audio_infoframe ai; + memset(&ai, 0, sizeof(ai)); if (conn_type == 0) { /* HDMI */ struct hdmi_audio_infoframe *hdmi_ai = &ai.hdmi; @@ -1123,8 +1124,10 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec, AMP_OUT_UNMUTE); eld = &per_pin->sink_eld; - if (!eld->monitor_present) + if (!eld->monitor_present) { + hdmi_set_channel_count(codec, per_pin->cvt_nid, channels); return; + } if (!non_pcm && per_pin->chmap_set) ca = hdmi_manual_channel_allocation(channels, per_pin->chmap); @@ -1554,19 +1557,22 @@ static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll) } } - if (pin_eld->eld_valid && !eld->eld_valid) { - update_eld = true; + if (pin_eld->eld_valid != eld->eld_valid) eld_changed = true; - } + + if (pin_eld->eld_valid && !eld->eld_valid) + update_eld = true; + if (update_eld) { bool old_eld_valid = pin_eld->eld_valid; pin_eld->eld_valid = eld->eld_valid; - eld_changed = pin_eld->eld_size != eld->eld_size || + if (pin_eld->eld_size != eld->eld_size || memcmp(pin_eld->eld_buffer, eld->eld_buffer, - eld->eld_size) != 0; - if (eld_changed) + eld->eld_size) != 0) { memcpy(pin_eld->eld_buffer, eld->eld_buffer, eld->eld_size); + eld_changed = true; + } pin_eld->eld_size = eld->eld_size; pin_eld->info = eld->info; @@ -2163,7 +2169,7 @@ static int generic_hdmi_resume(struct hda_codec *codec) struct hdmi_spec *spec = codec->spec; int pin_idx; - generic_hdmi_init(codec); + codec->patch_ops.init(codec); snd_hda_codec_resume_amp(codec); snd_hda_codec_resume_cache(codec); @@ -3311,6 +3317,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = { { .id = 0x80862808, .name = "Broadwell HDMI", .patch = patch_generic_hdmi }, { .id = 0x80862880, .name = "CedarTrail HDMI", .patch = patch_generic_hdmi }, { .id = 0x80862882, .name = "Valleyview2 HDMI", .patch = patch_generic_hdmi }, +{ .id = 0x80862883, .name = "Braswell HDMI", .patch = patch_generic_hdmi }, { .id = 0x808629fb, .name = "Crestline HDMI", .patch = patch_generic_hdmi }, {} /* terminator */ }; @@ -3367,6 +3374,7 @@ MODULE_ALIAS("snd-hda-codec-id:80862807"); MODULE_ALIAS("snd-hda-codec-id:80862808"); MODULE_ALIAS("snd-hda-codec-id:80862880"); MODULE_ALIAS("snd-hda-codec-id:80862882"); +MODULE_ALIAS("snd-hda-codec-id:80862883"); MODULE_ALIAS("snd-hda-codec-id:808629fb"); MODULE_LICENSE("GPL"); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8d0a84436674..4c826a40705c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -180,6 +180,8 @@ static void alc_fix_pll(struct hda_codec *codec) spec->pll_coef_idx); val = snd_hda_codec_read(codec, spec->pll_nid, 0, AC_VERB_GET_PROC_COEF, 0); + if (val == -1) + return; snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX, spec->pll_coef_idx); snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF, @@ -325,6 +327,7 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type) case 0x10ec0885: case 0x10ec0887: /*case 0x10ec0889:*/ /* this causes an SPDIF problem */ + case 0x10ec0900: alc889_coef_init(codec); break; case 0x10ec0888: @@ -993,6 +996,7 @@ static int alc_codec_rename_from_preset(struct hda_codec *codec) static const struct snd_pci_quirk beep_white_list[] = { SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1), + SND_PCI_QUIRK(0x1043, 0x115d, "ASUS", 1), SND_PCI_QUIRK(0x1043, 0x829f, "ASUS", 1), SND_PCI_QUIRK(0x1043, 0x8376, "EeePC", 1), SND_PCI_QUIRK(0x1043, 0x83ce, "EeePC", 1), @@ -1645,12 +1649,10 @@ static const struct hda_fixup alc260_fixups[] = { [ALC260_FIXUP_COEF] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { - { 0x20, AC_VERB_SET_COEF_INDEX, 0x07 }, - { 0x20, AC_VERB_SET_PROC_COEF, 0x3040 }, + { 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 }, + { 0x1a, AC_VERB_SET_PROC_COEF, 0x3040 }, { } }, - .chained = true, - .chain_id = ALC260_FIXUP_HP_PIN_0F, }, [ALC260_FIXUP_GPIO1] = { .type = HDA_FIXUP_VERBS, @@ -1665,8 +1667,8 @@ static const struct hda_fixup alc260_fixups[] = { [ALC260_FIXUP_REPLACER] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { - { 0x20, AC_VERB_SET_COEF_INDEX, 0x07 }, - { 0x20, AC_VERB_SET_PROC_COEF, 0x3050 }, + { 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 }, + { 0x1a, AC_VERB_SET_PROC_COEF, 0x3050 }, { } }, .chained = true, @@ -2329,6 +2331,7 @@ static int patch_alc882(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0882: case 0x10ec0885: + case 0x10ec0900: break; default: /* ALC883 and variants */ @@ -2766,6 +2769,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec) static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up) { int val = alc_read_coef_idx(codec, 0x04); + if (val == -1) + return; if (power_up) val |= 1 << 11; else @@ -2786,6 +2791,89 @@ static void alc269_shutup(struct hda_codec *codec) snd_hda_shutup_pins(codec); } +static void alc283_restore_default_value(struct hda_codec *codec) +{ + int val; + + /* Power Down Control */ + alc_write_coef_idx(codec, 0x03, 0x0002); + /* FIFO and filter clock */ + alc_write_coef_idx(codec, 0x05, 0x0700); + /* DMIC control */ + alc_write_coef_idx(codec, 0x07, 0x0200); + /* Analog clock */ + val = alc_read_coef_idx(codec, 0x06); + alc_write_coef_idx(codec, 0x06, (val & ~0x00f0) | 0x0); + /* JD */ + val = alc_read_coef_idx(codec, 0x08); + alc_write_coef_idx(codec, 0x08, (val & ~0xfffc) | 0x0c2c); + /* JD offset1 */ + alc_write_coef_idx(codec, 0x0a, 0xcccc); + /* JD offset2 */ + alc_write_coef_idx(codec, 0x0b, 0xcccc); + /* LDO1/2/3, DAC/ADC */ + alc_write_coef_idx(codec, 0x0e, 0x6fc0); + /* JD */ + val = alc_read_coef_idx(codec, 0x0f); + alc_write_coef_idx(codec, 0x0f, (val & ~0xf800) | 0x1000); + /* Capless */ + val = alc_read_coef_idx(codec, 0x10); + alc_write_coef_idx(codec, 0x10, (val & ~0xfc00) | 0x0c00); + /* Class D test 4 */ + alc_write_coef_idx(codec, 0x3a, 0x0); + /* IO power down directly */ + val = alc_read_coef_idx(codec, 0x0c); + alc_write_coef_idx(codec, 0x0c, (val & ~0xfe00) | 0x0); + /* ANC */ + alc_write_coef_idx(codec, 0x22, 0xa0c0); + /* AGC MUX */ + val = alc_read_coefex_idx(codec, 0x53, 0x01); + alc_write_coefex_idx(codec, 0x53, 0x01, (val & ~0x000f) | 0x0008); + /* DAC simple content protection */ + val = alc_read_coef_idx(codec, 0x1d); + alc_write_coef_idx(codec, 0x1d, (val & ~0x00e0) | 0x0); + /* ADC simple content protection */ + val = alc_read_coef_idx(codec, 0x1f); + alc_write_coef_idx(codec, 0x1f, (val & ~0x00e0) | 0x0); + /* DAC ADC Zero Detection */ + alc_write_coef_idx(codec, 0x21, 0x8804); + /* PLL */ + alc_write_coef_idx(codec, 0x2e, 0x2902); + /* capless control 2 */ + alc_write_coef_idx(codec, 0x33, 0xa080); + /* capless control 3 */ + alc_write_coef_idx(codec, 0x34, 0x3400); + /* capless control 4 */ + alc_write_coef_idx(codec, 0x35, 0x2f3e); + /* capless control 5 */ + alc_write_coef_idx(codec, 0x36, 0x0); + /* class D test 2 */ + val = alc_read_coef_idx(codec, 0x38); + alc_write_coef_idx(codec, 0x38, (val & ~0x0fff) | 0x0900); + /* class D test 3 */ + alc_write_coef_idx(codec, 0x39, 0x110a); + /* class D test 5 */ + val = alc_read_coef_idx(codec, 0x3b); + alc_write_coef_idx(codec, 0x3b, (val & ~0x00f8) | 0x00d8); + /* class D test 6 */ + alc_write_coef_idx(codec, 0x3c, 0x0014); + /* classD OCP */ + alc_write_coef_idx(codec, 0x3d, 0xc2ba); + /* classD pure DC test */ + val = alc_read_coef_idx(codec, 0x42); + alc_write_coef_idx(codec, 0x42, (val & ~0x0f80) | 0x0); + /* test mode */ + alc_write_coef_idx(codec, 0x49, 0x0); + /* Class D DC enable */ + val = alc_read_coef_idx(codec, 0x40); + alc_write_coef_idx(codec, 0x40, (val & ~0xf800) | 0x9800); + /* DC offset */ + val = alc_read_coef_idx(codec, 0x42); + alc_write_coef_idx(codec, 0x42, (val & ~0xf000) | 0x2000); + /* Class D amp control */ + alc_write_coef_idx(codec, 0x37, 0xfc06); +} + static void alc283_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -2793,6 +2881,8 @@ static void alc283_init(struct hda_codec *codec) bool hp_pin_sense; int val; + alc283_restore_default_value(codec); + if (!hp_pin) return; hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); @@ -2836,6 +2926,9 @@ static void alc283_shutup(struct hda_codec *codec) alc_write_coef_idx(codec, 0x43, 0x9004); + /*depop hp during suspend*/ + alc_write_coef_idx(codec, 0x06, 0x2100); + snd_hda_codec_write(codec, hp_pin, 0, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); @@ -2980,6 +3073,15 @@ static int alc269_resume(struct hda_codec *codec) snd_hda_codec_resume_cache(codec); alc_inv_dmic_sync(codec, true); hda_call_check_power_status(codec, 0x01); + + /* on some machine, the BIOS will clear the codec gpio data when enter + * suspend, and won't restore the data after resume, so we restore it + * in the driver. + */ + if (spec->gpio_led) + snd_hda_codec_write(codec, codec->afg, 0, AC_VERB_SET_GPIO_DATA, + spec->gpio_led); + if (spec->has_alc5505_dsp) alc5505_dsp_resume(codec); @@ -3126,8 +3228,9 @@ static void alc269_fixup_mic_mute_hook(void *private_data, int enabled) if (spec->mute_led_polarity) enabled = !enabled; - pinval = AC_PINCTL_IN_EN | - (enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80); + pinval = snd_hda_codec_get_pin_target(codec, spec->mute_led_nid); + pinval &= ~AC_PINCTL_VREFEN; + pinval |= enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80; if (spec->mute_led_nid) snd_hda_set_pin_ctl_cache(codec, spec->mute_led_nid, pinval); } @@ -3847,6 +3950,7 @@ enum { ALC269_FIXUP_HEADSET_MIC, ALC269_FIXUP_QUANTA_MUTE, ALC269_FIXUP_LIFEBOOK, + ALC269_FIXUP_LIFEBOOK_EXTMIC, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -3974,6 +4078,13 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_QUANTA_MUTE }, + [ALC269_FIXUP_LIFEBOOK_EXTMIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1903c }, /* headset mic, with jack detect */ + { } + }, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -4319,6 +4430,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x061f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0629, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x062c, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x062e, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0632, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK), SND_PCI_QUIRK(0x1028, 0x063e, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), @@ -4339,14 +4453,26 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED), /* ALC282 */ + SND_PCI_QUIRK(0x103c, 0x2191, "HP Touchsmart 14", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2192, "HP Touchsmart 15", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2210, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2211, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2212, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2214, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x226c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x226d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x226e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x226f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), @@ -4386,6 +4512,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2334, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -4408,6 +4538,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ), SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO), SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), @@ -4522,27 +4653,30 @@ static void alc269_fill_coef(struct hda_codec *codec) if ((alc_get_coef0(codec) & 0x00ff) == 0x017) { val = alc_read_coef_idx(codec, 0x04); /* Power up output pin */ - alc_write_coef_idx(codec, 0x04, val | (1<<11)); + if (val != -1) + alc_write_coef_idx(codec, 0x04, val | (1<<11)); } if ((alc_get_coef0(codec) & 0x00ff) == 0x018) { val = alc_read_coef_idx(codec, 0xd); - if ((val & 0x0c00) >> 10 != 0x1) { + if (val != -1 && (val & 0x0c00) >> 10 != 0x1) { /* Capless ramp up clock control */ alc_write_coef_idx(codec, 0xd, val | (1<<10)); } val = alc_read_coef_idx(codec, 0x17); - if ((val & 0x01c0) >> 6 != 0x4) { + if (val != -1 && (val & 0x01c0) >> 6 != 0x4) { /* Class D power on reset */ alc_write_coef_idx(codec, 0x17, val | (1<<7)); } } val = alc_read_coef_idx(codec, 0xd); /* Class D */ - alc_write_coef_idx(codec, 0xd, val | (1<<14)); + if (val != -1) + alc_write_coef_idx(codec, 0xd, val | (1<<14)); val = alc_read_coef_idx(codec, 0x4); /* HP */ - alc_write_coef_idx(codec, 0x4, val | (1<<11)); + if (val != -1) + alc_write_coef_idx(codec, 0x4, val | (1<<11)); } /* @@ -4618,6 +4752,7 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC285; break; case 0x10ec0286: + case 0x10ec0288: spec->codec_variant = ALC269_TYPE_ALC286; break; case 0x10ec0255: @@ -5184,6 +5319,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0626, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0628, "Dell", ALC668_FIXUP_AUTO_MUTE), SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_AUTO_MUTE), + SND_PCI_QUIRK(0x1028, 0x0696, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A_CHMAP), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_CHMAP), @@ -5424,6 +5561,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = { { .id = 0x10ec0284, .name = "ALC284", .patch = patch_alc269 }, { .id = 0x10ec0285, .name = "ALC285", .patch = patch_alc269 }, { .id = 0x10ec0286, .name = "ALC286", .patch = patch_alc269 }, + { .id = 0x10ec0288, .name = "ALC288", .patch = patch_alc269 }, { .id = 0x10ec0290, .name = "ALC290", .patch = patch_alc269 }, { .id = 0x10ec0292, .name = "ALC292", .patch = patch_alc269 }, { .id = 0x10ec0293, .name = "ALC293", .patch = patch_alc269 }, @@ -5444,6 +5582,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = { { .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 }, { .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 }, { .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 }, + { .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 }, { .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 }, { .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 }, { .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 }, diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 3bc29c9b2529..15270a2e71cc 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -84,6 +84,7 @@ enum { STAC_DELL_EQ, STAC_ALIENWARE_M17X, STAC_92HD89XX_HP_FRONT_JACK, + STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK, STAC_92HD73XX_MODELS }; @@ -558,8 +559,8 @@ static void stac_init_power_map(struct hda_codec *codec) if (snd_hda_jack_tbl_get(codec, nid)) continue; if (def_conf == AC_JACK_PORT_COMPLEX && - !(spec->vref_mute_led_nid == nid || - is_jack_detectable(codec, nid))) { + spec->vref_mute_led_nid != nid && + is_jack_detectable(codec, nid)) { snd_hda_jack_detect_enable_callback(codec, nid, STAC_PWR_EVENT, jack_update_power); @@ -1803,6 +1804,11 @@ static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = { {} }; +static const struct hda_pintbl stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs[] = { + { 0x0e, 0x400000f0 }, + {} +}; + static void stac92hd73xx_fixup_ref(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -1925,6 +1931,10 @@ static const struct hda_fixup stac92hd73xx_fixups[] = { [STAC_92HD89XX_HP_FRONT_JACK] = { .type = HDA_FIXUP_PINS, .v.pins = stac92hd89xx_hp_front_jack_pin_configs, + }, + [STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = { + .type = HDA_FIXUP_PINS, + .v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs, } }; @@ -1985,6 +1995,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = { "Alienware M17x", STAC_ALIENWARE_M17X), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490, "Alienware M17x R3", STAC_DELL_EQ), + SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1927, + "HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK), SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17, "unknown HP", STAC_92HD89XX_HP_FRONT_JACK), {} /* terminator */ @@ -4200,11 +4212,18 @@ static int stac_parse_auto_config(struct hda_codec *codec) return err; } - stac_init_power_map(codec); - return 0; } +static int stac_build_controls(struct hda_codec *codec) +{ + int err = snd_hda_gen_build_controls(codec); + + if (err < 0) + return err; + stac_init_power_map(codec); + return 0; +} static int stac_init(struct hda_codec *codec) { @@ -4316,7 +4335,7 @@ static int stac_suspend(struct hda_codec *codec) #endif /* CONFIG_PM */ static const struct hda_codec_ops stac_patch_ops = { - .build_controls = snd_hda_gen_build_controls, + .build_controls = stac_build_controls, .build_pcms = snd_hda_gen_build_pcms, .init = stac_init, .free = stac_free, diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c index 28ec872e54c0..b6e278fe8f67 100644 --- a/sound/pci/ice1712/ice1712.c +++ b/sound/pci/ice1712/ice1712.c @@ -685,9 +685,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pointer(struct snd_pcm_substream * if (!(snd_ice1712_read(ice, ICE1712_IREG_PBK_CTRL) & 1)) return 0; ptr = runtime->buffer_size - inw(ice->ddma_port + 4); + ptr = bytes_to_frames(substream->runtime, ptr); if (ptr == runtime->buffer_size) ptr = 0; - return bytes_to_frames(substream->runtime, ptr); + return ptr; } static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substream *substream) @@ -704,9 +705,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substrea addr = ICE1712_DSC_ADDR0; ptr = snd_ice1712_ds_read(ice, substream->number * 2, addr) - ice->playback_con_virt_addr[substream->number]; + ptr = bytes_to_frames(substream->runtime, ptr); if (ptr == substream->runtime->buffer_size) ptr = 0; - return bytes_to_frames(substream->runtime, ptr); + return ptr; } static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *substream) @@ -717,9 +719,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *s if (!(snd_ice1712_read(ice, ICE1712_IREG_CAP_CTRL) & 1)) return 0; ptr = inl(ICEREG(ice, CONCAP_ADDR)) - ice->capture_con_virt_addr; + ptr = bytes_to_frames(substream->runtime, ptr); if (ptr == substream->runtime->buffer_size) ptr = 0; - return bytes_to_frames(substream->runtime, ptr); + return ptr; } static const struct snd_pcm_hardware snd_ice1712_playback = { @@ -1113,9 +1116,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pro_pointer(struct snd_pcm_substre if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_PLAYBACK_START)) return 0; ptr = ice->playback_pro_size - (inw(ICEMT(ice, PLAYBACK_SIZE)) << 2); + ptr = bytes_to_frames(substream->runtime, ptr); if (ptr == substream->runtime->buffer_size) ptr = 0; - return bytes_to_frames(substream->runtime, ptr); + return ptr; } static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substream *substream) @@ -1126,9 +1130,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substrea if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_CAPTURE_START_SHADOW)) return 0; ptr = ice->capture_pro_size - (inw(ICEMT(ice, CAPTURE_SIZE)) << 2); + ptr = bytes_to_frames(substream->runtime, ptr); if (ptr == substream->runtime->buffer_size) ptr = 0; - return bytes_to_frames(substream->runtime, ptr); + return ptr; } static const struct snd_pcm_hardware snd_ice1712_playback_pro = { diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c index 64b9fda5f04a..dbbbacfd535e 100644 --- a/sound/pci/oxygen/virtuoso.c +++ b/sound/pci/oxygen/virtuoso.c @@ -53,6 +53,7 @@ static DEFINE_PCI_DEVICE_TABLE(xonar_ids) = { { OXYGEN_PCI_SUBID(0x1043, 0x835e) }, { OXYGEN_PCI_SUBID(0x1043, 0x838e) }, { OXYGEN_PCI_SUBID(0x1043, 0x8522) }, + { OXYGEN_PCI_SUBID(0x1043, 0x85f4) }, { OXYGEN_PCI_SUBID_BROKEN_EEPROM }, { } }; diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c index c8c7f2c9b355..e02605931669 100644 --- a/sound/pci/oxygen/xonar_pcm179x.c +++ b/sound/pci/oxygen/xonar_pcm179x.c @@ -100,8 +100,8 @@ */ /* - * Xonar Essence ST (Deluxe)/STX - * ----------------------------- + * Xonar Essence ST (Deluxe)/STX (II) + * ---------------------------------- * * CMI8788: * @@ -1138,6 +1138,14 @@ int get_xonar_pcm179x_model(struct oxygen *chip, chip->model.resume = xonar_stx_resume; chip->model.set_dac_params = set_pcm1796_params; break; + case 0x85f4: + chip->model = model_xonar_st; + /* TODO: daughterboard support */ + chip->model.shortname = "Xonar STX II"; + chip->model.init = xonar_stx_init; + chip->model.resume = xonar_stx_resume; + chip->model.set_dac_params = set_pcm1796_params; + break; default: return -EINVAL; } diff --git a/sound/soc/blackfin/bf5xx-i2s-pcm.c b/sound/soc/blackfin/bf5xx-i2s-pcm.c index a3881c4381c9..bcf591373a7a 100644 --- a/sound/soc/blackfin/bf5xx-i2s-pcm.c +++ b/sound/soc/blackfin/bf5xx-i2s-pcm.c @@ -290,19 +290,19 @@ static int bf5xx_pcm_silence(struct snd_pcm_substream *substream, unsigned int sample_size = runtime->sample_bits / 8; void *buf = runtime->dma_area; struct bf5xx_i2s_pcm_data *dma_data; - unsigned int offset, size; + unsigned int offset, samples; dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream); if (dma_data->tdm_mode) { offset = pos * 8 * sample_size; - size = count * 8 * sample_size; + samples = count * 8; } else { offset = frames_to_bytes(runtime, pos); - size = frames_to_bytes(runtime, count); + samples = count * runtime->channels; } - snd_pcm_format_set_silence(runtime->format, buf + offset, size); + snd_pcm_format_set_silence(runtime->format, buf + offset, samples); return 0; } diff --git a/sound/soc/codecs/adau1701.c b/sound/soc/codecs/adau1701.c index d71c59cf7bdd..370b742117ef 100644 --- a/sound/soc/codecs/adau1701.c +++ b/sound/soc/codecs/adau1701.c @@ -230,8 +230,10 @@ static int adau1701_reg_read(void *context, unsigned int reg, *value = 0; - for (i = 0; i < size; i++) - *value |= recv_buf[i] << (i * 8); + for (i = 0; i < size; i++) { + *value <<= 8; + *value |= recv_buf[i]; + } return 0; } diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c index 6e9ea8379a91..7a272fa90b39 100644 --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -124,9 +124,8 @@ static int cs42l51_set_chan_mix(struct snd_kcontrol *kcontrol, static const DECLARE_TLV_DB_SCALE(adc_pcm_tlv, -5150, 50, 0); static const DECLARE_TLV_DB_SCALE(tone_tlv, -1050, 150, 0); -/* This is a lie. after -102 db, it stays at -102 */ -/* maybe a range would be better */ -static const DECLARE_TLV_DB_SCALE(aout_tlv, -11550, 50, 0); + +static const DECLARE_TLV_DB_SCALE(aout_tlv, -10200, 50, 0); static const DECLARE_TLV_DB_SCALE(boost_tlv, 1600, 1600, 0); static const char *chan_mix[] = { @@ -141,7 +140,7 @@ static const struct soc_enum cs42l51_chan_mix = static const struct snd_kcontrol_new cs42l51_snd_controls[] = { SOC_DOUBLE_R_SX_TLV("PCM Playback Volume", CS42L51_PCMA_VOL, CS42L51_PCMB_VOL, - 6, 0x19, 0x7F, adc_pcm_tlv), + 0, 0x19, 0x7F, adc_pcm_tlv), SOC_DOUBLE_R("PCM Playback Switch", CS42L51_PCMA_VOL, CS42L51_PCMB_VOL, 7, 1, 1), SOC_DOUBLE_R_SX_TLV("Analog Playback Volume", @@ -149,7 +148,7 @@ static const struct snd_kcontrol_new cs42l51_snd_controls[] = { 0, 0x34, 0xE4, aout_tlv), SOC_DOUBLE_R_SX_TLV("ADC Mixer Volume", CS42L51_ADCA_VOL, CS42L51_ADCB_VOL, - 6, 0x19, 0x7F, adc_pcm_tlv), + 0, 0x19, 0x7F, adc_pcm_tlv), SOC_DOUBLE_R("ADC Mixer Switch", CS42L51_ADCA_VOL, CS42L51_ADCB_VOL, 7, 1, 1), SOC_SINGLE("Playback Deemphasis Switch", CS42L51_DAC_CTL, 3, 1, 0), diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c index 0bac6d5a4ac8..1102ced9b20e 100644 --- a/sound/soc/codecs/cs42l52.c +++ b/sound/soc/codecs/cs42l52.c @@ -347,7 +347,7 @@ static const char * const right_swap_text[] = { static const unsigned int swap_values[] = { 0, 1, 3 }; static const struct soc_enum adca_swap_enum = - SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 1, + SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 3, ARRAY_SIZE(left_swap_text), left_swap_text, swap_values); @@ -356,7 +356,7 @@ static const struct snd_kcontrol_new adca_mixer = SOC_DAPM_ENUM("Route", adca_swap_enum); static const struct soc_enum pcma_swap_enum = - SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 1, + SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 3, ARRAY_SIZE(left_swap_text), left_swap_text, swap_values); @@ -365,7 +365,7 @@ static const struct snd_kcontrol_new pcma_mixer = SOC_DAPM_ENUM("Route", pcma_swap_enum); static const struct soc_enum adcb_swap_enum = - SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 1, + SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 3, ARRAY_SIZE(right_swap_text), right_swap_text, swap_values); @@ -374,7 +374,7 @@ static const struct snd_kcontrol_new adcb_mixer = SOC_DAPM_ENUM("Route", adcb_swap_enum); static const struct soc_enum pcmb_swap_enum = - SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 1, + SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 3, ARRAY_SIZE(right_swap_text), right_swap_text, swap_values); diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c index 549d5d6a3fef..7b95f7cbc515 100644 --- a/sound/soc/codecs/cs42l73.c +++ b/sound/soc/codecs/cs42l73.c @@ -319,7 +319,7 @@ static const char * const cs42l73_mono_mix_texts[] = { static const unsigned int cs42l73_mono_mix_values[] = { 0, 1, 2 }; static const struct soc_enum spk_asp_enum = - SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 1, + SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 3, ARRAY_SIZE(cs42l73_mono_mix_texts), cs42l73_mono_mix_texts, cs42l73_mono_mix_values); @@ -337,7 +337,7 @@ static const struct snd_kcontrol_new spk_xsp_mixer = SOC_DAPM_ENUM("Route", spk_xsp_enum); static const struct soc_enum esl_asp_enum = - SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 5, + SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 3, ARRAY_SIZE(cs42l73_mono_mix_texts), cs42l73_mono_mix_texts, cs42l73_mono_mix_values); @@ -346,7 +346,7 @@ static const struct snd_kcontrol_new esl_asp_mixer = SOC_DAPM_ENUM("Route", esl_asp_enum); static const struct soc_enum esl_xsp_enum = - SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 7, + SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 3, ARRAY_SIZE(cs42l73_mono_mix_texts), cs42l73_mono_mix_texts, cs42l73_mono_mix_values); diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 9f714ea86613..ddfb0fddd030 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -255,6 +255,7 @@ static struct reg_default max98090_reg[] = { static bool max98090_volatile_register(struct device *dev, unsigned int reg) { switch (reg) { + case M98090_REG_SOFTWARE_RESET: case M98090_REG_DEVICE_STATUS: case M98090_REG_JACK_STATUS: case M98090_REG_REVISION_ID: @@ -2249,7 +2250,7 @@ static int max98090_probe(struct snd_soc_codec *codec) /* Register for interrupts */ dev_dbg(codec->dev, "irq = %d\n", max98090->irq); - ret = request_threaded_irq(max98090->irq, NULL, + ret = devm_request_threaded_irq(codec->dev, max98090->irq, NULL, max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "max98090_interrupt", codec); if (ret < 0) { @@ -2360,6 +2361,8 @@ static int max98090_runtime_resume(struct device *dev) regcache_cache_only(max98090->regmap, false); + max98090_reset(max98090); + regcache_sync(max98090->regmap); return 0; diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index 886924934aa5..5cb515b08a32 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2071,6 +2071,7 @@ static struct snd_soc_codec_driver soc_codec_dev_rt5640 = { static const struct regmap_config rt5640_regmap = { .reg_bits = 8, .val_bits = 16, + .use_single_rw = true, .max_register = RT5640_VENDOR_ID2 + 1 + (ARRAY_SIZE(rt5640_ranges) * RT5640_PR_SPACING), diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index 470fbfb4b386..fd53d37e1181 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -169,7 +169,7 @@ static int snd_soc_dapm_put_volsw_aic3x(struct snd_kcontrol *kcontrol, mask <<= shift; val <<= shift; - change = snd_soc_test_bits(codec, val, mask, reg); + change = snd_soc_test_bits(codec, reg, mask, val); if (change) { update.kcontrol = kcontrol; update.reg = reg; @@ -1121,6 +1121,7 @@ static int aic3x_regulator_event(struct notifier_block *nb, static int aic3x_set_power(struct snd_soc_codec *codec, int power) { struct aic3x_priv *aic3x = snd_soc_codec_get_drvdata(codec); + unsigned int pll_c, pll_d; int ret; if (power) { @@ -1138,6 +1139,18 @@ static int aic3x_set_power(struct snd_soc_codec *codec, int power) /* Sync reg_cache with the hardware */ regcache_cache_only(aic3x->regmap, false); regcache_sync(aic3x->regmap); + + /* Rewrite paired PLL D registers in case cached sync skipped + * writing one of them and thus caused other one also not + * being written + */ + pll_c = snd_soc_read(codec, AIC3X_PLL_PROGC_REG); + pll_d = snd_soc_read(codec, AIC3X_PLL_PROGD_REG); + if (pll_c == aic3x_reg[AIC3X_PLL_PROGC_REG].def || + pll_d == aic3x_reg[AIC3X_PLL_PROGD_REG].def) { + snd_soc_write(codec, AIC3X_PLL_PROGC_REG, pll_c); + snd_soc_write(codec, AIC3X_PLL_PROGD_REG, pll_d); + } } else { /* * Do soft reset to this codec instance in order to clear diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 97db3b45b411..799348e9cdd0 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -154,6 +154,7 @@ static struct reg_default wm8962_reg[] = { { 40, 0x0000 }, /* R40 - SPKOUTL volume */ { 41, 0x0000 }, /* R41 - SPKOUTR volume */ + { 49, 0x0010 }, /* R49 - Class D Control 1 */ { 51, 0x0003 }, /* R51 - Class D Control 2 */ { 56, 0x0506 }, /* R56 - Clocking 4 */ @@ -795,7 +796,6 @@ static bool wm8962_volatile_register(struct device *dev, unsigned int reg) case WM8962_ALC2: case WM8962_THERMAL_SHUTDOWN_STATUS: case WM8962_ADDITIONAL_CONTROL_4: - case WM8962_CLASS_D_CONTROL_1: case WM8962_DC_SERVO_6: case WM8962_INTERRUPT_STATUS_1: case WM8962_INTERRUPT_STATUS_2: @@ -2922,13 +2922,22 @@ static int wm8962_set_fll(struct snd_soc_codec *codec, int fll_id, int source, static int wm8962_mute(struct snd_soc_dai *dai, int mute) { struct snd_soc_codec *codec = dai->codec; - int val; + int val, ret; if (mute) - val = WM8962_DAC_MUTE; + val = WM8962_DAC_MUTE | WM8962_DAC_MUTE_ALT; else val = 0; + /** + * The DAC mute bit is mirrored in two registers, update both to keep + * the register cache consistent. + */ + ret = snd_soc_update_bits(codec, WM8962_CLASS_D_CONTROL_1, + WM8962_DAC_MUTE_ALT, val); + if (ret < 0) + return ret; + return snd_soc_update_bits(codec, WM8962_ADC_DAC_CONTROL_1, WM8962_DAC_MUTE, val); } diff --git a/sound/soc/codecs/wm8962.h b/sound/soc/codecs/wm8962.h index a1a5d5294c19..910aafd09d21 100644 --- a/sound/soc/codecs/wm8962.h +++ b/sound/soc/codecs/wm8962.h @@ -1954,6 +1954,10 @@ #define WM8962_SPKOUTL_ENA_MASK 0x0040 /* SPKOUTL_ENA */ #define WM8962_SPKOUTL_ENA_SHIFT 6 /* SPKOUTL_ENA */ #define WM8962_SPKOUTL_ENA_WIDTH 1 /* SPKOUTL_ENA */ +#define WM8962_DAC_MUTE_ALT 0x0010 /* DAC_MUTE */ +#define WM8962_DAC_MUTE_ALT_MASK 0x0010 /* DAC_MUTE */ +#define WM8962_DAC_MUTE_ALT_SHIFT 4 /* DAC_MUTE */ +#define WM8962_DAC_MUTE_ALT_WIDTH 1 /* DAC_MUTE */ #define WM8962_SPKOUTL_PGA_MUTE 0x0002 /* SPKOUTL_PGA_MUTE */ #define WM8962_SPKOUTL_PGA_MUTE_MASK 0x0002 /* SPKOUTL_PGA_MUTE */ #define WM8962_SPKOUTL_PGA_MUTE_SHIFT 1 /* SPKOUTL_PGA_MUTE */ diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index adb72063d44e..d98e52f647d2 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -3497,6 +3497,7 @@ static irqreturn_t wm8994_mic_irq(int irq, void *data) return IRQ_HANDLED; } +/* Should be called with accdet_lock held */ static void wm1811_micd_stop(struct snd_soc_codec *codec) { struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); @@ -3504,14 +3505,10 @@ static void wm1811_micd_stop(struct snd_soc_codec *codec) if (!wm8994->jackdet) return; - mutex_lock(&wm8994->accdet_lock); - snd_soc_update_bits(codec, WM8958_MIC_DETECT_1, WM8958_MICD_ENA, 0); wm1811_jackdet_set_mode(codec, WM1811_JACKDET_MODE_JACK); - mutex_unlock(&wm8994->accdet_lock); - if (wm8994->wm8994->pdata.jd_ext_cap) snd_soc_dapm_disable_pin(&codec->dapm, "MICBIAS2"); @@ -3552,10 +3549,10 @@ static void wm8958_open_circuit_work(struct work_struct *work) open_circuit_work.work); struct device *dev = wm8994->wm8994->dev; - wm1811_micd_stop(wm8994->hubs.codec); - mutex_lock(&wm8994->accdet_lock); + wm1811_micd_stop(wm8994->hubs.codec); + dev_dbg(dev, "Reporting open circuit\n"); wm8994->jack_mic = false; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 444626fcab40..53c03aff762e 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1745,3 +1745,5 @@ int wm_adsp2_init(struct wm_adsp *adsp, bool dvfs) return 0; } EXPORT_SYMBOL_GPL(wm_adsp2_init); + +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index 670afa29e30d..7350ebbae642 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -418,8 +418,17 @@ static int davinci_config_channel_size(struct davinci_mcasp *mcasp, { u32 fmt; u32 tx_rotate = (word_length / 4) & 0x7; - u32 rx_rotate = (32 - word_length) / 4; u32 mask = (1ULL << word_length) - 1; + /* + * For captured data we should not rotate, inversion and masking is + * enoguh to get the data to the right position: + * Format data from bus after reverse (XRBUF) + * S16_LE: |LSB|MSB|xxx|xxx| |xxx|xxx|MSB|LSB| + * S24_3LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB| + * S24_LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB| + * S32_LE: |LSB|DAT|DAT|MSB| |MSB|DAT|DAT|LSB| + */ + u32 rx_rotate = 0; /* * if s BCLK-to-LRCLK ratio has been configured via the set_clkdiv() diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c index a3119a00d8fa..6c6b35e471c8 100644 --- a/sound/soc/pxa/pxa-ssp.c +++ b/sound/soc/pxa/pxa-ssp.c @@ -725,7 +725,8 @@ static int pxa_ssp_probe(struct snd_soc_dai *dai) ssp_handle = of_parse_phandle(dev->of_node, "port", 0); if (!ssp_handle) { dev_err(dev, "unable to get 'port' phandle\n"); - return -ENODEV; + ret = -ENODEV; + goto err_priv; } priv->ssp = pxa_ssp_request_of(ssp_handle, "SoC audio"); @@ -766,9 +767,7 @@ static int pxa_ssp_remove(struct snd_soc_dai *dai) SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_64000 | \ SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000) -#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\ - SNDRV_PCM_FMTBIT_S24_LE | \ - SNDRV_PCM_FMTBIT_S32_LE) +#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE) static const struct snd_soc_dai_ops pxa_ssp_dai_ops = { .startup = pxa_ssp_startup, diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index 0a9b44c940ce..5dae66002a11 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -915,11 +915,9 @@ static int i2s_suspend(struct snd_soc_dai *dai) { struct i2s_dai *i2s = to_info(dai); - if (dai->active) { - i2s->suspend_i2smod = readl(i2s->addr + I2SMOD); - i2s->suspend_i2scon = readl(i2s->addr + I2SCON); - i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR); - } + i2s->suspend_i2smod = readl(i2s->addr + I2SMOD); + i2s->suspend_i2scon = readl(i2s->addr + I2SCON); + i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR); return 0; } @@ -928,11 +926,9 @@ static int i2s_resume(struct snd_soc_dai *dai) { struct i2s_dai *i2s = to_info(dai); - if (dai->active) { - writel(i2s->suspend_i2scon, i2s->addr + I2SCON); - writel(i2s->suspend_i2smod, i2s->addr + I2SMOD); - writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR); - } + writel(i2s->suspend_i2scon, i2s->addr + I2SCON); + writel(i2s->suspend_i2smod, i2s->addr + I2SMOD); + writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR); return 0; } diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index b9dc6acbba8c..e4da224d7253 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -251,7 +251,6 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget, static void dapm_kcontrol_free(struct snd_kcontrol *kctl) { struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl); - kfree(data->widget); kfree(data->wlist); kfree(data); } @@ -690,9 +689,9 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, int shared; struct snd_kcontrol *kcontrol; bool wname_in_long_name, kcname_in_long_name; - char *long_name; + char *long_name = NULL; const char *name; - int ret; + int ret = 0; if (dapm->codec) prefix = dapm->codec->name_prefix; @@ -757,15 +756,17 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, kcontrol = snd_soc_cnew(&w->kcontrol_news[kci], NULL, name, prefix); - kfree(long_name); - if (!kcontrol) - return -ENOMEM; + if (!kcontrol) { + ret = -ENOMEM; + goto exit_free; + } + kcontrol->private_free = dapm_kcontrol_free; ret = dapm_kcontrol_data_alloc(w, kcontrol); if (ret) { snd_ctl_free_one(kcontrol); - return ret; + goto exit_free; } ret = snd_ctl_add(card, kcontrol); @@ -773,17 +774,18 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, dev_err(dapm->dev, "ASoC: failed to add widget %s dapm kcontrol %s: %d\n", w->name, name, ret); - return ret; + goto exit_free; } } ret = dapm_kcontrol_add_widget(kcontrol, w); - if (ret) - return ret; + if (ret == 0) + w->kcontrols[kci] = kcontrol; - w->kcontrols[kci] = kcontrol; +exit_free: + kfree(long_name); - return 0; + return ret; } /* create new dapm mixer control */ @@ -2889,22 +2891,19 @@ int snd_soc_dapm_put_volsw(struct snd_kcontrol *kcontrol, mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); change = dapm_kcontrol_set_value(kcontrol, val); - - if (reg != SND_SOC_NOPM) { - mask = mask << shift; - val = val << shift; - - change = snd_soc_test_bits(codec, reg, mask, val); - } - if (change) { if (reg != SND_SOC_NOPM) { - update.kcontrol = kcontrol; - update.reg = reg; - update.mask = mask; - update.val = val; + mask = mask << shift; + val = val << shift; + + if (snd_soc_test_bits(codec, reg, mask, val)) { + update.kcontrol = kcontrol; + update.reg = reg; + update.mask = mask; + update.val = val; + card->update = &update; + } - card->update = &update; } ret = soc_dapm_mixer_update_power(card, kcontrol, connect); @@ -3650,8 +3649,11 @@ void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card) cpu_dai = rtd->cpu_dai; codec_dai = rtd->codec_dai; - /* dynamic FE links have no fixed DAI mapping */ - if (rtd->dai_link->dynamic) + /* + * dynamic FE links have no fixed DAI mapping. + * CODEC<->CODEC links have no direct connection. + */ + if (rtd->dai_link->dynamic || rtd->dai_link->params) continue; /* there is no point in connecting BE DAI links with dummies */ diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 28522bd03b8e..02733ded2cb1 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1989,7 +1989,6 @@ int soc_dpcm_runtime_update(struct snd_soc_card *card) paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list); if (paths < 0) { - dpcm_path_put(&list); dev_warn(fe->dev, "ASoC: %s no valid %s path\n", fe->dai_link->name, "playback"); mutex_unlock(&card->mutex); @@ -2012,6 +2011,7 @@ int soc_dpcm_runtime_update(struct snd_soc_card *card) dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK); } + dpcm_path_put(&list); capture: /* skip if FE doesn't have capture capability */ if (!fe->cpu_dai->driver->capture.channels_min) @@ -2019,7 +2019,6 @@ capture: paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list); if (paths < 0) { - dpcm_path_put(&list); dev_warn(fe->dev, "ASoC: %s no valid %s path\n", fe->dai_link->name, "capture"); mutex_unlock(&card->mutex); @@ -2084,7 +2083,6 @@ static int dpcm_fe_dai_open(struct snd_pcm_substream *fe_substream) fe->dpcm[stream].runtime = fe_substream->runtime; if (dpcm_path_get(fe, stream, &list) <= 0) { - dpcm_path_put(&list); dev_dbg(fe->dev, "ASoC: %s no valid %s route\n", fe->dai_link->name, stream ? "capture" : "playback"); } diff --git a/sound/usb/card.c b/sound/usb/card.c index d979050e6a6a..ab433a02dbf1 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -304,6 +304,11 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif) static int snd_usb_audio_free(struct snd_usb_audio *chip) { + struct list_head *p, *n; + + list_for_each_safe(p, n, &chip->ep_list) + snd_usb_endpoint_free(p); + mutex_destroy(&chip->mutex); kfree(chip); return 0; @@ -580,27 +585,30 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, struct snd_usb_audio *chip) { struct snd_card *card; - struct list_head *p, *n; + struct list_head *p; + bool was_shutdown; if (chip == (void *)-1L) return; card = chip->card; down_write(&chip->shutdown_rwsem); + was_shutdown = chip->shutdown; chip->shutdown = 1; up_write(&chip->shutdown_rwsem); mutex_lock(®ister_mutex); - chip->num_interfaces--; - if (chip->num_interfaces <= 0) { + if (!was_shutdown) { + struct snd_usb_endpoint *ep; + snd_card_disconnect(card); /* release the pcm resources */ list_for_each(p, &chip->pcm_list) { snd_usb_stream_disconnect(p); } /* release the endpoint resources */ - list_for_each_safe(p, n, &chip->ep_list) { - snd_usb_endpoint_free(p); + list_for_each_entry(ep, &chip->ep_list, list) { + snd_usb_endpoint_release(ep); } /* release the midi resources */ list_for_each(p, &chip->midi_list) { @@ -610,6 +618,10 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, list_for_each(p, &chip->mixer_list) { snd_usb_mixer_disconnect(p); } + } + + chip->num_interfaces--; + if (chip->num_interfaces <= 0) { usb_chip[chip->index] = NULL; mutex_unlock(®ister_mutex); snd_card_free_when_closed(card); diff --git a/sound/usb/card.h b/sound/usb/card.h index 9867ab866857..97acb906acc2 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -92,6 +92,7 @@ struct snd_usb_endpoint { unsigned int curframesize; /* current packet size in frames (for capture) */ unsigned int syncmaxsize; /* sync endpoint packet size */ unsigned int fill_max:1; /* fill max packet size always */ + unsigned int udh01_fb_quirk:1; /* corrupted feedback data */ unsigned int datainterval; /* log_2 of data packet interval */ unsigned int syncinterval; /* P for adaptive mode, 0 otherwise */ unsigned char silence_value; diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 83aabea259d7..105ece3c14e3 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -469,6 +469,10 @@ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip, ep->syncinterval = 3; ep->syncmaxsize = le16_to_cpu(get_endpoint(alts, 1)->wMaxPacketSize); + + if (chip->usb_id == USB_ID(0x0644, 0x8038) /* TEAC UD-H01 */ && + ep->syncmaxsize == 4) + ep->udh01_fb_quirk = 1; } list_add_tail(&ep->list, &chip->ep_list); @@ -977,19 +981,30 @@ void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep) } /** + * snd_usb_endpoint_release: Tear down an snd_usb_endpoint + * + * @ep: the endpoint to release + * + * This function does not care for the endpoint's use count but will tear + * down all the streaming URBs immediately. + */ +void snd_usb_endpoint_release(struct snd_usb_endpoint *ep) +{ + release_urbs(ep, 1); +} + +/** * snd_usb_endpoint_free: Free the resources of an snd_usb_endpoint * * @ep: the list header of the endpoint to free * - * This function does not care for the endpoint's use count but will tear - * down all the streaming URBs immediately and free all resources. + * This free all resources of the given ep. */ void snd_usb_endpoint_free(struct list_head *head) { struct snd_usb_endpoint *ep; ep = list_entry(head, struct snd_usb_endpoint, list); - release_urbs(ep, 1); kfree(ep); } @@ -1099,7 +1114,16 @@ void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep, if (f == 0) return; - if (unlikely(ep->freqshift == INT_MIN)) { + if (unlikely(sender->udh01_fb_quirk)) { + /* + * The TEAC UD-H01 firmware sometimes changes the feedback value + * by +/- 0x1.0000. + */ + if (f < ep->freqn - 0x8000) + f += 0x10000; + else if (f > ep->freqn + 0x8000) + f -= 0x10000; + } else if (unlikely(ep->freqshift == INT_MIN)) { /* * The first time we see a feedback value, determine its format * by shifting it left or right until it matches the nominal diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h index 1c7e8ee48abc..e61ee5c356a3 100644 --- a/sound/usb/endpoint.h +++ b/sound/usb/endpoint.h @@ -23,6 +23,7 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep); void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep); int snd_usb_endpoint_activate(struct snd_usb_endpoint *ep); void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep); +void snd_usb_endpoint_release(struct snd_usb_endpoint *ep); void snd_usb_endpoint_free(struct list_head *head); int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep); diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index ca3256d6fde3..ede4b92710aa 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1488,7 +1488,8 @@ static void retire_playback_urb(struct snd_usb_substream *subs, * on two reads of a counter updated every ms. */ if (abs(est_delay - subs->last_delay) * 1000 > runtime->rate * 2) - snd_printk(KERN_DEBUG "delay: estimated %d, actual %d\n", + dev_dbg_ratelimited(&subs->dev->dev, + "delay: estimated %d, actual %d\n", est_delay, subs->last_delay); if (!subs->running) { diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index f652b10ce905..c657752a420c 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -385,6 +385,36 @@ YAMAHA_DEVICE(0x105d, NULL), } }, { + USB_DEVICE(0x0499, 0x1509), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + /* .vendor_name = "Yamaha", */ + /* .product_name = "Steinberg UR22", */ + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 3, + .type = QUIRK_MIDI_YAMAHA + }, + { + .ifnum = 4, + .type = QUIRK_IGNORE_INTERFACE + }, + { + .ifnum = -1 + } + } + } +}, +{ USB_DEVICE(0x0499, 0x150a), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { /* .vendor_name = "Yamaha", */ @@ -1581,6 +1611,35 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, { + /* BOSS ME-25 */ + USB_DEVICE(0x0582, 0x0113), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = & (const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, +{ /* only 44.1 kHz works at the moment */ USB_DEVICE(0x0582, 0x0120), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 89730707614c..c64a3d96db22 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -666,7 +666,7 @@ static int snd_usb_gamecon780_boot_quirk(struct usb_device *dev) /* set the initial volume and don't change; other values are either * too loud or silent due to firmware bug (bko#65251) */ - u8 buf[2] = { 0x74, 0xdc }; + u8 buf[2] = { 0x74, 0xe3 }; return snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR, USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT, UAC_FU_VOLUME << 8, 9 << 8, buf, 2); diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 1587ea392ad6..30e8e0c3f117 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4321,6 +4321,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event format, len_arg, arg); trace_seq_terminate(&p); trace_seq_puts(s, p.buffer); + trace_seq_destroy(&p); arg = arg->next; break; default: diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 32487ed18354..3d5979b23e50 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -4,6 +4,7 @@ TARGETS += efivarfs TARGETS += kcmp TARGETS += memory-hotplug TARGETS += mqueue +TARGETS += mount TARGETS += net TARGETS += ptrace TARGETS += timers diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile new file mode 100644 index 000000000000..337d853c2b72 --- /dev/null +++ b/tools/testing/selftests/mount/Makefile @@ -0,0 +1,17 @@ +# Makefile for mount selftests. + +all: unprivileged-remount-test + +unprivileged-remount-test: unprivileged-remount-test.c + gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test + +# Allow specific tests to be selected. +test_unprivileged_remount: unprivileged-remount-test + @if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi + +run_tests: all test_unprivileged_remount + +clean: + rm -f unprivileged-remount-test + +.PHONY: all test_unprivileged_remount diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c new file mode 100644 index 000000000000..1b3ff2fda4d0 --- /dev/null +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -0,0 +1,242 @@ +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <sys/wait.h> +#include <stdlib.h> +#include <unistd.h> +#include <fcntl.h> +#include <grp.h> +#include <stdbool.h> +#include <stdarg.h> + +#ifndef CLONE_NEWNS +# define CLONE_NEWNS 0x00020000 +#endif +#ifndef CLONE_NEWUTS +# define CLONE_NEWUTS 0x04000000 +#endif +#ifndef CLONE_NEWIPC +# define CLONE_NEWIPC 0x08000000 +#endif +#ifndef CLONE_NEWNET +# define CLONE_NEWNET 0x40000000 +#endif +#ifndef CLONE_NEWUSER +# define CLONE_NEWUSER 0x10000000 +#endif +#ifndef CLONE_NEWPID +# define CLONE_NEWPID 0x20000000 +#endif + +#ifndef MS_RELATIME +#define MS_RELATIME (1 << 21) +#endif +#ifndef MS_STRICTATIME +#define MS_STRICTATIME (1 << 24) +#endif + +static void die(char *fmt, ...) +{ + va_list ap; + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + +static void write_file(char *filename, char *fmt, ...) +{ + char buf[4096]; + int fd; + ssize_t written; + int buf_len; + va_list ap; + + va_start(ap, fmt); + buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + if (buf_len < 0) { + die("vsnprintf failed: %s\n", + strerror(errno)); + } + if (buf_len >= sizeof(buf)) { + die("vsnprintf output truncated\n"); + } + + fd = open(filename, O_WRONLY); + if (fd < 0) { + die("open of %s failed: %s\n", + filename, strerror(errno)); + } + written = write(fd, buf, buf_len); + if (written != buf_len) { + if (written >= 0) { + die("short write to %s\n", filename); + } else { + die("write to %s failed: %s\n", + filename, strerror(errno)); + } + } + if (close(fd) != 0) { + die("close of %s failed: %s\n", + filename, strerror(errno)); + } +} + +static void create_and_enter_userns(void) +{ + uid_t uid; + gid_t gid; + + uid = getuid(); + gid = getgid(); + + if (unshare(CLONE_NEWUSER) !=0) { + die("unshare(CLONE_NEWUSER) failed: %s\n", + strerror(errno)); + } + + write_file("/proc/self/uid_map", "0 %d 1", uid); + write_file("/proc/self/gid_map", "0 %d 1", gid); + + if (setgroups(0, NULL) != 0) { + die("setgroups failed: %s\n", + strerror(errno)); + } + if (setgid(0) != 0) { + die ("setgid(0) failed %s\n", + strerror(errno)); + } + if (setuid(0) != 0) { + die("setuid(0) failed %s\n", + strerror(errno)); + } +} + +static +bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) +{ + pid_t child; + + child = fork(); + if (child == -1) { + die("fork failed: %s\n", + strerror(errno)); + } + if (child != 0) { /* parent */ + pid_t pid; + int status; + pid = waitpid(child, &status, 0); + if (pid == -1) { + die("waitpid failed: %s\n", + strerror(errno)); + } + if (pid != child) { + die("waited for %d got %d\n", + child, pid); + } + if (!WIFEXITED(status)) { + die("child did not terminate cleanly\n"); + } + return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false; + } + + create_and_enter_userns(); + if (unshare(CLONE_NEWNS) != 0) { + die("unshare(CLONE_NEWNS) failed: %s\n", + strerror(errno)); + } + + if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) { + die("mount of /tmp failed: %s\n", + strerror(errno)); + } + + create_and_enter_userns(); + + if (unshare(CLONE_NEWNS) != 0) { + die("unshare(CLONE_NEWNS) failed: %s\n", + strerror(errno)); + } + + if (mount("/tmp", "/tmp", "none", + MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp failed: %s\n", + strerror(errno)); + } + + if (mount("/tmp", "/tmp", "none", + MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp with invalid flags " + "succeeded unexpectedly\n"); + } + exit(EXIT_SUCCESS); +} + +static bool test_unpriv_remount_simple(int mount_flags) +{ + return test_unpriv_remount(mount_flags, mount_flags, 0); +} + +static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags) +{ + return test_unpriv_remount(mount_flags, mount_flags, invalid_flags); +} + +int main(int argc, char **argv) +{ + if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) { + die("MS_RDONLY malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NODEV)) { + die("MS_NODEV malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) { + die("MS_NOSUID malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) { + die("MS_NOEXEC malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_STRICTATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV, + MS_STRICTATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV, + MS_STRICTATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("Default atime malfunctions\n"); + } + return EXIT_SUCCESS; +} diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c index fe1e66b6ef40..a87e99f37c52 100644 --- a/tools/usb/ffs-test.c +++ b/tools/usb/ffs-test.c @@ -116,8 +116,8 @@ static const struct { .header = { .magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC), .length = cpu_to_le32(sizeof descriptors), - .fs_count = 3, - .hs_count = 3, + .fs_count = cpu_to_le32(3), + .hs_count = cpu_to_le32(3), }, .fs_descs = { .intf = { diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index bdb71a26ae35..00ea679b3826 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -172,7 +172,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq, GFP_ATOMIC); if (likely(r == 0)) { ++started; - if (unlikely(!virtqueue_kick(vq->vq)) + if (unlikely(!virtqueue_kick(vq->vq))) r = -1; } } else diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 8ca405cd7c1a..26954a7d9b03 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -916,6 +916,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg) case 0: if (!target_cpus) return; + break; case 1: target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff; diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 8631d9c14320..f2c80d5451c3 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -85,7 +85,7 @@ static void async_pf_execute(struct work_struct *work) if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); - mmdrop(mm); + mmput(mm); kvm_put_kvm(vcpu->kvm); } @@ -98,7 +98,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) typeof(*work), queue); list_del(&work->queue); if (cancel_work_sync(&work->work)) { - mmdrop(work->mm); + mmput(work->mm); kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */ kmem_cache_free(async_pf_cache, work); } @@ -162,7 +162,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, work->addr = gfn_to_hva(vcpu->kvm, gfn); work->arch = *arch; work->mm = current->mm; - atomic_inc(&work->mm->mm_count); + atomic_inc(&work->mm->mm_users); kvm_get_kvm(work->vcpu->kvm); /* this can't really happen otherwise gfn_to_pfn_async @@ -180,7 +180,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, return 1; retry_sync: kvm_put_kvm(work->vcpu->kvm); - mmdrop(work->mm); + mmput(work->mm); kmem_cache_free(async_pf_cache, work); return 0; } diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index ce9ed99ad7dc..b47541dd798f 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -203,10 +203,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, spin_lock(&ioapic->lock); for (index = 0; index < IOAPIC_NUM_PINS; index++) { e = &ioapic->redirtbl[index]; - if (!e->fields.mask && - (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || - kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, - index) || index == RTC_GSI)) { + if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || + kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) || + index == RTC_GSI) { if (kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id, e->fields.dest_mode)) { __set_bit(e->fields.vector, @@ -306,7 +305,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status) BUG_ON(ioapic->rtc_status.pending_eoi != 0); ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, ioapic->rtc_status.dest_map); - ioapic->rtc_status.pending_eoi = ret; + ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret); } else ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL); diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 0df7d4b34dfe..1f0dc1e5f1f0 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -43,13 +43,13 @@ static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, - unsigned long size) + unsigned long npages) { gfn_t end_gfn; pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); - end_gfn = gfn + (size >> PAGE_SHIFT); + end_gfn = gfn + npages; gfn += 1; if (is_error_noslot_pfn(pfn)) @@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } +static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +{ + unsigned long i; + + for (i = 0; i < npages; ++i) + kvm_release_pfn_clean(pfn + i); +} + int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; @@ -111,7 +119,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) * Pin all pages we are about to map in memory. This is * important because we unmap and unpin in 4kb steps later. */ - pfn = kvm_pin_pages(slot, gfn, page_size); + pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT); if (is_error_noslot_pfn(pfn)) { gfn += 1; continue; @@ -123,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) if (r) { printk(KERN_ERR "kvm_iommu_map_address:" "iommu failed to map pfn=%llx\n", pfn); + kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT); goto unmap_pages; } @@ -134,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) return 0; unmap_pages: - kvm_iommu_put_pages(kvm, slot->base_gfn, gfn); + kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn); return r; } @@ -266,14 +275,6 @@ out_unlock: return r; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) -{ - unsigned long i; - - for (i = 0; i < npages; ++i) - kvm_release_pfn_clean(pfn + i); -} - static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 03a0381b1cb7..66112533b1e9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -52,6 +52,7 @@ #include <asm/processor.h> #include <asm/io.h> +#include <asm/ioctl.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -95,8 +96,6 @@ static int hardware_enable_all(void); static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *new, u64 last_generation); static void kvm_release_pfn_dirty(pfn_t pfn); static void mark_page_dirty_in_slot(struct kvm *kvm, @@ -682,8 +681,7 @@ static void sort_memslots(struct kvm_memslots *slots) } static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *new, - u64 last_generation) + struct kvm_memory_slot *new) { if (new) { int id = new->id; @@ -694,8 +692,6 @@ static void update_memslots(struct kvm_memslots *slots, if (new->npages != npages) sort_memslots(slots); } - - slots->generation = last_generation + 1; } static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) @@ -717,10 +713,24 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, { struct kvm_memslots *old_memslots = kvm->memslots; - update_memslots(slots, new, kvm->memslots->generation); + /* + * Set the low bit in the generation, which disables SPTE caching + * until the end of synchronize_srcu_expedited. + */ + WARN_ON(old_memslots->generation & 1); + slots->generation = old_memslots->generation + 1; + + update_memslots(slots, new); rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); + /* + * Increment the new memslot generation a second time. This prevents + * vm exits that race with memslot updates from caching a memslot + * generation that will (potentially) be valid forever. + */ + slots->generation++; + kvm_arch_memslots_updated(kvm); return old_memslots; @@ -1970,6 +1980,9 @@ static long kvm_vcpu_ioctl(struct file *filp, if (vcpu->kvm->mm != current->mm) return -EIO; + if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) + return -EINVAL; + #if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) /* * Special cases: vcpu ioctls that are asynchronous to vcpu execution, |