From: Rafael J. Wysocki Date: Mon, 25 Jul 2016 11:45:39 +0000 (+0200) Subject: Merge branch 'x86/cpu' from tip X-Git-Tag: v4.8-rc1~158^2~4 X-Git-Url: http://git.cascardo.info/?p=cascardo%2Flinux.git;a=commitdiff_plain;h=9fedbb3b6bb8d00c973f01dcf14af8eedf5eb495;hp=b77b5651082a4fa4091ac4e864254d9e71d15880 Merge branch 'x86/cpu' from tip --- diff --git a/.mailmap b/.mailmap index 08b80428f583..52489f564069 100644 --- a/.mailmap +++ b/.mailmap @@ -21,6 +21,7 @@ Andrey Ryabinin Andrew Morton Andrew Vasquez Andy Adamson +Antoine Tenart Antonio Ospite Archit Taneja Arnaud Patard @@ -30,6 +31,9 @@ Axel Lin Ben Gardner Ben M Cahill Björn Steinbrink +Boris Brezillon +Boris Brezillon +Boris Brezillon Brian Avery Brian King Christoph Hellwig @@ -89,6 +93,7 @@ Leonid I Ananiev Linas Vepstas Mark Brown Matthieu CASTET +Mauro Carvalho Chehab Mayuresh Janorkar Michael Buesch Michel Dänzer @@ -122,6 +127,7 @@ Santosh Shilimkar Sascha Hauer S.Çağlar Onur Shiraz Hashim +Shuah Khan Simon Kelley Stéphane Witzmann Stephen Hemminger diff --git a/CREDITS b/CREDITS index 0f0bf22afe0c..2a3fbcd229e6 100644 --- a/CREDITS +++ b/CREDITS @@ -649,6 +649,7 @@ D: Configure, Menuconfig, xconfig N: Mauro Carvalho Chehab E: m.chehab@samsung.org +E: mchehab@osg.samsung.com E: mchehab@infradead.org D: Media subsystem (V4L/DVB) drivers and core D: EDAC drivers and EDAC 3.0 core rework diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc index 2f4a0051b32d..1ba0d0fda9c0 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget-uvc +++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc @@ -1,6 +1,6 @@ What: /config/usb-gadget/gadget/functions/uvc.name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: UVC function directory streaming_maxburst - 0..15 (ss only) @@ -9,37 +9,37 @@ Description: UVC function directory What: /config/usb-gadget/gadget/functions/uvc.name/control Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Control descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/class Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/class/ss Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Super speed control class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/class/fs Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Full speed control class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/output Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Output terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/output/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default output terminal descriptors All attributes read only: @@ -53,12 +53,12 @@ Description: Default output terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Camera terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default camera terminal descriptors All attributes read only: @@ -75,12 +75,12 @@ Description: Default camera terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/processing Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Processing unit descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/processing/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default processing unit descriptors All attributes read only: @@ -94,49 +94,49 @@ Description: Default processing unit descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/header Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Control header descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/header/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific control header descriptors dwClockFrequency bcdUVC What: /config/usb-gadget/gadget/functions/uvc.name/streaming Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Streaming descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/ss Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Super speed streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/hs Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: High speed streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/fs Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Full speed streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Color matching descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default color matching descriptors All attributes read only: @@ -150,12 +150,12 @@ Description: Default color matching descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: MJPEG format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific MJPEG format descriptors All attributes read only, @@ -174,7 +174,7 @@ Description: Specific MJPEG format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific MJPEG frame descriptors dwFrameInterval - indicates how frame interval can be @@ -196,12 +196,12 @@ Description: Specific MJPEG frame descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Uncompressed format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific uncompressed format descriptors bmaControls - this format's data for bmaControls in @@ -221,7 +221,7 @@ Description: Specific uncompressed format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific uncompressed frame descriptors dwFrameInterval - indicates how frame interval can be @@ -243,12 +243,12 @@ Description: Specific uncompressed frame descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Streaming header descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific streaming header descriptors All attributes read only: diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 index 6708c5e264aa..33e96f740639 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 +++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 @@ -1,4 +1,4 @@ -What /sys/bus/iio/devices/iio:deviceX/in_proximity_raw +What /sys/bus/iio/devices/iio:deviceX/in_proximity_input Date: March 2014 KernelVersion: 3.15 Contact: Matt Ranostay diff --git a/Documentation/gdb-kernel-debugging.txt b/Documentation/gdb-kernel-debugging.txt index 4ab7d43d0754..7050ce8794b9 100644 --- a/Documentation/gdb-kernel-debugging.txt +++ b/Documentation/gdb-kernel-debugging.txt @@ -139,27 +139,6 @@ Examples of using the Linux-provided gdb helpers start_comm = "swapper/2\000\000\000\000\000\000" } - o Dig into a radix tree data structure, such as the IRQ descriptors: - (gdb) print (struct irq_desc)$lx_radix_tree_lookup(irq_desc_tree, 18) - $6 = { - irq_common_data = { - state_use_accessors = 67584, - handler_data = 0x0 <__vectors_start>, - msi_desc = 0x0 <__vectors_start>, - affinity = {{ - bits = {65535} - }} - }, - irq_data = { - mask = 0, - irq = 18, - hwirq = 27, - common = 0xee803d80, - chip = 0xc0eb0854 , - domain = 0xee808000, - parent_data = 0x0 <__vectors_start>, - chip_data = 0xc0eb0854 - } <... trimmed ...> List of commands and functions ------------------------------ diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 82b42c958d1c..07960c24642d 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3594,6 +3594,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. present during boot. nocompress Don't compress/decompress hibernation images. no Disable hibernation and resume. + protect_image Turn on image protection during restoration + (that will set all pages holding image data + during restoration read-only). retain_initrd [RAM] Keep initrd memory after extraction diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt index d406d98339b2..44f5e6bccd97 100644 --- a/Documentation/leds/leds-class.txt +++ b/Documentation/leds/leds-class.txt @@ -74,8 +74,8 @@ blink_set() function (see ). To set an LED to blinking, however, it is better to use the API function led_blink_set(), as it will check and implement software fallback if necessary. -To turn off blinking again, use the API function led_brightness_set() -as that will not just set the LED brightness but also stop any software +To turn off blinking, use the API function led_brightness_set() +with brightness value LED_OFF, which should stop any software timers that may have been required for blinking. The blink_set() function should choose a user friendly blinking value diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt index 8638f61c8c9d..37eca00796ee 100644 --- a/Documentation/scsi/scsi_eh.txt +++ b/Documentation/scsi/scsi_eh.txt @@ -263,19 +263,23 @@ scmd->allowed. 3. scmd recovered ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd - - shost->host_failed-- - clear scmd->eh_eflags - scsi_setup_cmd_retry() - move from local eh_work_q to local eh_done_q LOCKING: none + CONCURRENCY: at most one thread per separate eh_work_q to + keep queue manipulation lockless 4. EH completes ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper - layer of failure. + layer of failure. May be called concurrently but must have + a no more than one thread per separate eh_work_q to + manipulate the queue locklessly - scmd is removed from eh_done_q and scmd->eh_entry is cleared - if retry is necessary, scmd is requeued using scsi_queue_insert() - otherwise, scsi_finish_command() is invoked for scmd + - zero shost->host_failed LOCKING: queue or finish function performs appropriate locking diff --git a/Documentation/x86/intel_mpx.txt b/Documentation/x86/intel_mpx.txt index 1a5a12184a35..85d0549ad846 100644 --- a/Documentation/x86/intel_mpx.txt +++ b/Documentation/x86/intel_mpx.txt @@ -45,7 +45,7 @@ is how we expect the compiler, application and kernel to work together. MPX-instrumented. 3) The kernel detects that the CPU has MPX, allows the new prctl() to succeed, and notes the location of the bounds directory. Userspace is - expected to keep the bounds directory at that locationWe note it + expected to keep the bounds directory at that location. We note it instead of reading it each time because the 'xsave' operation needed to access the bounds directory register is an expensive operation. 4) If the application needs to spill bounds out of the 4 registers, it @@ -167,7 +167,7 @@ If a #BR is generated due to a bounds violation caused by MPX. We need to decode MPX instructions to get violation address and set this address into extended struct siginfo. -The _sigfault feild of struct siginfo is extended as follow: +The _sigfault field of struct siginfo is extended as follow: 87 /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ 88 struct { @@ -240,5 +240,5 @@ them at the same bounds table. This is allowed architecturally. See more information "Intel(R) Architecture Instruction Set Extensions Programming Reference" (9.3.4). -However, if users did this, the kernel might be fooled in to unmaping an +However, if users did this, the kernel might be fooled in to unmapping an in-use bounds table since it does not recognize sharing. diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.txt index 39d172326703..6a0607b99ed8 100644 --- a/Documentation/x86/tlb.txt +++ b/Documentation/x86/tlb.txt @@ -5,7 +5,7 @@ memory, it has two choices: from areas other than the one we are trying to flush will be destroyed and must be refilled later, at some cost. 2. Use the invlpg instruction to invalidate a single page at a - time. This could potentialy cost many more instructions, but + time. This could potentially cost many more instructions, but it is a much more precise operation, causing no collateral damage to other TLB entries. @@ -19,7 +19,7 @@ Which method to do depends on a few things: work. 3. The size of the TLB. The larger the TLB, the more collateral damage we do with a full flush. So, the larger the TLB, the - more attrative an individual flush looks. Data and + more attractive an individual flush looks. Data and instructions have separate TLBs, as do different page sizes. 4. The microarchitecture. The TLB has become a multi-level cache on modern CPUs, and the global flushes have become more diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck index b1fb30273286..d0648a74fceb 100644 --- a/Documentation/x86/x86_64/machinecheck +++ b/Documentation/x86/x86_64/machinecheck @@ -36,7 +36,7 @@ between all CPUs. check_interval How often to poll for corrected machine check errors, in seconds - (Note output is hexademical). Default 5 minutes. When the poller + (Note output is hexadecimal). Default 5 minutes. When the poller finds MCEs it triggers an exponential speedup (poll more often) on the polling interval. When the poller stops finding MCEs, it triggers an exponential backoff (poll less often) on the polling diff --git a/MAINTAINERS b/MAINTAINERS index 16700e4fcc4a..8c20323d1277 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -595,6 +595,10 @@ S: Odd Fixes L: linux-alpha@vger.kernel.org F: arch/alpha/ +ALPS PS/2 TOUCHPAD DRIVER +R: Pali Rohár +F: drivers/input/mouse/alps.* + ALTERA MAILBOX DRIVER M: Ley Foon Tan L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) @@ -1159,6 +1163,7 @@ F: arch/arm/mach-footbridge/ ARM/FREESCALE IMX / MXC ARM ARCHITECTURE M: Shawn Guo M: Sascha Hauer +R: Fabio Estevam L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git @@ -1689,8 +1694,6 @@ S: Maintained F: drivers/edac/altera_edac. ARM/STI ARCHITECTURE -M: Srinivas Kandagatla -M: Maxime Coquelin M: Patrice Chotard L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kernel@stlinux.com @@ -1723,6 +1726,7 @@ F: drivers/ata/ahci_st.c ARM/STM32 ARCHITECTURE M: Maxime Coquelin +M: Alexandre Torgue L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcoquelin/stm32.git @@ -2242,7 +2246,8 @@ F: include/net/ax25.h F: net/ax25/ AZ6007 DVB DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -2709,7 +2714,8 @@ F: Documentation/filesystems/btrfs.txt F: fs/btrfs/ BTTV VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -2773,9 +2779,9 @@ F: include/net/caif/ F: net/caif/ CALGARY x86-64 IOMMU -M: Muli Ben-Yehuda -M: "Jon D. Mason" -L: discuss@x86-64.org +M: Muli Ben-Yehuda +M: Jon Mason +L: iommu@lists.linux-foundation.org S: Maintained F: arch/x86/kernel/pci-calgary_64.c F: arch/x86/kernel/tce_64.c @@ -3344,7 +3350,8 @@ S: Maintained F: drivers/media/dvb-frontends/cx24120* CX88 VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -3774,6 +3781,7 @@ Q: https://patchwork.kernel.org/project/linux-dmaengine/list/ S: Maintained F: drivers/dma/ F: include/linux/dmaengine.h +F: Documentation/devicetree/bindings/dma/ F: Documentation/dmaengine/ T: git git://git.infradead.org/users/vkoul/slave-dma.git @@ -4291,7 +4299,8 @@ F: fs/ecryptfs/ EDAC-CORE M: Doug Thompson M: Borislav Petkov -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac.git linux_next @@ -4336,7 +4345,8 @@ S: Maintained F: drivers/edac/e7xxx_edac.c EDAC-GHES -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/ghes_edac.c @@ -4360,19 +4370,22 @@ S: Maintained F: drivers/edac/i5000_edac.c EDAC-I5400 -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/i5400_edac.c EDAC-I7300 -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/i7300_edac.c EDAC-I7CORE -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/i7core_edac.c @@ -4409,7 +4422,8 @@ S: Maintained F: drivers/edac/r82600_edac.c EDAC-SBRIDGE -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/sb_edac.c @@ -4462,13 +4476,14 @@ S: Orphan F: fs/efs/ EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -M: Thadeu Lima de Souza Cascardo +M: Douglas Miller L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/ibm/ehea/ EM28XX VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -6487,6 +6502,7 @@ F: include/uapi/linux/sunrpc/ KERNEL SELFTEST FRAMEWORK M: Shuah Khan +M: Shuah Khan L: linux-kselftest@vger.kernel.org T: git git://git.kernel.org/pub/scm/shuah/linux-kselftest S: Maintained @@ -7358,7 +7374,8 @@ S: Supported F: drivers/media/pci/netup_unidvb/* MEDIA INPUT INFRASTRUCTURE (V4L/DVB) -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab P: LinuxTV.org Project L: linux-media@vger.kernel.org W: https://linuxtv.org @@ -7406,7 +7423,7 @@ F: drivers/scsi/megaraid.* F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) -M: Eugenia Emantayev +M: Tariq Toukan L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -7458,6 +7475,7 @@ Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ T: git git://git.infradead.org/linux-mtd.git T: git git://git.infradead.org/l2-mtd.git S: Maintained +F: Documentation/devicetree/bindings/mtd/ F: drivers/mtd/ F: include/linux/mtd/ F: include/uapi/mtd/ @@ -8945,6 +8963,7 @@ L: linux-gpio@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git S: Maintained F: Documentation/devicetree/bindings/pinctrl/ +F: Documentation/pinctrl.txt F: drivers/pinctrl/ F: include/linux/pinctrl/ @@ -9852,7 +9871,8 @@ S: Odd Fixes F: drivers/media/i2c/saa6588* SAA7134 VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -10371,7 +10391,8 @@ S: Maintained F: drivers/media/radio/si4713/radio-usb-si4713.c SIANO DVB DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11137,7 +11158,8 @@ S: Maintained F: drivers/media/i2c/tda9840* TEA5761 TUNER DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11145,7 +11167,8 @@ S: Odd fixes F: drivers/media/tuners/tea5761.* TEA5767 TUNER DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11532,7 +11555,8 @@ F: include/linux/shmem_fs.h F: mm/shmem.c TM6000 VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11886,7 +11910,8 @@ F: drivers/usb/common/usb-otg-fsm.c USB OVER IP DRIVER M: Valentina Manea -M: Shuah Khan +M: Shuah Khan +M: Shuah Khan L: linux-usb@vger.kernel.org S: Maintained F: Documentation/usb/usbip_protocol.txt @@ -11957,6 +11982,7 @@ L: linux-usb@vger.kernel.org W: http://www.linux-usb.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git S: Supported +F: Documentation/devicetree/bindings/usb/ F: Documentation/usb/ F: drivers/usb/ F: include/linux/usb.h @@ -12130,6 +12156,7 @@ VIRTIO CORE, NET AND BLOCK DRIVERS M: "Michael S. Tsirkin" L: virtualization@lists.linux-foundation.org S: Maintained +F: Documentation/devicetree/bindings/virtio/ F: drivers/virtio/ F: tools/virtio/ F: drivers/net/virtio_net.c @@ -12518,7 +12545,8 @@ S: Maintained F: arch/x86/entry/vdso/ XC2028/3028 TUNER DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git diff --git a/Makefile b/Makefile index b409076c7c18..66da9a38b13b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = NAME = Psychotic Stoned Sheep # *DOCUMENTATION* @@ -363,11 +363,13 @@ CHECK = sparse CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ -Wbitwise -Wno-return-void $(CF) +NOSTDINC_FLAGS = CFLAGS_MODULE = AFLAGS_MODULE = LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = +LDFLAGS_vmlinux = CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized CFLAGS_KCOV = -fsanitize-coverage=trace-pc diff --git a/arch/Kconfig b/arch/Kconfig index d794384a0404..15996290fed4 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -226,8 +226,8 @@ config ARCH_INIT_TASK config ARCH_TASK_STRUCT_ALLOCATOR bool -# Select if arch has its private alloc_thread_info() function -config ARCH_THREAD_INFO_ALLOCATOR +# Select if arch has its private alloc_thread_stack() function +config ARCH_THREAD_STACK_ALLOCATOR bool # Select if arch wants to size task_struct dynamically via arch_task_struct_size: @@ -606,6 +606,9 @@ config HAVE_ARCH_HASH file which provides platform-specific implementations of some functions in or fs/namei.c. +config ISA_BUS_API + def_bool ISA + # # ABI hall of shame # diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h index aab14a019c20..c2ebb6f36c9d 100644 --- a/arch/alpha/include/asm/pgalloc.h +++ b/arch/alpha/include/asm/pgalloc.h @@ -40,7 +40,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pmd_t * pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return ret; } @@ -53,7 +53,7 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return pte; } diff --git a/arch/arc/Makefile b/arch/arc/Makefile index d4df6be66d58..85814e74677d 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -66,8 +66,6 @@ endif endif -cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables - # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok ifeq ($(atleast_gcc48),y) cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 86ed671286df..3749234b7419 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -95,7 +95,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, + pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, __get_order_pte()); return pte; @@ -107,7 +107,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address) pgtable_t pte_pg; struct page *page; - pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte()); + pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL, __get_order_pte()); if (!pte_pg) return 0; memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t)); diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index e0efff15a5ae..b9192a653b7e 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, * prelogue is setup (callee regs saved and then fp set and not other * way around */ - pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); + pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); return 0; #endif diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 06b6c2d695bf..414b42710a36 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -741,6 +741,7 @@ dtb-$(CONFIG_MACH_SUN7I) += \ sun7i-a20-olimex-som-evb.dtb \ sun7i-a20-olinuxino-lime.dtb \ sun7i-a20-olinuxino-lime2.dtb \ + sun7i-a20-olinuxino-lime2-emmc.dtb \ sun7i-a20-olinuxino-micro.dtb \ sun7i-a20-orangepi.dtb \ sun7i-a20-orangepi-mini.dtb \ diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index d82dd6e3f9b1..5687d6b4da60 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -418,7 +418,7 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins>; - clock-frequency = <400000>; + clock-frequency = <100000>; tps@24 { compatible = "ti,tps65218"; diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi index b01a5948cdd0..0e63b9dff6e7 100644 --- a/arch/arm/boot/dts/am57xx-idk-common.dtsi +++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi @@ -60,10 +60,26 @@ tps659038_pmic { compatible = "ti,tps659038-pmic"; + + smps12-in-supply = <&vmain>; + smps3-in-supply = <&vmain>; + smps45-in-supply = <&vmain>; + smps6-in-supply = <&vmain>; + smps7-in-supply = <&vmain>; + smps8-in-supply = <&vmain>; + smps9-in-supply = <&vmain>; + ldo1-in-supply = <&vmain>; + ldo2-in-supply = <&vmain>; + ldo3-in-supply = <&vmain>; + ldo4-in-supply = <&vmain>; + ldo9-in-supply = <&vmain>; + ldoln-in-supply = <&vmain>; + ldousb-in-supply = <&vmain>; + ldortc-in-supply = <&vmain>; + regulators { smps12_reg: smps12 { /* VDD_MPU */ - vin-supply = <&vmain>; regulator-name = "smps12"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1250000>; @@ -73,7 +89,6 @@ smps3_reg: smps3 { /* VDD_DDR EMIF1 EMIF2 */ - vin-supply = <&vmain>; regulator-name = "smps3"; regulator-min-microvolt = <1350000>; regulator-max-microvolt = <1350000>; @@ -84,7 +99,6 @@ smps45_reg: smps45 { /* VDD_DSPEVE on AM572 */ /* VDD_IVA + VDD_DSP on AM571 */ - vin-supply = <&vmain>; regulator-name = "smps45"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1250000>; @@ -94,7 +108,6 @@ smps6_reg: smps6 { /* VDD_GPU */ - vin-supply = <&vmain>; regulator-name = "smps6"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1250000>; @@ -104,7 +117,6 @@ smps7_reg: smps7 { /* VDD_CORE */ - vin-supply = <&vmain>; regulator-name = "smps7"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1150000>; @@ -115,13 +127,11 @@ smps8_reg: smps8 { /* 5728 - VDD_IVAHD */ /* 5718 - N.C. test point */ - vin-supply = <&vmain>; regulator-name = "smps8"; }; smps9_reg: smps9 { /* VDD_3_3D */ - vin-supply = <&vmain>; regulator-name = "smps9"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; @@ -132,7 +142,6 @@ ldo1_reg: ldo1 { /* VDDSHV8 - VSDMMC */ /* NOTE: on rev 1.3a, data supply */ - vin-supply = <&vmain>; regulator-name = "ldo1"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -142,7 +151,6 @@ ldo2_reg: ldo2 { /* VDDSH18V */ - vin-supply = <&vmain>; regulator-name = "ldo2"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -152,7 +160,6 @@ ldo3_reg: ldo3 { /* R1.3a 572x V1_8PHY_LDO3: USB, SATA */ - vin-supply = <&vmain>; regulator-name = "ldo3"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -162,7 +169,6 @@ ldo4_reg: ldo4 { /* R1.3a 572x V1_8PHY_LDO4: PCIE, HDMI*/ - vin-supply = <&vmain>; regulator-name = "ldo4"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -174,7 +180,6 @@ ldo9_reg: ldo9 { /* VDD_RTC */ - vin-supply = <&vmain>; regulator-name = "ldo9"; regulator-min-microvolt = <840000>; regulator-max-microvolt = <1160000>; @@ -184,7 +189,6 @@ ldoln_reg: ldoln { /* VDDA_1V8_PLL */ - vin-supply = <&vmain>; regulator-name = "ldoln"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -194,7 +198,6 @@ ldousb_reg: ldousb { /* VDDA_3V_USB: VDDA_USBHS33 */ - vin-supply = <&vmain>; regulator-name = "ldousb"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; @@ -204,7 +207,6 @@ ldortc_reg: ldortc { /* VDDA_RTC */ - vin-supply = <&vmain>; regulator-name = "ldortc"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 8450944b28e6..22f7a13e20b4 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -58,8 +58,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>; internal-regs { diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts index cbc17b0794b1..4128fa91823c 100644 --- a/arch/arm/boot/dts/dm8148-evm.dts +++ b/arch/arm/boot/dts/dm8148-evm.dts @@ -93,6 +93,10 @@ }; }; +&mmc1 { + status = "disabled"; +}; + &mmc2 { pinctrl-names = "default"; pinctrl-0 = <&sd1_pins>; @@ -101,6 +105,10 @@ cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>; }; +&mmc3 { + status = "disabled"; +}; + &pincntl { sd1_pins: pinmux_sd1_pins { pinctrl-single,pins = < diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts index 5d4313fd5a46..3f184863e0c5 100644 --- a/arch/arm/boot/dts/dm8148-t410.dts +++ b/arch/arm/boot/dts/dm8148-t410.dts @@ -45,6 +45,14 @@ phy-mode = "rgmii"; }; +&mmc1 { + status = "disabled"; +}; + +&mmc2 { + status = "disabled"; +}; + &mmc3 { pinctrl-names = "default"; pinctrl-0 = <&sd2_pins>; @@ -53,6 +61,7 @@ dmas = <&edma_xbar 8 0 1 /* use SDTXEVT1 instead of MCASP0TX */ &edma_xbar 9 0 2>; /* use SDRXEVT1 instead of MCASP0RX */ dma-names = "tx", "rx"; + non-removable; }; &pincntl { diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index e0074014385a..3a8f3976f6f9 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1451,6 +1451,8 @@ ti,hwmods = "gpmc"; reg = <0x50000000 0x37c>; /* device IO registers */ interrupts = ; + dmas = <&edma_xbar 4 0>; + dma-names = "rxtx"; gpmc,num-cs = <8>; gpmc,num-waitpins = <2>; #address-cells = <2>; diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi index 4220eeffc65a..5e06020f450b 100644 --- a/arch/arm/boot/dts/dra74x.dtsi +++ b/arch/arm/boot/dts/dra74x.dtsi @@ -107,8 +107,8 @@ reg = <0x58000000 0x80>, <0x58004054 0x4>, <0x58004300 0x20>, - <0x58005054 0x4>, - <0x58005300 0x20>; + <0x58009054 0x4>, + <0x58009300 0x20>; reg-names = "dss", "pll1_clkctrl", "pll1", "pll2_clkctrl", "pll2"; diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi index ddfe1f558c10..fa14f77df563 100644 --- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi +++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi @@ -242,7 +242,7 @@ hpd-gpios = <&gpx0 7 GPIO_ACTIVE_HIGH>; ports { - port0 { + port { dp_out: endpoint { remote-endpoint = <&bridge_in>; }; @@ -485,13 +485,20 @@ edid-emulation = <5>; ports { - port0 { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + bridge_out: endpoint { remote-endpoint = <&panel_in>; }; }; - port1 { + port@1 { + reg = <1>; + bridge_in: endpoint { remote-endpoint = <&dp_out>; }; diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts index f9d2e4f1a0e0..1de972d46a87 100644 --- a/arch/arm/boot/dts/exynos5420-peach-pit.dts +++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts @@ -163,7 +163,7 @@ hpd-gpios = <&gpx2 6 GPIO_ACTIVE_HIGH>; ports { - port0 { + port { dp_out: endpoint { remote-endpoint = <&bridge_in>; }; @@ -631,13 +631,20 @@ use-external-pwm; ports { - port0 { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + bridge_out: endpoint { remote-endpoint = <&panel_in>; }; }; - port1 { + port@1 { + reg = <1>; + bridge_in: endpoint { remote-endpoint = <&dp_out>; }; diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts index 76056ba92ced..ed449827c3d3 100644 --- a/arch/arm/boot/dts/omap3-evm-37xx.dts +++ b/arch/arm/boot/dts/omap3-evm-37xx.dts @@ -85,7 +85,7 @@ OMAP3_CORE1_IOPAD(0x2158, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_clk.sdmmc2_clk */ OMAP3_CORE1_IOPAD(0x215a, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_cmd.sdmmc2_cmd */ OMAP3_CORE1_IOPAD(0x215c, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat0.sdmmc2_dat0 */ - OMAP3_CORE1_IOPAD(0x215e, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */ + OMAP3_CORE1_IOPAD(0x215e, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */ OMAP3_CORE1_IOPAD(0x2160, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat2.sdmmc2_dat2 */ OMAP3_CORE1_IOPAD(0x2162, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat3.sdmmc2_dat3 */ >; diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi index 41f5d386f21f..f4f2ce46d681 100644 --- a/arch/arm/boot/dts/omap3-igep.dtsi +++ b/arch/arm/boot/dts/omap3-igep.dtsi @@ -188,6 +188,7 @@ vmmc-supply = <&vmmc1>; vmmc_aux-supply = <&vsim>; bus-width = <4>; + cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>; }; &mmc3 { diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi index d6f839cab649..b6971060648a 100644 --- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi +++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi @@ -194,6 +194,12 @@ OMAP3630_CORE2_IOPAD(0x25f8, PIN_OUTPUT | MUX_MODE4) /* etk_d14.gpio_28 */ >; }; + + mmc1_wp_pins: pinmux_mmc1_cd_pins { + pinctrl-single,pins = < + OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT | MUX_MODE4) /* etk_d15.gpio_29 */ + >; + }; }; &i2c3 { @@ -250,3 +256,8 @@ }; }; }; + +&mmc1 { + pinctrl-0 = <&mmc1_pins &mmc1_wp_pins>; + wp-gpios = <&gpio1 29 GPIO_ACTIVE_LOW>; /* gpio_29 */ +}; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index d9e2d9c6e999..2b74a81d1de2 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -288,7 +288,7 @@ pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1) /* ssi1_rdy_tx */ OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1) /* ssi1_flag_tx */ - OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */ + OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */ OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1) /* ssi1_dat_tx */ OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1) /* ssi1_dat_rx */ OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1) /* ssi1_flag_rx */ @@ -300,7 +300,7 @@ modem_pins: pinmux_modem { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE4) /* gpio 70 => cmt_apeslpx */ - OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio 72 => ape_rst_rq */ + OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | MUX_MODE4) /* gpio 72 => ape_rst_rq */ OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE4) /* gpio 73 => cmt_rst_rq */ OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE4) /* gpio 74 => cmt_en */ OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE4) /* gpio 75 => cmt_rst */ diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index a00ca761675d..927b17fc4ed8 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -97,7 +97,7 @@ OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1) /* ssi1_dat_tx */ OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1) /* ssi1_flag_tx */ OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1) /* ssi1_rdy_tx */ - OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */ + OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */ OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1) /* ssi1_dat_rx */ OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1) /* ssi1_flag_rx */ OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE1) /* ssi1_rdy_rx */ @@ -110,7 +110,7 @@ OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE7) /* ssi1_dat_tx */ OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE7) /* ssi1_flag_tx */ OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLDOWN | MUX_MODE7) /* ssi1_rdy_tx */ - OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */ + OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */ OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE7) /* ssi1_dat_rx */ OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE7) /* ssi1_flag_rx */ OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE4) /* ssi1_rdy_rx */ @@ -120,7 +120,7 @@ modem_pins1: pinmux_modem_core1_pins { pinctrl-single,pins = < - OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio_34 (ape_rst_rq) */ + OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | MUX_MODE4) /* gpio_34 (ape_rst_rq) */ OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE4) /* gpio_88 (cmt_rst_rq) */ OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE4) /* gpio_93 (cmt_apeslpx) */ >; diff --git a/arch/arm/boot/dts/omap3-zoom3.dts b/arch/arm/boot/dts/omap3-zoom3.dts index f19170bdcc1f..c29b41dc7b95 100644 --- a/arch/arm/boot/dts/omap3-zoom3.dts +++ b/arch/arm/boot/dts/omap3-zoom3.dts @@ -98,7 +98,7 @@ pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2174, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */ OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */ - OMAP3_CORE1_IOPAD(0x217a, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */ + OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */ OMAP3_CORE1_IOPAD(0x2178, PIN_OUTPUT | MUX_MODE0) /* uart2_tx.uart2_tx */ >; }; @@ -107,7 +107,7 @@ pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x219a, PIN_INPUT_PULLDOWN | MUX_MODE0) /* uart3_cts_rctx.uart3_cts_rctx */ OMAP3_CORE1_IOPAD(0x219c, PIN_OUTPUT | MUX_MODE0) /* uart3_rts_sd.uart3_rts_sd */ - OMAP3_CORE1_IOPAD(0x219e, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */ + OMAP3_CORE1_IOPAD(0x219e, PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */ OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx.uart3_tx_irtx */ >; }; @@ -125,7 +125,7 @@ pinctrl-single,pins = < OMAP3630_CORE2_IOPAD(0x25d8, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_clk.sdmmc3_clk */ OMAP3630_CORE2_IOPAD(0x25e4, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d4.sdmmc3_dat0 */ - OMAP3630_CORE2_IOPAD(0x25e6, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */ + OMAP3630_CORE2_IOPAD(0x25e6, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */ OMAP3630_CORE2_IOPAD(0x25e8, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d6.sdmmc3_dat2 */ OMAP3630_CORE2_IOPAD(0x25e2, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d3.sdmmc3_dat3 */ >; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index dc759a3028b7..5d5b620b7d9b 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -14,6 +14,29 @@ display0 = &hdmi0; }; + vmain: fixedregulator-vmain { + compatible = "regulator-fixed"; + regulator-name = "vmain"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vsys_cobra: fixedregulator-vsys_cobra { + compatible = "regulator-fixed"; + regulator-name = "vsys_cobra"; + vin-supply = <&vmain>; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vdds_1v8_main: fixedregulator-vdds_1v8_main { + compatible = "regulator-fixed"; + regulator-name = "vdds_1v8_main"; + vin-supply = <&smps7_reg>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + vmmcsd_fixed: fixedregulator-mmcsd { compatible = "regulator-fixed"; regulator-name = "vmmcsd_fixed"; @@ -309,7 +332,7 @@ wlcore_irq_pin: pinmux_wlcore_irq_pin { pinctrl-single,pins = < - OMAP5_IOPAD(0x40, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE6) /* llia_wakereqin.gpio1_wk14 */ + OMAP5_IOPAD(0x40, PIN_INPUT_PULLUP | MUX_MODE6) /* llia_wakereqin.gpio1_wk14 */ >; }; }; @@ -409,6 +432,26 @@ ti,ldo6-vibrator; + smps123-in-supply = <&vsys_cobra>; + smps45-in-supply = <&vsys_cobra>; + smps6-in-supply = <&vsys_cobra>; + smps7-in-supply = <&vsys_cobra>; + smps8-in-supply = <&vsys_cobra>; + smps9-in-supply = <&vsys_cobra>; + smps10_out2-in-supply = <&vsys_cobra>; + smps10_out1-in-supply = <&vsys_cobra>; + ldo1-in-supply = <&vsys_cobra>; + ldo2-in-supply = <&vsys_cobra>; + ldo3-in-supply = <&vdds_1v8_main>; + ldo4-in-supply = <&vdds_1v8_main>; + ldo5-in-supply = <&vsys_cobra>; + ldo6-in-supply = <&vdds_1v8_main>; + ldo7-in-supply = <&vsys_cobra>; + ldo8-in-supply = <&vsys_cobra>; + ldo9-in-supply = <&vmmcsd_fixed>; + ldoln-in-supply = <&vsys_cobra>; + ldousb-in-supply = <&vsys_cobra>; + regulators { smps123_reg: smps123 { /* VDD_OPP_MPU */ @@ -600,7 +643,8 @@ pinctrl-0 = <&twl6040_pins>; interrupts = ; /* IRQ_SYS_2N cascaded to gic */ - ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>; /* gpio line 141 */ + + /* audpwron gpio defined in the board specific dts */ vio-supply = <&smps7_reg>; v2v1-supply = <&smps9_reg>; diff --git a/arch/arm/boot/dts/omap5-igep0050.dts b/arch/arm/boot/dts/omap5-igep0050.dts index 46ecb1dd3b5c..f75ce02fb398 100644 --- a/arch/arm/boot/dts/omap5-igep0050.dts +++ b/arch/arm/boot/dts/omap5-igep0050.dts @@ -35,6 +35,22 @@ }; }; +/* LDO4 is VPP1 - ball AD9 */ +&ldo4_reg { + regulator-min-microvolt = <2000000>; + regulator-max-microvolt = <2000000>; +}; + +/* + * LDO7 is used for HDMI: VDDA_DSIPORTA - ball AA33, VDDA_DSIPORTC - ball AE33, + * VDDA_HDMI - ball AN25 + */ +&ldo7_reg { + status = "okay"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; +}; + &omap5_pmx_core { i2c4_pins: pinmux_i2c4_pins { pinctrl-single,pins = < @@ -52,3 +68,13 @@ <&gpio7 3 0>; /* 195, SDA */ }; +&twl6040 { + ti,audpwron-gpio = <&gpio5 16 GPIO_ACTIVE_HIGH>; /* gpio line 144 */ +}; + +&twl6040_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x1c4, PIN_OUTPUT | MUX_MODE6) /* mcspi1_somi.gpio5_144 */ + OMAP5_IOPAD(0x1ca, PIN_OUTPUT | MUX_MODE6) /* perslimbus2_clock.gpio5_145 */ + >; +}; diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts index 60b3fbb3bf07..a51e60518eb6 100644 --- a/arch/arm/boot/dts/omap5-uevm.dts +++ b/arch/arm/boot/dts/omap5-uevm.dts @@ -51,3 +51,13 @@ <&gpio9 1 GPIO_ACTIVE_HIGH>, /* TCA6424A P00, LS OE */ <&gpio7 1 GPIO_ACTIVE_HIGH>; /* GPIO 193, HPD */ }; + +&twl6040 { + ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>; /* gpio line 141 */ +}; + +&twl6040_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x1be, PIN_OUTPUT | MUX_MODE6) /* mcspi1_somi.gpio5_141 */ + >; +}; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts index a3601e4c0a2e..b844473601d2 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts @@ -136,6 +136,7 @@ &gmac1 { status = "okay"; phy-mode = "rgmii"; + phy-handle = <&phy1>; snps,reset-gpio = <&porta 0 GPIO_ACTIVE_LOW>; snps,reset-active-low; diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index ad8ba10764a3..d294e82447a2 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -24,18 +24,21 @@ compatible = "shared-dma-pool"; reg = <0x40000000 0x01000000>; no-map; + status = "disabled"; }; gp1_reserved: rproc@41000000 { compatible = "shared-dma-pool"; reg = <0x41000000 0x01000000>; no-map; + status = "disabled"; }; audio_reserved: rproc@42000000 { compatible = "shared-dma-pool"; reg = <0x42000000 0x01000000>; no-map; + status = "disabled"; }; dmu_reserved: rproc@43000000 { diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index a03e56fb5dbc..ca58eb279d55 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -65,8 +65,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&dram_gates 26>; status = "disabled"; }; @@ -74,8 +75,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&ahb_gates 46>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&ahb_gates 46>, <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; @@ -84,9 +86,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>, - <&ahb_gates 46>, <&dram_gates 25>, - <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>, <&ahb_gates 46>, + <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; @@ -94,8 +96,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0-tve0"; - clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, - <&ahb_gates 44>, <&ahb_gates 46>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, + <&ahb_gates 36>, <&ahb_gates 44>, + <&ahb_gates 46>, <&dram_gates 5>, <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index bddd0de88af6..367f33012493 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -65,8 +65,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>; status = "disabled"; }; @@ -74,7 +74,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>; status = "disabled"; }; @@ -82,8 +83,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-tve0"; - clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, - <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, + <&ahb_gates 36>, <&ahb_gates 44>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts index a8d8b4582397..f694482bdeb6 100644 --- a/arch/arm/boot/dts/sun5i-r8-chip.dts +++ b/arch/arm/boot/dts/sun5i-r8-chip.dts @@ -52,7 +52,7 @@ / { model = "NextThing C.H.I.P."; - compatible = "nextthing,chip", "allwinner,sun5i-r8"; + compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13"; aliases { i2c0 = &i2c0; diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts index 68b479b8772c..73c133f5e79c 100644 --- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts +++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts @@ -176,8 +176,6 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; regulator-name = "vcc-lcd"; }; diff --git a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts index 360adfb1e9ca..d6ad6196a768 100644 --- a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts +++ b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts @@ -135,8 +135,6 @@ ®_dc1sw { regulator-name = "vcc-lcd-usb2"; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; }; ®_dc5ldo { diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index febdf4c72fb0..2c34bbbb9570 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -67,8 +67,9 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&dram_gates 26>; status = "disabled"; }; @@ -76,8 +77,8 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>, - <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>, <&dram_gates 26>; status = "disabled"; }; @@ -85,7 +86,7 @@ compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-tve0"; - clocks = <&pll5 1>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, <&ahb_gates 44>, <&dram_gates 5>, <&dram_gates 26>; status = "disabled"; @@ -231,6 +232,7 @@ pll3x2: pll3x2_clk { #clock-cells = <0>; compatible = "fixed-factor-clock"; + clocks = <&pll3>; clock-div = <1>; clock-mult = <2>; clock-output-names = "pll3-2x"; @@ -272,6 +274,7 @@ pll7x2: pll7x2_clk { #clock-cells = <0>; compatible = "fixed-factor-clock"; + clocks = <&pll7>; clock-div = <1>; clock-mult = <2>; clock-output-names = "pll7-2x"; diff --git a/arch/arm/boot/dts/tegra30-beaver.dts b/arch/arm/boot/dts/tegra30-beaver.dts index 1eca3b28ac64..b6da15d823a6 100644 --- a/arch/arm/boot/dts/tegra30-beaver.dts +++ b/arch/arm/boot/dts/tegra30-beaver.dts @@ -1843,7 +1843,7 @@ ldo5_reg: ldo5 { regulator-name = "vddio_sdmmc,avdd_vdac"; - regulator-min-microvolt = <3300000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-always-on; }; @@ -1914,6 +1914,7 @@ sdhci@78000000 { status = "okay"; + vqmmc-supply = <&ldo5_reg>; cd-gpios = <&gpio TEGRA_GPIO(I, 5) GPIO_ACTIVE_LOW>; wp-gpios = <&gpio TEGRA_GPIO(T, 3) GPIO_ACTIVE_HIGH>; power-gpios = <&gpio TEGRA_GPIO(D, 7) GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 10f49ab5328e..47195e8690b4 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -82,6 +82,7 @@ CONFIG_TOUCHSCREEN_MMS114=y CONFIG_INPUT_MISC=y CONFIG_INPUT_MAX77693_HAPTIC=y CONFIG_INPUT_MAX8997_HAPTIC=y +CONFIG_KEYBOARD_SAMSUNG=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_SAMSUNG=y CONFIG_SERIAL_SAMSUNG_CONSOLE=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 8f857564657f..8a5fff1b7f6f 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -264,6 +264,7 @@ CONFIG_KEYBOARD_TEGRA=y CONFIG_KEYBOARD_SPEAR=y CONFIG_KEYBOARD_ST_KEYSCAN=y CONFIG_KEYBOARD_CROS_EC=m +CONFIG_KEYBOARD_SAMSUNG=m CONFIG_MOUSE_PS2_ELANTECH=y CONFIG_MOUSE_CYAPA=m CONFIG_MOUSE_ELAN_I2C=y diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 19cfab526d13..20febb368844 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -29,7 +29,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT); + return (pmd_t *)get_zeroed_page(GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index aeddd28b3595..92fd2c8a9af0 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) +#define pmd_present(pmd) (pmd_val(pmd)) #define copy_pmd(pmdpd,pmdps) \ do { \ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index fa70db7c714b..2a029bceaf2f 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -211,6 +211,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) : !!(pmd_val(pmd) & (val))) #define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val))) +#define pmd_present(pmd) (pmd_isset((pmd), L_PMD_SECT_VALID)) #define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF)) #define pte_special(pte) (pte_isset((pte), L_PTE_SPECIAL)) static inline pte_t pte_mkspecial(pte_t pte) @@ -249,10 +250,10 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) -/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */ +/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */ static inline pmd_t pmd_mknotpresent(pmd_t pmd) { - return __pmd(0); + return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 348caabb7625..d62204060cbe 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; #define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) static inline pte_t *pmd_page_vaddr(pmd_t pmd) { diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index df90bc59bfce..861521606c6d 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -486,7 +486,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { static void smp_cross_call(const struct cpumask *target, unsigned int ipinr) { - trace_ipi_raise(target, ipi_types[ipinr]); + trace_ipi_raise_rcuidle(target, ipi_types[ipinr]); __smp_cross_call(target, ipinr); } diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 893941ec98dc..f1bde7c4e736 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -263,6 +263,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvm_timer_vcpu_terminate(vcpu); kvm_vgic_vcpu_destroy(vcpu); kvm_pmu_vcpu_destroy(vcpu); + kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vcpu); } diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index e65aa7d11b20..20dcf6e904b2 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -61,7 +61,6 @@ config ARCH_EXYNOS4 select CLKSRC_SAMSUNG_PWM if CPU_EXYNOS4210 select CPU_EXYNOS4210 select GIC_NON_BANKED - select KEYBOARD_SAMSUNG if INPUT_KEYBOARD select MIGHT_HAVE_CACHE_L2X0 help Samsung EXYNOS4 (Cortex-A9) SoC based systems diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c index a38b16b69923..b56de4b8cdf2 100644 --- a/arch/arm/mach-imx/mach-imx6ul.c +++ b/arch/arm/mach-imx/mach-imx6ul.c @@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev) static void __init imx6ul_enet_phy_init(void) { if (IS_BUILTIN(CONFIG_PHYLIB)) - phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff, + phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK, ksz8081_phy_fixup); } diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile index ecf9e0c3b107..e53c6cfcab51 100644 --- a/arch/arm/mach-mvebu/Makefile +++ b/arch/arm/mach-mvebu/Makefile @@ -7,9 +7,15 @@ CFLAGS_pmsu.o := -march=armv7-a obj-$(CONFIG_MACH_MVEBU_ANY) += system-controller.o mvebu-soc-id.o ifeq ($(CONFIG_MACH_MVEBU_V7),y) -obj-y += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o pm.o pm-board.o +obj-y += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o + +obj-$(CONFIG_PM) += pm.o pm-board.o obj-$(CONFIG_SMP) += platsmp.o headsmp.o platsmp-a9.o headsmp-a9.o endif obj-$(CONFIG_MACH_DOVE) += dove.o -obj-$(CONFIG_MACH_KIRKWOOD) += kirkwood.o kirkwood-pm.o + +ifeq ($(CONFIG_MACH_KIRKWOOD),y) +obj-y += kirkwood.o +obj-$(CONFIG_PM) += kirkwood-pm.o +endif diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 7e989d61159c..e80f0dde2189 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -162,22 +162,16 @@ exit: } /* - * This ioremap hook is used on Armada 375/38x to ensure that PCIe - * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This - * is needed as a workaround for a deadlock issue between the PCIe - * interface and the cache controller. + * This ioremap hook is used on Armada 375/38x to ensure that all MMIO + * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is + * needed for the HW I/O coherency mechanism to work properly without + * deadlock. */ static void __iomem * -armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, - unsigned int mtype, void *caller) +armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, + unsigned int mtype, void *caller) { - struct resource pcie_mem; - - mvebu_mbus_get_pcie_mem_aperture(&pcie_mem); - - if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end) - mtype = MT_UNCACHED; - + mtype = MT_UNCACHED; return __arm_ioremap_caller(phys_addr, size, mtype, caller); } @@ -186,7 +180,8 @@ static void __init armada_375_380_coherency_init(struct device_node *np) struct device_node *cache_dn; coherency_cpu_base = of_iomap(np, 0); - arch_ioremap_caller = armada_pcie_wa_ioremap_caller; + arch_ioremap_caller = armada_wa_ioremap_caller; + pci_ioremap_set_mem_type(MT_UNCACHED); /* * We should switch the PL310 to I/O coherency mode only if diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S index 5d7fb596bf4a..bf608441b357 100644 --- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S +++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S @@ -43,8 +43,8 @@ #define OTHERS_MASK (MODEM_IRQ_MASK | HOOK_SWITCH_MASK) /* IRQ handler register bitmasks */ -#define DEFERRED_FIQ_MASK (0x1 << (INT_DEFERRED_FIQ % IH2_BASE)) -#define GPIO_BANK1_MASK (0x1 << INT_GPIO_BANK1) +#define DEFERRED_FIQ_MASK OMAP_IRQ_BIT(INT_DEFERRED_FIQ) +#define GPIO_BANK1_MASK OMAP_IRQ_BIT(INT_GPIO_BANK1) /* Driver buffer byte offsets */ #define BUF_MASK (FIQ_MASK * 4) @@ -110,7 +110,7 @@ ENTRY(qwerty_fiqin_start) mov r8, #2 @ reset FIQ agreement str r8, [r12, #IRQ_CONTROL_REG_OFFSET] - cmp r10, #INT_GPIO_BANK1 @ is it GPIO bank interrupt? + cmp r10, #(INT_GPIO_BANK1 - NR_IRQS_LEGACY) @ is it GPIO interrupt? beq gpio @ yes - process it mov r8, #1 diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c index d1f12095f315..ec760ae2f917 100644 --- a/arch/arm/mach-omap1/ams-delta-fiq.c +++ b/arch/arm/mach-omap1/ams-delta-fiq.c @@ -109,7 +109,8 @@ void __init ams_delta_init_fiq(void) * Since no set_type() method is provided by OMAP irq chip, * switch to edge triggered interrupt type manually. */ - offset = IRQ_ILR0_REG_OFFSET + INT_DEFERRED_FIQ * 0x4; + offset = IRQ_ILR0_REG_OFFSET + + ((INT_DEFERRED_FIQ - NR_IRQS_LEGACY) & 0x1f) * 0x4; val = omap_readl(DEFERRED_FIQ_IH_BASE + offset) & ~(1 << 1); omap_writel(val, DEFERRED_FIQ_IH_BASE + offset); @@ -149,7 +150,7 @@ void __init ams_delta_init_fiq(void) /* * Redirect GPIO interrupts to FIQ */ - offset = IRQ_ILR0_REG_OFFSET + INT_GPIO_BANK1 * 0x4; + offset = IRQ_ILR0_REG_OFFSET + (INT_GPIO_BANK1 - NR_IRQS_LEGACY) * 0x4; val = omap_readl(OMAP_IH1_BASE + offset) | 1; omap_writel(val, OMAP_IH1_BASE + offset); } diff --git a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h index adb5e7649659..6dfc3e1210a3 100644 --- a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h +++ b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h @@ -14,6 +14,8 @@ #ifndef __AMS_DELTA_FIQ_H #define __AMS_DELTA_FIQ_H +#include + /* * Interrupt number used for passing control from FIQ to IRQ. * IRQ12, described as reserved, has been selected. diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 0517f0c1581a..1a648e9dfaa0 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -17,6 +17,7 @@ config ARCH_OMAP3 select PM_OPP if PM select PM if CPU_IDLE select SOC_HAS_OMAP2_SDRC + select ARM_ERRATA_430973 config ARCH_OMAP4 bool "TI OMAP4" @@ -36,6 +37,7 @@ config ARCH_OMAP4 select PM if CPU_IDLE select ARM_ERRATA_754322 select ARM_ERRATA_775420 + select OMAP_INTERCONNECT config SOC_OMAP5 bool "TI OMAP5" @@ -67,6 +69,8 @@ config SOC_AM43XX select HAVE_ARM_SCU select GENERIC_CLOCKEVENTS_BROADCAST select HAVE_ARM_TWD + select ARM_ERRATA_754322 + select ARM_ERRATA_775420 config SOC_DRA7XX bool "TI DRA7XX" @@ -240,4 +244,12 @@ endmenu endif +config OMAP5_ERRATA_801819 + bool "Errata 801819: An eviction from L1 data cache might stall indefinitely" + depends on SOC_OMAP5 || SOC_DRA7XX + help + A livelock can occur in the L2 cache arbitration that might prevent + a snoop from completing. Under certain conditions this can cause the + system to deadlock. + endmenu diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h index af2851fbcdf0..bae263fba640 100644 --- a/arch/arm/mach-omap2/omap-secure.h +++ b/arch/arm/mach-omap2/omap-secure.h @@ -46,6 +46,7 @@ #define OMAP5_DRA7_MON_SET_CNTFRQ_INDEX 0x109 #define OMAP5_MON_AMBA_IF_INDEX 0x108 +#define OMAP5_DRA7_MON_SET_ACR_INDEX 0x107 /* Secure PPA(Primary Protected Application) APIs */ #define OMAP4_PPA_L2_POR_INDEX 0x23 diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index c625cc10d9f9..8cd1de914ee4 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -50,6 +50,39 @@ void __iomem *omap4_get_scu_base(void) return scu_base; } +#ifdef CONFIG_OMAP5_ERRATA_801819 +void omap5_erratum_workaround_801819(void) +{ + u32 acr, revidr; + u32 acr_mask; + + /* REVIDR[3] indicates erratum fix available on silicon */ + asm volatile ("mrc p15, 0, %0, c0, c0, 6" : "=r" (revidr)); + if (revidr & (0x1 << 3)) + return; + + asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr)); + /* + * BIT(27) - Disables streaming. All write-allocate lines allocate in + * the L1 or L2 cache. + * BIT(25) - Disables streaming. All write-allocate lines allocate in + * the L1 cache. + */ + acr_mask = (0x3 << 25) | (0x3 << 27); + /* do we already have it done.. if yes, skip expensive smc */ + if ((acr & acr_mask) == acr_mask) + return; + + acr |= acr_mask; + omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr); + + pr_debug("%s: ARM erratum workaround 801819 applied on CPU%d\n", + __func__, smp_processor_id()); +} +#else +static inline void omap5_erratum_workaround_801819(void) { } +#endif + static void omap4_secondary_init(unsigned int cpu) { /* @@ -64,12 +97,15 @@ static void omap4_secondary_init(unsigned int cpu) omap_secure_dispatcher(OMAP4_PPA_CPU_ACTRL_SMP_INDEX, 4, 0, 0, 0, 0, 0); - /* - * Configure the CNTFRQ register for the secondary cpu's which - * indicates the frequency of the cpu local timers. - */ - if (soc_is_omap54xx() || soc_is_dra7xx()) + if (soc_is_omap54xx() || soc_is_dra7xx()) { + /* + * Configure the CNTFRQ register for the secondary cpu's which + * indicates the frequency of the cpu local timers. + */ set_cntfreq(); + /* Configure ACR to disable streaming WA for 801819 */ + omap5_erratum_workaround_801819(); + } /* * Synchronise with the boot thread. @@ -218,6 +254,8 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus) if (cpu_is_omap446x()) startup_addr = omap4460_secondary_startup; + if (soc_is_dra74x() || soc_is_omap54xx()) + omap5_erratum_workaround_801819(); /* * Write the address of secondary startup routine into the diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c index 78af6d8cf2e2..daf2753de7aa 100644 --- a/arch/arm/mach-omap2/powerdomain.c +++ b/arch/arm/mach-omap2/powerdomain.c @@ -186,8 +186,9 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag) trace_state = (PWRDM_TRACE_STATES_FLAG | ((next & OMAP_POWERSTATE_MASK) << 8) | ((prev & OMAP_POWERSTATE_MASK) << 0)); - trace_power_domain_target(pwrdm->name, trace_state, - smp_processor_id()); + trace_power_domain_target_rcuidle(pwrdm->name, + trace_state, + smp_processor_id()); } break; default: @@ -523,8 +524,8 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst) if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) { /* Trace the pwrdm desired target state */ - trace_power_domain_target(pwrdm->name, pwrst, - smp_processor_id()); + trace_power_domain_target_rcuidle(pwrdm->name, pwrst, + smp_processor_id()); /* Program the pwrdm desired target state */ ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst); } diff --git a/arch/arm/mach-omap2/powerdomains7xx_data.c b/arch/arm/mach-omap2/powerdomains7xx_data.c index 0ec2d00f4237..eb350a673133 100644 --- a/arch/arm/mach-omap2/powerdomains7xx_data.c +++ b/arch/arm/mach-omap2/powerdomains7xx_data.c @@ -36,14 +36,7 @@ static struct powerdomain iva_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_IVA_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 4, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* hwa_mem */ - [1] = PWRSTS_OFF_RET, /* sl2_mem */ - [2] = PWRSTS_OFF_RET, /* tcm1_mem */ - [3] = PWRSTS_OFF_RET, /* tcm2_mem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* hwa_mem */ [1] = PWRSTS_ON, /* sl2_mem */ @@ -76,12 +69,7 @@ static struct powerdomain ipu_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_IPU_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 2, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* aessmem */ - [1] = PWRSTS_OFF_RET, /* periphmem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* aessmem */ [1] = PWRSTS_ON, /* periphmem */ @@ -95,11 +83,7 @@ static struct powerdomain dss_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_DSS_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* dss_mem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* dss_mem */ }, @@ -111,13 +95,8 @@ static struct powerdomain l4per_7xx_pwrdm = { .name = "l4per_pwrdm", .prcm_offs = DRA7XX_PRM_L4PER_INST, .prcm_partition = DRA7XX_PRM_PARTITION, - .pwrsts = PWRSTS_RET_ON, - .pwrsts_logic_ret = PWRSTS_RET, + .pwrsts = PWRSTS_ON, .banks = 2, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* nonretained_bank */ - [1] = PWRSTS_OFF_RET, /* retained_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* nonretained_bank */ [1] = PWRSTS_ON, /* retained_bank */ @@ -132,9 +111,6 @@ static struct powerdomain gpu_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* gpu_mem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* gpu_mem */ }, @@ -148,8 +124,6 @@ static struct powerdomain wkupaon_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_ON, .banks = 1, - .pwrsts_mem_ret = { - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* wkup_bank */ }, @@ -161,15 +135,7 @@ static struct powerdomain core_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_CORE_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_ON, - .pwrsts_logic_ret = PWRSTS_RET, .banks = 5, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* core_nret_bank */ - [1] = PWRSTS_OFF_RET, /* core_ocmram */ - [2] = PWRSTS_OFF_RET, /* core_other_bank */ - [3] = PWRSTS_OFF_RET, /* ipu_l2ram */ - [4] = PWRSTS_OFF_RET, /* ipu_unicache */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* core_nret_bank */ [1] = PWRSTS_ON, /* core_ocmram */ @@ -226,11 +192,7 @@ static struct powerdomain vpe_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_VPE_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* vpe_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* vpe_bank */ }, @@ -260,14 +222,8 @@ static struct powerdomain l3init_7xx_pwrdm = { .name = "l3init_pwrdm", .prcm_offs = DRA7XX_PRM_L3INIT_INST, .prcm_partition = DRA7XX_PRM_PARTITION, - .pwrsts = PWRSTS_RET_ON, - .pwrsts_logic_ret = PWRSTS_RET, + .pwrsts = PWRSTS_ON, .banks = 3, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* gmac_bank */ - [1] = PWRSTS_OFF_RET, /* l3init_bank1 */ - [2] = PWRSTS_OFF_RET, /* l3init_bank2 */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* gmac_bank */ [1] = PWRSTS_ON, /* l3init_bank1 */ @@ -283,9 +239,6 @@ static struct powerdomain eve3_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve3_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve3_bank */ }, @@ -299,9 +252,6 @@ static struct powerdomain emu_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* emu_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* emu_bank */ }, @@ -314,11 +264,6 @@ static struct powerdomain dsp2_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 3, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* dsp2_edma */ - [1] = PWRSTS_OFF_RET, /* dsp2_l1 */ - [2] = PWRSTS_OFF_RET, /* dsp2_l2 */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* dsp2_edma */ [1] = PWRSTS_ON, /* dsp2_l1 */ @@ -334,11 +279,6 @@ static struct powerdomain dsp1_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 3, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* dsp1_edma */ - [1] = PWRSTS_OFF_RET, /* dsp1_l1 */ - [2] = PWRSTS_OFF_RET, /* dsp1_l2 */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* dsp1_edma */ [1] = PWRSTS_ON, /* dsp1_l1 */ @@ -354,9 +294,6 @@ static struct powerdomain cam_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* vip_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* vip_bank */ }, @@ -370,9 +307,6 @@ static struct powerdomain eve4_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve4_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve4_bank */ }, @@ -386,9 +320,6 @@ static struct powerdomain eve2_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve2_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve2_bank */ }, @@ -402,9 +333,6 @@ static struct powerdomain eve1_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve1_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve1_bank */ }, diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 5b385bb8aff9..cb9497a20fb3 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -496,8 +496,7 @@ void __init omap_init_time(void) __omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon", 2, "timer_sys_ck", NULL, false); - if (of_have_populated_dt()) - clocksource_probe(); + clocksource_probe(); } #if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM43XX) @@ -505,6 +504,8 @@ void __init omap3_secure_sync32k_timer_init(void) { __omap_sync32k_timer_init(12, "secure_32k_fck", "ti,timer-secure", 2, "timer_sys_ck", NULL, false); + + clocksource_probe(); } #endif /* CONFIG_ARCH_OMAP3 */ @@ -513,6 +514,8 @@ void __init omap3_gptimer_timer_init(void) { __omap_sync32k_timer_init(2, "timer_sys_ck", NULL, 1, "timer_sys_ck", "ti,timer-alwon", true); + + clocksource_probe(); } #endif diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 84baa16f4c0b..e93aa6734147 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -68,7 +68,7 @@ #include #include -static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); +#define samsung_device_dma_mask (*((u64[]) { DMA_BIT_MASK(32) })) /* AC97 */ #ifdef CONFIG_CPU_S3C2440 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 7085e322dc42..648a32c89541 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -95,7 +95,7 @@ boot := arch/arm64/boot Image: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -Image.%: vmlinux +Image.%: Image $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ zinstall install: diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi index 3a4e9a2ab313..fbafa24cd533 100644 --- a/arch/arm64/boot/dts/lg/lg1312.dtsi +++ b/arch/arm64/boot/dts/lg/lg1312.dtsi @@ -125,7 +125,7 @@ #size-cells = <1>; #interrupts-cells = <3>; - compatible = "arm,amba-bus"; + compatible = "simple-bus"; interrupt-parent = <&gic>; ranges; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 46f325a143b0..d7f8e06910bc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -163,7 +163,7 @@ }; amba { - compatible = "arm,amba-bus"; + compatible = "simple-bus"; #address-cells = <2>; #size-cells = <2>; ranges; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 87e1985f3be8..9d9fd4b9a72e 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -80,12 +80,14 @@ #define APM_CPU_PART_POTENZA 0x000 #define CAVIUM_CPU_PART_THUNDERX 0x0A1 +#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 #define BRCM_CPU_PART_VULCAN 0x516 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) +#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h index f69f69c8120c..da84645525b9 100644 --- a/arch/arm64/include/asm/kgdb.h +++ b/arch/arm64/include/asm/kgdb.h @@ -38,25 +38,54 @@ extern int kgdb_fault_expected; #endif /* !__ASSEMBLY__ */ /* - * gdb is expecting the following registers layout. + * gdb remote procotol (well most versions of it) expects the following + * register layout. * * General purpose regs: * r0-r30: 64 bit * sp,pc : 64 bit - * pstate : 64 bit - * Total: 34 + * pstate : 32 bit + * Total: 33 + 1 * FPU regs: * f0-f31: 128 bit - * Total: 32 - * Extra regs * fpsr & fpcr: 32 bit - * Total: 2 + * Total: 32 + 2 * + * To expand a little on the "most versions of it"... when the gdb remote + * protocol for AArch64 was developed it depended on a statement in the + * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register". + * and, as a result, allocated only 32-bits for the PSTATE in the remote + * protocol. In fact this statement is still present in ARM DDI 0487A.i. + * + * Unfortunately "is a 32-bit register" has a very special meaning for + * system registers. It means that "the upper bits, bits[63:32], are + * RES0.". RES0 is heavily used in the ARM architecture documents as a + * way to leave space for future architecture changes. So to translate a + * little for people who don't spend their spare time reading ARM architecture + * manuals, what "is a 32-bit register" actually means in this context is + * "is a 64-bit register but one with no meaning allocated to any of the + * upper 32-bits... *yet*". + * + * Perhaps then we should not be surprised that this has led to some + * confusion. Specifically a patch, influenced by the above translation, + * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch + * was reverted in gdb-7.8.1 and all later releases, when this was + * discovered to be an undocumented protocol change. + * + * So... it is *not* wrong for us to only allocate 32-bits to PSTATE + * here even though the kernel itself allocates 64-bits for the same + * state. That is because this bit of code tells the kernel how the gdb + * remote protocol (well most versions of it) describes the register state. + * + * Note that if you are using one of the versions of gdb that supports + * the gdb-7.7 version of the protocol you cannot use kgdb directly + * without providing a custom register description (gdb can load new + * protocol descriptions at runtime). */ -#define _GP_REGS 34 +#define _GP_REGS 33 #define _FP_REGS 32 -#define _EXTRA_REGS 2 +#define _EXTRA_REGS 3 /* * general purpose registers size in bytes. * pstate is only 4 bytes. subtract 4 bytes diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index ff98585d085a..d25f4f137c2a 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -26,7 +26,7 @@ #define check_pgt_cache() do { } while (0) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index a307eb6e7fa8..7f94755089e2 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -117,6 +117,8 @@ struct pt_regs { }; u64 orig_x0; u64 syscallno; + u64 orig_addr_limit; + u64 unused; // maintain 16 byte alignment }; #define arch_has_single_step() (1) diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 433e50405274..022644704a93 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void) cpu_park_loop(); } +/* + * If a secondary CPU enters the kernel but fails to come online, + * (e.g. due to mismatched features), and cannot exit the kernel, + * we increment cpus_stuck_in_kernel and leave the CPU in a + * quiesecent loop within the kernel text. The memory containing + * this loop must not be re-used for anything else as the 'stuck' + * core is executing it. + * + * This function is used to inhibit features like kexec and hibernate. + */ +bool cpus_are_stuck_in_kernel(void); + #endif /* ifndef __ASSEMBLY__ */ #endif /* ifndef __ASM_SMP_H */ diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index fc9682bfe002..e875a5a551d7 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { unsigned int tmp; arch_spinlock_t lockval; + u32 owner; + + /* + * Ensure prior spin_lock operations to other locks have completed + * on this CPU before we test whether "lock" is locked. + */ + smp_mb(); + owner = READ_ONCE(lock->owner) << 16; asm volatile( " sevl\n" "1: wfe\n" "2: ldaxr %w0, %2\n" + /* Is the lock free? */ " eor %w1, %w0, %w0, ror #16\n" -" cbnz %w1, 1b\n" +" cbz %w1, 3f\n" + /* Lock taken -- has there been a subsequent unlock->lock transition? */ +" eor %w1, %w3, %w0, lsl #16\n" +" cbz %w1, 1b\n" + /* + * The owner has been updated, so there was an unlock->lock + * transition that we missed. That means we can rely on the + * store-release of the unlock operation paired with the + * load-acquire of the lock operation to publish any of our + * previous stores to the new lock owner and therefore don't + * need to bother with the writeback below. + */ +" b 4f\n" +"3:\n" + /* + * Serialise against any concurrent lockers by writing back the + * unlocked lock value + */ ARM64_LSE_ATOMIC_INSN( /* LL/SC */ " stxr %w1, %w0, %2\n" -" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */ - /* LSE atomics */ " nop\n" -" nop\n") +" nop\n", + /* LSE atomics */ +" mov %w1, %w0\n" +" cas %w0, %w0, %2\n" +" eor %w1, %w1, %w0\n") + /* Somebody else wrote to the lock, GOTO 10 and reload the value */ +" cbnz %w1, 2b\n" +"4:" : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) - : + : "r" (owner) : "memory"); } @@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { + smp_mb(); /* See arch_spin_unlock_wait */ return !arch_spin_value_unlocked(READ_ONCE(*lock)); } diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f8e5d47f0880..2f4ba774488a 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -60,6 +60,7 @@ int main(void) DEFINE(S_PC, offsetof(struct pt_regs, pc)); DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); + DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index d42789499f17..af716b65110d 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { MIDR_RANGE(MIDR_THUNDERX, 0x00, (1 << MIDR_VARIANT_SHIFT) | 1), }, + { + /* Cavium ThunderX, T81 pass 1.0 */ + .desc = "Cavium erratum 27456", + .capability = ARM64_WORKAROUND_CAVIUM_27456, + MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00), + }, #endif { } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 12e8d2bcb3f9..6c3b7345a6c4 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -97,7 +98,14 @@ mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE - .endif + get_thread_info tsk + /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ + ldr x20, [tsk, #TI_ADDR_LIMIT] + str x20, [sp, #S_ORIG_ADDR_LIMIT] + mov x20, #TASK_SIZE_64 + str x20, [tsk, #TI_ADDR_LIMIT] + ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO) + .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 stp lr, x21, [sp, #S_LR] @@ -128,6 +136,14 @@ .endm .macro kernel_exit, el + .if \el != 0 + /* Restore the task's original addr_limit. */ + ldr x20, [sp, #S_ORIG_ADDR_LIMIT] + str x20, [tsk, #TI_ADDR_LIMIT] + + /* No need to restore UAO, it will be restored from SPSR_EL1 */ + .endif + ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 ct_user_enter @@ -406,7 +422,6 @@ el1_irq: bl trace_hardirqs_off #endif - get_thread_info tsk irq_handler #ifdef CONFIG_PREEMPT diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f8df75d740f4..21ab5df9fa76 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -236,6 +237,11 @@ int swsusp_arch_suspend(void) unsigned long flags; struct sleep_stack_data state; + if (cpus_are_stuck_in_kernel()) { + pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n"); + return -EBUSY; + } + local_dbg_save(flags); if (__cpu_suspend_enter(&state)) { diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index b67531a13136..b5f063e5eff7 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { { "x30", 8, offsetof(struct pt_regs, regs[30])}, { "sp", 8, offsetof(struct pt_regs, sp)}, { "pc", 8, offsetof(struct pt_regs, pc)}, - { "pstate", 8, offsetof(struct pt_regs, pstate)}, + /* + * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote + * protocol disagrees. Therefore we must extract only the lower + * 32-bits. Look for the big comment in asm/kgdb.h for more + * detail. + */ + { "pstate", 4, offsetof(struct pt_regs, pstate) +#ifdef CONFIG_CPU_BIG_ENDIAN + + 4 +#endif + }, { "v0", 16, -1 }, { "v1", 16, -1 }, { "v2", 16, -1 }, @@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task) memset((char *)gdb_regs, 0, NUMREGBYTES); thread_regs = task_pt_regs(task); memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES); + /* Special case for PSTATE (check comments in asm/kgdb.h for details) */ + dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs); } void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 678e0842cb3b..62ff3c0622e2 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; } + +static bool have_cpu_die(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + int any_cpu = raw_smp_processor_id(); + + if (cpu_ops[any_cpu]->cpu_die) + return true; +#endif + return false; +} + +bool cpus_are_stuck_in_kernel(void) +{ + bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die()); + + return !!cpus_stuck_in_kernel || smp_spin_tables; +} diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index f7cf463107df..2a43012616b7 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, /* * We need to switch to kernel mode so that we can use __get_user - * to safely read from kernel space. Note that we now dump the - * code first, just in case the backtrace kills us. + * to safely read from kernel space. */ fs = get_fs(); set_fs(KERNEL_DS); @@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where) print_ip_sym(where); } -static void dump_instr(const char *lvl, struct pt_regs *regs) +static void __dump_instr(const char *lvl, struct pt_regs *regs) { unsigned long addr = instruction_pointer(regs); - mm_segment_t fs; char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str; int i; - /* - * We need to switch to kernel mode so that we can use __get_user - * to safely read from kernel space. Note that we now dump the - * code first, just in case the backtrace kills us. - */ - fs = get_fs(); - set_fs(KERNEL_DS); - for (i = -4; i < 1; i++) { unsigned int val, bad; @@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) } } printk("%sCode: %s\n", lvl, str); +} - set_fs(fs); +static void dump_instr(const char *lvl, struct pt_regs *regs) +{ + if (!user_mode(regs)) { + mm_segment_t fs = get_fs(); + set_fs(KERNEL_DS); + __dump_instr(lvl, regs); + set_fs(fs); + } else { + __dump_instr(lvl, regs); + } } static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index b7b397802088..efcf1f7ef1e4 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) &asid_generation); flush_context(cpu); - /* We have at least 1 ASID per CPU, so this will always succeed */ + /* We have more ASIDs than CPUs, so this will always succeed */ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); set_asid: @@ -227,8 +227,11 @@ switch_mm_fastpath: static int asids_init(void) { asid_bits = get_cpu_asid_bits(); - /* If we end up with more CPUs than ASIDs, expect things to crash */ - WARN_ON(NUM_USER_ASIDS < num_possible_cpus()); + /* + * Expect allocation after rollover to fail if we don't have at least + * one more ASID than CPUs. ASID #0 is reserved for init_mm. + */ + WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus()); atomic64_set(&asid_generation, ASID_FIRST_VERSION); asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map), GFP_KERNEL); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index ba3fc12bd272..b1166d1e5955 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, } if (permission_fault(esr) && (addr < USER_DS)) { - if (get_fs() == KERNEL_DS) + /* regs->orig_addr_limit may be 0 if we entered from EL0 */ + if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); if (!search_exception_tables(regs->pc)) @@ -441,7 +442,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs) return 1; } -static struct fault_info { +static const struct fault_info { int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs); int sig; int code; diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index dbd12ea8ce68..43a76b07eb32 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) { struct page *page = pte_page(pte); - /* no flushing needed for anonymous pages */ - if (!page_mapping(page)) - return; - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) sync_icache_aliases(page_address(page), PAGE_SIZE << compound_order(page)); diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h index 1aba19d68c5e..db039cb368be 100644 --- a/arch/avr32/include/asm/pgalloc.h +++ b/arch/avr32/include/asm/pgalloc.h @@ -43,7 +43,7 @@ static inline void pgd_ctor(void *x) */ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - return quicklist_alloc(QUICK_PGD, GFP_KERNEL | __GFP_REPEAT, pgd_ctor); + return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor); } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -54,7 +54,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -63,7 +63,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, struct page *page; void *pg; - pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); if (!pg) return NULL; diff --git a/arch/cris/include/asm/pgalloc.h b/arch/cris/include/asm/pgalloc.h index 235ece437ddd..42f1affb9c2d 100644 --- a/arch/cris/include/asm/pgalloc.h +++ b/arch/cris/include/asm/pgalloc.h @@ -24,14 +24,14 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return pte; } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); + pte = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c index 41907d25ed38..c9ed14f6c67d 100644 --- a/arch/frv/mm/pgalloc.c +++ b/arch/frv/mm/pgalloc.c @@ -22,7 +22,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((aligned(PAGE_SIZE))); pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL); if (pte) clear_page(pte); return pte; @@ -33,9 +33,9 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) struct page *page; #ifdef CONFIG_HIGHPTE - page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0); + page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0); #else - page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + page = alloc_pages(GFP_KERNEL, 0); #endif if (!page) return NULL; diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index 77da3b0ae3c2..eeebf862c46c 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -64,7 +64,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + pte = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { @@ -78,7 +78,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO; + gfp_t flags = GFP_KERNEL | __GFP_ZERO; return (pte_t *) __get_free_page(flags); } diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index f80758cb7157..e109ee95e919 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -45,7 +45,7 @@ config IA64 select GENERIC_SMP_IDLE_THREAD select ARCH_INIT_TASK select ARCH_TASK_STRUCT_ALLOCATOR - select ARCH_THREAD_INFO_ALLOCATOR + select ARCH_THREAD_STACK_ALLOCATOR select ARCH_CLOCKSOURCE_DATA select GENERIC_TIME_VSYSCALL_OLD select SYSCTL_ARCH_UNALIGN_NO_WARN diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index aa995b67c3f5..d1212b84fb83 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -48,15 +48,15 @@ struct thread_info { #ifndef ASM_OFFSETS_C /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *) ((char *) current + IA64_TASK_SIZE)) -#define alloc_thread_info_node(tsk, node) \ - ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE)) +#define alloc_thread_stack_node(tsk, node) \ + ((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE)) #define task_thread_info(tsk) ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE)) #else #define current_thread_info() ((struct thread_info *) 0) -#define alloc_thread_info_node(tsk, node) ((struct thread_info *) 0) +#define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0) #define task_thread_info(tsk) ((struct thread_info *) 0) #endif -#define free_thread_info(ti) /* nothing */ +#define free_thread_stack(ti) /* nothing */ #define task_stack_page(tsk) ((void *)(tsk)) #define __HAVE_THREAD_FUNCTIONS diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c index f9efe9739d3f..0eaa89f3defd 100644 --- a/arch/ia64/kernel/init_task.c +++ b/arch/ia64/kernel/init_task.c @@ -26,6 +26,7 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); * handled. This is done by having a special ".data..init_task" section... */ #define init_thread_info init_task_mem.s.thread_info +#define init_stack init_task_mem.stack union { struct { diff --git a/arch/m32r/boot/compressed/m32r_sio.c b/arch/m32r/boot/compressed/m32r_sio.c index 01d877c6868f..cf3023dced49 100644 --- a/arch/m32r/boot/compressed/m32r_sio.c +++ b/arch/m32r/boot/compressed/m32r_sio.c @@ -8,12 +8,13 @@ #include -static void putc(char c); +static void m32r_putc(char c); static int puts(const char *s) { char c; - while ((c = *s++)) putc(c); + while ((c = *s++)) + m32r_putc(c); return 0; } @@ -41,7 +42,7 @@ static int puts(const char *s) #define BOOT_SIO0TXB PLD_ESIO0TXB #endif -static void putc(char c) +static void m32r_putc(char c) { while ((*BOOT_SIO0STS & 0x3) != 0x3) cpu_relax(); @@ -61,7 +62,7 @@ static void putc(char c) #define SIO0TXB (volatile unsigned short *)(0x00efd000 + 30) #endif -static void putc(char c) +static void m32r_putc(char c) { while ((*SIO0STS & 0x1) == 0) cpu_relax(); diff --git a/arch/m68k/coldfire/head.S b/arch/m68k/coldfire/head.S index fa31be297b85..73d92ea0ce65 100644 --- a/arch/m68k/coldfire/head.S +++ b/arch/m68k/coldfire/head.S @@ -288,7 +288,7 @@ _clear_bss: #endif /* - * Assember start up done, start code proper. + * Assembler start up done, start code proper. */ jsr start_kernel /* start Linux kernel */ diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c index c525e4c08f84..9abb1a441da0 100644 --- a/arch/m68k/coldfire/m5272.c +++ b/arch/m68k/coldfire/m5272.c @@ -111,7 +111,7 @@ void __init config_BSP(char *commandp, int size) /***************************************************************************/ /* - * Some 5272 based boards have the FEC ethernet diectly connected to + * Some 5272 based boards have the FEC ethernet directly connected to * an ethernet switch. In this case we need to use the fixed phy type, * and we need to declare it early in boot. */ diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c index 821de928dc3f..6a640be48568 100644 --- a/arch/m68k/coldfire/pci.c +++ b/arch/m68k/coldfire/pci.c @@ -42,7 +42,7 @@ static unsigned long iospace; /* * We need to be carefull probing on bus 0 (directly connected to host - * bridge). We should only acccess the well defined possible devices in + * bridge). We should only access the well defined possible devices in * use, ignore aliases and the like. */ static unsigned char mcf_host_slot2sid[32] = { diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 3ee6976f6088..8f5b6f7dd136 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -359,6 +360,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -553,7 +555,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index e96787ffcbce..31bded9c83d4 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -341,6 +342,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -512,7 +514,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 083fe6beac14..0d7739e04ae2 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -350,6 +351,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -533,7 +535,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 475130c06dcb..2cbb5c465fec 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -340,6 +341,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 4339658c200f..96102a42c156 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -341,6 +342,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -514,7 +516,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 831cc8c3a2e2..97d88f7dc5a7 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -357,6 +358,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -536,7 +538,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 6377afeb522b..be25ef208f0f 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -390,6 +391,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -616,7 +618,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 4304b3d56262..a008344360c9 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -339,6 +340,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 074bda4094ff..6735a25f36d4 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -340,6 +341,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 07b9fa8d7f2e..780c6e9f6cf9 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -346,6 +347,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -527,7 +529,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 36e6fae02d45..44693cf361e5 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -337,6 +338,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -506,7 +508,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 903acf929511..ef0071d61158 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -337,6 +338,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -506,7 +508,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/ifpsp060/src/fpsp.S b/arch/m68k/ifpsp060/src/fpsp.S index 78cb60f5bb4d..9bbffebe3eb5 100644 --- a/arch/m68k/ifpsp060/src/fpsp.S +++ b/arch/m68k/ifpsp060/src/fpsp.S @@ -10191,7 +10191,7 @@ xdnrm_con: xdnrm_sd: mov.l %a1,-(%sp) tst.b LOCAL_EX(%a0) # is denorm pos or neg? - smi.b %d1 # set d0 accodingly + smi.b %d1 # set d0 accordingly bsr.l unf_sub mov.l (%sp)+,%a1 xdnrm_exit: @@ -10990,7 +10990,7 @@ src_qnan_m: # routines where an instruction is selected by an index into # a large jump table corresponding to a given instruction which # has been decoded. Flow continues here where we now decode -# further accoding to the source operand type. +# further according to the source operand type. # global fsinh @@ -23196,14 +23196,14 @@ m_sign: # # 1. Branch on the sign of the adjusted exponent. # 2p.(positive exp) -# 2. Check M16 and the digits in lwords 2 and 3 in decending order. +# 2. Check M16 and the digits in lwords 2 and 3 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Subtract the count from the exp. # 5. Check if the exp has crossed zero in #3 above; make the exp abs # and set SE. # 6. Multiply the mantissa by 10**count. # 2n.(negative exp) -# 2. Check the digits in lwords 3 and 2 in decending order. +# 2. Check the digits in lwords 3 and 2 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Add the count to the exp. # 5. Check if the exp has crossed zero in #3 above; clear SE. diff --git a/arch/m68k/ifpsp060/src/pfpsp.S b/arch/m68k/ifpsp060/src/pfpsp.S index 4aedef973cf6..3535e6c87eec 100644 --- a/arch/m68k/ifpsp060/src/pfpsp.S +++ b/arch/m68k/ifpsp060/src/pfpsp.S @@ -13156,14 +13156,14 @@ m_sign: # # 1. Branch on the sign of the adjusted exponent. # 2p.(positive exp) -# 2. Check M16 and the digits in lwords 2 and 3 in decending order. +# 2. Check M16 and the digits in lwords 2 and 3 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Subtract the count from the exp. # 5. Check if the exp has crossed zero in #3 above; make the exp abs # and set SE. # 6. Multiply the mantissa by 10**count. # 2n.(negative exp) -# 2. Check the digits in lwords 3 and 2 in decending order. +# 2. Check the digits in lwords 3 and 2 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Add the count to the exp. # 5. Check if the exp has crossed zero in #3 above; clear SE. diff --git a/arch/m68k/include/asm/dma.h b/arch/m68k/include/asm/dma.h index 429fe26e320c..208b4daa14b3 100644 --- a/arch/m68k/include/asm/dma.h +++ b/arch/m68k/include/asm/dma.h @@ -18,7 +18,7 @@ * AUG/22/2000 : added support for 32-bit Dual-Address-Mode (K) 2000 * Oliver Kamphenkel (O.Kamphenkel@tu-bs.de) * - * AUG/25/2000 : addad support for 8, 16 and 32-bit Single-Address-Mode (K)2000 + * AUG/25/2000 : added support for 8, 16 and 32-bit Single-Address-Mode (K)2000 * Oliver Kamphenkel (O.Kamphenkel@tu-bs.de) * * APR/18/2002 : added proper support for MCF5272 DMA controller. diff --git a/arch/m68k/include/asm/m525xsim.h b/arch/m68k/include/asm/m525xsim.h index f186459072e9..699f20c8a0fe 100644 --- a/arch/m68k/include/asm/m525xsim.h +++ b/arch/m68k/include/asm/m525xsim.h @@ -123,10 +123,10 @@ /* * I2C module. */ -#define MCFI2C_BASE0 (MCF_MBAR + 0x280) /* Base addreess I2C0 */ +#define MCFI2C_BASE0 (MCF_MBAR + 0x280) /* Base address I2C0 */ #define MCFI2C_SIZE0 0x20 /* Register set size */ -#define MCFI2C_BASE1 (MCF_MBAR2 + 0x440) /* Base addreess I2C1 */ +#define MCFI2C_BASE1 (MCF_MBAR2 + 0x440) /* Base address I2C1 */ #define MCFI2C_SIZE1 0x20 /* Register set size */ /* diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index f9924fbcfe42..fb95aed5f428 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -14,7 +14,7 @@ extern const char bad_pmd_string[]; extern inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - unsigned long page = __get_free_page(GFP_DMA|__GFP_REPEAT); + unsigned long page = __get_free_page(GFP_DMA); if (!page) return NULL; @@ -51,7 +51,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page, static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_pages(GFP_DMA|__GFP_REPEAT, 0); + struct page *page = alloc_pages(GFP_DMA, 0); pte_t *pte; if (!page) diff --git a/arch/m68k/include/asm/mcfmmu.h b/arch/m68k/include/asm/mcfmmu.h index 26cc3d5a63f8..8824236e303f 100644 --- a/arch/m68k/include/asm/mcfmmu.h +++ b/arch/m68k/include/asm/mcfmmu.h @@ -38,7 +38,7 @@ /* * MMU Operation register. */ -#define MMUOR_UAA 0x00000001 /* Update allocatiom address */ +#define MMUOR_UAA 0x00000001 /* Update allocation address */ #define MMUOR_ACC 0x00000002 /* TLB access */ #define MMUOR_RD 0x00000004 /* TLB access read */ #define MMUOR_WR 0x00000000 /* TLB access write */ diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index 24bcba496c75..c895b987202c 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -11,7 +11,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long ad { pte_t *pte; - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); if (pte) { __flush_page_to_ram(pte); flush_tlb_kernel_page(pte); @@ -32,7 +32,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres struct page *page; pte_t *pte; - page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); + page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); if(!page) return NULL; if (!pgtable_page_ctor(page)) { diff --git a/arch/m68k/include/asm/q40_master.h b/arch/m68k/include/asm/q40_master.h index fc5b36278d04..c48d21b68f04 100644 --- a/arch/m68k/include/asm/q40_master.h +++ b/arch/m68k/include/asm/q40_master.h @@ -1,6 +1,6 @@ /* * Q40 master Chip Control - * RTC stuff merged for compactnes.. + * RTC stuff merged for compactness. */ #ifndef _Q40_MASTER_H diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 0931388de47f..1901f61f926f 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -37,7 +37,7 @@ do { \ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - unsigned long page = __get_free_page(GFP_KERNEL|__GFP_REPEAT); + unsigned long page = __get_free_page(GFP_KERNEL); if (!page) return NULL; @@ -49,7 +49,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + struct page *page = alloc_pages(GFP_KERNEL, 0); if (page == NULL) return NULL; diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c index 4d2adfb32a2a..7990b6f50105 100644 --- a/arch/m68k/mac/iop.c +++ b/arch/m68k/mac/iop.c @@ -60,7 +60,7 @@ * * The host talks to the IOPs using a rather simple message-passing scheme via * a shared memory area in the IOP RAM. Each IOP has seven "channels"; each - * channel is conneced to a specific software driver on the IOP. For example + * channel is connected to a specific software driver on the IOP. For example * on the SCC IOP there is one channel for each serial port. Each channel has * an incoming and and outgoing message queue with a depth of one. * diff --git a/arch/m68k/math-emu/fp_decode.h b/arch/m68k/math-emu/fp_decode.h index 759679d9ab96..6d1e760e2a0e 100644 --- a/arch/m68k/math-emu/fp_decode.h +++ b/arch/m68k/math-emu/fp_decode.h @@ -130,7 +130,7 @@ do_fscc=0 bfextu %d2{#13,#3},%d0 .endm -| decode the 8bit diplacement from the brief extension word +| decode the 8bit displacement from the brief extension word .macro fp_decode_disp8 move.b %d2,%d0 ext.w %d0 diff --git a/arch/metag/include/asm/pgalloc.h b/arch/metag/include/asm/pgalloc.h index 3104df0a4822..c2caa1ee4360 100644 --- a/arch/metag/include/asm/pgalloc.h +++ b/arch/metag/include/asm/pgalloc.h @@ -42,8 +42,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | - __GFP_ZERO); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); return pte; } @@ -51,7 +50,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); + pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index 61436d69775c..7c89390c0c13 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -116,9 +116,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, struct page *ptepage; #ifdef CONFIG_HIGHPTE - int flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT; + int flags = GFP_KERNEL | __GFP_HIGHMEM; #else - int flags = GFP_KERNEL | __GFP_REPEAT; + int flags = GFP_KERNEL; #endif ptepage = alloc_pages(flags, 0); diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c index 4f4520e779a5..eb99fcc76088 100644 --- a/arch/microblaze/mm/pgtable.c +++ b/arch/microblaze/mm/pgtable.c @@ -239,8 +239,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; if (mem_init_done) { - pte = (pte_t *)__get_free_page(GFP_KERNEL | - __GFP_REPEAT | __GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } else { pte = (pte_t *)early_get_page(); if (pte) diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6733ac575da4..36a391d289aa 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -74,7 +74,7 @@ #define KVM_GUEST_KUSEG 0x00000000UL #define KVM_GUEST_KSEG0 0x40000000UL #define KVM_GUEST_KSEG23 0x60000000UL -#define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0x60000000) +#define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0xe0000000) #define KVM_GUEST_CPHYSADDR(a) ((_ACAST32_(a)) & 0x1fffffff) #define KVM_GUEST_CKSEG0ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0) @@ -338,6 +338,7 @@ struct kvm_mips_tlb { #define KVM_MIPS_GUEST_TLB_SIZE 64 struct kvm_vcpu_arch { void *host_ebase, *guest_ebase; + int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); unsigned long host_stack; unsigned long host_gp; diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index b336037e8768..93c079a1cfc8 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -69,7 +69,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, PTE_ORDER); + pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); return pte; } @@ -79,7 +79,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); + pte = alloc_pages(GFP_KERNEL, PTE_ORDER); if (!pte) return NULL; clear_highpage(pte); @@ -113,7 +113,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { pmd_t *pmd; - pmd = (pmd_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PMD_ORDER); + pmd = (pmd_t *) __get_free_pages(GFP_KERNEL, PMD_ORDER); if (pmd) pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table); return pmd; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index a6b611f1da43..7d44e888134f 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -24,7 +24,7 @@ struct mm_struct; struct vm_area_struct; #define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_NO_READ | \ - _CACHE_CACHABLE_NONCOHERENT) + _page_cachable_default) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_WRITE | \ _page_cachable_default) #define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_NO_EXEC | \ @@ -476,7 +476,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) pte.pte_low &= (_PAGE_MODIFIED | _PAGE_ACCESSED | _PFNX_MASK); pte.pte_high &= (_PFN_MASK | _CACHE_MASK); pte.pte_low |= pgprot_val(newprot) & ~_PFNX_MASK; - pte.pte_high |= pgprot_val(newprot) & ~_PFN_MASK; + pte.pte_high |= pgprot_val(newprot) & ~(_PFN_MASK | _CACHE_MASK); return pte; } #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) @@ -491,7 +491,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #else static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | + (pgprot_val(newprot) & ~_PAGE_CHG_MASK)); } #endif @@ -632,7 +633,8 @@ static inline struct page *pmd_page(pmd_t pmd) static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | pgprot_val(newprot); + pmd_val(pmd) = (pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HUGE)) | + (pgprot_val(newprot) & ~_PAGE_CHG_MASK); return pmd; } diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 396df6eb0a12..645c8a1982a7 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1636,6 +1636,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, if (index < 0) { vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK); vcpu->arch.host_cp0_badvaddr = va; + vcpu->arch.pc = curr_pc; er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run, vcpu); preempt_enable(); @@ -1647,6 +1648,8 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, * invalid exception to the guest */ if (!TLB_IS_VALID(*tlb, va)) { + vcpu->arch.host_cp0_badvaddr = va; + vcpu->arch.pc = curr_pc; er = kvm_mips_emulate_tlbinv_ld(cause, NULL, run, vcpu); preempt_enable(); @@ -1666,7 +1669,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, cache, op, base, arch->gprs[base], offset); er = EMULATE_FAIL; preempt_enable(); - goto dont_update_pc; + goto done; } @@ -1694,16 +1697,20 @@ skip_fault: kvm_err("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n", cache, op, base, arch->gprs[base], offset); er = EMULATE_FAIL; - preempt_enable(); - goto dont_update_pc; } preempt_enable(); +done: + /* Rollback PC only if emulation was unsuccessful */ + if (er == EMULATE_FAIL) + vcpu->arch.pc = curr_pc; dont_update_pc: - /* Rollback PC */ - vcpu->arch.pc = curr_pc; -done: + /* + * This is for exceptions whose emulation updates the PC, so do not + * overwrite the PC under any circumstances + */ + return er; } diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h index 4ab4bdfad703..2143884709e4 100644 --- a/arch/mips/kvm/interrupt.h +++ b/arch/mips/kvm/interrupt.h @@ -28,6 +28,7 @@ #define MIPS_EXC_MAX 12 /* XXXSL More to follow */ +extern char __kvm_mips_vcpu_run_end[]; extern char mips32_exception[], mips32_exceptionEnd[]; extern char mips32_GuestException[], mips32_GuestExceptionEnd[]; diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 3ef03009de5f..828fcfc1cd7f 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -202,6 +202,7 @@ FEXPORT(__kvm_mips_load_k0k1) /* Jump to guest */ eret +EXPORT(__kvm_mips_vcpu_run_end) VECTOR(MIPSX(exception), unknown) /* Find out what mode we came from and jump to the proper handler. */ diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index dc052fb5c7a2..44da5259f390 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -315,6 +315,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) memcpy(gebase + offset, mips32_GuestException, mips32_GuestExceptionEnd - mips32_GuestException); +#ifdef MODULE + offset += mips32_GuestExceptionEnd - mips32_GuestException; + memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run, + __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run); + vcpu->arch.vcpu_run = gebase + offset; +#else + vcpu->arch.vcpu_run = __kvm_mips_vcpu_run; +#endif + /* Invalidate the icache for these ranges */ local_flush_icache_range((unsigned long)gebase, (unsigned long)gebase + ALIGN(size, PAGE_SIZE)); @@ -404,7 +413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Disable hardware page table walking while in guest */ htw_stop(); - r = __kvm_mips_vcpu_run(run, vcpu); + r = vcpu->arch.vcpu_run(run, vcpu); /* Re-enable HTW before enabling interrupts */ htw_start(); diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h index 4861a78c7160..f5f90bbf019d 100644 --- a/arch/mn10300/include/asm/thread_info.h +++ b/arch/mn10300/include/asm/thread_info.h @@ -115,7 +115,7 @@ static inline unsigned long current_stack_pointer(void) } #ifndef CONFIG_KGDB -void arch_release_thread_info(struct thread_info *ti); +void arch_release_thread_stack(unsigned long *stack); #endif #define get_thread_info(ti) get_task_struct((ti)->task) #define put_thread_info(ti) put_task_struct((ti)->task) diff --git a/arch/mn10300/kernel/kgdb.c b/arch/mn10300/kernel/kgdb.c index 99770823451a..2d7986c386fe 100644 --- a/arch/mn10300/kernel/kgdb.c +++ b/arch/mn10300/kernel/kgdb.c @@ -397,8 +397,9 @@ static bool kgdb_arch_undo_singlestep(struct pt_regs *regs) * single-step state is cleared. At this point the breakpoints should have * been removed by __switch_to(). */ -void arch_release_thread_info(struct thread_info *ti) +void arch_release_thread_stack(unsigned long *stack) { + struct thread_info *ti = (void *)stack; if (kgdb_sstep_thread == ti) { kgdb_sstep_thread = NULL; diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c index e77a7c728081..9577cf768875 100644 --- a/arch/mn10300/mm/pgtable.c +++ b/arch/mn10300/mm/pgtable.c @@ -63,7 +63,7 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL); if (pte) clear_page(pte); return pte; @@ -74,9 +74,9 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) struct page *pte; #ifdef CONFIG_HIGHPTE - pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0); + pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0); #else - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + pte = alloc_pages(GFP_KERNEL, 0); #endif if (!pte) return NULL; diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index 6e2985e0a7b9..bb47d08c8ef7 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, - PTE_ORDER); + pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); return pte; } @@ -53,7 +52,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); + pte = alloc_pages(GFP_KERNEL, PTE_ORDER); if (pte) { if (!pgtable_page_ctor(pte)) { __free_page(pte); diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index 21484e5b9e9a..87eebd185089 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -77,7 +77,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + pte = alloc_pages(GFP_KERNEL, 0); if (!pte) return NULL; clear_page(page_address(pte)); diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 62b08ef392be..5b2a95116e8f 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -122,7 +122,7 @@ pte_t __init_refok *pte_alloc_one_kernel(struct mm_struct *mm, pte_t *pte; if (likely(mem_init_done)) { - pte = (pte_t *) __get_free_page(GFP_KERNEL | __GFP_REPEAT); + pte = (pte_t *) __get_free_page(GFP_KERNEL); } else { pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); #if 0 diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index f2fd327dce2e..f08dda3f0995 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -63,8 +63,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT, - PMD_ORDER); + pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER); if (pmd) memset(pmd, 0, PAGE_SIZE< diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 937d4e247ac3..df294224e280 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -228,5 +228,20 @@ extern void radix__vmemmap_remove_mapping(unsigned long start, extern int radix__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t flags, unsigned int psz); + +static inline unsigned long radix__get_tree_size(void) +{ + unsigned long rts_field; + /* + * we support 52 bits, hence 52-31 = 21, 0b10101 + * RTS encoding details + * bits 0 - 3 of rts -> bits 6 - 8 unsigned long + * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long + */ + rts_field = (0x5UL << 5); /* 6 - 8 bits */ + rts_field |= (0x2UL << 61); + + return rts_field; +} #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 13ef38828dfe..3fa94fcac628 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -18,16 +18,19 @@ extern void radix__local_flush_tlb_mm(struct mm_struct *mm); extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid); +extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__tlb_flush(struct mmu_gather *tlb); #ifdef CONFIG_SMP extern void radix__flush_tlb_mm(struct mm_struct *mm); extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid); +extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); #else #define radix__flush_tlb_mm(mm) radix__local_flush_tlb_mm(mm) #define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr) #define radix___flush_tlb_page(mm,addr,p,i) radix___local_flush_tlb_page(mm,addr,p,i) +#define radix__flush_tlb_pwc(tlb, addr) radix__local_flush_tlb_pwc(tlb, addr) #endif #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index d98424ae356c..96e5769b18b0 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -72,5 +72,19 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, #define flush_tlb_mm(mm) local_flush_tlb_mm(mm) #define flush_tlb_page(vma, addr) local_flush_tlb_page(vma, addr) #endif /* CONFIG_SMP */ +/* + * flush the page walk cache for the address + */ +static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address) +{ + /* + * Flush the page table walk cache on freeing a page table. We already + * have marked the upper/higher level page table entry none by now. + * So it is safe to flush PWC here. + */ + if (!radix_enabled()) + return; + radix__flush_tlb_pwc(tlb, address); +} #endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h index 54f591e9572e..c0a69ae92256 100644 --- a/arch/powerpc/include/asm/book3s/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/pgalloc.h @@ -4,11 +4,6 @@ #include extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -static inline void tlb_flush_pgtable(struct mmu_gather *tlb, - unsigned long address) -{ - -} #ifdef CONFIG_PPC64 #include diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 069369f6414b..897d2e1c8a9b 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -57,8 +57,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -88,7 +87,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -190,8 +189,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 2714a3b81d24..d70101e1e25c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -642,13 +642,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (pe->type & EEH_PE_VF) { eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pci_hp_remove_devices(bus); pci_unlock_rescan_remove(); } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); + eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } /* @@ -692,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, */ edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - if (pe->type & EEH_PE_VF) + if (pe->type & EEH_PE_VF) { eeh_add_virt_device(edev, NULL); - else + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_hp_add_devices(bus); + } } else if (frozen_bus && rmv_data->removed) { pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); ssleep(5); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 4c9440629128..8bcc1b457115 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1399,11 +1399,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX) lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ mtlr r10 -BEGIN_MMU_FTR_SECTION - b 2f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) andi. r10,r12,MSR_RI /* check for unrecoverable exception */ +BEGIN_MMU_FTR_SECTION beq- 2f +FTR_SECTION_ELSE + b 2f +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) .machine push .machine "power4" diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3759df52bd67..a5ae49a2dcc4 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -47,7 +47,6 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - pci_io_base = ISA_IO_BASE; /* For now, override phys_mem_access_prot. If we need it,g * later, we may move that initialization to each ppc_md */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index e2f12cbcade9..0b93893424f5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index bf8f34a58670..b7019b559ddb 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 40e05e7f43de..f8a871a72985 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -316,8 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, DBG_LOW(" -> hit\n"); /* Update the HPTE */ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & - ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N | + ~(HPTE_R_PPP | HPTE_R_N)) | + (newpp & (HPTE_R_PPP | HPTE_R_N | HPTE_R_C))); } native_unlock_hpte(hptep); @@ -385,8 +385,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, /* Update the HPTE */ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & - ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N))); + ~(HPTE_R_PPP | HPTE_R_N)) | + (newpp & (HPTE_R_PPP | HPTE_R_N))); /* * Ensure it is out of the tlb too. Bolted entries base and * actual page size will be same. diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index b2740c67e172..2971ea18c768 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -201,9 +201,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) /* * We can't allow hardware to update hpte bits. Hence always * set 'R' bit and set 'C' if it is a write fault - * Memory coherence is always enabled */ - rflags |= HPTE_R_R | HPTE_R_M; + rflags |= HPTE_R_R; if (pteflags & _PAGE_DIRTY) rflags |= HPTE_R_C; @@ -213,10 +212,15 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT) rflags |= HPTE_R_I; - if ((pteflags & _PAGE_CACHE_CTL ) == _PAGE_NON_IDEMPOTENT) + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT) rflags |= (HPTE_R_I | HPTE_R_G); - if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) - rflags |= (HPTE_R_I | HPTE_R_W); + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) + rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M); + else + /* + * Add memory coherence if cache inhibited is not set + */ + rflags |= HPTE_R_M; return rflags; } @@ -918,6 +922,10 @@ void __init hash__early_init_mmu(void) vmemmap = (struct page *)H_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* Initialize the MMU Hash table and create the linear mapping * of memory. Has to be done before SLB initialization as this is * currently where the page size encoding is obtained. diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 5aac1a3f86cd..119d18611500 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -73,7 +73,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, cachep = PGT_CACHE(pdshift - pshift); #endif - new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT); + new = kmem_cache_zalloc(cachep, GFP_KERNEL); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 227b2a6c4544..196222227e82 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -65,7 +65,7 @@ static int radix__init_new_context(struct mm_struct *mm, int index) /* * set the process table entry, */ - rts_field = 3ull << PPC_BITLSHIFT(2); + rts_field = radix__get_tree_size(); process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE); return 0; } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index c939e6e57a9e..7931e1496f0d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -160,9 +160,8 @@ redo: process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT); /* * Fill in the process table. - * we support 52 bits, hence 52-28 = 24, 11000 */ - rts_field = 3ull << PPC_BITLSHIFT(2); + rts_field = radix__get_tree_size(); process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE); /* * Fill in the partition table. We are suppose to use effective address @@ -176,10 +175,8 @@ redo: static void __init radix_init_partition_table(void) { unsigned long rts_field; - /* - * we support 52 bits, hence 52-28 = 24, 11000 - */ - rts_field = 3ull << PPC_BITLSHIFT(2); + + rts_field = radix__get_tree_size(); BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large."); partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT); @@ -331,6 +328,11 @@ void __init radix__early_init_mmu(void) __vmalloc_end = RADIX_VMALLOC_END; vmemmap = (struct page *)RADIX_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; + +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* * For now radix also use the same frag size */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index bf7bf32b54f8..7f922f557936 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -84,7 +84,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add pte_t *pte; if (slab_is_available()) { - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); } else { pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); if (pte) @@ -97,7 +97,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *ptepage; - gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO; + gfp_t flags = GFP_KERNEL | __GFP_ZERO; ptepage = alloc_pages(flags, 0); if (!ptepage) diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index e009e0604a8a..f5e8d4edb808 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -350,8 +350,7 @@ static pte_t *get_from_cache(struct mm_struct *mm) static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) { void *ret = NULL; - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (!page) return NULL; if (!kernel && !pgtable_page_ctor(page)) { diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 54efba2fd66e..ab2f60e812e2 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -18,16 +18,20 @@ static DEFINE_RAW_SPINLOCK(native_tlbie_lock); -static inline void __tlbiel_pid(unsigned long pid, int set) +#define RIC_FLUSH_TLB 0 +#define RIC_FLUSH_PWC 1 +#define RIC_FLUSH_ALL 2 + +static inline void __tlbiel_pid(unsigned long pid, int set, + unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = PPC_BIT(53); /* IS = 1 */ rb |= set << PPC_BITLSHIFT(51); rs = ((unsigned long)pid) << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 2; /* invalidate all the caches */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |" @@ -39,25 +43,24 @@ static inline void __tlbiel_pid(unsigned long pid, int set) /* * We use 128 set in radix mode and 256 set in hpt mode. */ -static inline void _tlbiel_pid(unsigned long pid) +static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) { int set; for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) { - __tlbiel_pid(pid, set); + __tlbiel_pid(pid, set, ric); } return; } -static inline void _tlbie_pid(unsigned long pid) +static inline void _tlbie_pid(unsigned long pid, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = PPC_BIT(53); /* IS = 1 */ rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 2; /* invalidate all the caches */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |" @@ -67,16 +70,15 @@ static inline void _tlbie_pid(unsigned long pid) } static inline void _tlbiel_va(unsigned long va, unsigned long pid, - unsigned long ap) + unsigned long ap, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = va & ~(PPC_BITMASK(52, 63)); rb |= ap << PPC_BITLSHIFT(58); rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 0; /* no cluster flush yet */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |" @@ -86,16 +88,15 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, } static inline void _tlbie_va(unsigned long va, unsigned long pid, - unsigned long ap) + unsigned long ap, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = va & ~(PPC_BITMASK(52, 63)); rb |= ap << PPC_BITLSHIFT(58); rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 0; /* no cluster flush yet */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |" @@ -122,11 +123,26 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm) preempt_disable(); pid = mm->context.id; if (pid != MMU_NO_CONTEXT) - _tlbiel_pid(pid); + _tlbiel_pid(pid, RIC_FLUSH_ALL); preempt_enable(); } EXPORT_SYMBOL(radix__local_flush_tlb_mm); +void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +{ + unsigned long pid; + struct mm_struct *mm = tlb->mm; + + preempt_disable(); + + pid = mm->context.id; + if (pid != MMU_NO_CONTEXT) + _tlbiel_pid(pid, RIC_FLUSH_PWC); + + preempt_enable(); +} +EXPORT_SYMBOL(radix__local_flush_tlb_pwc); + void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid) { @@ -135,7 +151,7 @@ void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, preempt_disable(); pid = mm ? mm->context.id : 0; if (pid != MMU_NO_CONTEXT) - _tlbiel_va(vmaddr, pid, ap); + _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); preempt_enable(); } @@ -172,16 +188,42 @@ void radix__flush_tlb_mm(struct mm_struct *mm) if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_pid(pid); + _tlbie_pid(pid, RIC_FLUSH_ALL); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } else - _tlbiel_pid(pid); + _tlbiel_pid(pid, RIC_FLUSH_ALL); no_context: preempt_enable(); } EXPORT_SYMBOL(radix__flush_tlb_mm); +void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +{ + unsigned long pid; + struct mm_struct *mm = tlb->mm; + + preempt_disable(); + + pid = mm->context.id; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto no_context; + + if (!mm_is_core_local(mm)) { + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + + if (lock_tlbie) + raw_spin_lock(&native_tlbie_lock); + _tlbie_pid(pid, RIC_FLUSH_PWC); + if (lock_tlbie) + raw_spin_unlock(&native_tlbie_lock); + } else + _tlbiel_pid(pid, RIC_FLUSH_PWC); +no_context: + preempt_enable(); +} +EXPORT_SYMBOL(radix__flush_tlb_pwc); + void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid) { @@ -196,11 +238,11 @@ void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_va(vmaddr, pid, ap); + _tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } else - _tlbiel_va(vmaddr, pid, ap); + _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); bail: preempt_enable(); } @@ -224,7 +266,7 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_pid(0); + _tlbie_pid(0, RIC_FLUSH_ALL); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index 5e04f3cbd320..8ae236b0f80b 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc) " la %0,0\n" "1:\n" EX_TABLE(0b,1b) - : "=d" (rc), "=d" (orig_fpc) + : "=d" (rc), "=&d" (orig_fpc) : "d" (fpc), "0" (-EINVAL)); return rc; } diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 37b9017c6a96..ac82e8eb936d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -245,6 +245,7 @@ struct kvm_vcpu_stat { u32 exit_stop_request; u32 exit_validity; u32 exit_instruction; + u32 exit_pei; u32 halt_successful_poll; u32 halt_attempted_poll; u32 halt_poll_invalid; diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index f20abdb5630a..d14069d4b88d 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2064,12 +2064,5 @@ void s390_reset_system(void) S390_lowcore.program_new_psw.addr = (unsigned long) s390_base_pgm_handler; - /* - * Clear subchannel ID and number to signal new kernel that no CCW or - * SCSI IPL has been done (for kexec and kdump) - */ - S390_lowcore.subchannel_id = 0; - S390_lowcore.subchannel_nr = 0; - do_reset_calls(); } diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 59215c518f37..7ec63b1d920d 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -649,6 +649,8 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu) /* Performance monitoring unit for s390x */ static struct pmu cpumf_pmu = { + .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, .pmu_enable = cpumf_pmu_enable, .pmu_disable = cpumf_pmu_disable, .event_init = cpumf_pmu_event_init, @@ -708,12 +710,6 @@ static int __init cpumf_pmu_init(void) goto out; } - /* The CPU measurement counter facility does not have overflow - * interrupts to do sampling. Sampling must be provided by - * external means, for example, by timers. - */ - cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; - cpumf_pmu.attr_groups = cpumf_cf_event_group(); rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); if (rc) { diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 2e6b54e4d3f9..252157181302 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -341,6 +341,8 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) static int handle_partial_execution(struct kvm_vcpu *vcpu) { + vcpu->stat.exit_pei++; + if (vcpu->arch.sie_block->ipa == 0xb254) /* MVPG */ return handle_mvpg_pei(vcpu); if (vcpu->arch.sie_block->ipa >> 8 == 0xae) /* SIGP */ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6d8ec3ac9dd8..43f2a2b80490 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -61,6 +61,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "exit_external_request", VCPU_STAT(exit_external_request) }, { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) }, { "exit_instruction", VCPU_STAT(exit_instruction) }, + { "exit_pei", VCPU_STAT(exit_pei) }, { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, @@ -657,7 +658,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr) kvm->arch.model.cpuid = proc->cpuid; lowest_ibc = sclp.ibc >> 16 & 0xfff; unblocked_ibc = sclp.ibc & 0xfff; - if (lowest_ibc) { + if (lowest_ibc && proc->ibc) { if (proc->ibc > unblocked_ibc) kvm->arch.model.ibc = unblocked_ibc; else if (proc->ibc < lowest_ibc) diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index e8b5962ac12a..e2565d2d0c32 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -169,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) return table; } /* Allocate a fresh page */ - page = alloc_page(GFP_KERNEL|__GFP_REPEAT); + page = alloc_page(GFP_KERNEL); if (!page) return NULL; if (!pgtable_page_ctor(page)) { diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 4324b87f9398..9f0ce0e6eeb4 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -437,7 +437,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr, pgste = pgste_get_lock(ptep); pgstev = pgste_val(pgste); pte = *ptep; - if (pte_swap(pte) && + if (!reset && pte_swap(pte) && ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED || (pgstev & _PGSTE_GPS_ZERO))) { ptep_zap_swap_entry(mm, pte_to_swp_entry(pte)); diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h index 2e067657db98..49b012d78c1a 100644 --- a/arch/score/include/asm/pgalloc.h +++ b/arch/score/include/asm/pgalloc.h @@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, - PTE_ORDER); + pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); return pte; } @@ -53,7 +52,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); + pte = alloc_pages(GFP_KERNEL, PTE_ORDER); if (!pte) return NULL; clear_highpage(pte); diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index a33673b3687d..f3f42c84c40f 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -34,7 +34,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -43,7 +43,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, struct page *page; void *pg; - pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); if (!pg) return NULL; page = virt_to_page(pg); diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c index 26e03a1f7ca4..a62bd8696779 100644 --- a/arch/sh/mm/pgtable.c +++ b/arch/sh/mm/pgtable.c @@ -1,7 +1,7 @@ #include #include -#define PGALLOC_GFP GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO static struct kmem_cache *pgd_cachep; #if PAGETABLE_LEVELS > 2 diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index 5e3187185b4a..3529f1378cd8 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -41,8 +41,7 @@ static inline void __pud_populate(pud_t *pud, pmd_t *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); + return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -52,8 +51,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(pgtable_cache, - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 14bb0d5ed3c6..aec508e37490 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2704,8 +2704,7 @@ void __flush_tlb_all(void) pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pte_t *pte = NULL; if (page) @@ -2717,8 +2716,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (!page) return NULL; if (!pgtable_page_ctor(page)) { diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index 4b7cef9e94e0..c1467ac59ce6 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -78,7 +78,7 @@ struct thread_info { #ifndef __ASSEMBLY__ -void arch_release_thread_info(struct thread_info *info); +void arch_release_thread_stack(unsigned long *stack); /* How to get the thread information struct from C. */ register unsigned long stack_pointer __asm__("sp"); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 6b705ccc9cc1..a465d8372edd 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -73,8 +73,9 @@ void arch_cpu_idle(void) /* * Release a thread_info structure */ -void arch_release_thread_info(struct thread_info *info) +void arch_release_thread_stack(unsigned long *stack) { + struct thread_info *info = (void *)stack; struct single_step_state *step_state = info->step_state; if (step_state) { diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c index 7bf2491a9c1f..c4d5bf841a7f 100644 --- a/arch/tile/mm/pgtable.c +++ b/arch/tile/mm/pgtable.c @@ -231,7 +231,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address, int order) { - gfp_t flags = GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO; + gfp_t flags = GFP_KERNEL|__GFP_ZERO; struct page *p; int i; diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index b2a2dff50b4e..e7437ec62710 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -204,7 +204,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { pte_t *pte; - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return pte; } @@ -212,7 +212,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = alloc_page(GFP_KERNEL|__GFP_ZERO); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h index 2e02d1356fdf..26775793c204 100644 --- a/arch/unicore32/include/asm/pgalloc.h +++ b/arch/unicore32/include/asm/pgalloc.h @@ -28,7 +28,7 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd); #define pgd_alloc(mm) get_pgd_slow(mm) #define pgd_free(mm, pgd) free_pgd_slow(mm, pgd) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) /* * Allocate one PTE table. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0a7b885964ba..d9a94da0c29f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2439,6 +2439,15 @@ config PCI_CNB20LE_QUIRK source "drivers/pci/Kconfig" +config ISA_BUS + bool "ISA-style bus support on modern systems" if EXPERT + select ISA_BUS_API + help + Enables ISA-style drivers on modern systems. This is necessary to + support PC/104 devices on X86_64 platforms. + + If unsure, say N. + # x86_64 have no ISA slots, but can have ISA-style DMA. config ISA_DMA_API bool "ISA-style DMA support" if (X86_64 && EXPERT) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 33787ee817f0..91eac39625be 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -263,7 +263,7 @@ static bool check_hw_exists(void) msr_fail: pr_cont("Broken PMU hardware detected, using software events only.\n"); - pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, reg, val_new); @@ -2319,7 +2319,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; - const void __user *fp; + const unsigned long __user *fp; if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ @@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; - fp = (void __user *)regs->bp; + fp = (unsigned long __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; + frame.next_frame = NULL; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, 16)) + if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2)) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); if (bytes != 0) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); + bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); if (bytes != 0) break; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 3660b2cf245a..06c2baa51814 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,8 +1,8 @@ obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o -obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o -intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o +intel-rapl-perf-objs := rapl.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7c666958a625..9b4f9d3ce465 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc6, 0xf), /* FRONTEND_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = { /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4a413485f9eb..c64b1e9c5d1a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,10 +301,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +308,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 4421b5da409d..d1d1e5094c28 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -38,12 +38,11 @@ typedef u8 kprobe_opcode_t; #define RELATIVECALL_OPCODE 0xe8 #define RELATIVE_ADDR_SIZE 4 #define MAX_STACK_SIZE 64 -#define MIN_STACK_SIZE(ADDR) \ - (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \ - THREAD_SIZE - (unsigned long)(ADDR))) \ - ? (MAX_STACK_SIZE) \ - : (((unsigned long)current_thread_info()) + \ - THREAD_SIZE - (unsigned long)(ADDR))) +#define CUR_STACK_SIZE(ADDR) \ + (current_top_of_stack() - (unsigned long)(ADDR)) +#define MIN_STACK_SIZE(ADDR) \ + (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ? \ + MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR)) #define flush_insn_slot(p) do { } while (0) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e0fbe7e70dc1..69e62862b622 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -27,6 +27,7 @@ #include #include +#include #include #include #include @@ -1368,4 +1369,14 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} +static inline int kvm_cpu_get_apicid(int mps_cpu) +{ +#ifdef CONFIG_X86_LOCAL_APIC + return __default_cpu_present_to_apicid(mps_cpu); +#else + WARN_ON_ONCE(1); + return BAD_APICID; +#endif +} + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index bf7f8b55b0f9..574c23cf761a 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -81,7 +81,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; - page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { @@ -125,7 +125,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return (pud_t *)get_zeroed_page(GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index fdcc04020636..7c1c89598688 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -68,30 +68,23 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) return product; } -static __always_inline -u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) -{ - u64 delta = rdtsc_ordered() - src->tsc_timestamp; - return pvclock_scale_delta(delta, src->tsc_to_system_mul, - src->tsc_shift); -} - static __always_inline unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, cycle_t *cycles, u8 *flags) { unsigned version; - cycle_t ret, offset; - u8 ret_flags; + cycle_t offset; + u64 delta; version = src->version; + /* Make the latest version visible */ + smp_rmb(); - offset = pvclock_get_nsec_offset(src); - ret = src->system_time + offset; - ret_flags = src->flags; - - *cycles = ret; - *flags = ret_flags; + delta = rdtsc_ordered() - src->tsc_timestamp; + offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); + *cycles = src->system_time + offset; + *flags = src->flags; return version; } diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 66b057306f40..7427ca895a27 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -135,6 +135,7 @@ int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_disable(void); int common_cpu_die(unsigned int cpu); void native_cpu_die(unsigned int cpu); +void hlt_play_dead(void); void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 7c247e7404be..0944218af9e2 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -14,7 +14,7 @@ extern int kstack_depth_to_print; struct thread_info; struct stacktrace_ops; -typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo, +typedef unsigned long (*walk_stack_t)(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, @@ -23,13 +23,13 @@ typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo, int *graph); extern unsigned long -print_context_stack(struct thread_info *tinfo, +print_context_stack(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph); extern unsigned long -print_context_stack_bp(struct thread_info *tinfo, +print_context_stack_bp(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index a147e676fc7b..e991d5c8bb3a 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 2bb25c3fe2e8..ef8017ca5ba9 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -42,16 +42,14 @@ void printk_address(unsigned long address) static void print_ftrace_graph_addr(unsigned long addr, void *data, const struct stacktrace_ops *ops, - struct thread_info *tinfo, int *graph) + struct task_struct *task, int *graph) { - struct task_struct *task; unsigned long ret_addr; int index; if (addr != (unsigned long)return_to_handler) return; - task = tinfo->task; index = task->curr_ret_stack; if (!task->ret_stack || index < *graph) @@ -68,7 +66,7 @@ print_ftrace_graph_addr(unsigned long addr, void *data, static inline void print_ftrace_graph_addr(unsigned long addr, void *data, const struct stacktrace_ops *ops, - struct thread_info *tinfo, int *graph) + struct task_struct *task, int *graph) { } #endif @@ -79,10 +77,10 @@ print_ftrace_graph_addr(unsigned long addr, void *data, * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -static inline int valid_stack_ptr(struct thread_info *tinfo, +static inline int valid_stack_ptr(struct task_struct *task, void *p, unsigned int size, void *end) { - void *t = tinfo; + void *t = task_stack_page(task); if (end) { if (p < end && p >= (end-THREAD_SIZE)) return 1; @@ -93,14 +91,14 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, } unsigned long -print_context_stack(struct thread_info *tinfo, +print_context_stack(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph) { struct stack_frame *frame = (struct stack_frame *)bp; - while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) { + while (valid_stack_ptr(task, stack, sizeof(*stack), end)) { unsigned long addr; addr = *stack; @@ -112,7 +110,7 @@ print_context_stack(struct thread_info *tinfo, } else { ops->address(data, addr, 0); } - print_ftrace_graph_addr(addr, data, ops, tinfo, graph); + print_ftrace_graph_addr(addr, data, ops, task, graph); } stack++; } @@ -121,7 +119,7 @@ print_context_stack(struct thread_info *tinfo, EXPORT_SYMBOL_GPL(print_context_stack); unsigned long -print_context_stack_bp(struct thread_info *tinfo, +print_context_stack_bp(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph) @@ -129,7 +127,7 @@ print_context_stack_bp(struct thread_info *tinfo, struct stack_frame *frame = (struct stack_frame *)bp; unsigned long *ret_addr = &frame->return_address; - while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) { + while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) { unsigned long addr = *ret_addr; if (!__kernel_text_address(addr)) @@ -139,7 +137,7 @@ print_context_stack_bp(struct thread_info *tinfo, break; frame = frame->next_frame; ret_addr = &frame->return_address; - print_ftrace_graph_addr(addr, data, ops, tinfo, graph); + print_ftrace_graph_addr(addr, data, ops, task, graph); } return (unsigned long)frame; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 464ffd69b92e..fef917e79b9d 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -61,15 +61,13 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, bp = stack_frame(task, regs); for (;;) { - struct thread_info *context; void *end_stack; end_stack = is_hardirq_stack(stack, cpu); if (!end_stack) end_stack = is_softirq_stack(stack, cpu); - context = task_thread_info(task); - bp = ops->walk_stack(context, stack, bp, ops, data, + bp = ops->walk_stack(task, stack, bp, ops, data, end_stack, &graph); /* Stop if not on irq stack */ diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 5f1c6266eb30..d558a8a49016 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -153,7 +153,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); - struct thread_info *tinfo; unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); unsigned long dummy; unsigned used = 0; @@ -179,7 +178,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, * current stack address. If the stacks consist of nested * exceptions */ - tinfo = task_thread_info(task); while (!done) { unsigned long *stack_end; enum stack_type stype; @@ -202,7 +200,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, id) < 0) break; - bp = ops->walk_stack(tinfo, stack, bp, ops, + bp = ops->walk_stack(task, stack, bp, ops, data, stack_end, &graph); ops->stack(data, ""); /* @@ -218,7 +216,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, "IRQ") < 0) break; - bp = ops->walk_stack(tinfo, stack, bp, + bp = ops->walk_stack(task, stack, bp, ops, data, stack_end, &graph); /* * We link to the next stack (which would be @@ -240,7 +238,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, /* * This handles the process stack: */ - bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); + bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph); put_cpu(); } EXPORT_SYMBOL(dump_trace); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index bca14c899137..57b71373bae3 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include #include +#include +#include #include +#include +#include #include #include #include @@ -21,6 +25,9 @@ #include #include #include +#include + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -75,6 +82,13 @@ static void __init nvidia_bugs(int num, int slot, int func) { #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC + /* + * Only applies to Nvidia root ports (bus 0) and not to + * Nvidia graphics cards with PCI ports on secondary buses. + */ + if (num) + return; + /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. @@ -590,6 +604,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -603,12 +672,6 @@ struct chipset { void (*f)(int num, int slot, int func); }; -/* - * Only works for devices on the root bus. If you add any devices - * not on bus 0 readd another loop level in early_quirks(). But - * be careful because at least the Nvidia quirk here relies on - * only matching on bus 0. - */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -638,9 +701,13 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; +static void __init early_pci_scan_bus(int bus); + /** * check_dev_quirk - apply early quirks to a given PCI device * @num: bus number @@ -649,7 +716,7 @@ static struct chipset early_qrk[] __initdata = { * * Check the vendor & device ID against the early quirks table. * - * If the device is single function, let early_quirks() know so we don't + * If the device is single function, let early_pci_scan_bus() know so we don't * poke at this device again. */ static int __init check_dev_quirk(int num, int slot, int func) @@ -658,6 +725,7 @@ static int __init check_dev_quirk(int num, int slot, int func) u16 vendor; u16 device; u8 type; + u8 sec; int i; class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); @@ -685,25 +753,36 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); + + if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); + if (sec > num) + early_pci_scan_bus(sec); + } + if (!(type & 0x80)) return -1; return 0; } -void __init early_quirks(void) +static void __init early_pci_scan_bus(int bus) { int slot, func; - if (!early_pci_allowed()) - return; - /* Poor man's PCI discovery */ - /* Only scan the root bus */ for (slot = 0; slot < 32; slot++) for (func = 0; func < 8; func++) { /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(0, slot, func)) + if (check_dev_quirk(bus, slot, func)) break; } } + +void __init early_quirks(void) +{ + if (!early_pci_allowed()) + return; + + early_pci_scan_bus(0); +} diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 4d38416e2a7f..04f89caef9c4 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -57,7 +57,7 @@ # error "Need more than one PGD for the ESPFIX hack" #endif -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) /* This contains the *bottom* address of the espfix stack */ DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 38da8f29a9c8..c627bf8d98ad 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -130,11 +130,9 @@ void irq_ctx_init(int cpu) void do_softirq_own_stack(void) { - struct thread_info *curstk; struct irq_stack *irqstk; u32 *isp, *prev_esp; - curstk = current_stack(); irqstk = __this_cpu_read(softirq_stack); /* build the stack frame on the softirq stack */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 38cf7a741250..7847e5c0e0b5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -961,7 +961,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * normal page fault. */ regs->ip = (unsigned long)cur->addr; + /* + * Trap flag (TF) has been set here because this fault + * happened where the single stepping will be done. + * So clear it by resetting the current kprobe: + */ + regs->flags &= ~X86_EFLAGS_TF; + + /* + * If the TF flag was set before the kprobe hit, + * don't touch it: + */ regs->flags |= kcb->kprobe_old_flags; + if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 99bfc025111d..06c58ce46762 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -61,11 +61,16 @@ void pvclock_resume(void) u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) { unsigned version; - cycle_t ret; u8 flags; do { - version = __pvclock_read_cycles(src, &ret, &flags); + version = src->version; + /* Make the latest version visible */ + smp_rmb(); + + flags = src->flags; + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); return flags & valid_flags; @@ -80,6 +85,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fafe8b923cac..8264dfad9cf8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1622,7 +1622,7 @@ static inline void mwait_play_dead(void) } } -static inline void hlt_play_dead(void) +void hlt_play_dead(void) { if (__this_cpu_read(cpu_info.x86) >= 4) wbinvd(); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bbb5b283ff63..a397200281c1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1310,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(tsc_deadline - guest_tsc); + __delay(min(tsc_deadline - guest_tsc, + nsec_to_cycles(vcpu, lapic_timer_advance_ns))); } static void start_apic_timer(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1163e8173e5a..16ef31b87452 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -238,7 +238,9 @@ module_param(nested, int, S_IRUGO); /* enable / disable AVIC */ static int avic; +#ifdef CONFIG_X86_LOCAL_APIC module_param(avic, int, S_IRUGO); +#endif static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); @@ -981,11 +983,14 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); - if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC))) - avic = false; - - if (avic) - pr_info("AVIC enabled\n"); + if (avic) { + if (!npt_enabled || + !boot_cpu_has(X86_FEATURE_AVIC) || + !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) + avic = false; + else + pr_info("AVIC enabled\n"); + } return 0; @@ -1324,7 +1329,7 @@ free_avic: static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) { u64 entry; - int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu); + int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); if (!kvm_vcpu_apicv_active(vcpu)) @@ -1349,7 +1354,7 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; /* ID = 0xff (broadcast), ID > 0xff (reserved) */ - int h_physical_id = __default_cpu_present_to_apicid(cpu); + int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); if (!kvm_vcpu_apicv_active(vcpu)) @@ -4236,7 +4241,7 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) if (avic_vcpu_is_running(vcpu)) wrmsrl(SVM_AVIC_DOORBELL, - __default_cpu_present_to_apicid(vcpu->cpu)); + kvm_cpu_get_apicid(vcpu->cpu)); else kvm_vcpu_wake_up(vcpu); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index fb93010beaa4..64a79f271276 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) unsigned int dest; if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; do { @@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; /* Set SN when the vCPU is preempted */ @@ -6669,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6686,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); @@ -10714,7 +10715,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return 0; vcpu->pre_pcpu = vcpu->cpu; @@ -10780,7 +10782,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu) unsigned long flags; if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; do { @@ -10833,7 +10836,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, int idx, ret = -EINVAL; if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(kvm->vcpus[0])) return 0; idx = srcu_read_lock(&kvm->irq_srcu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 902d9da12392..7da5dd2057a9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1244,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); static unsigned long max_tsc_khz; -static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) -{ - return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, - vcpu->arch.virtual_tsc_shift); -} - static u32 adjust_tsc_khz(u32 khz, s32 ppm) { u64 v = (u64)khz * (1000000 + ppm); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7ce3634ab5fe..a82ca466b62e 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_X86_H #include +#include #include "kvm_cache_regs.h" #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL @@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns; extern struct static_key kvm_no_apic_vcpu; +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +{ + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); +} + /* Same "calling convention" as do_div: * - divide (n << 32) by base * - put result in n diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1b1110fa0057..0493c17b8a51 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -54,8 +54,8 @@ static int kasan_die_handler(struct notifier_block *self, void *data) { if (val == DIE_GPF) { - pr_emerg("CONFIG_KASAN_INLINE enabled"); - pr_emerg("GPF could be caused by NULL-ptr deref or user memory access"); + pr_emerg("CONFIG_KASAN_INLINE enabled\n"); + pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n"); } return NOTIFY_OK; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 4eb287e25043..aa0ff4b02a96 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,7 +6,7 @@ #include #include -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b2a4e2a61f6b..3cd69832d7f4 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -396,6 +396,7 @@ int __init pci_acpi_init(void) return -ENODEV; printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; x86_init.pci.init_irq = x86_init_noop; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 6e7242be1c87..b226b3f497f1 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -139,7 +139,7 @@ int __init efi_alloc_page_tables(void) if (efi_enabled(EFI_OLD_MEMMAP)) return 0; - gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO; + gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_page(gfp_mask); if (!efi_pgd) return -ENOMEM; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index d5f64996394a..b12c26e2e309 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -266,6 +267,35 @@ void notrace restore_processor_state(void) EXPORT_SYMBOL(restore_processor_state); #endif +#if defined(CONFIG_HIBERNATION) && defined(CONFIG_HOTPLUG_CPU) +static void resume_play_dead(void) +{ + play_dead_common(); + tboot_shutdown(TB_SHUTDOWN_WFS); + hlt_play_dead(); +} + +int hibernate_resume_nonboot_cpu_disable(void) +{ + void (*play_dead)(void) = smp_ops.play_dead; + int ret; + + /* + * Ensure that MONITOR/MWAIT will not be used in the "play dead" loop + * during hibernate image restoration, because it is likely that the + * monitored address will be actually written to at that time and then + * the "dead" CPU will attempt to execute instructions again, but the + * address in its instruction pointer may not be possible to resolve + * any more at that point (the page tables used by it previously may + * have been overwritten by hibernate image data). + */ + smp_ops.play_dead = resume_play_dead; + ret = disable_nonboot_cpus(); + smp_ops.play_dead = play_dead; + return ret; +} +#endif + /* * When bsp_check() is called in hibernate and suspend, cpu hotplug * is disabled already. So it's unnessary to handle race condition between diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 009947d419a6..f2b5e6a5cf95 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -19,6 +19,7 @@ #include #include #include +#include /* Defined in hibernate_asm_64.S */ extern asmlinkage __visible int restore_image(void); @@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void); * kernel's text (this value is passed in the image header). */ unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; /* * Value of the cr3 register from before the hibernation (this value is passed @@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible; pgd_t *temp_level4_pgt __visible; -void *relocated_restore_code __visible; +unsigned long relocated_restore_code __visible; + +static int set_up_temporary_text_mapping(void) +{ + pmd_t *pmd; + pud_t *pud; + + /* + * The new mapping only has to cover the page containing the image + * kernel's entry point (jump_address_phys), because the switch over to + * it is carried out by relocated code running from a page allocated + * specifically for this purpose and covered by the identity mapping, so + * the temporary kernel text mapping is only needed for the final jump. + * Moreover, in that mapping the virtual address of the image kernel's + * entry point must be the same as its virtual address in the image + * kernel (restore_jump_address), so the image kernel's + * restore_registers() code doesn't find itself in a different area of + * the virtual address space after switching over to the original page + * tables used by the image kernel. + */ + pud = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!pud) + return -ENOMEM; + + pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!pmd) + return -ENOMEM; + + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); + set_pud(pud + pud_index(restore_jump_address), + __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pgd(temp_level4_pgt + pgd_index(restore_jump_address), + __pgd(__pa(pud) | _KERNPG_TABLE)); + + return 0; +} static void *alloc_pgt_page(void *context) { @@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void) if (!temp_level4_pgt) return -ENOMEM; - /* It is safe to reuse the original kernel mapping */ - set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), - init_level4_pgt[pgd_index(__START_KERNEL_map)]); + /* Prepare a temporary mapping for the kernel text */ + result = set_up_temporary_text_mapping(); + if (result) + return result; /* Set up the direct mapping from scratch */ for (i = 0; i < nr_pfn_mapped; i++) { @@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void) return 0; } +static int relocate_restore_code(void) +{ + pgd_t *pgd; + pud_t *pud; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pud = pud_offset(pgd, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + } else { + pmd_t *pmd = pmd_offset(pud, relocated_restore_code); + + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + } else { + pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); + + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); + } + } + __flush_tlb_all(); + + return 0; +} + int swsusp_arch_resume(void) { int error; /* We have got enough memory and from now on we cannot recover */ - if ((error = set_up_temporary_mappings())) + error = set_up_temporary_mappings(); + if (error) return error; - relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - memcpy(relocated_restore_code, &core_restore_code, - &restore_registers - &core_restore_code); + error = relocate_restore_code(); + if (error) + return error; restore_image(); return 0; @@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn) struct restore_data_record { unsigned long jump_address; + unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; }; -#define RESTORE_MAGIC 0x0123456789ABCDEFUL +#define RESTORE_MAGIC 0x123456789ABCDEF0UL /** * arch_hibernation_header_save - populate the architecture specific part @@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) if (max_size < sizeof(struct restore_data_record)) return -EOVERFLOW; - rdr->jump_address = restore_jump_address; + rdr->jump_address = (unsigned long)&restore_registers; + rdr->jump_address_phys = __pa_symbol(&restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; return 0; @@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr) struct restore_data_record *rdr = addr; restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4400a43b9e28..3177c2bc26f6 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend) pushfq popq pt_regs_flags(%rax) - /* save the address of restore_registers */ - movq $restore_registers, %rax - movq %rax, restore_jump_address(%rip) /* save cr3 */ movq %cr3, %rax movq %rax, restore_cr3(%rip) @@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend) ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) - /* switch to temporary page tables */ - movq $__PAGE_OFFSET, %rdx - movq temp_level4_pgt(%rip), %rax - subq %rdx, %rax - movq %rax, %cr3 - /* Flush TLB */ - movq mmu_cr4_features(%rip), %rax - movq %rax, %rdx - andq $~(X86_CR4_PGE), %rdx - movq %rdx, %cr4; # turn off PGE - movq %cr3, %rcx; # flush TLB - movq %rcx, %cr3; - movq %rax, %cr4; # turn PGE back on - /* prepare to jump to the image kernel */ - movq restore_jump_address(%rip), %rax - movq restore_cr3(%rip), %rbx + movq restore_jump_address(%rip), %r8 + movq restore_cr3(%rip), %r9 + + /* prepare to switch to temporary page tables */ + movq temp_level4_pgt(%rip), %rax + movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ movq restore_pblist(%rip), %rdx + + /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx jmpq *%rcx /* code below has been relocated to a safe page */ ENTRY(core_restore_code) + /* switch to temporary page tables */ + movq $__PAGE_OFFSET, %rcx + subq %rcx, %rax + movq %rax, %cr3 + /* flush TLB */ + movq %rbx, %rcx + andq $~(X86_CR4_PGE), %rcx + movq %rcx, %cr4; # turn off PGE + movq %cr3, %rcx; # flush TLB + movq %rcx, %cr3; + movq %rbx, %cr4; # turn PGE back on .Lloop: testq %rdx, %rdx jz .Ldone @@ -96,24 +96,17 @@ ENTRY(core_restore_code) /* progress to the next pbe */ movq pbe_next(%rdx), %rdx jmp .Lloop + .Ldone: /* jump to the restore_registers address from the image header */ - jmpq *%rax - /* - * NOTE: This assumes that the boot kernel's text mapping covers the - * image kernel's page containing restore_registers and the address of - * this page is the same as in the image kernel's text mapping (it - * should always be true, because the text mapping is linear, starting - * from 0, and is supposed to cover the entire kernel text for every - * kernel). - * - * code below belongs to the image kernel - */ + jmpq *%r8 + /* code below belongs to the image kernel */ + .align PAGE_SIZE ENTRY(restore_registers) FRAME_BEGIN /* go back to the original page tables */ - movq %rbx, %cr3 + movq %r9, %cr3 /* Flush TLB, including "global" things (vmalloc) */ movq mmu_cr4_features(%rip), %rax diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 478a2de543a5..67433714b791 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr, /* NOTE: The loop is more greedy than the cleanup_highmap variant. * We include the PMD passed in on _both_ boundaries. */ - for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE)); + for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD)); pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; @@ -1551,41 +1551,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) #endif } -#ifdef CONFIG_X86_32 -static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) -{ - /* If there's an existing pte, then don't allow _PAGE_RW to be set */ - if (pte_val_ma(*ptep) & _PAGE_PRESENT) - pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & - pte_val_ma(pte)); - - return pte; -} -#else /* CONFIG_X86_64 */ -static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) -{ - unsigned long pfn; - - if (xen_feature(XENFEAT_writable_page_tables) || - xen_feature(XENFEAT_auto_translated_physmap) || - xen_start_info->mfn_list >= __START_KERNEL_map) - return pte; - - /* - * Pages belonging to the initial p2m list mapped outside the default - * address range must be mapped read-only. This region contains the - * page tables for mapping the p2m list, too, and page tables MUST be - * mapped read-only. - */ - pfn = pte_pfn(pte); - if (pfn >= xen_start_info->first_p2m_pfn && - pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) - pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW); - - return pte; -} -#endif /* CONFIG_X86_64 */ - /* * Init-time set_pte while constructing initial pagetables, which * doesn't allow RO page table pages to be remapped RW. @@ -1600,13 +1565,37 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) * so always write the PTE directly and rely on Xen trapping and * emulating any updates as necessary. */ -static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) +__visible pte_t xen_make_pte_init(pteval_t pte) { - if (pte_mfn(pte) != INVALID_P2M_ENTRY) - pte = mask_rw_pte(ptep, pte); - else - pte = __pte_ma(0); +#ifdef CONFIG_X86_64 + unsigned long pfn; + + /* + * Pages belonging to the initial p2m list mapped outside the default + * address range must be mapped read-only. This region contains the + * page tables for mapping the p2m list, too, and page tables MUST be + * mapped read-only. + */ + pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT; + if (xen_start_info->mfn_list < __START_KERNEL_map && + pfn >= xen_start_info->first_p2m_pfn && + pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) + pte &= ~_PAGE_RW; +#endif + pte = pte_pfn_to_mfn(pte); + return native_make_pte(pte); +} +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init); +static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) +{ +#ifdef CONFIG_X86_32 + /* If there's an existing pte, then don't allow _PAGE_RW to be set */ + if (pte_mfn(pte) != INVALID_P2M_ENTRY + && pte_val_ma(*ptep) & _PAGE_PRESENT) + pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & + pte_val_ma(pte)); +#endif native_set_pte(ptep, pte); } @@ -2407,6 +2396,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.alloc_pud = xen_alloc_pud; pv_mmu_ops.release_pud = xen_release_pud; #endif + pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte); #ifdef CONFIG_X86_64 pv_mmu_ops.write_cr3 = &xen_write_cr3; @@ -2455,7 +2445,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .pte_val = PV_CALLEE_SAVE(xen_pte_val), .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), - .make_pte = PV_CALLEE_SAVE(xen_make_pte), + .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), #ifdef CONFIG_X86_PAE diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index cab9f766bb06..dd2a49a8aacc 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -182,7 +182,7 @@ static void * __ref alloc_p2m_page(void) if (unlikely(!slab_is_available())) return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE); - return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT); + return (void *)__get_free_page(GFP_KERNEL); } static void __ref free_p2m_page(void *p) diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index d38eb9237e64..1065bc8bcae5 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -44,7 +44,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, pte_t *ptep; int i; - ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + ptep = (pte_t *)__get_free_page(GFP_KERNEL); if (!ptep) return NULL; for (i = 0; i < 1024; i++) diff --git a/block/ioprio.c b/block/ioprio.c index cc7800e9eb44..01b8116298a1 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -150,8 +150,10 @@ static int get_task_ioprio(struct task_struct *p) if (ret) goto out; ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM); + task_lock(p); if (p->io_context) ret = p->io_context->ioprio; + task_unlock(p); out: return ret; } diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c index 6a76d5c70ef6..9492e1c22d38 100644 --- a/crypto/asymmetric_keys/mscode_parser.c +++ b/crypto/asymmetric_keys/mscode_parser.c @@ -124,5 +124,10 @@ int mscode_note_digest(void *context, size_t hdrlen, struct pefile_context *ctx = context; ctx->digest = kmemdup(value, vlen, GFP_KERNEL); - return ctx->digest ? 0 : -ENOMEM; + if (!ctx->digest) + return -ENOMEM; + + ctx->digest_len = vlen; + + return 0; } diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index 44b746e9df1b..2ffd69769466 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -227,7 +227,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7, if (asymmetric_key_id_same(p->id, auth)) goto found_issuer_check_skid; } - } else { + } else if (sig->auth_ids[1]) { auth = sig->auth_ids[1]; pr_debug("- want %*phN\n", auth->len, auth->data); for (p = pkcs7->certs; p; p = p->next) { diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c index ac4bddf669de..19d1afb9890f 100644 --- a/crypto/asymmetric_keys/restrict.c +++ b/crypto/asymmetric_keys/restrict.c @@ -87,7 +87,7 @@ int restrict_link_by_signature(struct key *trust_keyring, sig = payload->data[asym_auth]; if (!sig->auth_ids[0] && !sig->auth_ids[1]) - return 0; + return -ENOKEY; if (ca_keyid && !asymmetric_key_id_partial(sig->auth_ids[1], ca_keyid)) return -EPERM; diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 43fe85f20d57..7097a3395b25 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -455,6 +455,7 @@ static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, }; diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c index ead8dc0d084e..8ba426635b1b 100644 --- a/crypto/rsa-pkcs1pad.c +++ b/crypto/rsa-pkcs1pad.c @@ -102,10 +102,10 @@ struct pkcs1pad_inst_ctx { }; struct pkcs1pad_request { - struct akcipher_request child_req; - struct scatterlist in_sg[3], out_sg[2]; uint8_t *in_buf, *out_buf; + + struct akcipher_request child_req; }; static int pkcs1pad_set_pub_key(struct crypto_akcipher *tfm, const void *key, diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c index 1f4128487dd4..dee86925a9a1 100644 --- a/drivers/acpi/acpi_dbg.c +++ b/drivers/acpi/acpi_dbg.c @@ -602,7 +602,7 @@ static int acpi_aml_read_user(char __user *buf, int len) crc->tail = (crc->tail + n) & (ACPI_AML_BUF_SIZE - 1); ret = n; out: - acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !ret); + acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, ret >= 0); return ret; } @@ -672,7 +672,7 @@ static int acpi_aml_write_user(const char __user *buf, int len) crc->head = (crc->head + n) & (ACPI_AML_BUF_SIZE - 1); ret = n; out: - acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !ret); + acpi_aml_unlock_fifo(ACPI_AML_IN_USER, ret >= 0); return n; } diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c index daceb80022b0..3b7fb99362b6 100644 --- a/drivers/acpi/acpica/hwregs.c +++ b/drivers/acpi/acpica/hwregs.c @@ -306,12 +306,6 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg) acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg) { u64 address; - u8 access_width; - u32 bit_width; - u8 bit_offset; - u64 value64; - u32 new_value32, old_value32; - u8 index; acpi_status status; ACPI_FUNCTION_NAME(hw_write); @@ -323,145 +317,23 @@ acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg) return (status); } - /* Convert access_width into number of bits based */ - - access_width = acpi_hw_get_access_bit_width(reg, 32); - bit_width = reg->bit_offset + reg->bit_width; - bit_offset = reg->bit_offset; - /* * Two address spaces supported: Memory or IO. PCI_Config is * not supported here because the GAS structure is insufficient */ - index = 0; - while (bit_width) { - /* - * Use offset style bit reads because "Index * AccessWidth" is - * ensured to be less than 32-bits by acpi_hw_validate_register(). - */ - new_value32 = ACPI_GET_BITS(&value, index * access_width, - ACPI_MASK_BITS_ABOVE_32 - (access_width)); - - if (bit_offset >= access_width) { - bit_offset -= access_width; - } else { - /* - * Use offset style bit masks because access_width is ensured - * to be less than 32-bits by acpi_hw_validate_register() and - * bit_offset/bit_width is less than access_width here. - */ - if (bit_offset) { - new_value32 &= ACPI_MASK_BITS_BELOW(bit_offset); - } - if (bit_width < access_width) { - new_value32 &= ACPI_MASK_BITS_ABOVE(bit_width); - } - - if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { - if (bit_offset || bit_width < access_width) { - /* - * Read old values in order not to modify the bits that - * are beyond the register bit_width/bit_offset setting. - */ - status = - acpi_os_read_memory((acpi_physical_address) - address + - index * - ACPI_DIV_8 - (access_width), - &value64, - access_width); - old_value32 = (u32)value64; - - /* - * Use offset style bit masks because access_width is - * ensured to be less than 32-bits by - * acpi_hw_validate_register() and bit_offset/bit_width is - * less than access_width here. - */ - if (bit_offset) { - old_value32 &= - ACPI_MASK_BITS_ABOVE - (bit_offset); - bit_offset = 0; - } - if (bit_width < access_width) { - old_value32 &= - ACPI_MASK_BITS_BELOW - (bit_width); - } - - new_value32 |= old_value32; - } - - value64 = (u64)new_value32; - status = - acpi_os_write_memory((acpi_physical_address) - address + - index * - ACPI_DIV_8 - (access_width), - value64, access_width); - } else { /* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */ - - if (bit_offset || bit_width < access_width) { - /* - * Read old values in order not to modify the bits that - * are beyond the register bit_width/bit_offset setting. - */ - status = - acpi_hw_read_port((acpi_io_address) - address + - index * - ACPI_DIV_8 - (access_width), - &old_value32, - access_width); - - /* - * Use offset style bit masks because access_width is - * ensured to be less than 32-bits by - * acpi_hw_validate_register() and bit_offset/bit_width is - * less than access_width here. - */ - if (bit_offset) { - old_value32 &= - ACPI_MASK_BITS_ABOVE - (bit_offset); - bit_offset = 0; - } - if (bit_width < access_width) { - old_value32 &= - ACPI_MASK_BITS_BELOW - (bit_width); - } - - new_value32 |= old_value32; - } - - status = acpi_hw_write_port((acpi_io_address) - address + - index * - ACPI_DIV_8 - (access_width), - new_value32, - access_width); - } - } - - /* - * Index * access_width is ensured to be less than 32-bits by - * acpi_hw_validate_register(). - */ - bit_width -= - bit_width > access_width ? access_width : bit_width; - index++; + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + status = acpi_os_write_memory((acpi_physical_address) + address, (u64)value, + reg->bit_width); + } else { /* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */ + + status = acpi_hw_write_port((acpi_io_address) + address, value, reg->bit_width); } ACPI_DEBUG_PRINT((ACPI_DB_IO, "Wrote: %8.8X width %2d to %8.8X%8.8X (%s)\n", - value, access_width, ACPI_FORMAT_UINT64(address), + value, reg->bit_width, ACPI_FORMAT_UINT64(address), acpi_ut_get_region_name(reg->space_id))); return (status); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 73c76d646064..290d6f5be44b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1331,8 +1331,6 @@ static int ec_install_handlers(struct acpi_ec *ec) static void ec_remove_handlers(struct acpi_ec *ec) { - acpi_ec_stop(ec, false); - if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_address_space_handler(ec->handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) @@ -1340,6 +1338,19 @@ static void ec_remove_handlers(struct acpi_ec *ec) clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } + /* + * Stops handling the EC transactions after removing the operation + * region handler. This is required because _REG(DISCONNECT) + * invoked during the removal can result in new EC transactions. + * + * Flushes the EC requests and thus disables the GPE before + * removing the GPE handler. This is required by the current ACPICA + * GPE core. ACPICA GPE core will automatically disable a GPE when + * it is indicated but there is no way to handle it. So the drivers + * must disable the GPEs prior to removing the GPE handlers. + */ + acpi_ec_stop(ec, false); + if (test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe, &acpi_ec_gpe_handler))) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 2215fc847fa9..1f0e06065ae6 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -928,7 +928,7 @@ static ssize_t format_show(struct device *dev, { struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev); - return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->code)); + return sprintf(buf, "0x%04x\n", le16_to_cpu(dcr->code)); } static DEVICE_ATTR_RO(format); @@ -961,8 +961,8 @@ static ssize_t format1_show(struct device *dev, continue; if (nfit_dcr->dcr->code == dcr->code) continue; - rc = sprintf(buf, "%#x\n", - be16_to_cpu(nfit_dcr->dcr->code)); + rc = sprintf(buf, "0x%04x\n", + le16_to_cpu(nfit_dcr->dcr->code)); break; } if (rc != ENXIO) @@ -1151,9 +1151,10 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, if (disable_vendor_specific) dsm_mask &= ~(1 << 8); } else { - dev_err(dev, "unknown dimm command family\n"); + dev_dbg(dev, "unknown dimm command family\n"); nfit_mem->family = -1; - return force_enable_dimms ? 0 : -ENODEV; + /* DSMs are optional, continue loading the driver... */ + return 0; } uuid = to_nfit_uuid(nfit_mem->family); diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h index 11cb38348aef..02b9ea1e8d2e 100644 --- a/drivers/acpi/nfit.h +++ b/drivers/acpi/nfit.h @@ -53,12 +53,12 @@ enum nfit_uuids { }; /* - * Region format interface codes are stored as an array of bytes in the - * NFIT DIMM Control Region structure + * Region format interface codes are stored with the interface as the + * LSB and the function as the MSB. */ -#define NFIT_FIC_BYTE cpu_to_be16(0x101) /* byte-addressable energy backed */ -#define NFIT_FIC_BLK cpu_to_be16(0x201) /* block-addressable non-energy backed */ -#define NFIT_FIC_BYTEN cpu_to_be16(0x301) /* byte-addressable non-energy backed */ +#define NFIT_FIC_BYTE cpu_to_le16(0x101) /* byte-addressable energy backed */ +#define NFIT_FIC_BLK cpu_to_le16(0x201) /* block-addressable non-energy backed */ +#define NFIT_FIC_BYTEN cpu_to_le16(0x301) /* byte-addressable non-energy backed */ enum { NFIT_BLK_READ_FLUSH = 1, diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 8fc7323ed3e8..c983bf733ad3 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -470,6 +470,7 @@ static int acpi_irq_pci_sharing_penalty(int irq) { struct acpi_pci_link *link; int penalty = 0; + int i; list_for_each_entry(link, &acpi_link_list, list) { /* @@ -478,18 +479,14 @@ static int acpi_irq_pci_sharing_penalty(int irq) */ if (link->irq.active && link->irq.active == irq) penalty += PIRQ_PENALTY_PCI_USING; - else { - int i; - - /* - * If a link is inactive, penalize the IRQs it - * might use, but not as severely. - */ - for (i = 0; i < link->irq.possible_count; i++) - if (link->irq.possible[i] == irq) - penalty += PIRQ_PENALTY_PCI_POSSIBLE / - link->irq.possible_count; - } + + /* + * penalize the IRQs PCI might use, but not as severely. + */ + for (i = 0; i < link->irq.possible_count; i++) + if (link->irq.possible[i] == irq) + penalty += PIRQ_PENALTY_PCI_POSSIBLE / + link->irq.possible_count; } return penalty; @@ -499,9 +496,6 @@ static int acpi_irq_get_penalty(int irq) { int penalty = 0; - if (irq < ACPI_MAX_ISA_IRQS) - penalty += acpi_isa_irq_penalty[irq]; - /* * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict * with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be @@ -516,10 +510,49 @@ static int acpi_irq_get_penalty(int irq) penalty += PIRQ_PENALTY_PCI_USING; } + if (irq < ACPI_MAX_ISA_IRQS) + return penalty + acpi_isa_irq_penalty[irq]; + penalty += acpi_irq_pci_sharing_penalty(irq); return penalty; } +int __init acpi_irq_penalty_init(void) +{ + struct acpi_pci_link *link; + int i; + + /* + * Update penalties to facilitate IRQ balancing. + */ + list_for_each_entry(link, &acpi_link_list, list) { + + /* + * reflect the possible and active irqs in the penalty table -- + * useful for breaking ties. + */ + if (link->irq.possible_count) { + int penalty = + PIRQ_PENALTY_PCI_POSSIBLE / + link->irq.possible_count; + + for (i = 0; i < link->irq.possible_count; i++) { + if (link->irq.possible[i] < ACPI_MAX_ISA_IRQS) + acpi_isa_irq_penalty[link->irq. + possible[i]] += + penalty; + } + + } else if (link->irq.active && + (link->irq.active < ACPI_MAX_ISA_IRQS)) { + acpi_isa_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_POSSIBLE; + } + } + + return 0; +} + static int acpi_irq_balance = -1; /* 0: static, 1: balance */ static int acpi_pci_link_allocate(struct acpi_pci_link *link) @@ -839,7 +872,7 @@ void acpi_penalize_isa_irq(int irq, int active) { if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty))) acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) + - active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING; + (active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING); } bool acpi_isa_irq_available(int irq) diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c index 6e702ab57220..1d31c0c0fc20 100644 --- a/drivers/ata/ahci_seattle.c +++ b/drivers/ata/ahci_seattle.c @@ -137,7 +137,7 @@ static const struct ata_port_info *ahci_seattle_get_port_info( u32 val; plat_data = devm_kzalloc(dev, sizeof(*plat_data), GFP_KERNEL); - if (IS_ERR(plat_data)) + if (!plat_data) return &ahci_port_info; plat_data->sgpio_ctrl = devm_ioremap_resource(dev, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 6be7770f68e9..31c183aed368 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4314,6 +4314,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { */ { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, + /* + * Device times out with higher max sects. + * https://bugzilla.kernel.org/show_bug.cgi?id=121671 + */ + { "LITEON CX1-JB256-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 61dc7a99e89a..c6f017458958 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host) ata_scsi_port_error_handler(host, ap); /* finish or retry handled scmd's and clean up */ - WARN_ON(host->host_failed || !list_empty(&eh_work_q)); + WARN_ON(!list_empty(&eh_work_q)); DPRINTK("EXIT\n"); } diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index bd74ee555278..745489a1c86a 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -986,7 +986,7 @@ static inline void mv_write_cached_reg(void __iomem *addr, u32 *old, u32 new) * Looks like a lot of fuss, but it avoids an unnecessary * +1 usec read-after-write delay for unaffected registers. */ - laddr = (long)addr & 0xffff; + laddr = (unsigned long)addr & 0xffff; if (laddr >= 0x300 && laddr <= 0x33c) { laddr &= 0x000f; if (laddr == 0x4 || laddr == 0xc) { diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 6b2a84e7f2be..2609ba20b396 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_DMA_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o -obj-$(CONFIG_ISA) += isa.o +obj-$(CONFIG_ISA_BUS_API) += isa.o obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o diff --git a/drivers/base/isa.c b/drivers/base/isa.c index 91dba65d7264..cd6ccdcf9df0 100644 --- a/drivers/base/isa.c +++ b/drivers/base/isa.c @@ -180,4 +180,4 @@ static int __init isa_bus_init(void) return error; } -device_initcall(isa_bus_init); +postcore_initcall(isa_bus_init); diff --git a/drivers/base/module.c b/drivers/base/module.c index db930d3ee312..2a215780eda2 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -24,10 +24,12 @@ static char *make_driver_name(struct device_driver *drv) static void module_create_drivers_dir(struct module_kobject *mk) { - if (!mk || mk->drivers_dir) - return; + static DEFINE_MUTEX(drivers_dir_mutex); - mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj); + mutex_lock(&drivers_dir_mutex); + if (mk && !mk->drivers_dir) + mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj); + mutex_unlock(&drivers_dir_mutex); } void module_add_driver(struct module *mod, struct device_driver *drv) diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index 3657ac1cb801..8e2e4757adcb 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -121,6 +121,7 @@ int pm_clk_add(struct device *dev, const char *con_id) { return __pm_clk_add(dev, con_id, NULL); } +EXPORT_SYMBOL_GPL(pm_clk_add); /** * pm_clk_add_clk - Start using a device clock for power management. @@ -136,8 +137,41 @@ int pm_clk_add_clk(struct device *dev, struct clk *clk) { return __pm_clk_add(dev, NULL, clk); } +EXPORT_SYMBOL_GPL(pm_clk_add_clk); +/** + * of_pm_clk_add_clk - Start using a device clock for power management. + * @dev: Device whose clock is going to be used for power management. + * @name: Name of clock that is going to be used for power management. + * + * Add the clock described in the 'clocks' device-tree node that matches + * with the 'name' provided, to the list of clocks used for the power + * management of @dev. On success, returns 0. Returns a negative error + * code if the clock is not found or cannot be added. + */ +int of_pm_clk_add_clk(struct device *dev, const char *name) +{ + struct clk *clk; + int ret; + + if (!dev || !dev->of_node || !name) + return -EINVAL; + + clk = of_clk_get_by_name(dev->of_node, name); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + ret = pm_clk_add_clk(dev, clk); + if (ret) { + clk_put(clk); + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(of_pm_clk_add_clk); + /** * of_pm_clk_add_clks - Start using device clock(s) for power management. * @dev: Device whose clock(s) is going to be used for power management. @@ -192,6 +226,7 @@ error: return ret; } +EXPORT_SYMBOL_GPL(of_pm_clk_add_clks); /** * __pm_clk_remove - Destroy PM clock entry. @@ -252,6 +287,7 @@ void pm_clk_remove(struct device *dev, const char *con_id) __pm_clk_remove(ce); } +EXPORT_SYMBOL_GPL(pm_clk_remove); /** * pm_clk_remove_clk - Stop using a device clock for power management. @@ -285,6 +321,7 @@ void pm_clk_remove_clk(struct device *dev, struct clk *clk) __pm_clk_remove(ce); } +EXPORT_SYMBOL_GPL(pm_clk_remove_clk); /** * pm_clk_init - Initialize a device's list of power management clocks. @@ -299,6 +336,7 @@ void pm_clk_init(struct device *dev) if (psd) INIT_LIST_HEAD(&psd->clock_list); } +EXPORT_SYMBOL_GPL(pm_clk_init); /** * pm_clk_create - Create and initialize a device's list of PM clocks. @@ -311,6 +349,7 @@ int pm_clk_create(struct device *dev) { return dev_pm_get_subsys_data(dev); } +EXPORT_SYMBOL_GPL(pm_clk_create); /** * pm_clk_destroy - Destroy a device's list of power management clocks. @@ -345,6 +384,7 @@ void pm_clk_destroy(struct device *dev) __pm_clk_remove(ce); } } +EXPORT_SYMBOL_GPL(pm_clk_destroy); /** * pm_clk_suspend - Disable clocks in a device's PM clock list. @@ -375,6 +415,7 @@ int pm_clk_suspend(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(pm_clk_suspend); /** * pm_clk_resume - Enable clocks in a device's PM clock list. @@ -400,6 +441,7 @@ int pm_clk_resume(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(pm_clk_resume); /** * pm_clk_notify - Notify routine for device addition and removal. @@ -480,6 +522,7 @@ int pm_clk_runtime_suspend(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(pm_clk_runtime_suspend); int pm_clk_runtime_resume(struct device *dev) { @@ -495,6 +538,7 @@ int pm_clk_runtime_resume(struct device *dev) return pm_generic_runtime_resume(dev); } +EXPORT_SYMBOL_GPL(pm_clk_runtime_resume); #else /* !CONFIG_PM_CLK */ @@ -598,3 +642,4 @@ void pm_clk_add_notifier(struct bus_type *bus, clknb->nb.notifier_call = pm_clk_notify; bus_register_notifier(bus, &clknb->nb); } +EXPORT_SYMBOL_GPL(pm_clk_add_notifier); diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index de23b648fce3..a1f2aff33997 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -187,8 +187,7 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth) struct gpd_link *link; int ret = 0; - if (genpd->status == GPD_STATE_ACTIVE - || (genpd->prepared_count > 0 && genpd->suspend_power_off)) + if (genpd->status == GPD_STATE_ACTIVE) return 0; /* @@ -735,81 +734,23 @@ static int pm_genpd_prepare(struct device *dev) mutex_lock(&genpd->lock); - if (genpd->prepared_count++ == 0) { + if (genpd->prepared_count++ == 0) genpd->suspended_count = 0; - genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF; - } mutex_unlock(&genpd->lock); - if (genpd->suspend_power_off) - return 0; - - /* - * The PM domain must be in the GPD_STATE_ACTIVE state at this point, - * so genpd_poweron() will return immediately, but if the device - * is suspended (e.g. it's been stopped by genpd_stop_dev()), we need - * to make it operational. - */ - pm_runtime_resume(dev); - __pm_runtime_disable(dev, false); - ret = pm_generic_prepare(dev); if (ret) { mutex_lock(&genpd->lock); - if (--genpd->prepared_count == 0) - genpd->suspend_power_off = false; + genpd->prepared_count--; mutex_unlock(&genpd->lock); - pm_runtime_enable(dev); } return ret; } -/** - * pm_genpd_suspend - Suspend a device belonging to an I/O PM domain. - * @dev: Device to suspend. - * - * Suspend a device under the assumption that its pm_domain field points to the - * domain member of an object of type struct generic_pm_domain representing - * a PM domain consisting of I/O devices. - */ -static int pm_genpd_suspend(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_suspend(dev); -} - -/** - * pm_genpd_suspend_late - Late suspend of a device from an I/O PM domain. - * @dev: Device to suspend. - * - * Carry out a late suspend of a device under the assumption that its - * pm_domain field points to the domain member of an object of type - * struct generic_pm_domain representing a PM domain consisting of I/O devices. - */ -static int pm_genpd_suspend_late(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_suspend_late(dev); -} - /** * pm_genpd_suspend_noirq - Completion of suspend of device in an I/O PM domain. * @dev: Device to suspend. @@ -820,6 +761,7 @@ static int pm_genpd_suspend_late(struct device *dev) static int pm_genpd_suspend_noirq(struct device *dev) { struct generic_pm_domain *genpd; + int ret; dev_dbg(dev, "%s()\n", __func__); @@ -827,11 +769,14 @@ static int pm_genpd_suspend_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - if (genpd->suspend_power_off - || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))) + if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)) return 0; - genpd_stop_dev(genpd, dev); + if (genpd->dev_ops.stop && genpd->dev_ops.start) { + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + } /* * Since all of the "noirq" callbacks are executed sequentially, it is @@ -853,6 +798,7 @@ static int pm_genpd_suspend_noirq(struct device *dev) static int pm_genpd_resume_noirq(struct device *dev) { struct generic_pm_domain *genpd; + int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -860,8 +806,7 @@ static int pm_genpd_resume_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - if (genpd->suspend_power_off - || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))) + if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)) return 0; /* @@ -872,93 +817,10 @@ static int pm_genpd_resume_noirq(struct device *dev) pm_genpd_sync_poweron(genpd, true); genpd->suspended_count--; - return genpd_start_dev(genpd, dev); -} - -/** - * pm_genpd_resume_early - Early resume of a device in an I/O PM domain. - * @dev: Device to resume. - * - * Carry out an early resume of a device under the assumption that its - * pm_domain field points to the domain member of an object of type - * struct generic_pm_domain representing a power domain consisting of I/O - * devices. - */ -static int pm_genpd_resume_early(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_resume_early(dev); -} - -/** - * pm_genpd_resume - Resume of device in an I/O PM domain. - * @dev: Device to resume. - * - * Resume a device under the assumption that its pm_domain field points to the - * domain member of an object of type struct generic_pm_domain representing - * a power domain consisting of I/O devices. - */ -static int pm_genpd_resume(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_resume(dev); -} - -/** - * pm_genpd_freeze - Freezing a device in an I/O PM domain. - * @dev: Device to freeze. - * - * Freeze a device under the assumption that its pm_domain field points to the - * domain member of an object of type struct generic_pm_domain representing - * a power domain consisting of I/O devices. - */ -static int pm_genpd_freeze(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_freeze(dev); -} + if (genpd->dev_ops.stop && genpd->dev_ops.start) + ret = pm_runtime_force_resume(dev); -/** - * pm_genpd_freeze_late - Late freeze of a device in an I/O PM domain. - * @dev: Device to freeze. - * - * Carry out a late freeze of a device under the assumption that its - * pm_domain field points to the domain member of an object of type - * struct generic_pm_domain representing a power domain consisting of I/O - * devices. - */ -static int pm_genpd_freeze_late(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_freeze_late(dev); + return ret; } /** @@ -973,6 +835,7 @@ static int pm_genpd_freeze_late(struct device *dev) static int pm_genpd_freeze_noirq(struct device *dev) { struct generic_pm_domain *genpd; + int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -980,7 +843,10 @@ static int pm_genpd_freeze_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - return genpd->suspend_power_off ? 0 : genpd_stop_dev(genpd, dev); + if (genpd->dev_ops.stop && genpd->dev_ops.start) + ret = pm_runtime_force_suspend(dev); + + return ret; } /** @@ -993,6 +859,7 @@ static int pm_genpd_freeze_noirq(struct device *dev) static int pm_genpd_thaw_noirq(struct device *dev) { struct generic_pm_domain *genpd; + int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -1000,51 +867,10 @@ static int pm_genpd_thaw_noirq(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - return genpd->suspend_power_off ? - 0 : genpd_start_dev(genpd, dev); -} - -/** - * pm_genpd_thaw_early - Early thaw of device in an I/O PM domain. - * @dev: Device to thaw. - * - * Carry out an early thaw of a device under the assumption that its - * pm_domain field points to the domain member of an object of type - * struct generic_pm_domain representing a power domain consisting of I/O - * devices. - */ -static int pm_genpd_thaw_early(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_thaw_early(dev); -} - -/** - * pm_genpd_thaw - Thaw a device belonging to an I/O power domain. - * @dev: Device to thaw. - * - * Thaw a device under the assumption that its pm_domain field points to the - * domain member of an object of type struct generic_pm_domain representing - * a power domain consisting of I/O devices. - */ -static int pm_genpd_thaw(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); + if (genpd->dev_ops.stop && genpd->dev_ops.start) + ret = pm_runtime_force_resume(dev); - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - return genpd->suspend_power_off ? 0 : pm_generic_thaw(dev); + return ret; } /** @@ -1057,6 +883,7 @@ static int pm_genpd_thaw(struct device *dev) static int pm_genpd_restore_noirq(struct device *dev) { struct generic_pm_domain *genpd; + int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -1072,30 +899,20 @@ static int pm_genpd_restore_noirq(struct device *dev) * At this point suspended_count == 0 means we are being run for the * first time for the given domain in the present cycle. */ - if (genpd->suspended_count++ == 0) { + if (genpd->suspended_count++ == 0) /* * The boot kernel might put the domain into arbitrary state, * so make it appear as powered off to pm_genpd_sync_poweron(), * so that it tries to power it on in case it was really off. */ genpd->status = GPD_STATE_POWER_OFF; - if (genpd->suspend_power_off) { - /* - * If the domain was off before the hibernation, make - * sure it will be off going forward. - */ - genpd_power_off(genpd, true); - - return 0; - } - } - - if (genpd->suspend_power_off) - return 0; pm_genpd_sync_poweron(genpd, true); - return genpd_start_dev(genpd, dev); + if (genpd->dev_ops.stop && genpd->dev_ops.start) + ret = pm_runtime_force_resume(dev); + + return ret; } /** @@ -1110,7 +927,6 @@ static int pm_genpd_restore_noirq(struct device *dev) static void pm_genpd_complete(struct device *dev) { struct generic_pm_domain *genpd; - bool run_complete; dev_dbg(dev, "%s()\n", __func__); @@ -1118,20 +934,15 @@ static void pm_genpd_complete(struct device *dev) if (IS_ERR(genpd)) return; + pm_generic_complete(dev); + mutex_lock(&genpd->lock); - run_complete = !genpd->suspend_power_off; - if (--genpd->prepared_count == 0) - genpd->suspend_power_off = false; + genpd->prepared_count--; + if (!genpd->prepared_count) + genpd_queue_power_off_work(genpd); mutex_unlock(&genpd->lock); - - if (run_complete) { - pm_generic_complete(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - pm_request_idle(dev); - } } /** @@ -1173,18 +984,10 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron); #else /* !CONFIG_PM_SLEEP */ #define pm_genpd_prepare NULL -#define pm_genpd_suspend NULL -#define pm_genpd_suspend_late NULL #define pm_genpd_suspend_noirq NULL -#define pm_genpd_resume_early NULL #define pm_genpd_resume_noirq NULL -#define pm_genpd_resume NULL -#define pm_genpd_freeze NULL -#define pm_genpd_freeze_late NULL #define pm_genpd_freeze_noirq NULL -#define pm_genpd_thaw_early NULL #define pm_genpd_thaw_noirq NULL -#define pm_genpd_thaw NULL #define pm_genpd_restore_noirq NULL #define pm_genpd_complete NULL @@ -1455,12 +1258,14 @@ EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain); * @genpd: PM domain object to initialize. * @gov: PM domain governor to associate with the domain (may be NULL). * @is_off: Initial value of the domain's power_is_off field. + * + * Returns 0 on successful initialization, else a negative error code. */ -void pm_genpd_init(struct generic_pm_domain *genpd, - struct dev_power_governor *gov, bool is_off) +int pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off) { if (IS_ERR_OR_NULL(genpd)) - return; + return -EINVAL; INIT_LIST_HEAD(&genpd->master_links); INIT_LIST_HEAD(&genpd->slave_links); @@ -1476,24 +1281,24 @@ void pm_genpd_init(struct generic_pm_domain *genpd, genpd->domain.ops.runtime_suspend = genpd_runtime_suspend; genpd->domain.ops.runtime_resume = genpd_runtime_resume; genpd->domain.ops.prepare = pm_genpd_prepare; - genpd->domain.ops.suspend = pm_genpd_suspend; - genpd->domain.ops.suspend_late = pm_genpd_suspend_late; + genpd->domain.ops.suspend = pm_generic_suspend; + genpd->domain.ops.suspend_late = pm_generic_suspend_late; genpd->domain.ops.suspend_noirq = pm_genpd_suspend_noirq; genpd->domain.ops.resume_noirq = pm_genpd_resume_noirq; - genpd->domain.ops.resume_early = pm_genpd_resume_early; - genpd->domain.ops.resume = pm_genpd_resume; - genpd->domain.ops.freeze = pm_genpd_freeze; - genpd->domain.ops.freeze_late = pm_genpd_freeze_late; + genpd->domain.ops.resume_early = pm_generic_resume_early; + genpd->domain.ops.resume = pm_generic_resume; + genpd->domain.ops.freeze = pm_generic_freeze; + genpd->domain.ops.freeze_late = pm_generic_freeze_late; genpd->domain.ops.freeze_noirq = pm_genpd_freeze_noirq; genpd->domain.ops.thaw_noirq = pm_genpd_thaw_noirq; - genpd->domain.ops.thaw_early = pm_genpd_thaw_early; - genpd->domain.ops.thaw = pm_genpd_thaw; - genpd->domain.ops.poweroff = pm_genpd_suspend; - genpd->domain.ops.poweroff_late = pm_genpd_suspend_late; + genpd->domain.ops.thaw_early = pm_generic_thaw_early; + genpd->domain.ops.thaw = pm_generic_thaw; + genpd->domain.ops.poweroff = pm_generic_poweroff; + genpd->domain.ops.poweroff_late = pm_generic_poweroff_late; genpd->domain.ops.poweroff_noirq = pm_genpd_suspend_noirq; genpd->domain.ops.restore_noirq = pm_genpd_restore_noirq; - genpd->domain.ops.restore_early = pm_genpd_resume_early; - genpd->domain.ops.restore = pm_genpd_resume; + genpd->domain.ops.restore_early = pm_generic_restore_early; + genpd->domain.ops.restore = pm_generic_restore; genpd->domain.ops.complete = pm_genpd_complete; if (genpd->flags & GENPD_FLAG_PM_CLK) { @@ -1518,6 +1323,8 @@ void pm_genpd_init(struct generic_pm_domain *genpd, mutex_lock(&gpd_list_lock); list_add(&genpd->gpd_list_node, &gpd_list); mutex_unlock(&gpd_list_lock); + + return 0; } EXPORT_SYMBOL_GPL(pm_genpd_init); diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c index 83d6e7ba1a34..8c3434bdb26d 100644 --- a/drivers/base/power/opp/cpu.c +++ b/drivers/base/power/opp/cpu.c @@ -211,7 +211,7 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, } /* Mark opp-table as multiple CPUs are sharing it now */ - opp_table->shared_opp = true; + opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED; } unlock: mutex_unlock(&opp_table_lock); @@ -227,7 +227,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus); * * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev. * - * Returns -ENODEV if OPP table isn't already present. + * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP + * table's status is access-unknown. * * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks @@ -249,9 +250,14 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) goto unlock; } + if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) { + ret = -EINVAL; + goto unlock; + } + cpumask_clear(cpumask); - if (opp_table->shared_opp) { + if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) { list_for_each_entry(opp_dev, &opp_table->dev_list, node) cpumask_set_cpu(opp_dev->dev->id, cpumask); } else { diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c index 94d2010558e3..1dfd3dd92624 100644 --- a/drivers/base/power/opp/of.c +++ b/drivers/base/power/opp/of.c @@ -34,7 +34,10 @@ static struct opp_table *_managed_opp(const struct device_node *np) * But the OPPs will be considered as shared only if the * OPP table contains a "opp-shared" property. */ - return opp_table->shared_opp ? opp_table : NULL; + if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) + return opp_table; + + return NULL; } } @@ -353,7 +356,10 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) } opp_table->np = opp_np; - opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared"); + if (of_property_read_bool(opp_np, "opp-shared")) + opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED; + else + opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE; mutex_unlock(&opp_table_lock); diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index 20f3be22e060..fabd5ca1a083 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -119,6 +119,12 @@ struct opp_device { #endif }; +enum opp_table_access { + OPP_TABLE_ACCESS_UNKNOWN = 0, + OPP_TABLE_ACCESS_EXCLUSIVE = 1, + OPP_TABLE_ACCESS_SHARED = 2, +}; + /** * struct opp_table - Device opp structure * @node: table node - contains the devices with OPPs that @@ -166,7 +172,7 @@ struct opp_table { /* For backward compatibility with v1 bindings */ unsigned int voltage_tolerance_v1; - bool shared_opp; + enum opp_table_access shared_opp; struct dev_pm_opp *suspend_opp; unsigned int *supported_hw; diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index b74690418504..e097d355cc04 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1045,10 +1045,14 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) */ if (!parent->power.disable_depth && !parent->power.ignore_children - && parent->power.runtime_status != RPM_ACTIVE) + && parent->power.runtime_status != RPM_ACTIVE) { + dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n", + dev_name(dev), + dev_name(parent)); error = -EBUSY; - else if (dev->power.runtime_status == RPM_SUSPENDED) + } else if (dev->power.runtime_status == RPM_SUSPENDED) { atomic_inc(&parent->power.child_count); + } spin_unlock(&parent->power.lock); @@ -1256,7 +1260,7 @@ void pm_runtime_allow(struct device *dev) dev->power.runtime_auto = true; if (atomic_dec_and_test(&dev->power.usage_count)) - rpm_idle(dev, RPM_AUTO); + rpm_idle(dev, RPM_AUTO | RPM_ASYNC); out: spin_unlock_irq(&dev->power.lock); @@ -1506,6 +1510,9 @@ int pm_runtime_force_resume(struct device *dev) goto out; } + if (!pm_runtime_status_suspended(dev)) + goto out; + ret = pm_runtime_set_active(dev); if (ret) goto out; diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index eda09090cb52..f642c4264c27 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -8,8 +8,6 @@ #include #include -#define BCMA_CORE_SIZE 0x1000 - #define bcma_err(bus, fmt, ...) \ pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_warn(bus, fmt, ...) \ diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index d597e432e195..ab19adb07a12 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -1750,7 +1750,7 @@ aoecmd_init(void) int ret; /* get_zeroed_page returns page with ref count 1 */ - p = (void *) get_zeroed_page(GFP_KERNEL | __GFP_REPEAT); + p = (void *) get_zeroed_page(GFP_KERNEL); if (!p) return -ENOMEM; empty_page = virt_to_page(p); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 2e6d1e9c3345..fcc5b4e0aef2 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -207,6 +207,9 @@ struct blkfront_info struct blk_mq_tag_set tag_set; struct blkfront_ring_info *rinfo; unsigned int nr_rings; + /* Save uncomplete reqs and bios for migration. */ + struct list_head requests; + struct bio_list bio_list; }; static unsigned int nr_minors; @@ -2002,69 +2005,22 @@ static int blkif_recover(struct blkfront_info *info) { unsigned int i, r_index; struct request *req, *n; - struct blk_shadow *copy; int rc; struct bio *bio, *cloned_bio; - struct bio_list bio_list, merge_bio; unsigned int segs, offset; int pending, size; struct split_bio *split_bio; - struct list_head requests; blkfront_gather_backend_features(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; blk_queue_max_segments(info->rq, segs); - bio_list_init(&bio_list); - INIT_LIST_HEAD(&requests); for (r_index = 0; r_index < info->nr_rings; r_index++) { - struct blkfront_ring_info *rinfo; - - rinfo = &info->rinfo[r_index]; - /* Stage 1: Make a safe copy of the shadow state. */ - copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow), - GFP_NOIO | __GFP_REPEAT | __GFP_HIGH); - if (!copy) - return -ENOMEM; - - /* Stage 2: Set up free list. */ - memset(&rinfo->shadow, 0, sizeof(rinfo->shadow)); - for (i = 0; i < BLK_RING_SIZE(info); i++) - rinfo->shadow[i].req.u.rw.id = i+1; - rinfo->shadow_free = rinfo->ring.req_prod_pvt; - rinfo->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff; + struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; rc = blkfront_setup_indirect(rinfo); - if (rc) { - kfree(copy); + if (rc) return rc; - } - - for (i = 0; i < BLK_RING_SIZE(info); i++) { - /* Not in use? */ - if (!copy[i].request) - continue; - - /* - * Get the bios in the request so we can re-queue them. - */ - if (copy[i].request->cmd_flags & - (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) { - /* - * Flush operations don't contain bios, so - * we need to requeue the whole request - */ - list_add(©[i].request->queuelist, &requests); - continue; - } - merge_bio.head = copy[i].request->bio; - merge_bio.tail = copy[i].request->biotail; - bio_list_merge(&bio_list, &merge_bio); - copy[i].request->bio = NULL; - blk_end_request_all(copy[i].request, 0); - } - - kfree(copy); } xenbus_switch_state(info->xbdev, XenbusStateConnected); @@ -2079,7 +2035,7 @@ static int blkif_recover(struct blkfront_info *info) kick_pending_request_queues(rinfo); } - list_for_each_entry_safe(req, n, &requests, queuelist) { + list_for_each_entry_safe(req, n, &info->requests, queuelist) { /* Requeue pending requests (flush or discard) */ list_del_init(&req->queuelist); BUG_ON(req->nr_phys_segments > segs); @@ -2087,7 +2043,7 @@ static int blkif_recover(struct blkfront_info *info) } blk_mq_kick_requeue_list(info->rq); - while ((bio = bio_list_pop(&bio_list)) != NULL) { + while ((bio = bio_list_pop(&info->bio_list)) != NULL) { /* Traverse the list of pending bios and re-queue them */ if (bio_segments(bio) > segs) { /* @@ -2133,9 +2089,42 @@ static int blkfront_resume(struct xenbus_device *dev) { struct blkfront_info *info = dev_get_drvdata(&dev->dev); int err = 0; + unsigned int i, j; dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename); + bio_list_init(&info->bio_list); + INIT_LIST_HEAD(&info->requests); + for (i = 0; i < info->nr_rings; i++) { + struct blkfront_ring_info *rinfo = &info->rinfo[i]; + struct bio_list merge_bio; + struct blk_shadow *shadow = rinfo->shadow; + + for (j = 0; j < BLK_RING_SIZE(info); j++) { + /* Not in use? */ + if (!shadow[j].request) + continue; + + /* + * Get the bios in the request so we can re-queue them. + */ + if (shadow[j].request->cmd_flags & + (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) { + /* + * Flush operations don't contain bios, so + * we need to requeue the whole request + */ + list_add(&shadow[j].request->queuelist, &info->requests); + continue; + } + merge_bio.head = shadow[j].request->bio; + merge_bio.tail = shadow[j].request->biotail; + bio_list_merge(&info->bio_list, &merge_bio); + shadow[j].request->bio = NULL; + blk_mq_end_request(shadow[j].request, 0); + } + } + blkif_free(info, info->connected == BLKIF_STATE_CONNECTED); err = negotiate_mq(info); diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 94fb407d8561..44b1bd6baa38 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3820,6 +3820,7 @@ static void handle_new_recv_msgs(ipmi_smi_t intf) while (!list_empty(&intf->waiting_rcv_msgs)) { smi_msg = list_entry(intf->waiting_rcv_msgs.next, struct ipmi_smi_msg, link); + list_del(&smi_msg->link); if (!run_to_completion) spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock, flags); @@ -3829,11 +3830,14 @@ static void handle_new_recv_msgs(ipmi_smi_t intf) if (rv > 0) { /* * To preserve message order, quit if we - * can't handle a message. + * can't handle a message. Add the message + * back at the head, this is safe because this + * tasklet is the only thing that pulls the + * messages. */ + list_add(&smi_msg->link, &intf->waiting_rcv_msgs); break; } else { - list_del(&smi_msg->link); if (rv == 0) /* Message handled */ ipmi_free_smi_msg(smi_msg); diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c index 10f846cc8db1..25d5906640c3 100644 --- a/drivers/clk/at91/clk-programmable.c +++ b/drivers/clk/at91/clk-programmable.c @@ -99,7 +99,7 @@ static int clk_programmable_set_parent(struct clk_hw *hw, u8 index) struct clk_programmable *prog = to_clk_programmable(hw); const struct clk_programmable_layout *layout = prog->layout; unsigned int mask = layout->css_mask; - unsigned int pckr = 0; + unsigned int pckr = index; if (layout->have_slck_mck) mask |= AT91_PMC_CSSMCK_MCK; diff --git a/drivers/clk/clk-oxnas.c b/drivers/clk/clk-oxnas.c index efba7d4dbcfc..79bcb2e42060 100644 --- a/drivers/clk/clk-oxnas.c +++ b/drivers/clk/clk-oxnas.c @@ -144,9 +144,9 @@ static int oxnas_stdclk_probe(struct platform_device *pdev) return -ENOMEM; regmap = syscon_node_to_regmap(of_get_parent(np)); - if (!regmap) { + if (IS_ERR(regmap)) { dev_err(&pdev->dev, "failed to have parent regmap\n"); - return -EINVAL; + return PTR_ERR(regmap); } for (i = 0; i < ARRAY_SIZE(clk_oxnas_init); i++) { diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c index 4bb130cd0062..05b3d73bfefa 100644 --- a/drivers/clk/rockchip/clk-cpu.c +++ b/drivers/clk/rockchip/clk-cpu.c @@ -321,9 +321,9 @@ struct clk *rockchip_clk_register_cpuclk(const char *name, } cclk = clk_register(NULL, &cpuclk->hw); - if (IS_ERR(clk)) { + if (IS_ERR(cclk)) { pr_err("%s: could not register cpuclk %s\n", __func__, name); - ret = PTR_ERR(clk); + ret = PTR_ERR(cclk); goto free_rate_table; } diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c index bc856f21f6b2..077fcdc7908b 100644 --- a/drivers/clk/rockchip/clk-mmc-phase.c +++ b/drivers/clk/rockchip/clk-mmc-phase.c @@ -41,8 +41,6 @@ static unsigned long rockchip_mmc_recalc(struct clk_hw *hw, #define ROCKCHIP_MMC_DEGREE_MASK 0x3 #define ROCKCHIP_MMC_DELAYNUM_OFFSET 2 #define ROCKCHIP_MMC_DELAYNUM_MASK (0xff << ROCKCHIP_MMC_DELAYNUM_OFFSET) -#define ROCKCHIP_MMC_INIT_STATE_RESET 0x1 -#define ROCKCHIP_MMC_INIT_STATE_SHIFT 1 #define PSECS_PER_SEC 1000000000000LL @@ -154,6 +152,7 @@ struct clk *rockchip_clk_register_mmc(const char *name, return ERR_PTR(-ENOMEM); init.name = name; + init.flags = 0; init.num_parents = num_parents; init.parent_names = parent_names; init.ops = &rockchip_mmc_clk_ops; @@ -162,15 +161,6 @@ struct clk *rockchip_clk_register_mmc(const char *name, mmc_clock->reg = reg; mmc_clock->shift = shift; - /* - * Assert init_state to soft reset the CLKGEN - * for mmc tuning phase and degree - */ - if (mmc_clock->shift == ROCKCHIP_MMC_INIT_STATE_SHIFT) - writel(HIWORD_UPDATE(ROCKCHIP_MMC_INIT_STATE_RESET, - ROCKCHIP_MMC_INIT_STATE_RESET, - mmc_clock->shift), mmc_clock->reg); - clk = clk_register(NULL, &mmc_clock->hw); if (IS_ERR(clk)) kfree(mmc_clock); diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index 291543f52caa..8059a8d3ea36 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -832,9 +832,9 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { RK3399_CLKGATE_CON(13), 1, GFLAGS), /* perihp */ - GATE(0, "cpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED, + GATE(0, "cpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED, RK3399_CLKGATE_CON(5), 0, GFLAGS), - GATE(0, "gpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED, + GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED, RK3399_CLKGATE_CON(5), 1, GFLAGS), COMPOSITE(ACLK_PERIHP, "aclk_perihp", mux_aclk_perihp_p, CLK_IGNORE_UNUSED, RK3399_CLKSEL_CON(14), 7, 1, MFLAGS, 0, 5, DFLAGS, @@ -1466,6 +1466,8 @@ static struct rockchip_clk_branch rk3399_clk_pmu_branches[] __initdata = { static const char *const rk3399_cru_critical_clocks[] __initconst = { "aclk_cci_pre", + "aclk_gic", + "aclk_gic_noc", "pclk_perilp0", "pclk_perilp0", "hclk_perilp0", @@ -1508,6 +1510,7 @@ static void __init rk3399_clk_init(struct device_node *np) ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS); if (IS_ERR(ctx)) { pr_err("%s: rockchip clk init failed\n", __func__); + iounmap(reg_base); return; } @@ -1553,6 +1556,7 @@ static void __init rk3399_pmu_clk_init(struct device_node *np) ctx = rockchip_clk_init(np, reg_base, CLKPMU_NR_CLKS); if (IS_ERR(ctx)) { pr_err("%s: rockchip pmu clk init failed\n", __func__); + iounmap(reg_base); return; } diff --git a/drivers/clk/sunxi/clk-sun4i-display.c b/drivers/clk/sunxi/clk-sun4i-display.c index 445a7498d6df..9780fac6d029 100644 --- a/drivers/clk/sunxi/clk-sun4i-display.c +++ b/drivers/clk/sunxi/clk-sun4i-display.c @@ -33,6 +33,8 @@ struct sun4i_a10_display_clk_data { u8 width_div; u8 width_mux; + + u32 flags; }; struct reset_data { @@ -166,7 +168,7 @@ static void __init sun4i_a10_display_init(struct device_node *node, data->has_div ? &div->hw : NULL, data->has_div ? &clk_divider_ops : NULL, &gate->hw, &clk_gate_ops, - 0); + data->flags); if (IS_ERR(clk)) { pr_err("%s: Couldn't register the clock\n", clk_name); goto free_div; @@ -232,6 +234,7 @@ static const struct sun4i_a10_display_clk_data sun4i_a10_tcon_ch0_data __initcon .offset_rst = 29, .offset_mux = 24, .width_mux = 2, + .flags = CLK_SET_RATE_PARENT, }; static void __init sun4i_a10_tcon_ch0_setup(struct device_node *node) diff --git a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c index 98a4582de56a..b6d29d1bedca 100644 --- a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c +++ b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c @@ -79,15 +79,11 @@ static int tcon_ch1_is_enabled(struct clk_hw *hw) static u8 tcon_ch1_get_parent(struct clk_hw *hw) { struct tcon_ch1_clk *tclk = hw_to_tclk(hw); - int num_parents = clk_hw_get_num_parents(hw); u32 reg; reg = readl(tclk->reg) >> TCON_CH1_SCLK2_MUX_SHIFT; reg &= reg >> TCON_CH1_SCLK2_MUX_MASK; - if (reg >= num_parents) - return -EINVAL; - return reg; } diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 15d06fcf0b50..b02f9c606e0b 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -56,11 +56,21 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; /* proc_event_counts is used as the sequence number of the netlink message */ static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 }; -static inline void get_seq(__u32 *ts, int *cpu) +static inline void send_msg(struct cn_msg *msg) { preempt_disable(); - *ts = __this_cpu_inc_return(proc_event_counts) - 1; - *cpu = smp_processor_id(); + + msg->seq = __this_cpu_inc_return(proc_event_counts) - 1; + ((struct proc_event *)msg->data)->cpu = smp_processor_id(); + + /* + * Preemption remains disabled during send to ensure the messages are + * ordered according to their sequence numbers. + * + * If cn_netlink_send() fails, the data is not sent. + */ + cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); + preempt_enable(); } @@ -77,7 +87,6 @@ void proc_fork_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_FORK; rcu_read_lock(); @@ -92,8 +101,7 @@ void proc_fork_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - /* If cn_netlink_send() failed, the data is not sent */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_exec_connector(struct task_struct *task) @@ -108,7 +116,6 @@ void proc_exec_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXEC; ev->event_data.exec.process_pid = task->pid; @@ -118,7 +125,7 @@ void proc_exec_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_id_connector(struct task_struct *task, int which_id) @@ -150,14 +157,13 @@ void proc_id_connector(struct task_struct *task, int which_id) return; } rcu_read_unlock(); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_sid_connector(struct task_struct *task) @@ -172,7 +178,6 @@ void proc_sid_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_SID; ev->event_data.sid.process_pid = task->pid; @@ -182,7 +187,7 @@ void proc_sid_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_ptrace_connector(struct task_struct *task, int ptrace_id) @@ -197,7 +202,6 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_PTRACE; ev->event_data.ptrace.process_pid = task->pid; @@ -215,7 +219,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_comm_connector(struct task_struct *task) @@ -230,7 +234,6 @@ void proc_comm_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COMM; ev->event_data.comm.process_pid = task->pid; @@ -241,7 +244,7 @@ void proc_comm_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_coredump_connector(struct task_struct *task) @@ -256,7 +259,6 @@ void proc_coredump_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; @@ -266,7 +268,7 @@ void proc_coredump_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_exit_connector(struct task_struct *task) @@ -281,7 +283,6 @@ void proc_exit_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXIT; ev->event_data.exit.process_pid = task->pid; @@ -293,7 +294,7 @@ void proc_exit_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } /* @@ -325,7 +326,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) msg->ack = rcvd_ack + 1; msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } /** diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 3646b143bbf5..0bb44d5b5df4 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -79,15 +79,16 @@ static const struct of_device_id machines[] __initconst = { static int __init cpufreq_dt_platdev_init(void) { struct device_node *np = of_find_node_by_path("/"); + const struct of_device_id *match; if (!np) return -ENODEV; - if (!of_match_node(machines, np)) + match = of_match_node(machines, np); + of_node_put(np); + if (!match) return -ENODEV; - of_node_put(of_root); - return PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt", -1, NULL, 0)); } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 9009295f5134..5617c7087d77 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2261,6 +2261,10 @@ int cpufreq_update_policy(unsigned int cpu) * -> ask driver for current freq and notify governors about a change */ if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { + if (cpufreq_suspended) { + ret = -EAGAIN; + goto unlock; + } new_policy.cur = cpufreq_update_current_freq(policy); if (WARN_ON(!new_policy.cur)) { ret = -EIO; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index e1b7a5e288f9..28690b284846 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -373,26 +373,9 @@ static bool intel_pstate_get_ppc_enable_status(void) return acpi_ppc; } -/* - * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and - * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and - * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state - * ratio, out of it only high 8 bits are used. For example 0x1700 is setting - * target ratio 0x17. The _PSS control value stores in a format which can be - * directly written to PERF_CTL MSR. But in intel_pstate driver this shift - * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()). - * This function converts the _PSS control value to intel pstate driver format - * for comparison and assignment. - */ -static int convert_to_native_pstate_format(struct cpudata *cpu, int index) -{ - return cpu->acpi_perf_data.states[index].control >> 8; -} - static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { struct cpudata *cpu; - int turbo_pss_ctl; int ret; int i; @@ -442,11 +425,10 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) * max frequency, which will cause a reduced performance as * this driver uses real max turbo frequency as the max * frequency. So correct this frequency in _PSS table to - * correct max turbo frequency based on the turbo ratio. + * correct max turbo frequency based on the turbo state. * Also need to convert to MHz as _PSS freq is in MHz. */ - turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0); - if (turbo_pss_ctl > cpu->pstate.max_pstate) + if (!limits->turbo_disabled) cpu->acpi_perf_data.states[0].core_frequency = policy->cpuinfo.max_freq / 1000; cpu->valid_pss_table = true; @@ -1419,6 +1401,9 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num) { struct cpudata *cpu = all_cpu_data[cpu_num]; + if (cpu->update_util_set) + return; + /* Prevent intel_pstate_update_util() from using stale data. */ cpu->sample.time = 0; cpufreq_add_update_util_hook(cpu_num, &cpu->update_util, @@ -1459,8 +1444,6 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) if (!policy->cpuinfo.max_freq) return -ENODEV; - intel_pstate_clear_update_util_hook(policy->cpu); - pr_debug("set_policy cpuinfo.max %u policy->max %u\n", policy->cpuinfo.max_freq, policy->max); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 808a320e9d5d..a7ecb9a84c15 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -487,7 +487,7 @@ static int __init pcc_cpufreq_probe(void) doorbell.space_id = reg_resource->space_id; doorbell.bit_width = reg_resource->bit_width; doorbell.bit_offset = reg_resource->bit_offset; - doorbell.access_width = 64; + doorbell.access_width = 4; doorbell.address = reg_resource->address; pr_debug("probe: doorbell: space_id is %d, bit_width is %d, " diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index a4d0059e232c..c73207abb5a4 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -173,7 +173,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, struct cpuidle_state *target_state = &drv->states[index]; bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); - u64 time_start, time_end; + ktime_t time_start, time_end; s64 diff; /* @@ -195,13 +195,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, sched_idle_set_state(target_state); trace_cpu_idle_rcuidle(index, dev->cpu); - time_start = local_clock(); + time_start = ns_to_ktime(local_clock()); stop_critical_timings(); entered_state = target_state->enter(dev, drv, index); start_critical_timings(); - time_end = local_clock(); + time_end = ns_to_ktime(local_clock()); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); /* The cpu is no longer idle or about to enter idle. */ @@ -217,11 +217,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, if (!cpuidle_state_is_coupled(drv, index)) local_irq_enable(); - /* - * local_clock() returns the time in nanosecond, let's shift - * by 10 (divide by 1024) to have microsecond based time. - */ - diff = (time_end - time_start) >> 10; + diff = ktime_us_delta(time_end, time_start); if (diff > INT_MAX) diff = INT_MAX; diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile index 6d74b91f2152..5fc3dbb9ada0 100644 --- a/drivers/crypto/qat/qat_common/Makefile +++ b/drivers/crypto/qat/qat_common/Makefile @@ -2,6 +2,7 @@ $(obj)/qat_rsapubkey-asn1.o: $(obj)/qat_rsapubkey-asn1.c \ $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \ $(obj)/qat_rsaprivkey-asn1.h +$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h clean-files += qat_rsaprivkey-asn1.c qat_rsaprivkey-asn1.h diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index 574e87c7f2b8..9acccad26928 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -781,7 +781,7 @@ static int hash_process_data(struct hash_device_data *device_data, &device_data->state); memmove(req_ctx->state.buffer, device_data->state.buffer, - HASH_BLOCK_SIZE / sizeof(u32)); + HASH_BLOCK_SIZE); if (ret) { dev_err(device_data->dev, "%s: hash_resume_state() failed!\n", @@ -832,7 +832,7 @@ static int hash_process_data(struct hash_device_data *device_data, memmove(device_data->state.buffer, req_ctx->state.buffer, - HASH_BLOCK_SIZE / sizeof(u32)); + HASH_BLOCK_SIZE); if (ret) { dev_err(device_data->dev, "%s: hash_save_state() failed!\n", __func__); diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c index 495577b6d31b..94ad5c0adbcb 100644 --- a/drivers/crypto/vmx/aes_cbc.c +++ b/drivers/crypto/vmx/aes_cbc.c @@ -182,7 +182,7 @@ struct crypto_alg p8_aes_cbc_alg = { .cra_name = "cbc(aes)", .cra_driver_name = "p8_aes_cbc", .cra_module = THIS_MODULE, - .cra_priority = 1000, + .cra_priority = 2000, .cra_type = &crypto_blkcipher_type, .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK, .cra_alignmask = 0, diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c index 0a3c1b04cf3c..38ed10d761d0 100644 --- a/drivers/crypto/vmx/aes_ctr.c +++ b/drivers/crypto/vmx/aes_ctr.c @@ -166,7 +166,7 @@ struct crypto_alg p8_aes_ctr_alg = { .cra_name = "ctr(aes)", .cra_driver_name = "p8_aes_ctr", .cra_module = THIS_MODULE, - .cra_priority = 1000, + .cra_priority = 2000, .cra_type = &crypto_blkcipher_type, .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK, .cra_alignmask = 0, diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl index 9f4994cabcc7..b18e67d0e065 100644 --- a/drivers/crypto/vmx/ppc-xlate.pl +++ b/drivers/crypto/vmx/ppc-xlate.pl @@ -141,7 +141,7 @@ my $vmr = sub { # Some ABIs specify vrsave, special-purpose register #256, as reserved # for system use. -my $no_vrsave = ($flavour =~ /aix|linux64le/); +my $no_vrsave = ($flavour =~ /linux-ppc64le/); my $mtspr = sub { my ($f,$idx,$ra) = @_; if ($idx == 256 && $no_vrsave) { diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index 78dac0e9da11..a5be56ec57f2 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -75,7 +75,7 @@ config DEVFREQ_GOV_PASSIVE comment "DEVFREQ Drivers" config ARM_EXYNOS_BUS_DEVFREQ - bool "ARM EXYNOS Generic Memory Bus DEVFREQ Driver" + tristate "ARM EXYNOS Generic Memory Bus DEVFREQ Driver" depends on ARCH_EXYNOS select DEVFREQ_GOV_SIMPLE_ONDEMAND select DEVFREQ_GOV_PASSIVE diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c index 39b048eda2ce..9aea2c7ecbe6 100644 --- a/drivers/devfreq/devfreq-event.c +++ b/drivers/devfreq/devfreq-event.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include #include @@ -481,13 +481,3 @@ static int __init devfreq_event_init(void) return 0; } subsys_initcall(devfreq_event_init); - -static void __exit devfreq_event_exit(void) -{ - class_destroy(devfreq_event_class); -} -module_exit(devfreq_event_exit); - -MODULE_AUTHOR("Chanwoo Choi "); -MODULE_DESCRIPTION("DEVFREQ-Event class support"); -MODULE_LICENSE("GPL"); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 1d6c803804d5..478006b7764a 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include #include @@ -268,8 +268,11 @@ int update_devfreq(struct devfreq *devfreq) devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE); err = devfreq->profile->target(devfreq->dev.parent, &freq, flags); - if (err) + if (err) { + freqs.new = cur_freq; + devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); return err; + } freqs.new = freq; devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); @@ -552,6 +555,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->profile = profile; strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN); devfreq->previous_freq = profile->initial_freq; + devfreq->last_status.current_frequency = profile->initial_freq; devfreq->data = data; devfreq->nb.notifier_call = devfreq_notifier_call; @@ -561,23 +565,22 @@ struct devfreq *devfreq_add_device(struct device *dev, mutex_lock(&devfreq->lock); } - devfreq->trans_table = devm_kzalloc(dev, sizeof(unsigned int) * - devfreq->profile->max_state * - devfreq->profile->max_state, - GFP_KERNEL); - devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) * - devfreq->profile->max_state, - GFP_KERNEL); - devfreq->last_stat_updated = jiffies; - dev_set_name(&devfreq->dev, "%s", dev_name(dev)); err = device_register(&devfreq->dev); if (err) { - put_device(&devfreq->dev); mutex_unlock(&devfreq->lock); goto err_out; } + devfreq->trans_table = devm_kzalloc(&devfreq->dev, sizeof(unsigned int) * + devfreq->profile->max_state * + devfreq->profile->max_state, + GFP_KERNEL); + devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) * + devfreq->profile->max_state, + GFP_KERNEL); + devfreq->last_stat_updated = jiffies; + srcu_init_notifier_head(&devfreq->transition_notifier_list); mutex_unlock(&devfreq->lock); @@ -603,7 +606,6 @@ struct devfreq *devfreq_add_device(struct device *dev, err_init: list_del(&devfreq->node); device_unregister(&devfreq->dev); - kfree(devfreq); err_out: return ERR_PTR(err); } @@ -621,7 +623,6 @@ int devfreq_remove_device(struct devfreq *devfreq) return -EINVAL; device_unregister(&devfreq->dev); - put_device(&devfreq->dev); return 0; } @@ -706,10 +707,12 @@ struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index) if (devfreq->dev.parent && devfreq->dev.parent->of_node == node) { mutex_unlock(&devfreq_list_lock); + of_node_put(node); return devfreq; } } mutex_unlock(&devfreq_list_lock); + of_node_put(node); return ERR_PTR(-EPROBE_DEFER); } @@ -1198,13 +1201,6 @@ static int __init devfreq_init(void) } subsys_initcall(devfreq_init); -static void __exit devfreq_exit(void) -{ - class_destroy(devfreq_class); - destroy_workqueue(devfreq_wq); -} -module_exit(devfreq_exit); - /* * The followings are helper functions for devfreq user device drivers with * OPP framework. @@ -1470,7 +1466,3 @@ void devm_devfreq_unregister_notifier(struct device *dev, devm_devfreq_dev_match, devfreq)); } EXPORT_SYMBOL(devm_devfreq_unregister_notifier); - -MODULE_AUTHOR("MyungJoo Ham "); -MODULE_DESCRIPTION("devfreq class support"); -MODULE_LICENSE("GPL"); diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig index 1e8b4f469f38..eb6f74a2b6b9 100644 --- a/drivers/devfreq/event/Kconfig +++ b/drivers/devfreq/event/Kconfig @@ -14,7 +14,7 @@ menuconfig PM_DEVFREQ_EVENT if PM_DEVFREQ_EVENT config DEVFREQ_EVENT_EXYNOS_NOCP - bool "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver" + tristate "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver" depends on ARCH_EXYNOS select PM_OPP help @@ -22,7 +22,7 @@ config DEVFREQ_EVENT_EXYNOS_NOCP (Network on Chip) Probe counters to measure the bandwidth of AXI bus. config DEVFREQ_EVENT_EXYNOS_PPMU - bool "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver" + tristate "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver" depends on ARCH_EXYNOS select PM_OPP help diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c index 6b6a5f310486..a5841403bde8 100644 --- a/drivers/devfreq/event/exynos-nocp.c +++ b/drivers/devfreq/event/exynos-nocp.c @@ -220,9 +220,6 @@ static int exynos_nocp_parse_dt(struct platform_device *pdev, /* Maps the memory mapped IO to control nocp register */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (IS_ERR(res)) - return PTR_ERR(res); - base = devm_ioremap_resource(dev, res); if (IS_ERR(base)) return PTR_ERR(base); diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c index f312485f1451..845bf25fb9fb 100644 --- a/drivers/devfreq/event/exynos-ppmu.c +++ b/drivers/devfreq/event/exynos-ppmu.c @@ -482,7 +482,8 @@ static int exynos_ppmu_probe(struct platform_device *pdev) if (!info->edev) { dev_err(&pdev->dev, "failed to allocate memory devfreq-event devices\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err; } edev = info->edev; platform_set_drvdata(pdev, info); diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c index 2363d0a189b7..29866f7e6d7e 100644 --- a/drivers/devfreq/exynos-bus.c +++ b/drivers/devfreq/exynos-bus.c @@ -383,7 +383,7 @@ err_clk: static int exynos_bus_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; + struct device_node *np = dev->of_node, *node; struct devfreq_dev_profile *profile; struct devfreq_simple_ondemand_data *ondemand_data; struct devfreq_passive_data *passive_data; @@ -407,7 +407,7 @@ static int exynos_bus_probe(struct platform_device *pdev) /* Parse the device-tree to get the resource information */ ret = exynos_bus_parse_of(np, bus); if (ret < 0) - goto err; + return ret; profile = devm_kzalloc(dev, sizeof(*profile), GFP_KERNEL); if (!profile) { @@ -415,10 +415,13 @@ static int exynos_bus_probe(struct platform_device *pdev) goto err; } - if (of_parse_phandle(dev->of_node, "devfreq", 0)) + node = of_parse_phandle(dev->of_node, "devfreq", 0); + if (node) { + of_node_put(node); goto passive; - else + } else { ret = exynos_bus_parent_parse_of(np, bus); + } if (ret < 0) goto err; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 8e304b1befc5..75bd6621dc5d 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -242,7 +242,7 @@ struct at_xdmac_lld { u32 mbr_dus; /* Destination Microblock Stride Register */ }; - +/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */ struct at_xdmac_desc { struct at_xdmac_lld lld; enum dma_transfer_direction direction; @@ -253,7 +253,7 @@ struct at_xdmac_desc { unsigned int xfer_size; struct list_head descs_list; struct list_head xfer_node; -}; +} __aligned(sizeof(u64)); static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb) { @@ -1400,6 +1400,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, u32 cur_nda, check_nda, cur_ubc, mask, value; u8 dwidth = 0; unsigned long flags; + bool initd; ret = dma_cookie_status(chan, cookie, txstate); if (ret == DMA_COMPLETE) @@ -1424,7 +1425,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, residue = desc->xfer_size; /* * Flush FIFO: only relevant when the transfer is source peripheral - * synchronized. + * synchronized. Flush is needed before reading CUBC because data in + * the FIFO are not reported by CUBC. Reporting a residue of the + * transfer length while we have data in FIFO can cause issue. + * Usecase: atmel USART has a timeout which means I have received + * characters but there is no more character received for a while. On + * timeout, it requests the residue. If the data are in the DMA FIFO, + * we will return a residue of the transfer length. It means no data + * received. If an application is waiting for these data, it will hang + * since we won't have another USART timeout without receiving new + * data. */ mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC; value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM; @@ -1435,34 +1445,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, } /* - * When processing the residue, we need to read two registers but we - * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where - * we stand in the descriptor list and AT_XDMAC_CUBC is used - * to know how many data are remaining for the current descriptor. - * Since the dma channel is not paused to not loose data, between the - * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of - * descriptor. - * For that reason, after reading AT_XDMAC_CUBC, we check if we are - * still using the same descriptor by reading a second time - * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to - * read again AT_XDMAC_CUBC. + * The easiest way to compute the residue should be to pause the DMA + * but doing this can lead to miss some data as some devices don't + * have FIFO. + * We need to read several registers because: + * - DMA is running therefore a descriptor change is possible while + * reading these registers + * - When the block transfer is done, the value of the CUBC register + * is set to its initial value until the fetch of the next descriptor. + * This value will corrupt the residue calculation so we have to skip + * it. + * + * INITD -------- ------------ + * |____________________| + * _______________________ _______________ + * NDA @desc2 \/ @desc3 + * _______________________/\_______________ + * __________ ___________ _______________ + * CUBC 0 \/ MAX desc1 \/ MAX desc2 + * __________/\___________/\_______________ + * + * Since descriptors are aligned on 64 bits, we can assume that + * the update of NDA and CUBC is atomic. * Memory barriers are used to ensure the read order of the registers. - * A max number of retries is set because unlikely it can never ends if - * we are transferring a lot of data with small buffers. + * A max number of retries is set because unlikely it could never ends. */ - cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; - rmb(); - cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) { - rmb(); check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; - - if (likely(cur_nda == check_nda)) - break; - - cur_nda = check_nda; + rmb(); + initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD); rmb(); cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + rmb(); + cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + rmb(); + + if ((check_nda == cur_nda) && initd) + break; } if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) { @@ -1470,6 +1489,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, goto spin_unlock; } + /* + * Flush FIFO: only relevant when the transfer is source peripheral + * synchronized. Another flush is needed here because CUBC is updated + * when the controller sends the data write command. It can lead to + * report data that are not written in the memory or the device. The + * FIFO flush ensures that data are really written. + */ + if ((desc->lld.mbr_cfg & mask) == value) { + at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask); + while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS)) + cpu_relax(); + } + /* * Remove size of all microblocks already transferred and the current * one. Then add the remaining size to transfer of the current diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 25d1dadcddd1..d0446a75990a 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -703,8 +703,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan) goto free_resources; } - src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0, - PAGE_SIZE, DMA_TO_DEVICE); + src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), + (size_t)src & ~PAGE_MASK, PAGE_SIZE, + DMA_TO_DEVICE); unmap->addr[0] = src_dma; ret = dma_mapping_error(dma_chan->device->dev, src_dma); @@ -714,8 +715,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan) } unmap->to_cnt = 1; - dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0, - PAGE_SIZE, DMA_FROM_DEVICE); + dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), + (size_t)dest & ~PAGE_MASK, PAGE_SIZE, + DMA_FROM_DEVICE); unmap->addr[1] = dest_dma; ret = dma_mapping_error(dma_chan->device->dev, dest_dma); diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 6744d88bdea8..4fb2eb7c800d 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -2378,22 +2378,19 @@ static int sbridge_get_onedevice(struct pci_dev **prev, * @num_mc: pointer to the memory controllers count, to be incremented in case * of success. * @table: model specific table - * @allow_dups: allow for multiple devices to exist with the same device id - * (as implemented, this isn't expected to work correctly in the - * multi-socket case). - * @multi_bus: don't assume devices on different buses belong to different - * memory controllers. * * returns 0 in case of success or error code */ -static int sbridge_get_all_devices_full(u8 *num_mc, - const struct pci_id_table *table, - int allow_dups, - int multi_bus) +static int sbridge_get_all_devices(u8 *num_mc, + const struct pci_id_table *table) { int i, rc; struct pci_dev *pdev = NULL; + int allow_dups = 0; + int multi_bus = 0; + if (table->type == KNIGHTS_LANDING) + allow_dups = multi_bus = 1; while (table && table->descr) { for (i = 0; i < table->n_devs; i++) { if (!allow_dups || i == 0 || @@ -2420,11 +2417,6 @@ static int sbridge_get_all_devices_full(u8 *num_mc, return 0; } -#define sbridge_get_all_devices(num_mc, table) \ - sbridge_get_all_devices_full(num_mc, table, 0, 0) -#define sbridge_get_all_devices_knl(num_mc, table) \ - sbridge_get_all_devices_full(num_mc, table, 1, 1) - static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, struct sbridge_dev *sbridge_dev) { diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c index 8b3226dca1d9..caff46c0e214 100644 --- a/drivers/extcon/extcon-palmas.c +++ b/drivers/extcon/extcon-palmas.c @@ -360,6 +360,8 @@ static int palmas_usb_probe(struct platform_device *pdev) palmas_enable_irq(palmas_usb); /* perform initial detection */ + if (palmas_usb->enable_gpio_vbus_detection) + palmas_vbus_irq_handler(palmas_usb->gpio_vbus_irq, palmas_usb); palmas_gpio_id_detect(&palmas_usb->wq_detectid.work); device_set_wakeup_capable(&pdev->dev, true); return 0; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index a116609b1914..d7860614f87f 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -49,7 +49,7 @@ config GPIO_DEVRES config OF_GPIO def_bool y - depends on OF || COMPILE_TEST + depends on OF config GPIO_ACPI def_bool y @@ -402,9 +402,12 @@ config GPIO_TB10X select OF_GPIO config GPIO_TEGRA - bool - default y + bool "NVIDIA Tegra GPIO support" + default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST + depends on OF + help + Say yes here to support GPIO pins on NVIDIA Tegra SoCs. config GPIO_TS4800 tristate "TS-4800 DIO blocks and compatibles" @@ -531,7 +534,7 @@ menu "Port-mapped I/O GPIO drivers" config GPIO_104_DIO_48E tristate "ACCES 104-DIO-48E GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the ACCES 104-DIO-48E series (104-DIO-48E, @@ -541,7 +544,7 @@ config GPIO_104_DIO_48E config GPIO_104_IDIO_16 tristate "ACCES 104-IDIO-16 GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the ACCES 104-IDIO-16 family (104-IDIO-16, @@ -552,7 +555,7 @@ config GPIO_104_IDIO_16 config GPIO_104_IDI_48 tristate "ACCES 104-IDI-48 GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the ACCES 104-IDI-48 family (104-IDI-48A, @@ -628,7 +631,7 @@ config GPIO_TS5500 config GPIO_WS16C48 tristate "WinSystems WS16C48 GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the WinSystems WS16C48. The base port diff --git a/drivers/gpio/gpio-104-idi-48.c b/drivers/gpio/gpio-104-idi-48.c index 6c75c83baf5a..2d2763ea1a68 100644 --- a/drivers/gpio/gpio-104-idi-48.c +++ b/drivers/gpio/gpio-104-idi-48.c @@ -247,6 +247,7 @@ static int idi_48_probe(struct device *dev, unsigned int id) idi48gpio->irq = irq[id]; spin_lock_init(&idi48gpio->lock); + spin_lock_init(&idi48gpio->ack_lock); dev_set_drvdata(dev, idi48gpio); diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c index e85e7539cf5d..eb43ae4835c1 100644 --- a/drivers/gpio/gpio-sch.c +++ b/drivers/gpio/gpio-sch.c @@ -61,9 +61,8 @@ static unsigned sch_gpio_bit(struct sch_gpio *sch, unsigned gpio) return gpio % 8; } -static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg) +static int sch_gpio_reg_get(struct sch_gpio *sch, unsigned gpio, unsigned reg) { - struct sch_gpio *sch = gpiochip_get_data(gc); unsigned short offset, bit; u8 reg_val; @@ -75,10 +74,9 @@ static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg) return reg_val; } -static void sch_gpio_reg_set(struct gpio_chip *gc, unsigned gpio, unsigned reg, +static void sch_gpio_reg_set(struct sch_gpio *sch, unsigned gpio, unsigned reg, int val) { - struct sch_gpio *sch = gpiochip_get_data(gc); unsigned short offset, bit; u8 reg_val; @@ -98,14 +96,15 @@ static int sch_gpio_direction_in(struct gpio_chip *gc, unsigned gpio_num) struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GIO, 1); + sch_gpio_reg_set(sch, gpio_num, GIO, 1); spin_unlock(&sch->lock); return 0; } static int sch_gpio_get(struct gpio_chip *gc, unsigned gpio_num) { - return sch_gpio_reg_get(gc, gpio_num, GLV); + struct sch_gpio *sch = gpiochip_get_data(gc); + return sch_gpio_reg_get(sch, gpio_num, GLV); } static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val) @@ -113,7 +112,7 @@ static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val) struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GLV, val); + sch_gpio_reg_set(sch, gpio_num, GLV, val); spin_unlock(&sch->lock); } @@ -123,7 +122,7 @@ static int sch_gpio_direction_out(struct gpio_chip *gc, unsigned gpio_num, struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GIO, 0); + sch_gpio_reg_set(sch, gpio_num, GIO, 0); spin_unlock(&sch->lock); /* @@ -182,13 +181,13 @@ static int sch_gpio_probe(struct platform_device *pdev) * GPIO7 is configured by the CMC as SLPIOVR * Enable GPIO[9:8] core powered gpios explicitly */ - sch_gpio_reg_set(&sch->chip, 8, GEN, 1); - sch_gpio_reg_set(&sch->chip, 9, GEN, 1); + sch_gpio_reg_set(sch, 8, GEN, 1); + sch_gpio_reg_set(sch, 9, GEN, 1); /* * SUS_GPIO[2:0] enabled by default * Enable SUS_GPIO3 resume powered gpio explicitly */ - sch_gpio_reg_set(&sch->chip, 13, GEN, 1); + sch_gpio_reg_set(sch, 13, GEN, 1); break; case PCI_DEVICE_ID_INTEL_ITC_LPC: diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index ec891a27952f..661b0e34e067 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -98,7 +98,6 @@ struct tegra_gpio_info { const struct tegra_gpio_soc_config *soc; struct gpio_chip gc; struct irq_chip ic; - struct lock_class_key lock_class; u32 bank_count; }; @@ -547,6 +546,12 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(tegra_gpio_suspend, tegra_gpio_resume) }; +/* + * This lock class tells lockdep that GPIO irqs are in a different category + * than their parents, so it won't report false recursion. + */ +static struct lock_class_key gpio_lock_class; + static int tegra_gpio_probe(struct platform_device *pdev) { const struct tegra_gpio_soc_config *config; @@ -660,7 +665,7 @@ static int tegra_gpio_probe(struct platform_device *pdev) bank = &tgi->bank_info[GPIO_BANK(gpio)]; - irq_set_lockdep_class(irq, &tgi->lock_class); + irq_set_lockdep_class(irq, &gpio_lock_class); irq_set_chip_data(irq, bank); irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq); } diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c index 3a5c7011ad3b..8b830996fe02 100644 --- a/drivers/gpio/gpiolib-legacy.c +++ b/drivers/gpio/gpiolib-legacy.c @@ -28,6 +28,10 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (!desc && gpio_is_valid(gpio)) return -EPROBE_DEFER; + err = gpiod_request(desc, label); + if (err) + return err; + if (flags & GPIOF_OPEN_DRAIN) set_bit(FLAG_OPEN_DRAIN, &desc->flags); @@ -37,10 +41,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (flags & GPIOF_ACTIVE_LOW) set_bit(FLAG_ACTIVE_LOW, &desc->flags); - err = gpiod_request(desc, label); - if (err) - return err; - if (flags & GPIOF_DIR_IN) err = gpiod_direction_input(desc); else diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 58d822d7e8da..be74bd370f1f 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1352,14 +1352,6 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label) spin_lock_irqsave(&gpio_lock, flags); } done: - if (status < 0) { - /* Clear flags that might have been set by the caller before - * requesting the GPIO. - */ - clear_bit(FLAG_ACTIVE_LOW, &desc->flags); - clear_bit(FLAG_OPEN_DRAIN, &desc->flags); - clear_bit(FLAG_OPEN_SOURCE, &desc->flags); - } spin_unlock_irqrestore(&gpio_lock, flags); return status; } @@ -1373,8 +1365,12 @@ done: #define VALIDATE_DESC(desc) do { \ if (!desc) \ return 0; \ + if (IS_ERR(desc)) { \ + pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \ + return PTR_ERR(desc); \ + } \ if (!desc->gdev) { \ - pr_warn("%s: invalid GPIO\n", __func__); \ + pr_warn("%s: invalid GPIO (no device)\n", __func__); \ return -EINVAL; \ } \ if ( !desc->gdev->chip ) { \ @@ -1386,8 +1382,12 @@ done: #define VALIDATE_DESC_VOID(desc) do { \ if (!desc) \ return; \ + if (IS_ERR(desc)) { \ + pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \ + return; \ + } \ if (!desc->gdev) { \ - pr_warn("%s: invalid GPIO\n", __func__); \ + pr_warn("%s: invalid GPIO (no device)\n", __func__); \ return; \ } \ if (!desc->gdev->chip) { \ @@ -2056,7 +2056,14 @@ int gpiod_to_irq(const struct gpio_desc *desc) struct gpio_chip *chip; int offset; - VALIDATE_DESC(desc); + /* + * Cannot VALIDATE_DESC() here as gpiod_to_irq() consumer semantics + * requires this function to not return zero on an invalid descriptor + * but rather a negative error number. + */ + if (!desc || IS_ERR(desc) || !desc->gdev || !desc->gdev->chip) + return -EINVAL; + chip = desc->gdev->chip; offset = gpio_chip_hwgpio(desc); if (chip->to_irq) { @@ -2572,28 +2579,13 @@ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev, } EXPORT_SYMBOL_GPL(gpiod_get_optional); -/** - * gpiod_parse_flags - helper function to parse GPIO lookup flags - * @desc: gpio to be setup - * @lflags: gpio_lookup_flags - returned from of_find_gpio() or - * of_get_gpio_hog() - * - * Set the GPIO descriptor flags based on the given GPIO lookup flags. - */ -static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) -{ - if (lflags & GPIO_ACTIVE_LOW) - set_bit(FLAG_ACTIVE_LOW, &desc->flags); - if (lflags & GPIO_OPEN_DRAIN) - set_bit(FLAG_OPEN_DRAIN, &desc->flags); - if (lflags & GPIO_OPEN_SOURCE) - set_bit(FLAG_OPEN_SOURCE, &desc->flags); -} /** * gpiod_configure_flags - helper function to configure a given GPIO * @desc: gpio whose value will be assigned * @con_id: function within the GPIO consumer + * @lflags: gpio_lookup_flags - returned from of_find_gpio() or + * of_get_gpio_hog() * @dflags: gpiod_flags - optional GPIO initialization flags * * Return 0 on success, -ENOENT if no GPIO has been assigned to the @@ -2601,10 +2593,17 @@ static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) * occurred while trying to acquire the GPIO. */ static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, - enum gpiod_flags dflags) + unsigned long lflags, enum gpiod_flags dflags) { int status; + if (lflags & GPIO_ACTIVE_LOW) + set_bit(FLAG_ACTIVE_LOW, &desc->flags); + if (lflags & GPIO_OPEN_DRAIN) + set_bit(FLAG_OPEN_DRAIN, &desc->flags); + if (lflags & GPIO_OPEN_SOURCE) + set_bit(FLAG_OPEN_SOURCE, &desc->flags); + /* No particular flag request, return here... */ if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) { pr_debug("no flags found for %s\n", con_id); @@ -2671,13 +2670,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev, return desc; } - gpiod_parse_flags(desc, lookupflags); - status = gpiod_request(desc, con_id); if (status < 0) return ERR_PTR(status); - status = gpiod_configure_flags(desc, con_id, flags); + status = gpiod_configure_flags(desc, con_id, lookupflags, flags); if (status < 0) { dev_dbg(dev, "setup of GPIO %s failed\n", con_id); gpiod_put(desc); @@ -2733,6 +2730,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, if (IS_ERR(desc)) return desc; + ret = gpiod_request(desc, NULL); + if (ret) + return ERR_PTR(ret); + if (active_low) set_bit(FLAG_ACTIVE_LOW, &desc->flags); @@ -2743,10 +2744,6 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, set_bit(FLAG_OPEN_SOURCE, &desc->flags); } - ret = gpiod_request(desc, NULL); - if (ret) - return ERR_PTR(ret); - return desc; } EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod); @@ -2799,8 +2796,6 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, chip = gpiod_to_chip(desc); hwnum = gpio_chip_hwgpio(desc); - gpiod_parse_flags(desc, lflags); - local_desc = gpiochip_request_own_desc(chip, hwnum, name); if (IS_ERR(local_desc)) { status = PTR_ERR(local_desc); @@ -2809,7 +2804,7 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, return status; } - status = gpiod_configure_flags(desc, name, dflags); + status = gpiod_configure_flags(desc, name, lflags, dflags); if (status < 0) { pr_err("setup of hog GPIO %s (chip %s, offset %d) failed, %d\n", name, chip->label, hwnum, status); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 01c36b8d6222..e055d5be1c3c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -799,7 +799,6 @@ struct amdgpu_ring { unsigned cond_exe_offs; u64 cond_exe_gpu_addr; volatile u32 *cond_exe_cpu_addr; - int vmid; }; /* @@ -937,8 +936,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr, uint32_t gds_base, uint32_t gds_size, uint32_t gws_base, uint32_t gws_size, - uint32_t oa_base, uint32_t oa_size, - bool vmid_switch); + uint32_t oa_base, uint32_t oa_size); void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vm_id); uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr); int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, @@ -1822,6 +1820,8 @@ struct amdgpu_asic_funcs { /* MM block clocks */ int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk); int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk); + /* query virtual capabilities */ + u32 (*get_virtual_caps)(struct amdgpu_device *adev); }; /* @@ -1916,8 +1916,12 @@ void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device); /* GPU virtualization */ +#define AMDGPU_VIRT_CAPS_SRIOV_EN (1 << 0) +#define AMDGPU_VIRT_CAPS_IS_VF (1 << 1) struct amdgpu_virtualization { bool supports_sr_iov; + bool is_virtual; + u32 caps; }; /* @@ -2206,6 +2210,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) #define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev)) #define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d)) #define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec)) +#define amdgpu_asic_get_virtual_caps(adev) ((adev)->asic_funcs->get_virtual_caps((adev))) #define amdgpu_asic_get_gpu_clock_counter(adev) (adev)->asic_funcs->get_gpu_clock_counter((adev)) #define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev)) #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index 252edba16e36..892d60fb225b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -421,29 +421,6 @@ static int acp_suspend(void *handle) static int acp_resume(void *handle) { - int i, ret; - struct acp_pm_domain *apd; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - /* return early if no ACP */ - if (!adev->acp.acp_genpd) - return 0; - - /* SMU block will power on ACP irrespective of ACP runtime status. - * Power off explicitly based on genpd ACP runtime status so that ACP - * hw and ACP-genpd status are in sync. - * 'suspend_power_off' represents "Power status before system suspend" - */ - if (adev->acp.acp_genpd->gpd.suspend_power_off == true) { - apd = container_of(&adev->acp.acp_genpd->gpd, - struct acp_pm_domain, gpd); - - for (i = 4; i >= 0 ; i--) { - ret = acp_suspend_tile(apd->cgs_dev, ACP_TILE_P1 + i); - if (ret) - pr_err("ACP tile %d tile suspend failed\n", i); - } - } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 8943099eb135..cf6f49fc1c75 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -909,7 +909,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, struct cgs_acpi_method_argument *argument = NULL; uint32_t i, count; acpi_status status; - int result; + int result = 0; uint32_t func_no = 0xFFFFFFFF; handle = ACPI_HANDLE(&adev->pdev->dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 964f31404f17..6e920086af46 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1385,6 +1385,15 @@ static int amdgpu_resume(struct amdgpu_device *adev) return 0; } +static bool amdgpu_device_is_virtual(void) +{ +#ifdef CONFIG_X86 + return boot_cpu_has(X86_FEATURE_HYPERVISOR); +#else + return false; +#endif +} + /** * amdgpu_device_init - initialize the driver * @@ -1519,8 +1528,14 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->virtualization.supports_sr_iov = amdgpu_atombios_has_gpu_virtualization_table(adev); + /* Check if we are executing in a virtualized environment */ + adev->virtualization.is_virtual = amdgpu_device_is_virtual(); + adev->virtualization.caps = amdgpu_asic_get_virtual_caps(adev); + /* Post card if necessary */ - if (!amdgpu_card_posted(adev)) { + if (!amdgpu_card_posted(adev) || + (adev->virtualization.is_virtual && + !(adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN))) { if (!adev->bios) { dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n"); return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 7a0b1e50f293..34e35423b78e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -122,7 +122,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, bool skip_preamble, need_ctx_switch; unsigned patch_offset = ~0; struct amdgpu_vm *vm; - int vmid = 0, old_vmid = ring->vmid; struct fence *hwf; uint64_t ctx; @@ -136,11 +135,9 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, if (job) { vm = job->vm; ctx = job->ctx; - vmid = job->vm_id; } else { vm = NULL; ctx = 0; - vmid = 0; } if (!ring->ready) { @@ -166,8 +163,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, r = amdgpu_vm_flush(ring, job->vm_id, job->vm_pd_addr, job->gds_base, job->gds_size, job->gws_base, job->gws_size, - job->oa_base, job->oa_size, - (ring->current_ctx == ctx) && (old_vmid != vmid)); + job->oa_base, job->oa_size); if (r) { amdgpu_ring_undo(ring); return r; @@ -184,6 +180,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, need_ctx_switch = ring->current_ctx != ctx; for (i = 0; i < num_ibs; ++i) { ib = &ibs[i]; + /* drop preamble IBs if we don't have a context switch */ if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && skip_preamble) continue; @@ -191,7 +188,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, amdgpu_ring_emit_ib(ring, ib, job ? job->vm_id : 0, need_ctx_switch); need_ctx_switch = false; - ring->vmid = vmid; } if (ring->funcs->emit_hdp_invalidate) @@ -202,7 +198,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, dev_err(adev->dev, "failed to emit fence (%d)\n", r); if (job && job->vm_id) amdgpu_vm_reset_id(adev, job->vm_id); - ring->vmid = old_vmid; amdgpu_ring_undo(ring); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 40a23704a981..d851ea15059f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -447,7 +447,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file dev_info.max_memory_clock = adev->pm.default_mclk * 10; } dev_info.enabled_rb_pipes_mask = adev->gfx.config.backend_enable_mask; - dev_info.num_rb_pipes = adev->gfx.config.num_rbs; + dev_info.num_rb_pipes = adev->gfx.config.max_backends_per_se * + adev->gfx.config.max_shader_engines; dev_info.num_hw_gfx_contexts = adev->gfx.config.max_hw_contexts; dev_info._pad = 0; dev_info.ids_flags = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 589b36e8c5cf..0e13d80d2a95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -270,30 +270,28 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = ddev->dev_private; enum amd_pm_state_type state = 0; - long idx; + unsigned long idx; int ret; if (strlen(buf) == 1) adev->pp_force_state_enabled = false; - else { - ret = kstrtol(buf, 0, &idx); + else if (adev->pp_enabled) { + struct pp_states_info data; - if (ret) { + ret = kstrtoul(buf, 0, &idx); + if (ret || idx >= ARRAY_SIZE(data.states)) { count = -EINVAL; goto fail; } - if (adev->pp_enabled) { - struct pp_states_info data; - amdgpu_dpm_get_pp_num_states(adev, &data); - state = data.states[idx]; - /* only set user selected power states */ - if (state != POWER_STATE_TYPE_INTERNAL_BOOT && - state != POWER_STATE_TYPE_DEFAULT) { - amdgpu_dpm_dispatch_task(adev, - AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL); - adev->pp_force_state_enabled = true; - } + amdgpu_dpm_get_pp_num_states(adev, &data); + state = data.states[idx]; + /* only set user selected power states */ + if (state != POWER_STATE_TYPE_INTERNAL_BOOT && + state != POWER_STATE_TYPE_DEFAULT) { + amdgpu_dpm_dispatch_task(adev, + AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL); + adev->pp_force_state_enabled = true; } } fail: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index e19520c4b4b6..d9c88d13f8db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1106,6 +1106,10 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work) if (fences == 0 && handles == 0) { if (adev->pm.dpm_enabled) { amdgpu_dpm_enable_uvd(adev, false); + /* just work around for uvd clock remain high even + * when uvd dpm disabled on Polaris10 */ + if (adev->asic_type == CHIP_POLARIS10) + amdgpu_asic_set_uvd_clocks(adev, 0, 0); } else { amdgpu_asic_set_uvd_clocks(adev, 0, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 62a4c127620f..9f36ed30ba11 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -298,8 +298,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr, uint32_t gds_base, uint32_t gds_size, uint32_t gws_base, uint32_t gws_size, - uint32_t oa_base, uint32_t oa_size, - bool vmid_switch) + uint32_t oa_base, uint32_t oa_size) { struct amdgpu_device *adev = ring->adev; struct amdgpu_vm_id *id = &adev->vm_manager.ids[vm_id]; @@ -313,7 +312,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, int r; if (ring->funcs->emit_pipeline_sync && ( - pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed || vmid_switch)) + pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed || + ring->type == AMDGPU_RING_TYPE_COMPUTE)) amdgpu_ring_emit_pipeline_sync(ring); if (ring->funcs->emit_vm_flush && diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c index 13cdb01e9b45..bc56c8a181e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c @@ -156,3 +156,18 @@ u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap) return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, u8 slave_addr, u8 line_number, u8 offset, u8 data) +{ + PROCESS_I2C_CHANNEL_TRANSACTION_PS_ALLOCATION args; + int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction); + + args.ucRegIndex = offset; + args.lpI2CDataOut = data; + args.ucFlag = 1; + args.ucI2CSpeed = TARGET_HW_I2C_CLOCK; + args.ucTransBytes = 1; + args.ucSlaveAddr = slave_addr; + args.ucLineNumber = line_number; + + amdgpu_atom_execute_table(adev->mode_info.atom_context, index, (uint32_t *)&args); +} diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h index d6128d9de56e..251aaf41f65d 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h @@ -27,5 +27,7 @@ int amdgpu_atombios_i2c_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg *msgs, int num); u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap); +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, + u8 slave_addr, u8 line_number, u8 offset, u8 data); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 07bc795a4ca9..910431808542 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -962,6 +962,12 @@ static bool cik_read_bios_from_rom(struct amdgpu_device *adev, return true; } +static u32 cik_get_virtual_caps(struct amdgpu_device *adev) +{ + /* CIK does not support SR-IOV */ + return 0; +} + static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] = { {mmGRBM_STATUS, false}, {mmGB_ADDR_CONFIG, false}, @@ -2007,6 +2013,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs = .get_xclk = &cik_get_xclk, .set_uvd_clocks = &cik_set_uvd_clocks, .set_vce_clocks = &cik_set_vce_clocks, + .get_virtual_caps = &cik_get_virtual_caps, /* these should be moved to their own ip modules */ .get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter, .wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 8c6ad1e72f02..fc8ff4d3ccf8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4833,7 +4833,7 @@ static int gfx_v7_0_eop_irq(struct amdgpu_device *adev, case 2: for (i = 0; i < adev->gfx.num_compute_rings; i++) { ring = &adev->gfx.compute_ring[i]; - if ((ring->me == me_id) & (ring->pipe == pipe_id)) + if ((ring->me == me_id) && (ring->pipe == pipe_id)) amdgpu_fence_process(ring); } break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 9f6f8669edc3..c2ef94511f70 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -28,6 +28,7 @@ #include "vid.h" #include "amdgpu_ucode.h" #include "amdgpu_atombios.h" +#include "atombios_i2c.h" #include "clearstate_vi.h" #include "gmc/gmc_8_2_d.h" @@ -47,6 +48,8 @@ #include "dce/dce_10_0_d.h" #include "dce/dce_10_0_sh_mask.h" +#include "smu/smu_7_1_3_d.h" + #define GFX8_NUM_GFX_RINGS 1 #define GFX8_NUM_COMPUTE_RINGS 8 @@ -282,6 +285,7 @@ static const u32 golden_settings_polaris11_a11[] = mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00003210, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris11_golden_common_all[] = @@ -297,7 +301,8 @@ static const u32 polaris11_golden_common_all[] = static const u32 golden_settings_polaris10_a11[] = { mmATC_MISC_CG, 0x000c0fc0, 0x000c0200, - mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208, + mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208, + mmCB_HW_CONTROL_2, 0, 0x0f000000, mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040, mmDB_DEBUG2, 0xf00fffff, 0x00000400, mmPA_SC_ENHANCE, 0xffffffff, 0x20000001, @@ -311,6 +316,7 @@ static const u32 golden_settings_polaris10_a11[] = mmTCC_CTRL, 0x00100000, 0xf31fff7f, mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f7, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris10_golden_common_all[] = @@ -692,6 +698,11 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev) amdgpu_program_register_sequence(adev, polaris10_golden_common_all, (const u32)ARRAY_SIZE(polaris10_golden_common_all)); + WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C); + if (adev->pdev->revision == 0xc7) { + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1E, 0xDD); + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1F, 0xD0); + } break; case CHIP_CARRIZO: amdgpu_program_register_sequence(adev, diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 2c88d0b66cf3..a65c96029476 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -421,6 +421,20 @@ static bool vi_read_bios_from_rom(struct amdgpu_device *adev, return true; } +static u32 vi_get_virtual_caps(struct amdgpu_device *adev) +{ + u32 caps = 0; + u32 reg = RREG32(mmBIF_IOV_FUNC_IDENTIFIER); + + if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, IOV_ENABLE)) + caps |= AMDGPU_VIRT_CAPS_SRIOV_EN; + + if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, FUNC_IDENTIFIER)) + caps |= AMDGPU_VIRT_CAPS_IS_VF; + + return caps; +} + static const struct amdgpu_allowed_register_entry tonga_allowed_read_registers[] = { {mmGB_MACROTILE_MODE7, true}, }; @@ -1118,6 +1132,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs = .get_xclk = &vi_get_xclk, .set_uvd_clocks = &vi_set_uvd_clocks, .set_vce_clocks = &vi_set_vce_clocks, + .get_virtual_caps = &vi_get_virtual_caps, /* these should be moved to their own ip modules */ .get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter, .wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index ac005796b71c..7708d90b9da9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -242,13 +242,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, pqm_uninit(&p->pqm); /* Iterate over all process device data structure and check - * if we should reset all wavefronts */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) + * if we should delete debug managers and reset all wavefronts + */ + list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + if ((pdd->dev->dbgmgr) && + (pdd->dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(pdd->dev->dbgmgr); + if (pdd->reset_wavefronts) { pr_warn("amdkfd: Resetting all wave fronts\n"); dbgdev_wave_reset_wavefronts(pdd->dev, p); pdd->reset_wavefronts = false; } + } mutex_unlock(&p->mutex); @@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid) idx = srcu_read_lock(&kfd_processes_srcu); + /* + * Look for the process that matches the pasid. If there is no such + * process, we either released it in amdkfd's own notifier, or there + * is a bug. Unfortunately, there is no way to tell... + */ hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes) - if (p->pasid == pasid) - break; + if (p->pasid == pasid) { - srcu_read_unlock(&kfd_processes_srcu, idx); + srcu_read_unlock(&kfd_processes_srcu, idx); - BUG_ON(p->pasid != pasid); + pr_debug("Unbinding process %d from IOMMU\n", pasid); - mutex_lock(&p->mutex); + mutex_lock(&p->mutex); - if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) - kfd_dbgmgr_destroy(dev->dbgmgr); + if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(dev->dbgmgr); - pqm_uninit(&p->pqm); + pqm_uninit(&p->pqm); - pdd = kfd_get_process_device_data(dev, p); + pdd = kfd_get_process_device_data(dev, p); - if (!pdd) { - mutex_unlock(&p->mutex); - return; - } + if (!pdd) { + mutex_unlock(&p->mutex); + return; + } - if (pdd->reset_wavefronts) { - dbgdev_wave_reset_wavefronts(pdd->dev, p); - pdd->reset_wavefronts = false; - } + if (pdd->reset_wavefronts) { + dbgdev_wave_reset_wavefronts(pdd->dev, p); + pdd->reset_wavefronts = false; + } - /* - * Just mark pdd as unbound, because we still need it to call - * amd_iommu_unbind_pasid() in when the process exits. - * We don't call amd_iommu_unbind_pasid() here - * because the IOMMU called us. - */ - pdd->bound = false; + /* + * Just mark pdd as unbound, because we still need it + * to call amd_iommu_unbind_pasid() in when the + * process exits. + * We don't call amd_iommu_unbind_pasid() here + * because the IOMMU called us. + */ + pdd->bound = false; - mutex_unlock(&p->mutex); + mutex_unlock(&p->mutex); + + return; + } + + srcu_read_unlock(&kfd_processes_srcu, idx); } struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 74909e72a009..884c96f50c3d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -666,7 +666,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->node_props.simd_count); if (dev->mem_bank_count < dev->node_props.mem_banks_count) { - pr_warn("kfd: mem_banks_count truncated from %d to %d\n", + pr_info_once("kfd: mem_banks_count truncated from %d to %d\n", dev->node_props.mem_banks_count, dev->mem_bank_count); sysfs_show_32bit_prop(buffer, "mem_banks_count", diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h index 32f3e345de08..3493da5c8f0e 100644 --- a/drivers/gpu/drm/amd/include/atombios.h +++ b/drivers/gpu/drm/amd/include/atombios.h @@ -5538,6 +5538,78 @@ typedef struct _ATOM_ASIC_PROFILING_INFO_V3_5 ULONG ulReserved[12]; }ATOM_ASIC_PROFILING_INFO_V3_5; +/* for Polars10/11 AVFS parameters */ +typedef struct _ATOM_ASIC_PROFILING_INFO_V3_6 +{ + ATOM_COMMON_TABLE_HEADER asHeader; + ULONG ulMaxVddc; + ULONG ulMinVddc; + USHORT usLkgEuseIndex; + UCHAR ucLkgEfuseBitLSB; + UCHAR ucLkgEfuseLength; + ULONG ulLkgEncodeLn_MaxDivMin; + ULONG ulLkgEncodeMax; + ULONG ulLkgEncodeMin; + EFUSE_LINEAR_FUNC_PARAM sRoFuse; + ULONG ulEvvDefaultVddc; + ULONG ulEvvNoCalcVddc; + ULONG ulSpeed_Model; + ULONG ulSM_A0; + ULONG ulSM_A1; + ULONG ulSM_A2; + ULONG ulSM_A3; + ULONG ulSM_A4; + ULONG ulSM_A5; + ULONG ulSM_A6; + ULONG ulSM_A7; + UCHAR ucSM_A0_sign; + UCHAR ucSM_A1_sign; + UCHAR ucSM_A2_sign; + UCHAR ucSM_A3_sign; + UCHAR ucSM_A4_sign; + UCHAR ucSM_A5_sign; + UCHAR ucSM_A6_sign; + UCHAR ucSM_A7_sign; + ULONG ulMargin_RO_a; + ULONG ulMargin_RO_b; + ULONG ulMargin_RO_c; + ULONG ulMargin_fixed; + ULONG ulMargin_Fmax_mean; + ULONG ulMargin_plat_mean; + ULONG ulMargin_Fmax_sigma; + ULONG ulMargin_plat_sigma; + ULONG ulMargin_DC_sigma; + ULONG ulLoadLineSlop; + ULONG ulaTDClimitPerDPM[8]; + ULONG ulaNoCalcVddcPerDPM[8]; + ULONG ulAVFS_meanNsigma_Acontant0; + ULONG ulAVFS_meanNsigma_Acontant1; + ULONG ulAVFS_meanNsigma_Acontant2; + USHORT usAVFS_meanNsigma_DC_tol_sigma; + USHORT usAVFS_meanNsigma_Platform_mean; + USHORT usAVFS_meanNsigma_Platform_sigma; + ULONG ulGB_VDROOP_TABLE_CKSOFF_a0; + ULONG ulGB_VDROOP_TABLE_CKSOFF_a1; + ULONG ulGB_VDROOP_TABLE_CKSOFF_a2; + ULONG ulGB_VDROOP_TABLE_CKSON_a0; + ULONG ulGB_VDROOP_TABLE_CKSON_a1; + ULONG ulGB_VDROOP_TABLE_CKSON_a2; + ULONG ulAVFSGB_FUSE_TABLE_CKSOFF_m1; + USHORT usAVFSGB_FUSE_TABLE_CKSOFF_m2; + ULONG ulAVFSGB_FUSE_TABLE_CKSOFF_b; + ULONG ulAVFSGB_FUSE_TABLE_CKSON_m1; + USHORT usAVFSGB_FUSE_TABLE_CKSON_m2; + ULONG ulAVFSGB_FUSE_TABLE_CKSON_b; + USHORT usMaxVoltage_0_25mv; + UCHAR ucEnableGB_VDROOP_TABLE_CKSOFF; + UCHAR ucEnableGB_VDROOP_TABLE_CKSON; + UCHAR ucEnableGB_FUSE_TABLE_CKSOFF; + UCHAR ucEnableGB_FUSE_TABLE_CKSON; + USHORT usPSM_Age_ComFactor; + UCHAR ucEnableApplyAVFS_CKS_OFF_Voltage; + UCHAR ucReserved; +}ATOM_ASIC_PROFILING_INFO_V3_6; + typedef struct _ATOM_SCLK_FCW_RANGE_ENTRY_V1{ ULONG ulMaxSclkFreq; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c index 586f73276226..92912ab20944 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c @@ -633,6 +633,8 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vddci_control = FIJI_VOLTAGE_CONTROL_NONE; data->mvdd_control = FIJI_VOLTAGE_CONTROL_NONE; + data->force_pcie_gen = PP_PCIEGenInvalid; + if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) data->voltage_control = FIJI_VOLTAGE_CONTROL_BY_SVID2; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c index fa208ada6892..efb77eda7508 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c @@ -306,10 +306,14 @@ int phm_store_dal_configuration_data(struct pp_hwmgr *hwmgr, { PHM_FUNC_CHECK(hwmgr); - if (hwmgr->hwmgr_func->store_cc6_data == NULL) + if (display_config == NULL) return -EINVAL; hwmgr->display_config = *display_config; + + if (hwmgr->hwmgr_func->store_cc6_data == NULL) + return -EINVAL; + /* to do pass other display configuration in furture */ if (hwmgr->hwmgr_func->store_cc6_data) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h index 347fef127ce9..2930a3355948 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h @@ -39,6 +39,7 @@ struct phm_ppt_v1_clock_voltage_dependency_record { uint8_t phases; uint8_t cks_enable; uint8_t cks_voffset; + uint32_t sclk_offset; }; typedef struct phm_ppt_v1_clock_voltage_dependency_record phm_ppt_v1_clock_voltage_dependency_record; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c index aa6be033f21b..91e25f942d90 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c @@ -732,7 +732,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[level] |= data->mvdd_voltage_table.entries[level].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count); } @@ -999,7 +999,7 @@ static int polaris10_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), (dep_table->entries[i].vddc - (uint16_t)data->vddc_vddci_delta)); - *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; + *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; } if (POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control) @@ -1296,7 +1296,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr, } mem_level->MclkFrequency = clock; - mem_level->StutterEnable = 0; mem_level->EnabledForThrottle = 1; mem_level->EnabledForActivity = 0; mem_level->UpHyst = 0; @@ -1304,7 +1303,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr, mem_level->VoltageDownHyst = 0; mem_level->ActivityLevel = (uint16_t)data->mclk_activity_target; mem_level->StutterEnable = false; - mem_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW; data->display_timing.num_existing_displays = info.display_count; @@ -1363,7 +1361,7 @@ static int polaris10_populate_all_memory_levels(struct pp_hwmgr *hwmgr) * a higher state by default such that we are not effected by * up threshold or and MCLK DPM latency. */ - levels[0].ActivityLevel = (uint16_t)data->mclk_dpm0_activity_target; + levels[0].ActivityLevel = 0x1f; CONVERT_FROM_HOST_TO_SMC_US(levels[0].ActivityLevel); data->smc_state_table.MemoryDpmLevelCount = @@ -1424,22 +1422,19 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr, table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC; - if (!data->sclk_dpm_key_disabled) { - /* Get MinVoltage and Frequency from DPM0, - * already converted to SMC_UL */ - sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value; - result = polaris10_get_dependency_volt_by_clk(hwmgr, - table_info->vdd_dep_on_sclk, - table->ACPILevel.SclkFrequency, - &table->ACPILevel.MinVoltage, &mvdd); - PP_ASSERT_WITH_CODE((0 == result), - "Cannot find ACPI VDDC voltage value " - "in Clock Dependency Table", ); - } else { - sclk_frequency = data->vbios_boot_state.sclk_bootup_value; - table->ACPILevel.MinVoltage = - data->vbios_boot_state.vddc_bootup_value * VOLTAGE_SCALE; - } + + /* Get MinVoltage and Frequency from DPM0, + * already converted to SMC_UL */ + sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value; + result = polaris10_get_dependency_volt_by_clk(hwmgr, + table_info->vdd_dep_on_sclk, + sclk_frequency, + &table->ACPILevel.MinVoltage, &mvdd); + PP_ASSERT_WITH_CODE((0 == result), + "Cannot find ACPI VDDC voltage value " + "in Clock Dependency Table", + ); + result = polaris10_calculate_sclk_params(hwmgr, sclk_frequency, &(table->ACPILevel.SclkSetting)); PP_ASSERT_WITH_CODE(result == 0, "Error retrieving Engine Clock dividers from VBIOS.", return result); @@ -1464,24 +1459,18 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr, CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw1_frac); CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Sclk_ss_slew_rate); - if (!data->mclk_dpm_key_disabled) { - /* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */ - table->MemoryACPILevel.MclkFrequency = - data->dpm_table.mclk_table.dpm_levels[0].value; - result = polaris10_get_dependency_volt_by_clk(hwmgr, - table_info->vdd_dep_on_mclk, - table->MemoryACPILevel.MclkFrequency, - &table->MemoryACPILevel.MinVoltage, &mvdd); - PP_ASSERT_WITH_CODE((0 == result), - "Cannot find ACPI VDDCI voltage value " - "in Clock Dependency Table", - ); - } else { - table->MemoryACPILevel.MclkFrequency = - data->vbios_boot_state.mclk_bootup_value; - table->MemoryACPILevel.MinVoltage = - data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE; - } + + /* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */ + table->MemoryACPILevel.MclkFrequency = + data->dpm_table.mclk_table.dpm_levels[0].value; + result = polaris10_get_dependency_volt_by_clk(hwmgr, + table_info->vdd_dep_on_mclk, + table->MemoryACPILevel.MclkFrequency, + &table->MemoryACPILevel.MinVoltage, &mvdd); + PP_ASSERT_WITH_CODE((0 == result), + "Cannot find ACPI VDDCI voltage value " + "in Clock Dependency Table", + ); us_mvdd = 0; if ((POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control) || @@ -1526,6 +1515,7 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr, struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table = table_info->mm_dep_table; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t vddci; table->VceLevelCount = (uint8_t)(mm_table->count); table->VceBootLevel = 0; @@ -1535,9 +1525,18 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr, table->VceLevel[count].MinVoltage = 0; table->VceLevel[count].MinVoltage |= (mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; + + if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) + vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table), + mm_table->entries[count].vddc - VDDC_VDDCI_DELTA); + else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control) + vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA; + else + vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT; + + table->VceLevel[count].MinVoltage |= - ((mm_table->entries[count].vddc - data->vddc_vddci_delta) * - VOLTAGE_SCALE) << VDDCI_SHIFT; + (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; table->VceLevel[count].MinVoltage |= 1 << PHASES_SHIFT; /*retrieve divider value for VBIOS */ @@ -1566,6 +1565,7 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr, struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table = table_info->mm_dep_table; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t vddci; table->SamuBootLevel = 0; table->SamuLevelCount = (uint8_t)(mm_table->count); @@ -1576,8 +1576,16 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr, table->SamuLevel[count].Frequency = mm_table->entries[count].samclock; table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; - table->SamuLevel[count].MinVoltage |= ((mm_table->entries[count].vddc - - data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT; + + if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) + vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table), + mm_table->entries[count].vddc - VDDC_VDDCI_DELTA); + else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control) + vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA; + else + vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT; + + table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT; /* retrieve divider value for VBIOS */ @@ -1660,6 +1668,7 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr, struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table = table_info->mm_dep_table; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t vddci; table->UvdLevelCount = (uint8_t)(mm_table->count); table->UvdBootLevel = 0; @@ -1670,8 +1679,16 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr, table->UvdLevel[count].DclkFrequency = mm_table->entries[count].dclk; table->UvdLevel[count].MinVoltage |= (mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; - table->UvdLevel[count].MinVoltage |= ((mm_table->entries[count].vddc - - data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT; + + if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) + vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table), + mm_table->entries[count].vddc - VDDC_VDDCI_DELTA); + else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control) + vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA; + else + vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT; + + table->UvdLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; table->UvdLevel[count].MinVoltage |= 1 << PHASES_SHIFT; /* retrieve divider value for VBIOS */ @@ -1692,8 +1709,8 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr, CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].VclkFrequency); CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].DclkFrequency); CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].MinVoltage); - } + return result; } @@ -1761,12 +1778,9 @@ static int polaris10_populate_smc_initailial_state(struct pp_hwmgr *hwmgr) static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) { - uint32_t ro, efuse, efuse2, clock_freq, volt_without_cks, - volt_with_cks, value; - uint16_t clock_freq_u16; + uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - uint8_t type, i, j, cks_setting, stretch_amount, stretch_amount2, - volt_offset = 0; + uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0; struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table = @@ -1778,50 +1792,44 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) * if the part is SS or FF. if RO >= 1660MHz, part is FF. */ efuse = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixSMU_EFUSE_0 + (146 * 4)); - efuse2 = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixSMU_EFUSE_0 + (148 * 4)); + ixSMU_EFUSE_0 + (67 * 4)); efuse &= 0xFF000000; efuse = efuse >> 24; - efuse2 &= 0xF; - - if (efuse2 == 1) - ro = (2300 - 1350) * efuse / 255 + 1350; - else - ro = (2500 - 1000) * efuse / 255 + 1000; - if (ro >= 1660) - type = 0; - else - type = 1; + if (hwmgr->chip_id == CHIP_POLARIS10) { + min = 1000; + max = 2300; + } else { + min = 1100; + max = 2100; + } - /* Populate Stretch amount */ - data->smc_state_table.ClockStretcherAmount = stretch_amount; + ro = efuse * (max -min)/255 + min; /* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */ for (i = 0; i < sclk_table->count; i++) { data->smc_state_table.Sclk_CKS_masterEn0_7 |= sclk_table->entries[i].cks_enable << i; - volt_without_cks = (uint32_t)((14041 * - (sclk_table->entries[i].clk/100) / 10000 + 3571 + 75 - ro) * 1000 / - (4026 - (13924 * (sclk_table->entries[i].clk/100) / 10000))); - volt_with_cks = (uint32_t)((13946 * - (sclk_table->entries[i].clk/100) / 10000 + 3320 + 45 - ro) * 1000 / - (3664 - (11454 * (sclk_table->entries[i].clk/100) / 10000))); + if (hwmgr->chip_id == CHIP_POLARIS10) { + volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \ + (2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000)); + volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \ + (2522480 - sclk_table->entries[i].clk/100 * 115764/100)); + } else { + volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \ + (2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000))); + volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \ + (3422454 - sclk_table->entries[i].clk/100 * (18886376/10000))); + } + if (volt_without_cks >= volt_with_cks) volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks + - sclk_table->entries[i].cks_voffset) * 100 / 625) + 1); + sclk_table->entries[i].cks_voffset) * 100 + 624) / 625); + data->smc_state_table.Sclk_voltageOffset[i] = volt_offset; } - PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, - STRETCH_ENABLE, 0x0); - PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, - masterReset, 0x1); - /* PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, staticEnable, 0x1); */ - PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, - masterReset, 0x0); - + data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6; /* Populate CKS Lookup Table */ if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5) stretch_amount2 = 0; @@ -1835,69 +1843,6 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) return -EINVAL); } - value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixPWR_CKS_CNTL); - value &= 0xFFC2FF87; - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq = - polaris10_clock_stretcher_lookup_table[stretch_amount2][0]; - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq = - polaris10_clock_stretcher_lookup_table[stretch_amount2][1]; - clock_freq_u16 = (uint16_t)(PP_SMC_TO_HOST_UL(data->smc_state_table. - GraphicsLevel[data->smc_state_table.GraphicsDpmLevelCount - 1].SclkSetting.SclkFrequency) / 100); - if (polaris10_clock_stretcher_lookup_table[stretch_amount2][0] < clock_freq_u16 - && polaris10_clock_stretcher_lookup_table[stretch_amount2][1] > clock_freq_u16) { - /* Program PWR_CKS_CNTL. CKS_USE_FOR_LOW_FREQ */ - value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 16; - /* Program PWR_CKS_CNTL. CKS_LDO_REFSEL */ - value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][2]) << 18; - /* Program PWR_CKS_CNTL. CKS_STRETCH_AMOUNT */ - value |= (polaris10_clock_stretch_amount_conversion - [polaris10_clock_stretcher_lookup_table[stretch_amount2][3]] - [stretch_amount]) << 3; - } - CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq); - CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq); - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting = - polaris10_clock_stretcher_lookup_table[stretch_amount2][2] & 0x7F; - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting |= - (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 7; - - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixPWR_CKS_CNTL, value); - - /* Populate DDT Lookup Table */ - for (i = 0; i < 4; i++) { - /* Assign the minimum and maximum VID stored - * in the last row of Clock Stretcher Voltage Table. - */ - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].minVID = - (uint8_t) polaris10_clock_stretcher_ddt_table[type][i][2]; - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].maxVID = - (uint8_t) polaris10_clock_stretcher_ddt_table[type][i][3]; - /* Loop through each SCLK and check the frequency - * to see if it lies within the frequency for clock stretcher. - */ - for (j = 0; j < data->smc_state_table.GraphicsDpmLevelCount; j++) { - cks_setting = 0; - clock_freq = PP_SMC_TO_HOST_UL( - data->smc_state_table.GraphicsLevel[j].SclkSetting.SclkFrequency); - /* Check the allowed frequency against the sclk level[j]. - * Sclk's endianness has already been converted, - * and it's in 10Khz unit, - * as opposed to Data table, which is in Mhz unit. - */ - if (clock_freq >= (polaris10_clock_stretcher_ddt_table[type][i][0]) * 100) { - cks_setting |= 0x2; - if (clock_freq < (polaris10_clock_stretcher_ddt_table[type][i][1]) * 100) - cks_setting |= 0x1; - } - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting - |= cks_setting << (j * 2); - } - CONVERT_FROM_HOST_TO_SMC_US( - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting); - } - value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL); value &= 0xFFFFFFFE; cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL, value); @@ -1956,6 +1901,90 @@ static int polaris10_populate_vr_config(struct pp_hwmgr *hwmgr, return 0; } + +int polaris10_populate_avfs_parameters(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + SMU74_Discrete_DpmTable *table = &(data->smc_state_table); + int result = 0; + struct pp_atom_ctrl__avfs_parameters avfs_params = {0}; + AVFS_meanNsigma_t AVFS_meanNsigma = { {0} }; + AVFS_Sclk_Offset_t AVFS_SclkOffset = { {0} }; + uint32_t tmp, i; + struct pp_smumgr *smumgr = hwmgr->smumgr; + struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend); + + struct phm_ppt_v1_information *table_info = + (struct phm_ppt_v1_information *)hwmgr->pptable; + struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table = + table_info->vdd_dep_on_sclk; + + + if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED) + return result; + + result = atomctrl_get_avfs_information(hwmgr, &avfs_params); + + if (0 == result) { + table->BTCGB_VDROOP_TABLE[0].a0 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a0); + table->BTCGB_VDROOP_TABLE[0].a1 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a1); + table->BTCGB_VDROOP_TABLE[0].a2 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a2); + table->BTCGB_VDROOP_TABLE[1].a0 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a0); + table->BTCGB_VDROOP_TABLE[1].a1 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a1); + table->BTCGB_VDROOP_TABLE[1].a2 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a2); + table->AVFSGB_VDROOP_TABLE[0].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_m1); + table->AVFSGB_VDROOP_TABLE[0].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSON_m2); + table->AVFSGB_VDROOP_TABLE[0].b = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_b); + table->AVFSGB_VDROOP_TABLE[0].m1_shift = 24; + table->AVFSGB_VDROOP_TABLE[0].m2_shift = 12; + table->AVFSGB_VDROOP_TABLE[1].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_m1); + table->AVFSGB_VDROOP_TABLE[1].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSOFF_m2); + table->AVFSGB_VDROOP_TABLE[1].b = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_b); + table->AVFSGB_VDROOP_TABLE[1].m1_shift = 24; + table->AVFSGB_VDROOP_TABLE[1].m2_shift = 12; + table->MaxVoltage = PP_HOST_TO_SMC_US(avfs_params.usMaxVoltage_0_25mv); + AVFS_meanNsigma.Aconstant[0] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant0); + AVFS_meanNsigma.Aconstant[1] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant1); + AVFS_meanNsigma.Aconstant[2] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant2); + AVFS_meanNsigma.DC_tol_sigma = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_DC_tol_sigma); + AVFS_meanNsigma.Platform_mean = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_mean); + AVFS_meanNsigma.PSM_Age_CompFactor = PP_HOST_TO_SMC_US(avfs_params.usPSM_Age_ComFactor); + AVFS_meanNsigma.Platform_sigma = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_sigma); + + for (i = 0; i < NUM_VFT_COLUMNS; i++) { + AVFS_meanNsigma.Static_Voltage_Offset[i] = (uint8_t)(sclk_table->entries[i].cks_voffset * 100 / 625); + AVFS_SclkOffset.Sclk_Offset[i] = PP_HOST_TO_SMC_US((uint16_t)(sclk_table->entries[i].sclk_offset) / 100); + } + + result = polaris10_read_smc_sram_dword(smumgr, + SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsMeanNSigma), + &tmp, data->sram_end); + + polaris10_copy_bytes_to_smc(smumgr, + tmp, + (uint8_t *)&AVFS_meanNsigma, + sizeof(AVFS_meanNsigma_t), + data->sram_end); + + result = polaris10_read_smc_sram_dword(smumgr, + SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsSclkOffsetTable), + &tmp, data->sram_end); + polaris10_copy_bytes_to_smc(smumgr, + tmp, + (uint8_t *)&AVFS_SclkOffset, + sizeof(AVFS_Sclk_Offset_t), + data->sram_end); + + data->avfs_vdroop_override_setting = (avfs_params.ucEnableGB_VDROOP_TABLE_CKSON << BTCGB0_Vdroop_Enable_SHIFT) | + (avfs_params.ucEnableGB_VDROOP_TABLE_CKSOFF << BTCGB1_Vdroop_Enable_SHIFT) | + (avfs_params.ucEnableGB_FUSE_TABLE_CKSON << AVFSGB0_Vdroop_Enable_SHIFT) | + (avfs_params.ucEnableGB_FUSE_TABLE_CKSOFF << AVFSGB1_Vdroop_Enable_SHIFT); + data->apply_avfs_cks_off_voltage = (avfs_params.ucEnableApplyAVFS_CKS_OFF_Voltage == 1) ? true : false; + } + return result; +} + + /** * Initializes the SMC table and uploads it * @@ -2056,6 +2085,10 @@ static int polaris10_init_smc_table(struct pp_hwmgr *hwmgr) "Failed to populate Clock Stretcher Data Table!", return result); } + + result = polaris10_populate_avfs_parameters(hwmgr); + PP_ASSERT_WITH_CODE(0 == result, "Failed to populate AVFS Parameters!", return result;); + table->CurrSclkPllRange = 0xff; table->GraphicsVoltageChangeEnable = 1; table->GraphicsThermThrottleEnable = 1; @@ -2252,6 +2285,9 @@ static int polaris10_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr) static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t soft_register_value = 0; + uint32_t handshake_disables_offset = data->soft_regs_start + + offsetof(SMU74_SoftRegisters, HandshakeDisables); /* enable SCLK dpm */ if (!data->sclk_dpm_key_disabled) @@ -2262,6 +2298,12 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) /* enable MCLK dpm */ if (0 == data->mclk_dpm_key_disabled) { +/* Disable UVD - SMU handshake for MCLK. */ + soft_register_value = cgs_read_ind_register(hwmgr->device, + CGS_IND_REG__SMC, handshake_disables_offset); + soft_register_value |= SMU7_UVD_MCLK_HANDSHAKE_DISABLE; + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + handshake_disables_offset, soft_register_value); PP_ASSERT_WITH_CODE( (0 == smum_send_msg_to_smc(hwmgr->smumgr, @@ -2269,7 +2311,6 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) "Failed to enable MCLK DPM during DPM Start Function!", return -1); - PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1); cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x5); @@ -2471,6 +2512,8 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to enable VR hot GPIO interrupt!", result = tmp_result); + smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay); + tmp_result = polaris10_enable_sclk_control(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to enable SCLK control!", result = tmp_result); @@ -2606,6 +2649,7 @@ int polaris10_set_features_platform_caps(struct pp_hwmgr *hwmgr) phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_FanSpeedInTableIsRPM); + if (hwmgr->chip_id == CHIP_POLARIS11) phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SPLLShutdownSupport); @@ -2638,7 +2682,7 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); uint16_t vv_id; - uint16_t vddc = 0; + uint32_t vddc = 0; uint16_t i, j; uint32_t sclk = 0; struct phm_ppt_v1_information *table_info = @@ -2669,8 +2713,9 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) continue); - /* need to make sure vddc is less than 2v or else, it could burn the ASIC. */ - PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0), + /* need to make sure vddc is less than 2v or else, it could burn the ASIC. + * real voltage level in unit of 0.01mv */ + PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0), "Invalid VDDC value", result = -EINVAL;); /* the voltage should not be zero nor equal to leakage ID */ @@ -2896,6 +2941,31 @@ static int polaris10_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr) return 0; } +int polaris10_patch_voltage_workaround(struct pp_hwmgr *hwmgr) +{ + struct phm_ppt_v1_information *table_info = + (struct phm_ppt_v1_information *)(hwmgr->pptable); + struct phm_ppt_v1_clock_voltage_dependency_table *dep_mclk_table = + table_info->vdd_dep_on_mclk; + struct phm_ppt_v1_voltage_lookup_table *lookup_table = + table_info->vddc_lookup_table; + uint32_t i; + + if (hwmgr->chip_id == CHIP_POLARIS10 && hwmgr->hw_revision == 0xC7) { + if (lookup_table->entries[dep_mclk_table->entries[dep_mclk_table->count-1].vddInd].us_vdd >= 1000) + return 0; + + for (i = 0; i < lookup_table->count; i++) { + if (lookup_table->entries[i].us_vdd < 0xff01 && lookup_table->entries[i].us_vdd >= 1000) { + dep_mclk_table->entries[dep_mclk_table->count-1].vddInd = (uint8_t) i; + return 0; + } + } + } + return 0; +} + + int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); @@ -2938,6 +3008,11 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vddci_control = POLARIS10_VOLTAGE_CONTROL_NONE; data->mvdd_control = POLARIS10_VOLTAGE_CONTROL_NONE; + data->enable_tdc_limit_feature = true; + data->enable_pkg_pwr_tracking_feature = true; + data->force_pcie_gen = PP_PCIEGenInvalid; + data->mclk_stutter_mode_threshold = 40000; + if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) data->voltage_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2; @@ -2962,8 +3037,13 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vddci_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2; } + if (table_info->cac_dtp_table->usClockStretchAmount != 0) + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_ClockStretcher); + polaris10_set_features_platform_caps(hwmgr); + polaris10_patch_voltage_workaround(hwmgr); polaris10_init_dpm_defaults(hwmgr); /* Get leakage voltage based on leakage ID. */ @@ -3520,10 +3600,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, ATOM_Tonga_State *state_entry = (ATOM_Tonga_State *)state; ATOM_Tonga_POWERPLAYTABLE *powerplay_table = (ATOM_Tonga_POWERPLAYTABLE *)pp_table; - ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table = - (ATOM_Tonga_SCLK_Dependency_Table *) + PPTable_Generic_SubTable_Header *sclk_dep_table = + (PPTable_Generic_SubTable_Header *) (((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usSclkDependencyTableOffset)); + ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table = (ATOM_Tonga_MCLK_Dependency_Table *) (((unsigned long)powerplay_table) + @@ -3575,7 +3656,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, /* Performance levels are arranged from low to high. */ performance_level->memory_clock = mclk_dep_table->entries [state_entry->ucMemoryClockIndexLow].ulMclk; - performance_level->engine_clock = sclk_dep_table->entries + if (sclk_dep_table->ucRevId == 0) + performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries + [state_entry->ucEngineClockIndexLow].ulSclk; + else if (sclk_dep_table->ucRevId == 1) + performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries [state_entry->ucEngineClockIndexLow].ulSclk; performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap, state_entry->ucPCIEGenLow); @@ -3586,8 +3671,14 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, [polaris10_power_state->performance_level_count++]); performance_level->memory_clock = mclk_dep_table->entries [state_entry->ucMemoryClockIndexHigh].ulMclk; - performance_level->engine_clock = sclk_dep_table->entries + + if (sclk_dep_table->ucRevId == 0) + performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries + [state_entry->ucEngineClockIndexHigh].ulSclk; + else if (sclk_dep_table->ucRevId == 1) + performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries [state_entry->ucEngineClockIndexHigh].ulSclk; + performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap, state_entry->ucPCIEGenHigh); performance_level->pcie_lane = get_pcie_lane_support(data->pcie_lane_cap, @@ -3645,7 +3736,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr, switch (state->classification.ui_label) { case PP_StateUILabel_Performance: data->use_pcie_performance_levels = true; - for (i = 0; i < ps->performance_level_count; i++) { if (data->pcie_gen_performance.max < ps->performance_levels[i].pcie_gen) @@ -3661,7 +3751,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr, ps->performance_levels[i].pcie_lane) data->pcie_lane_performance.max = ps->performance_levels[i].pcie_lane; - if (data->pcie_lane_performance.min > ps->performance_levels[i].pcie_lane) data->pcie_lane_performance.min = @@ -4187,12 +4276,9 @@ int polaris10_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); uint32_t mm_boot_level_offset, mm_boot_level_value; - struct phm_ppt_v1_information *table_info = - (struct phm_ppt_v1_information *)(hwmgr->pptable); if (!bgate) { - data->smc_state_table.SamuBootLevel = - (uint8_t) (table_info->mm_dep_table->count - 1); + data->smc_state_table.SamuBootLevel = 0; mm_boot_level_offset = data->dpm_table_start + offsetof(SMU74_Discrete_DpmTable, SamuBootLevel); mm_boot_level_offset /= 4; @@ -4327,6 +4413,15 @@ static int polaris10_notify_link_speed_change_after_state_change( return 0; } +static int polaris10_notify_smc_display(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + + smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + (PPSMC_Msg)PPSMC_MSG_SetVBITimeout, data->frame_time_x2); + return (smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay) == 0) ? 0 : -EINVAL; +} + static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input) { int tmp_result, result = 0; @@ -4375,6 +4470,11 @@ static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *i "Failed to program memory timing parameters!", result = tmp_result); + tmp_result = polaris10_notify_smc_display(hwmgr); + PP_ASSERT_WITH_CODE((0 == tmp_result), + "Failed to notify smc display settings!", + result = tmp_result); + tmp_result = polaris10_unfreeze_sclk_mclk_dpm(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to unfreeze SCLK MCLK DPM!", @@ -4409,6 +4509,7 @@ static int polaris10_set_max_fan_pwm_output(struct pp_hwmgr *hwmgr, uint16_t us_ PPSMC_MSG_SetFanPwmMax, us_max_fan_pwm); } + int polaris10_notify_smc_display_change(struct pp_hwmgr *hwmgr, bool has_display) { PPSMC_Msg msg = has_display ? (PPSMC_Msg)PPSMC_HasDisplay : (PPSMC_Msg)PPSMC_NoDisplay; @@ -4428,8 +4529,6 @@ int polaris10_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwm if (num_active_displays > 1) /* to do && (pHwMgr->pPECI->displayConfiguration.bMultiMonitorInSync != TRUE)) */ polaris10_notify_smc_display_change(hwmgr, false); - else - polaris10_notify_smc_display_change(hwmgr, true); return 0; } @@ -4470,6 +4569,8 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr) frame_time_in_us = 1000000 / refresh_rate; pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us; + data->frame_time_x2 = frame_time_in_us * 2 / 100; + display_gap2 = pre_vbi_time_in_us * (ref_clock / 100); cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL2, display_gap2); @@ -4478,8 +4579,6 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr) cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start + offsetof(SMU74_SoftRegisters, VBlankTimeout), (frame_time_in_us - pre_vbi_time_in_us)); - polaris10_notify_smc_display_change(hwmgr, num_active_displays != 0); - return 0; } @@ -4591,7 +4690,7 @@ int polaris10_upload_mc_firmware(struct pp_hwmgr *hwmgr) return 0; } - data->need_long_memory_training = true; + data->need_long_memory_training = false; /* * PPMCME_FirmwareDescriptorEntry *pfd = NULL; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h index beedf35cbfa6..afc3434822d1 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h @@ -312,6 +312,10 @@ struct polaris10_hwmgr { /* soft pptable for re-uploading into smu */ void *soft_pp_table; + + uint32_t avfs_vdroop_override_setting; + bool apply_avfs_cks_off_voltage; + uint32_t frame_time_x2; }; /* To convert to Q8.8 format for firmware */ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c index aba167f7d167..b206632d4650 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c @@ -625,10 +625,14 @@ static int tf_polaris10_thermal_avfs_enable(struct pp_hwmgr *hwmgr, int ret; struct pp_smumgr *smumgr = (struct pp_smumgr *)(hwmgr->smumgr); struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend); + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - if (smu_data->avfs.avfs_btc_status != AVFS_BTC_ENABLEAVFS) + if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED) return 0; + ret = smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + PPSMC_MSG_SetGBDroopSettings, data->avfs_vdroop_override_setting); + ret = (smum_send_msg_to_smc(smumgr, PPSMC_MSG_EnableAvfs) == 0) ? 0 : -1; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c index 58742e0d1492..a3c38bbd1e94 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c @@ -44,6 +44,20 @@ bool acpi_atcs_functions_supported(void *device, uint32_t index) return result == 0 ? (output_buf.function_bits & (1 << (index - 1))) != 0 : false; } +bool acpi_atcs_notify_pcie_device_ready(void *device) +{ + int32_t temp_buffer = 1; + + return cgs_call_acpi_method(device, CGS_ACPI_METHOD_ATCS, + ATCS_FUNCTION_PCIE_DEVICE_READY_NOTIFICATION, + &temp_buffer, + NULL, + 0, + sizeof(temp_buffer), + 0); +} + + int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise) { struct atcs_pref_req_input atcs_input; @@ -52,7 +66,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise) int result; struct cgs_system_info info = {0}; - if (!acpi_atcs_functions_supported(device, ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST)) + if( 0 != acpi_atcs_notify_pcie_device_ready(device)) return -EINVAL; info.size = sizeof(struct cgs_system_info); @@ -77,7 +91,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise) ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST, &atcs_input, &atcs_output, - 0, + 1, sizeof(atcs_input), sizeof(atcs_output)); if (result != 0) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c index da9f5f1b6dc2..90b35c5c10a4 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c @@ -1256,7 +1256,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, } int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage) + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage) { int result; @@ -1274,7 +1274,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_ if (0 != result) return result; - *voltage = get_voltage_info_param_space.usVoltageLevel; + *voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel; return result; } @@ -1302,3 +1302,46 @@ int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctr return 0; } + +int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param) +{ + ATOM_ASIC_PROFILING_INFO_V3_6 *profile = NULL; + + if (param == NULL) + return -EINVAL; + + profile = (ATOM_ASIC_PROFILING_INFO_V3_6 *) + cgs_atom_get_data_table(hwmgr->device, + GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo), + NULL, NULL, NULL); + if (!profile) + return -1; + + param->ulAVFS_meanNsigma_Acontant0 = profile->ulAVFS_meanNsigma_Acontant0; + param->ulAVFS_meanNsigma_Acontant1 = profile->ulAVFS_meanNsigma_Acontant1; + param->ulAVFS_meanNsigma_Acontant2 = profile->ulAVFS_meanNsigma_Acontant2; + param->usAVFS_meanNsigma_DC_tol_sigma = profile->usAVFS_meanNsigma_DC_tol_sigma; + param->usAVFS_meanNsigma_Platform_mean = profile->usAVFS_meanNsigma_Platform_mean; + param->usAVFS_meanNsigma_Platform_sigma = profile->usAVFS_meanNsigma_Platform_sigma; + param->ulGB_VDROOP_TABLE_CKSOFF_a0 = profile->ulGB_VDROOP_TABLE_CKSOFF_a0; + param->ulGB_VDROOP_TABLE_CKSOFF_a1 = profile->ulGB_VDROOP_TABLE_CKSOFF_a1; + param->ulGB_VDROOP_TABLE_CKSOFF_a2 = profile->ulGB_VDROOP_TABLE_CKSOFF_a2; + param->ulGB_VDROOP_TABLE_CKSON_a0 = profile->ulGB_VDROOP_TABLE_CKSON_a0; + param->ulGB_VDROOP_TABLE_CKSON_a1 = profile->ulGB_VDROOP_TABLE_CKSON_a1; + param->ulGB_VDROOP_TABLE_CKSON_a2 = profile->ulGB_VDROOP_TABLE_CKSON_a2; + param->ulAVFSGB_FUSE_TABLE_CKSOFF_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_m1; + param->usAVFSGB_FUSE_TABLE_CKSOFF_m2 = profile->usAVFSGB_FUSE_TABLE_CKSOFF_m2; + param->ulAVFSGB_FUSE_TABLE_CKSOFF_b = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_b; + param->ulAVFSGB_FUSE_TABLE_CKSON_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSON_m1; + param->usAVFSGB_FUSE_TABLE_CKSON_m2 = profile->usAVFSGB_FUSE_TABLE_CKSON_m2; + param->ulAVFSGB_FUSE_TABLE_CKSON_b = profile->ulAVFSGB_FUSE_TABLE_CKSON_b; + param->usMaxVoltage_0_25mv = profile->usMaxVoltage_0_25mv; + param->ucEnableGB_VDROOP_TABLE_CKSOFF = profile->ucEnableGB_VDROOP_TABLE_CKSOFF; + param->ucEnableGB_VDROOP_TABLE_CKSON = profile->ucEnableGB_VDROOP_TABLE_CKSON; + param->ucEnableGB_FUSE_TABLE_CKSOFF = profile->ucEnableGB_FUSE_TABLE_CKSOFF; + param->ucEnableGB_FUSE_TABLE_CKSON = profile->ucEnableGB_FUSE_TABLE_CKSON; + param->usPSM_Age_ComFactor = profile->usPSM_Age_ComFactor; + param->ucEnableApplyAVFS_CKS_OFF_Voltage = profile->ucEnableApplyAVFS_CKS_OFF_Voltage; + + return 0; +} diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h index d24ebb566905..1e35a9625baf 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h @@ -250,6 +250,35 @@ struct pp_atomctrl_gpio_pin_assignment { }; typedef struct pp_atomctrl_gpio_pin_assignment pp_atomctrl_gpio_pin_assignment; +struct pp_atom_ctrl__avfs_parameters { + uint32_t ulAVFS_meanNsigma_Acontant0; + uint32_t ulAVFS_meanNsigma_Acontant1; + uint32_t ulAVFS_meanNsigma_Acontant2; + uint16_t usAVFS_meanNsigma_DC_tol_sigma; + uint16_t usAVFS_meanNsigma_Platform_mean; + uint16_t usAVFS_meanNsigma_Platform_sigma; + uint32_t ulGB_VDROOP_TABLE_CKSOFF_a0; + uint32_t ulGB_VDROOP_TABLE_CKSOFF_a1; + uint32_t ulGB_VDROOP_TABLE_CKSOFF_a2; + uint32_t ulGB_VDROOP_TABLE_CKSON_a0; + uint32_t ulGB_VDROOP_TABLE_CKSON_a1; + uint32_t ulGB_VDROOP_TABLE_CKSON_a2; + uint32_t ulAVFSGB_FUSE_TABLE_CKSOFF_m1; + uint16_t usAVFSGB_FUSE_TABLE_CKSOFF_m2; + uint32_t ulAVFSGB_FUSE_TABLE_CKSOFF_b; + uint32_t ulAVFSGB_FUSE_TABLE_CKSON_m1; + uint16_t usAVFSGB_FUSE_TABLE_CKSON_m2; + uint32_t ulAVFSGB_FUSE_TABLE_CKSON_b; + uint16_t usMaxVoltage_0_25mv; + uint8_t ucEnableGB_VDROOP_TABLE_CKSOFF; + uint8_t ucEnableGB_VDROOP_TABLE_CKSON; + uint8_t ucEnableGB_FUSE_TABLE_CKSOFF; + uint8_t ucEnableGB_FUSE_TABLE_CKSON; + uint16_t usPSM_Age_ComFactor; + uint8_t ucEnableApplyAVFS_CKS_OFF_Voltage; + uint8_t ucReserved; +}; + extern bool atomctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pinId, pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment); extern int atomctrl_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage); extern uint32_t atomctrl_get_mpll_reference_clock(struct pp_hwmgr *hwmgr); @@ -276,7 +305,10 @@ extern int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, uint32_t extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, uint8_t level); extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage); + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage); extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table); + +extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param); + #endif diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c index d27e8c40602a..5d0f655bf160 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c @@ -1302,7 +1302,7 @@ static int tonga_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[count] |= data->mvdd_voltage_table.entries[count].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount); } @@ -4489,6 +4489,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vdd_ci_control = TONGA_VOLTAGE_CONTROL_NONE; data->vdd_gfx_control = TONGA_VOLTAGE_CONTROL_NONE; data->mvdd_control = TONGA_VOLTAGE_CONTROL_NONE; + data->force_pcie_gen = PP_PCIEGenInvalid; if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) { diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h index 1b44f4e9b8f5..f127198aafc4 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h @@ -197,6 +197,22 @@ typedef struct _ATOM_Tonga_SCLK_Dependency_Table { ATOM_Tonga_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ } ATOM_Tonga_SCLK_Dependency_Table; +typedef struct _ATOM_Polaris_SCLK_Dependency_Record { + UCHAR ucVddInd; /* Base voltage */ + USHORT usVddcOffset; /* Offset relative to base voltage */ + ULONG ulSclk; + USHORT usEdcCurrent; + UCHAR ucReliabilityTemperature; + UCHAR ucCKSVOffsetandDisable; /* Bits 0~6: Voltage offset for CKS, Bit 7: Disable/enable for the SCLK level. */ + ULONG ulSclkOffset; +} ATOM_Polaris_SCLK_Dependency_Record; + +typedef struct _ATOM_Polaris_SCLK_Dependency_Table { + UCHAR ucRevId; + UCHAR ucNumEntries; /* Number of entries. */ + ATOM_Polaris_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ +} ATOM_Polaris_SCLK_Dependency_Table; + typedef struct _ATOM_Tonga_PCIE_Record { UCHAR ucPCIEGenSpeed; UCHAR usPCIELaneWidth; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c index 296ec7ef6d45..dccc859f638c 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c @@ -302,7 +302,7 @@ static int init_dpm_2_parameters( (((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset)); if (0 != powerplay_table->usPPMTableOffset) { - if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) { + if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) { phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_EnablePlatformPowerManagement); } @@ -408,41 +408,78 @@ static int get_mclk_voltage_dependency_table( static int get_sclk_voltage_dependency_table( struct pp_hwmgr *hwmgr, phm_ppt_v1_clock_voltage_dependency_table **pp_tonga_sclk_dep_table, - const ATOM_Tonga_SCLK_Dependency_Table * sclk_dep_table + const PPTable_Generic_SubTable_Header *sclk_dep_table ) { uint32_t table_size, i; phm_ppt_v1_clock_voltage_dependency_table *sclk_table; - PP_ASSERT_WITH_CODE((0 != sclk_dep_table->ucNumEntries), - "Invalid PowerPlay Table!", return -1); + if (sclk_dep_table->ucRevId < 1) { + const ATOM_Tonga_SCLK_Dependency_Table *tonga_table = + (ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table; - table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record) - * sclk_dep_table->ucNumEntries; + PP_ASSERT_WITH_CODE((0 != tonga_table->ucNumEntries), + "Invalid PowerPlay Table!", return -1); - sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *) - kzalloc(table_size, GFP_KERNEL); + table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record) + * tonga_table->ucNumEntries; - if (NULL == sclk_table) - return -ENOMEM; + sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *) + kzalloc(table_size, GFP_KERNEL); - memset(sclk_table, 0x00, table_size); - - sclk_table->count = (uint32_t)sclk_dep_table->ucNumEntries; - - for (i = 0; i < sclk_dep_table->ucNumEntries; i++) { - sclk_table->entries[i].vddInd = - sclk_dep_table->entries[i].ucVddInd; - sclk_table->entries[i].vdd_offset = - sclk_dep_table->entries[i].usVddcOffset; - sclk_table->entries[i].clk = - sclk_dep_table->entries[i].ulSclk; - sclk_table->entries[i].cks_enable = - (((sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0; - sclk_table->entries[i].cks_voffset = - (sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x7F); - } + if (NULL == sclk_table) + return -ENOMEM; + + memset(sclk_table, 0x00, table_size); + + sclk_table->count = (uint32_t)tonga_table->ucNumEntries; + + for (i = 0; i < tonga_table->ucNumEntries; i++) { + sclk_table->entries[i].vddInd = + tonga_table->entries[i].ucVddInd; + sclk_table->entries[i].vdd_offset = + tonga_table->entries[i].usVddcOffset; + sclk_table->entries[i].clk = + tonga_table->entries[i].ulSclk; + sclk_table->entries[i].cks_enable = + (((tonga_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0; + sclk_table->entries[i].cks_voffset = + (tonga_table->entries[i].ucCKSVOffsetandDisable & 0x7F); + } + } else { + const ATOM_Polaris_SCLK_Dependency_Table *polaris_table = + (ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table; + PP_ASSERT_WITH_CODE((0 != polaris_table->ucNumEntries), + "Invalid PowerPlay Table!", return -1); + + table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record) + * polaris_table->ucNumEntries; + + sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *) + kzalloc(table_size, GFP_KERNEL); + + if (NULL == sclk_table) + return -ENOMEM; + + memset(sclk_table, 0x00, table_size); + + sclk_table->count = (uint32_t)polaris_table->ucNumEntries; + + for (i = 0; i < polaris_table->ucNumEntries; i++) { + sclk_table->entries[i].vddInd = + polaris_table->entries[i].ucVddInd; + sclk_table->entries[i].vdd_offset = + polaris_table->entries[i].usVddcOffset; + sclk_table->entries[i].clk = + polaris_table->entries[i].ulSclk; + sclk_table->entries[i].cks_enable = + (((polaris_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0; + sclk_table->entries[i].cks_voffset = + (polaris_table->entries[i].ucCKSVOffsetandDisable & 0x7F); + sclk_table->entries[i].sclk_offset = polaris_table->entries[i].ulSclkOffset; + } + } *pp_tonga_sclk_dep_table = sclk_table; return 0; @@ -708,8 +745,8 @@ static int init_clock_voltage_dependency( const ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table = (const ATOM_Tonga_MCLK_Dependency_Table *)(((unsigned long) powerplay_table) + le16_to_cpu(powerplay_table->usMclkDependencyTableOffset)); - const ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table = - (const ATOM_Tonga_SCLK_Dependency_Table *)(((unsigned long) powerplay_table) + + const PPTable_Generic_SubTable_Header *sclk_dep_table = + (const PPTable_Generic_SubTable_Header *)(((unsigned long) powerplay_table) + le16_to_cpu(powerplay_table->usSclkDependencyTableOffset)); const ATOM_Tonga_Hard_Limit_Table *pHardLimits = (const ATOM_Tonga_Hard_Limit_Table *)(((unsigned long) powerplay_table) + diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h index 28f571449495..77e8e33d5870 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h @@ -411,6 +411,8 @@ struct phm_cac_tdp_table { uint8_t ucVr_I2C_Line; uint8_t ucPlx_I2C_address; uint8_t ucPlx_I2C_Line; + uint32_t usBoostPowerLimit; + uint8_t ucCKS_LDO_REFSEL; }; struct phm_ppm_table { diff --git a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h index 0c6a413eaa5b..b8f4b73c322e 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h @@ -27,6 +27,7 @@ #pragma pack(push, 1) +#define PPSMC_MSG_SetGBDroopSettings ((uint16_t) 0x305) #define PPSMC_SWSTATE_FLAG_DC 0x01 #define PPSMC_SWSTATE_FLAG_UVD 0x02 @@ -391,6 +392,8 @@ typedef uint16_t PPSMC_Result; #define PPSMC_MSG_SetGpuPllDfsForSclk ((uint16_t) 0x300) #define PPSMC_MSG_Didt_Block_Function ((uint16_t) 0x301) +#define PPSMC_MSG_SetVBITimeout ((uint16_t) 0x306) + #define PPSMC_MSG_SecureSRBMWrite ((uint16_t) 0x600) #define PPSMC_MSG_SecureSRBMRead ((uint16_t) 0x601) #define PPSMC_MSG_SetAddress ((uint16_t) 0x800) diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h index 3bd5e69b9045..3df5de2cdab0 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h +++ b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h @@ -26,3 +26,4 @@ extern bool acpi_atcs_functions_supported(void *device, extern int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise); +extern bool acpi_atcs_notify_pcie_device_ready(void *device); diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74.h b/drivers/gpu/drm/amd/powerplay/inc/smu74.h index 1a12d85b8e97..fd10a9fa843d 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu74.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu74.h @@ -34,6 +34,30 @@ #define SMU__NUM_LCLK_DPM_LEVELS 8 #define SMU__NUM_PCIE_DPM_LEVELS 8 +#define EXP_M1 35 +#define EXP_M2 92821 +#define EXP_B 66629747 + +#define EXP_M1_1 365 +#define EXP_M2_1 658700 +#define EXP_B_1 305506134 + +#define EXP_M1_2 189 +#define EXP_M2_2 379692 +#define EXP_B_2 194609469 + +#define EXP_M1_3 99 +#define EXP_M2_3 217915 +#define EXP_B_3 122255994 + +#define EXP_M1_4 51 +#define EXP_M2_4 122643 +#define EXP_B_4 74893384 + +#define EXP_M1_5 423 +#define EXP_M2_5 1103326 +#define EXP_B_5 728122621 + enum SID_OPTION { SID_OPTION_HI, SID_OPTION_LO, @@ -548,20 +572,20 @@ struct SMU74_Firmware_Header { uint32_t CacConfigTable; uint32_t CacStatusTable; - uint32_t mcRegisterTable; - uint32_t mcArbDramTimingTable; - - - uint32_t PmFuseTable; uint32_t Globals; uint32_t ClockStretcherTable; uint32_t VftTable; - uint32_t Reserved[21]; + uint32_t Reserved1; + uint32_t AvfsTable; + uint32_t AvfsCksOffGbvTable; + uint32_t AvfsMeanNSigma; + uint32_t AvfsSclkOffsetTable; + uint32_t Reserved[16]; uint32_t Signature; }; @@ -701,8 +725,6 @@ VR Config info is contained in dpmTable.VRConfig */ struct SMU_ClockStretcherDataTableEntry { uint8_t minVID; uint8_t maxVID; - - uint16_t setting; }; typedef struct SMU_ClockStretcherDataTableEntry SMU_ClockStretcherDataTableEntry; @@ -769,6 +791,43 @@ struct VFT_TABLE_t { typedef struct VFT_TABLE_t VFT_TABLE_t; +/* Total margin, root mean square of Fmax + DC + Platform */ +struct AVFS_Margin_t { + VFT_CELL_t Cell[NUM_VFT_COLUMNS]; +}; +typedef struct AVFS_Margin_t AVFS_Margin_t; + +#define BTCGB_VDROOP_TABLE_MAX_ENTRIES 2 +#define AVFSGB_VDROOP_TABLE_MAX_ENTRIES 2 + +struct GB_VDROOP_TABLE_t { + int32_t a0; + int32_t a1; + int32_t a2; + uint32_t spare; +}; +typedef struct GB_VDROOP_TABLE_t GB_VDROOP_TABLE_t; + +struct AVFS_CksOff_Gbv_t { + VFT_CELL_t Cell[NUM_VFT_COLUMNS]; +}; +typedef struct AVFS_CksOff_Gbv_t AVFS_CksOff_Gbv_t; + +struct AVFS_meanNsigma_t { + uint32_t Aconstant[3]; + uint16_t DC_tol_sigma; + uint16_t Platform_mean; + uint16_t Platform_sigma; + uint16_t PSM_Age_CompFactor; + uint8_t Static_Voltage_Offset[NUM_VFT_COLUMNS]; +}; +typedef struct AVFS_meanNsigma_t AVFS_meanNsigma_t; + +struct AVFS_Sclk_Offset_t { + uint16_t Sclk_Offset[8]; +}; +typedef struct AVFS_Sclk_Offset_t AVFS_Sclk_Offset_t; + #endif diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h index 0dfe82336dc7..899d6d8108c2 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h @@ -223,6 +223,16 @@ struct SMU74_Discrete_StateInfo { typedef struct SMU74_Discrete_StateInfo SMU74_Discrete_StateInfo; +struct SMU_QuadraticCoeffs { + int32_t m1; + uint32_t b; + + int16_t m2; + uint8_t m1_shift; + uint8_t m2_shift; +}; +typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs; + struct SMU74_Discrete_DpmTable { SMU74_PIDController GraphicsPIDController; @@ -258,7 +268,15 @@ struct SMU74_Discrete_DpmTable { uint8_t ThermOutPolarity; uint8_t ThermOutMode; uint8_t BootPhases; - uint32_t Reserved[4]; + + uint8_t VRHotLevel; + uint8_t LdoRefSel; + uint8_t Reserved1[2]; + uint16_t FanStartTemperature; + uint16_t FanStopTemperature; + uint16_t MaxVoltage; + uint16_t Reserved2; + uint32_t Reserved[1]; SMU74_Discrete_GraphicsLevel GraphicsLevel[SMU74_MAX_LEVELS_GRAPHICS]; SMU74_Discrete_MemoryLevel MemoryACPILevel; @@ -347,6 +365,8 @@ struct SMU74_Discrete_DpmTable { uint32_t CurrSclkPllRange; sclkFcwRange_t SclkFcwRangeTable[NUM_SCLK_RANGE]; + GB_VDROOP_TABLE_t BTCGB_VDROOP_TABLE[BTCGB_VDROOP_TABLE_MAX_ENTRIES]; + SMU_QuadraticCoeffs AVFSGB_VDROOP_TABLE[AVFSGB_VDROOP_TABLE_MAX_ENTRIES]; }; typedef struct SMU74_Discrete_DpmTable SMU74_Discrete_DpmTable; @@ -550,16 +570,6 @@ struct SMU7_AcpiScoreboard { typedef struct SMU7_AcpiScoreboard SMU7_AcpiScoreboard; -struct SMU_QuadraticCoeffs { - int32_t m1; - uint32_t b; - - int16_t m2; - uint8_t m1_shift; - uint8_t m2_shift; -}; -typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs; - struct SMU74_Discrete_PmFuses { uint8_t BapmVddCVidHiSidd[8]; uint8_t BapmVddCVidLoSidd[8]; @@ -821,6 +831,17 @@ typedef struct SMU7_GfxCuPgScoreboard SMU7_GfxCuPgScoreboard; #define DB_PCC_SHIFT 26 #define DB_EDC_SHIFT 27 +#define BTCGB0_Vdroop_Enable_MASK 0x1 +#define BTCGB1_Vdroop_Enable_MASK 0x2 +#define AVFSGB0_Vdroop_Enable_MASK 0x4 +#define AVFSGB1_Vdroop_Enable_MASK 0x8 + +#define BTCGB0_Vdroop_Enable_SHIFT 0 +#define BTCGB1_Vdroop_Enable_SHIFT 1 +#define AVFSGB0_Vdroop_Enable_SHIFT 2 +#define AVFSGB1_Vdroop_Enable_SHIFT 3 + + #pragma pack(pop) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c index 043b6ac09d5f..5dba7c509710 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c @@ -52,19 +52,18 @@ static const SMU74_Discrete_GraphicsLevel avfs_graphics_level_polaris10[8] = { /* Min pcie DeepSleep Activity CgSpll CgSpll CcPwr CcPwr Sclk Enabled Enabled Voltage Power */ /* Voltage, DpmLevel, DivId, Level, FuncCntl3, FuncCntl4, DynRm, DynRm1 Did, Padding,ForActivity, ForThrottle, UpHyst, DownHyst, DownHyst, Throttle */ - { 0x3c0fd047, 0x00, 0x03, 0x1e00, 0x00200410, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x30750000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0xa00fd047, 0x01, 0x04, 0x1e00, 0x00800510, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x409c0000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x0410d047, 0x01, 0x00, 0x1e00, 0x00600410, 0x87020000, 0, 0, 0x0e, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x50c30000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x6810d047, 0x01, 0x00, 0x1e00, 0x00800410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x60ea0000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0xcc10d047, 0x01, 0x00, 0x1e00, 0x00e00410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xe8fd0000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x3011d047, 0x01, 0x00, 0x1e00, 0x00400510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x70110100, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x9411d047, 0x01, 0x00, 0x1e00, 0x00a00510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xf8240100, 0, 0, 0, 0, 0, 0, 0 } }, - { 0xf811d047, 0x01, 0x00, 0x1e00, 0x00000610, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x80380100, 0, 0, 0, 0, 0, 0, 0 } } + { 0x100ea446, 0x00, 0x03, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x30750000, 0x3000, 0, 0x2600, 0, 0, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } }, + { 0x400ea446, 0x01, 0x04, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x409c0000, 0x2000, 0, 0x1e00, 1, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } }, + { 0x740ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x50c30000, 0x2800, 0, 0x2000, 1, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } }, + { 0xa40ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x60ea0000, 0x3000, 0, 0x2600, 1, 1, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } }, + { 0xd80ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x70110100, 0x3800, 0, 0x2c00, 1, 1, 0x0004, 0x1203, 0xffff, 0x3600, 0xc9e2, 0x2e00 } }, + { 0x3c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x80380100, 0x2000, 0, 0x1e00, 2, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } }, + { 0x6c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x905f0100, 0x2400, 0, 0x1e00, 2, 1, 0x0004, 0x8901, 0xffff, 0x2300, 0x314c, 0x1d00 } }, + { 0xa00fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0xa0860100, 0x2800, 0, 0x2000, 2, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } } }; static const SMU74_Discrete_MemoryLevel avfs_memory_level_polaris10 = - {0x50140000, 0x50140000, 0x00320000, 0x00, 0x00, - 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x0000, 0x00, 0x00}; + {0x100ea446, 0, 0x30750000, 0x01, 0x01, 0x01, 0x00, 0x00, 0x64, 0x00, 0x00, 0x1f00, 0x00, 0x00}; /** * Set the address for reading/writing the SMC SRAM space. @@ -219,6 +218,18 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr) && (0x20100 <= cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMC_PC_C))); } +static bool polaris10_is_hw_avfs_present(struct pp_smumgr *smumgr) +{ + uint32_t efuse; + + efuse = cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMU_EFUSE_0 + (49*4)); + efuse &= 0x00000001; + if (efuse) + return true; + + return false; +} + /** * Send a message to the SMC, and wait for its response. * @@ -228,21 +239,27 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr) */ int polaris10_send_msg_to_smc(struct pp_smumgr *smumgr, uint16_t msg) { + int ret; + if (!polaris10_is_smc_ram_running(smumgr)) return -1; + SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0); - if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP)) - printk("Failed to send Previous Message.\n"); + ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP); + if (ret != 1) + printk("\n failed to send pre message %x ret is %d \n", msg, ret); cgs_write_register(smumgr->device, mmSMC_MESSAGE_0, msg); SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0); - if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP)) - printk("Failed to send Message.\n"); + ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP); + + if (ret != 1) + printk("\n failed to send message %x ret is %d \n", msg, ret); return 0; } @@ -953,6 +970,11 @@ static int polaris10_smu_init(struct pp_smumgr *smumgr) (cgs_handle_t)smu_data->smu_buffer.handle); return -1;); + if (polaris10_is_hw_avfs_present(smumgr)) + smu_data->avfs.avfs_btc_status = AVFS_BTC_BOOT; + else + smu_data->avfs.avfs_btc_status = AVFS_BTC_NOTSUPPORTED; + return 0; } diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c index 39802c0539b6..3d34fc4ca826 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c @@ -266,9 +266,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev) if (!ret) ret = atmel_hlcdc_check_endpoint(dev, &ep); - of_node_put(ep_np); - if (ret) + if (ret) { + of_node_put(ep_np); return ret; + } } for_each_endpoint_of_node(dev->dev->of_node, ep_np) { @@ -276,9 +277,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev) if (!ret) ret = atmel_hlcdc_attach_endpoint(dev, &ep); - of_node_put(ep_np); - if (ret) + if (ret) { + of_node_put(ep_np); return ret; + } } return 0; diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index aef3ca8a81fa..016c191221f3 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -339,6 +339,8 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane, atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, factor_reg); + } else { + atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0); } } diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index c204ef32df16..9bb99e274d23 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1296,14 +1296,39 @@ EXPORT_SYMBOL(drm_atomic_add_affected_planes); */ void drm_atomic_legacy_backoff(struct drm_atomic_state *state) { + struct drm_device *dev = state->dev; + unsigned crtc_mask = 0; + struct drm_crtc *crtc; int ret; + bool global = false; + + drm_for_each_crtc(crtc, dev) { + if (crtc->acquire_ctx != state->acquire_ctx) + continue; + + crtc_mask |= drm_crtc_mask(crtc); + crtc->acquire_ctx = NULL; + } + + if (WARN_ON(dev->mode_config.acquire_ctx == state->acquire_ctx)) { + global = true; + + dev->mode_config.acquire_ctx = NULL; + } retry: drm_modeset_backoff(state->acquire_ctx); - ret = drm_modeset_lock_all_ctx(state->dev, state->acquire_ctx); + ret = drm_modeset_lock_all_ctx(dev, state->acquire_ctx); if (ret) goto retry; + + drm_for_each_crtc(crtc, dev) + if (drm_crtc_mask(crtc) & crtc_mask) + crtc->acquire_ctx = state->acquire_ctx; + + if (global) + dev->mode_config.acquire_ctx = state->acquire_ctx; } EXPORT_SYMBOL(drm_atomic_legacy_backoff); diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index a6e42433ef0e..26feb2f8453f 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -528,11 +528,11 @@ drm_crtc_helper_disable(struct drm_crtc *crtc) int drm_crtc_helper_set_config(struct drm_mode_set *set) { struct drm_device *dev; - struct drm_crtc *new_crtc; - struct drm_encoder *save_encoders, *new_encoder, *encoder; + struct drm_crtc **save_encoder_crtcs, *new_crtc; + struct drm_encoder **save_connector_encoders, *new_encoder, *encoder; bool mode_changed = false; /* if true do a full mode set */ bool fb_changed = false; /* if true and !mode_changed just do a flip */ - struct drm_connector *save_connectors, *connector; + struct drm_connector *connector; int count = 0, ro, fail = 0; const struct drm_crtc_helper_funcs *crtc_funcs; struct drm_mode_set save_set; @@ -574,15 +574,15 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) * Allocate space for the backup of all (non-pointer) encoder and * connector data. */ - save_encoders = kzalloc(dev->mode_config.num_encoder * - sizeof(struct drm_encoder), GFP_KERNEL); - if (!save_encoders) + save_encoder_crtcs = kzalloc(dev->mode_config.num_encoder * + sizeof(struct drm_crtc *), GFP_KERNEL); + if (!save_encoder_crtcs) return -ENOMEM; - save_connectors = kzalloc(dev->mode_config.num_connector * - sizeof(struct drm_connector), GFP_KERNEL); - if (!save_connectors) { - kfree(save_encoders); + save_connector_encoders = kzalloc(dev->mode_config.num_connector * + sizeof(struct drm_encoder *), GFP_KERNEL); + if (!save_connector_encoders) { + kfree(save_encoder_crtcs); return -ENOMEM; } @@ -593,12 +593,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) */ count = 0; drm_for_each_encoder(encoder, dev) { - save_encoders[count++] = *encoder; + save_encoder_crtcs[count++] = encoder->crtc; } count = 0; drm_for_each_connector(connector, dev) { - save_connectors[count++] = *connector; + save_connector_encoders[count++] = connector->encoder; } save_set.crtc = set->crtc; @@ -631,8 +631,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) mode_changed = true; } - /* take a reference on all connectors in set */ + /* take a reference on all unbound connectors in set, reuse the + * already taken reference for bound connectors + */ for (ro = 0; ro < set->num_connectors; ro++) { + if (set->connectors[ro]->encoder) + continue; drm_connector_reference(set->connectors[ro]); } @@ -754,30 +758,28 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) } } - /* after fail drop reference on all connectors in save set */ - count = 0; - drm_for_each_connector(connector, dev) { - drm_connector_unreference(&save_connectors[count++]); - } - - kfree(save_connectors); - kfree(save_encoders); + kfree(save_connector_encoders); + kfree(save_encoder_crtcs); return 0; fail: /* Restore all previous data. */ count = 0; drm_for_each_encoder(encoder, dev) { - *encoder = save_encoders[count++]; + encoder->crtc = save_encoder_crtcs[count++]; } count = 0; drm_for_each_connector(connector, dev) { - *connector = save_connectors[count++]; + connector->encoder = save_connector_encoders[count++]; } - /* after fail drop reference on all connectors in set */ + /* after fail drop reference on all unbound connectors in set, let + * bound connectors keep their reference + */ for (ro = 0; ro < set->num_connectors; ro++) { + if (set->connectors[ro]->encoder) + continue; drm_connector_unreference(set->connectors[ro]); } @@ -787,8 +789,8 @@ fail: save_set.y, save_set.fb)) DRM_ERROR("failed to restore config after modeset failure\n"); - kfree(save_connectors); - kfree(save_encoders); + kfree(save_connector_encoders); + kfree(save_encoder_crtcs); return ret; } EXPORT_SYMBOL(drm_crtc_helper_set_config); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index a13edf5de2d6..6537908050d7 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -2927,11 +2927,9 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) drm_dp_port_teardown_pdt(port, port->pdt); if (!port->input && port->vcpi.vcpi > 0) { - if (mgr->mst_state) { - drm_dp_mst_reset_vcpi_slots(mgr, port); - drm_dp_update_payload_part1(mgr); - drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); - } + drm_dp_mst_reset_vcpi_slots(mgr, port); + drm_dp_update_payload_part1(mgr); + drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); } kref_put(&port->kref, drm_dp_free_mst_port); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c index 522cfd447892..16353ee81651 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c @@ -225,6 +225,7 @@ struct iommu_domain *etnaviv_iommu_domain_alloc(struct etnaviv_gpu *gpu) etnaviv_domain->domain.type = __IOMMU_DOMAIN_PAGING; etnaviv_domain->domain.ops = &etnaviv_iommu_ops.ops; + etnaviv_domain->domain.pgsize_bitmap = SZ_4K; etnaviv_domain->domain.geometry.aperture_start = GPU_MEM_START; etnaviv_domain->domain.geometry.aperture_end = GPU_MEM_START + PT_ENTRIES * SZ_4K - 1; diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index f6223f907c15..7f9901b7777b 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -31,7 +31,6 @@ #include "exynos_drm_plane.h" #include "exynos_drm_drv.h" #include "exynos_drm_fb.h" -#include "exynos_drm_fbdev.h" #include "exynos_drm_iommu.h" /* diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index 468498e3fec1..4c1fb3f8b5a6 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -34,7 +34,7 @@ struct exynos_dp_device { struct drm_encoder encoder; - struct drm_connector connector; + struct drm_connector *connector; struct drm_bridge *ptn_bridge; struct drm_device *drm_dev; struct device *dev; @@ -70,7 +70,7 @@ static int exynos_dp_poweroff(struct analogix_dp_plat_data *plat_data) static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data) { struct exynos_dp_device *dp = to_dp(plat_data); - struct drm_connector *connector = &dp->connector; + struct drm_connector *connector = dp->connector; struct drm_display_mode *mode; int num_modes = 0; @@ -103,6 +103,7 @@ static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data, int ret; drm_connector_register(connector); + dp->connector = connector; /* Pre-empt DP connector creation if there's a bridge */ if (dp->ptn_bridge) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c index 011211e4167d..edbd98ff293e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_core.c +++ b/drivers/gpu/drm/exynos/exynos_drm_core.c @@ -15,7 +15,6 @@ #include #include "exynos_drm_drv.h" #include "exynos_drm_crtc.h" -#include "exynos_drm_fbdev.h" static LIST_HEAD(exynos_drm_subdrv_list); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 3efe1aa89416..d47216488985 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -30,7 +30,6 @@ #include "exynos_drm_drv.h" #include "exynos_drm_fb.h" -#include "exynos_drm_fbdev.h" #include "exynos_drm_crtc.h" #include "exynos_drm_plane.h" #include "exynos_drm_iommu.h" @@ -120,7 +119,6 @@ static struct fimd_driver_data s3c64xx_fimd_driver_data = { .timing_base = 0x0, .has_clksel = 1, .has_limited_fmt = 1, - .has_hw_trigger = 1, }; static struct fimd_driver_data exynos3_fimd_driver_data = { @@ -171,14 +169,11 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = { .lcdblk_vt_shift = 24, .lcdblk_bypass_shift = 15, .lcdblk_mic_bypass_shift = 11, - .trg_type = I80_HW_TRG, .has_shadowcon = 1, .has_vidoutcon = 1, .has_vtsel = 1, .has_mic_bypass = 1, .has_dp_clk = 1, - .has_hw_trigger = 1, - .has_trigger_per_te = 1, }; struct fimd_context { diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 493552368295..8564c3da0d22 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -48,13 +48,13 @@ /* registers for base address */ #define G2D_SRC_BASE_ADDR 0x0304 -#define G2D_SRC_STRIDE_REG 0x0308 +#define G2D_SRC_STRIDE 0x0308 #define G2D_SRC_COLOR_MODE 0x030C #define G2D_SRC_LEFT_TOP 0x0310 #define G2D_SRC_RIGHT_BOTTOM 0x0314 #define G2D_SRC_PLANE2_BASE_ADDR 0x0318 #define G2D_DST_BASE_ADDR 0x0404 -#define G2D_DST_STRIDE_REG 0x0408 +#define G2D_DST_STRIDE 0x0408 #define G2D_DST_COLOR_MODE 0x040C #define G2D_DST_LEFT_TOP 0x0410 #define G2D_DST_RIGHT_BOTTOM 0x0414 @@ -563,7 +563,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset) switch (reg_offset) { case G2D_SRC_BASE_ADDR: - case G2D_SRC_STRIDE_REG: + case G2D_SRC_STRIDE: case G2D_SRC_COLOR_MODE: case G2D_SRC_LEFT_TOP: case G2D_SRC_RIGHT_BOTTOM: @@ -573,7 +573,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset) reg_type = REG_TYPE_SRC_PLANE2; break; case G2D_DST_BASE_ADDR: - case G2D_DST_STRIDE_REG: + case G2D_DST_STRIDE: case G2D_DST_COLOR_MODE: case G2D_DST_LEFT_TOP: case G2D_DST_RIGHT_BOTTOM: @@ -968,8 +968,8 @@ static int g2d_check_reg_offset(struct device *dev, } else buf_info->types[reg_type] = BUF_TYPE_GEM; break; - case G2D_SRC_STRIDE_REG: - case G2D_DST_STRIDE_REG: + case G2D_SRC_STRIDE: + case G2D_DST_STRIDE: if (for_addr) goto err; diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c index 55f1d37c666a..77f12c00abf9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_plane.c +++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c @@ -242,7 +242,7 @@ exynos_drm_plane_check_size(const struct exynos_drm_plane_config *config, state->v_ratio == (1 << 15)) height_ok = true; - if (width_ok & height_ok) + if (width_ok && height_ok) return 0; DRM_DEBUG_KMS("scaling mode is not supported"); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 32690332d441..103546834b60 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -2365,16 +2365,16 @@ static int i915_ppgtt_info(struct seq_file *m, void *data) task = get_pid_task(file->pid, PIDTYPE_PID); if (!task) { ret = -ESRCH; - goto out_put; + goto out_unlock; } seq_printf(m, "\nproc: %s\n", task->comm); put_task_struct(task); idr_for_each(&file_priv->context_idr, per_file_ctx, (void *)(unsigned long)m); } +out_unlock: mutex_unlock(&dev->filelist_mutex); -out_put: intel_runtime_pm_put(dev_priv); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f313b4d8344f..85c4debf47e0 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -512,6 +512,10 @@ void intel_detect_pch(struct drm_device *dev) DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n"); WARN_ON(!IS_SKYLAKE(dev) && !IS_KABYLAKE(dev)); + } else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) { + dev_priv->pch_type = PCH_KBP; + DRM_DEBUG_KMS("Found KabyPoint PCH\n"); + WARN_ON(!IS_KABYLAKE(dev)); } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) || ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 5faacc6e548d..bc3f2e6842e7 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -990,6 +990,7 @@ enum intel_pch { PCH_CPT, /* Cougarpoint PCH */ PCH_LPT, /* Lynxpoint PCH */ PCH_SPT, /* Sunrisepoint PCH */ + PCH_KBP, /* Kabypoint PCH */ PCH_NOP, }; @@ -2600,6 +2601,15 @@ struct drm_i915_cmd_table { #define IS_BXT_REVID(p, since, until) (IS_BROXTON(p) && IS_REVID(p, since, until)) +#define KBL_REVID_A0 0x0 +#define KBL_REVID_B0 0x1 +#define KBL_REVID_C0 0x2 +#define KBL_REVID_D0 0x3 +#define KBL_REVID_E0 0x4 + +#define IS_KBL_REVID(p, since, until) \ + (IS_KABYLAKE(p) && IS_REVID(p, since, until)) + /* * The genX designation typically refers to the render engine, so render * capability related checks should use IS_GEN, while display and other checks @@ -2708,11 +2718,13 @@ struct drm_i915_cmd_table { #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE 0x9c00 #define INTEL_PCH_SPT_DEVICE_ID_TYPE 0xA100 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE 0x9D00 +#define INTEL_PCH_KBP_DEVICE_ID_TYPE 0xA200 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 #define INTEL_PCH_P3X_DEVICE_ID_TYPE 0x7000 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type) +#define HAS_PCH_KBP(dev) (INTEL_PCH_TYPE(dev) == PCH_KBP) #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT) #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT) #define HAS_PCH_LPT_LP(dev) (__I915__(dev)->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) @@ -3481,6 +3493,7 @@ int intel_bios_init(struct drm_i915_private *dev_priv); bool intel_bios_is_valid_vbt(const void *buf, size_t size); bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv); bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin); +bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port); bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port); bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum port port); bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv, enum port *port); diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 425e721aac58..66571466e9a8 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -40,7 +40,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) if (!mutex_is_locked(mutex)) return false; -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES) +#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) return mutex->owner == task; #else /* Since UP may be pre-empted, we cannot assume that we own the lock */ diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index b7ce963fb8f8..44004e3f09e4 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -55,8 +55,10 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, return -ENODEV; /* See the comment at the drm_mm_init() call for more about this check. - * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */ - if (INTEL_INFO(dev_priv)->gen == 8 && start < 4096) + * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete) + */ + if (start < 4096 && (IS_GEN8(dev_priv) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0))) start = 4096; mutex_lock(&dev_priv->mm.stolen_lock); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 2f6fd33c07ba..aab47f7bb61b 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2471,7 +2471,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) I915_WRITE(SDEIIR, iir); ret = IRQ_HANDLED; - if (HAS_PCH_SPT(dev_priv)) + if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv)) spt_irq_handler(dev, iir); else cpt_irq_handler(dev, iir); @@ -4661,7 +4661,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev->driver->disable_vblank = gen8_disable_vblank; if (IS_BROXTON(dev)) dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup; - else if (HAS_PCH_SPT(dev)) + else if (HAS_PCH_SPT(dev) || HAS_PCH_KBP(dev)) dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup; else dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b407411e31ba..3fcf7dd5b6ca 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -220,6 +220,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ECOCHK_PPGTT_WT_HSW (0x2<<3) #define ECOCHK_PPGTT_WB_HSW (0x3<<3) +#define GEN8_CONFIG0 _MMIO(0xD00) +#define GEN9_DEFAULT_FIXES (1 << 3 | 1 << 2 | 1 << 1) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1<<13) #define ECOBITS_PPGTT_CACHE64B (3<<8) @@ -1669,6 +1672,9 @@ enum skl_disp_power_wells { #define GEN7_TLB_RD_ADDR _MMIO(0x4700) +#define GAMT_CHKN_BIT_REG _MMIO(0x4ab8) +#define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1<<28) + #if 0 #define PRB0_TAIL _MMIO(0x2030) #define PRB0_HEAD _MMIO(0x2034) @@ -1804,6 +1810,10 @@ enum skl_disp_power_wells { #define GEN9_IZ_HASHING_MASK(slice) (0x3 << ((slice) * 2)) #define GEN9_IZ_HASHING(slice, val) ((val) << ((slice) * 2)) +/* chicken reg for WaConextSwitchWithConcurrentTLBInvalidate */ +#define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20D4) +#define GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2) + /* WaClearTdlStateAckDirtyBits */ #define GEN8_STATE_ACK _MMIO(0x20F0) #define GEN9_STATE_ACK_SLICE1 _MMIO(0x20F8) @@ -2200,6 +2210,8 @@ enum skl_disp_power_wells { #define ILK_DPFC_STATUS _MMIO(0x43210) #define ILK_DPFC_FENCE_YOFF _MMIO(0x43218) #define ILK_DPFC_CHICKEN _MMIO(0x43224) +#define ILK_DPFC_DISABLE_DUMMY0 (1<<8) +#define ILK_DPFC_NUKE_ON_ANY_MODIFICATION (1<<23) #define ILK_FBC_RT_BASE _MMIO(0x2128) #define ILK_FBC_RT_VALID (1<<0) #define SNB_FBC_FRONT_BUFFER (1<<1) @@ -6031,6 +6043,7 @@ enum skl_disp_power_wells { #define CHICKEN_PAR1_1 _MMIO(0x42080) #define DPA_MASK_VBLANK_SRD (1 << 15) #define FORCE_ARB_IDLE_PLANES (1 << 14) +#define SKL_EDP_PSR_FIX_RDWRAP (1 << 3) #define _CHICKEN_PIPESL_1_A 0x420b0 #define _CHICKEN_PIPESL_1_B 0x420b4 @@ -6039,6 +6052,7 @@ enum skl_disp_power_wells { #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B) #define DISP_ARB_CTL _MMIO(0x45000) +#define DISP_FBC_MEMORY_WAKE (1<<31) #define DISP_TILE_SURFACE_SWIZZLING (1<<13) #define DISP_FBC_WM_DIS (1<<15) #define DISP_ARB_CTL2 _MMIO(0x45004) @@ -6052,6 +6066,9 @@ enum skl_disp_power_wells { #define HSW_NDE_RSTWRN_OPT _MMIO(0x46408) #define RESET_PCH_HANDSHAKE_ENABLE (1<<4) +#define GEN8_CHICKEN_DCPR_1 _MMIO(0x46430) +#define MASK_WAKEMEM (1<<13) + #define SKL_DFSM _MMIO(0x51000) #define SKL_DFSM_CDCLK_LIMIT_MASK (3 << 23) #define SKL_DFSM_CDCLK_LIMIT_675 (0 << 23) @@ -6069,6 +6086,7 @@ enum skl_disp_power_wells { #define GEN9_TSG_BARRIER_ACK_DISABLE (1<<8) #define GEN9_CS_DEBUG_MODE1 _MMIO(0x20ec) +#define GEN9_CTX_PREEMPT_REG _MMIO(0x2248) #define GEN8_CS_CHICKEN1 _MMIO(0x2580) /* GEN7 chicken */ @@ -6076,6 +6094,7 @@ enum skl_disp_power_wells { # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC ((1<<10) | (1<<26)) # define GEN9_RHWO_OPTIMIZATION_DISABLE (1<<14) #define COMMON_SLICE_CHICKEN2 _MMIO(0x7014) +# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8) # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE (1<<0) #define HIZ_CHICKEN _MMIO(0x7018) @@ -6921,6 +6940,7 @@ enum skl_disp_power_wells { #define EDRAM_SETS_IDX(cap) (((cap) >> 8) & 0x3) #define GEN6_UCGCTL1 _MMIO(0x9400) +# define GEN6_GAMUNIT_CLOCK_GATE_DISABLE (1 << 22) # define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE (1 << 16) # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE (1 << 5) # define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7) @@ -6937,6 +6957,7 @@ enum skl_disp_power_wells { #define GEN7_UCGCTL4 _MMIO(0x940c) #define GEN7_L3BANK2X_CLOCK_GATE_DISABLE (1<<25) +#define GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE (1<<14) #define GEN6_RCGCTL1 _MMIO(0x9410) #define GEN6_RCGCTL2 _MMIO(0x9414) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index b235b6e88ead..b9022fa053d6 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -139,6 +139,11 @@ fill_detail_timing_data(struct drm_display_mode *panel_fixed_mode, else panel_fixed_mode->flags |= DRM_MODE_FLAG_NVSYNC; + panel_fixed_mode->width_mm = (dvo_timing->himage_hi << 8) | + dvo_timing->himage_lo; + panel_fixed_mode->height_mm = (dvo_timing->vimage_hi << 8) | + dvo_timing->vimage_lo; + /* Some VBTs have bogus h/vtotal values */ if (panel_fixed_mode->hsync_end > panel_fixed_mode->htotal) panel_fixed_mode->htotal = panel_fixed_mode->hsync_end + 1; @@ -1187,7 +1192,7 @@ parse_device_mapping(struct drm_i915_private *dev_priv, } if (bdb->version < 106) { expected_size = 22; - } else if (bdb->version < 109) { + } else if (bdb->version < 111) { expected_size = 27; } else if (bdb->version < 195) { BUILD_BUG_ON(sizeof(struct old_child_dev_config) != 33); @@ -1545,6 +1550,45 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin) return false; } +/** + * intel_bios_is_port_present - is the specified digital port present + * @dev_priv: i915 device instance + * @port: port to check + * + * Return true if the device in %port is present. + */ +bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port) +{ + static const struct { + u16 dp, hdmi; + } port_mapping[] = { + [PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, }, + [PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, }, + [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, }, + [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, }, + }; + int i; + + /* FIXME maybe deal with port A as well? */ + if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping)) + return false; + + if (!dev_priv->vbt.child_dev_num) + return false; + + for (i = 0; i < dev_priv->vbt.child_dev_num; i++) { + const union child_device_config *p_child = + &dev_priv->vbt.child_dev[i]; + if ((p_child->common.dvo_port == port_mapping[port].dp || + p_child->common.dvo_port == port_mapping[port].hdmi) && + (p_child->common.device_type & (DEVICE_TYPE_TMDS_DVI_SIGNALING | + DEVICE_TYPE_DISPLAYPORT_OUTPUT))) + return true; + } + + return false; +} + /** * intel_bios_is_port_edp - is the device in given port eDP * @dev_priv: i915 device instance diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index a34c23eceba0..2b3b428d9cd2 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -41,16 +41,22 @@ * be moved to FW_FAILED. */ +#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_KBL); +#define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1) + #define I915_CSR_SKL "i915/skl_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_SKL); +#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) + #define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" +MODULE_FIRMWARE(I915_CSR_BXT); +#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) #define FIRMWARE_URL "https://01.org/linuxgraphics/intel-linux-graphics-firmwares" -MODULE_FIRMWARE(I915_CSR_SKL); -MODULE_FIRMWARE(I915_CSR_BXT); -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) -#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) + #define CSR_MAX_FW_SIZE 0x2FFF #define CSR_DEFAULT_FW_OFFSET 0xFFFFFFFF @@ -169,12 +175,10 @@ struct stepping_info { char substepping; }; -/* - * Kabylake derivated from Skylake H0, so SKL H0 - * is the right firmware for KBL A0 (revid 0). - */ static const struct stepping_info kbl_stepping_info[] = { - {'H', '0'}, {'I', '0'} + {'A', '0'}, {'B', '0'}, {'C', '0'}, + {'D', '0'}, {'E', '0'}, {'F', '0'}, + {'G', '0'}, {'H', '0'}, {'I', '0'}, }; static const struct stepping_info skl_stepping_info[] = { @@ -298,7 +302,9 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, csr->version = css_header->version; - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + if (IS_KABYLAKE(dev_priv)) { + required_min_version = KBL_CSR_VERSION_REQUIRED; + } else if (IS_SKYLAKE(dev_priv)) { required_min_version = SKL_CSR_VERSION_REQUIRED; } else if (IS_BROXTON(dev_priv)) { required_min_version = BXT_CSR_VERSION_REQUIRED; @@ -446,7 +452,9 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv) if (!HAS_CSR(dev_priv)) return; - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + if (IS_KABYLAKE(dev_priv)) + csr->fw_path = I915_CSR_KBL; + else if (IS_SKYLAKE(dev_priv)) csr->fw_path = I915_CSR_SKL; else if (IS_BROXTON(dev_priv)) csr->fw_path = I915_CSR_BXT; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2113f401f0ba..3074c56a643d 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -8275,12 +8275,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_encoder *encoder; + int i; u32 val, final; bool has_lvds = false; bool has_cpu_edp = false; bool has_panel = false; bool has_ck505 = false; bool can_ssc = false; + bool using_ssc_source = false; /* We need to take the global config into account */ for_each_intel_encoder(dev, encoder) { @@ -8307,8 +8309,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) can_ssc = true; } - DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n", - has_panel, has_lvds, has_ck505); + /* Check if any DPLLs are using the SSC source */ + for (i = 0; i < dev_priv->num_shared_dpll; i++) { + u32 temp = I915_READ(PCH_DPLL(i)); + + if (!(temp & DPLL_VCO_ENABLE)) + continue; + + if ((temp & PLL_REF_INPUT_MASK) == + PLLB_REF_INPUT_SPREADSPECTRUMIN) { + using_ssc_source = true; + break; + } + } + + DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n", + has_panel, has_lvds, has_ck505, using_ssc_source); /* Ironlake: try to setup display ref clock before DPLL * enabling. This is only under driver's control after @@ -8345,9 +8361,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; } else final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - } else { - final |= DREF_SSC_SOURCE_DISABLE; - final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; + } else if (using_ssc_source) { + final |= DREF_SSC_SOURCE_ENABLE; + final |= DREF_SSC1_ENABLE; } if (final == val) @@ -8393,7 +8409,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) POSTING_READ(PCH_DREF_CONTROL); udelay(200); } else { - DRM_DEBUG_KMS("Disabling SSC entirely\n"); + DRM_DEBUG_KMS("Disabling CPU source output\n"); val &= ~DREF_CPU_SOURCE_OUTPUT_MASK; @@ -8404,16 +8420,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) POSTING_READ(PCH_DREF_CONTROL); udelay(200); - /* Turn off the SSC source */ - val &= ~DREF_SSC_SOURCE_MASK; - val |= DREF_SSC_SOURCE_DISABLE; + if (!using_ssc_source) { + DRM_DEBUG_KMS("Disabling SSC source\n"); - /* Turn off SSC1 */ - val &= ~DREF_SSC1_ENABLE; + /* Turn off the SSC source */ + val &= ~DREF_SSC_SOURCE_MASK; + val |= DREF_SSC_SOURCE_DISABLE; - I915_WRITE(PCH_DREF_CONTROL, val); - POSTING_READ(PCH_DREF_CONTROL); - udelay(200); + /* Turn off SSC1 */ + val &= ~DREF_SSC1_ENABLE; + + I915_WRITE(PCH_DREF_CONTROL, val); + POSTING_READ(PCH_DREF_CONTROL); + udelay(200); + } } BUG_ON(val != final); @@ -8427,16 +8447,16 @@ static void lpt_reset_fdi_mphy(struct drm_i915_private *dev_priv) tmp |= FDI_MPHY_IOSFSB_RESET_CTL; I915_WRITE(SOUTH_CHICKEN2, tmp); - if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) & - FDI_MPHY_IOSFSB_RESET_STATUS, 100)) + if (wait_for_us(I915_READ(SOUTH_CHICKEN2) & + FDI_MPHY_IOSFSB_RESET_STATUS, 100)) DRM_ERROR("FDI mPHY reset assert timeout\n"); tmp = I915_READ(SOUTH_CHICKEN2); tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL; I915_WRITE(SOUTH_CHICKEN2, tmp); - if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) & - FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100)) + if (wait_for_us((I915_READ(SOUTH_CHICKEN2) & + FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100)) DRM_ERROR("FDI mPHY reset de-assert timeout\n"); } @@ -9420,8 +9440,8 @@ static void hsw_disable_lcpll(struct drm_i915_private *dev_priv, val |= LCPLL_CD_SOURCE_FCLK; I915_WRITE(LCPLL_CTL, val); - if (wait_for_atomic_us(I915_READ(LCPLL_CTL) & - LCPLL_CD_SOURCE_FCLK_DONE, 1)) + if (wait_for_us(I915_READ(LCPLL_CTL) & + LCPLL_CD_SOURCE_FCLK_DONE, 1)) DRM_ERROR("Switching to FCLK failed\n"); val = I915_READ(LCPLL_CTL); @@ -9494,8 +9514,8 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv) val &= ~LCPLL_CD_SOURCE_FCLK; I915_WRITE(LCPLL_CTL, val); - if (wait_for_atomic_us((I915_READ(LCPLL_CTL) & - LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1)) + if (wait_for_us((I915_READ(LCPLL_CTL) & + LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1)) DRM_ERROR("Switching back to LCPLL failed\n"); } @@ -11977,6 +11997,12 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, ret = intel_color_check(crtc, crtc_state); if (ret) return ret; + + /* + * Changing color management on Intel hardware is + * handled as part of planes update. + */ + crtc_state->planes_changed = true; } ret = 0; @@ -14554,6 +14580,8 @@ static void intel_setup_outputs(struct drm_device *dev) if (I915_READ(PCH_DP_D) & DP_DETECTED) intel_dp_init(dev, PCH_DP_D, PORT_D); } else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { + bool has_edp, has_port; + /* * The DP_DETECTED bit is the latched state of the DDC * SDA pin at boot. However since eDP doesn't require DDC @@ -14562,27 +14590,37 @@ static void intel_setup_outputs(struct drm_device *dev) * Thus we can't rely on the DP_DETECTED bit alone to detect * eDP ports. Consult the VBT as well as DP_DETECTED to * detect eDP ports. + * + * Sadly the straps seem to be missing sometimes even for HDMI + * ports (eg. on Voyo V3 - CHT x7-Z8700), so check both strap + * and VBT for the presence of the port. Additionally we can't + * trust the port type the VBT declares as we've seen at least + * HDMI ports that the VBT claim are DP or eDP. */ - if (I915_READ(VLV_HDMIB) & SDVO_DETECTED && - !intel_dp_is_edp(dev, PORT_B)) + has_edp = intel_dp_is_edp(dev, PORT_B); + has_port = intel_bios_is_port_present(dev_priv, PORT_B); + if (I915_READ(VLV_DP_B) & DP_DETECTED || has_port) + has_edp &= intel_dp_init(dev, VLV_DP_B, PORT_B); + if ((I915_READ(VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp) intel_hdmi_init(dev, VLV_HDMIB, PORT_B); - if (I915_READ(VLV_DP_B) & DP_DETECTED || - intel_dp_is_edp(dev, PORT_B)) - intel_dp_init(dev, VLV_DP_B, PORT_B); - if (I915_READ(VLV_HDMIC) & SDVO_DETECTED && - !intel_dp_is_edp(dev, PORT_C)) + has_edp = intel_dp_is_edp(dev, PORT_C); + has_port = intel_bios_is_port_present(dev_priv, PORT_C); + if (I915_READ(VLV_DP_C) & DP_DETECTED || has_port) + has_edp &= intel_dp_init(dev, VLV_DP_C, PORT_C); + if ((I915_READ(VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp) intel_hdmi_init(dev, VLV_HDMIC, PORT_C); - if (I915_READ(VLV_DP_C) & DP_DETECTED || - intel_dp_is_edp(dev, PORT_C)) - intel_dp_init(dev, VLV_DP_C, PORT_C); if (IS_CHERRYVIEW(dev)) { - /* eDP not supported on port D, so don't check VBT */ - if (I915_READ(CHV_HDMID) & SDVO_DETECTED) - intel_hdmi_init(dev, CHV_HDMID, PORT_D); - if (I915_READ(CHV_DP_D) & DP_DETECTED) + /* + * eDP not supported on port D, + * so no need to worry about it + */ + has_port = intel_bios_is_port_present(dev_priv, PORT_D); + if (I915_READ(CHV_DP_D) & DP_DETECTED || has_port) intel_dp_init(dev, CHV_DP_D, PORT_D); + if (I915_READ(CHV_HDMID) & SDVO_DETECTED || has_port) + intel_hdmi_init(dev, CHV_HDMID, PORT_D); } intel_dsi_init(dev); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index f192f58708c2..891107f92d9f 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -663,7 +663,7 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq) done = wait_event_timeout(dev_priv->gmbus_wait_queue, C, msecs_to_jiffies_timeout(10)); else - done = wait_for_atomic(C, 10) == 0; + done = wait_for(C, 10) == 0; if (!done) DRM_ERROR("dp aux hw did not signal timeout (has irq: %i)!\n", has_aux_irq); @@ -4645,7 +4645,7 @@ intel_dp_detect(struct drm_connector *connector, bool force) intel_dp->detect_done = false; - if (intel_connector->detect_edid) + if (is_edp(intel_dp) || intel_connector->detect_edid) return connector_status_connected; else return connector_status_disconnected; @@ -4899,13 +4899,15 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) void intel_dp_encoder_reset(struct drm_encoder *encoder) { - struct intel_dp *intel_dp; + struct drm_i915_private *dev_priv = to_i915(encoder->dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + + if (!HAS_DDI(dev_priv)) + intel_dp->DP = I915_READ(intel_dp->output_reg); if (to_intel_encoder(encoder)->type != INTEL_OUTPUT_EDP) return; - intel_dp = enc_to_intel_dp(encoder); - pps_lock(intel_dp); /* @@ -4977,9 +4979,6 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) intel_display_power_get(dev_priv, power_domain); if (long_hpd) { - /* indicate that we need to restart link training */ - intel_dp->train_set_valid = false; - intel_dp_long_pulse(intel_dp->attached_connector); if (intel_dp->is_mst) ret = IRQ_HANDLED; @@ -5725,8 +5724,11 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, if (!fixed_mode && dev_priv->vbt.lfp_lvds_vbt_mode) { fixed_mode = drm_mode_duplicate(dev, dev_priv->vbt.lfp_lvds_vbt_mode); - if (fixed_mode) + if (fixed_mode) { fixed_mode->type |= DRM_MODE_TYPE_PREFERRED; + connector->display_info.width_mm = fixed_mode->width_mm; + connector->display_info.height_mm = fixed_mode->height_mm; + } } mutex_unlock(&dev->mode_config.mutex); @@ -5923,9 +5925,9 @@ fail: return false; } -void -intel_dp_init(struct drm_device *dev, - i915_reg_t output_reg, enum port port) +bool intel_dp_init(struct drm_device *dev, + i915_reg_t output_reg, + enum port port) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_digital_port *intel_dig_port; @@ -5935,7 +5937,7 @@ intel_dp_init(struct drm_device *dev, intel_dig_port = kzalloc(sizeof(*intel_dig_port), GFP_KERNEL); if (!intel_dig_port) - return; + return false; intel_connector = intel_connector_alloc(); if (!intel_connector) @@ -5992,7 +5994,7 @@ intel_dp_init(struct drm_device *dev, if (!intel_dp_init_connector(intel_dig_port, intel_connector)) goto err_init_connector; - return; + return true; err_init_connector: drm_encoder_cleanup(encoder); @@ -6000,8 +6002,7 @@ err_encoder_init: kfree(intel_connector); err_connector_alloc: kfree(intel_dig_port); - - return; + return false; } void intel_dp_mst_suspend(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c index 0b8eefc2acc5..60fb39cd220b 100644 --- a/drivers/gpu/drm/i915/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/intel_dp_link_training.c @@ -85,8 +85,7 @@ static bool intel_dp_reset_link_train(struct intel_dp *intel_dp, uint8_t dp_train_pat) { - if (!intel_dp->train_set_valid) - memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); + memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); intel_dp_set_signal_levels(intel_dp); return intel_dp_set_link_train(intel_dp, dp_train_pat); } @@ -161,23 +160,6 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp) break; } - /* - * if we used previously trained voltage and pre-emphasis values - * and we don't get clock recovery, reset link training values - */ - if (intel_dp->train_set_valid) { - DRM_DEBUG_KMS("clock recovery not ok, reset"); - /* clear the flag as we are not reusing train set */ - intel_dp->train_set_valid = false; - if (!intel_dp_reset_link_train(intel_dp, - DP_TRAINING_PATTERN_1 | - DP_LINK_SCRAMBLING_DISABLE)) { - DRM_ERROR("failed to enable link training\n"); - return; - } - continue; - } - /* Check to see if we've tried the max voltage */ for (i = 0; i < intel_dp->lane_count; i++) if ((intel_dp->train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0) @@ -284,7 +266,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) /* Make sure clock is still ok */ if (!drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) { - intel_dp->train_set_valid = false; intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, training_pattern | @@ -301,7 +282,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) /* Try 5 times, then try clock recovery if that fails */ if (tries > 5) { - intel_dp->train_set_valid = false; intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, training_pattern | @@ -322,10 +302,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) intel_dp_set_idle_link_train(intel_dp); - if (channel_eq) { - intel_dp->train_set_valid = true; + if (channel_eq) DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n"); - } } void intel_dp_stop_link_train(struct intel_dp *intel_dp) diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c index 3ac705936b04..58f60b27837e 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c @@ -366,6 +366,9 @@ ibx_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state, DPLL_ID_PCH_PLL_B); } + if (!pll) + return NULL; + /* reference the pll */ intel_reference_shared_dpll(pll, crtc_state); @@ -1374,8 +1377,8 @@ static void bxt_ddi_pll_enable(struct drm_i915_private *dev_priv, I915_WRITE(BXT_PORT_PLL_ENABLE(port), temp); POSTING_READ(BXT_PORT_PLL_ENABLE(port)); - if (wait_for_atomic_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) & - PORT_PLL_LOCK), 200)) + if (wait_for_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) & PORT_PLL_LOCK), + 200)) DRM_ERROR("PLL %d not locked\n", port); /* diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index a28b4aac1e02..f7f0f01814f6 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -863,8 +863,6 @@ struct intel_dp { /* This is called before a link training is starterd */ void (*prepare_link_retrain)(struct intel_dp *intel_dp); - bool train_set_valid; - /* Displayport compliance testing */ unsigned long compliance_test_type; unsigned long compliance_test_data; @@ -1284,7 +1282,7 @@ void intel_csr_ucode_suspend(struct drm_i915_private *); void intel_csr_ucode_resume(struct drm_i915_private *); /* intel_dp.c */ -void intel_dp_init(struct drm_device *dev, i915_reg_t output_reg, enum port port); +bool intel_dp_init(struct drm_device *dev, i915_reg_t output_reg, enum port port); bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port, struct intel_connector *intel_connector); void intel_dp_set_link_params(struct intel_dp *intel_dp, diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 366ad6c67ce4..4756ef639648 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -1545,6 +1545,9 @@ void intel_dsi_init(struct drm_device *dev) goto err; } + connector->display_info.width_mm = fixed_mode->width_mm; + connector->display_info.height_mm = fixed_mode->height_mm; + intel_panel_init(&intel_connector->panel, fixed_mode, NULL); intel_dsi_add_properties(intel_connector); diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index d5a7cfec589b..647127f3aaff 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -824,8 +824,7 @@ static bool intel_fbc_can_choose(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; struct intel_fbc *fbc = &dev_priv->fbc; - bool enable_by_default = IS_HASWELL(dev_priv) || - IS_BROADWELL(dev_priv); + bool enable_by_default = IS_BROADWELL(dev_priv); if (intel_vgpu_active(dev_priv->dev)) { fbc->no_fbc_reason = "VGPU is active"; diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 2c3bd9c2573e..a8844702d11b 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -2142,6 +2142,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, enum port port = intel_dig_port->port; uint8_t alternate_ddc_pin; + DRM_DEBUG_KMS("Adding HDMI connector on port %c\n", + port_name(port)); + if (WARN(intel_dig_port->max_lanes < 4, "Not enough lanes (%d) for HDMI on port %c\n", intel_dig_port->max_lanes, port_name(port))) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 42eac37de047..7f2d8415ed8b 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1103,15 +1103,17 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, uint32_t *const batch, uint32_t index) { + struct drm_i915_private *dev_priv = engine->dev->dev_private; uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES); /* - * WaDisableLSQCROPERFforOCL:skl + * WaDisableLSQCROPERFforOCL:skl,kbl * This WA is implemented in skl_init_clock_gating() but since * this batch updates GEN8_L3SQCREG4 with default value we need to * set this bit here to retain the WA during flush. */ - if (IS_SKL_REVID(engine->dev, 0, SKL_REVID_E0)) + if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | @@ -1273,6 +1275,7 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, { int ret; struct drm_device *dev = engine->dev; + struct drm_i915_private *dev_priv = dev->dev_private; uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS); /* WaDisableCtxRestoreArbitration:skl,bxt */ @@ -1286,6 +1289,22 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, return ret; index = ret; + /* WaClearSlmSpaceAtContextSwitch:kbl */ + /* Actual scratch location is at 128 bytes offset */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) { + uint32_t scratch_addr + = engine->scratch.gtt_offset + 2*CACHELINE_BYTES; + + wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6)); + wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 | + PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_QW_WRITE)); + wa_ctx_emit(batch, index, scratch_addr); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + } /* Pad to end of cacheline */ while (index % CACHELINE_DWORDS) wa_ctx_emit(batch, index, MI_NOOP); @@ -1687,9 +1706,10 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, struct intel_ringbuffer *ringbuf = request->ringbuf; struct intel_engine_cs *engine = ringbuf->engine; u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES; - bool vf_flush_wa = false; + bool vf_flush_wa = false, dc_flush_wa = false; u32 flags = 0; int ret; + int len; flags |= PIPE_CONTROL_CS_STALL; @@ -1716,9 +1736,21 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, */ if (IS_GEN9(engine->dev)) vf_flush_wa = true; + + /* WaForGAMHang:kbl */ + if (IS_KBL_REVID(request->i915, 0, KBL_REVID_B0)) + dc_flush_wa = true; } - ret = intel_ring_begin(request, vf_flush_wa ? 12 : 6); + len = 6; + + if (vf_flush_wa) + len += 6; + + if (dc_flush_wa) + len += 12; + + ret = intel_ring_begin(request, len); if (ret) return ret; @@ -1731,12 +1763,31 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, intel_logical_ring_emit(ringbuf, 0); } + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_DC_FLUSH_ENABLE); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); intel_logical_ring_emit(ringbuf, flags); intel_logical_ring_emit(ringbuf, scratch_addr); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); + + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_CS_STALL); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_advance(ringbuf); return 0; diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index bc53c0dd34d0..96281e628d2a 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -1082,6 +1082,8 @@ void intel_lvds_init(struct drm_device *dev) fixed_mode = drm_mode_duplicate(dev, dev_priv->vbt.lfp_lvds_vbt_mode); if (fixed_mode) { fixed_mode->type |= DRM_MODE_TYPE_PREFERRED; + connector->display_info.width_mm = fixed_mode->width_mm; + connector->display_info.height_mm = fixed_mode->height_mm; goto out; } } diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index 99e26034ae8d..16e209d326b6 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -1038,5 +1038,16 @@ intel_opregion_get_panel_type(struct drm_device *dev) return -ENODEV; } + /* + * FIXME On Dell XPS 13 9350 the OpRegion panel type (0) gives us + * low vswing for eDP, whereas the VBT panel type (2) gives us normal + * vswing instead. Low vswing results in some display flickers, so + * let's simply ignore the OpRegion panel type on SKL for now. + */ + if (IS_SKYLAKE(dev)) { + DRM_DEBUG_KMS("Ignoring OpRegion panel type (%d)\n", ret - 1); + return -ENODEV; + } + return ret - 1; } diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 8357d571553a..aba94099886b 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -1731,7 +1731,8 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel) panel->backlight.set = bxt_set_backlight; panel->backlight.get = bxt_get_backlight; panel->backlight.hz_to_pwm = bxt_hz_to_pwm; - } else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv)) { + } else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv) || + HAS_PCH_KBP(dev_priv)) { panel->backlight.setup = lpt_setup_backlight; panel->backlight.enable = lpt_enable_backlight; panel->backlight.disable = lpt_disable_backlight; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a7ef45da0a9e..2863b92c9da6 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -54,10 +54,38 @@ #define INTEL_RC6p_ENABLE (1<<1) #define INTEL_RC6pp_ENABLE (1<<2) +static void gen9_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl */ + I915_WRITE(CHICKEN_PAR1_1, + I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP); + + I915_WRITE(GEN8_CONFIG0, + I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES); + + /* WaEnableChickenDCPR:skl,bxt,kbl */ + I915_WRITE(GEN8_CHICKEN_DCPR_1, + I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM); + + /* WaFbcTurnOffFbcWatermark:skl,bxt,kbl */ + /* WaFbcWakeMemOn:skl,bxt,kbl */ + I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) | + DISP_FBC_WM_DIS | + DISP_FBC_MEMORY_WAKE); + + /* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_DISABLE_DUMMY0); +} + static void bxt_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + gen9_init_clock_gating(dev); + /* WaDisableSDEUnitClockGating:bxt */ I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | GEN8_SDEUNIT_CLOCK_GATE_DISABLE); @@ -6698,6 +6726,38 @@ static void lpt_suspend_hw(struct drm_device *dev) } } +static void kabylake_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + + /* WaDisableSDEUnitClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | + GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableGamClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_GAMUNIT_CLOCK_GATE_DISABLE); + + /* WaFbcNukeOnHostModify:kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); +} + +static void skylake_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + + /* WaFbcNukeOnHostModify:skl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); +} + static void broadwell_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -7163,9 +7223,9 @@ static void nop_init_clock_gating(struct drm_device *dev) void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) { if (IS_SKYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = nop_init_clock_gating; + dev_priv->display.init_clock_gating = skylake_init_clock_gating; else if (IS_KABYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = nop_init_clock_gating; + dev_priv->display.init_clock_gating = kabylake_init_clock_gating; else if (IS_BROXTON(dev_priv)) dev_priv->display.init_clock_gating = bxt_init_clock_gating; else if (IS_BROADWELL(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 04402bb9d26b..68c5af079ef8 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -913,24 +913,26 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) { struct drm_device *dev = engine->dev; struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t tmp; int ret; - /* WaEnableLbsSlaRetryTimerDecrement:skl */ + /* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl */ + I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE)); + + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl */ I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); - /* WaDisableKillLogic:bxt,skl */ + /* WaDisableKillLogic:bxt,skl,kbl */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | ECOCHK_DIS_TLB); - /* WaClearFlowControlGpgpuContextSave:skl,bxt */ - /* WaDisablePartialInstShootdown:skl,bxt */ + /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl */ + /* WaDisablePartialInstShootdown:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, FLOW_CONTROL_ENABLE | PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); - /* Syncing dependencies between camera and graphics:skl,bxt */ + /* Syncing dependencies between camera and graphics:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC); @@ -952,18 +954,18 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) */ } - /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt */ - /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt */ + /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl */ + /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7, GEN9_ENABLE_YV12_BUGFIX | GEN9_ENABLE_GPGPU_PREEMPTION); - /* Wa4x4STCOptimizationDisable:skl,bxt */ - /* WaDisablePartialResolveInVc:skl,bxt */ + /* Wa4x4STCOptimizationDisable:skl,bxt,kbl */ + /* WaDisablePartialResolveInVc:skl,bxt,kbl */ WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE | GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE)); - /* WaCcsTlbPrefetchDisable:skl,bxt */ + /* WaCcsTlbPrefetchDisable:skl,bxt,kbl */ WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5, GEN9_CCS_TLB_PREFETCH_ENABLE); @@ -973,31 +975,57 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0, PIXEL_MASK_CAMMING_DISABLE); - /* WaForceContextSaveRestoreNonCoherent:skl,bxt */ - tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT; - if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) || - IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER)) - tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE; - WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp); + /* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | + HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE); + + /* WaForceEnableNonCoherent and WaDisableHDCInvalidation are + * both tied to WaForceContextSaveRestoreNonCoherent + * in some hsds for skl. We keep the tie for all gen9. The + * documentation is a bit hazy and so we want to get common behaviour, + * even though there is no clear evidence we would need both on kbl/bxt. + * This area has been source of system hangs so we play it safe + * and mimic the skl regardless of what bspec says. + * + * Use Force Non-Coherent whenever executing a 3D context. This + * is a workaround for a possible hang in the unlikely event + * a TLB invalidation occurs during a PSD flush. + */ - /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */ - if (IS_SKYLAKE(dev) || IS_BXT_REVID(dev, 0, BXT_REVID_B0)) + /* WaForceEnableNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_NON_COHERENT); + + /* WaDisableHDCInvalidation:skl,bxt,kbl */ + I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | + BDW_DISABLE_HDC_INVALIDATION); + + /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl */ + if (IS_SKYLAKE(dev_priv) || + IS_KABYLAKE(dev_priv) || + IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN8_SAMPLER_POWER_BYPASS_DIS); - /* WaDisableSTUnitPowerOptimization:skl,bxt */ + /* WaDisableSTUnitPowerOptimization:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); - /* WaOCLCoherentLineFlush:skl,bxt */ + /* WaOCLCoherentLineFlush:skl,bxt,kbl */ I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES)); - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt */ + /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt */ + ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); + if (ret) + return ret; + + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl */ ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); if (ret) return ret; - /* WaAllowUMDToModifyHDCChicken1:skl,bxt */ + /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl */ ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1); if (ret) return ret; @@ -1092,22 +1120,6 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(HIZ_CHICKEN, BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE); - /* This is tied to WaForceContextSaveRestoreNonCoherent */ - if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) { - /* - *Use Force Non-Coherent whenever executing a 3D context. This - * is a workaround for a possible hang in the unlikely event - * a TLB invalidation occurs during a PSD flush. - */ - /* WaForceEnableNonCoherent:skl */ - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FORCE_NON_COHERENT); - - /* WaDisableHDCInvalidation:skl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); - } - /* WaBarrierPerformanceFixDisable:skl */ if (IS_SKL_REVID(dev, SKL_REVID_C0, SKL_REVID_D0)) WA_SET_BIT_MASKED(HDC_CHICKEN0, @@ -1120,6 +1132,9 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) GEN7_HALF_SLICE_CHICKEN1, GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + /* WaDisableGafsUnitClkGating:skl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + /* WaDisableLSQCROPERFforOCL:skl */ ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); if (ret) @@ -1174,6 +1189,63 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) return ret; } + /* WaInsertDummyPushConstPs:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + return 0; +} + +static int kbl_init_workarounds(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->dev->dev_private; + int ret; + + ret = gen9_init_workarounds(engine); + if (ret) + return ret; + + /* WaEnableGapsTsvCreditFix:kbl */ + I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | + GEN9_GAPS_TSV_CREDIT_DISABLE)); + + /* WaDisableDynamicCreditSharing:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT(GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + + /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */ + if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0)) + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FENCE_DEST_SLM_DISABLE); + + /* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes + * involving this register should also be added to WA batch as required. + */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) + /* WaDisableLSQCROPERFforOCL:kbl */ + I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | + GEN8_LQSC_RO_PERF_DIS); + + /* WaInsertDummyPushConstPs:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + /* WaDisableGafsUnitClkGating:kbl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSbeCacheDispatchPortSharing:kbl */ + WA_SET_BIT_MASKED( + GEN7_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + + /* WaDisableLSQCROPERFforOCL:kbl */ + ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); + if (ret) + return ret; + return 0; } @@ -1199,6 +1271,9 @@ int init_workarounds_ring(struct intel_engine_cs *engine) if (IS_BROXTON(dev)) return bxt_init_workarounds(engine); + if (IS_KABYLAKE(dev_priv)) + return kbl_init_workarounds(engine); + return 0; } diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h index c15051de8023..44fb0b35eed3 100644 --- a/drivers/gpu/drm/i915/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/intel_vbt_defs.h @@ -403,9 +403,10 @@ struct lvds_dvo_timing { u8 vsync_off:4; u8 rsvd0:6; u8 hsync_off_hi:2; - u8 h_image; - u8 v_image; - u8 max_hv; + u8 himage_lo; + u8 vimage_lo; + u8 vimage_hi:4; + u8 himage_hi:4; u8 h_border; u8 v_border; u8 rsvd1:3; diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 300ea03be8f0..d1f248fd3506 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -552,7 +552,8 @@ nouveau_fbcon_init(struct drm_device *dev) if (ret) goto fini; - fbcon->helper.fbdev->pixmap.buf_align = 4; + if (fbcon->helper.fbdev) + fbcon->helper.fbdev->pixmap.buf_align = 4; return 0; fini: diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c index 18fab3973ce5..62ad0300cfa5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c @@ -1614,7 +1614,7 @@ nvkm_device_pci_func = { .fini = nvkm_device_pci_fini, .resource_addr = nvkm_device_pci_resource_addr, .resource_size = nvkm_device_pci_resource_size, - .cpu_coherent = !IS_ENABLED(CONFIG_ARM) && !IS_ENABLED(CONFIG_ARM64), + .cpu_coherent = !IS_ENABLED(CONFIG_ARM), }; int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c index 22706c0a54b5..49bd5da194e1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c @@ -40,7 +40,8 @@ static int gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern) { struct nvkm_device *device = outp->base.disp->engine.subdev.device; - nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern); + const u32 soff = gf119_sor_soff(outp); + nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, 0x01010101 * pattern); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c index 323c79abe468..41bd5d0f7692 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c @@ -276,6 +276,8 @@ nvkm_iccsense_oneinit(struct nvkm_subdev *subdev) struct pwr_rail_t *r = &stbl.rail[i]; struct nvkm_iccsense_rail *rail; struct nvkm_iccsense_sensor *sensor; + int (*read)(struct nvkm_iccsense *, + struct nvkm_iccsense_rail *); if (!r->mode || r->resistor_mohm == 0) continue; @@ -284,31 +286,31 @@ nvkm_iccsense_oneinit(struct nvkm_subdev *subdev) if (!sensor) continue; - rail = kmalloc(sizeof(*rail), GFP_KERNEL); - if (!rail) - return -ENOMEM; - switch (sensor->type) { case NVBIOS_EXTDEV_INA209: if (r->rail != 0) continue; - rail->read = nvkm_iccsense_ina209_read; + read = nvkm_iccsense_ina209_read; break; case NVBIOS_EXTDEV_INA219: if (r->rail != 0) continue; - rail->read = nvkm_iccsense_ina219_read; + read = nvkm_iccsense_ina219_read; break; case NVBIOS_EXTDEV_INA3221: if (r->rail >= 3) continue; - rail->read = nvkm_iccsense_ina3221_read; + read = nvkm_iccsense_ina3221_read; break; default: continue; } + rail = kmalloc(sizeof(*rail), GFP_KERNEL); + if (!rail) + return -ENOMEM; sensor->rail_mask |= 1 << r->rail; + rail->read = read; rail->sensor = sensor; rail->idx = r->rail; rail->mohm = r->resistor_mohm; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 2e216e2ea78c..259cd6e6d71c 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -589,7 +589,8 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev) || ASIC_IS_DCE8(rdev)) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; /* use frac fb div on RS780/RS880 */ - if ((rdev->family == CHIP_RS780) || (rdev->family == CHIP_RS880)) + if (((rdev->family == CHIP_RS780) || (rdev->family == CHIP_RS880)) + && !radeon_crtc->ss_enabled) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; if (ASIC_IS_DCE32(rdev) && mode->clock > 165000) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; @@ -626,7 +627,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, if (radeon_crtc->ss.refdiv) { radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV; radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv; - if (ASIC_IS_AVIVO(rdev)) + if (rdev->family >= CHIP_RV770) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; } } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index e721e6b2766e..21c44b2293bc 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -630,6 +630,23 @@ void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc) /* * GPU helpers function. */ + +/** + * radeon_device_is_virtual - check if we are running is a virtual environment + * + * Check if the asic has been passed through to a VM (all asics). + * Used at driver startup. + * Returns true if virtual or false if not. + */ +static bool radeon_device_is_virtual(void) +{ +#ifdef CONFIG_X86 + return boot_cpu_has(X86_FEATURE_HYPERVISOR); +#else + return false; +#endif +} + /** * radeon_card_posted - check if the hw has already been initialized * @@ -643,6 +660,10 @@ bool radeon_card_posted(struct radeon_device *rdev) { uint32_t reg; + /* for pass through, always force asic_init */ + if (radeon_device_is_virtual()) + return false; + /* required for EFI mode on macbook2,1 which uses an r5xx asic */ if (efi_enabled(EFI_BOOT) && (rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) && @@ -1631,7 +1652,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, radeon_agp_suspend(rdev); pci_save_state(dev->pdev); - if (freeze && rdev->family >= CHIP_R600) { + if (freeze && rdev->family >= CHIP_CEDAR) { rdev->asic->asic_reset(rdev, true); pci_restore_state(dev->pdev); } else if (suspend) { diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index 99510e64e91a..a4b357db8856 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -1,6 +1,6 @@ config DRM_SUN4I tristate "DRM Support for Allwinner A10 Display Engine" - depends on DRM && ARM + depends on DRM && ARM && COMMON_CLK depends on ARCH_SUNXI || COMPILE_TEST select DRM_GEM_CMA_HELPER select DRM_KMS_HELPER diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index f7a15c1a93bf..3ab560450a82 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -190,7 +190,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend, /* Get the physical address of the buffer in memory */ gem = drm_fb_cma_get_gem_obj(fb, 0); - DRM_DEBUG_DRIVER("Using GEM @ 0x%x\n", gem->paddr); + DRM_DEBUG_DRIVER("Using GEM @ %pad\n", &gem->paddr); /* Compute the start of the displayed memory */ bpp = drm_format_plane_cpp(fb->pixel_format, 0); @@ -198,7 +198,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend, paddr += (state->src_x >> 16) * bpp; paddr += (state->src_y >> 16) * fb->pitches[0]; - DRM_DEBUG_DRIVER("Setting buffer address to 0x%x\n", paddr); + DRM_DEBUG_DRIVER("Setting buffer address to %pad\n", &paddr); /* Write the 32 lower bits of the address (in bits) */ lo_paddr = paddr << 3; diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c index 4182a21f5923..41cacecbea9a 100644 --- a/drivers/gpu/drm/sun4i/sun4i_crtc.c +++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c @@ -65,6 +65,14 @@ static void sun4i_crtc_disable(struct drm_crtc *crtc) DRM_DEBUG_DRIVER("Disabling the CRTC\n"); sun4i_tcon_disable(drv->tcon); + + if (crtc->state->event && !crtc->state->active) { + spin_lock_irq(&crtc->dev->event_lock); + drm_crtc_send_vblank_event(crtc, crtc->state->event); + spin_unlock_irq(&crtc->dev->event_lock); + + crtc->state->event = NULL; + } } static void sun4i_crtc_enable(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/sun4i/sun4i_dotclock.c b/drivers/gpu/drm/sun4i/sun4i_dotclock.c index 3ff668cb463c..5b3463197c48 100644 --- a/drivers/gpu/drm/sun4i/sun4i_dotclock.c +++ b/drivers/gpu/drm/sun4i/sun4i_dotclock.c @@ -72,14 +72,40 @@ static unsigned long sun4i_dclk_recalc_rate(struct clk_hw *hw, static long sun4i_dclk_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate) { - return *parent_rate / DIV_ROUND_CLOSEST(*parent_rate, rate); + unsigned long best_parent = 0; + u8 best_div = 1; + int i; + + for (i = 6; i < 127; i++) { + unsigned long ideal = rate * i; + unsigned long rounded; + + rounded = clk_hw_round_rate(clk_hw_get_parent(hw), + ideal); + + if (rounded == ideal) { + best_parent = rounded; + best_div = i; + goto out; + } + + if ((rounded < ideal) && (rounded > best_parent)) { + best_parent = rounded; + best_div = i; + } + } + +out: + *parent_rate = best_parent; + + return best_parent / best_div; } static int sun4i_dclk_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { struct sun4i_dclk *dclk = hw_to_dclk(hw); - int div = DIV_ROUND_CLOSEST(parent_rate, rate); + u8 div = parent_rate / rate; return regmap_update_bits(dclk->regmap, SUN4I_TCON0_DCLK_REG, GENMASK(6, 0), div); @@ -127,10 +153,14 @@ int sun4i_dclk_create(struct device *dev, struct sun4i_tcon *tcon) const char *clk_name, *parent_name; struct clk_init_data init; struct sun4i_dclk *dclk; + int ret; parent_name = __clk_get_name(tcon->sclk0); - of_property_read_string_index(dev->of_node, "clock-output-names", 0, - &clk_name); + ret = of_property_read_string_index(dev->of_node, + "clock-output-names", 0, + &clk_name); + if (ret) + return ret; dclk = devm_kzalloc(dev, sizeof(*dclk), GFP_KERNEL); if (!dclk) @@ -140,6 +170,7 @@ int sun4i_dclk_create(struct device *dev, struct sun4i_tcon *tcon) init.ops = &sun4i_dclk_ops; init.parent_names = &parent_name; init.num_parents = 1; + init.flags = CLK_SET_RATE_PARENT; dclk->regmap = tcon->regs; dclk->hw.init = &init; diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 76e922bb60e5..937394cbc241 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -24,34 +24,6 @@ #include "sun4i_layer.h" #include "sun4i_tcon.h" -static int sun4i_drv_connector_plug_all(struct drm_device *drm) -{ - struct drm_connector *connector, *failed; - int ret; - - mutex_lock(&drm->mode_config.mutex); - list_for_each_entry(connector, &drm->mode_config.connector_list, head) { - ret = drm_connector_register(connector); - if (ret) { - failed = connector; - goto err; - } - } - mutex_unlock(&drm->mode_config.mutex); - return 0; - -err: - list_for_each_entry(connector, &drm->mode_config.connector_list, head) { - if (failed == connector) - break; - - drm_connector_unregister(connector); - } - mutex_unlock(&drm->mode_config.mutex); - - return ret; -} - static int sun4i_drv_enable_vblank(struct drm_device *drm, unsigned int pipe) { struct sun4i_drv *drv = drm->dev_private; @@ -120,11 +92,27 @@ static struct drm_driver sun4i_drv_driver = { /* Frame Buffer Operations */ /* VBlank Operations */ - .get_vblank_counter = drm_vblank_count, + .get_vblank_counter = drm_vblank_no_hw_counter, .enable_vblank = sun4i_drv_enable_vblank, .disable_vblank = sun4i_drv_disable_vblank, }; +static void sun4i_remove_framebuffers(void) +{ + struct apertures_struct *ap; + + ap = alloc_apertures(1); + if (!ap) + return; + + /* The framebuffer can be located anywhere in RAM */ + ap->ranges[0].base = 0; + ap->ranges[0].size = ~0; + + remove_conflicting_framebuffers(ap, "sun4i-drm-fb", false); + kfree(ap); +} + static int sun4i_drv_bind(struct device *dev) { struct drm_device *drm; @@ -172,6 +160,9 @@ static int sun4i_drv_bind(struct device *dev) } drm->irq_enabled = true; + /* Remove early framebuffers (ie. simplefb) */ + sun4i_remove_framebuffers(); + /* Create our framebuffer */ drv->fbdev = sun4i_framebuffer_init(drm); if (IS_ERR(drv->fbdev)) { @@ -187,7 +178,7 @@ static int sun4i_drv_bind(struct device *dev) if (ret) goto free_drm; - ret = sun4i_drv_connector_plug_all(drm); + ret = drm_connector_register_all(drm); if (ret) goto unregister_drm; @@ -204,6 +195,7 @@ static void sun4i_drv_unbind(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); + drm_connector_unregister_all(drm); drm_dev_unregister(drm); drm_kms_helper_poll_fini(drm); sun4i_framebuffer_free(drm); @@ -318,6 +310,7 @@ static int sun4i_drv_probe(struct platform_device *pdev) count += sun4i_drv_add_endpoints(&pdev->dev, &match, pipeline); + of_node_put(pipeline); DRM_DEBUG_DRIVER("Queued %d outputs on pipeline %d\n", count, i); diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index ab6494818050..aaffe9e64ffb 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -54,8 +54,13 @@ static int sun4i_rgb_get_modes(struct drm_connector *connector) static int sun4i_rgb_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct sun4i_rgb *rgb = drm_connector_to_sun4i_rgb(connector); + struct sun4i_drv *drv = rgb->drv; + struct sun4i_tcon *tcon = drv->tcon; u32 hsync = mode->hsync_end - mode->hsync_start; u32 vsync = mode->vsync_end - mode->vsync_start; + unsigned long rate = mode->clock * 1000; + long rounded_rate; DRM_DEBUG_DRIVER("Validating modes...\n"); @@ -87,6 +92,15 @@ static int sun4i_rgb_mode_valid(struct drm_connector *connector, DRM_DEBUG_DRIVER("Vertical parameters OK\n"); + rounded_rate = clk_round_rate(tcon->dclk, rate); + if (rounded_rate < rate) + return MODE_CLOCK_LOW; + + if (rounded_rate > rate) + return MODE_CLOCK_HIGH; + + DRM_DEBUG_DRIVER("Clock rate OK\n"); + return MODE_OK; } @@ -203,7 +217,7 @@ int sun4i_rgb_init(struct drm_device *drm) int ret; /* If we don't have a panel, there's no point in going on */ - if (!tcon->panel) + if (IS_ERR(tcon->panel)) return -ENODEV; rgb = devm_kzalloc(drm->dev, sizeof(*rgb), GFP_KERNEL); diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 9f19b0e08560..652385f09735 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -425,11 +425,11 @@ static struct drm_panel *sun4i_tcon_find_panel(struct device_node *node) remote = of_graph_get_remote_port_parent(end_node); if (!remote) { - DRM_DEBUG_DRIVER("Enable to parse remote node\n"); + DRM_DEBUG_DRIVER("Unable to parse remote node\n"); return ERR_PTR(-EINVAL); } - return of_drm_find_panel(remote); + return of_drm_find_panel(remote) ?: ERR_PTR(-EPROBE_DEFER); } static int sun4i_tcon_bind(struct device *dev, struct device *master, @@ -490,7 +490,11 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master, return 0; } - return sun4i_rgb_init(drm); + ret = sun4i_rgb_init(drm); + if (ret < 0) + goto err_free_clocks; + + return 0; err_free_clocks: sun4i_tcon_free_clocks(tcon); @@ -522,12 +526,13 @@ static int sun4i_tcon_probe(struct platform_device *pdev) * Defer the probe. */ panel = sun4i_tcon_find_panel(node); - if (IS_ERR(panel)) { - /* - * If we don't have a panel endpoint, just go on - */ - if (PTR_ERR(panel) != -ENODEV) - return -EPROBE_DEFER; + + /* + * If we don't have a panel endpoint, just go on + */ + if (PTR_ERR(panel) == -EPROBE_DEFER) { + DRM_DEBUG_DRIVER("Still waiting for our panel. Deferring...\n"); + return -EPROBE_DEFER; } return component_add(&pdev->dev, &sun4i_tcon_ops); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 39386f50af87..a71cf98c655f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1034,9 +1034,9 @@ out_unlock: return ret; } -static bool ttm_bo_mem_compat(struct ttm_placement *placement, - struct ttm_mem_reg *mem, - uint32_t *new_flags) +bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags) { int i; @@ -1068,6 +1068,7 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement, return false; } +EXPORT_SYMBOL(ttm_bo_mem_compat); int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c index 9b078a493996..0cd889015dc5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c @@ -49,6 +49,7 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv, { struct ttm_buffer_object *bo = &buf->base; int ret; + uint32_t new_flags; ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); if (unlikely(ret != 0)) @@ -60,7 +61,12 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; - ret = ttm_bo_validate(bo, placement, interruptible, false); + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, placement, interruptible, false); + if (!ret) vmw_bo_pin_reserved(buf, true); @@ -91,6 +97,7 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, { struct ttm_buffer_object *bo = &buf->base; int ret; + uint32_t new_flags; ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); if (unlikely(ret != 0)) @@ -102,6 +109,12 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; + if (buf->pin_count > 0) { + ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + goto out_unreserve; + } + ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, interruptible, false); if (likely(ret == 0) || ret == -ERESTARTSYS) @@ -161,6 +174,7 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv, struct ttm_placement placement; struct ttm_place place; int ret = 0; + uint32_t new_flags; place = vmw_vram_placement.placement[0]; place.lpfn = bo->num_pages; @@ -185,10 +199,15 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv, */ if (bo->mem.mem_type == TTM_PL_VRAM && bo->mem.start < bo->num_pages && - bo->mem.start > 0) + bo->mem.start > 0 && + buf->pin_count == 0) (void) ttm_bo_validate(bo, &vmw_sys_placement, false, false); - ret = ttm_bo_validate(bo, &placement, interruptible, false); + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(&placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, &placement, interruptible, false); /* For some reason we didn't end up at the start of vram */ WARN_ON(ret == 0 && bo->offset != 0); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 9fcd8200d485..8d528fcf6e96 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -233,6 +233,7 @@ static int vmw_force_iommu; static int vmw_restrict_iommu; static int vmw_force_coherent; static int vmw_restrict_dma_mask; +static int vmw_assume_16bpp; static int vmw_probe(struct pci_dev *, const struct pci_device_id *); static void vmw_master_init(struct vmw_master *); @@ -249,6 +250,8 @@ MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages"); module_param_named(force_coherent, vmw_force_coherent, int, 0600); MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU"); module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600); +MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes"); +module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600); static void vmw_print_capabilities(uint32_t capabilities) @@ -660,6 +663,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->vram_start = pci_resource_start(dev->pdev, 1); dev_priv->mmio_start = pci_resource_start(dev->pdev, 2); + dev_priv->assume_16bpp = !!vmw_assume_16bpp; + dev_priv->enable_fb = enable_fbdev; vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2); @@ -706,6 +711,13 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) vmw_read(dev_priv, SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB); + /* + * Workaround for low memory 2D VMs to compensate for the + * allocation taken by fbdev + */ + if (!(dev_priv->capabilities & SVGA_CAP_3D)) + mem_size *= 2; + dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE; dev_priv->prim_bb_mem = vmw_read(dev_priv, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 1980e2a28265..89fb19443a3f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -386,6 +386,7 @@ struct vmw_private { spinlock_t hw_lock; spinlock_t cap_lock; bool has_dx; + bool assume_16bpp; /* * VGA registers. diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 679a4cb98ee3..d2d93959b119 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -517,28 +517,6 @@ static int vmw_fb_kms_framebuffer(struct fb_info *info) par->set_fb = &vfb->base; - if (!par->bo_ptr) { - /* - * Pin before mapping. Since we don't know in what placement - * to pin, call into KMS to do it for us. - */ - ret = vfb->pin(vfb); - if (ret) { - DRM_ERROR("Could not pin the fbdev framebuffer.\n"); - return ret; - } - - ret = ttm_bo_kmap(&par->vmw_bo->base, 0, - par->vmw_bo->base.num_pages, &par->map); - if (ret) { - vfb->unpin(vfb); - DRM_ERROR("Could not map the fbdev framebuffer.\n"); - return ret; - } - - par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite); - } - return 0; } @@ -601,6 +579,31 @@ static int vmw_fb_set_par(struct fb_info *info) if (ret) goto out_unlock; + if (!par->bo_ptr) { + struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(set.fb); + + /* + * Pin before mapping. Since we don't know in what placement + * to pin, call into KMS to do it for us. + */ + ret = vfb->pin(vfb); + if (ret) { + DRM_ERROR("Could not pin the fbdev framebuffer.\n"); + goto out_unlock; + } + + ret = ttm_bo_kmap(&par->vmw_bo->base, 0, + par->vmw_bo->base.num_pages, &par->map); + if (ret) { + vfb->unpin(vfb); + DRM_ERROR("Could not map the fbdev framebuffer.\n"); + goto out_unlock; + } + + par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite); + } + + vmw_fb_dirty_mark(par, par->fb_x, par->fb_y, par->set_fb->width, par->set_fb->height); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 55231cce73a0..e29da45a2847 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1553,14 +1553,10 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }; int i; - u32 assumed_bpp = 2; + u32 assumed_bpp = 4; - /* - * If using screen objects, then assume 32-bpp because that's what the - * SVGA device is assuming - */ - if (dev_priv->active_display_unit == vmw_du_screen_object) - assumed_bpp = 4; + if (dev_priv->assume_16bpp) + assumed_bpp = 2; if (dev_priv->active_display_unit == vmw_du_screen_target) { max_width = min(max_width, dev_priv->stdu_max_width); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index f0374f9b56ca..e57a0bad7a62 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -300,6 +300,9 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, break; } + if (retries == RETRIES) + return -EINVAL; + *msg_len = reply_len; *msg = reply; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 9ca818fb034c..41932a7c4f79 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -399,8 +399,10 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, WARN_ON_ONCE(!stdu->defined); - if (!vfb->dmabuf && new_fb->width == mode->hdisplay && - new_fb->height == mode->vdisplay) + new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb); + + if (new_vfbs && new_vfbs->surface->base_size.width == mode->hdisplay && + new_vfbs->surface->base_size.height == mode->vdisplay) new_content_type = SAME_AS_DISPLAY; else if (vfb->dmabuf) new_content_type = SEPARATE_DMA; @@ -444,7 +446,6 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, content_srf.mip_levels[0] = 1; content_srf.multisample_count = 0; } else { - new_vfbs = vmw_framebuffer_to_vfbs(new_fb); content_srf = *new_vfbs->surface; } @@ -464,7 +465,6 @@ static int vmw_stdu_bind_fb(struct vmw_private *dev_priv, return ret; } } else if (new_content_type == SAME_AS_DISPLAY) { - new_vfbs = vmw_framebuffer_to_vfbs(new_fb); new_display_srf = vmw_surface_reference(new_vfbs->surface); } diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c index aad8c162a825..0cd4f7216239 100644 --- a/drivers/hid/hid-elo.c +++ b/drivers/hid/hid-elo.c @@ -261,7 +261,7 @@ static void elo_remove(struct hid_device *hdev) struct elo_priv *priv = hid_get_drvdata(hdev); hid_hw_stop(hdev); - flush_workqueue(wq); + cancel_delayed_work_sync(&priv->work); kfree(priv); } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index c741f5e50a66..fb6f1f447279 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -61,6 +61,7 @@ MODULE_LICENSE("GPL"); #define MT_QUIRK_ALWAYS_VALID (1 << 4) #define MT_QUIRK_VALID_IS_INRANGE (1 << 5) #define MT_QUIRK_VALID_IS_CONFIDENCE (1 << 6) +#define MT_QUIRK_CONFIDENCE (1 << 7) #define MT_QUIRK_SLOT_IS_CONTACTID_MINUS_ONE (1 << 8) #define MT_QUIRK_NO_AREA (1 << 9) #define MT_QUIRK_IGNORE_DUPLICATES (1 << 10) @@ -78,6 +79,7 @@ struct mt_slot { __s32 contactid; /* the device ContactID assigned to this slot */ bool touch_state; /* is the touch valid? */ bool inrange_state; /* is the finger in proximity of the sensor? */ + bool confidence_state; /* is the touch made by a finger? */ }; struct mt_class { @@ -503,10 +505,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 1; case HID_DG_CONFIDENCE: if (cls->name == MT_CLS_WIN_8 && - field->application == HID_DG_TOUCHPAD) { - cls->quirks &= ~MT_QUIRK_ALWAYS_VALID; - cls->quirks |= MT_QUIRK_VALID_IS_CONFIDENCE; - } + field->application == HID_DG_TOUCHPAD) + cls->quirks |= MT_QUIRK_CONFIDENCE; mt_store_field(usage, td, hi); return 1; case HID_DG_TIPSWITCH: @@ -619,6 +619,7 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input) return; if (td->curvalid || (td->mtclass.quirks & MT_QUIRK_ALWAYS_VALID)) { + int active; int slotnum = mt_compute_slot(td, input); struct mt_slot *s = &td->curdata; struct input_mt *mt = input->mt; @@ -633,10 +634,14 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input) return; } + if (!(td->mtclass.quirks & MT_QUIRK_CONFIDENCE)) + s->confidence_state = 1; + active = (s->touch_state || s->inrange_state) && + s->confidence_state; + input_mt_slot(input, slotnum); - input_mt_report_slot_state(input, MT_TOOL_FINGER, - s->touch_state || s->inrange_state); - if (s->touch_state || s->inrange_state) { + input_mt_report_slot_state(input, MT_TOOL_FINGER, active); + if (active) { /* this finger is in proximity of the sensor */ int wide = (s->w > s->h); /* divided by two to match visual scale of touch */ @@ -701,6 +706,8 @@ static void mt_process_mt_event(struct hid_device *hid, struct hid_field *field, td->curdata.touch_state = value; break; case HID_DG_CONFIDENCE: + if (quirks & MT_QUIRK_CONFIDENCE) + td->curdata.confidence_state = value; if (quirks & MT_QUIRK_VALID_IS_CONFIDENCE) td->curvalid = value; break; @@ -1401,6 +1408,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_PCT) }, + /* Ntrig Panel */ + { .driver_data = MT_CLS_NSMU, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_NTRIG, 0x1b05) }, + /* PixArt optical touch screen */ { .driver_data = MT_CLS_INRANGE_CONTACTNUMBER, MT_USB_DEVICE(USB_VENDOR_ID_PIXART, diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 2f1ddca6f2e0..700145b15088 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -516,13 +516,13 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, goto inval; } else if (uref->usage_index >= field->report_count) goto inval; - - else if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) && - (uref_multi->num_values > HID_MAX_MULTI_USAGES || - uref->usage_index + uref_multi->num_values > field->report_count)) - goto inval; } + if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) && + (uref_multi->num_values > HID_MAX_MULTI_USAGES || + uref->usage_index + uref_multi->num_values > field->report_count)) + goto inval; + switch (cmd) { case HIDIOCGUSAGE: uref->value = field->value[uref->usage_index]; diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index c43318d3416e..2ac87d553e22 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -35,6 +35,7 @@ #include #include #include +#include #include @@ -66,11 +67,13 @@ static DEFINE_MUTEX(i8k_mutex); static char bios_version[4]; +static char bios_machineid[16]; static struct device *i8k_hwmon_dev; static u32 i8k_hwmon_flags; static uint i8k_fan_mult = I8K_FAN_MULT; static uint i8k_pwm_mult; static uint i8k_fan_max = I8K_FAN_HIGH; +static bool disallow_fan_type_call; #define I8K_HWMON_HAVE_TEMP1 (1 << 0) #define I8K_HWMON_HAVE_TEMP2 (1 << 1) @@ -94,13 +97,13 @@ module_param(ignore_dmi, bool, 0); MODULE_PARM_DESC(ignore_dmi, "Continue probing hardware even if DMI data does not match"); #if IS_ENABLED(CONFIG_I8K) -static bool restricted; +static bool restricted = true; module_param(restricted, bool, 0); -MODULE_PARM_DESC(restricted, "Allow fan control if SYS_ADMIN capability set"); +MODULE_PARM_DESC(restricted, "Restrict fan control and serial number to CAP_SYS_ADMIN (default: 1)"); static bool power_status; module_param(power_status, bool, 0600); -MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k"); +MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k (default: 0)"); #endif static uint fan_mult; @@ -235,14 +238,28 @@ static int i8k_get_fan_speed(int fan) /* * Read the fan type. */ -static int i8k_get_fan_type(int fan) +static int _i8k_get_fan_type(int fan) { struct smm_regs regs = { .eax = I8K_SMM_GET_FAN_TYPE, }; + if (disallow_fan_type_call) + return -EINVAL; + regs.ebx = fan & 0xff; return i8k_smm(®s) ? : regs.eax & 0xff; } +static int i8k_get_fan_type(int fan) +{ + /* I8K_SMM_GET_FAN_TYPE SMM call is expensive, so cache values */ + static int types[2] = { INT_MIN, INT_MIN }; + + if (types[fan] == INT_MIN) + types[fan] = _i8k_get_fan_type(fan); + + return types[fan]; +} + /* * Read the fan nominal rpm for specific fan speed. */ @@ -387,14 +404,20 @@ i8k_ioctl_unlocked(struct file *fp, unsigned int cmd, unsigned long arg) switch (cmd) { case I8K_BIOS_VERSION: + if (!isdigit(bios_version[0]) || !isdigit(bios_version[1]) || + !isdigit(bios_version[2])) + return -EINVAL; + val = (bios_version[0] << 16) | (bios_version[1] << 8) | bios_version[2]; break; case I8K_MACHINE_ID: - memset(buff, 0, 16); - strlcpy(buff, i8k_get_dmi_data(DMI_PRODUCT_SERIAL), - sizeof(buff)); + if (restricted && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + memset(buff, 0, sizeof(buff)); + strlcpy(buff, bios_machineid, sizeof(buff)); break; case I8K_FN_STATUS: @@ -511,7 +534,7 @@ static int i8k_proc_show(struct seq_file *seq, void *offset) seq_printf(seq, "%s %s %s %d %d %d %d %d %d %d\n", I8K_PROC_FMT, bios_version, - i8k_get_dmi_data(DMI_PRODUCT_SERIAL), + (restricted && !capable(CAP_SYS_ADMIN)) ? "-1" : bios_machineid, cpu_temp, left_fan, right_fan, left_speed, right_speed, ac_power, fn_key); @@ -718,6 +741,9 @@ static struct attribute *i8k_attrs[] = { static umode_t i8k_is_visible(struct kobject *kobj, struct attribute *attr, int index) { + if (disallow_fan_type_call && + (index == 9 || index == 12)) + return 0; if (index >= 0 && index <= 1 && !(i8k_hwmon_flags & I8K_HWMON_HAVE_TEMP1)) return 0; @@ -767,13 +793,17 @@ static int __init i8k_init_hwmon(void) if (err >= 0) i8k_hwmon_flags |= I8K_HWMON_HAVE_TEMP4; - /* First fan attributes, if fan type is OK */ - err = i8k_get_fan_type(0); + /* First fan attributes, if fan status or type is OK */ + err = i8k_get_fan_status(0); + if (err < 0) + err = i8k_get_fan_type(0); if (err >= 0) i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN1; - /* Second fan attributes, if fan type is OK */ - err = i8k_get_fan_type(1); + /* Second fan attributes, if fan status or type is OK */ + err = i8k_get_fan_status(1); + if (err < 0) + err = i8k_get_fan_type(1); if (err >= 0) i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN2; @@ -929,12 +959,14 @@ static struct dmi_system_id i8k_dmi_table[] __initdata = { MODULE_DEVICE_TABLE(dmi, i8k_dmi_table); -static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = { +/* + * On some machines once I8K_SMM_GET_FAN_TYPE is issued then CPU fan speed + * randomly going up and down due to bug in Dell SMM or BIOS. Here is blacklist + * of affected Dell machines for which we disallow I8K_SMM_GET_FAN_TYPE call. + * See bug: https://bugzilla.kernel.org/show_bug.cgi?id=100121 + */ +static struct dmi_system_id i8k_blacklist_fan_type_dmi_table[] __initdata = { { - /* - * CPU fan speed going up and down on Dell Studio XPS 8000 - * for unknown reasons. - */ .ident = "Dell Studio XPS 8000", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), @@ -942,16 +974,19 @@ static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = { }, }, { - /* - * CPU fan speed going up and down on Dell Studio XPS 8100 - * for unknown reasons. - */ .ident = "Dell Studio XPS 8100", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8100"), }, }, + { + .ident = "Dell Inspiron 580", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Inspiron 580 "), + }, + }, { } }; @@ -966,8 +1001,7 @@ static int __init i8k_probe(void) /* * Get DMI information */ - if (!dmi_check_system(i8k_dmi_table) || - dmi_check_system(i8k_blacklist_dmi_table)) { + if (!dmi_check_system(i8k_dmi_table)) { if (!ignore_dmi && !force) return -ENODEV; @@ -978,8 +1012,13 @@ static int __init i8k_probe(void) i8k_get_dmi_data(DMI_BIOS_VERSION)); } + if (dmi_check_system(i8k_blacklist_fan_type_dmi_table)) + disallow_fan_type_call = true; + strlcpy(bios_version, i8k_get_dmi_data(DMI_BIOS_VERSION), sizeof(bios_version)); + strlcpy(bios_machineid, i8k_get_dmi_data(DMI_PRODUCT_SERIAL), + sizeof(bios_machineid)); /* * Get SMM Dell signature diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 847d1b5f2c13..688be9e060fc 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -300,13 +300,10 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata) if (local_read(&drvdata->mode) == CS_MODE_SYSFS) { /* * The trace run will continue with the same allocated trace - * buffer. As such zero-out the buffer so that we don't end - * up with stale data. - * - * Since the tracer is still enabled drvdata::buf - * can't be NULL. + * buffer. The trace buffer is cleared in tmc_etr_enable_hw(), + * so we don't have to explicitly clear it. Also, since the + * tracer is still enabled drvdata::buf can't be NULL. */ - memset(drvdata->buf, 0, drvdata->size); tmc_etr_enable_hw(drvdata); } else { /* @@ -315,7 +312,7 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata) */ vaddr = drvdata->vaddr; paddr = drvdata->paddr; - drvdata->buf = NULL; + drvdata->buf = drvdata->vaddr = NULL; } drvdata->reading = false; diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 5443d03a1eec..d08d1ab9bba5 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -385,7 +385,6 @@ static int _coresight_build_path(struct coresight_device *csdev, int i; bool found = false; struct coresight_node *node; - struct coresight_connection *conn; /* An activated sink has been found. Enqueue the element */ if ((csdev->type == CORESIGHT_DEV_TYPE_SINK || @@ -394,8 +393,9 @@ static int _coresight_build_path(struct coresight_device *csdev, /* Not a sink - recursively explore each port found on this element */ for (i = 0; i < csdev->nr_outport; i++) { - conn = &csdev->conns[i]; - if (_coresight_build_path(conn->child_dev, path) == 0) { + struct coresight_device *child_dev = csdev->conns[i].child_dev; + + if (child_dev && _coresight_build_path(child_dev, path) == 0) { found = true; break; } @@ -425,6 +425,7 @@ out: struct list_head *coresight_build_path(struct coresight_device *csdev) { struct list_head *path; + int rc; path = kzalloc(sizeof(struct list_head), GFP_KERNEL); if (!path) @@ -432,9 +433,10 @@ struct list_head *coresight_build_path(struct coresight_device *csdev) INIT_LIST_HEAD(path); - if (_coresight_build_path(csdev, path)) { + rc = _coresight_build_path(csdev, path); + if (rc) { kfree(path); - path = NULL; + return ERR_PTR(rc); } return path; @@ -507,8 +509,9 @@ int coresight_enable(struct coresight_device *csdev) goto out; path = coresight_build_path(csdev); - if (!path) { + if (IS_ERR(path)) { pr_err("building path(s) failed\n"); + ret = PTR_ERR(path); goto out; } diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index cc6439ab3f71..041050edd809 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -1268,6 +1268,8 @@ static int qup_i2c_xfer_v2(struct i2c_adapter *adap, } } + idx = 0; + do { if (msgs[idx].len == 0) { ret = -EINVAL; diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 445398c314a3..b126dbaa47e3 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -912,7 +912,7 @@ static int tegra_i2c_probe(struct platform_device *pdev) ret = tegra_i2c_init(i2c_dev); if (ret) { dev_err(&pdev->dev, "Failed to initialize i2c controller"); - goto unprepare_div_clk; + goto disable_div_clk; } ret = devm_request_irq(&pdev->dev, i2c_dev->irq, diff --git a/drivers/i2c/i2c-boardinfo.c b/drivers/i2c/i2c-boardinfo.c index e33022e2d459..6e5fac6a5262 100644 --- a/drivers/i2c/i2c-boardinfo.c +++ b/drivers/i2c/i2c-boardinfo.c @@ -56,9 +56,7 @@ EXPORT_SYMBOL_GPL(__i2c_first_dynamic_bus_num); * The board info passed can safely be __initdata, but be careful of embedded * pointers (for platform_data, functions, etc) since that won't be copied. */ -int __init -i2c_register_board_info(int busnum, - struct i2c_board_info const *info, unsigned len) +int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned len) { int status; diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c index 26e7c5187a58..c6a90b4a9c62 100644 --- a/drivers/i2c/muxes/i2c-mux-reg.c +++ b/drivers/i2c/muxes/i2c-mux-reg.c @@ -145,7 +145,7 @@ static int i2c_mux_reg_probe_dt(struct regmux *mux, mux->data.idle_in_use = true; /* map address from "reg" if exists */ - if (of_address_to_resource(np, 0, &res)) { + if (of_address_to_resource(np, 0, &res) == 0) { mux->data.reg_size = resource_size(&res); mux->data.reg = devm_ioremap_resource(&pdev->dev, &res); if (IS_ERR(mux->data.reg)) diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c index 923f56598d4b..3a9f106787d2 100644 --- a/drivers/iio/accel/kxsd9.c +++ b/drivers/iio/accel/kxsd9.c @@ -81,7 +81,7 @@ static int kxsd9_write_scale(struct iio_dev *indio_dev, int micro) mutex_lock(&st->buf_lock); ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C)); - if (ret) + if (ret < 0) goto error_ret; st->tx[0] = KXSD9_WRITE(KXSD9_REG_CTRL_C); st->tx[1] = (ret & ~KXSD9_FS_MASK) | i; @@ -163,7 +163,7 @@ static int kxsd9_read_raw(struct iio_dev *indio_dev, break; case IIO_CHAN_INFO_SCALE: ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C)); - if (ret) + if (ret < 0) goto error_ret; *val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK]; ret = IIO_VAL_INT_PLUS_MICRO; diff --git a/drivers/iio/accel/st_accel_buffer.c b/drivers/iio/accel/st_accel_buffer.c index a1e642ee13d6..7fddc137e91e 100644 --- a/drivers/iio/accel/st_accel_buffer.c +++ b/drivers/iio/accel/st_accel_buffer.c @@ -91,7 +91,7 @@ static const struct iio_buffer_setup_ops st_accel_buffer_setup_ops = { int st_accel_allocate_ring(struct iio_dev *indio_dev) { - return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time, + return iio_triggered_buffer_setup(indio_dev, NULL, &st_sensors_trigger_handler, &st_accel_buffer_setup_ops); } diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index dc73f2d85e6d..4d95bfc4786c 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -741,6 +741,7 @@ static const struct iio_info accel_info = { static const struct iio_trigger_ops st_accel_trigger_ops = { .owner = THIS_MODULE, .set_trigger_state = ST_ACCEL_TRIGGER_SET_STATE, + .validate_device = st_sensors_validate_device, }; #define ST_ACCEL_TRIGGER_OPS (&st_accel_trigger_ops) #else diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c index 21e19b60e2b9..2123f0ac2e2a 100644 --- a/drivers/iio/adc/ad7266.c +++ b/drivers/iio/adc/ad7266.c @@ -396,8 +396,8 @@ static int ad7266_probe(struct spi_device *spi) st = iio_priv(indio_dev); - st->reg = devm_regulator_get(&spi->dev, "vref"); - if (!IS_ERR_OR_NULL(st->reg)) { + st->reg = devm_regulator_get_optional(&spi->dev, "vref"); + if (!IS_ERR(st->reg)) { ret = regulator_enable(st->reg); if (ret) return ret; @@ -408,6 +408,9 @@ static int ad7266_probe(struct spi_device *spi) st->vref_mv = ret / 1000; } else { + /* Any other error indicates that the regulator does exist */ + if (PTR_ERR(st->reg) != -ENODEV) + return PTR_ERR(st->reg); /* Use internal reference */ st->vref_mv = 2500; } diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index c55898543a47..f1693dbebb8a 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -57,31 +57,20 @@ irqreturn_t st_sensors_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct st_sensor_data *sdata = iio_priv(indio_dev); + s64 timestamp; - /* If we have a status register, check if this IRQ came from us */ - if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) { - u8 status; - - len = sdata->tf->read_byte(&sdata->tb, sdata->dev, - sdata->sensor_settings->drdy_irq.addr_stat_drdy, - &status); - if (len < 0) - dev_err(sdata->dev, "could not read channel status\n"); - - /* - * If this was not caused by any channels on this sensor, - * return IRQ_NONE - */ - if (!(status & (u8)indio_dev->active_scan_mask[0])) - return IRQ_NONE; - } + /* If we do timetamping here, do it before reading the values */ + if (sdata->hw_irq_trigger) + timestamp = sdata->hw_timestamp; + else + timestamp = iio_get_time_ns(); len = st_sensors_get_buffer_element(indio_dev, sdata->buffer_data); if (len < 0) goto st_sensors_get_buffer_element_error; iio_push_to_buffers_with_timestamp(indio_dev, sdata->buffer_data, - pf->timestamp); + timestamp); st_sensors_get_buffer_element_error: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index dffe00692169..9e59c90f6a8d 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -363,6 +363,11 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, if (err < 0) return err; + /* Disable DRDY, this might be still be enabled after reboot. */ + err = st_sensors_set_dataready_irq(indio_dev, false); + if (err < 0) + return err; + if (sdata->current_fullscale) { err = st_sensors_set_fullscale(indio_dev, sdata->current_fullscale->num); @@ -424,6 +429,9 @@ int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable) else drdy_mask = sdata->sensor_settings->drdy_irq.mask_int2; + /* Flag to the poll function that the hardware trigger is in use */ + sdata->hw_irq_trigger = enable; + /* Enable/Disable the interrupt generator for data ready. */ err = st_sensors_write_data_with_mask(indio_dev, sdata->sensor_settings->drdy_irq.addr, diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index da72279fcf99..296e4ff19ae8 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -17,6 +17,73 @@ #include #include "st_sensors_core.h" +/** + * st_sensors_irq_handler() - top half of the IRQ-based triggers + * @irq: irq number + * @p: private handler data + */ +irqreturn_t st_sensors_irq_handler(int irq, void *p) +{ + struct iio_trigger *trig = p; + struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig); + struct st_sensor_data *sdata = iio_priv(indio_dev); + + /* Get the time stamp as close in time as possible */ + sdata->hw_timestamp = iio_get_time_ns(); + return IRQ_WAKE_THREAD; +} + +/** + * st_sensors_irq_thread() - bottom half of the IRQ-based triggers + * @irq: irq number + * @p: private handler data + */ +irqreturn_t st_sensors_irq_thread(int irq, void *p) +{ + struct iio_trigger *trig = p; + struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig); + struct st_sensor_data *sdata = iio_priv(indio_dev); + int ret; + + /* + * If this trigger is backed by a hardware interrupt and we have a + * status register, check if this IRQ came from us + */ + if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) { + u8 status; + + ret = sdata->tf->read_byte(&sdata->tb, sdata->dev, + sdata->sensor_settings->drdy_irq.addr_stat_drdy, + &status); + if (ret < 0) { + dev_err(sdata->dev, "could not read channel status\n"); + goto out_poll; + } + /* + * the lower bits of .active_scan_mask[0] is directly mapped + * to the channels on the sensor: either bit 0 for + * one-dimensional sensors, or e.g. x,y,z for accelerometers, + * gyroscopes or magnetometers. No sensor use more than 3 + * channels, so cut the other status bits here. + */ + status &= 0x07; + + /* + * If this was not caused by any channels on this sensor, + * return IRQ_NONE + */ + if (!indio_dev->active_scan_mask) + return IRQ_NONE; + if (!(status & (u8)indio_dev->active_scan_mask[0])) + return IRQ_NONE; + } + +out_poll: + /* It's our IRQ: proceed to handle the register polling */ + iio_trigger_poll_chained(p); + return IRQ_HANDLED; +} + int st_sensors_allocate_trigger(struct iio_dev *indio_dev, const struct iio_trigger_ops *trigger_ops) { @@ -30,6 +97,10 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, return -ENOMEM; } + iio_trigger_set_drvdata(sdata->trig, indio_dev); + sdata->trig->ops = trigger_ops; + sdata->trig->dev.parent = sdata->dev; + irq = sdata->get_irq_data_ready(indio_dev); irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq)); /* @@ -77,9 +148,12 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.addr_stat_drdy) irq_trig |= IRQF_SHARED; - err = request_threaded_irq(irq, - iio_trigger_generic_data_rdy_poll, - NULL, + /* Let's create an interrupt thread masking the hard IRQ here */ + irq_trig |= IRQF_ONESHOT; + + err = request_threaded_irq(sdata->get_irq_data_ready(indio_dev), + st_sensors_irq_handler, + st_sensors_irq_thread, irq_trig, sdata->trig->name, sdata->trig); @@ -88,10 +162,6 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, goto iio_trigger_free; } - iio_trigger_set_drvdata(sdata->trig, indio_dev); - sdata->trig->ops = trigger_ops; - sdata->trig->dev.parent = sdata->dev; - err = iio_trigger_register(sdata->trig); if (err < 0) { dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); @@ -119,6 +189,18 @@ void st_sensors_deallocate_trigger(struct iio_dev *indio_dev) } EXPORT_SYMBOL(st_sensors_deallocate_trigger); +int st_sensors_validate_device(struct iio_trigger *trig, + struct iio_dev *indio_dev) +{ + struct iio_dev *indio = iio_trigger_get_drvdata(trig); + + if (indio != indio_dev) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(st_sensors_validate_device); + MODULE_AUTHOR("Denis Ciocca "); MODULE_DESCRIPTION("STMicroelectronics ST-sensors trigger"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig index e63b957c985f..f7c71da42f15 100644 --- a/drivers/iio/dac/Kconfig +++ b/drivers/iio/dac/Kconfig @@ -247,7 +247,7 @@ config MCP4922 config STX104 tristate "Apex Embedded Systems STX104 DAC driver" - depends on X86 && ISA + depends on X86 && ISA_BUS_API help Say yes here to build support for the 2-channel DAC on the Apex Embedded Systems STX104 integrated analog PC/104 card. The base port diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index 948f600e7059..69bde5909854 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -525,7 +525,7 @@ static int ad5592r_alloc_channels(struct ad5592r_state *st) device_for_each_child_node(st->dev, child) { ret = fwnode_property_read_u32(child, "reg", ®); - if (ret || reg > ARRAY_SIZE(st->channel_modes)) + if (ret || reg >= ARRAY_SIZE(st->channel_modes)) continue; ret = fwnode_property_read_u32(child, "adi,mode", &tmp); diff --git a/drivers/iio/gyro/st_gyro_buffer.c b/drivers/iio/gyro/st_gyro_buffer.c index d67b17b6a7aa..a5377044e42f 100644 --- a/drivers/iio/gyro/st_gyro_buffer.c +++ b/drivers/iio/gyro/st_gyro_buffer.c @@ -91,7 +91,7 @@ static const struct iio_buffer_setup_ops st_gyro_buffer_setup_ops = { int st_gyro_allocate_ring(struct iio_dev *indio_dev) { - return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time, + return iio_triggered_buffer_setup(indio_dev, NULL, &st_sensors_trigger_handler, &st_gyro_buffer_setup_ops); } diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index 52a3c87c375c..a8012955a1f6 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -409,6 +409,7 @@ static const struct iio_info gyro_info = { static const struct iio_trigger_ops st_gyro_trigger_ops = { .owner = THIS_MODULE, .set_trigger_state = ST_GYRO_TRIGGER_SET_STATE, + .validate_device = st_sensors_validate_device, }; #define ST_GYRO_TRIGGER_OPS (&st_gyro_trigger_ops) #else diff --git a/drivers/iio/humidity/am2315.c b/drivers/iio/humidity/am2315.c index 3be6d209a159..11535911a5c6 100644 --- a/drivers/iio/humidity/am2315.c +++ b/drivers/iio/humidity/am2315.c @@ -165,10 +165,8 @@ static irqreturn_t am2315_trigger_handler(int irq, void *p) struct am2315_sensor_data sensor_data; ret = am2315_read_data(data, &sensor_data); - if (ret < 0) { - mutex_unlock(&data->lock); + if (ret < 0) goto err; - } mutex_lock(&data->lock); if (*(indio_dev->active_scan_mask) == AM2315_ALL_CHANNEL_MASK) { diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index fa4767613173..a03832a5fc95 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -55,7 +55,7 @@ static const struct { }, { /* IIO_HUMIDITYRELATIVE channel */ .shift = 8, - .mask = 2, + .mask = 3, }, }; @@ -164,14 +164,14 @@ static int hdc100x_get_measurement(struct hdc100x_data *data, dev_err(&client->dev, "cannot read high byte measurement"); return ret; } - val = ret << 6; + val = ret << 8; ret = i2c_smbus_read_byte(client); if (ret < 0) { dev_err(&client->dev, "cannot read low byte measurement"); return ret; } - val |= ret >> 2; + val |= ret; return val; } @@ -211,18 +211,18 @@ static int hdc100x_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_SCALE: if (chan->type == IIO_TEMP) { - *val = 165; - *val2 = 65536 >> 2; + *val = 165000; + *val2 = 65536; return IIO_VAL_FRACTIONAL; } else { - *val = 0; - *val2 = 10000; - return IIO_VAL_INT_PLUS_MICRO; + *val = 100; + *val2 = 65536; + return IIO_VAL_FRACTIONAL; } break; case IIO_CHAN_INFO_OFFSET: - *val = -3971; - *val2 = 879096; + *val = -15887; + *val2 = 515151; return IIO_VAL_INT_PLUS_MICRO; default: return -EINVAL; diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c index 0bf92b06d7d8..b8a290ec984e 100644 --- a/drivers/iio/imu/bmi160/bmi160_core.c +++ b/drivers/iio/imu/bmi160/bmi160_core.c @@ -209,11 +209,11 @@ static const struct bmi160_scale_item bmi160_scale_table[] = { }; static const struct bmi160_odr bmi160_accel_odr[] = { - {0x01, 0, 78125}, - {0x02, 1, 5625}, - {0x03, 3, 125}, - {0x04, 6, 25}, - {0x05, 12, 5}, + {0x01, 0, 781250}, + {0x02, 1, 562500}, + {0x03, 3, 125000}, + {0x04, 6, 250000}, + {0x05, 12, 500000}, {0x06, 25, 0}, {0x07, 50, 0}, {0x08, 100, 0}, @@ -229,7 +229,7 @@ static const struct bmi160_odr bmi160_gyro_odr[] = { {0x08, 100, 0}, {0x09, 200, 0}, {0x0A, 400, 0}, - {0x0B, 8000, 0}, + {0x0B, 800, 0}, {0x0C, 1600, 0}, {0x0D, 3200, 0}, }; @@ -364,8 +364,8 @@ int bmi160_set_odr(struct bmi160_data *data, enum bmi160_sensor_type t, return regmap_update_bits(data->regmap, bmi160_regs[t].config, - bmi160_odr_table[t].tbl[i].bits, - bmi160_regs[t].config_odr_mask); + bmi160_regs[t].config_odr_mask, + bmi160_odr_table[t].tbl[i].bits); } static int bmi160_get_odr(struct bmi160_data *data, enum bmi160_sensor_type t, diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c index f62b8bd9ad7e..dd6fc6d21f9d 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c @@ -56,6 +56,7 @@ static int asus_acpi_get_sensor_info(struct acpi_device *adev, int i; acpi_status status; union acpi_object *cpm; + int ret; status = acpi_evaluate_object(adev->handle, "CNF0", NULL, &buffer); if (ACPI_FAILURE(status)) @@ -82,10 +83,10 @@ static int asus_acpi_get_sensor_info(struct acpi_device *adev, } } } - + ret = cpm->package.count; kfree(buffer.pointer); - return cpm->package.count; + return ret; } static int acpi_i2c_check_resource(struct acpi_resource *ares, void *data) diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index ae2806aafb72..0c52dfe64977 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -210,22 +210,35 @@ static int iio_trigger_attach_poll_func(struct iio_trigger *trig, /* Prevent the module from being removed whilst attached to a trigger */ __module_get(pf->indio_dev->info->driver_module); + + /* Get irq number */ pf->irq = iio_trigger_get_irq(trig); + if (pf->irq < 0) + goto out_put_module; + + /* Request irq */ ret = request_threaded_irq(pf->irq, pf->h, pf->thread, pf->type, pf->name, pf); - if (ret < 0) { - module_put(pf->indio_dev->info->driver_module); - return ret; - } + if (ret < 0) + goto out_put_irq; + /* Enable trigger in driver */ if (trig->ops && trig->ops->set_trigger_state && notinuse) { ret = trig->ops->set_trigger_state(trig, true); if (ret < 0) - module_put(pf->indio_dev->info->driver_module); + goto out_free_irq; } return ret; + +out_free_irq: + free_irq(pf->irq, pf); +out_put_irq: + iio_trigger_put_irq(trig, pf->irq); +out_put_module: + module_put(pf->indio_dev->info->driver_module); + return ret; } static int iio_trigger_detach_poll_func(struct iio_trigger *trig, diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c index b4dbb3912977..651d57b8abbf 100644 --- a/drivers/iio/light/apds9960.c +++ b/drivers/iio/light/apds9960.c @@ -1011,6 +1011,7 @@ static int apds9960_probe(struct i2c_client *client, iio_device_attach_buffer(indio_dev, buffer); + indio_dev->dev.parent = &client->dev; indio_dev->info = &apds9960_info; indio_dev->name = APDS9960_DRV_NAME; indio_dev->channels = apds9960_channels; diff --git a/drivers/iio/light/bh1780.c b/drivers/iio/light/bh1780.c index 72b364e4aa72..b54dcba05a82 100644 --- a/drivers/iio/light/bh1780.c +++ b/drivers/iio/light/bh1780.c @@ -84,7 +84,7 @@ static int bh1780_debugfs_reg_access(struct iio_dev *indio_dev, int ret; if (!readval) - bh1780_write(bh1780, (u8)reg, (u8)writeval); + return bh1780_write(bh1780, (u8)reg, (u8)writeval); ret = bh1780_read(bh1780, (u8)reg); if (ret < 0) @@ -187,7 +187,7 @@ static int bh1780_probe(struct i2c_client *client, indio_dev->dev.parent = &client->dev; indio_dev->info = &bh1780_info; - indio_dev->name = id->name; + indio_dev->name = "bh1780"; indio_dev->channels = bh1780_channels; indio_dev->num_channels = ARRAY_SIZE(bh1780_channels); indio_dev->modes = INDIO_DIRECT_MODE; @@ -226,7 +226,8 @@ static int bh1780_remove(struct i2c_client *client) static int bh1780_runtime_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); - struct bh1780_data *bh1780 = i2c_get_clientdata(client); + struct iio_dev *indio_dev = i2c_get_clientdata(client); + struct bh1780_data *bh1780 = iio_priv(indio_dev); int ret; ret = bh1780_write(bh1780, BH1780_REG_CONTROL, BH1780_POFF); @@ -241,7 +242,8 @@ static int bh1780_runtime_suspend(struct device *dev) static int bh1780_runtime_resume(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); - struct bh1780_data *bh1780 = i2c_get_clientdata(client); + struct iio_dev *indio_dev = i2c_get_clientdata(client); + struct bh1780_data *bh1780 = iio_priv(indio_dev); int ret; ret = bh1780_write(bh1780, BH1780_REG_CONTROL, BH1780_PON); diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c index e01e58a9bd14..f17cb2ea18f5 100644 --- a/drivers/iio/light/max44000.c +++ b/drivers/iio/light/max44000.c @@ -147,7 +147,6 @@ static const struct iio_chan_spec max44000_channels[] = { { .type = IIO_PROXIMITY, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .scan_index = MAX44000_SCAN_INDEX_PRX, .scan_type = { .sign = 'u', diff --git a/drivers/iio/magnetometer/st_magn_buffer.c b/drivers/iio/magnetometer/st_magn_buffer.c index ecd3bd0a9769..0a9e8fadfa9d 100644 --- a/drivers/iio/magnetometer/st_magn_buffer.c +++ b/drivers/iio/magnetometer/st_magn_buffer.c @@ -82,7 +82,7 @@ static const struct iio_buffer_setup_ops st_magn_buffer_setup_ops = { int st_magn_allocate_ring(struct iio_dev *indio_dev) { - return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time, + return iio_triggered_buffer_setup(indio_dev, NULL, &st_sensors_trigger_handler, &st_magn_buffer_setup_ops); } diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 62036d2a9956..8250fc322c56 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -572,6 +572,7 @@ static const struct iio_info magn_info = { static const struct iio_trigger_ops st_magn_trigger_ops = { .owner = THIS_MODULE, .set_trigger_state = ST_MAGN_TRIGGER_SET_STATE, + .validate_device = st_sensors_validate_device, }; #define ST_MAGN_TRIGGER_OPS (&st_magn_trigger_ops) #else diff --git a/drivers/iio/pressure/bmp280.c b/drivers/iio/pressure/bmp280.c index 2f1498e12bb2..724452d61846 100644 --- a/drivers/iio/pressure/bmp280.c +++ b/drivers/iio/pressure/bmp280.c @@ -879,8 +879,8 @@ static int bmp280_probe(struct i2c_client *client, if (ret < 0) return ret; if (chip_id != id->driver_data) { - dev_err(&client->dev, "bad chip id. expected %x got %x\n", - BMP280_CHIP_ID, chip_id); + dev_err(&client->dev, "bad chip id. expected %lx got %x\n", + id->driver_data, chip_id); return -EINVAL; } diff --git a/drivers/iio/pressure/st_pressure_buffer.c b/drivers/iio/pressure/st_pressure_buffer.c index 2ff53f222352..99468d0a64e7 100644 --- a/drivers/iio/pressure/st_pressure_buffer.c +++ b/drivers/iio/pressure/st_pressure_buffer.c @@ -82,7 +82,7 @@ static const struct iio_buffer_setup_ops st_press_buffer_setup_ops = { int st_press_allocate_ring(struct iio_dev *indio_dev) { - return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time, + return iio_triggered_buffer_setup(indio_dev, NULL, &st_sensors_trigger_handler, &st_press_buffer_setup_ops); } diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index 9e9b72a8f18f..92a118c3c4ac 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -28,15 +28,21 @@ #include #include "st_pressure.h" +#define MCELSIUS_PER_CELSIUS 1000 + +/* Default pressure sensitivity */ #define ST_PRESS_LSB_PER_MBAR 4096UL #define ST_PRESS_KPASCAL_NANO_SCALE (100000000UL / \ ST_PRESS_LSB_PER_MBAR) + +/* Default temperature sensitivity */ #define ST_PRESS_LSB_PER_CELSIUS 480UL -#define ST_PRESS_CELSIUS_NANO_SCALE (1000000000UL / \ - ST_PRESS_LSB_PER_CELSIUS) +#define ST_PRESS_MILLI_CELSIUS_OFFSET 42500UL + #define ST_PRESS_NUMBER_DATA_CHANNELS 1 /* FULLSCALE */ +#define ST_PRESS_FS_AVL_1100MB 1100 #define ST_PRESS_FS_AVL_1260MB 1260 #define ST_PRESS_1_OUT_XL_ADDR 0x28 @@ -54,9 +60,6 @@ #define ST_PRESS_LPS331AP_PW_MASK 0x80 #define ST_PRESS_LPS331AP_FS_ADDR 0x23 #define ST_PRESS_LPS331AP_FS_MASK 0x30 -#define ST_PRESS_LPS331AP_FS_AVL_1260_VAL 0x00 -#define ST_PRESS_LPS331AP_FS_AVL_1260_GAIN ST_PRESS_KPASCAL_NANO_SCALE -#define ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN ST_PRESS_CELSIUS_NANO_SCALE #define ST_PRESS_LPS331AP_BDU_ADDR 0x20 #define ST_PRESS_LPS331AP_BDU_MASK 0x04 #define ST_PRESS_LPS331AP_DRDY_IRQ_ADDR 0x22 @@ -67,9 +70,14 @@ #define ST_PRESS_LPS331AP_OD_IRQ_ADDR 0x22 #define ST_PRESS_LPS331AP_OD_IRQ_MASK 0x40 #define ST_PRESS_LPS331AP_MULTIREAD_BIT true -#define ST_PRESS_LPS331AP_TEMP_OFFSET 42500 /* CUSTOM VALUES FOR LPS001WP SENSOR */ + +/* LPS001WP pressure resolution */ +#define ST_PRESS_LPS001WP_LSB_PER_MBAR 16UL +/* LPS001WP temperature resolution */ +#define ST_PRESS_LPS001WP_LSB_PER_CELSIUS 64UL + #define ST_PRESS_LPS001WP_WAI_EXP 0xba #define ST_PRESS_LPS001WP_ODR_ADDR 0x20 #define ST_PRESS_LPS001WP_ODR_MASK 0x30 @@ -78,6 +86,8 @@ #define ST_PRESS_LPS001WP_ODR_AVL_13HZ_VAL 0x03 #define ST_PRESS_LPS001WP_PW_ADDR 0x20 #define ST_PRESS_LPS001WP_PW_MASK 0x40 +#define ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN \ + (100000000UL / ST_PRESS_LPS001WP_LSB_PER_MBAR) #define ST_PRESS_LPS001WP_BDU_ADDR 0x20 #define ST_PRESS_LPS001WP_BDU_MASK 0x04 #define ST_PRESS_LPS001WP_MULTIREAD_BIT true @@ -94,11 +104,6 @@ #define ST_PRESS_LPS25H_ODR_AVL_25HZ_VAL 0x04 #define ST_PRESS_LPS25H_PW_ADDR 0x20 #define ST_PRESS_LPS25H_PW_MASK 0x80 -#define ST_PRESS_LPS25H_FS_ADDR 0x00 -#define ST_PRESS_LPS25H_FS_MASK 0x00 -#define ST_PRESS_LPS25H_FS_AVL_1260_VAL 0x00 -#define ST_PRESS_LPS25H_FS_AVL_1260_GAIN ST_PRESS_KPASCAL_NANO_SCALE -#define ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN ST_PRESS_CELSIUS_NANO_SCALE #define ST_PRESS_LPS25H_BDU_ADDR 0x20 #define ST_PRESS_LPS25H_BDU_MASK 0x04 #define ST_PRESS_LPS25H_DRDY_IRQ_ADDR 0x23 @@ -109,7 +114,6 @@ #define ST_PRESS_LPS25H_OD_IRQ_ADDR 0x22 #define ST_PRESS_LPS25H_OD_IRQ_MASK 0x40 #define ST_PRESS_LPS25H_MULTIREAD_BIT true -#define ST_PRESS_LPS25H_TEMP_OFFSET 42500 #define ST_PRESS_LPS25H_OUT_XL_ADDR 0x28 #define ST_TEMP_LPS25H_OUT_L_ADDR 0x2b @@ -161,7 +165,9 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = { .storagebits = 16, .endianness = IIO_LE, }, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), + .info_mask_separate = + BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_SCALE), .modified = 0, }, { @@ -177,7 +183,7 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = { }, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_OFFSET), + BIT(IIO_CHAN_INFO_SCALE), .modified = 0, }, IIO_CHAN_SOFT_TIMESTAMP(1) @@ -212,11 +218,14 @@ static const struct st_sensor_settings st_press_sensors_settings[] = { .addr = ST_PRESS_LPS331AP_FS_ADDR, .mask = ST_PRESS_LPS331AP_FS_MASK, .fs_avl = { + /* + * Pressure and temperature sensitivity values + * as defined in table 3 of LPS331AP datasheet. + */ [0] = { .num = ST_PRESS_FS_AVL_1260MB, - .value = ST_PRESS_LPS331AP_FS_AVL_1260_VAL, - .gain = ST_PRESS_LPS331AP_FS_AVL_1260_GAIN, - .gain2 = ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN, + .gain = ST_PRESS_KPASCAL_NANO_SCALE, + .gain2 = ST_PRESS_LSB_PER_CELSIUS, }, }, }, @@ -261,7 +270,17 @@ static const struct st_sensor_settings st_press_sensors_settings[] = { .value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE, }, .fs = { - .addr = 0, + .fs_avl = { + /* + * Pressure and temperature resolution values + * as defined in table 3 of LPS001WP datasheet. + */ + [0] = { + .num = ST_PRESS_FS_AVL_1100MB, + .gain = ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN, + .gain2 = ST_PRESS_LPS001WP_LSB_PER_CELSIUS, + }, + }, }, .bdu = { .addr = ST_PRESS_LPS001WP_BDU_ADDR, @@ -298,14 +317,15 @@ static const struct st_sensor_settings st_press_sensors_settings[] = { .value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE, }, .fs = { - .addr = ST_PRESS_LPS25H_FS_ADDR, - .mask = ST_PRESS_LPS25H_FS_MASK, .fs_avl = { + /* + * Pressure and temperature sensitivity values + * as defined in table 3 of LPS25H datasheet. + */ [0] = { .num = ST_PRESS_FS_AVL_1260MB, - .value = ST_PRESS_LPS25H_FS_AVL_1260_VAL, - .gain = ST_PRESS_LPS25H_FS_AVL_1260_GAIN, - .gain2 = ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN, + .gain = ST_PRESS_KPASCAL_NANO_SCALE, + .gain2 = ST_PRESS_LSB_PER_CELSIUS, }, }, }, @@ -364,26 +384,26 @@ static int st_press_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: - *val = 0; - switch (ch->type) { case IIO_PRESSURE: + *val = 0; *val2 = press_data->current_fullscale->gain; - break; + return IIO_VAL_INT_PLUS_NANO; case IIO_TEMP: + *val = MCELSIUS_PER_CELSIUS; *val2 = press_data->current_fullscale->gain2; - break; + return IIO_VAL_FRACTIONAL; default: err = -EINVAL; goto read_error; } - return IIO_VAL_INT_PLUS_NANO; case IIO_CHAN_INFO_OFFSET: switch (ch->type) { case IIO_TEMP: - *val = 425; - *val2 = 10; + *val = ST_PRESS_MILLI_CELSIUS_OFFSET * + press_data->current_fullscale->gain2; + *val2 = MCELSIUS_PER_CELSIUS; break; default: err = -EINVAL; @@ -425,6 +445,7 @@ static const struct iio_info press_info = { static const struct iio_trigger_ops st_press_trigger_ops = { .owner = THIS_MODULE, .set_trigger_state = ST_PRESS_TRIGGER_SET_STATE, + .validate_device = st_sensors_validate_device, }; #define ST_PRESS_TRIGGER_OPS (&st_press_trigger_ops) #else diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c index f4d29d5dbd5f..e2f926cdcad2 100644 --- a/drivers/iio/proximity/as3935.c +++ b/drivers/iio/proximity/as3935.c @@ -64,6 +64,7 @@ struct as3935_state { struct delayed_work work; u32 tune_cap; + u8 buffer[16]; /* 8-bit data + 56-bit padding + 64-bit timestamp */ u8 buf[2] ____cacheline_aligned; }; @@ -72,7 +73,8 @@ static const struct iio_chan_spec as3935_channels[] = { .type = IIO_PROXIMITY, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_PROCESSED), + BIT(IIO_CHAN_INFO_PROCESSED) | + BIT(IIO_CHAN_INFO_SCALE), .scan_index = 0, .scan_type = { .sign = 'u', @@ -181,7 +183,12 @@ static int as3935_read_raw(struct iio_dev *indio_dev, /* storm out of range */ if (*val == AS3935_DATA_MASK) return -EINVAL; - *val *= 1000; + + if (m == IIO_CHAN_INFO_PROCESSED) + *val *= 1000; + break; + case IIO_CHAN_INFO_SCALE: + *val = 1000; break; default: return -EINVAL; @@ -206,10 +213,10 @@ static irqreturn_t as3935_trigger_handler(int irq, void *private) ret = as3935_read(st, AS3935_DATA, &val); if (ret) goto err_read; - val &= AS3935_DATA_MASK; - val *= 1000; - iio_push_to_buffers_with_timestamp(indio_dev, &val, pf->timestamp); + st->buffer[0] = val & AS3935_DATA_MASK; + iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer, + pf->timestamp); err_read: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 040966775f40..1a2984c28b95 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -411,7 +411,9 @@ int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port, for (ix = 0; ix < table->sz; ix++) if (table->data_vec[ix].attr.ndev == ndev) - if (!del_gid(ib_dev, port, table, ix, false)) + if (!del_gid(ib_dev, port, table, ix, + !!(table->data_vec[ix].props & + GID_TABLE_ENTRY_DEFAULT))) deleted = true; write_unlock_irq(&table->rwlock); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index f0c91ba3178a..ad1b1adcf6f0 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -708,17 +708,6 @@ static void cma_deref_id(struct rdma_id_private *id_priv) complete(&id_priv->comp); } -static int cma_disable_callback(struct rdma_id_private *id_priv, - enum rdma_cm_state state) -{ - mutex_lock(&id_priv->handler_mutex); - if (id_priv->state != state) { - mutex_unlock(&id_priv->handler_mutex); - return -EINVAL; - } - return 0; -} - struct rdma_cm_id *rdma_create_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_port_space ps, @@ -1671,11 +1660,12 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) struct rdma_cm_event event; int ret = 0; + mutex_lock(&id_priv->handler_mutex); if ((ib_event->event != IB_CM_TIMEWAIT_EXIT && - cma_disable_callback(id_priv, RDMA_CM_CONNECT)) || + id_priv->state != RDMA_CM_CONNECT) || (ib_event->event == IB_CM_TIMEWAIT_EXIT && - cma_disable_callback(id_priv, RDMA_CM_DISCONNECT))) - return 0; + id_priv->state != RDMA_CM_DISCONNECT)) + goto out; memset(&event, 0, sizeof event); switch (ib_event->event) { @@ -1870,7 +1860,7 @@ static int cma_check_req_qp_type(struct rdma_cm_id *id, struct ib_cm_event *ib_e 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_id_private *listen_id, *conn_id = NULL; struct rdma_cm_event event; struct net_device *net_dev; int offset, ret; @@ -1884,9 +1874,10 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) goto net_dev_put; } - if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) { + mutex_lock(&listen_id->handler_mutex); + if (listen_id->state != RDMA_CM_LISTEN) { ret = -ECONNABORTED; - goto net_dev_put; + goto err1; } memset(&event, 0, sizeof event); @@ -1976,8 +1967,9 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; - if (cma_disable_callback(id_priv, RDMA_CM_CONNECT)) - return 0; + mutex_lock(&id_priv->handler_mutex); + if (id_priv->state != RDMA_CM_CONNECT) + goto out; memset(&event, 0, sizeof event); switch (iw_event->event) { @@ -2029,6 +2021,7 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) return ret; } +out: mutex_unlock(&id_priv->handler_mutex); return ret; } @@ -2039,13 +2032,15 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, struct rdma_cm_id *new_cm_id; struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event; - int ret; + int ret = -ECONNABORTED; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; listen_id = cm_id->context; - if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) - return -ECONNABORTED; + + mutex_lock(&listen_id->handler_mutex); + if (listen_id->state != RDMA_CM_LISTEN) + goto out; /* Create a new RDMA id for the new IW CM ID */ new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net, @@ -3216,8 +3211,9 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; int ret = 0; - if (cma_disable_callback(id_priv, RDMA_CM_CONNECT)) - return 0; + mutex_lock(&id_priv->handler_mutex); + if (id_priv->state != RDMA_CM_CONNECT) + goto out; memset(&event, 0, sizeof event); switch (ib_event->event) { @@ -3673,12 +3669,13 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) struct rdma_id_private *id_priv; struct cma_multicast *mc = multicast->context; struct rdma_cm_event event; - int ret; + int ret = 0; id_priv = mc->id_priv; - if (cma_disable_callback(id_priv, RDMA_CM_ADDR_BOUND) && - cma_disable_callback(id_priv, RDMA_CM_ADDR_RESOLVED)) - return 0; + mutex_lock(&id_priv->handler_mutex); + if (id_priv->state != RDMA_CM_ADDR_BOUND && + id_priv->state != RDMA_CM_ADDR_RESOLVED) + goto out; if (!status) status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); @@ -3720,6 +3717,7 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) return 0; } +out: mutex_unlock(&id_priv->handler_mutex); return 0; } @@ -3878,12 +3876,12 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; if (addr->sa_family == AF_INET) { - if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) + if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { + mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid, true); - if (!err) { - mc->igmp_joined = true; - mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; + if (!err) + mc->igmp_joined = true; } } else { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index a5793c8f1590..60df4f8e81be 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -530,6 +530,7 @@ static PORT_PMA_ATTR(port_xmit_data , 12, 32, 192); static PORT_PMA_ATTR(port_rcv_data , 13, 32, 224); static PORT_PMA_ATTR(port_xmit_packets , 14, 32, 256); static PORT_PMA_ATTR(port_rcv_packets , 15, 32, 288); +static PORT_PMA_ATTR(port_xmit_wait , 0, 32, 320); /* * Counters added by extended set @@ -560,6 +561,7 @@ static struct attribute *pma_attrs[] = { &port_pma_attr_port_rcv_data.attr.attr, &port_pma_attr_port_xmit_packets.attr.attr, &port_pma_attr_port_rcv_packets.attr.attr, + &port_pma_attr_port_xmit_wait.attr.attr, NULL }; @@ -579,6 +581,7 @@ static struct attribute *pma_attrs_ext[] = { &port_pma_attr_ext_port_xmit_data.attr.attr, &port_pma_attr_ext_port_rcv_data.attr.attr, &port_pma_attr_ext_port_xmit_packets.attr.attr, + &port_pma_attr_port_xmit_wait.attr.attr, &port_pma_attr_ext_port_rcv_packets.attr.attr, &port_pma_attr_ext_unicast_rcv_packets.attr.attr, &port_pma_attr_ext_unicast_xmit_packets.attr.attr, @@ -604,6 +607,7 @@ static struct attribute *pma_attrs_noietf[] = { &port_pma_attr_ext_port_rcv_data.attr.attr, &port_pma_attr_ext_port_xmit_packets.attr.attr, &port_pma_attr_ext_port_rcv_packets.attr.attr, + &port_pma_attr_port_xmit_wait.attr.attr, NULL }; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 1a8babb8ee3c..825021d1008b 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1747,7 +1747,7 @@ static int create_qp(struct ib_uverbs_file *file, struct ib_srq *srq = NULL; struct ib_qp *qp; char *buf; - struct ib_qp_init_attr attr; + struct ib_qp_init_attr attr = {}; struct ib_uverbs_ex_create_qp_resp resp; int ret; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 1d7d4cf442e3..6298f54b4137 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -511,12 +511,16 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, ah_attr->grh.dgid = sgid; if (!rdma_cap_eth_ah(device, port_num)) { - ret = ib_find_cached_gid_by_port(device, &dgid, - IB_GID_TYPE_IB, - port_num, NULL, - &gid_index); - if (ret) - return ret; + if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) { + ret = ib_find_cached_gid_by_port(device, &dgid, + IB_GID_TYPE_IB, + port_num, NULL, + &gid_index); + if (ret) + return ret; + } else { + gid_index = 0; + } } ah_attr->grh.sgid_index = (u8) gid_index; diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 81619fbb5842..dad4d0ebbdff 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1037,7 +1037,7 @@ static void dc_shutdown(struct hfi1_devdata *); static void dc_start(struct hfi1_devdata *); static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp, unsigned int *np); -static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd); +static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd); /* * Error interrupt table entry. This is used as input to the interrupt @@ -6962,8 +6962,6 @@ void handle_link_down(struct work_struct *work) } reset_neighbor_info(ppd); - if (ppd->mgmt_allowed) - remove_full_mgmt_pkey(ppd); /* disable the port */ clear_rcvctrl(ppd->dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK); @@ -7070,12 +7068,16 @@ static void add_full_mgmt_pkey(struct hfi1_pportdata *ppd) __func__, ppd->pkeys[2], FULL_MGMT_P_KEY); ppd->pkeys[2] = FULL_MGMT_P_KEY; (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); + hfi1_event_pkey_change(ppd->dd, ppd->port); } -static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd) +static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd) { - ppd->pkeys[2] = 0; - (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); + if (ppd->pkeys[2] != 0) { + ppd->pkeys[2] = 0; + (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); + hfi1_event_pkey_change(ppd->dd, ppd->port); + } } /* @@ -9168,6 +9170,13 @@ int start_link(struct hfi1_pportdata *ppd) return 0; } + /* + * FULL_MGMT_P_KEY is cleared from the pkey table, so that the + * pkey table can be configured properly if the HFI unit is connected + * to switch port with MgmtAllowed=NO + */ + clear_full_mgmt_pkey(ppd); + return set_link_state(ppd, HLS_DN_POLL); } @@ -9777,7 +9786,7 @@ static void set_send_length(struct hfi1_pportdata *ppd) u64 len1 = 0, len2 = (((dd->vld[15].mtu + max_hb) >> 2) & SEND_LEN_CHECK1_LEN_VL15_MASK) << SEND_LEN_CHECK1_LEN_VL15_SHIFT; - int i; + int i, j; u32 thres; for (i = 0; i < ppd->vls_supported; i++) { @@ -9801,7 +9810,10 @@ static void set_send_length(struct hfi1_pportdata *ppd) sc_mtu_to_threshold(dd->vld[i].sc, dd->vld[i].mtu, dd->rcd[0]->rcvhdrqentsize)); - sc_set_cr_threshold(dd->vld[i].sc, thres); + for (j = 0; j < INIT_SC_PER_VL; j++) + sc_set_cr_threshold( + pio_select_send_context_vl(dd, j, i), + thres); } thres = min(sc_percent_to_threshold(dd->vld[15].sc, 50), sc_mtu_to_threshold(dd->vld[15].sc, @@ -14101,8 +14113,14 @@ static int init_asic_data(struct hfi1_devdata *dd) { unsigned long flags; struct hfi1_devdata *tmp, *peer = NULL; + struct hfi1_asic_data *asic_data; int ret = 0; + /* pre-allocate the asic structure in case we are the first device */ + asic_data = kzalloc(sizeof(*dd->asic_data), GFP_KERNEL); + if (!asic_data) + return -ENOMEM; + spin_lock_irqsave(&hfi1_devs_lock, flags); /* Find our peer device */ list_for_each_entry(tmp, &hfi1_dev_list, list) { @@ -14114,18 +14132,14 @@ static int init_asic_data(struct hfi1_devdata *dd) } if (peer) { + /* use already allocated structure */ dd->asic_data = peer->asic_data; + kfree(asic_data); } else { - dd->asic_data = kzalloc(sizeof(*dd->asic_data), GFP_KERNEL); - if (!dd->asic_data) { - ret = -ENOMEM; - goto done; - } + dd->asic_data = asic_data; mutex_init(&dd->asic_data->asic_resource_mutex); } dd->asic_data->dds[dd->hfi1_id] = dd; /* self back-pointer */ - -done: spin_unlock_irqrestore(&hfi1_devs_lock, flags); return ret; } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 7a5b0e676cc7..c702a009608f 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -203,6 +203,9 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, switch (cmd) { case HFI1_IOCTL_ASSIGN_CTXT: + if (uctxt) + return -EINVAL; + if (copy_from_user(&uinfo, (struct hfi1_user_info __user *)arg, sizeof(uinfo))) diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 0d28a5a40fae..eed971ccd2a1 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1383,7 +1383,7 @@ static void postinit_cleanup(struct hfi1_devdata *dd) static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { int ret = 0, j, pidx, initfail; - struct hfi1_devdata *dd = NULL; + struct hfi1_devdata *dd = ERR_PTR(-EINVAL); struct hfi1_pportdata *ppd; /* First, lock the non-writable module parameters */ diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 219029576ba0..fca07a1d6c28 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -78,6 +78,16 @@ static inline void clear_opa_smp_data(struct opa_smp *smp) memset(data, 0, size); } +void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port) +{ + struct ib_event event; + + event.event = IB_EVENT_PKEY_CHANGE; + event.device = &dd->verbs_dev.rdi.ibdev; + event.element.port_num = port; + ib_dispatch_event(&event); +} + static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len) { struct ib_mad_send_buf *send_buf; @@ -1418,15 +1428,10 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys) } if (changed) { - struct ib_event event; - (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); - - event.event = IB_EVENT_PKEY_CHANGE; - event.device = &dd->verbs_dev.rdi.ibdev; - event.element.port_num = port; - ib_dispatch_event(&event); + hfi1_event_pkey_change(dd, port); } + return 0; } diff --git a/drivers/infiniband/hw/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h index 55ee08675333..8b734aaae88a 100644 --- a/drivers/infiniband/hw/hfi1/mad.h +++ b/drivers/infiniband/hw/hfi1/mad.h @@ -434,4 +434,6 @@ struct sc2vlnt { COUNTER_MASK(1, 3) | \ COUNTER_MASK(1, 4)) +void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port); + #endif /* _HFI1_MAD_H */ diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index d5edb1afbb8f..d4022450b73f 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -995,7 +995,7 @@ static void sc_wait_for_packet_egress(struct send_context *sc, int pause) /* counter is reset if occupancy count changes */ if (reg != reg_prev) loop = 0; - if (loop > 500) { + if (loop > 50000) { /* timed out - bounce the link */ dd_dev_err(dd, "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n", @@ -1797,6 +1797,21 @@ static void pio_map_rcu_callback(struct rcu_head *list) pio_map_free(m); } +/* + * Set credit return threshold for the kernel send context + */ +static void set_threshold(struct hfi1_devdata *dd, int scontext, int i) +{ + u32 thres; + + thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext], + 50), + sc_mtu_to_threshold(dd->kernel_send_context[scontext], + dd->vld[i].mtu, + dd->rcd[0]->rcvhdrqentsize)); + sc_set_cr_threshold(dd->kernel_send_context[scontext], thres); +} + /* * pio_map_init - called when #vls change * @dd: hfi1_devdata @@ -1872,11 +1887,16 @@ int pio_map_init(struct hfi1_devdata *dd, u8 port, u8 num_vls, u8 *vl_scontexts) if (!newmap->map[i]) goto bail; newmap->map[i]->mask = (1 << ilog2(sz)) - 1; - /* assign send contexts */ + /* + * assign send contexts and + * adjust credit return threshold + */ for (j = 0; j < sz; j++) { - if (dd->kernel_send_context[scontext]) + if (dd->kernel_send_context[scontext]) { newmap->map[i]->ksc[j] = dd->kernel_send_context[scontext]; + set_threshold(dd, scontext, i); + } if (++scontext >= first_scontext + vl_scontexts[i]) /* wrap back to first send context */ diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c index 2441669f0817..9fb561682c66 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.c +++ b/drivers/infiniband/hw/hfi1/qsfp.c @@ -579,7 +579,8 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len) if (ppd->qsfp_info.cache_valid) { if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS])) - sprintf(lenstr, "%dM ", cache[QSFP_MOD_LEN_OFFS]); + snprintf(lenstr, sizeof(lenstr), "%dM ", + cache[QSFP_MOD_LEN_OFFS]); power_byte = cache[QSFP_MOD_PWR_OFFS]; sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n", diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 1e503ad0bebb..be91f6fa1c87 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -678,8 +678,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) u32 tlen = packet->tlen; struct rvt_qp *qp = packet->qp; bool has_grh = rcv_flags & HFI1_HAS_GRH; - bool sc4_bit = has_sc4_bit(packet); - u8 sc; + u8 sc5 = hdr2sc((struct hfi1_message_header *)hdr, packet->rhf); u32 bth1; int is_mcast; struct ib_grh *grh = NULL; @@ -697,10 +696,8 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) */ struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); u32 lqpn = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK; - u8 sl, sc5; + u8 sl; - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; sl = ibp->sc_to_sl[sc5]; process_becn(ppd, sl, 0, lqpn, 0, IB_CC_SVCTYPE_UD); @@ -717,10 +714,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) if (!is_mcast && (opcode != IB_OPCODE_CNP) && bth1 & HFI1_FECN_SMASK) { u16 slid = be16_to_cpu(hdr->lrh[3]); - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; return_cnp(ibp, qp, src_qp, pkey, dlid, slid, sc5, grh); } @@ -745,10 +738,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) if (qp->ibqp.qp_num > 1) { struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); u16 slid; - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; slid = be16_to_cpu(hdr->lrh[3]); if (unlikely(rcv_pkey_check(ppd, pkey, sc5, slid))) { @@ -790,10 +779,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) /* Received on QP0, and so by definition, this is an SMP */ struct opa_smp *smp = (struct opa_smp *)data; u16 slid = be16_to_cpu(hdr->lrh[3]); - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; if (opa_smp_check(ibp, pkey, sc5, qp, slid, smp)) goto drop; @@ -890,9 +875,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) } wc.slid = be16_to_cpu(hdr->lrh[3]); - sc = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc |= sc4_bit; - wc.sl = ibp->sc_to_sl[sc]; + wc.sl = ibp->sc_to_sl[sc5]; /* * Save the LMC lower bits if the destination LID is a unicast LID. diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c index bc95c4112c61..d8fb056526f8 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.c +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c @@ -92,11 +92,10 @@ void hfi1_put_txreq(struct verbs_txreq *tx) struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, struct rvt_qp *qp) + __must_hold(&qp->s_lock) { struct verbs_txreq *tx = ERR_PTR(-EBUSY); - unsigned long flags; - spin_lock_irqsave(&qp->s_lock, flags); write_seqlock(&dev->iowait_lock); if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) { struct hfi1_qp_priv *priv; @@ -116,7 +115,6 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, } out: write_sequnlock(&dev->iowait_lock); - spin_unlock_irqrestore(&qp->s_lock, flags); return tx; } diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h index 1cf69b2fe4a5..a1d6e0807f97 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.h +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h @@ -73,6 +73,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev, struct rvt_qp *qp) + __must_hold(&qp->slock) { struct verbs_txreq *tx; struct hfi1_qp_priv *priv = qp->priv; diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index 8b9532034558..b738acdb9b02 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -113,6 +113,8 @@ #define IW_HMC_OBJ_TYPE_NUM ARRAY_SIZE(iw_hmc_obj_types) #define IW_CFG_FPM_QP_COUNT 32768 +#define I40IW_MAX_PAGES_PER_FMR 512 +#define I40IW_MIN_PAGES_PER_FMR 1 #define I40IW_MTU_TO_MSS 40 #define I40IW_DEFAULT_MSS 1460 diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index c963cad92f5a..6e9081380a27 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -600,8 +600,7 @@ static enum i40iw_status_code i40iw_create_cqp(struct i40iw_device *iwdev) cqp_init_info.scratch_array = cqp->scratch_array; status = dev->cqp_ops->cqp_init(dev->cqp, &cqp_init_info); if (status) { - i40iw_pr_err("cqp init status %d maj_err %d min_err %d\n", - status, maj_err, min_err); + i40iw_pr_err("cqp init status %d\n", status); goto exit; } status = dev->cqp_ops->cqp_create(dev->cqp, true, &maj_err, &min_err); diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 02a735b64208..283b64c942ee 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -79,6 +79,7 @@ static int i40iw_query_device(struct ib_device *ibdev, props->max_qp_init_rd_atom = props->max_qp_rd_atom; props->atomic_cap = IB_ATOMIC_NONE; props->max_map_per_fmr = 1; + props->max_fast_reg_page_list_len = I40IW_MAX_PAGES_PER_FMR; return 0; } @@ -1473,6 +1474,7 @@ static int i40iw_hw_alloc_stag(struct i40iw_device *iwdev, struct i40iw_mr *iwmr info->stag_idx = iwmr->stag >> I40IW_CQPSQ_STAG_IDX_SHIFT; info->pd_id = iwpd->sc_pd.pd_id; info->total_len = iwmr->length; + info->remote_access = true; cqp_info->cqp_cmd = OP_ALLOC_STAG; cqp_info->post_sq = 1; cqp_info->in.u.alloc_stag.dev = &iwdev->sc_dev; @@ -1527,7 +1529,7 @@ static struct ib_mr *i40iw_alloc_mr(struct ib_pd *pd, mutex_lock(&iwdev->pbl_mutex); status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt); mutex_unlock(&iwdev->pbl_mutex); - if (!status) + if (status) goto err1; if (palloc->level != I40IW_LEVEL_1) @@ -2149,6 +2151,7 @@ static int i40iw_post_send(struct ib_qp *ibqp, struct i40iw_sc_dev *dev = &iwqp->iwdev->sc_dev; struct i40iw_fast_reg_stag_info info; + memset(&info, 0, sizeof(info)); info.access_rights = I40IW_ACCESS_FLAGS_LOCALREAD; info.access_rights |= i40iw_get_user_access(flags); info.stag_key = reg_wr(ib_wr)->key & 0xff; @@ -2158,10 +2161,14 @@ static int i40iw_post_send(struct ib_qp *ibqp, info.addr_type = I40IW_ADDR_TYPE_VA_BASED; info.va = (void *)(uintptr_t)iwmr->ibmr.iova; info.total_len = iwmr->ibmr.length; + info.reg_addr_pa = *(u64 *)palloc->level1.addr; info.first_pm_pbl_index = palloc->level1.idx; info.local_fence = ib_wr->send_flags & IB_SEND_FENCE; info.signaled = ib_wr->send_flags & IB_SEND_SIGNALED; + if (iwmr->npages > I40IW_MIN_PAGES_PER_FMR) + info.chunk_size = 1; + if (page_shift == 21) info.page_size = 1; /* 2M page */ @@ -2327,13 +2334,16 @@ static int i40iw_req_notify_cq(struct ib_cq *ibcq, { struct i40iw_cq *iwcq; struct i40iw_cq_uk *ukcq; - enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_SOLICITED; + unsigned long flags; + enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_EVENT; iwcq = (struct i40iw_cq *)ibcq; ukcq = &iwcq->sc_cq.cq_uk; - if (notify_flags == IB_CQ_NEXT_COMP) - cq_notify = IW_CQ_COMPL_EVENT; + if (notify_flags == IB_CQ_SOLICITED) + cq_notify = IW_CQ_COMPL_SOLICITED; + spin_lock_irqsave(&iwcq->lock, flags); ukcq->ops.iw_cq_request_notification(ukcq, cq_notify); + spin_unlock_irqrestore(&iwcq->lock, flags); return 0; } diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 105246fba2e7..5fc623362731 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -47,6 +47,7 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr, ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24)); ah->av.ib.g_slid = ah_attr->src_path_bits; + ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28); if (ah_attr->ah_flags & IB_AH_GRH) { ah->av.ib.g_slid |= 0x80; ah->av.ib.gid_index = ah_attr->grh.sgid_index; @@ -64,7 +65,6 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr, !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support)) --ah->av.ib.stat_rate; } - ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28); return &ah->ibah; } diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index d68f506c1922..9c2e53d28f98 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -527,7 +527,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1); spin_unlock(&tun_qp->tx_lock); if (ret) - goto out; + goto end; tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr); if (tun_qp->tx_ring[tun_tx_ix].ah) @@ -596,9 +596,15 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, wr.wr.send_flags = IB_SEND_SIGNALED; ret = ib_post_send(src_qp, &wr.wr, &bad_wr); -out: - if (ret) - ib_destroy_ah(ah); + if (!ret) + return 0; + out: + spin_lock(&tun_qp->tx_lock); + tun_qp->tx_ix_tail++; + spin_unlock(&tun_qp->tx_lock); + tun_qp->tx_ring[tun_tx_ix].ah = NULL; +end: + ib_destroy_ah(ah); return ret; } @@ -1326,9 +1332,15 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port, ret = ib_post_send(send_qp, &wr.wr, &bad_wr); + if (!ret) + return 0; + + spin_lock(&sqp->tx_lock); + sqp->tx_ix_tail++; + spin_unlock(&sqp->tx_lock); + sqp->tx_ring[wire_tx_ix].ah = NULL; out: - if (ret) - ib_destroy_ah(ah); + ib_destroy_ah(ah); return ret; } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 0eb09e104542..42a46078d7d5 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1704,6 +1704,9 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct mlx4_dev *dev = (to_mdev(qp->device))->dev; int is_bonded = mlx4_is_bonded(dev); + if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt) + return ERR_PTR(-EINVAL); + if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) && (flow_attr->type != IB_FLOW_ATTR_NORMAL)) return ERR_PTR(-EOPNOTSUPP); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 6c5ac5d8f32f..29acda249612 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -139,7 +139,7 @@ struct mlx4_ib_mr { u32 max_pages; struct mlx4_mr mmr; struct ib_umem *umem; - void *pages_alloc; + size_t page_map_size; }; struct mlx4_ib_mw { diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 631272172a0b..5d73989d9771 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -277,20 +277,23 @@ mlx4_alloc_priv_pages(struct ib_device *device, struct mlx4_ib_mr *mr, int max_pages) { - int size = max_pages * sizeof(u64); - int add_size; int ret; - add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0); + /* Ensure that size is aligned to DMA cacheline + * requirements. + * max_pages is limited to MLX4_MAX_FAST_REG_PAGES + * so page_map_size will never cross PAGE_SIZE. + */ + mr->page_map_size = roundup(max_pages * sizeof(u64), + MLX4_MR_PAGES_ALIGN); - mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL); - if (!mr->pages_alloc) + /* Prevent cross page boundary allocation. */ + mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL); + if (!mr->pages) return -ENOMEM; - mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN); - mr->page_map = dma_map_single(device->dma_device, mr->pages, - size, DMA_TO_DEVICE); + mr->page_map_size, DMA_TO_DEVICE); if (dma_mapping_error(device->dma_device, mr->page_map)) { ret = -ENOMEM; @@ -298,9 +301,9 @@ mlx4_alloc_priv_pages(struct ib_device *device, } return 0; -err: - kfree(mr->pages_alloc); +err: + free_page((unsigned long)mr->pages); return ret; } @@ -309,11 +312,10 @@ mlx4_free_priv_pages(struct mlx4_ib_mr *mr) { if (mr->pages) { struct ib_device *device = mr->ibmr.device; - int size = mr->max_pages * sizeof(u64); dma_unmap_single(device->dma_device, mr->page_map, - size, DMA_TO_DEVICE); - kfree(mr->pages_alloc); + mr->page_map_size, DMA_TO_DEVICE); + free_page((unsigned long)mr->pages); mr->pages = NULL; } } @@ -537,14 +539,12 @@ int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, mr->npages = 0; ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map, - sizeof(u64) * mr->max_pages, - DMA_TO_DEVICE); + mr->page_map_size, DMA_TO_DEVICE); rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page); ib_dma_sync_single_for_device(ibmr->device, mr->page_map, - sizeof(u64) * mr->max_pages, - DMA_TO_DEVICE); + mr->page_map_size, DMA_TO_DEVICE); return rc; } diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 81b0e1fbec1d..8db8405c1e99 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -362,7 +362,7 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags) sizeof (struct mlx4_wqe_raddr_seg); case MLX4_IB_QPT_RC: return sizeof (struct mlx4_wqe_ctrl_seg) + - sizeof (struct mlx4_wqe_atomic_seg) + + sizeof (struct mlx4_wqe_masked_atomic_seg) + sizeof (struct mlx4_wqe_raddr_seg); case MLX4_IB_QPT_SMI: case MLX4_IB_QPT_GSI: @@ -1191,8 +1191,10 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, { err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata, 0, &qp, gfp); - if (err) + if (err) { + kfree(qp); return ERR_PTR(err); + } qp->ibqp.qp_num = qp->mqp.qpn; qp->xrcdn = xrcdn; diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 1534af113058..364aab9f3c9e 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -121,7 +121,7 @@ static void pma_cnt_ext_assign(struct ib_pma_portcounters_ext *pma_cnt_ext, pma_cnt_ext->port_xmit_data = cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.octets, transmitted_ib_multicast.octets) >> 2); - pma_cnt_ext->port_xmit_data = + pma_cnt_ext->port_rcv_data = cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.octets, received_ib_multicast.octets) >> 2); pma_cnt_ext->port_xmit_packets = diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index ce434228a5ea..ce0a7ab35a22 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -3332,10 +3332,11 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr) return MLX5_FENCE_MODE_SMALL_AND_FENCE; else return fence; - - } else { - return 0; + } else if (unlikely(wr->send_flags & IB_SEND_FENCE)) { + return MLX5_FENCE_MODE_FENCE; } + + return 0; } static int begin_wqe(struct mlx5_ib_qp *qp, void **seg, diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index ff946d5f59e4..382466a90da7 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -2178,6 +2178,11 @@ static ssize_t qib_write(struct file *fp, const char __user *data, switch (cmd.type) { case QIB_CMD_ASSIGN_CTXT: + if (rcd) { + ret = -EINVAL; + goto bail; + } + ret = qib_assign_ctxt(fp, &cmd.cmd.user_info); if (ret) goto bail; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 7de5134bec85..41ba7e9cadaa 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -369,8 +369,8 @@ static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt, /* wrap to first map page, invert bit 0 */ offset = qpt->incr | ((offset & 1) ^ 1); } - /* there can be no bits at shift and below */ - WARN_ON(offset & (rdi->dparms.qos_shift - 1)); + /* there can be no set bits in low-order QoS bits */ + WARN_ON(offset & (BIT(rdi->dparms.qos_shift) - 1)); qpn = mk_qpn(qpt, map, offset); } @@ -576,12 +576,6 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, qp->s_ssn = 1; qp->s_lsn = 0; qp->s_mig_state = IB_MIG_MIGRATED; - if (qp->s_ack_queue) - memset( - qp->s_ack_queue, - 0, - rvt_max_atomic(rdi) * - sizeof(*qp->s_ack_queue)); qp->r_head_ack_queue = 0; qp->s_tail_ack_queue = 0; qp->s_num_rd_atomic = 0; @@ -705,8 +699,10 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, * initialization that is needed. */ priv = rdi->driver_f.qp_priv_alloc(rdi, qp, gfp); - if (!priv) + if (IS_ERR(priv)) { + ret = priv; goto bail_qp; + } qp->priv = priv; qp->timeout_jiffies = usecs_to_jiffies((4096UL * (1UL << qp->timeout)) / diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index e1cc2cc42f25..30c4fda7a05a 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -501,9 +501,7 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb) !rdi->driver_f.quiesce_qp || !rdi->driver_f.notify_error_qp || !rdi->driver_f.mtu_from_qp || - !rdi->driver_f.mtu_to_path_mtu || - !rdi->driver_f.shut_down_port || - !rdi->driver_f.cap_mask_chg) + !rdi->driver_f.mtu_to_path_mtu) return -EINVAL; break; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index e68b20cba70b..4a4155640d51 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1638,8 +1638,7 @@ retry: */ qp_init->cap.max_send_wr = srp_sq_size / 2; qp_init->cap.max_rdma_ctxs = srp_sq_size / 2; - qp_init->cap.max_send_sge = max(sdev->device->attrs.max_sge_rd, - sdev->device->attrs.max_sge); + qp_init->cap.max_send_sge = SRPT_DEF_SG_PER_WQE; qp_init->port_num = ch->sport->port; ch->qp = ib_create_qp(sdev->pd, qp_init); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h index fee6bfd7ca21..389030487da7 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.h +++ b/drivers/infiniband/ulp/srpt/ib_srpt.h @@ -106,6 +106,7 @@ enum { SRP_LOGIN_RSP_MULTICHAN_MAINTAINED = 0x2, SRPT_DEF_SG_TABLESIZE = 128, + SRPT_DEF_SG_PER_WQE = 16, MIN_SRPT_SQ_SIZE = 16, DEF_SRPT_SQ_SIZE = 4096, diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 804dbcc37d3f..a529a4535457 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1031,17 +1031,17 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect case XTYPE_XBOXONE: packet->data[0] = 0x09; /* activate rumble */ - packet->data[1] = 0x08; + packet->data[1] = 0x00; packet->data[2] = xpad->odata_serial++; - packet->data[3] = 0x08; /* continuous effect */ - packet->data[4] = 0x00; /* simple rumble mode */ - packet->data[5] = 0x03; /* L and R actuator only */ - packet->data[6] = 0x00; /* TODO: LT actuator */ - packet->data[7] = 0x00; /* TODO: RT actuator */ + packet->data[3] = 0x09; + packet->data[4] = 0x00; + packet->data[5] = 0x0F; + packet->data[6] = 0x00; + packet->data[7] = 0x00; packet->data[8] = strong / 512; /* left actuator */ packet->data[9] = weak / 512; /* right actuator */ - packet->data[10] = 0x80; /* length of pulse */ - packet->data[11] = 0x00; /* stop period of pulse */ + packet->data[10] = 0xFF; + packet->data[11] = 0x00; packet->data[12] = 0x00; packet->len = 13; packet->pending = true; @@ -1431,22 +1431,15 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id int ep_irq_in_idx; int i, error; + if (intf->cur_altsetting->desc.bNumEndpoints != 2) + return -ENODEV; + for (i = 0; xpad_device[i].idVendor; i++) { if ((le16_to_cpu(udev->descriptor.idVendor) == xpad_device[i].idVendor) && (le16_to_cpu(udev->descriptor.idProduct) == xpad_device[i].idProduct)) break; } - if (xpad_device[i].xtype == XTYPE_XBOXONE && - intf->cur_altsetting->desc.bInterfaceNumber != 0) { - /* - * The Xbox One controller lists three interfaces all with the - * same interface class, subclass and protocol. Differentiate by - * interface number. - */ - return -ENODEV; - } - xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL); if (!xpad) return -ENOMEM; @@ -1478,6 +1471,8 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) { if (intf->cur_altsetting->desc.bInterfaceProtocol == 129) xpad->xtype = XTYPE_XBOX360W; + else if (intf->cur_altsetting->desc.bInterfaceProtocol == 208) + xpad->xtype = XTYPE_XBOXONE; else xpad->xtype = XTYPE_XBOX360; } else { @@ -1492,6 +1487,17 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id xpad->mapping |= MAP_STICKS_TO_NULL; } + if (xpad->xtype == XTYPE_XBOXONE && + intf->cur_altsetting->desc.bInterfaceNumber != 0) { + /* + * The Xbox One controller lists three interfaces all with the + * same interface class, subclass and protocol. Differentiate by + * interface number. + */ + error = -ENODEV; + goto err_free_in_urb; + } + error = xpad_init_output(intf, xpad); if (error) goto err_free_in_urb; diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 78f93cf68840..be5b399da5d3 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1568,13 +1568,7 @@ static int elantech_set_properties(struct elantech_data *etd) case 5: etd->hw_version = 3; break; - case 6: - case 7: - case 8: - case 9: - case 10: - case 13: - case 14: + case 6 ... 14: etd->hw_version = 4; break; default: diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c index a3f0f5a47490..0f586780ceb4 100644 --- a/drivers/input/mouse/vmmouse.c +++ b/drivers/input/mouse/vmmouse.c @@ -355,18 +355,11 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties) return -ENXIO; } - if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) { - psmouse_dbg(psmouse, "VMMouse port in use.\n"); - return -EBUSY; - } - /* Check if the device is present */ response = ~VMMOUSE_PROTO_MAGIC; VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2); - if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) { - release_region(VMMOUSE_PROTO_PORT, 4); + if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) return -ENXIO; - } if (set_properties) { psmouse->vendor = VMMOUSE_VENDOR; @@ -374,8 +367,6 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties) psmouse->model = version; } - release_region(VMMOUSE_PROTO_PORT, 4); - return 0; } @@ -394,7 +385,6 @@ static void vmmouse_disconnect(struct psmouse *psmouse) psmouse_reset(psmouse); input_unregister_device(priv->abs_dev); kfree(priv); - release_region(VMMOUSE_PROTO_PORT, 4); } /** @@ -438,15 +428,10 @@ int vmmouse_init(struct psmouse *psmouse) struct input_dev *rel_dev = psmouse->dev, *abs_dev; int error; - if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) { - psmouse_dbg(psmouse, "VMMouse port in use.\n"); - return -EBUSY; - } - psmouse_reset(psmouse); error = vmmouse_enable(psmouse); if (error) - goto release_region; + return error; priv = kzalloc(sizeof(*priv), GFP_KERNEL); abs_dev = input_allocate_device(); @@ -502,8 +487,5 @@ init_fail: kfree(priv); psmouse->private = NULL; -release_region: - release_region(VMMOUSE_PROTO_PORT, 4); - return error; } diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c index b368b0515c5a..253df96be427 100644 --- a/drivers/input/rmi4/rmi_bus.c +++ b/drivers/input/rmi4/rmi_bus.c @@ -157,11 +157,11 @@ static int rmi_function_match(struct device *dev, struct device_driver *drv) static void rmi_function_of_probe(struct rmi_function *fn) { char of_name[9]; + struct device_node *node = fn->rmi_dev->xport->dev->of_node; snprintf(of_name, sizeof(of_name), "rmi4-f%02x", fn->fd.function_number); - fn->dev.of_node = of_find_node_by_name( - fn->rmi_dev->xport->dev->of_node, of_name); + fn->dev.of_node = of_get_child_by_name(node, of_name); } #else static inline void rmi_function_of_probe(struct rmi_function *fn) diff --git a/drivers/input/rmi4/rmi_f12.c b/drivers/input/rmi4/rmi_f12.c index 8dd3fb5e1f94..88e91559c84e 100644 --- a/drivers/input/rmi4/rmi_f12.c +++ b/drivers/input/rmi4/rmi_f12.c @@ -66,7 +66,7 @@ static int rmi_f12_read_sensor_tuning(struct f12_data *f12) struct rmi_device *rmi_dev = fn->rmi_dev; int ret; int offset; - u8 buf[14]; + u8 buf[15]; int pitch_x = 0; int pitch_y = 0; int clip_x_low = 0; @@ -86,9 +86,10 @@ static int rmi_f12_read_sensor_tuning(struct f12_data *f12) offset = rmi_register_desc_calc_reg_offset(&f12->control_reg_desc, 8); - if (item->reg_size > 14) { - dev_err(&fn->dev, "F12 control8 should be 14 bytes, not: %ld\n", - item->reg_size); + if (item->reg_size > sizeof(buf)) { + dev_err(&fn->dev, + "F12 control8 should be no bigger than %zd bytes, not: %ld\n", + sizeof(buf), item->reg_size); return -ENODEV; } diff --git a/drivers/input/touchscreen/ts4800-ts.c b/drivers/input/touchscreen/ts4800-ts.c index 3c3dd78303be..fed73eeb47b3 100644 --- a/drivers/input/touchscreen/ts4800-ts.c +++ b/drivers/input/touchscreen/ts4800-ts.c @@ -118,6 +118,13 @@ static int ts4800_parse_dt(struct platform_device *pdev, return -ENODEV; } + ts->regmap = syscon_node_to_regmap(syscon_np); + of_node_put(syscon_np); + if (IS_ERR(ts->regmap)) { + dev_err(dev, "cannot get parent's regmap\n"); + return PTR_ERR(ts->regmap); + } + error = of_property_read_u32_index(np, "syscon", 1, ®); if (error < 0) { dev_err(dev, "no offset in syscon\n"); @@ -134,12 +141,6 @@ static int ts4800_parse_dt(struct platform_device *pdev, ts->bit = BIT(bit); - ts->regmap = syscon_node_to_regmap(syscon_np); - if (IS_ERR(ts->regmap)) { - dev_err(dev, "cannot get parent's regmap\n"); - return PTR_ERR(ts->regmap); - } - return 0; } diff --git a/drivers/input/touchscreen/tsc2004.c b/drivers/input/touchscreen/tsc2004.c index 7295c198aa08..6fe55d598fac 100644 --- a/drivers/input/touchscreen/tsc2004.c +++ b/drivers/input/touchscreen/tsc2004.c @@ -22,6 +22,11 @@ #include #include "tsc200x-core.h" +static const struct input_id tsc2004_input_id = { + .bustype = BUS_I2C, + .product = 2004, +}; + static int tsc2004_cmd(struct device *dev, u8 cmd) { u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd; @@ -42,7 +47,7 @@ static int tsc2004_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { - return tsc200x_probe(&i2c->dev, i2c->irq, BUS_I2C, + return tsc200x_probe(&i2c->dev, i2c->irq, &tsc2004_input_id, devm_regmap_init_i2c(i2c, &tsc200x_regmap_config), tsc2004_cmd); } diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c index b9f593dfd2ef..f2c5f0e47f77 100644 --- a/drivers/input/touchscreen/tsc2005.c +++ b/drivers/input/touchscreen/tsc2005.c @@ -24,6 +24,11 @@ #include #include "tsc200x-core.h" +static const struct input_id tsc2005_input_id = { + .bustype = BUS_SPI, + .product = 2005, +}; + static int tsc2005_cmd(struct device *dev, u8 cmd) { u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd; @@ -62,7 +67,7 @@ static int tsc2005_probe(struct spi_device *spi) if (error) return error; - return tsc200x_probe(&spi->dev, spi->irq, BUS_SPI, + return tsc200x_probe(&spi->dev, spi->irq, &tsc2005_input_id, devm_regmap_init_spi(spi, &tsc200x_regmap_config), tsc2005_cmd); } diff --git a/drivers/input/touchscreen/tsc200x-core.c b/drivers/input/touchscreen/tsc200x-core.c index 15240c1ee850..dfa7f1c4f545 100644 --- a/drivers/input/touchscreen/tsc200x-core.c +++ b/drivers/input/touchscreen/tsc200x-core.c @@ -450,7 +450,7 @@ static void tsc200x_close(struct input_dev *input) mutex_unlock(&ts->mutex); } -int tsc200x_probe(struct device *dev, int irq, __u16 bustype, +int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, struct regmap *regmap, int (*tsc200x_cmd)(struct device *dev, u8 cmd)) { @@ -547,9 +547,18 @@ int tsc200x_probe(struct device *dev, int irq, __u16 bustype, snprintf(ts->phys, sizeof(ts->phys), "%s/input-ts", dev_name(dev)); - input_dev->name = "TSC200X touchscreen"; + if (tsc_id->product == 2004) { + input_dev->name = "TSC200X touchscreen"; + } else { + input_dev->name = devm_kasprintf(dev, GFP_KERNEL, + "TSC%04d touchscreen", + tsc_id->product); + if (!input_dev->name) + return -ENOMEM; + } + input_dev->phys = ts->phys; - input_dev->id.bustype = bustype; + input_dev->id = *tsc_id; input_dev->dev.parent = dev; input_dev->evbit[0] = BIT(EV_ABS) | BIT(EV_KEY); input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH); diff --git a/drivers/input/touchscreen/tsc200x-core.h b/drivers/input/touchscreen/tsc200x-core.h index 7a482d102614..49a63a3c6840 100644 --- a/drivers/input/touchscreen/tsc200x-core.h +++ b/drivers/input/touchscreen/tsc200x-core.h @@ -70,7 +70,7 @@ extern const struct regmap_config tsc200x_regmap_config; extern const struct dev_pm_ops tsc200x_pm_ops; -int tsc200x_probe(struct device *dev, int irq, __u16 bustype, +int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, struct regmap *regmap, int (*tsc200x_cmd)(struct device *dev, u8 cmd)); int tsc200x_remove(struct device *dev); diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c index bab3c6acf6a2..b6fc4bde79de 100644 --- a/drivers/input/touchscreen/wacom_w8001.c +++ b/drivers/input/touchscreen/wacom_w8001.c @@ -27,7 +27,7 @@ MODULE_AUTHOR("Jaya Kumar "); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); -#define W8001_MAX_LENGTH 11 +#define W8001_MAX_LENGTH 13 #define W8001_LEAD_MASK 0x80 #define W8001_LEAD_BYTE 0x80 #define W8001_TAB_MASK 0x40 @@ -155,6 +155,7 @@ static void parse_multi_touch(struct w8001 *w8001) bool touch = data[0] & (1 << i); input_mt_slot(dev, i); + input_mt_report_slot_state(dev, MT_TOOL_FINGER, touch); if (touch) { x = (data[6 * i + 1] << 7) | data[6 * i + 2]; y = (data[6 * i + 3] << 7) | data[6 * i + 4]; @@ -339,6 +340,15 @@ static irqreturn_t w8001_interrupt(struct serio *serio, w8001->idx = 0; parse_multi_touch(w8001); break; + + default: + /* + * ThinkPad X60 Tablet PC (pen only device) sometimes + * sends invalid data packets that are larger than + * W8001_PKTLEN_TPCPEN. Let's start over again. + */ + if (!w8001->touch_dev && w8001->idx > W8001_PKTLEN_TPCPEN - 1) + w8001->idx = 0; } return IRQ_HANDLED; @@ -513,6 +523,8 @@ static int w8001_setup_touch(struct w8001 *w8001, char *basename, 0, touch.x, 0, 0); input_set_abs_params(dev, ABS_MT_POSITION_Y, 0, touch.y, 0, 0); + input_set_abs_params(dev, ABS_MT_TOOL_TYPE, + 0, MT_TOOL_MAX, 0, 0); strlcat(basename, " 2FG", basename_sz); if (w8001->max_pen_x && w8001->max_pen_y) diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 9e0034196e10..59741ead7e15 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1107,13 +1107,13 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, break; } + devid = e->devid; DUMP_printk(" DEV_ACPI_HID(%s[%s])\t\tdevid: %02x:%02x.%x\n", hid, uid, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid)); - devid = e->devid; flags = e->flags; ret = add_acpi_hid_device(hid, uid, &devid, false); @@ -1568,13 +1568,23 @@ static int __init amd_iommu_init_pci(void) break; } + /* + * Order is important here to make sure any unity map requirements are + * fulfilled. The unity mappings are created and written to the device + * table during the amd_iommu_init_api() call. + * + * After that we call init_device_table_dma() to make sure any + * uninitialized DTE will block DMA, and in the end we flush the caches + * of all IOMMUs to make sure the changes to the device table are + * active. + */ + ret = amd_iommu_init_api(); + init_device_table_dma(); for_each_iommu(iommu) iommu_flush_all_caches(iommu); - ret = amd_iommu_init_api(); - if (!ret) print_iommu_info(); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 94b68213c50d..5f6b3bcab078 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1941,6 +1941,7 @@ static struct iommu_ops arm_smmu_ops = { .attach_dev = arm_smmu_attach_dev, .map = arm_smmu_map, .unmap = arm_smmu_unmap, + .map_sg = default_iommu_map_sg, .iova_to_phys = arm_smmu_iova_to_phys, .add_device = arm_smmu_add_device, .remove_device = arm_smmu_remove_device, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a644d0cec2d8..323dac9900ba 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3222,11 +3222,6 @@ static int __init init_dmars(void) } } - iommu_flush_write_buffer(iommu); - iommu_set_root_entry(iommu); - iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); - iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); - if (!ecap_pass_through(iommu->ecap)) hw_pass_through = 0; #ifdef CONFIG_INTEL_IOMMU_SVM @@ -3235,6 +3230,18 @@ static int __init init_dmars(void) #endif } + /* + * Now that qi is enabled on all iommus, set the root entry and flush + * caches. This is required on some Intel X58 chipsets, otherwise the + * flush_context function will loop forever and the boot hangs. + */ + for_each_active_iommu(iommu, drhd) { + iommu_flush_write_buffer(iommu); + iommu_set_root_entry(iommu); + iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); + iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); + } + if (iommu_pass_through) iommu_identity_mapping |= IDENTMAP_ALL; @@ -4595,13 +4602,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu) for (i = 0; i < g_num_of_iommus; i++) { struct intel_iommu *iommu = g_iommus[i]; struct dmar_domain *domain; - u16 did; + int did; if (!iommu) continue; - for (did = 0; did < 0xffff; did++) { - domain = get_iommu_domain(iommu, did); + for (did = 0; did < cap_ndoms(iommu->cap); did++) { + domain = get_iommu_domain(iommu, (u16)did); if (!domain) continue; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index ba764a0835d3..e23001bfcfee 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -420,8 +420,10 @@ retry: /* Try replenishing IOVAs by flushing rcache. */ flushed_rcache = true; + preempt_disable(); for_each_online_cpu(cpu) free_cpu_cached_iovas(cpu, iovad); + preempt_enable(); goto retry; } @@ -749,7 +751,7 @@ static bool __iova_rcache_insert(struct iova_domain *iovad, bool can_insert = false; unsigned long flags; - cpu_rcache = this_cpu_ptr(rcache->cpu_rcaches); + cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches); spin_lock_irqsave(&cpu_rcache->lock, flags); if (!iova_magazine_full(cpu_rcache->loaded)) { @@ -779,6 +781,7 @@ static bool __iova_rcache_insert(struct iova_domain *iovad, iova_magazine_push(cpu_rcache->loaded, iova_pfn); spin_unlock_irqrestore(&cpu_rcache->lock, flags); + put_cpu_ptr(rcache->cpu_rcaches); if (mag_to_free) { iova_magazine_free_pfns(mag_to_free, iovad); @@ -812,7 +815,7 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache, bool has_pfn = false; unsigned long flags; - cpu_rcache = this_cpu_ptr(rcache->cpu_rcaches); + cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches); spin_lock_irqsave(&cpu_rcache->lock, flags); if (!iova_magazine_empty(cpu_rcache->loaded)) { @@ -834,6 +837,7 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache, iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn); spin_unlock_irqrestore(&cpu_rcache->lock, flags); + put_cpu_ptr(rcache->cpu_rcaches); return iova_pfn; } diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index c7d6156ff536..25b4627cb57f 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -815,7 +815,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, dte_addr = virt_to_phys(rk_domain->dt); for (i = 0; i < iommu->num_mmu; i++) { rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, dte_addr); - rk_iommu_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE); + rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE); rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK); } diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 3b5e10aa48ab..70ed1d0151b8 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -718,7 +718,7 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, spin_lock_irqsave(&gic_lock, flags); gic_map_to_pin(intr, gic_cpu_pin); - gic_map_to_vpe(intr, vpe); + gic_map_to_vpe(intr, mips_cm_vp_id(vpe)); for (i = 0; i < min(gic_vpes, NR_CPUS); i++) clear_bit(intr, pcpu_masks[i].pcpu_mask); set_bit(intr, pcpu_masks[vpe].pcpu_mask); @@ -746,6 +746,12 @@ static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq, /* verify that it doesn't conflict with an IPI irq */ if (test_bit(spec->hwirq, ipi_resrv)) return -EBUSY; + + hwirq = GIC_SHARED_TO_HWIRQ(spec->hwirq); + + return irq_domain_set_hwirq_and_chip(d, virq, hwirq, + &gic_level_irq_controller, + NULL); } else { base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs); if (base_hwirq == gic_shared_intrs) { @@ -867,10 +873,14 @@ static int gic_dev_domain_alloc(struct irq_domain *d, unsigned int virq, &gic_level_irq_controller, NULL); if (ret) - return ret; + goto error; } return 0; + +error: + irq_domain_free_irqs_parent(d, virq, nr_irqs); + return ret; } void gic_dev_domain_free(struct irq_domain *d, unsigned int virq, @@ -949,7 +959,7 @@ int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node, switch (bus_token) { case DOMAIN_BUS_IPI: is_ipi = d->bus_token == bus_token; - return to_of_node(d->fwnode) == node && is_ipi; + return (!node || to_of_node(d->fwnode) == node) && is_ipi; break; default: return 0; diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index 3495d5d6547f..3bce44893021 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -53,11 +53,12 @@ static void led_timer_function(unsigned long data) if (!led_cdev->blink_delay_on || !led_cdev->blink_delay_off) { led_set_brightness_nosleep(led_cdev, LED_OFF); + led_cdev->flags &= ~LED_BLINK_SW; return; } if (led_cdev->flags & LED_BLINK_ONESHOT_STOP) { - led_cdev->flags &= ~LED_BLINK_ONESHOT_STOP; + led_cdev->flags &= ~(LED_BLINK_ONESHOT_STOP | LED_BLINK_SW); return; } @@ -151,6 +152,7 @@ static void led_set_software_blink(struct led_classdev *led_cdev, return; } + led_cdev->flags |= LED_BLINK_SW; mod_timer(&led_cdev->blink_timer, jiffies + 1); } @@ -219,6 +221,7 @@ void led_stop_software_blink(struct led_classdev *led_cdev) del_timer_sync(&led_cdev->blink_timer); led_cdev->blink_delay_on = 0; led_cdev->blink_delay_off = 0; + led_cdev->flags &= ~LED_BLINK_SW; } EXPORT_SYMBOL_GPL(led_stop_software_blink); @@ -226,10 +229,10 @@ void led_set_brightness(struct led_classdev *led_cdev, enum led_brightness brightness) { /* - * In case blinking is on delay brightness setting + * If software blink is active, delay brightness setting * until the next timer tick. */ - if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) { + if (led_cdev->flags & LED_BLINK_SW) { /* * If we need to disable soft blinking delegate this to the * work queue task to avoid problems in case we are called diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c index 410c39c62dc7..c9f386213e9e 100644 --- a/drivers/leds/trigger/ledtrig-heartbeat.c +++ b/drivers/leds/trigger/ledtrig-heartbeat.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "../leds.h" static int panic_heartbeats; @@ -154,6 +155,30 @@ static struct led_trigger heartbeat_led_trigger = { .deactivate = heartbeat_trig_deactivate, }; +static int heartbeat_pm_notifier(struct notifier_block *nb, + unsigned long pm_event, void *unused) +{ + int rc; + + switch (pm_event) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + case PM_RESTORE_PREPARE: + led_trigger_unregister(&heartbeat_led_trigger); + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + case PM_POST_RESTORE: + rc = led_trigger_register(&heartbeat_led_trigger); + if (rc) + pr_err("could not re-register heartbeat trigger\n"); + break; + default: + break; + } + return NOTIFY_DONE; +} + static int heartbeat_reboot_notifier(struct notifier_block *nb, unsigned long code, void *unused) { @@ -168,6 +193,10 @@ static int heartbeat_panic_notifier(struct notifier_block *nb, return NOTIFY_DONE; } +static struct notifier_block heartbeat_pm_nb = { + .notifier_call = heartbeat_pm_notifier, +}; + static struct notifier_block heartbeat_reboot_nb = { .notifier_call = heartbeat_reboot_notifier, }; @@ -184,12 +213,14 @@ static int __init heartbeat_trig_init(void) atomic_notifier_chain_register(&panic_notifier_list, &heartbeat_panic_nb); register_reboot_notifier(&heartbeat_reboot_nb); + register_pm_notifier(&heartbeat_pm_nb); } return rc; } static void __exit heartbeat_trig_exit(void) { + unregister_pm_notifier(&heartbeat_pm_nb); unregister_reboot_notifier(&heartbeat_reboot_nb); atomic_notifier_chain_unregister(&panic_notifier_list, &heartbeat_panic_nb); diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index b73c6e7d28e4..6f2c8522e14a 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -61,21 +61,36 @@ static int mcb_probe(struct device *dev) struct mcb_driver *mdrv = to_mcb_driver(dev->driver); struct mcb_device *mdev = to_mcb_device(dev); const struct mcb_device_id *found_id; + struct module *carrier_mod; + int ret; found_id = mcb_match_id(mdrv->id_table, mdev); if (!found_id) return -ENODEV; - return mdrv->probe(mdev, found_id); + carrier_mod = mdev->dev.parent->driver->owner; + if (!try_module_get(carrier_mod)) + return -EINVAL; + + get_device(dev); + ret = mdrv->probe(mdev, found_id); + if (ret) + module_put(carrier_mod); + + return ret; } static int mcb_remove(struct device *dev) { struct mcb_driver *mdrv = to_mcb_driver(dev->driver); struct mcb_device *mdev = to_mcb_device(dev); + struct module *carrier_mod; mdrv->remove(mdev); + carrier_mod = mdev->dev.parent->driver->owner; + module_put(carrier_mod); + put_device(&mdev->dev); return 0; diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index beb2841ceae5..3f1ab4986cfc 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -779,11 +779,31 @@ static const struct v4l2_dv_timings_cap adv76xx_timings_cap_digital = { V4L2_DV_BT_CAP_CUSTOM) }; -static inline const struct v4l2_dv_timings_cap * -adv76xx_get_dv_timings_cap(struct v4l2_subdev *sd) +/* + * Return the DV timings capabilities for the requested sink pad. As a special + * case, pad value -1 returns the capabilities for the currently selected input. + */ +static const struct v4l2_dv_timings_cap * +adv76xx_get_dv_timings_cap(struct v4l2_subdev *sd, int pad) { - return is_digital_input(sd) ? &adv76xx_timings_cap_digital : - &adv7604_timings_cap_analog; + if (pad == -1) { + struct adv76xx_state *state = to_state(sd); + + pad = state->selected_input; + } + + switch (pad) { + case ADV76XX_PAD_HDMI_PORT_A: + case ADV7604_PAD_HDMI_PORT_B: + case ADV7604_PAD_HDMI_PORT_C: + case ADV7604_PAD_HDMI_PORT_D: + return &adv76xx_timings_cap_digital; + + case ADV7604_PAD_VGA_RGB: + case ADV7604_PAD_VGA_COMP: + default: + return &adv7604_timings_cap_analog; + } } @@ -1329,7 +1349,7 @@ static int stdi2dv_timings(struct v4l2_subdev *sd, const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt; if (!v4l2_valid_dv_timings(&v4l2_dv_timings_presets[i], - adv76xx_get_dv_timings_cap(sd), + adv76xx_get_dv_timings_cap(sd, -1), adv76xx_check_dv_timings, NULL)) continue; if (vtotal(bt) != stdi->lcf + 1) @@ -1430,18 +1450,22 @@ static int adv76xx_enum_dv_timings(struct v4l2_subdev *sd, return -EINVAL; return v4l2_enum_dv_timings_cap(timings, - adv76xx_get_dv_timings_cap(sd), adv76xx_check_dv_timings, NULL); + adv76xx_get_dv_timings_cap(sd, timings->pad), + adv76xx_check_dv_timings, NULL); } static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd, struct v4l2_dv_timings_cap *cap) { struct adv76xx_state *state = to_state(sd); + unsigned int pad = cap->pad; if (cap->pad >= state->source_pad) return -EINVAL; - *cap = *adv76xx_get_dv_timings_cap(sd); + *cap = *adv76xx_get_dv_timings_cap(sd, pad); + cap->pad = pad; + return 0; } @@ -1450,9 +1474,9 @@ static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd, static void adv76xx_fill_optional_dv_timings_fields(struct v4l2_subdev *sd, struct v4l2_dv_timings *timings) { - v4l2_find_dv_timings_cap(timings, adv76xx_get_dv_timings_cap(sd), - is_digital_input(sd) ? 250000 : 1000000, - adv76xx_check_dv_timings, NULL); + v4l2_find_dv_timings_cap(timings, adv76xx_get_dv_timings_cap(sd, -1), + is_digital_input(sd) ? 250000 : 1000000, + adv76xx_check_dv_timings, NULL); } static unsigned int adv7604_read_hdmi_pixelclock(struct v4l2_subdev *sd) @@ -1620,7 +1644,7 @@ static int adv76xx_s_dv_timings(struct v4l2_subdev *sd, bt = &timings->bt; - if (!v4l2_valid_dv_timings(timings, adv76xx_get_dv_timings_cap(sd), + if (!v4l2_valid_dv_timings(timings, adv76xx_get_dv_timings_cap(sd, -1), adv76xx_check_dv_timings, NULL)) return -ERANGE; diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c index 87c12930416f..92d9d4214c3a 100644 --- a/drivers/media/usb/airspy/airspy.c +++ b/drivers/media/usb/airspy/airspy.c @@ -1072,7 +1072,7 @@ static int airspy_probe(struct usb_interface *intf, if (ret) { dev_err(s->dev, "Failed to register as video device (%d)\n", ret); - goto err_unregister_v4l2_dev; + goto err_free_controls; } dev_info(s->dev, "Registered as %s\n", video_device_node_name(&s->vdev)); @@ -1081,7 +1081,6 @@ static int airspy_probe(struct usb_interface *intf, err_free_controls: v4l2_ctrl_handler_free(&s->hdl); -err_unregister_v4l2_dev: v4l2_device_unregister(&s->v4l2_dev); err_free_mem: kfree(s); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 28e5be2c2eef..528390f33b53 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2171,7 +2171,7 @@ static int v4l_cropcap(const struct v4l2_ioctl_ops *ops, * The determine_valid_ioctls() call already should ensure * that this can never happen, but just in case... */ - if (WARN_ON(!ops->vidioc_cropcap && !ops->vidioc_cropcap)) + if (WARN_ON(!ops->vidioc_cropcap && !ops->vidioc_g_selection)) return -ENOTTY; if (ops->vidioc_cropcap) diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c index ca94bded3386..8bef4331bd51 100644 --- a/drivers/media/v4l2-core/v4l2-mc.c +++ b/drivers/media/v4l2-core/v4l2-mc.c @@ -1,7 +1,7 @@ /* * Media Controller ancillary functions * - * Copyright (c) 2016 Mauro Carvalho Chehab + * Copyright (c) 2016 Mauro Carvalho Chehab * Copyright (C) 2016 Shuah Khan * Copyright (C) 2006-2010 Nokia Corporation * Copyright (c) 2016 Intel Corporation. diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index af4884ba6b7c..15508df24e5d 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -398,7 +398,7 @@ static void gpmc_cs_bool_timings(int cs, const struct gpmc_bool_timings *p) gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4, GPMC_CONFIG4_OEEXTRADELAY, p->oe_extra_delay); gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4, - GPMC_CONFIG4_OEEXTRADELAY, p->we_extra_delay); + GPMC_CONFIG4_WEEXTRADELAY, p->we_extra_delay); gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG6, GPMC_CONFIG6_CYCLE2CYCLESAMECSEN, p->cycle2cyclesamecsen); diff --git a/drivers/mfd/max77620.c b/drivers/mfd/max77620.c index 199d261990be..f32fbb8e8129 100644 --- a/drivers/mfd/max77620.c +++ b/drivers/mfd/max77620.c @@ -203,6 +203,7 @@ static int max77620_get_fps_period_reg_value(struct max77620_chip *chip, break; case MAX77620: fps_min_period = MAX77620_FPS_PERIOD_MIN_US; + break; default: return -EINVAL; } @@ -236,6 +237,7 @@ static int max77620_config_fps(struct max77620_chip *chip, break; case MAX77620: fps_max_period = MAX77620_FPS_PERIOD_MAX_US; + break; default: return -EINVAL; } diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index eed254da63a8..641c1a566687 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -730,7 +730,7 @@ static void mei_cl_wake_all(struct mei_cl *cl) /* synchronized under device mutex */ if (waitqueue_active(&cl->wait)) { cl_dbg(dev, cl, "Waking up ctrl write clients!\n"); - wake_up_interruptible(&cl->wait); + wake_up(&cl->wait); } } diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index e62fde3ac431..c5472e3c9231 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -355,8 +355,10 @@ static struct mmc_blk_ioc_data *mmc_blk_ioctl_copy_from_user( goto idata_err; } - if (!idata->buf_bytes) + if (!idata->buf_bytes) { + idata->buf = NULL; return idata; + } idata->buf = kmalloc(idata->buf_bytes, GFP_KERNEL); if (!idata->buf) { @@ -1786,8 +1788,8 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, packed_cmd_hdr = packed->cmd_hdr; memset(packed_cmd_hdr, 0, sizeof(packed->cmd_hdr)); - packed_cmd_hdr[0] = (packed->nr_entries << 16) | - (PACKED_CMD_WR << 8) | PACKED_CMD_VER; + packed_cmd_hdr[0] = cpu_to_le32((packed->nr_entries << 16) | + (PACKED_CMD_WR << 8) | PACKED_CMD_VER); hdr_blocks = mmc_large_sector(card) ? 8 : 1; /* @@ -1801,14 +1803,14 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, ((brq->data.blocks * brq->data.blksz) >= card->ext_csd.data_tag_unit_size); /* Argument of CMD23 */ - packed_cmd_hdr[(i * 2)] = + packed_cmd_hdr[(i * 2)] = cpu_to_le32( (do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) | (do_data_tag ? MMC_CMD23_ARG_TAG_REQ : 0) | - blk_rq_sectors(prq); + blk_rq_sectors(prq)); /* Argument of CMD18 or CMD25 */ - packed_cmd_hdr[((i * 2)) + 1] = + packed_cmd_hdr[((i * 2)) + 1] = cpu_to_le32( mmc_card_blockaddr(card) ? - blk_rq_pos(prq) : blk_rq_pos(prq) << 9; + blk_rq_pos(prq) : blk_rq_pos(prq) << 9); packed->blocks += blk_rq_sectors(prq); i++; } diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 86fac3e86833..c763b404510f 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -789,14 +789,16 @@ static int pxamci_probe(struct platform_device *pdev) gpio_direction_output(gpio_power, host->pdata->gpio_power_invert); } - if (gpio_is_valid(gpio_ro)) + if (gpio_is_valid(gpio_ro)) { ret = mmc_gpio_request_ro(mmc, gpio_ro); - if (ret) { - dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro); - goto out; - } else { - mmc->caps2 |= host->pdata->gpio_card_ro_invert ? - 0 : MMC_CAP2_RO_ACTIVE_HIGH; + if (ret) { + dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", + gpio_ro); + goto out; + } else { + mmc->caps2 |= host->pdata->gpio_card_ro_invert ? + 0 : MMC_CAP2_RO_ACTIVE_HIGH; + } } if (gpio_is_valid(gpio_cd)) diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index 08e158895635..a136da8df6fe 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -1657,8 +1657,11 @@ static int omap_get_dt_info(struct device *dev, struct omap_nand_info *info) /* detect availability of ELM module. Won't be present pre-OMAP4 */ info->elm_of_node = of_parse_phandle(child, "ti,elm-id", 0); - if (!info->elm_of_node) - dev_dbg(dev, "ti,elm-id not in DT\n"); + if (!info->elm_of_node) { + info->elm_of_node = of_parse_phandle(child, "elm_id", 0); + if (!info->elm_of_node) + dev_dbg(dev, "ti,elm-id not in DT\n"); + } /* select ecc-scheme for NAND */ if (of_property_read_string(child, "ti,nand-ecc-opt", &s)) { diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 16baeb51b2bd..ef3618299494 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1147,11 +1147,17 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway) */ static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev) { - struct kstat stat; int err, minor; + struct path path; + struct kstat stat; /* Probably this is an MTD character device node path */ - err = vfs_stat(mtd_dev, &stat); + err = kern_path(mtd_dev, LOOKUP_FOLLOW, &path); + if (err) + return ERR_PTR(err); + + err = vfs_getattr(&path, &stat); + path_put(&path); if (err) return ERR_PTR(err); @@ -1160,6 +1166,7 @@ static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev) return ERR_PTR(-EINVAL); minor = MINOR(stat.rdev); + if (minor & 1) /* * Just do not think the "/dev/mtdrX" devices support is need, diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 5780dd1ba79d..ebf517271d29 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -575,6 +575,7 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum, int err, idx = vol_id2idx(ubi, vol_id), new_pnum, data_size, tries = 0; struct ubi_volume *vol = ubi->volumes[idx]; struct ubi_vid_hdr *vid_hdr; + uint32_t crc; vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS); if (!vid_hdr) @@ -599,14 +600,8 @@ retry: goto out_put; } - vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); - err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr); - if (err) { - up_read(&ubi->fm_eba_sem); - goto write_error; - } + ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC); - data_size = offset + len; mutex_lock(&ubi->buf_mutex); memset(ubi->peb_buf + offset, 0xFF, len); @@ -621,6 +616,19 @@ retry: memcpy(ubi->peb_buf + offset, buf, len); + data_size = offset + len; + crc = crc32(UBI_CRC32_INIT, ubi->peb_buf, data_size); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); + vid_hdr->copy_flag = 1; + vid_hdr->data_size = cpu_to_be32(data_size); + vid_hdr->data_crc = cpu_to_be32(crc); + err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr); + if (err) { + mutex_unlock(&ubi->buf_mutex); + up_read(&ubi->fm_eba_sem); + goto write_error; + } + err = ubi_io_write_data(ubi, ubi->peb_buf, new_pnum, 0, data_size); if (err) { mutex_unlock(&ubi->buf_mutex); diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c index 348dbbcbedc8..a9e2cef7c95c 100644 --- a/drivers/mtd/ubi/kapi.c +++ b/drivers/mtd/ubi/kapi.c @@ -302,6 +302,7 @@ EXPORT_SYMBOL_GPL(ubi_open_volume_nm); struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode) { int error, ubi_num, vol_id; + struct path path; struct kstat stat; dbg_gen("open volume %s, mode %d", pathname, mode); @@ -309,7 +310,12 @@ struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode) if (!pathname || !*pathname) return ERR_PTR(-EINVAL); - error = vfs_stat(pathname, &stat); + error = kern_path(pathname, LOOKUP_FOLLOW, &path); + if (error) + return ERR_PTR(error); + + error = vfs_getattr(&path, &stat); + path_put(&path); if (error) return ERR_PTR(error); diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index b9304a295f86..edc70ffad660 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -101,11 +101,14 @@ enum ad_link_speed_type { #define MAC_ADDRESS_EQUAL(A, B) \ ether_addr_equal_64bits((const u8 *)A, (const u8 *)B) -static struct mac_addr null_mac_addr = { { 0, 0, 0, 0, 0, 0 } }; +static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = { + 0, 0, 0, 0, 0, 0 +}; static u16 ad_ticks_per_sec; static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; -static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR; +static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = + MULTICAST_LACPDU_ADDR; /* ================= main 802.3ad protocol functions ================== */ static int ad_lacpdu_send(struct port *port); @@ -657,6 +660,20 @@ static void __set_agg_ports_ready(struct aggregator *aggregator, int val) } } +static int __agg_active_ports(struct aggregator *agg) +{ + struct port *port; + int active = 0; + + for (port = agg->lag_ports; port; + port = port->next_port_in_aggregator) { + if (port->is_enabled) + active++; + } + + return active; +} + /** * __get_agg_bandwidth - get the total bandwidth of an aggregator * @aggregator: the aggregator we're looking at @@ -664,39 +681,40 @@ static void __set_agg_ports_ready(struct aggregator *aggregator, int val) */ static u32 __get_agg_bandwidth(struct aggregator *aggregator) { + int nports = __agg_active_ports(aggregator); u32 bandwidth = 0; - if (aggregator->num_of_ports) { + if (nports) { switch (__get_link_speed(aggregator->lag_ports)) { case AD_LINK_SPEED_1MBPS: - bandwidth = aggregator->num_of_ports; + bandwidth = nports; break; case AD_LINK_SPEED_10MBPS: - bandwidth = aggregator->num_of_ports * 10; + bandwidth = nports * 10; break; case AD_LINK_SPEED_100MBPS: - bandwidth = aggregator->num_of_ports * 100; + bandwidth = nports * 100; break; case AD_LINK_SPEED_1000MBPS: - bandwidth = aggregator->num_of_ports * 1000; + bandwidth = nports * 1000; break; case AD_LINK_SPEED_2500MBPS: - bandwidth = aggregator->num_of_ports * 2500; + bandwidth = nports * 2500; break; case AD_LINK_SPEED_10000MBPS: - bandwidth = aggregator->num_of_ports * 10000; + bandwidth = nports * 10000; break; case AD_LINK_SPEED_20000MBPS: - bandwidth = aggregator->num_of_ports * 20000; + bandwidth = nports * 20000; break; case AD_LINK_SPEED_40000MBPS: - bandwidth = aggregator->num_of_ports * 40000; + bandwidth = nports * 40000; break; case AD_LINK_SPEED_56000MBPS: - bandwidth = aggregator->num_of_ports * 56000; + bandwidth = nports * 56000; break; case AD_LINK_SPEED_100000MBPS: - bandwidth = aggregator->num_of_ports * 100000; + bandwidth = nports * 100000; break; default: bandwidth = 0; /* to silence the compiler */ @@ -1530,10 +1548,10 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best, switch (__get_agg_selection_mode(curr->lag_ports)) { case BOND_AD_COUNT: - if (curr->num_of_ports > best->num_of_ports) + if (__agg_active_ports(curr) > __agg_active_ports(best)) return curr; - if (curr->num_of_ports < best->num_of_ports) + if (__agg_active_ports(curr) < __agg_active_ports(best)) return best; /*FALLTHROUGH*/ @@ -1561,8 +1579,14 @@ static int agg_device_up(const struct aggregator *agg) if (!port) return 0; - return netif_running(port->slave->dev) && - netif_carrier_ok(port->slave->dev); + for (port = agg->lag_ports; port; + port = port->next_port_in_aggregator) { + if (netif_running(port->slave->dev) && + netif_carrier_ok(port->slave->dev)) + return 1; + } + + return 0; } /** @@ -1610,7 +1634,7 @@ static void ad_agg_selection_logic(struct aggregator *agg, agg->is_active = 0; - if (agg->num_of_ports && agg_device_up(agg)) + if (__agg_active_ports(agg) && agg_device_up(agg)) best = ad_agg_selection_test(best, agg); } @@ -1622,7 +1646,7 @@ static void ad_agg_selection_logic(struct aggregator *agg, * answering partner. */ if (active && active->lag_ports && - active->lag_ports->is_enabled && + __agg_active_ports(active) && (__agg_has_partner(active) || (!__agg_has_partner(active) && !__agg_has_partner(best)))) { @@ -1718,7 +1742,7 @@ static void ad_clear_agg(struct aggregator *aggregator) aggregator->is_individual = false; aggregator->actor_admin_aggregator_key = 0; aggregator->actor_oper_aggregator_key = 0; - aggregator->partner_system = null_mac_addr; + eth_zero_addr(aggregator->partner_system.mac_addr_value); aggregator->partner_system_priority = 0; aggregator->partner_oper_aggregator_key = 0; aggregator->receive_state = 0; @@ -1740,7 +1764,7 @@ static void ad_initialize_agg(struct aggregator *aggregator) if (aggregator) { ad_clear_agg(aggregator); - aggregator->aggregator_mac_address = null_mac_addr; + eth_zero_addr(aggregator->aggregator_mac_address.mac_addr_value); aggregator->aggregator_identifier = 0; aggregator->slave = NULL; } @@ -2133,7 +2157,7 @@ void bond_3ad_unbind_slave(struct slave *slave) else temp_aggregator->lag_ports = temp_port->next_port_in_aggregator; temp_aggregator->num_of_ports--; - if (temp_aggregator->num_of_ports == 0) { + if (__agg_active_ports(temp_aggregator) == 0) { select_new_active_agg = temp_aggregator->is_active; ad_clear_agg(temp_aggregator); if (select_new_active_agg) { @@ -2432,7 +2456,9 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave) */ void bond_3ad_handle_link_change(struct slave *slave, char link) { + struct aggregator *agg; struct port *port; + bool dummy; port = &(SLAVE_AD_INFO(slave)->port); @@ -2459,6 +2485,9 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) port->is_enabled = false; ad_update_actor_keys(port, true); } + agg = __get_first_agg(port); + ad_agg_selection_logic(agg, &dummy); + netdev_dbg(slave->bond->dev, "Port %d changed link status to %s\n", port->actor_port_number, link == BOND_LINK_UP ? "UP" : "DOWN"); @@ -2499,7 +2528,7 @@ int bond_3ad_set_carrier(struct bonding *bond) active = __get_active_agg(&(SLAVE_AD_INFO(first_slave)->aggregator)); if (active) { /* are enough slaves available to consider link up? */ - if (active->num_of_ports < bond->params.min_links) { + if (__agg_active_ports(active) < bond->params.min_links) { if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); goto out; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index c5ac160a8ae9..551f0f8dead3 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -42,13 +42,10 @@ -#ifndef __long_aligned -#define __long_aligned __attribute__((aligned((sizeof(long))))) -#endif -static const u8 mac_bcast[ETH_ALEN] __long_aligned = { +static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; -static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = { +static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x01 }; static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 941ec99cd3b6..a2afa3be17a4 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1584,6 +1584,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } /* check for initial state */ + new_slave->link = BOND_LINK_NOCHANGE; if (bond->params.miimon) { if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { if (bond->params.updelay) { diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index db760e84119f..b8df0f5e8c25 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev, if (err < 0) return err; - return register_netdevice(bond_dev); + err = register_netdevice(bond_dev); + + netif_carrier_off(bond_dev); + + return err; } static size_t bond_get_size(const struct net_device *bond_dev) diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 8b3275d7792a..8f5e93cb7975 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -712,9 +712,10 @@ static int at91_poll_rx(struct net_device *dev, int quota) /* upper group completed, look again in lower */ if (priv->rx_next > get_mb_rx_low_last(priv) && - quota > 0 && mb > get_mb_rx_last(priv)) { + mb > get_mb_rx_last(priv)) { priv->rx_next = get_mb_rx_first(priv); - goto again; + if (quota > 0) + goto again; } return received; diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index f91b094288da..e3dccd3200d5 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -332,9 +332,23 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface, priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl); - for (i = 0; i < frame->can_dlc; i += 2) { - priv->write_reg(priv, C_CAN_IFACE(DATA1_REG, iface) + i / 2, - frame->data[i] | (frame->data[i + 1] << 8)); + if (priv->type == BOSCH_D_CAN) { + u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface); + + for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) { + data = (u32)frame->data[i]; + data |= (u32)frame->data[i + 1] << 8; + data |= (u32)frame->data[i + 2] << 16; + data |= (u32)frame->data[i + 3] << 24; + priv->write_reg32(priv, dreg, data); + } + } else { + for (i = 0; i < frame->can_dlc; i += 2) { + priv->write_reg(priv, + C_CAN_IFACE(DATA1_REG, iface) + i / 2, + frame->data[i] | + (frame->data[i + 1] << 8)); + } } } @@ -402,10 +416,20 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl) } else { int i, dreg = C_CAN_IFACE(DATA1_REG, iface); - for (i = 0; i < frame->can_dlc; i += 2, dreg ++) { - data = priv->read_reg(priv, dreg); - frame->data[i] = data; - frame->data[i + 1] = data >> 8; + if (priv->type == BOSCH_D_CAN) { + for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) { + data = priv->read_reg32(priv, dreg); + frame->data[i] = data; + frame->data[i + 1] = data >> 8; + frame->data[i + 2] = data >> 16; + frame->data[i + 3] = data >> 24; + } + } else { + for (i = 0; i < frame->can_dlc; i += 2, dreg++) { + data = priv->read_reg(priv, dreg); + frame->data[i] = data; + frame->data[i + 1] = data >> 8; + } } } diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 910c12e2638e..ad535a854e5c 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -798,6 +798,9 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[]) * - control mode with CAN_CTRLMODE_FD set */ + if (!data) + return 0; + if (data[IFLA_CAN_CTRLMODE]) { struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); @@ -1008,6 +1011,11 @@ static int can_newlink(struct net *src_net, struct net_device *dev, return -EOPNOTSUPP; } +static void can_dellink(struct net_device *dev, struct list_head *head) +{ + return; +} + static struct rtnl_link_ops can_link_ops __read_mostly = { .kind = "can", .maxtype = IFLA_CAN_MAX, @@ -1016,6 +1024,7 @@ static struct rtnl_link_ops can_link_ops __read_mostly = { .validate = can_validate, .newlink = can_newlink, .changelink = can_changelink, + .dellink = can_dellink, .get_size = can_get_size, .fill_info = can_fill_info, .get_xstats_size = can_get_xstats_size, diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index bcb272f6c68a..8483a40e7e9e 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -16,7 +16,8 @@ config CAN_ESD_USB2 config CAN_GS_USB tristate "Geschwister Schneider UG interfaces" ---help--- - This driver supports the Geschwister Schneider USB/CAN devices. + This driver supports the Geschwister Schneider and bytewerk.org + candleLight USB CAN interfaces USB/CAN devices If unsure choose N, choose Y for built in support, M to compile as module (module will be named: gs_usb). @@ -46,6 +47,8 @@ config CAN_KVASER_USB - Kvaser USBcan R - Kvaser Leaf Light v2 - Kvaser Mini PCI Express HS + - Kvaser Mini PCI Express 2xHS + - Kvaser USBcan Light 2xHS - Kvaser USBcan II HS/HS - Kvaser USBcan II HS/LS - Kvaser USBcan Rugged ("USBcan Rev B") diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 1556d4286235..acb0c8490673 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -1,7 +1,9 @@ -/* CAN driver for Geschwister Schneider USB/CAN devices. +/* CAN driver for Geschwister Schneider USB/CAN devices + * and bytewerk.org candleLight USB CAN interfaces. * - * Copyright (C) 2013 Geschwister Schneider Technologie-, + * Copyright (C) 2013-2016 Geschwister Schneider Technologie-, * Entwicklungs- und Vertriebs UG (Haftungsbeschränkt). + * Copyright (C) 2016 Hubert Denkmair * * Many thanks to all socketcan devs! * @@ -29,6 +31,9 @@ #define USB_GSUSB_1_VENDOR_ID 0x1d50 #define USB_GSUSB_1_PRODUCT_ID 0x606f +#define USB_CANDLELIGHT_VENDOR_ID 0x1209 +#define USB_CANDLELIGHT_PRODUCT_ID 0x2323 + #define GSUSB_ENDPOINT_IN 1 #define GSUSB_ENDPOINT_OUT 2 @@ -952,6 +957,8 @@ static void gs_usb_disconnect(struct usb_interface *intf) static const struct usb_device_id gs_usb_table[] = { { USB_DEVICE_INTERFACE_NUMBER(USB_GSUSB_1_VENDOR_ID, USB_GSUSB_1_PRODUCT_ID, 0) }, + { USB_DEVICE_INTERFACE_NUMBER(USB_CANDLELIGHT_VENDOR_ID, + USB_CANDLELIGHT_PRODUCT_ID, 0) }, {} /* Terminating entry */ }; @@ -969,5 +976,6 @@ module_usb_driver(gs_usb_driver); MODULE_AUTHOR("Maximilian Schneider "); MODULE_DESCRIPTION( "Socket CAN device driver for Geschwister Schneider Technologie-, " -"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces."); +"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces\n" +"and bytewerk.org candleLight USB CAN interfaces."); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 022bfa13ebfa..6f1f3b675ff5 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -59,11 +59,14 @@ #define USB_CAN_R_PRODUCT_ID 39 #define USB_LEAF_LITE_V2_PRODUCT_ID 288 #define USB_MINI_PCIE_HS_PRODUCT_ID 289 +#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290 +#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID 291 +#define USB_MINI_PCIE_2HS_PRODUCT_ID 292 static inline bool kvaser_is_leaf(const struct usb_device_id *id) { return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID && - id->idProduct <= USB_MINI_PCIE_HS_PRODUCT_ID; + id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID; } /* Kvaser USBCan-II devices */ @@ -537,6 +540,9 @@ static const struct usb_device_id kvaser_usb_table[] = { .driver_info = KVASER_HAS_TXRX_ERRORS }, { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) }, /* USBCANII family IDs */ { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID), diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 30defe6c81f2..821d86c38ab2 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -3851,7 +3851,7 @@ static void et131x_tx_timeout(struct net_device *netdev) unsigned long flags; /* If the device is closed, ignore the timeout */ - if (~(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE)) + if (!(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE)) return; /* Any nonrecoverable hardware error? diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index e0fb0f1122db..20760e10211a 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -509,8 +509,8 @@ static int au1000_mii_probe(struct net_device *dev) * on the current MAC's MII bus */ for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++) - if (mdiobus_get_phy(aup->mii_bus, aup->phy_addr)) { - phydev = mdiobus_get_phy(aup->mii_bus, aup->phy_addr); + if (mdiobus_get_phy(aup->mii_bus, phy_addr)) { + phydev = mdiobus_get_phy(aup->mii_bus, phy_addr); if (!aup->phy_search_highest_addr) /* break out with first one found */ break; diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index d02c4240b7df..8fc93c5f6abc 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -96,10 +96,6 @@ struct alx_priv { unsigned int rx_ringsz; unsigned int rxbuf_size; - struct page *rx_page; - unsigned int rx_page_offset; - unsigned int rx_frag_size; - struct napi_struct napi; struct alx_tx_queue txq; struct alx_rx_queue rxq; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index c98acdc0d14f..e708e360a9e3 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -70,35 +70,6 @@ static void alx_free_txbuf(struct alx_priv *alx, int entry) } } -static struct sk_buff *alx_alloc_skb(struct alx_priv *alx, gfp_t gfp) -{ - struct sk_buff *skb; - struct page *page; - - if (alx->rx_frag_size > PAGE_SIZE) - return __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp); - - page = alx->rx_page; - if (!page) { - alx->rx_page = page = alloc_page(gfp); - if (unlikely(!page)) - return NULL; - alx->rx_page_offset = 0; - } - - skb = build_skb(page_address(page) + alx->rx_page_offset, - alx->rx_frag_size); - if (likely(skb)) { - alx->rx_page_offset += alx->rx_frag_size; - if (alx->rx_page_offset >= PAGE_SIZE) - alx->rx_page = NULL; - else - get_page(page); - } - return skb; -} - - static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp) { struct alx_rx_queue *rxq = &alx->rxq; @@ -115,9 +86,22 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp) while (!cur_buf->skb && next != rxq->read_idx) { struct alx_rfd *rfd = &rxq->rfd[cur]; - skb = alx_alloc_skb(alx, gfp); + /* + * When DMA RX address is set to something like + * 0x....fc0, it will be very likely to cause DMA + * RFD overflow issue. + * + * To work around it, we apply rx skb with 64 bytes + * longer space, and offset the address whenever + * 0x....fc0 is detected. + */ + skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size + 64, gfp); if (!skb) break; + + if (((unsigned long)skb->data & 0xfff) == 0xfc0) + skb_reserve(skb, 64); + dma = dma_map_single(&alx->hw.pdev->dev, skb->data, alx->rxbuf_size, DMA_FROM_DEVICE); @@ -153,7 +137,6 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp) alx_write_mem16(&alx->hw, ALX_RFD_PIDX, cur); } - return count; } @@ -622,11 +605,6 @@ static void alx_free_rings(struct alx_priv *alx) kfree(alx->txq.bufs); kfree(alx->rxq.bufs); - if (alx->rx_page) { - put_page(alx->rx_page); - alx->rx_page = NULL; - } - dma_free_coherent(&alx->hw.pdev->dev, alx->descmem.size, alx->descmem.virt, @@ -681,7 +659,6 @@ static int alx_request_irq(struct alx_priv *alx) alx->dev->name, alx); if (!err) goto out; - /* fall back to legacy interrupt */ pci_disable_msi(alx->hw.pdev); } @@ -725,7 +702,6 @@ static int alx_init_sw(struct alx_priv *alx) struct pci_dev *pdev = alx->hw.pdev; struct alx_hw *hw = &alx->hw; int err; - unsigned int head_size; err = alx_identify_hw(alx); if (err) { @@ -741,12 +717,7 @@ static int alx_init_sw(struct alx_priv *alx) hw->smb_timer = 400; hw->mtu = alx->dev->mtu; - alx->rxbuf_size = ALX_MAX_FRAME_LEN(hw->mtu); - head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - alx->rx_frag_size = roundup_pow_of_two(head_size); - alx->tx_ringsz = 256; alx->rx_ringsz = 512; hw->imt = 200; @@ -848,7 +819,6 @@ static int alx_change_mtu(struct net_device *netdev, int mtu) { struct alx_priv *alx = netdev_priv(netdev); int max_frame = ALX_MAX_FRAME_LEN(mtu); - unsigned int head_size; if ((max_frame < ALX_MIN_FRAME_SIZE) || (max_frame > ALX_MAX_FRAME_SIZE)) @@ -860,9 +830,6 @@ static int alx_change_mtu(struct net_device *netdev, int mtu) netdev->mtu = mtu; alx->hw.mtu = mtu; alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE); - head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - alx->rx_frag_size = roundup_pow_of_two(head_size); netdev_update_features(netdev); if (netif_running(netdev)) alx_reinit(alx); diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 08a23e6b60e9..1a3555d03a96 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -259,6 +259,7 @@ static void nb8800_receive(struct net_device *dev, unsigned int i, if (err) { netdev_err(dev, "rx buffer allocation failed\n"); dev->stats.rx_dropped++; + dev_kfree_skb(skb); return; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 543bf38105c9..bfa26a2590c9 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -392,7 +392,7 @@ static void bcm_sysport_get_stats(struct net_device *dev, else p = (char *)priv; p += s->stat_offset; - data[i] = *(u32 *)p; + data[i] = *(unsigned long *)p; } } diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index ee5f431ab32a..25bbae5928d4 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -231,7 +231,7 @@ err_dma: dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb), DMA_TO_DEVICE); - while (i > 0) { + while (i-- > 0) { int index = (ring->end + i) % BGMAC_TX_RING_SLOTS; struct bgmac_slot_info *slot = &ring->slots[index]; u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1); @@ -267,15 +267,16 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring) while (ring->start != ring->end) { int slot_idx = ring->start % BGMAC_TX_RING_SLOTS; struct bgmac_slot_info *slot = &ring->slots[slot_idx]; - u32 ctl1; + u32 ctl0, ctl1; int len; if (slot_idx == empty_slot) break; + ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0); ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1); len = ctl1 & BGMAC_DESC_CTL1_LEN; - if (ctl1 & BGMAC_DESC_CTL0_SOF) + if (ctl0 & BGMAC_DESC_CTL0_SOF) /* Unmap no longer used buffer */ dma_unmap_single(dma_dev, slot->dma_addr, len, DMA_TO_DEVICE); @@ -1312,7 +1313,8 @@ static int bgmac_open(struct net_device *net_dev) phy_start(bgmac->phy_dev); - netif_carrier_on(net_dev); + netif_start_queue(net_dev); + return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index a38cb047b540..1b0ae4a72e9e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1591,7 +1591,7 @@ static int bnxt_get_module_eeprom(struct net_device *dev, { struct bnxt *bp = netdev_priv(dev); u16 start = eeprom->offset, length = eeprom->len; - int rc; + int rc = 0; memset(data, 0, eeprom->len); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 8de79ae63231..0e7e7da8d201 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2821,7 +2821,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) if (!g) { netif_info(lio, tx_err, lio->netdev, "Transmit scatter gather: glist null!\n"); - goto lio_xmit_failed; + goto lio_xmit_dma_failed; } cmdsetup.s.gather = 1; @@ -2892,7 +2892,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) else status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more); if (status == IQ_SEND_FAILED) - goto lio_xmit_failed; + goto lio_xmit_dma_failed; netif_info(lio, tx_queued, lio->netdev, "Transmit queued successfully\n"); @@ -2906,12 +2906,13 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; +lio_xmit_dma_failed: + dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr, + ndata.datasize, DMA_TO_DEVICE); lio_xmit_failed: stats->tx_dropped++; netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n", iq_no, stats->tx_dropped); - dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr, - ndata.datasize, DMA_TO_DEVICE); recv_buffer_free(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 95f17f8cadac..16ed20357c5c 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -499,6 +499,7 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic, u32 rr_quantum; u8 sq_idx = sq->sq_num; u8 pqs_vnic; + int svf; if (sq->sqs_mode) pqs_vnic = nic->pqs_vf[vnic]; @@ -511,10 +512,19 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic, /* 24 bytes for FCS, IPG and preamble */ rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4); - tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX); + if (!sq->sqs_mode) { + tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX); + } else { + for (svf = 0; svf < MAX_SQS_PER_VF; svf++) { + if (nic->vf_sqs[pqs_vnic][svf] == vnic) + break; + } + tl4 = (MAX_LMAC_PER_BGX * NIC_TL4_PER_LMAC); + tl4 += (lmac * NIC_TL4_PER_LMAC * MAX_SQS_PER_VF); + tl4 += (svf * NIC_TL4_PER_LMAC); + tl4 += (bgx * NIC_TL4_PER_BGX); + } tl4 += sq_idx; - if (sq->sqs_mode) - tl4 += vnic * 8; tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3); nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 | diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 3ed21988626b..63a39ac97d53 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -551,7 +551,9 @@ static int bgx_xaui_check_link(struct lmac *lmac) } /* Clear rcvflt bit (latching high) and read it back */ - bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT); + if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) + bgx_reg_modify(bgx, lmacid, + BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT); if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) { dev_err(&bgx->pdev->dev, "Receive fault, retry training\n"); if (bgx->use_training) { @@ -570,13 +572,6 @@ static int bgx_xaui_check_link(struct lmac *lmac) return -1; } - /* Wait for MAC RX to be ready */ - if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL, - SMU_RX_CTL_STATUS, true)) { - dev_err(&bgx->pdev->dev, "SMU RX link not okay\n"); - return -1; - } - /* Wait for BGX RX to be idle */ if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) { dev_err(&bgx->pdev->dev, "SMU RX not idle\n"); @@ -589,29 +584,30 @@ static int bgx_xaui_check_link(struct lmac *lmac) return -1; } - if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) { - dev_err(&bgx->pdev->dev, "Receive fault\n"); - return -1; - } - - /* Receive link is latching low. Force it high and verify it */ - bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK); - if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1, - SPU_STATUS1_RCV_LNK, false)) { - dev_err(&bgx->pdev->dev, "SPU receive link down\n"); - return -1; - } - + /* Clear receive packet disable */ cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL); cfg &= ~SPU_MISC_CTL_RX_DIS; bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg); - return 0; + + /* Check for MAC RX faults */ + cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_CTL); + /* 0 - Link is okay, 1 - Local fault, 2 - Remote fault */ + cfg &= SMU_RX_CTL_STATUS; + if (!cfg) + return 0; + + /* Rx local/remote fault seen. + * Do lmac reinit to see if condition recovers + */ + bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type); + + return -1; } static void bgx_poll_for_link(struct work_struct *work) { struct lmac *lmac; - u64 link; + u64 spu_link, smu_link; lmac = container_of(work, struct lmac, dwork.work); @@ -621,8 +617,11 @@ static void bgx_poll_for_link(struct work_struct *work) bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK, false); - link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1); - if (link & SPU_STATUS1_RCV_LNK) { + spu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1); + smu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SMUX_RX_CTL); + + if ((spu_link & SPU_STATUS1_RCV_LNK) && + !(smu_link & SMU_RX_CTL_STATUS)) { lmac->link_up = 1; if (lmac->bgx->lmac_type == BGX_MODE_XLAUI) lmac->last_speed = 40000; @@ -636,9 +635,15 @@ static void bgx_poll_for_link(struct work_struct *work) } if (lmac->last_link != lmac->link_up) { + if (lmac->link_up) { + if (bgx_xaui_check_link(lmac)) { + /* Errors, clear link_up state */ + lmac->link_up = 0; + lmac->last_speed = SPEED_UNKNOWN; + lmac->last_duplex = DUPLEX_UNKNOWN; + } + } lmac->last_link = lmac->link_up; - if (lmac->link_up) - bgx_xaui_check_link(lmac); } queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2); @@ -710,7 +715,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) { struct lmac *lmac; - u64 cmrx_cfg; + u64 cfg; lmac = &bgx->lmac[lmacid]; if (lmac->check_link) { @@ -719,9 +724,33 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) destroy_workqueue(lmac->check_link); } - cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); - cmrx_cfg &= ~(1 << 15); - bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg); + /* Disable packet reception */ + cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); + cfg &= ~CMR_PKT_RX_EN; + bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); + + /* Give chance for Rx/Tx FIFO to get drained */ + bgx_poll_reg(bgx, lmacid, BGX_CMRX_RX_FIFO_LEN, (u64)0x1FFF, true); + bgx_poll_reg(bgx, lmacid, BGX_CMRX_TX_FIFO_LEN, (u64)0x3FFF, true); + + /* Disable packet transmission */ + cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); + cfg &= ~CMR_PKT_TX_EN; + bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); + + /* Disable serdes lanes */ + if (!lmac->is_sgmii) + bgx_reg_modify(bgx, lmacid, + BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER); + else + bgx_reg_modify(bgx, lmacid, + BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_PWR_DN); + + /* Disable LMAC */ + cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); + cfg &= ~CMR_EN; + bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); + bgx_flush_dmac_addrs(bgx, lmacid); if ((bgx->lmac_type != BGX_MODE_XFI) && diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index 149e179363a1..42010d2e5ddf 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -41,6 +41,7 @@ #define BGX_CMRX_RX_STAT10 0xC0 #define BGX_CMRX_RX_BP_DROP 0xC8 #define BGX_CMRX_RX_DMAC_CTL 0x0E8 +#define BGX_CMRX_RX_FIFO_LEN 0x108 #define BGX_CMR_RX_DMACX_CAM 0x200 #define RX_DMACX_CAM_EN BIT_ULL(48) #define RX_DMACX_CAM_LMACID(x) (x << 49) @@ -50,6 +51,7 @@ #define BGX_CMR_CHAN_MSK_AND 0x450 #define BGX_CMR_BIST_STATUS 0x460 #define BGX_CMR_RX_LMACS 0x468 +#define BGX_CMRX_TX_FIFO_LEN 0x518 #define BGX_CMRX_TX_STAT0 0x600 #define BGX_CMRX_TX_STAT1 0x608 #define BGX_CMRX_TX_STAT2 0x610 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index c4b262ca7d43..2accab386323 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -36,8 +36,8 @@ #define __T4FW_VERSION_H__ #define T4FW_VERSION_MAJOR 0x01 -#define T4FW_VERSION_MINOR 0x0E -#define T4FW_VERSION_MICRO 0x04 +#define T4FW_VERSION_MINOR 0x0F +#define T4FW_VERSION_MICRO 0x25 #define T4FW_VERSION_BUILD 0x00 #define T4FW_MIN_VERSION_MAJOR 0x01 @@ -45,8 +45,8 @@ #define T4FW_MIN_VERSION_MICRO 0x00 #define T5FW_VERSION_MAJOR 0x01 -#define T5FW_VERSION_MINOR 0x0E -#define T5FW_VERSION_MICRO 0x04 +#define T5FW_VERSION_MINOR 0x0F +#define T5FW_VERSION_MICRO 0x25 #define T5FW_VERSION_BUILD 0x00 #define T5FW_MIN_VERSION_MAJOR 0x00 @@ -54,8 +54,8 @@ #define T5FW_MIN_VERSION_MICRO 0x00 #define T6FW_VERSION_MAJOR 0x01 -#define T6FW_VERSION_MINOR 0x0E -#define T6FW_VERSION_MICRO 0x04 +#define T6FW_VERSION_MINOR 0x0F +#define T6FW_VERSION_MICRO 0x25 #define T6FW_VERSION_BUILD 0x00 #define T6FW_MIN_VERSION_MAJOR 0x00 diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 4edb98c3c6c7..4466a1187110 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -860,6 +860,11 @@ static netdev_tx_t ethoc_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int entry; void *dest; + if (skb_put_padto(skb, ETHOC_ZLEN)) { + dev->stats.tx_errors++; + goto out_no_free; + } + if (unlikely(skb->len > ETHOC_BUFSIZ)) { dev->stats.tx_errors++; goto out; @@ -894,6 +899,7 @@ static netdev_tx_t ethoc_start_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); out: dev_kfree_skb(skb); +out_no_free: return NETDEV_TX_OK; } @@ -1086,7 +1092,7 @@ static int ethoc_probe(struct platform_device *pdev) if (!priv->iobase) { dev_err(&pdev->dev, "cannot remap I/O memory space\n"); ret = -ENXIO; - goto error; + goto free; } if (netdev->mem_end) { @@ -1095,7 +1101,7 @@ static int ethoc_probe(struct platform_device *pdev) if (!priv->membase) { dev_err(&pdev->dev, "cannot remap memory space\n"); ret = -ENXIO; - goto error; + goto free; } } else { /* Allocate buffer memory */ @@ -1106,7 +1112,7 @@ static int ethoc_probe(struct platform_device *pdev) dev_err(&pdev->dev, "cannot allocate %dB buffer\n", buffer_size); ret = -ENOMEM; - goto error; + goto free; } netdev->mem_end = netdev->mem_start + buffer_size; priv->dma_alloc = buffer_size; @@ -1120,7 +1126,7 @@ static int ethoc_probe(struct platform_device *pdev) 128, (netdev->mem_end - netdev->mem_start + 1) / ETHOC_BUFSIZ); if (num_bd < 4) { ret = -ENODEV; - goto error; + goto free; } priv->num_bd = num_bd; /* num_tx must be a power of two */ @@ -1133,7 +1139,7 @@ static int ethoc_probe(struct platform_device *pdev) priv->vma = devm_kzalloc(&pdev->dev, num_bd*sizeof(void *), GFP_KERNEL); if (!priv->vma) { ret = -ENOMEM; - goto error; + goto free; } /* Allow the platform setup code to pass in a MAC address. */ diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 06f031715b57..9b7a3f5a2818 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -285,6 +285,7 @@ static void nps_enet_hw_reset(struct net_device *ndev) ge_rst_value |= NPS_ENET_ENABLE << RST_GMAC_0_SHIFT; nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value); usleep_range(10, 20); + ge_rst_value = 0; nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value); /* Tx fifo reset sequence */ diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 864cb21351a4..88f3c85fb04a 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -75,6 +75,7 @@ #include #include #include +#include #include "ibmvnic.h" @@ -89,6 +90,7 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION); static int ibmvnic_version = IBMVNIC_INITIAL_VERSION; static int ibmvnic_remove(struct vio_dev *); static void release_sub_crqs(struct ibmvnic_adapter *); +static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *); static int ibmvnic_reset_crq(struct ibmvnic_adapter *); static int ibmvnic_send_crq_init(struct ibmvnic_adapter *); static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *); @@ -469,7 +471,8 @@ static int ibmvnic_open(struct net_device *netdev) crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_UP; ibmvnic_send_crq(adapter, &crq); - netif_start_queue(netdev); + netif_tx_start_all_queues(netdev); + return 0; bounce_map_failed: @@ -519,7 +522,7 @@ static int ibmvnic_close(struct net_device *netdev) for (i = 0; i < adapter->req_rx_queues; i++) napi_disable(&adapter->napi[i]); - netif_stop_queue(netdev); + netif_tx_stop_all_queues(netdev); if (adapter->bounce_buffer) { if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) { @@ -1212,12 +1215,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter goto reg_failed; } - scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); - if (scrq->irq == NO_IRQ) { - dev_err(dev, "Error mapping irq\n"); - goto map_irq_failed; - } - scrq->adapter = adapter; scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs); scrq->cur = 0; @@ -1230,12 +1227,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter return scrq; -map_irq_failed: - do { - rc = plpar_hcall_norets(H_FREE_SUB_CRQ, - adapter->vdev->unit_address, - scrq->crq_num); - } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); reg_failed: dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, DMA_BIDIRECTIONAL); @@ -1256,6 +1247,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) if (adapter->tx_scrq[i]) { free_irq(adapter->tx_scrq[i]->irq, adapter->tx_scrq[i]); + irq_dispose_mapping(adapter->tx_scrq[i]->irq); release_sub_crq_queue(adapter, adapter->tx_scrq[i]); } @@ -1267,6 +1259,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) if (adapter->rx_scrq[i]) { free_irq(adapter->rx_scrq[i]->irq, adapter->rx_scrq[i]); + irq_dispose_mapping(adapter->rx_scrq[i]->irq); release_sub_crq_queue(adapter, adapter->rx_scrq[i]); } @@ -1276,6 +1269,29 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) adapter->requested_caps = 0; } +static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *adapter) +{ + int i; + + if (adapter->tx_scrq) { + for (i = 0; i < adapter->req_tx_queues; i++) + if (adapter->tx_scrq[i]) + release_sub_crq_queue(adapter, + adapter->tx_scrq[i]); + adapter->tx_scrq = NULL; + } + + if (adapter->rx_scrq) { + for (i = 0; i < adapter->req_rx_queues; i++) + if (adapter->rx_scrq[i]) + release_sub_crq_queue(adapter, + adapter->rx_scrq[i]); + adapter->rx_scrq = NULL; + } + + adapter->requested_caps = 0; +} + static int disable_scrq_irq(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *scrq) { @@ -1395,6 +1411,66 @@ static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance) return IRQ_HANDLED; } +static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter) +{ + struct device *dev = &adapter->vdev->dev; + struct ibmvnic_sub_crq_queue *scrq; + int i = 0, j = 0; + int rc = 0; + + for (i = 0; i < adapter->req_tx_queues; i++) { + scrq = adapter->tx_scrq[i]; + scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); + + if (scrq->irq == NO_IRQ) { + rc = -EINVAL; + dev_err(dev, "Error mapping irq\n"); + goto req_tx_irq_failed; + } + + rc = request_irq(scrq->irq, ibmvnic_interrupt_tx, + 0, "ibmvnic_tx", scrq); + + if (rc) { + dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n", + scrq->irq, rc); + irq_dispose_mapping(scrq->irq); + goto req_rx_irq_failed; + } + } + + for (i = 0; i < adapter->req_rx_queues; i++) { + scrq = adapter->rx_scrq[i]; + scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); + if (scrq->irq == NO_IRQ) { + rc = -EINVAL; + dev_err(dev, "Error mapping irq\n"); + goto req_rx_irq_failed; + } + rc = request_irq(scrq->irq, ibmvnic_interrupt_rx, + 0, "ibmvnic_rx", scrq); + if (rc) { + dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n", + scrq->irq, rc); + irq_dispose_mapping(scrq->irq); + goto req_rx_irq_failed; + } + } + return rc; + +req_rx_irq_failed: + for (j = 0; j < i; j++) + free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]); + irq_dispose_mapping(adapter->rx_scrq[j]->irq); + i = adapter->req_tx_queues; +req_tx_irq_failed: + for (j = 0; j < i; j++) + free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); + irq_dispose_mapping(adapter->rx_scrq[j]->irq); + release_sub_crqs_no_irqs(adapter); + return rc; +} + static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) { struct device *dev = &adapter->vdev->dev; @@ -1403,8 +1479,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) union ibmvnic_crq crq; int total_queues; int more = 0; - int i, j; - int rc; + int i; if (!retry) { /* Sub-CRQ entries are 32 byte long */ @@ -1483,13 +1558,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) for (i = 0; i < adapter->req_tx_queues; i++) { adapter->tx_scrq[i] = allqueues[i]; adapter->tx_scrq[i]->pool_index = i; - rc = request_irq(adapter->tx_scrq[i]->irq, ibmvnic_interrupt_tx, - 0, "ibmvnic_tx", adapter->tx_scrq[i]); - if (rc) { - dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n", - adapter->tx_scrq[i]->irq, rc); - goto req_tx_irq_failed; - } } adapter->rx_scrq = kcalloc(adapter->req_rx_queues, @@ -1500,13 +1568,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) for (i = 0; i < adapter->req_rx_queues; i++) { adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues]; adapter->rx_scrq[i]->scrq_num = i; - rc = request_irq(adapter->rx_scrq[i]->irq, ibmvnic_interrupt_rx, - 0, "ibmvnic_rx", adapter->rx_scrq[i]); - if (rc) { - dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n", - adapter->rx_scrq[i]->irq, rc); - goto req_rx_irq_failed; - } } memset(&crq, 0, sizeof(crq)); @@ -1559,15 +1620,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) return; -req_rx_irq_failed: - for (j = 0; j < i; j++) - free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]); - i = adapter->req_tx_queues; -req_tx_irq_failed: - for (j = 0; j < i; j++) - free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); - kfree(adapter->rx_scrq); - adapter->rx_scrq = NULL; rx_failed: kfree(adapter->tx_scrq); adapter->tx_scrq = NULL; @@ -2121,7 +2173,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq, struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; - struct ibmvnic_error_buff *error_buff; + struct ibmvnic_error_buff *error_buff, *tmp; unsigned long flags; bool found = false; int i; @@ -2133,7 +2185,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq, } spin_lock_irqsave(&adapter->error_list_lock, flags); - list_for_each_entry(error_buff, &adapter->errors, list) + list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list) if (error_buff->error_id == crq->request_error_rsp.error_id) { found = true; list_del(&error_buff->list); @@ -2348,9 +2400,9 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, *req_value, (long int)be32_to_cpu(crq->request_capability_rsp. number), name); - release_sub_crqs(adapter); + release_sub_crqs_no_irqs(adapter); *req_value = be32_to_cpu(crq->request_capability_rsp.number); - complete(&adapter->init_done); + init_sub_crqs(adapter, 1); return; default: dev_err(dev, "Error %d in request cap rsp\n", @@ -2659,7 +2711,7 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, out: if (atomic_read(&adapter->running_cap_queries) == 0) - complete(&adapter->init_done); + init_sub_crqs(adapter, 0); /* We're done querying the capabilities, initialize sub-crqs */ } @@ -3141,14 +3193,14 @@ static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq, static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter) { - struct ibmvnic_inflight_cmd *inflight_cmd; + struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1; struct device *dev = &adapter->vdev->dev; - struct ibmvnic_error_buff *error_buff; + struct ibmvnic_error_buff *error_buff, *tmp2; unsigned long flags; unsigned long flags2; spin_lock_irqsave(&adapter->inflight_lock, flags); - list_for_each_entry(inflight_cmd, &adapter->inflight, list) { + list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) { switch (inflight_cmd->crq.generic.cmd) { case LOGIN: dma_unmap_single(dev, adapter->login_buf_token, @@ -3165,8 +3217,8 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter) break; case REQUEST_ERROR_INFO: spin_lock_irqsave(&adapter->error_list_lock, flags2); - list_for_each_entry(error_buff, &adapter->errors, - list) { + list_for_each_entry_safe(error_buff, tmp2, + &adapter->errors, list) { dma_unmap_single(dev, error_buff->dma, error_buff->len, DMA_FROM_DEVICE); @@ -3202,8 +3254,8 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, dev_info(dev, "Partner initialized\n"); /* Send back a response */ rc = ibmvnic_send_crq_init_complete(adapter); - if (rc == 0) - send_version_xchg(adapter); + if (!rc) + schedule_work(&adapter->vnic_crq_init); else dev_err(dev, "Can't send initrsp rc=%ld\n", rc); break; @@ -3555,8 +3607,63 @@ static const struct file_operations ibmvnic_dump_ops = { .release = single_release, }; +static void handle_crq_init_rsp(struct work_struct *work) +{ + struct ibmvnic_adapter *adapter = container_of(work, + struct ibmvnic_adapter, + vnic_crq_init); + struct device *dev = &adapter->vdev->dev; + struct net_device *netdev = adapter->netdev; + unsigned long timeout = msecs_to_jiffies(30000); + int rc; + + send_version_xchg(adapter); + reinit_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { + dev_err(dev, "Passive init timeout\n"); + goto task_failed; + } + + do { + if (adapter->renegotiate) { + adapter->renegotiate = false; + release_sub_crqs_no_irqs(adapter); + send_cap_queries(adapter); + + reinit_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, + timeout)) { + dev_err(dev, "Passive init timeout\n"); + goto task_failed; + } + } + } while (adapter->renegotiate); + rc = init_sub_crq_irqs(adapter); + + if (rc) + goto task_failed; + + netdev->real_num_tx_queues = adapter->req_tx_queues; + + rc = register_netdev(netdev); + if (rc) { + dev_err(dev, + "failed to register netdev rc=%d\n", rc); + goto register_failed; + } + dev_info(dev, "ibmvnic registered\n"); + + return; + +register_failed: + release_sub_crqs(adapter); +task_failed: + dev_err(dev, "Passive initialization was not successful\n"); +} + static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) { + unsigned long timeout = msecs_to_jiffies(30000); struct ibmvnic_adapter *adapter; struct net_device *netdev; unsigned char *mac_addr_p; @@ -3593,6 +3700,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) netdev->ethtool_ops = &ibmvnic_ethtool_ops; SET_NETDEV_DEV(netdev, &dev->dev); + INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp); + spin_lock_init(&adapter->stats_lock); rc = ibmvnic_init_crq_queue(adapter); @@ -3635,30 +3744,26 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) ibmvnic_send_crq_init(adapter); init_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) + return 0; do { - adapter->renegotiate = false; - - init_sub_crqs(adapter, 0); - reinit_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); - if (adapter->renegotiate) { - release_sub_crqs(adapter); + adapter->renegotiate = false; + release_sub_crqs_no_irqs(adapter); send_cap_queries(adapter); reinit_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); + if (!wait_for_completion_timeout(&adapter->init_done, + timeout)) + return 0; } } while (adapter->renegotiate); - /* if init_sub_crqs is partially successful, retry */ - while (!adapter->tx_scrq || !adapter->rx_scrq) { - init_sub_crqs(adapter, 1); - - reinit_completion(&adapter->init_done); - wait_for_completion(&adapter->init_done); + rc = init_sub_crq_irqs(adapter); + if (rc) { + dev_err(&dev->dev, "failed to initialize sub crq irqs\n"); + goto free_debugfs; } netdev->real_num_tx_queues = adapter->req_tx_queues; @@ -3666,12 +3771,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) rc = register_netdev(netdev); if (rc) { dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); - goto free_debugfs; + goto free_sub_crqs; } dev_info(&dev->dev, "ibmvnic registered\n"); return 0; +free_sub_crqs: + release_sub_crqs(adapter); free_debugfs: if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) debugfs_remove_recursive(adapter->debugfs_dir); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 0b66a506a4e4..e82898fd518e 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1045,4 +1045,6 @@ struct ibmvnic_adapter { u64 opt_rxba_entries_per_subcrq; __be64 tx_rx_desc_req; u8 map_id; + + struct work_struct vnic_crq_init; }; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 75e60897b7e7..2b2e2f8c6369 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2789,7 +2789,7 @@ static void e1000e_vlan_filter_enable(struct e1000_adapter *adapter) } /** - * e1000e_vlan_strip_enable - helper to disable HW VLAN stripping + * e1000e_vlan_strip_disable - helper to disable HW VLAN stripping * @adapter: board private structure to initialize **/ static void e1000e_vlan_strip_disable(struct e1000_adapter *adapter) @@ -6915,6 +6915,14 @@ static netdev_features_t e1000_fix_features(struct net_device *netdev, if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN)) features &= ~NETIF_F_RXFCS; + /* Since there is no support for separate Rx/Tx vlan accel + * enable/disable make sure Tx flag is always in same state as Rx. + */ + if (features & NETIF_F_HW_VLAN_CTAG_RX) + features |= NETIF_F_HW_VLAN_CTAG_TX; + else + features &= ~NETIF_F_HW_VLAN_CTAG_TX; + return features; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5ea22008d721..501f15d9f4d6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1344,6 +1344,13 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, if (!vsi || !macaddr) return NULL; + /* Do not allow broadcast filter to be added since broadcast filter + * is added as part of add VSI for any newly created VSI except + * FDIR VSI + */ + if (is_broadcast_ether_addr(macaddr)) + return NULL; + f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); @@ -2151,18 +2158,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) aq_ret, pf->hw.aq.asq_last_status); } } - aq_ret = i40e_aq_set_vsi_broadcast(&vsi->back->hw, - vsi->seid, - cur_promisc, NULL); - if (aq_ret) { - retval = i40e_aq_rc_to_posix(aq_ret, - pf->hw.aq.asq_last_status); - dev_info(&pf->pdev->dev, - "set brdcast promisc failed, err %s, aq_err %s\n", - i40e_stat_str(&pf->hw, aq_ret), - i40e_aq_str(&pf->hw, - pf->hw.aq.asq_last_status)); - } } out: /* if something went wrong then set the changed flag so we try again */ @@ -7726,10 +7721,11 @@ static int i40e_init_msix(struct i40e_pf *pf) * i40e_vsi_alloc_q_vector - Allocate memory for a single interrupt vector * @vsi: the VSI being configured * @v_idx: index of the vector in the vsi struct + * @cpu: cpu to be used on affinity_mask * * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ -static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx) +static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) { struct i40e_q_vector *q_vector; @@ -7740,7 +7736,8 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx) q_vector->vsi = vsi; q_vector->v_idx = v_idx; - cpumask_set_cpu(v_idx, &q_vector->affinity_mask); + cpumask_set_cpu(cpu, &q_vector->affinity_mask); + if (vsi->netdev) netif_napi_add(vsi->netdev, &q_vector->napi, i40e_napi_poll, NAPI_POLL_WEIGHT); @@ -7764,8 +7761,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx) static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - int v_idx, num_q_vectors; - int err; + int err, v_idx, num_q_vectors, current_cpu; /* if not MSIX, give the one vector only to the LAN VSI */ if (pf->flags & I40E_FLAG_MSIX_ENABLED) @@ -7775,10 +7771,15 @@ static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi) else return -EINVAL; + current_cpu = cpumask_first(cpu_online_mask); + for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { - err = i40e_vsi_alloc_q_vector(vsi, v_idx); + err = i40e_vsi_alloc_q_vector(vsi, v_idx, current_cpu); if (err) goto err_out; + current_cpu = cpumask_next(current_cpu, cpu_online_mask); + if (unlikely(current_cpu >= nr_cpu_ids)) + current_cpu = cpumask_first(cpu_online_mask); } return 0; @@ -9224,6 +9225,7 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi) static int i40e_add_vsi(struct i40e_vsi *vsi) { int ret = -ENODEV; + i40e_status aq_ret = 0; u8 laa_macaddr[ETH_ALEN]; bool found_laa_mac_filter = false; struct i40e_pf *pf = vsi->back; @@ -9413,6 +9415,18 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->seid = ctxt.seid; vsi->id = ctxt.vsi_number; } + /* Except FDIR VSI, for all othet VSI set the broadcast filter */ + if (vsi->type != I40E_VSI_FDIR) { + aq_ret = i40e_aq_set_vsi_broadcast(hw, vsi->seid, true, NULL); + if (aq_ret) { + ret = i40e_aq_rc_to_posix(aq_ret, + hw->aq.asq_last_status); + dev_info(&pf->pdev->dev, + "set brdcast promisc failed, err %s, aq_err %s\n", + i40e_stat_str(hw, aq_ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + } + } spin_lock_bh(&vsi->mac_filter_list_lock); /* If macvlan filters already exist, force them to get loaded */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 55f151fca1dc..a8868e1bf832 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1280,8 +1280,8 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, union i40e_rx_desc *rx_desc) { struct i40e_rx_ptype_decoded decoded; - bool ipv4, ipv6, tunnel = false; u32 rx_error, rx_status; + bool ipv4, ipv6; u8 ptype; u64 qword; @@ -1336,19 +1336,23 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* The hardware supported by this driver does not validate outer - * checksums for tunneled VXLAN or GENEVE frames. I don't agree - * with it but the specification states that you "MAY validate", it - * doesn't make it a hard requirement so if we have validated the - * inner checksum report CHECKSUM_UNNECESSARY. + /* If there is an outer header present that might contain a checksum + * we need to bump the checksum level by 1 to reflect the fact that + * we are indicating we validated the inner checksum. */ - if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP | - I40E_RX_PTYPE_INNER_PROT_UDP | - I40E_RX_PTYPE_INNER_PROT_SCTP)) - tunnel = true; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = tunnel ? 1 : 0; + if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT) + skb->csum_level = 1; + + /* Only report checksum unnecessary for TCP, UDP, or SCTP */ + switch (decoded.inner_prot) { + case I40E_RX_PTYPE_INNER_PROT_TCP: + case I40E_RX_PTYPE_INNER_PROT_UDP: + case I40E_RX_PTYPE_INNER_PROT_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + /* fall though */ + default: + break; + } return; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index be99189da925..79d99cd91b24 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -752,8 +752,8 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, union i40e_rx_desc *rx_desc) { struct i40e_rx_ptype_decoded decoded; - bool ipv4, ipv6, tunnel = false; u32 rx_error, rx_status; + bool ipv4, ipv6; u8 ptype; u64 qword; @@ -808,19 +808,23 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* The hardware supported by this driver does not validate outer - * checksums for tunneled VXLAN or GENEVE frames. I don't agree - * with it but the specification states that you "MAY validate", it - * doesn't make it a hard requirement so if we have validated the - * inner checksum report CHECKSUM_UNNECESSARY. + /* If there is an outer header present that might contain a checksum + * we need to bump the checksum level by 1 to reflect the fact that + * we are indicating we validated the inner checksum. */ - if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP | - I40E_RX_PTYPE_INNER_PROT_UDP | - I40E_RX_PTYPE_INNER_PROT_SCTP)) - tunnel = true; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = tunnel ? 1 : 0; + if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT) + skb->csum_level = 1; + + /* Only report checksum unnecessary for TCP, UDP, or SCTP */ + switch (decoded.inner_prot) { + case I40E_RX_PTYPE_INNER_PROT_TCP: + case I40E_RX_PTYPE_INNER_PROT_UDP: + case I40E_RX_PTYPE_INNER_PROT_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + /* fall though */ + default: + break; + } return; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 088c47cf27d9..8bebd862a54c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2887,7 +2887,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) if (!test_bit(__IXGBE_DOWN, &adapter->state)) ixgbe_irq_enable_queues(adapter, BIT_ULL(q_vector->v_idx)); - return 0; + return min(work_done, budget - 1); } /** diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c index 61a80da8b6f0..2819abc454c7 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.c +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c @@ -85,7 +85,7 @@ static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw) static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) { struct ixgbe_mbx_info *mbx = &hw->mbx; - s32 ret_val = -IXGBE_ERR_MBX; + s32 ret_val = IXGBE_ERR_MBX; if (!mbx->ops.read) goto out; @@ -111,7 +111,7 @@ out: static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) { struct ixgbe_mbx_info *mbx = &hw->mbx; - s32 ret_val = -IXGBE_ERR_MBX; + s32 ret_val = IXGBE_ERR_MBX; /* exit if either we can't write or there isn't a defined timeout */ if (!mbx->ops.write || !mbx->timeout) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index a6d26d351dfc..f92018b13d28 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -244,7 +244,7 @@ /* Various constants */ /* Coalescing */ -#define MVNETA_TXDONE_COAL_PKTS 1 +#define MVNETA_TXDONE_COAL_PKTS 0 /* interrupt per packet */ #define MVNETA_RX_COAL_PKTS 32 #define MVNETA_RX_COAL_USEC 100 @@ -3458,6 +3458,8 @@ static int mvneta_open(struct net_device *dev) return 0; err_free_irq: + unregister_cpu_notifier(&pp->cpu_notifier); + on_each_cpu(mvneta_percpu_disable, pp, true); free_percpu_irq(pp->dev->irq, pp->ports); err_cleanup_txqs: mvneta_cleanup_txqs(pp); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 4763252bbf85..d1cdc2d76151 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -481,20 +481,23 @@ static inline void mtk_rx_get_desc(struct mtk_rx_dma *rxd, /* the qdma core needs scratch memory to be setup */ static int mtk_init_fq_dma(struct mtk_eth *eth) { - dma_addr_t phy_ring_head, phy_ring_tail; + dma_addr_t phy_ring_tail; int cnt = MTK_DMA_SIZE; dma_addr_t dma_addr; int i; eth->scratch_ring = dma_alloc_coherent(eth->dev, cnt * sizeof(struct mtk_tx_dma), - &phy_ring_head, + ð->phy_scratch_ring, GFP_ATOMIC | __GFP_ZERO); if (unlikely(!eth->scratch_ring)) return -ENOMEM; eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE, GFP_KERNEL); + if (unlikely(!eth->scratch_head)) + return -ENOMEM; + dma_addr = dma_map_single(eth->dev, eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE, DMA_FROM_DEVICE); @@ -502,19 +505,19 @@ static int mtk_init_fq_dma(struct mtk_eth *eth) return -ENOMEM; memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt); - phy_ring_tail = phy_ring_head + + phy_ring_tail = eth->phy_scratch_ring + (sizeof(struct mtk_tx_dma) * (cnt - 1)); for (i = 0; i < cnt; i++) { eth->scratch_ring[i].txd1 = (dma_addr + (i * MTK_QDMA_PAGE_SIZE)); if (i < cnt - 1) - eth->scratch_ring[i].txd2 = (phy_ring_head + + eth->scratch_ring[i].txd2 = (eth->phy_scratch_ring + ((i + 1) * sizeof(struct mtk_tx_dma))); eth->scratch_ring[i].txd3 = TX_DMA_SDL(MTK_QDMA_PAGE_SIZE); } - mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD); + mtk_w32(eth, eth->phy_scratch_ring, MTK_QDMA_FQ_HEAD); mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL); mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT); mtk_w32(eth, MTK_QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN); @@ -671,7 +674,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, err_dma: do { - tx_buf = mtk_desc_to_tx_buf(ring, txd); + tx_buf = mtk_desc_to_tx_buf(ring, itxd); /* unmap dma */ mtk_tx_unmap(&dev->dev, tx_buf); @@ -701,6 +704,20 @@ static inline int mtk_cal_txd_req(struct sk_buff *skb) return nfrags; } +static int mtk_queue_stopped(struct mtk_eth *eth) +{ + int i; + + for (i = 0; i < MTK_MAC_COUNT; i++) { + if (!eth->netdev[i]) + continue; + if (netif_queue_stopped(eth->netdev[i])) + return 1; + } + + return 0; +} + static void mtk_wake_queue(struct mtk_eth *eth) { int i; @@ -766,12 +783,9 @@ static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev) if (mtk_tx_map(skb, dev, tx_num, ring, gso) < 0) goto drop; - if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) { + if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) mtk_stop_queue(eth); - if (unlikely(atomic_read(&ring->free_count) > - ring->thresh)) - mtk_wake_queue(eth); - } + spin_unlock_irqrestore(ð->page_lock, flags); return NETDEV_TX_OK; @@ -826,6 +840,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) { skb_free_frag(new_data); + netdev->stats.rx_dropped++; goto release_desc; } @@ -833,6 +848,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, skb = build_skb(data, ring->frag_size); if (unlikely(!skb)) { put_page(virt_to_head_page(new_data)); + netdev->stats.rx_dropped++; goto release_desc; } skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); @@ -921,7 +937,6 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again) } mtk_tx_unmap(eth->dev, tx_buf); - ring->last_free->txd2 = next_cpu; ring->last_free = desc; atomic_inc(&ring->free_count); @@ -946,7 +961,8 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again) if (!total) return 0; - if (atomic_read(&ring->free_count) > ring->thresh) + if (mtk_queue_stopped(eth) && + (atomic_read(&ring->free_count) > ring->thresh)) mtk_wake_queue(eth); return total; @@ -1027,9 +1043,8 @@ static int mtk_tx_alloc(struct mtk_eth *eth) atomic_set(&ring->free_count, MTK_DMA_SIZE - 2); ring->next_free = &ring->dma[0]; - ring->last_free = &ring->dma[MTK_DMA_SIZE - 2]; - ring->thresh = max((unsigned long)MTK_DMA_SIZE >> 2, - MAX_SKB_FRAGS); + ring->last_free = &ring->dma[MTK_DMA_SIZE - 1]; + ring->thresh = MAX_SKB_FRAGS; /* make sure that all changes to the dma ring are flushed before we * continue @@ -1207,6 +1222,14 @@ static void mtk_dma_free(struct mtk_eth *eth) for (i = 0; i < MTK_MAC_COUNT; i++) if (eth->netdev[i]) netdev_reset_queue(eth->netdev[i]); + if (eth->scratch_ring) { + dma_free_coherent(eth->dev, + MTK_DMA_SIZE * sizeof(struct mtk_tx_dma), + eth->scratch_ring, + eth->phy_scratch_ring); + eth->scratch_ring = NULL; + eth->phy_scratch_ring = 0; + } mtk_tx_clean(eth); mtk_rx_clean(eth); kfree(eth->scratch_head); @@ -1269,7 +1292,7 @@ static int mtk_start_dma(struct mtk_eth *eth) mtk_w32(eth, MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN | MTK_RX_2B_OFFSET | MTK_DMA_SIZE_16DWORDS | - MTK_RX_BT_32DWORDS, + MTK_RX_BT_32DWORDS | MTK_NDP_CO_PRO, MTK_QDMA_GLO_CFG); return 0; @@ -1383,7 +1406,7 @@ static int __init mtk_hw_init(struct mtk_eth *eth) /* disable delay and normal interrupt */ mtk_w32(eth, 0, MTK_QDMA_DELAY_INT); - mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT); + mtk_irq_disable(eth, ~0); mtk_w32(eth, RST_GL_PSE, MTK_RST_GL); mtk_w32(eth, 0, MTK_RST_GL); @@ -1697,7 +1720,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET; SET_NETDEV_DEV(eth->netdev[id], eth->dev); - eth->netdev[id]->watchdog_timeo = HZ; + eth->netdev[id]->watchdog_timeo = 5 * HZ; eth->netdev[id]->netdev_ops = &mtk_netdev_ops; eth->netdev[id]->base_addr = (unsigned long)eth->base; eth->netdev[id]->vlan_features = MTK_HW_FEATURES & diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index eed626d56ea4..a5eb7c62306b 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -91,6 +91,7 @@ #define MTK_QDMA_GLO_CFG 0x1A04 #define MTK_RX_2B_OFFSET BIT(31) #define MTK_RX_BT_32DWORDS (3 << 11) +#define MTK_NDP_CO_PRO BIT(10) #define MTK_TX_WB_DDONE BIT(6) #define MTK_DMA_SIZE_16DWORDS (2 << 4) #define MTK_RX_DMA_BUSY BIT(3) @@ -357,6 +358,7 @@ struct mtk_rx_ring { * @rx_ring: Pointer to the memore holding info about the RX ring * @rx_napi: The NAPI struct * @scratch_ring: Newer SoCs need memory for a second HW managed TX ring + * @phy_scratch_ring: physical address of scratch_ring * @scratch_head: The scratch memory that scratch_ring points to. * @clk_ethif: The ethif clock * @clk_esw: The switch clock @@ -384,6 +386,7 @@ struct mtk_eth { struct mtk_rx_ring rx_ring; struct napi_struct rx_napi; struct mtk_tx_dma *scratch_ring; + dma_addr_t phy_scratch_ring; void *scratch_head; struct clk *clk_ethif; struct clk *clk_esw; diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index e94ca1c3fc7c..f04a423ff79d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2597,7 +2597,6 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev) priv->cmd.free_head = 0; sema_init(&priv->cmd.event_sem, priv->cmd.max_cmds); - spin_lock_init(&priv->cmd.context_lock); for (priv->cmd.token_mask = 1; priv->cmd.token_mask < priv->cmd.max_cmds; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index fc95affaf76b..44cf16d01f42 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1042,6 +1042,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; u32 rx_size, tx_size; int port_up = 0; int err = 0; @@ -1061,22 +1063,25 @@ static int mlx4_en_set_ringparam(struct net_device *dev, tx_size == priv->tx_ring[0]->size) return 0; + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + mutex_lock(&mdev->state_lock); + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + new_prof.tx_ring_size = tx_size; + new_prof.rx_ring_size = rx_size; + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + if (err) + goto out; + if (priv->port_up) { port_up = 1; mlx4_en_stop_port(dev, 1); } - mlx4_en_free_resources(priv); - - priv->prof->tx_ring_size = tx_size; - priv->prof->rx_ring_size = rx_size; + mlx4_en_safe_replace_resources(priv, tmp); - err = mlx4_en_alloc_resources(priv); - if (err) { - en_err(priv, "Failed reallocating port resources\n"); - goto out; - } if (port_up) { err = mlx4_en_start_port(dev); if (err) @@ -1084,8 +1089,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev, } err = mlx4_en_moderation_update(priv); - out: + kfree(tmp); mutex_unlock(&mdev->state_lock); return err; } @@ -1714,6 +1719,8 @@ static int mlx4_en_set_channels(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; int port_up = 0; int err = 0; @@ -1723,23 +1730,26 @@ static int mlx4_en_set_channels(struct net_device *dev, !channel->tx_count || !channel->rx_count) return -EINVAL; + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + mutex_lock(&mdev->state_lock); + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + new_prof.num_tx_rings_p_up = channel->tx_count; + new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP; + new_prof.rx_ring_num = channel->rx_count; + + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + if (err) + goto out; + if (priv->port_up) { port_up = 1; mlx4_en_stop_port(dev, 1); } - mlx4_en_free_resources(priv); - - priv->num_tx_rings_p_up = channel->tx_count; - priv->tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP; - priv->rx_ring_num = channel->rx_count; - - err = mlx4_en_alloc_resources(priv); - if (err) { - en_err(priv, "Failed reallocating port resources\n"); - goto out; - } + mlx4_en_safe_replace_resources(priv, tmp); netif_set_real_num_tx_queues(dev, priv->tx_ring_num); netif_set_real_num_rx_queues(dev, priv->rx_ring_num); @@ -1757,8 +1767,8 @@ static int mlx4_en_set_channels(struct net_device *dev, } err = mlx4_en_moderation_update(priv); - out: + kfree(tmp); mutex_unlock(&mdev->state_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 19ceced6736c..8359e9e51b3b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -406,14 +406,18 @@ static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, mutex_lock(&mdev->state_lock); if (mdev->device_up && priv->port_up) { err = mlx4_SET_VLAN_FLTR(mdev->dev, priv); - if (err) + if (err) { en_err(priv, "Failed configuring VLAN filter\n"); + goto out; + } } - if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx)) - en_dbg(HW, priv, "failed adding vlan %d\n", vid); - mutex_unlock(&mdev->state_lock); + err = mlx4_register_vlan(mdev->dev, priv->port, vid, &idx); + if (err) + en_dbg(HW, priv, "Failed adding vlan %d\n", vid); - return 0; +out: + mutex_unlock(&mdev->state_lock); + return err; } static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, @@ -421,7 +425,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - int err; + int err = 0; en_dbg(HW, priv, "Killing VID:%d\n", vid); @@ -438,7 +442,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, } mutex_unlock(&mdev->state_lock); - return 0; + return err; } static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac) @@ -1950,7 +1954,7 @@ static int mlx4_en_close(struct net_device *dev) return 0; } -void mlx4_en_free_resources(struct mlx4_en_priv *priv) +static void mlx4_en_free_resources(struct mlx4_en_priv *priv) { int i; @@ -1975,7 +1979,7 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv) } -int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) +static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) { struct mlx4_en_port_profile *prof = priv->prof; int i; @@ -2032,11 +2036,91 @@ err: return -ENOMEM; } +static void mlx4_en_shutdown(struct net_device *dev) +{ + rtnl_lock(); + netif_device_detach(dev); + mlx4_en_close(dev); + rtnl_unlock(); +} + +static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, + struct mlx4_en_priv *src, + struct mlx4_en_port_profile *prof) +{ + memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config, + sizeof(dst->hwtstamp_config)); + dst->num_tx_rings_p_up = src->mdev->profile.num_tx_rings_p_up; + dst->tx_ring_num = prof->tx_ring_num; + dst->rx_ring_num = prof->rx_ring_num; + dst->flags = prof->flags; + dst->mdev = src->mdev; + dst->port = src->port; + dst->dev = src->dev; + dst->prof = prof; + dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) + + DS_SIZE * MLX4_EN_MAX_RX_FRAGS); + + dst->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS, + GFP_KERNEL); + if (!dst->tx_ring) + return -ENOMEM; + + dst->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS, + GFP_KERNEL); + if (!dst->tx_cq) { + kfree(dst->tx_ring); + return -ENOMEM; + } + return 0; +} + +static void mlx4_en_update_priv(struct mlx4_en_priv *dst, + struct mlx4_en_priv *src) +{ + memcpy(dst->rx_ring, src->rx_ring, + sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num); + memcpy(dst->rx_cq, src->rx_cq, + sizeof(struct mlx4_en_cq *) * src->rx_ring_num); + memcpy(&dst->hwtstamp_config, &src->hwtstamp_config, + sizeof(dst->hwtstamp_config)); + dst->tx_ring_num = src->tx_ring_num; + dst->rx_ring_num = src->rx_ring_num; + dst->tx_ring = src->tx_ring; + dst->tx_cq = src->tx_cq; + memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile)); +} + +int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp, + struct mlx4_en_port_profile *prof) +{ + mlx4_en_copy_priv(tmp, priv, prof); + + if (mlx4_en_alloc_resources(tmp)) { + en_warn(priv, + "%s: Resource allocation failed, using previous configuration\n", + __func__); + kfree(tmp->tx_ring); + kfree(tmp->tx_cq); + return -ENOMEM; + } + return 0; +} + +void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp) +{ + mlx4_en_free_resources(priv); + mlx4_en_update_priv(priv, tmp); +} void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + bool shutdown = mdev->dev->persist->interface_state & + MLX4_INTERFACE_STATE_SHUTDOWN; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2044,7 +2128,10 @@ void mlx4_en_destroy_netdev(struct net_device *dev) if (priv->registered) { devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, priv->port)); - unregister_netdev(dev); + if (shutdown) + mlx4_en_shutdown(dev); + else + unregister_netdev(dev); } if (priv->allocated) @@ -2064,12 +2151,17 @@ void mlx4_en_destroy_netdev(struct net_device *dev) mdev->upper[priv->port] = NULL; mutex_unlock(&mdev->state_lock); +#ifdef CONFIG_RFS_ACCEL + mlx4_en_cleanup_filters(priv); +#endif + mlx4_en_free_resources(priv); kfree(priv->tx_ring); kfree(priv->tx_cq); - free_netdev(dev); + if (!shutdown) + free_netdev(dev); } static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) @@ -2447,9 +2539,14 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb, * strip that feature if this is an IPv6 encapsulated frame. */ if (skb->encapsulation && - (skb->ip_summed == CHECKSUM_PARTIAL) && - (ip_hdr(skb)->version != 4)) - features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + (skb->ip_summed == CHECKSUM_PARTIAL)) { + struct mlx4_en_priv *priv = netdev_priv(dev); + + if (!priv->vxlan_port || + (ip_hdr(skb)->version != 4) || + (udp_hdr(skb)->dest != priv->vxlan_port)) + features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } return features; } @@ -3102,6 +3199,8 @@ int mlx4_en_reset_config(struct net_device *dev, { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_port_profile new_prof; + struct mlx4_en_priv *tmp; int port_up = 0; int err = 0; @@ -3118,19 +3217,29 @@ int mlx4_en_reset_config(struct net_device *dev, return -EINVAL; } + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + mutex_lock(&mdev->state_lock); + + memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); + memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config)); + + err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof); + if (err) + goto out; + if (priv->port_up) { port_up = 1; mlx4_en_stop_port(dev, 1); } - mlx4_en_free_resources(priv); - en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n", - ts_config.rx_filter, !!(features & NETIF_F_HW_VLAN_CTAG_RX)); + ts_config.rx_filter, + !!(features & NETIF_F_HW_VLAN_CTAG_RX)); - priv->hwtstamp_config.tx_type = ts_config.tx_type; - priv->hwtstamp_config.rx_filter = ts_config.rx_filter; + mlx4_en_safe_replace_resources(priv, tmp); if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) { if (features & NETIF_F_HW_VLAN_CTAG_RX) @@ -3164,11 +3273,6 @@ int mlx4_en_reset_config(struct net_device *dev, dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; } - err = mlx4_en_alloc_resources(priv); - if (err) { - en_err(priv, "Failed reallocating port resources\n"); - goto out; - } if (port_up) { err = mlx4_en_start_port(dev); if (err) @@ -3177,6 +3281,8 @@ int mlx4_en_reset_config(struct net_device *dev, out: mutex_unlock(&mdev->state_lock); - netdev_features_change(dev); + kfree(tmp); + if (!err) + netdev_features_change(dev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index c1b3a9c8cf3b..99b5407f2278 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -514,9 +514,6 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, ring->rx_info = NULL; kfree(ring); *pring = NULL; -#ifdef CONFIG_RFS_ACCEL - mlx4_en_cleanup_filters(priv); -#endif } void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 12c77a70abdb..546fab0ecc3b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3222,6 +3222,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data, INIT_LIST_HEAD(&priv->pgdir_list); mutex_init(&priv->pgdir_mutex); + spin_lock_init(&priv->cmd.context_lock); INIT_LIST_HEAD(&priv->bf_list); mutex_init(&priv->bf_mutex); @@ -4134,8 +4135,11 @@ static void mlx4_shutdown(struct pci_dev *pdev) mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); - if (persist->interface_state & MLX4_INTERFACE_STATE_UP) + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) { + /* Notify mlx4 clients that the kernel is being shut down */ + persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN; mlx4_unload_one(pdev); + } mutex_unlock(&persist->interface_state_mutex); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 467d47ed2c39..13d297ee34bb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -353,12 +353,14 @@ struct mlx4_en_port_profile { u32 rx_ring_num; u32 tx_ring_size; u32 rx_ring_size; + u8 num_tx_rings_p_up; u8 rx_pause; u8 rx_ppp; u8 tx_pause; u8 tx_ppp; int rss_rings; int inline_thold; + struct hwtstamp_config hwtstamp_config; }; struct mlx4_en_profile { @@ -623,8 +625,11 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, u8 rx_ppp, u8 rx_pause, u8 tx_ppp, u8 tx_pause); -void mlx4_en_free_resources(struct mlx4_en_priv *priv); -int mlx4_en_alloc_resources(struct mlx4_en_priv *priv); +int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp, + struct mlx4_en_port_profile *prof); +void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv, + struct mlx4_en_priv *tmp); int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq, int entries, int ring, enum cq_type mode, int node); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index dcd2df6518de..d6e2a1cae19a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -295,6 +295,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_DESTROY_FLOW_GROUP: case MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY: case MLX5_CMD_OP_DEALLOC_FLOW_COUNTER: + case MLX5_CMD_OP_2ERR_QP: + case MLX5_CMD_OP_2RST_QP: + case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT: + case MLX5_CMD_OP_MODIFY_FLOW_TABLE: + case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY: + case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -321,8 +327,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_RTR2RTS_QP: case MLX5_CMD_OP_RTS2RTS_QP: case MLX5_CMD_OP_SQERR2RTS_QP: - case MLX5_CMD_OP_2ERR_QP: - case MLX5_CMD_OP_2RST_QP: case MLX5_CMD_OP_QUERY_QP: case MLX5_CMD_OP_SQD_RTS_QP: case MLX5_CMD_OP_INIT2INIT_QP: @@ -342,7 +346,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT: case MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT: case MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT: - case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT: case MLX5_CMD_OP_QUERY_ROCE_ADDRESS: case MLX5_CMD_OP_SET_ROCE_ADDRESS: case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT: @@ -390,11 +393,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_CREATE_RQT: case MLX5_CMD_OP_MODIFY_RQT: case MLX5_CMD_OP_QUERY_RQT: + case MLX5_CMD_OP_CREATE_FLOW_TABLE: case MLX5_CMD_OP_QUERY_FLOW_TABLE: case MLX5_CMD_OP_CREATE_FLOW_GROUP: case MLX5_CMD_OP_QUERY_FLOW_GROUP: - case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY: + case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY: case MLX5_CMD_OP_ALLOC_FLOW_COUNTER: case MLX5_CMD_OP_QUERY_FLOW_COUNTER: @@ -545,6 +549,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(ALLOC_FLOW_COUNTER); MLX5_COMMAND_STR_CASE(DEALLOC_FLOW_COUNTER); MLX5_COMMAND_STR_CASE(QUERY_FLOW_COUNTER); + MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE); default: return "unknown command opcode"; } } @@ -601,11 +606,36 @@ static void dump_command(struct mlx5_core_dev *dev, pr_debug("\n"); } +static u16 msg_to_opcode(struct mlx5_cmd_msg *in) +{ + struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data); + + return be16_to_cpu(hdr->opcode); +} + +static void cb_timeout_handler(struct work_struct *work) +{ + struct delayed_work *dwork = container_of(work, struct delayed_work, + work); + struct mlx5_cmd_work_ent *ent = container_of(dwork, + struct mlx5_cmd_work_ent, + cb_timeout_work); + struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, + cmd); + + ent->ret = -ETIMEDOUT; + mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", + mlx5_command_str(msg_to_opcode(ent->in)), + msg_to_opcode(ent->in)); + mlx5_cmd_comp_handler(dev, 1UL << ent->idx); +} + static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); struct mlx5_cmd *cmd = ent->cmd; struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd); + unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); struct mlx5_cmd_layout *lay; struct semaphore *sem; unsigned long flags; @@ -646,6 +676,9 @@ static void cmd_work_handler(struct work_struct *work) dump_command(dev, ent, 1); ent->ts1 = ktime_get_ns(); + if (ent->callback) + schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -690,13 +723,6 @@ static const char *deliv_status_to_str(u8 status) } } -static u16 msg_to_opcode(struct mlx5_cmd_msg *in) -{ - struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data); - - return be16_to_cpu(hdr->opcode); -} - static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); @@ -705,13 +731,13 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) if (cmd->mode == CMD_MODE_POLLING) { wait_for_completion(&ent->done); - err = ent->ret; - } else { - if (!wait_for_completion_timeout(&ent->done, timeout)) - err = -ETIMEDOUT; - else - err = 0; + } else if (!wait_for_completion_timeout(&ent->done, timeout)) { + ent->ret = -ETIMEDOUT; + mlx5_cmd_comp_handler(dev, 1UL << ent->idx); } + + err = ent->ret; + if (err == -ETIMEDOUT) { mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", mlx5_command_str(msg_to_opcode(ent->in)), @@ -760,6 +786,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (!callback) init_completion(&ent->done); + INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler); INIT_WORK(&ent->work, cmd_work_handler); if (page_queue) { cmd_work_handler(&ent->work); @@ -769,28 +796,26 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, goto out_free; } - if (!callback) { - err = wait_func(dev, ent); - if (err == -ETIMEDOUT) - goto out; - - ds = ent->ts2 - ent->ts1; - op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode); - if (op < ARRAY_SIZE(cmd->stats)) { - stats = &cmd->stats[op]; - spin_lock_irq(&stats->lock); - stats->sum += ds; - ++stats->n; - spin_unlock_irq(&stats->lock); - } - mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME, - "fw exec time for %s is %lld nsec\n", - mlx5_command_str(op), ds); - *status = ent->status; - free_cmd(ent); - } + if (callback) + goto out; - return err; + err = wait_func(dev, ent); + if (err == -ETIMEDOUT) + goto out_free; + + ds = ent->ts2 - ent->ts1; + op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode); + if (op < ARRAY_SIZE(cmd->stats)) { + stats = &cmd->stats[op]; + spin_lock_irq(&stats->lock); + stats->sum += ds; + ++stats->n; + spin_unlock_irq(&stats->lock); + } + mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME, + "fw exec time for %s is %lld nsec\n", + mlx5_command_str(op), ds); + *status = ent->status; out_free: free_cmd(ent); @@ -1180,41 +1205,30 @@ err_dbg: return err; } -void mlx5_cmd_use_events(struct mlx5_core_dev *dev) +static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) { struct mlx5_cmd *cmd = &dev->cmd; int i; for (i = 0; i < cmd->max_reg_cmds; i++) down(&cmd->sem); - down(&cmd->pages_sem); - flush_workqueue(cmd->wq); - - cmd->mode = CMD_MODE_EVENTS; + cmd->mode = mode; up(&cmd->pages_sem); for (i = 0; i < cmd->max_reg_cmds; i++) up(&cmd->sem); } -void mlx5_cmd_use_polling(struct mlx5_core_dev *dev) +void mlx5_cmd_use_events(struct mlx5_core_dev *dev) { - struct mlx5_cmd *cmd = &dev->cmd; - int i; - - for (i = 0; i < cmd->max_reg_cmds; i++) - down(&cmd->sem); - - down(&cmd->pages_sem); - - flush_workqueue(cmd->wq); - cmd->mode = CMD_MODE_POLLING; + mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS); +} - up(&cmd->pages_sem); - for (i = 0; i < cmd->max_reg_cmds; i++) - up(&cmd->sem); +void mlx5_cmd_use_polling(struct mlx5_core_dev *dev) +{ + mlx5_cmd_change_mod(dev, CMD_MODE_POLLING); } static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg) @@ -1250,6 +1264,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec) struct semaphore *sem; ent = cmd->ent_arr[i]; + if (ent->callback) + cancel_delayed_work(&ent->cb_timeout_work); if (ent->page_queue) sem = &cmd->pages_sem; else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index e8a6c3325b39..943b1bd434bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -145,7 +145,6 @@ struct mlx5e_umr_wqe { #ifdef CONFIG_MLX5_CORE_EN_DCB #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */ -#define MLX5E_MIN_BW_ALLOC 1 /* Min percentage of BW allocation */ #endif struct mlx5e_params { @@ -191,6 +190,7 @@ struct mlx5e_tstamp { enum { MLX5E_RQ_STATE_POST_WQES_ENABLE, MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, + MLX5E_RQ_STATE_FLUSH_TIMEOUT, }; struct mlx5e_cq { @@ -220,6 +220,8 @@ typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq, typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix); +typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix); + struct mlx5e_dma_info { struct page *page; dma_addr_t addr; @@ -241,6 +243,7 @@ struct mlx5e_rq { struct mlx5e_cq cq; mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_alloc_wqe alloc_wqe; + mlx5e_fp_dealloc_wqe dealloc_wqe; unsigned long state; int ix; @@ -305,6 +308,7 @@ struct mlx5e_sq_dma { enum { MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, MLX5E_SQ_STATE_BF_ENABLE, + MLX5E_SQ_STATE_TX_TIMEOUT, }; struct mlx5e_ico_wqe_info { @@ -401,7 +405,7 @@ enum mlx5e_traffic_types { }; enum { - MLX5E_STATE_ASYNC_EVENTS_ENABLE, + MLX5E_STATE_ASYNC_EVENTS_ENABLED, MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, }; @@ -538,6 +542,7 @@ struct mlx5e_priv { struct workqueue_struct *wq; struct work_struct update_carrier_work; struct work_struct set_rx_mode_work; + struct work_struct tx_timeout_work; struct delayed_work update_stats_work; struct mlx5_core_dev *mdev; @@ -589,12 +594,16 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); int mlx5e_napi_poll(struct napi_struct *napi, int budget); bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); +void mlx5e_free_tx_descs(struct mlx5e_sq *sq); +void mlx5e_free_rx_descs(struct mlx5e_rq *rq); void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix); int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix); +void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix); +void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix); void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq); void mlx5e_complete_rx_linear_mpwqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index b2db180ae2a5..c585349e05c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -96,7 +96,7 @@ static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw, tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; break; case IEEE_8021QAZ_TSA_ETS: - tc_tx_bw[i] = ets->tc_tx_bw[i] ?: MLX5E_MIN_BW_ALLOC; + tc_tx_bw[i] = ets->tc_tx_bw[i]; break; } } @@ -140,8 +140,12 @@ static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets) /* Validate Bandwidth Sum */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { + if (!ets->tc_tx_bw[i]) + return -EINVAL; + bw_sum += ets->tc_tx_bw[i]; + } } if (bw_sum != 0 && bw_sum != 100) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index fc7dcc03b1de..e667a870e0c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -184,7 +184,9 @@ static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv) #define MLX5E_NUM_SQ_STATS(priv) \ (NUM_SQ_STATS * priv->params.num_channels * priv->params.num_tc * \ test_bit(MLX5E_STATE_OPENED, &priv->state)) -#define MLX5E_NUM_PFC_COUNTERS(priv) hweight8(mlx5e_query_pfc_combined(priv)) +#define MLX5E_NUM_PFC_COUNTERS(priv) \ + (hweight8(mlx5e_query_pfc_combined(priv)) * \ + NUM_PPORT_PER_PRIO_PFC_COUNTERS) static int mlx5e_get_sset_count(struct net_device *dev, int sset) { @@ -211,42 +213,41 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) /* SW counters */ for (i = 0; i < NUM_SW_COUNTERS; i++) - strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].name); + strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].format); /* Q counters */ for (i = 0; i < MLX5E_NUM_Q_CNTRS(priv); i++) - strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].name); + strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format); /* VPORT counters */ for (i = 0; i < NUM_VPORT_COUNTERS; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - vport_stats_desc[i].name); + vport_stats_desc[i].format); /* PPORT counters */ for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - pport_802_3_stats_desc[i].name); + pport_802_3_stats_desc[i].format); for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - pport_2863_stats_desc[i].name); + pport_2863_stats_desc[i].format); for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - pport_2819_stats_desc[i].name); + pport_2819_stats_desc[i].format); for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++) - sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s", - prio, - pport_per_prio_traffic_stats_desc[i].name); + sprintf(data + (idx++) * ETH_GSTRING_LEN, + pport_per_prio_traffic_stats_desc[i].format, prio); } pfc_combined = mlx5e_query_pfc_combined(priv); for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) { for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) { - sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s", - prio, pport_per_prio_pfc_stats_desc[i].name); + sprintf(data + (idx++) * ETH_GSTRING_LEN, + pport_per_prio_pfc_stats_desc[i].format, prio); } } @@ -256,16 +257,15 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) /* per channel counters */ for (i = 0; i < priv->params.num_channels; i++) for (j = 0; j < NUM_RQ_STATS; j++) - sprintf(data + (idx++) * ETH_GSTRING_LEN, "rx%d_%s", i, - rq_stats_desc[j].name); + sprintf(data + (idx++) * ETH_GSTRING_LEN, + rq_stats_desc[j].format, i); for (tc = 0; tc < priv->params.num_tc; tc++) for (i = 0; i < priv->params.num_channels; i++) for (j = 0; j < NUM_SQ_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, - "tx%d_%s", - priv->channeltc_to_txq_map[i][tc], - sq_stats_desc[j].name); + sq_stats_desc[j].format, + priv->channeltc_to_txq_map[i][tc]); } static void mlx5e_get_strings(struct net_device *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f5c8d5db25a8..5a4d88c2cdb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -39,6 +39,13 @@ #include "eswitch.h" #include "vxlan.h" +enum { + MLX5_EN_QP_FLUSH_TIMEOUT_MS = 5000, + MLX5_EN_QP_FLUSH_MSLEEP_QUANT = 20, + MLX5_EN_QP_FLUSH_MAX_ITER = MLX5_EN_QP_FLUSH_TIMEOUT_MS / + MLX5_EN_QP_FLUSH_MSLEEP_QUANT, +}; + struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; struct mlx5_wq_param wq; @@ -74,10 +81,13 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv) port_state = mlx5_query_vport_state(mdev, MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0); - if (port_state == VPORT_STATE_UP) + if (port_state == VPORT_STATE_UP) { + netdev_info(priv->netdev, "Link up\n"); netif_carrier_on(priv->netdev); - else + } else { + netdev_info(priv->netdev, "Link down\n"); netif_carrier_off(priv->netdev); + } } static void mlx5e_update_carrier_work(struct work_struct *work) @@ -91,6 +101,26 @@ static void mlx5e_update_carrier_work(struct work_struct *work) mutex_unlock(&priv->state_lock); } +static void mlx5e_tx_timeout_work(struct work_struct *work) +{ + struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, + tx_timeout_work); + int err; + + rtnl_lock(); + mutex_lock(&priv->state_lock); + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + mlx5e_close_locked(priv->netdev); + err = mlx5e_open_locked(priv->netdev); + if (err) + netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n", + err); +unlock: + mutex_unlock(&priv->state_lock); + rtnl_unlock(); +} + static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) { struct mlx5e_sw_stats *s = &priv->stats.sw; @@ -105,11 +135,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->rx_packets += rq_stats->packets; s->rx_bytes += rq_stats->bytes; - s->lro_packets += rq_stats->lro_packets; - s->lro_bytes += rq_stats->lro_bytes; + s->rx_lro_packets += rq_stats->lro_packets; + s->rx_lro_bytes += rq_stats->lro_bytes; s->rx_csum_none += rq_stats->csum_none; - s->rx_csum_sw += rq_stats->csum_sw; - s->rx_csum_inner += rq_stats->csum_inner; + s->rx_csum_complete += rq_stats->csum_complete; + s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; s->rx_wqe_err += rq_stats->wqe_err; s->rx_mpwqe_filler += rq_stats->mpwqe_filler; s->rx_mpwqe_frag += rq_stats->mpwqe_frag; @@ -122,24 +152,23 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->tx_packets += sq_stats->packets; s->tx_bytes += sq_stats->bytes; - s->tso_packets += sq_stats->tso_packets; - s->tso_bytes += sq_stats->tso_bytes; - s->tso_inner_packets += sq_stats->tso_inner_packets; - s->tso_inner_bytes += sq_stats->tso_inner_bytes; + s->tx_tso_packets += sq_stats->tso_packets; + s->tx_tso_bytes += sq_stats->tso_bytes; + s->tx_tso_inner_packets += sq_stats->tso_inner_packets; + s->tx_tso_inner_bytes += sq_stats->tso_inner_bytes; s->tx_queue_stopped += sq_stats->stopped; s->tx_queue_wake += sq_stats->wake; s->tx_queue_dropped += sq_stats->dropped; - s->tx_csum_inner += sq_stats->csum_offload_inner; - tx_offload_none += sq_stats->csum_offload_none; + s->tx_csum_partial_inner += sq_stats->csum_partial_inner; + tx_offload_none += sq_stats->csum_none; } } /* Update calculated offload counters */ - s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner; - s->rx_csum_good = s->rx_packets - s->rx_csum_none - - s->rx_csum_sw; + s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner; + s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete; - s->link_down_events = MLX5_GET(ppcnt_reg, + s->link_down_events_phy = MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters, counter_set.phys_layer_cntrs.link_down_events); } @@ -244,7 +273,7 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, { struct mlx5e_priv *priv = vpriv; - if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state)) + if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state)) return; switch (event) { @@ -260,12 +289,12 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, static void mlx5e_enable_async_events(struct mlx5e_priv *priv) { - set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state); + set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state); } static void mlx5e_disable_async_events(struct mlx5e_priv *priv) { - clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state); + clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state); synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC)); } @@ -306,6 +335,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, } rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq; rq->alloc_wqe = mlx5e_alloc_rx_mpwqe; + rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz); rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides); @@ -321,6 +351,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, } rq->handle_rx_cqe = mlx5e_handle_rx_cqe; rq->alloc_wqe = mlx5e_alloc_rx_wqe; + rq->dealloc_wqe = mlx5e_dealloc_rx_wqe; rq->wqe_sz = (priv->params.lro_en) ? priv->params.lro_wqe_sz : @@ -526,17 +557,25 @@ err_destroy_rq: static void mlx5e_close_rq(struct mlx5e_rq *rq) { + int tout = 0; + int err; + clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state); napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ - mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR); - while (!mlx5_wq_ll_is_empty(&rq->wq)) - msleep(20); + err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR); + while (!mlx5_wq_ll_is_empty(&rq->wq) && !err && + tout++ < MLX5_EN_QP_FLUSH_MAX_ITER) + msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT); + + if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER) + set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state); /* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */ napi_synchronize(&rq->channel->napi); mlx5e_disable_rq(rq); + mlx5e_free_rx_descs(rq); mlx5e_destroy_rq(rq); } @@ -580,7 +619,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq); int err; - err = mlx5_alloc_map_uar(mdev, &sq->uar, true); + err = mlx5_alloc_map_uar(mdev, &sq->uar, !!MLX5_CAP_GEN(mdev, bf)); if (err) return err; @@ -783,6 +822,9 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_close_sq(struct mlx5e_sq *sq) { + int tout = 0; + int err; + if (sq->txq) { clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state); /* prevent netif_tx_wake_queue */ @@ -793,15 +835,24 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq) if (mlx5e_sq_has_room_for(sq, 1)) mlx5e_send_nop(sq, true); - mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR); + err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, + MLX5_SQC_STATE_ERR); + if (err) + set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); } - while (sq->cc != sq->pc) /* wait till sq is empty */ - msleep(20); + /* wait till sq is empty, unless a TX timeout occurred on this SQ */ + while (sq->cc != sq->pc && + !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) { + msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT); + if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER) + set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); + } /* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */ napi_synchronize(&sq->channel->napi); + mlx5e_free_tx_descs(sq); mlx5e_disable_sq(sq); mlx5e_destroy_sq(sq); } @@ -1297,6 +1348,11 @@ static int mlx5e_open_channels(struct mlx5e_priv *priv) goto err_close_channels; } + /* FIXME: This is a W/A for tx timeout watch dog false alarm when + * polling for inactive tx queues. + */ + netif_tx_start_all_queues(priv->netdev); + kfree(cparam); return 0; @@ -1316,6 +1372,12 @@ static void mlx5e_close_channels(struct mlx5e_priv *priv) { int i; + /* FIXME: This is a W/A only for tx timeout watch dog false alarm when + * polling for inactive tx queues. + */ + netif_tx_stop_all_queues(priv->netdev); + netif_tx_disable(priv->netdev); + for (i = 0; i < priv->params.num_channels; i++) mlx5e_close_channel(priv->channel[i]); @@ -1659,8 +1721,11 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) netdev_set_num_tc(netdev, ntc); + /* Map netdev TCs to offset 0 + * We have our own UP to TXQ mapping for QoS + */ for (tc = 0; tc < ntc; tc++) - netdev_set_tc_queue(netdev, tc, nch, tc * nch); + netdev_set_tc_queue(netdev, tc, nch, 0); } int mlx5e_open_locked(struct net_device *netdev) @@ -2591,6 +2656,29 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb, return features; } +static void mlx5e_tx_timeout(struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + bool sched_work = false; + int i; + + netdev_err(dev, "TX timeout detected\n"); + + for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) { + struct mlx5e_sq *sq = priv->txq_to_sq_map[i]; + + if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i))) + continue; + sched_work = true; + set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); + netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n", + i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc); + } + + if (sched_work && test_bit(MLX5E_STATE_OPENED, &priv->state)) + schedule_work(&priv->tx_timeout_work); +} + static const struct net_device_ops mlx5e_netdev_ops_basic = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, @@ -2608,6 +2696,7 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = { #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif + .ndo_tx_timeout = mlx5e_tx_timeout, }; static const struct net_device_ops mlx5e_netdev_ops_sriov = { @@ -2637,6 +2726,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { .ndo_get_vf_config = mlx5e_get_vf_config, .ndo_set_vf_link_state = mlx5e_set_vf_link_state, .ndo_get_vf_stats = mlx5e_get_vf_stats, + .ndo_tx_timeout = mlx5e_tx_timeout, }; static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) @@ -2839,6 +2929,7 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work); INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work); + INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work); INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index bd947704b59c..9f2a16a507e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -212,6 +212,20 @@ err_free_skb: return -ENOMEM; } +void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) +{ + struct sk_buff *skb = rq->skb[ix]; + + if (skb) { + rq->skb[ix] = NULL; + dma_unmap_single(rq->pdev, + *((dma_addr_t *)skb->cb), + rq->wqe_sz, + DMA_FROM_DEVICE); + dev_kfree_skb(skb); + } +} + static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq) { return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER; @@ -574,6 +588,30 @@ int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix) return 0; } +void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) +{ + struct mlx5e_mpw_info *wi = &rq->wqe_info[ix]; + + wi->free_wqe(rq, wi); +} + +void mlx5e_free_rx_descs(struct mlx5e_rq *rq) +{ + struct mlx5_wq_ll *wq = &rq->wq; + struct mlx5e_rx_wqe *wqe; + __be16 wqe_ix_be; + u16 wqe_ix; + + while (!mlx5_wq_ll_is_empty(wq)) { + wqe_ix_be = *wq->tail_next; + wqe_ix = be16_to_cpu(wqe_ix_be); + wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix); + rq->dealloc_wqe(rq, wqe_ix); + mlx5_wq_ll_pop(&rq->wq, wqe_ix_be, + &wqe->next.next_wqe_index); + } +} + #define RQ_CANNOT_POST(rq) \ (!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \ test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) @@ -689,7 +727,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (is_first_ethertype_ip(skb)) { skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); - rq->stats.csum_sw++; + rq->stats.csum_complete++; return; } @@ -699,7 +737,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (cqe_is_tunneled(cqe)) { skb->csum_level = 1; skb->encapsulation = 1; - rq->stats.csum_inner++; + rq->stats.csum_unnecessary_inner++; } return; } @@ -878,6 +916,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); int work_done = 0; + if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state))) + return 0; + if (cq->decmprs_left) work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 83bc32b25849..fcd490cc5610 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -42,9 +42,11 @@ be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset)) #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld) +#define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld) struct counter_desc { - char name[ETH_GSTRING_LEN]; + char format[ETH_GSTRING_LEN]; int offset; /* Byte offset */ }; @@ -53,18 +55,18 @@ struct mlx5e_sw_stats { u64 rx_bytes; u64 tx_packets; u64 tx_bytes; - u64 tso_packets; - u64 tso_bytes; - u64 tso_inner_packets; - u64 tso_inner_bytes; - u64 lro_packets; - u64 lro_bytes; - u64 rx_csum_good; + u64 tx_tso_packets; + u64 tx_tso_bytes; + u64 tx_tso_inner_packets; + u64 tx_tso_inner_bytes; + u64 rx_lro_packets; + u64 rx_lro_bytes; + u64 rx_csum_unnecessary; u64 rx_csum_none; - u64 rx_csum_sw; - u64 rx_csum_inner; - u64 tx_csum_offload; - u64 tx_csum_inner; + u64 rx_csum_complete; + u64 rx_csum_unnecessary_inner; + u64 tx_csum_partial; + u64 tx_csum_partial_inner; u64 tx_queue_stopped; u64 tx_queue_wake; u64 tx_queue_dropped; @@ -76,7 +78,7 @@ struct mlx5e_sw_stats { u64 rx_cqe_compress_pkts; /* Special handling counters */ - u64 link_down_events; + u64 link_down_events_phy; }; static const struct counter_desc sw_stats_desc[] = { @@ -84,18 +86,18 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_good) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_sw) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_inner) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_offload) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_inner) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) }, @@ -105,7 +107,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) }, }; struct mlx5e_qcounter_stats { @@ -125,12 +127,6 @@ struct mlx5e_vport_stats { }; static const struct counter_desc vport_stats_desc[] = { - { "rx_vport_error_packets", - VPORT_COUNTER_OFF(received_errors.packets) }, - { "rx_vport_error_bytes", VPORT_COUNTER_OFF(received_errors.octets) }, - { "tx_vport_error_packets", - VPORT_COUNTER_OFF(transmit_errors.packets) }, - { "tx_vport_error_bytes", VPORT_COUNTER_OFF(transmit_errors.octets) }, { "rx_vport_unicast_packets", VPORT_COUNTER_OFF(received_eth_unicast.packets) }, { "rx_vport_unicast_bytes", @@ -192,94 +188,68 @@ struct mlx5e_pport_stats { }; static const struct counter_desc pport_802_3_stats_desc[] = { - { "frames_tx", PPORT_802_3_OFF(a_frames_transmitted_ok) }, - { "frames_rx", PPORT_802_3_OFF(a_frames_received_ok) }, - { "check_seq_err", PPORT_802_3_OFF(a_frame_check_sequence_errors) }, - { "alignment_err", PPORT_802_3_OFF(a_alignment_errors) }, - { "octets_tx", PPORT_802_3_OFF(a_octets_transmitted_ok) }, - { "octets_received", PPORT_802_3_OFF(a_octets_received_ok) }, - { "multicast_xmitted", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) }, - { "broadcast_xmitted", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) }, - { "multicast_rx", PPORT_802_3_OFF(a_multicast_frames_received_ok) }, - { "broadcast_rx", PPORT_802_3_OFF(a_broadcast_frames_received_ok) }, - { "in_range_len_errors", PPORT_802_3_OFF(a_in_range_length_errors) }, - { "out_of_range_len", PPORT_802_3_OFF(a_out_of_range_length_field) }, - { "too_long_errors", PPORT_802_3_OFF(a_frame_too_long_errors) }, - { "symbol_err", PPORT_802_3_OFF(a_symbol_error_during_carrier) }, - { "mac_control_tx", PPORT_802_3_OFF(a_mac_control_frames_transmitted) }, - { "mac_control_rx", PPORT_802_3_OFF(a_mac_control_frames_received) }, - { "unsupported_op_rx", - PPORT_802_3_OFF(a_unsupported_opcodes_received) }, - { "pause_ctrl_rx", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) }, - { "pause_ctrl_tx", - PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) }, + { "tx_packets_phy", PPORT_802_3_OFF(a_frames_transmitted_ok) }, + { "rx_packets_phy", PPORT_802_3_OFF(a_frames_received_ok) }, + { "rx_crc_errors_phy", PPORT_802_3_OFF(a_frame_check_sequence_errors) }, + { "tx_bytes_phy", PPORT_802_3_OFF(a_octets_transmitted_ok) }, + { "rx_bytes_phy", PPORT_802_3_OFF(a_octets_received_ok) }, + { "tx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) }, + { "tx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) }, + { "rx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_received_ok) }, + { "rx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_received_ok) }, + { "rx_in_range_len_errors_phy", PPORT_802_3_OFF(a_in_range_length_errors) }, + { "rx_out_of_range_len_phy", PPORT_802_3_OFF(a_out_of_range_length_field) }, + { "rx_oversize_pkts_phy", PPORT_802_3_OFF(a_frame_too_long_errors) }, + { "rx_symbol_err_phy", PPORT_802_3_OFF(a_symbol_error_during_carrier) }, + { "tx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_transmitted) }, + { "rx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_received) }, + { "rx_unsupported_op_phy", PPORT_802_3_OFF(a_unsupported_opcodes_received) }, + { "rx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) }, + { "tx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) }, }; static const struct counter_desc pport_2863_stats_desc[] = { - { "in_octets", PPORT_2863_OFF(if_in_octets) }, - { "in_ucast_pkts", PPORT_2863_OFF(if_in_ucast_pkts) }, - { "in_discards", PPORT_2863_OFF(if_in_discards) }, - { "in_errors", PPORT_2863_OFF(if_in_errors) }, - { "in_unknown_protos", PPORT_2863_OFF(if_in_unknown_protos) }, - { "out_octets", PPORT_2863_OFF(if_out_octets) }, - { "out_ucast_pkts", PPORT_2863_OFF(if_out_ucast_pkts) }, - { "out_discards", PPORT_2863_OFF(if_out_discards) }, - { "out_errors", PPORT_2863_OFF(if_out_errors) }, - { "in_multicast_pkts", PPORT_2863_OFF(if_in_multicast_pkts) }, - { "in_broadcast_pkts", PPORT_2863_OFF(if_in_broadcast_pkts) }, - { "out_multicast_pkts", PPORT_2863_OFF(if_out_multicast_pkts) }, - { "out_broadcast_pkts", PPORT_2863_OFF(if_out_broadcast_pkts) }, + { "rx_discards_phy", PPORT_2863_OFF(if_in_discards) }, + { "tx_discards_phy", PPORT_2863_OFF(if_out_discards) }, + { "tx_errors_phy", PPORT_2863_OFF(if_out_errors) }, }; static const struct counter_desc pport_2819_stats_desc[] = { - { "drop_events", PPORT_2819_OFF(ether_stats_drop_events) }, - { "octets", PPORT_2819_OFF(ether_stats_octets) }, - { "pkts", PPORT_2819_OFF(ether_stats_pkts) }, - { "broadcast_pkts", PPORT_2819_OFF(ether_stats_broadcast_pkts) }, - { "multicast_pkts", PPORT_2819_OFF(ether_stats_multicast_pkts) }, - { "crc_align_errors", PPORT_2819_OFF(ether_stats_crc_align_errors) }, - { "undersize_pkts", PPORT_2819_OFF(ether_stats_undersize_pkts) }, - { "oversize_pkts", PPORT_2819_OFF(ether_stats_oversize_pkts) }, - { "fragments", PPORT_2819_OFF(ether_stats_fragments) }, - { "jabbers", PPORT_2819_OFF(ether_stats_jabbers) }, - { "collisions", PPORT_2819_OFF(ether_stats_collisions) }, - { "p64octets", PPORT_2819_OFF(ether_stats_pkts64octets) }, - { "p65to127octets", PPORT_2819_OFF(ether_stats_pkts65to127octets) }, - { "p128to255octets", PPORT_2819_OFF(ether_stats_pkts128to255octets) }, - { "p256to511octets", PPORT_2819_OFF(ether_stats_pkts256to511octets) }, - { "p512to1023octets", PPORT_2819_OFF(ether_stats_pkts512to1023octets) }, - { "p1024to1518octets", - PPORT_2819_OFF(ether_stats_pkts1024to1518octets) }, - { "p1519to2047octets", - PPORT_2819_OFF(ether_stats_pkts1519to2047octets) }, - { "p2048to4095octets", - PPORT_2819_OFF(ether_stats_pkts2048to4095octets) }, - { "p4096to8191octets", - PPORT_2819_OFF(ether_stats_pkts4096to8191octets) }, - { "p8192to10239octets", - PPORT_2819_OFF(ether_stats_pkts8192to10239octets) }, + { "rx_undersize_pkts_phy", PPORT_2819_OFF(ether_stats_undersize_pkts) }, + { "rx_fragments_phy", PPORT_2819_OFF(ether_stats_fragments) }, + { "rx_jabbers_phy", PPORT_2819_OFF(ether_stats_jabbers) }, + { "rx_64_bytes_phy", PPORT_2819_OFF(ether_stats_pkts64octets) }, + { "rx_65_to_127_bytes_phy", PPORT_2819_OFF(ether_stats_pkts65to127octets) }, + { "rx_128_to_255_bytes_phy", PPORT_2819_OFF(ether_stats_pkts128to255octets) }, + { "rx_256_to_511_bytes_phy", PPORT_2819_OFF(ether_stats_pkts256to511octets) }, + { "rx_512_to_1023_bytes_phy", PPORT_2819_OFF(ether_stats_pkts512to1023octets) }, + { "rx_1024_to_1518_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1024to1518octets) }, + { "rx_1519_to_2047_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1519to2047octets) }, + { "rx_2048_to_4095_bytes_phy", PPORT_2819_OFF(ether_stats_pkts2048to4095octets) }, + { "rx_4096_to_8191_bytes_phy", PPORT_2819_OFF(ether_stats_pkts4096to8191octets) }, + { "rx_8192_to_10239_bytes_phy", PPORT_2819_OFF(ether_stats_pkts8192to10239octets) }, }; static const struct counter_desc pport_per_prio_traffic_stats_desc[] = { - { "rx_octets", PPORT_PER_PRIO_OFF(rx_octets) }, - { "rx_frames", PPORT_PER_PRIO_OFF(rx_frames) }, - { "tx_octets", PPORT_PER_PRIO_OFF(tx_octets) }, - { "tx_frames", PPORT_PER_PRIO_OFF(tx_frames) }, + { "rx_prio%d_bytes", PPORT_PER_PRIO_OFF(rx_octets) }, + { "rx_prio%d_packets", PPORT_PER_PRIO_OFF(rx_frames) }, + { "tx_prio%d_bytes", PPORT_PER_PRIO_OFF(tx_octets) }, + { "tx_prio%d_packets", PPORT_PER_PRIO_OFF(tx_frames) }, }; static const struct counter_desc pport_per_prio_pfc_stats_desc[] = { - { "rx_pause", PPORT_PER_PRIO_OFF(rx_pause) }, - { "rx_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) }, - { "tx_pause", PPORT_PER_PRIO_OFF(tx_pause) }, - { "tx_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) }, - { "rx_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) }, + { "rx_prio%d_pause", PPORT_PER_PRIO_OFF(rx_pause) }, + { "rx_prio%d_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) }, + { "tx_prio%d_pause", PPORT_PER_PRIO_OFF(tx_pause) }, + { "tx_prio%d_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) }, + { "rx_prio%d_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) }, }; struct mlx5e_rq_stats { u64 packets; u64 bytes; - u64 csum_sw; - u64 csum_inner; + u64 csum_complete; + u64 csum_unnecessary_inner; u64 csum_none; u64 lro_packets; u64 lro_bytes; @@ -292,19 +262,19 @@ struct mlx5e_rq_stats { }; static const struct counter_desc rq_stats_desc[] = { - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_sw) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_inner) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_none) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, wqe_err) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_filler) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_frag) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, buff_alloc_err) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_blks) }, - { MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_frag) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) }, }; struct mlx5e_sq_stats { @@ -315,28 +285,28 @@ struct mlx5e_sq_stats { u64 tso_bytes; u64 tso_inner_packets; u64 tso_inner_bytes; - u64 csum_offload_inner; + u64 csum_partial_inner; u64 nop; /* less likely accessed in data path */ - u64 csum_offload_none; + u64 csum_none; u64 stopped; u64 wake; u64 dropped; }; static const struct counter_desc sq_stats_desc[] = { - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_inner) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, nop) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_none) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, stopped) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, wake) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, dropped) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, packets) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, bytes) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_packets) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) }, }; #define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index b000ddc29553..5740b465ef84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -110,8 +110,20 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, { struct mlx5e_priv *priv = netdev_priv(dev); int channel_ix = fallback(dev, skb); - int up = (netdev_get_num_tc(dev) && skb_vlan_tag_present(skb)) ? - skb->vlan_tci >> VLAN_PRIO_SHIFT : 0; + int up = 0; + + if (!netdev_get_num_tc(dev)) + return channel_ix; + + if (skb_vlan_tag_present(skb)) + up = skb->vlan_tci >> VLAN_PRIO_SHIFT; + + /* channel_ix can be larger than num_channels since + * dev->num_real_tx_queues = num_channels * num_tc + */ + if (channel_ix >= priv->params.num_channels) + channel_ix = reciprocal_scale(channel_ix, + priv->params.num_channels); return priv->channeltc_to_txq_map[channel_ix][up]; } @@ -123,7 +135,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, * headers and occur before the data gather. * Therefore these headers must be copied into the WQE */ -#define MLX5E_MIN_INLINE ETH_HLEN +#define MLX5E_MIN_INLINE (ETH_HLEN + VLAN_HLEN) if (bf) { u16 ihs = skb_headlen(skb); @@ -135,7 +147,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, return skb_headlen(skb); } - return MLX5E_MIN_INLINE; + return max(skb_network_offset(skb), MLX5E_MIN_INLINE); } static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data, @@ -192,12 +204,12 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) if (skb->encapsulation) { eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM | MLX5_ETH_WQE_L4_INNER_CSUM; - sq->stats.csum_offload_inner++; + sq->stats.csum_partial_inner++; } else { eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; } } else - sq->stats.csum_offload_none++; + sq->stats.csum_none++; if (sq->cc != sq->prev_cc) { sq->prev_cc = sq->cc; @@ -341,6 +353,35 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) return mlx5e_sq_xmit(sq, skb); } +void mlx5e_free_tx_descs(struct mlx5e_sq *sq) +{ + struct mlx5e_tx_wqe_info *wi; + struct sk_buff *skb; + u16 ci; + int i; + + while (sq->cc != sq->pc) { + ci = sq->cc & sq->wq.sz_m1; + skb = sq->skb[ci]; + wi = &sq->wqe_info[ci]; + + if (!skb) { /* nop */ + sq->cc++; + continue; + } + + for (i = 0; i < wi->num_dma; i++) { + struct mlx5e_sq_dma *dma = + mlx5e_dma_get(sq, sq->dma_fifo_cc++); + + mlx5e_tx_dma_unmap(sq->pdev, dma); + } + + dev_kfree_skb_any(skb); + sq->cc += wi->num_wqebbs; + } +} + bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_sq *sq; @@ -352,6 +393,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_sq, cq); + if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state))) + return false; + npkts = 0; nbytes = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 42d16b9458e4..96a59463ae65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -108,15 +108,21 @@ static int in_fatal(struct mlx5_core_dev *dev) void mlx5_enter_error_state(struct mlx5_core_dev *dev) { + mutex_lock(&dev->intf_state_mutex); if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) - return; + goto unlock; mlx5_core_err(dev, "start\n"); - if (pci_channel_offline(dev->pdev) || in_fatal(dev)) + if (pci_channel_offline(dev->pdev) || in_fatal(dev)) { dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; + trigger_cmd_completions(dev); + } mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0); mlx5_core_err(dev, "end\n"); + +unlock: + mutex_unlock(&dev->intf_state_mutex); } static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) @@ -245,7 +251,6 @@ static void poll_health(unsigned long data) u32 count; if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { - trigger_cmd_completions(dev); mod_timer(&health->timer, get_next_poll_jiffies()); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a19b59348dd6..6695893ddd2d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1422,46 +1422,31 @@ void mlx5_disable_device(struct mlx5_core_dev *dev) mlx5_pci_err_detected(dev->pdev, 0); } -/* wait for the device to show vital signs. For now we check - * that we can read the device ID and that the health buffer - * shows a non zero value which is different than 0xffffffff +/* wait for the device to show vital signs by waiting + * for the health counter to start counting. */ -static void wait_vital(struct pci_dev *pdev) +static int wait_vital(struct pci_dev *pdev) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct mlx5_core_health *health = &dev->priv.health; const int niter = 100; + u32 last_count = 0; u32 count; - u16 did; int i; - /* Wait for firmware to be ready after reset */ - msleep(1000); - for (i = 0; i < niter; i++) { - if (pci_read_config_word(pdev, 2, &did)) { - dev_warn(&pdev->dev, "failed reading config word\n"); - break; - } - if (did == pdev->device) { - dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i); - break; - } - msleep(50); - } - if (i == niter) - dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__); - for (i = 0; i < niter; i++) { count = ioread32be(health->health_counter); if (count && count != 0xffffffff) { - dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i); - break; + if (last_count && last_count != count) { + dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i); + return 0; + } + last_count = count; } msleep(50); } - if (i == niter) - dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__); + return -ETIMEDOUT; } static void mlx5_pci_resume(struct pci_dev *pdev) @@ -1473,7 +1458,11 @@ static void mlx5_pci_resume(struct pci_dev *pdev) dev_info(&pdev->dev, "%s was called\n", __func__); pci_save_state(pdev); - wait_vital(pdev); + err = wait_vital(pdev); + if (err) { + dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__); + return; + } err = mlx5_load_one(dev, priv); if (err) @@ -1508,8 +1497,9 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1014), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4 VF */ { PCI_VDEVICE(MELLANOX, 0x1015) }, /* ConnectX-4LX */ { PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */ - { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5 */ + { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */ { PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */ + { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */ { 0, } }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 9eeee0545f1c..32dea3524cee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -345,7 +345,6 @@ retry: func_id, npages, err); goto out_4k; } - dev->priv.fw_pages += npages; err = mlx5_cmd_status_to_err(&out.hdr); if (err) { @@ -373,6 +372,33 @@ out_free: return err; } +static int reclaim_pages_cmd(struct mlx5_core_dev *dev, + struct mlx5_manage_pages_inbox *in, int in_size, + struct mlx5_manage_pages_outbox *out, int out_size) +{ + struct fw_page *fwp; + struct rb_node *p; + u32 npages; + u32 i = 0; + + if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR) + return mlx5_cmd_exec_check_status(dev, (u32 *)in, in_size, + (u32 *)out, out_size); + + npages = be32_to_cpu(in->num_entries); + + p = rb_first(&dev->priv.page_root); + while (p && i < npages) { + fwp = rb_entry(p, struct fw_page, rb_node); + out->pas[i] = cpu_to_be64(fwp->addr); + p = rb_next(p); + i++; + } + + out->num_entries = cpu_to_be32(i); + return 0; +} + static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, int *nclaimed) { @@ -398,15 +424,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, in.func_id = cpu_to_be16(func_id); in.num_entries = cpu_to_be32(npages); mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen); - err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen); + err = reclaim_pages_cmd(dev, &in, sizeof(in), out, outlen); if (err) { - mlx5_core_err(dev, "failed reclaiming pages\n"); - goto out_free; - } - dev->priv.fw_pages -= npages; - - if (out->hdr.status) { - err = mlx5_cmd_status_to_err(&out->hdr); + mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err); goto out_free; } @@ -417,13 +437,15 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, err = -EINVAL; goto out_free; } - if (nclaimed) - *nclaimed = num_claimed; for (i = 0; i < num_claimed; i++) { addr = be64_to_cpu(out->pas[i]); free_4k(dev, addr); } + + if (nclaimed) + *nclaimed = num_claimed; + dev->priv.fw_pages -= num_claimed; if (func_id) dev->priv.vfs_pages -= num_claimed; @@ -514,14 +536,10 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) p = rb_first(&dev->priv.page_root); if (p) { fwp = rb_entry(p, struct fw_page, rb_node); - if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { - free_4k(dev, fwp->addr); - nclaimed = 1; - } else { - err = reclaim_pages(dev, fwp->func_id, - optimal_reclaimed_pages(), - &nclaimed); - } + err = reclaim_pages(dev, fwp->func_id, + optimal_reclaimed_pages(), + &nclaimed); + if (err) { mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", err); @@ -536,6 +554,13 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) } } while (p); + WARN(dev->priv.fw_pages, + "FW pages counter is %d after reclaiming all pages\n", + dev->priv.fw_pages); + WARN(dev->priv.vfs_pages, + "VFs FW pages counter is %d after reclaiming all pages\n", + dev->priv.vfs_pages); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index daf44cd4c566..91846dfcbe9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -513,7 +513,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, { int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); void *nic_vport_context; - u8 *guid; void *in; int err; @@ -535,8 +534,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in, in, nic_vport_context); - guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context, - node_guid); MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid); err = mlx5_modify_nic_vport_context(mdev, in, inlen); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index f2fd1ef16da7..e25a73ed2981 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -72,8 +72,8 @@ static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port) u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]; u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)]; - memset(&in, 0, sizeof(in)); - memset(&out, 0, sizeof(out)); + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); MLX5_SET(delete_vxlan_udp_dport_in, in, opcode, MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT); @@ -105,6 +105,9 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) struct mlx5e_vxlan *vxlan; int err; + if (mlx5e_vxlan_lookup_port(priv, port)) + goto free_work; + if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) goto free_work; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index ce21ee5b2357..821a087c7ae2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -75,14 +75,14 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err); return err; } err = mlx5_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq), &wq_ctrl->buf, param->buf_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err); goto err_db_free; } @@ -111,14 +111,14 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err); return err; } err = mlx5_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq), &wq_ctrl->buf, param->buf_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err); goto err_db_free; } @@ -148,13 +148,14 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err); return err; } - err = mlx5_buf_alloc(mdev, mlx5_wq_ll_get_byte_size(wq), &wq_ctrl->buf); + err = mlx5_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq), + &wq_ctrl->buf, param->buf_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err); goto err_db_free; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 1977e7a5c530..57d48da709fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -2718,7 +2718,7 @@ static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port, * Configures the switch priority to buffer table. */ #define MLXSW_REG_PPTB_ID 0x500B -#define MLXSW_REG_PPTB_LEN 0x0C +#define MLXSW_REG_PPTB_LEN 0x10 static const struct mlxsw_reg_info mlxsw_reg_pptb = { .id = MLXSW_REG_PPTB_ID, @@ -2784,6 +2784,13 @@ MLXSW_ITEM32(reg, pptb, pm_msb, 0x08, 24, 8); */ MLXSW_ITEM32(reg, pptb, untagged_buff, 0x08, 0, 4); +/* reg_pptb_prio_to_buff_msb + * Mapping of switch priority to one of the allocated receive port + * buffers. + * Access: RW + */ +MLXSW_ITEM_BIT_ARRAY(reg, pptb, prio_to_buff_msb, 0x0C, 0x04, 4); + #define MLXSW_REG_PPTB_ALL_PRIO 0xFF static inline void mlxsw_reg_pptb_pack(char *payload, u8 local_port) @@ -2792,6 +2799,14 @@ static inline void mlxsw_reg_pptb_pack(char *payload, u8 local_port) mlxsw_reg_pptb_mm_set(payload, MLXSW_REG_PPTB_MM_UM); mlxsw_reg_pptb_local_port_set(payload, local_port); mlxsw_reg_pptb_pm_set(payload, MLXSW_REG_PPTB_ALL_PRIO); + mlxsw_reg_pptb_pm_msb_set(payload, MLXSW_REG_PPTB_ALL_PRIO); +} + +static inline void mlxsw_reg_pptb_prio_to_buff_pack(char *payload, u8 prio, + u8 buff) +{ + mlxsw_reg_pptb_prio_to_buff_set(payload, prio, buff); + mlxsw_reg_pptb_prio_to_buff_msb_set(payload, prio, buff); } /* PBMC - Port Buffer Management Control Register diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 6f9e3ddff4a8..374080027b2f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -171,23 +171,6 @@ static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(paos), paos_pl); } -static int mlxsw_sp_port_oper_status_get(struct mlxsw_sp_port *mlxsw_sp_port, - bool *p_is_up) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char paos_pl[MLXSW_REG_PAOS_LEN]; - u8 oper_status; - int err; - - mlxsw_reg_paos_pack(paos_pl, mlxsw_sp_port->local_port, 0); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(paos), paos_pl); - if (err) - return err; - oper_status = mlxsw_reg_paos_oper_status_get(paos_pl); - *p_is_up = oper_status == MLXSW_PORT_ADMIN_STATUS_UP ? true : false; - return 0; -} - static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port, unsigned char *addr) { @@ -408,7 +391,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, } mlxsw_sp_txhdr_construct(skb, &tx_info); - len = skb->len; + /* TX header is consumed by HW on the way so we shouldn't count its + * bytes as being sent. + */ + len = skb->len - MLXSW_TXHDR_LEN; + /* Due to a race we might fail here because of a full queue. In that * unlikely case we simply drop the packet. */ @@ -1430,7 +1417,8 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev, cmd->supported = mlxsw_sp_from_ptys_supported_port(eth_proto_cap) | mlxsw_sp_from_ptys_supported_link(eth_proto_cap) | - SUPPORTED_Pause | SUPPORTED_Asym_Pause; + SUPPORTED_Pause | SUPPORTED_Asym_Pause | + SUPPORTED_Autoneg; cmd->advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_admin); mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev), eth_proto_oper, cmd); @@ -1489,7 +1477,6 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev, u32 eth_proto_new; u32 eth_proto_cap; u32 eth_proto_admin; - bool is_up; int err; speed = ethtool_cmd_speed(cmd); @@ -1521,12 +1508,7 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev, return err; } - err = mlxsw_sp_port_oper_status_get(mlxsw_sp_port, &is_up); - if (err) { - netdev_err(dev, "Failed to get oper status"); - return err; - } - if (!is_up) + if (!netif_running(dev)) return 0; err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index a3720a0fad7d..074cdda7b6f3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -194,7 +194,7 @@ static int mlxsw_sp_port_pb_prio_init(struct mlxsw_sp_port *mlxsw_sp_port) mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port); for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - mlxsw_reg_pptb_prio_to_buff_set(pptb_pl, i, 0); + mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, 0); return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb), pptb_pl); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c index 0b323661c0b6..01cfb7512827 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c @@ -103,7 +103,8 @@ static int mlxsw_sp_port_pg_prio_map(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port); for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - mlxsw_reg_pptb_prio_to_buff_set(pptb_pl, i, prio_tc[i]); + mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, prio_tc[i]); + return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb), pptb_pl); } @@ -249,6 +250,7 @@ static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev, return err; memcpy(mlxsw_sp_port->dcb.ets, ets, sizeof(*ets)); + mlxsw_sp_port->dcb.ets->ets_cap = IEEE_8021QAZ_MAX_TCS; return 0; } @@ -351,7 +353,8 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); int err; - if (mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) { + if ((mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) && + pfc->pfc_en) { netdev_err(dev, "PAUSE frames already enabled on port\n"); return -EINVAL; } @@ -371,6 +374,7 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, } memcpy(mlxsw_sp_port->dcb.pfc, pfc, sizeof(*pfc)); + mlxsw_sp_port->dcb.pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS; return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 3842eab9449a..25f658b3849a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -316,7 +316,10 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb, } } mlxsw_sx_txhdr_construct(skb, &tx_info); - len = skb->len; + /* TX header is consumed by HW on the way so we shouldn't count its + * bytes as being sent. + */ + len = skb->len - MLXSW_TXHDR_LEN; /* Due to a race we might fail here because of a full queue. In that * unlikely case we simply drop the packet. */ diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c index 7066954c39d6..0a26b11ca8f6 100644 --- a/drivers/net/ethernet/microchip/enc28j60.c +++ b/drivers/net/ethernet/microchip/enc28j60.c @@ -1151,7 +1151,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work) enc28j60_phy_read(priv, PHIR); } /* TX complete handler */ - if ((intflags & EIR_TXIF) != 0) { + if (((intflags & EIR_TXIF) != 0) && + ((intflags & EIR_TXERIF) == 0)) { bool err = false; loop++; if (netif_msg_intr(priv)) @@ -1203,7 +1204,7 @@ static void enc28j60_irq_work_handler(struct work_struct *work) enc28j60_tx_clear(ndev, true); } else enc28j60_tx_clear(ndev, true); - locked_reg_bfclr(priv, EIR, EIR_TXERIF); + locked_reg_bfclr(priv, EIR, EIR_TXERIF | EIR_TXIF); } /* RX Error handler */ if ((intflags & EIR_RXERIF) != 0) { @@ -1238,6 +1239,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work) */ static void enc28j60_hw_tx(struct enc28j60_net *priv) { + BUG_ON(!priv->tx_skb); + if (netif_msg_tx_queued(priv)) printk(KERN_DEBUG DRV_NAME ": Tx Packet Len:%d\n", priv->tx_skb->len); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index fa47c14c743a..ba26bb356b8d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2015,7 +2015,7 @@ static void nfp_net_open_stack(struct nfp_net *nn) netif_tx_wake_all_queues(nn->netdev); - enable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector); + enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); nfp_net_read_link_status(nn); } @@ -2044,7 +2044,7 @@ static int nfp_net_netdev_open(struct net_device *netdev) NFP_NET_IRQ_LSC_IDX, nn->lsc_handler); if (err) goto err_free_exn; - disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector); + disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); nn->rx_rings = kcalloc(nn->num_rx_rings, sizeof(*nn->rx_rings), GFP_KERNEL); @@ -2133,7 +2133,7 @@ static void nfp_net_close_stack(struct nfp_net *nn) { unsigned int r; - disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector); + disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector); netif_carrier_off(nn->netdev); nn->link_up = false; diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 9afc15fdbb02..e29ed5a69566 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -3700,6 +3700,7 @@ struct public_port { #define MEDIA_DA_TWINAX 0x3 #define MEDIA_BASE_T 0x4 #define MEDIA_SFP_1G_FIBER 0x5 +#define MEDIA_MODULE_FIBER 0x6 #define MEDIA_KR 0xf0 #define MEDIA_NOT_PRESENT 0xff diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 8fba87dd48af..aada4c7e095f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -72,6 +72,7 @@ int qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn, p_ramrod->mtu = cpu_to_le16(p_params->mtu); p_ramrod->inner_vlan_removal_en = p_params->remove_inner_vlan; p_ramrod->drop_ttl0_en = p_params->drop_ttl0; + p_ramrod->untagged = p_params->only_untagged; SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_UCAST_DROP_ALL, 1); SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_MCAST_DROP_ALL, 1); @@ -247,10 +248,6 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn, SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_DROP_ALL, !!(accept_filter & QED_ACCEPT_NONE)); - SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL, - (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) && - !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED))); - SET_FIELD(state, ETH_VPORT_TX_MODE_MCAST_DROP_ALL, !!(accept_filter & QED_ACCEPT_NONE)); @@ -1748,7 +1745,8 @@ static int qed_start_vport(struct qed_dev *cdev, start.vport_id, start.mtu); } - qed_reset_vport_stats(cdev); + if (params->clear_stats) + qed_reset_vport_stats(cdev); return 0; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 61cc6869fa65..c7e01b303540 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1085,6 +1085,7 @@ static int qed_get_port_type(u32 media_type) case MEDIA_SFPP_10G_FIBER: case MEDIA_SFP_1G_FIBER: case MEDIA_XFP_FIBER: + case MEDIA_MODULE_FIBER: case MEDIA_KR: port_type = PORT_FIBRE; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index acac6626a1b2..b122f6013b6c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -213,19 +213,15 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn, SET_FIELD(db.params, CORE_DB_DATA_AGG_VAL_SEL, DQ_XCM_CORE_SPQ_PROD_CMD); db.agg_flags = DQ_XCM_CORE_DQ_CF_CMD; - - /* validate producer is up to-date */ - rmb(); - db.spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain)); - /* do not reorder */ - barrier(); + /* make sure the SPQE is updated before the doorbell */ + wmb(); DOORBELL(p_hwfn, qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY), *(u32 *)&db); /* make sure doorbell is rang */ - mmiowb(); + wmb(); DP_VERBOSE(p_hwfn, QED_MSG_SPQ, "Doorbelled [0x%08x, CID 0x%08x] with Flags: %02x agg_params: %02x, prod: %04x\n", @@ -614,7 +610,9 @@ qed_spq_add_entry(struct qed_hwfn *p_hwfn, *p_en2 = *p_ent; - kfree(p_ent); + /* EBLOCK responsible to free the allocated p_ent */ + if (p_ent->comp_mode != QED_SPQ_MODE_EBLOCK) + kfree(p_ent); p_ent = p_en2; } @@ -749,6 +747,15 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, * Thus, after gaining the answer perform the cleanup here. */ rc = qed_spq_block(p_hwfn, p_ent, fw_return_code); + + if (p_ent->queue == &p_spq->unlimited_pending) { + /* This is an allocated p_ent which does not need to + * return to pool. + */ + kfree(p_ent); + return rc; + } + if (rc) goto spq_post_fail2; @@ -844,8 +851,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, found->comp_cb.function(p_hwfn, found->comp_cb.cookie, p_data, fw_return_code); - if (found->comp_mode != QED_SPQ_MODE_EBLOCK) - /* EBLOCK is responsible for freeing its own entry */ + if ((found->comp_mode != QED_SPQ_MODE_EBLOCK) || + (found->queue == &p_spq->unlimited_pending)) + /* EBLOCK is responsible for returning its own entry into the + * free list, unless it originally added the entry into the + * unlimited pending list. + */ qed_spq_return_entry(p_hwfn, found); /* Attempt to post pending requests */ diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 5733d1888223..f8e11f953acb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -3231,7 +3231,7 @@ static int qede_stop_queues(struct qede_dev *edev) return rc; } -static int qede_start_queues(struct qede_dev *edev) +static int qede_start_queues(struct qede_dev *edev, bool clear_stats) { int rc, tc, i; int vlan_removal_en = 1; @@ -3462,6 +3462,7 @@ out: enum qede_load_mode { QEDE_LOAD_NORMAL, + QEDE_LOAD_RELOAD, }; static int qede_load(struct qede_dev *edev, enum qede_load_mode mode) @@ -3500,7 +3501,7 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode) goto err3; DP_INFO(edev, "Setup IRQs succeeded\n"); - rc = qede_start_queues(edev); + rc = qede_start_queues(edev, mode != QEDE_LOAD_RELOAD); if (rc) goto err4; DP_INFO(edev, "Start VPORT, RXQ and TXQ succeeded\n"); @@ -3555,7 +3556,7 @@ void qede_reload(struct qede_dev *edev, if (func) func(edev, args); - qede_load(edev, QEDE_LOAD_NORMAL); + qede_load(edev, QEDE_LOAD_RELOAD); mutex_lock(&edev->qede_lock); qede_config_rx_mode(edev->ndev); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 7bd6f25b4625..87c642d3b075 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -772,6 +772,8 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tx_ring->tx_stats.tx_bytes += skb->len; tx_ring->tx_stats.xmit_called++; + /* Ensure writes are complete before HW fetches Tx descriptors */ + wmb(); qlcnic_update_cmd_producer(tx_ring); return NETDEV_TX_OK; @@ -2220,7 +2222,7 @@ void qlcnic_83xx_process_rcv_ring_diag(struct qlcnic_host_sds_ring *sds_ring) if (!opcode) return; - ring = QLCNIC_FETCH_RING_ID(qlcnic_83xx_hndl(sts_data[0])); + ring = QLCNIC_FETCH_RING_ID(sts_data[0]); qlcnic_83xx_process_rcv_diag(adapter, ring, sts_data); desc = &sds_ring->desc_head[consumer]; desc->status_desc_data[0] = cpu_to_le64(STATUS_OWNER_PHANTOM); diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 133e9e35be9e..4c83739d158f 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -104,7 +104,8 @@ int efx_farch_test_registers(struct efx_nic *efx, const struct efx_farch_register_test *regs, size_t n_regs) { - unsigned address = 0, i, j; + unsigned address = 0; + int i, j; efx_oword_t mask, imask, original, reg, buf; for (i = 0; i < n_regs; ++i) { diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 8af25563f627..b5ab5e120bca 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -116,7 +116,6 @@ struct smsc911x_data { struct phy_device *phy_dev; struct mii_bus *mii_bus; - int phy_irq[PHY_MAX_ADDR]; unsigned int using_extphy; int last_duplex; int last_carrier; @@ -1073,7 +1072,6 @@ static int smsc911x_mii_init(struct platform_device *pdev, pdata->mii_bus->priv = pdata; pdata->mii_bus->read = smsc911x_mii_read; pdata->mii_bus->write = smsc911x_mii_write; - memcpy(pdata->mii_bus->irq, pdata->phy_irq, sizeof(pdata->mii_bus)); pdata->mii_bus->parent = &pdev->dev; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a473c182c91d..e4071265be76 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2804,7 +2804,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) priv->tx_path_in_lpi_mode = true; if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE) priv->tx_path_in_lpi_mode = false; - if (status & CORE_IRQ_MTL_RX_OVERFLOW) + if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr) priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, priv->rx_tail_addr, STMMAC_CHAN0); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index e6bb0ecb12c7..53190894f17a 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2505,8 +2505,6 @@ static int cpsw_probe(struct platform_device *pdev) clean_ale_ret: cpsw_ale_destroy(priv->ale); clean_dma_ret: - cpdma_chan_destroy(priv->txch); - cpdma_chan_destroy(priv->rxch); cpdma_ctlr_destroy(priv->dma); clean_runtime_disable_ret: pm_runtime_disable(&pdev->dev); @@ -2534,8 +2532,6 @@ static int cpsw_remove(struct platform_device *pdev) unregister_netdev(ndev); cpsw_ale_destroy(priv->ale); - cpdma_chan_destroy(priv->txch); - cpdma_chan_destroy(priv->rxch); cpdma_ctlr_destroy(priv->dma); pm_runtime_disable(&pdev->dev); device_for_each_child(&pdev->dev, NULL, cpsw_remove_child_device); diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 0a15acc075b3..11213a38c795 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -462,7 +462,7 @@ static void tile_tx_timestamp(struct sk_buff *skb, int instance) if (unlikely((shtx->tx_flags & SKBTX_HW_TSTAMP) != 0)) { struct mpipe_data *md = &mpipe_data[instance]; struct skb_shared_hwtstamps shhwtstamps; - struct timespec ts; + struct timespec64 ts; shtx->tx_flags |= SKBTX_IN_PROGRESS; gxio_mpipe_get_timestamp(&md->context, &ts); @@ -886,9 +886,9 @@ static struct ptp_clock_info ptp_mpipe_caps = { /* Sync mPIPE's timestamp up with Linux system time and register PTP clock. */ static void register_ptp_clock(struct net_device *dev, struct mpipe_data *md) { - struct timespec ts; + struct timespec64 ts; - getnstimeofday(&ts); + ktime_get_ts64(&ts); gxio_mpipe_set_timestamp(&md->context, &ts); mutex_init(&md->ptp_lock); diff --git a/drivers/net/fddi/skfp/Makefile b/drivers/net/fddi/skfp/Makefile index b0be0234abf6..a957a1c7e5ba 100644 --- a/drivers/net/fddi/skfp/Makefile +++ b/drivers/net/fddi/skfp/Makefile @@ -17,4 +17,4 @@ skfp-objs := skfddi.o hwmtm.o fplustm.o smt.o cfm.o \ # projects. To keep the source common for all those drivers (and # thus simplify fixes to it), please do not clean it up! -ccflags-y := -Idrivers/net/skfp -DPCI -DMEM_MAPPED_IO -Wno-strict-prototypes +ccflags-y := -DPCI -DMEM_MAPPED_IO -Wno-strict-prototypes diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index cadefe4fdaa2..9b3dc3c61e00 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -958,8 +958,8 @@ tx_error: dev->stats.collisions++; else if (err == -ENETUNREACH) dev->stats.tx_carrier_errors++; - else - dev->stats.tx_errors++; + + dev->stats.tx_errors++; return NETDEV_TX_OK; } @@ -1048,8 +1048,8 @@ tx_error: dev->stats.collisions++; else if (err == -ENETUNREACH) dev->stats.tx_carrier_errors++; - else - dev->stats.tx_errors++; + + dev->stats.tx_errors++; return NETDEV_TX_OK; } #endif @@ -1072,12 +1072,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict) { + struct geneve_dev *geneve = netdev_priv(dev); /* The max_mtu calculation does not take account of GENEVE * options, to avoid excluding potentially valid * configurations. */ - int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr) - - dev->hard_header_len; + int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len; + + if (geneve->remote.sa.sa_family == AF_INET6) + max_mtu -= sizeof(struct ipv6hdr); + else + max_mtu -= sizeof(struct iphdr); if (new_mtu < 68) return -EINVAL; @@ -1508,6 +1513,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; + LIST_HEAD(list_kill); int err; memset(tb, 0, sizeof(tb)); @@ -1519,8 +1525,10 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, err = geneve_configure(net, dev, &geneve_remote_unspec, 0, 0, 0, 0, htons(dst_port), true, GENEVE_F_UDP_ZERO_CSUM6_RX); - if (err) - goto err; + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. @@ -1529,10 +1537,15 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, if (err) goto err; + err = rtnl_configure_link(dev, NULL); + if (err < 0) + goto err; + return dev; err: - free_netdev(dev); + geneve_dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 47ee2c840b55..8bcd78f94966 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -605,12 +605,41 @@ static void macsec_encrypt_done(struct crypto_async_request *base, int err) dev_put(dev); } +static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm, + unsigned char **iv, + struct scatterlist **sg) +{ + size_t size, iv_offset, sg_offset; + struct aead_request *req; + void *tmp; + + size = sizeof(struct aead_request) + crypto_aead_reqsize(tfm); + iv_offset = size; + size += GCM_AES_IV_LEN; + + size = ALIGN(size, __alignof__(struct scatterlist)); + sg_offset = size; + size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1); + + tmp = kmalloc(size, GFP_ATOMIC); + if (!tmp) + return NULL; + + *iv = (unsigned char *)(tmp + iv_offset); + *sg = (struct scatterlist *)(tmp + sg_offset); + req = tmp; + + aead_request_set_tfm(req, tfm); + + return req; +} + static struct sk_buff *macsec_encrypt(struct sk_buff *skb, struct net_device *dev) { int ret; - struct scatterlist sg[MAX_SKB_FRAGS + 1]; - unsigned char iv[GCM_AES_IV_LEN]; + struct scatterlist *sg; + unsigned char *iv; struct ethhdr *eth; struct macsec_eth_header *hh; size_t unprotected_len; @@ -668,8 +697,6 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, macsec_fill_sectag(hh, secy, pn); macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN); - macsec_fill_iv(iv, secy->sci, pn); - skb_put(skb, secy->icv_len); if (skb->len - ETH_HLEN > macsec_priv(dev)->real_dev->mtu) { @@ -684,13 +711,15 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, return ERR_PTR(-EINVAL); } - req = aead_request_alloc(tx_sa->key.tfm, GFP_ATOMIC); + req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg); if (!req) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOMEM); } + macsec_fill_iv(iv, secy->sci, pn); + sg_init_table(sg, MAX_SKB_FRAGS + 1); skb_to_sgvec(skb, sg, 0, skb->len); @@ -861,7 +890,6 @@ static void macsec_decrypt_done(struct crypto_async_request *base, int err) out: macsec_rxsa_put(rx_sa); dev_put(dev); - return; } static struct sk_buff *macsec_decrypt(struct sk_buff *skb, @@ -871,8 +899,8 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, struct macsec_secy *secy) { int ret; - struct scatterlist sg[MAX_SKB_FRAGS + 1]; - unsigned char iv[GCM_AES_IV_LEN]; + struct scatterlist *sg; + unsigned char *iv; struct aead_request *req; struct macsec_eth_header *hdr; u16 icv_len = secy->icv_len; @@ -882,7 +910,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, if (!skb) return ERR_PTR(-ENOMEM); - req = aead_request_alloc(rx_sa->key.tfm, GFP_ATOMIC); + req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg); if (!req) { kfree_skb(skb); return ERR_PTR(-ENOMEM); @@ -1234,7 +1262,7 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) struct crypto_aead *tfm; int ret; - tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_aead("gcm(aes)", 0, 0); if (!tfm || IS_ERR(tfm)) return NULL; @@ -2612,6 +2640,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.OutPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); + skb->dev = macsec->real_dev; len = skb->len; ret = dev_queue_xmit(skb); count_tx(dev, ret, len); @@ -3361,6 +3390,7 @@ static void __exit macsec_exit(void) genl_unregister_family(&macsec_fam); rtnl_link_unregister(&macsec_link_ops); unregister_netdevice_notifier(&macsec_notifier); + rcu_barrier(); } module_init(macsec_init); diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 2afa61b51d41..91177a4a32ad 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -57,6 +57,7 @@ /* PHY CTRL bits */ #define DP83867_PHYCR_FIFO_DEPTH_SHIFT 14 +#define DP83867_PHYCR_FIFO_DEPTH_MASK (3 << 14) /* RGMIIDCTL bits */ #define DP83867_RGMII_TX_CLK_DELAY_SHIFT 4 @@ -133,8 +134,8 @@ static int dp83867_of_init(struct phy_device *phydev) static int dp83867_config_init(struct phy_device *phydev) { struct dp83867_private *dp83867; - int ret; - u16 val, delay; + int ret, val; + u16 delay; if (!phydev->priv) { dp83867 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83867), @@ -151,8 +152,12 @@ static int dp83867_config_init(struct phy_device *phydev) } if (phy_interface_is_rgmii(phydev)) { - ret = phy_write(phydev, MII_DP83867_PHYCTRL, - (dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT)); + val = phy_read(phydev, MII_DP83867_PHYCTRL); + if (val < 0) + return val; + val &= ~DP83867_PHYCR_FIFO_DEPTH_MASK; + val |= (dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT); + ret = phy_write(phydev, MII_DP83867_PHYCTRL, val); if (ret) return ret; } diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 2d2e4339f0df..9ec7f7353434 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -23,6 +23,7 @@ #include #include #include +#include #define MII_REGS_NUM 29 @@ -286,6 +287,8 @@ err_regs: } EXPORT_SYMBOL_GPL(fixed_phy_add); +static DEFINE_IDA(phy_fixed_ida); + static void fixed_phy_del(int phy_addr) { struct fixed_mdio_bus *fmb = &platform_fmb; @@ -297,14 +300,12 @@ static void fixed_phy_del(int phy_addr) if (gpio_is_valid(fp->link_gpio)) gpio_free(fp->link_gpio); kfree(fp); + ida_simple_remove(&phy_fixed_ida, phy_addr); return; } } } -static int phy_fixed_addr; -static DEFINE_SPINLOCK(phy_fixed_addr_lock); - struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, int link_gpio, @@ -319,17 +320,15 @@ struct phy_device *fixed_phy_register(unsigned int irq, return ERR_PTR(-EPROBE_DEFER); /* Get the next available PHY address, up to PHY_MAX_ADDR */ - spin_lock(&phy_fixed_addr_lock); - if (phy_fixed_addr == PHY_MAX_ADDR) { - spin_unlock(&phy_fixed_addr_lock); - return ERR_PTR(-ENOSPC); - } - phy_addr = phy_fixed_addr++; - spin_unlock(&phy_fixed_addr_lock); + phy_addr = ida_simple_get(&phy_fixed_ida, 0, PHY_MAX_ADDR, GFP_KERNEL); + if (phy_addr < 0) + return ERR_PTR(phy_addr); ret = fixed_phy_add(irq, phy_addr, status, link_gpio); - if (ret < 0) + if (ret < 0) { + ida_simple_remove(&phy_fixed_ida, phy_addr); return ERR_PTR(ret); + } phy = get_phy_device(fmb->mii_bus, phy_addr, false); if (IS_ERR(phy)) { @@ -434,6 +433,7 @@ static void __exit fixed_mdio_bus_exit(void) list_del(&fp->node); kfree(fp); } + ida_destroy(&phy_fixed_ida); } module_exit(fixed_mdio_bus_exit); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 280e8795b463..ec2c1eee6405 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -285,6 +285,48 @@ static int marvell_config_aneg(struct phy_device *phydev) return 0; } +static int m88e1111_config_aneg(struct phy_device *phydev) +{ + int err; + + /* The Marvell PHY has an errata which requires + * that certain registers get written in order + * to restart autonegotiation + */ + err = phy_write(phydev, MII_BMCR, BMCR_RESET); + + err = marvell_set_polarity(phydev, phydev->mdix); + if (err < 0) + return err; + + err = phy_write(phydev, MII_M1111_PHY_LED_CONTROL, + MII_M1111_PHY_LED_DIRECT); + if (err < 0) + return err; + + err = genphy_config_aneg(phydev); + if (err < 0) + return err; + + if (phydev->autoneg != AUTONEG_ENABLE) { + int bmcr; + + /* A write to speed/duplex bits (that is performed by + * genphy_config_aneg() call above) must be followed by + * a software reset. Otherwise, the write has no effect. + */ + bmcr = phy_read(phydev, MII_BMCR); + if (bmcr < 0) + return bmcr; + + err = phy_write(phydev, MII_BMCR, bmcr | BMCR_RESET); + if (err < 0) + return err; + } + + return 0; +} + #ifdef CONFIG_OF_MDIO /* * Set and/or override some configuration registers based on the @@ -407,15 +449,7 @@ static int m88e1121_config_aneg(struct phy_device *phydev) if (err < 0) return err; - oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE); - - phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_LED_PAGE); - phy_write(phydev, MII_88E1121_PHY_LED_CTRL, MII_88E1121_PHY_LED_DEF); - phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage); - - err = genphy_config_aneg(phydev); - - return err; + return genphy_config_aneg(phydev); } static int m88e1318_config_aneg(struct phy_device *phydev) @@ -636,6 +670,28 @@ static int m88e1111_config_init(struct phy_device *phydev) return phy_write(phydev, MII_BMCR, BMCR_RESET); } +static int m88e1121_config_init(struct phy_device *phydev) +{ + int err, oldpage; + + oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE); + + err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_LED_PAGE); + if (err < 0) + return err; + + /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */ + err = phy_write(phydev, MII_88E1121_PHY_LED_CTRL, + MII_88E1121_PHY_LED_DEF); + if (err < 0) + return err; + + phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage); + + /* Set marvell,reg-init configuration from device tree */ + return marvell_config_init(phydev); +} + static int m88e1510_config_init(struct phy_device *phydev) { int err; @@ -668,7 +724,7 @@ static int m88e1510_config_init(struct phy_device *phydev) return err; } - return marvell_config_init(phydev); + return m88e1121_config_init(phydev); } static int m88e1118_config_aneg(struct phy_device *phydev) @@ -1161,7 +1217,7 @@ static struct phy_driver marvell_drivers[] = { .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, .config_init = &m88e1111_config_init, - .config_aneg = &marvell_config_aneg, + .config_aneg = &m88e1111_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, .config_intr = &marvell_config_intr, @@ -1196,7 +1252,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, - .config_init = &marvell_config_init, + .config_init = &m88e1121_config_init, .config_aneg = &m88e1121_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1215,7 +1271,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, - .config_init = &marvell_config_init, + .config_init = &m88e1121_config_init, .config_aneg = &m88e1318_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 2e21e9366f76..b62c4aaee40b 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -75,22 +75,13 @@ static int smsc_phy_reset(struct phy_device *phydev) * in all capable mode before using it. */ if ((rc & MII_LAN83C185_MODE_MASK) == MII_LAN83C185_MODE_POWERDOWN) { - int timeout = 50000; - - /* set "all capable" mode and reset the phy */ + /* set "all capable" mode */ rc |= MII_LAN83C185_MODE_ALL; phy_write(phydev, MII_LAN83C185_SPECIAL_MODES, rc); - phy_write(phydev, MII_BMCR, BMCR_RESET); - - /* wait end of reset (max 500 ms) */ - do { - udelay(10); - if (timeout-- == 0) - return -1; - rc = phy_read(phydev, MII_BMCR); - } while (rc & BMCR_RESET); } - return 0; + + /* reset the phy */ + return genphy_soft_reset(phydev); } static int lan911x_config_init(struct phy_device *phydev) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 8dedafa1a95d..a30ee427efab 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2601,8 +2601,6 @@ ppp_unregister_channel(struct ppp_channel *chan) spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); - put_net(pch->chan_net); - pch->chan_net = NULL; pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); @@ -3136,6 +3134,9 @@ ppp_disconnect_channel(struct channel *pch) */ static void ppp_destroy_channel(struct channel *pch) { + put_net(pch->chan_net); + pch->chan_net = NULL; + atomic_dec(&channel_count); if (!pch->file.dead) { diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 2ace126533cd..fdee77207323 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1203,8 +1203,10 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_dev_open; } + netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); dev_mc_sync_multiple(port_dev, dev); + netif_addr_unlock_bh(dev); err = vlan_vids_add_by_dev(port_dev, dev); if (err) { diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 53759c315b97..877c9516e781 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -854,6 +854,13 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ if (cdc_ncm_init(dev)) goto error2; + /* Some firmwares need a pause here or they will silently fail + * to set up the interface properly. This value was decided + * empirically on a Sierra Wireless MC7455 running 02.08.02.00 + * firmware. + */ + usleep_range(10000, 20000); + /* configure data interface */ temp = usb_set_interface(dev->udev, iface_no, data_altsetting); if (temp) { diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 3f9f6ed3eec4..e9654a685381 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -26,12 +26,13 @@ #include #include #include +#include /* Information for net-next */ #define NETNEXT_VERSION "08" /* Information for net */ -#define NET_VERSION "3" +#define NET_VERSION "5" #define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION #define DRIVER_AUTHOR "Realtek linux nic maintainers " @@ -116,6 +117,7 @@ #define USB_TX_DMA 0xd434 #define USB_TOLERANCE 0xd490 #define USB_LPM_CTRL 0xd41a +#define USB_BMU_RESET 0xd4b0 #define USB_UPS_CTRL 0xd800 #define USB_MISC_0 0xd81a #define USB_POWER_CUT 0xd80a @@ -338,6 +340,10 @@ #define TEST_MODE_DISABLE 0x00000001 #define TX_SIZE_ADJUST1 0x00000100 +/* USB_BMU_RESET */ +#define BMU_RESET_EP_IN 0x01 +#define BMU_RESET_EP_OUT 0x02 + /* USB_UPS_CTRL */ #define POWER_CUT 0x0100 @@ -455,6 +461,11 @@ /* SRAM_IMPEDANCE */ #define RX_DRIVING_MASK 0x6000 +/* MAC PASSTHRU */ +#define AD_MASK 0xfee0 +#define EFUSE 0xcfdb +#define PASS_THRU_MASK 0x1 + enum rtl_register_content { _1000bps = 0x10, _100bps = 0x08, @@ -619,6 +630,7 @@ struct r8152 { int (*eee_get)(struct r8152 *, struct ethtool_eee *); int (*eee_set)(struct r8152 *, struct ethtool_eee *); bool (*in_nway)(struct r8152 *); + void (*autosuspend_en)(struct r8152 *tp, bool enable); } rtl_ops; int intr_interval; @@ -1030,6 +1042,65 @@ out1: return ret; } +/* Devices containing RTL8153-AD can support a persistent + * host system provided MAC address. + * Examples of this are Dell TB15 and Dell WD15 docks + */ +static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa) +{ + acpi_status status; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *obj; + int ret = -EINVAL; + u32 ocp_data; + unsigned char buf[6]; + + /* test for -AD variant of RTL8153 */ + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0); + if ((ocp_data & AD_MASK) != 0x1000) + return -ENODEV; + + /* test for MAC address pass-through bit */ + ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, EFUSE); + if ((ocp_data & PASS_THRU_MASK) != 1) + return -ENODEV; + + /* returns _AUXMAC_#AABBCCDDEEFF# */ + status = acpi_evaluate_object(NULL, "\\_SB.AMAC", NULL, &buffer); + obj = (union acpi_object *)buffer.pointer; + if (!ACPI_SUCCESS(status)) + return -ENODEV; + if (obj->type != ACPI_TYPE_BUFFER || obj->string.length != 0x17) { + netif_warn(tp, probe, tp->netdev, + "Invalid buffer when reading pass-thru MAC addr: " + "(%d, %d)\n", + obj->type, obj->string.length); + goto amacout; + } + if (strncmp(obj->string.pointer, "_AUXMAC_#", 9) != 0 || + strncmp(obj->string.pointer + 0x15, "#", 1) != 0) { + netif_warn(tp, probe, tp->netdev, + "Invalid header when reading pass-thru MAC addr\n"); + goto amacout; + } + ret = hex2bin(buf, obj->string.pointer + 9, 6); + if (!(ret == 0 && is_valid_ether_addr(buf))) { + netif_warn(tp, probe, tp->netdev, + "Invalid MAC when reading pass-thru MAC addr: " + "%d, %pM\n", ret, buf); + ret = -EINVAL; + goto amacout; + } + memcpy(sa->sa_data, buf, 6); + ether_addr_copy(tp->netdev->dev_addr, sa->sa_data); + netif_info(tp, probe, tp->netdev, + "Using pass-thru MAC addr %pM\n", sa->sa_data); + +amacout: + kfree(obj); + return ret; +} + static int set_ethernet_addr(struct r8152 *tp) { struct net_device *dev = tp->netdev; @@ -1038,8 +1109,15 @@ static int set_ethernet_addr(struct r8152 *tp) if (tp->version == RTL_VER_01) ret = pla_ocp_read(tp, PLA_IDR, 8, sa.sa_data); - else - ret = pla_ocp_read(tp, PLA_BACKUP, 8, sa.sa_data); + else { + /* if this is not an RTL8153-AD, no eFuse mac pass thru set, + * or system doesn't provide valid _SB.AMAC this will be + * be expected to non-zero + */ + ret = vendor_mac_passthru_addr_read(tp, &sa); + if (ret < 0) + ret = pla_ocp_read(tp, PLA_BACKUP, 8, sa.sa_data); + } if (ret < 0) { netif_err(tp, probe, dev, "Get ether addr fail\n"); @@ -2169,7 +2247,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp) static void r8153_set_rx_early_size(struct r8152 *tp) { u32 mtu = tp->netdev->mtu; - u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 4; + u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 8; ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE, ocp_data); } @@ -2290,10 +2368,6 @@ static u32 __rtl_get_wol(struct r8152 *tp) u32 ocp_data; u32 wolopts = 0; - ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5); - if (!(ocp_data & LAN_WAKE_EN)) - return 0; - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34); if (ocp_data & LINK_ON_WAKE_EN) wolopts |= WAKE_PHY; @@ -2326,15 +2400,13 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts) ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data); ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG5); - ocp_data &= ~(UWF_EN | BWF_EN | MWF_EN | LAN_WAKE_EN); + ocp_data &= ~(UWF_EN | BWF_EN | MWF_EN); if (wolopts & WAKE_UCAST) ocp_data |= UWF_EN; if (wolopts & WAKE_BCAST) ocp_data |= BWF_EN; if (wolopts & WAKE_MCAST) ocp_data |= MWF_EN; - if (wolopts & WAKE_ANY) - ocp_data |= LAN_WAKE_EN; ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG5, ocp_data); ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); @@ -2403,9 +2475,6 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) if (enable) { u32 ocp_data; - r8153_u1u2en(tp, false); - r8153_u2p3en(tp, false); - __rtl_set_wol(tp, WAKE_ANY); ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG); @@ -2416,7 +2485,28 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); } else { + u32 ocp_data; + __rtl_set_wol(tp, tp->saved_wolopts); + + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG); + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34); + ocp_data &= ~LINK_OFF_WAKE_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data); + + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); + } +} + +static void rtl8153_runtime_enable(struct r8152 *tp, bool enable) +{ + rtl_runtime_suspend_enable(tp, enable); + + if (enable) { + r8153_u1u2en(tp, false); + r8153_u2p3en(tp, false); + } else { r8153_u2p3en(tp, true); r8153_u1u2en(tp, true); } @@ -2456,6 +2546,17 @@ static void r8153_teredo_off(struct r8152 *tp) ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0); } +static void rtl_reset_bmu(struct r8152 *tp) +{ + u32 ocp_data; + + ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_BMU_RESET); + ocp_data &= ~(BMU_RESET_EP_IN | BMU_RESET_EP_OUT); + ocp_write_byte(tp, MCU_TYPE_USB, USB_BMU_RESET, ocp_data); + ocp_data |= BMU_RESET_EP_IN | BMU_RESET_EP_OUT; + ocp_write_byte(tp, MCU_TYPE_USB, USB_BMU_RESET, ocp_data); +} + static void r8152_aldps_en(struct r8152 *tp, bool enable) { if (enable) { @@ -2681,6 +2782,7 @@ static void r8153_first_init(struct r8152 *tp) r8153_hw_phy_cfg(tp); rtl8152_nic_reset(tp); + rtl_reset_bmu(tp); ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); ocp_data &= ~NOW_IS_OOB; @@ -2742,6 +2844,7 @@ static void r8153_enter_oob(struct r8152 *tp) ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); rtl_disable(tp); + rtl_reset_bmu(tp); for (i = 0; i < 1000; i++) { ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); @@ -2803,6 +2906,7 @@ static void rtl8153_disable(struct r8152 *tp) { r8153_aldps_en(tp, false); rtl_disable(tp); + rtl_reset_bmu(tp); r8153_aldps_en(tp, true); usb_enable_lpm(tp->udev); } @@ -3382,15 +3486,11 @@ static void r8153_init(struct r8152 *tp) r8153_power_cut_en(tp, false); r8153_u1u2en(tp, true); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, ALDPS_SPDWN_RATIO); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, EEE_SPDWN_RATIO); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, - PKT_AVAIL_SPDWN_EN | SUSPEND_SPDWN_EN | - U1U2_SPDWN_EN | L1_SPDWN_EN); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, - PWRSAVE_SPDWN_EN | RXDV_SPDWN_EN | TX10MIDLE_EN | - TP100_SPDWN_EN | TP500_SPDWN_EN | TP1000_SPDWN_EN | - EEE_SPDWN_EN); + /* MAC clock speed down */ + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0); r8153_enable_eee(tp); r8153_aldps_en(tp, true); @@ -3497,7 +3597,7 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) napi_disable(&tp->napi); if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { rtl_stop_rx(tp); - rtl_runtime_suspend_enable(tp, true); + tp->rtl_ops.autosuspend_en(tp, true); } else { cancel_delayed_work_sync(&tp->schedule); tp->rtl_ops.down(tp); @@ -3523,7 +3623,7 @@ static int rtl8152_resume(struct usb_interface *intf) if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) { if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { - rtl_runtime_suspend_enable(tp, false); + tp->rtl_ops.autosuspend_en(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); napi_disable(&tp->napi); set_bit(WORK_ENABLE, &tp->flags); @@ -3542,7 +3642,7 @@ static int rtl8152_resume(struct usb_interface *intf) usb_submit_urb(tp->intr_urb, GFP_KERNEL); } else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { if (tp->netdev->flags & IFF_UP) - rtl_runtime_suspend_enable(tp, false); + tp->rtl_ops.autosuspend_en(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); } @@ -4122,6 +4222,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->eee_get = r8152_get_eee; ops->eee_set = r8152_set_eee; ops->in_nway = rtl8152_in_nway; + ops->autosuspend_en = rtl_runtime_suspend_enable; break; case RTL_VER_03: @@ -4137,6 +4238,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->eee_get = r8153_get_eee; ops->eee_set = r8153_set_eee; ops->in_nway = rtl8153_in_nway; + ops->autosuspend_en = rtl8153_runtime_enable; break; default: @@ -4323,3 +4425,4 @@ module_usb_driver(rtl8152_driver); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); +MODULE_VERSION(DRIVER_VERSION); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 61ba46404937..6086a0163249 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -395,8 +395,11 @@ int usbnet_change_mtu (struct net_device *net, int new_mtu) dev->hard_mtu = net->mtu + net->hard_header_len; if (dev->rx_urb_size == old_hard_mtu) { dev->rx_urb_size = dev->hard_mtu; - if (dev->rx_urb_size > old_rx_urb_size) + if (dev->rx_urb_size > old_rx_urb_size) { + usbnet_pause_rx(dev); usbnet_unlink_rx_urbs(dev); + usbnet_resume_rx(dev); + } } /* max qlen depend on hard_mtu and rx_urb_size */ @@ -1508,8 +1511,9 @@ static void usbnet_bh (unsigned long param) } else if (netif_running (dev->net) && netif_device_present (dev->net) && netif_carrier_ok(dev->net) && - !timer_pending (&dev->delay) && - !test_bit (EVENT_RX_HALT, &dev->flags)) { + !timer_pending(&dev->delay) && + !test_bit(EVENT_RX_PAUSED, &dev->flags) && + !test_bit(EVENT_RX_HALT, &dev->flags)) { int temp = dev->rxq.qlen; if (temp < RX_QLEN(dev)) { diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index dff08842f26d..8bd8c7e1ee87 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -304,7 +304,7 @@ static int vrf_rt6_create(struct net_device *dev) dst_hold(&rt6->dst); rt6->rt6i_table = rt6i_table; - rt6->dst.output = vrf_output6; + rt6->dst.output = vrf_output6; rcu_assign_pointer(vrf->rt6, rt6); rc = 0; @@ -403,7 +403,7 @@ static int vrf_rtable_create(struct net_device *dev) if (!rth) return -ENOMEM; - rth->dst.output = vrf_output; + rth->dst.output = vrf_output; rth->rt_table_id = vrf->tb_id; rcu_assign_pointer(vrf->rth, rth); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f999db2f97b4..b3b9db68f758 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2952,30 +2952,6 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, return 0; } -struct net_device *vxlan_dev_create(struct net *net, const char *name, - u8 name_assign_type, struct vxlan_config *conf) -{ - struct nlattr *tb[IFLA_MAX+1]; - struct net_device *dev; - int err; - - memset(&tb, 0, sizeof(tb)); - - dev = rtnl_create_link(net, name, name_assign_type, - &vxlan_link_ops, tb); - if (IS_ERR(dev)) - return dev; - - err = vxlan_dev_configure(net, dev, conf); - if (err < 0) { - free_netdev(dev); - return ERR_PTR(err); - } - - return dev; -} -EXPORT_SYMBOL_GPL(vxlan_dev_create); - static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { @@ -3268,6 +3244,40 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .get_link_net = vxlan_get_link_net, }; +struct net_device *vxlan_dev_create(struct net *net, const char *name, + u8 name_assign_type, + struct vxlan_config *conf) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + int err; + + memset(&tb, 0, sizeof(tb)); + + dev = rtnl_create_link(net, name, name_assign_type, + &vxlan_link_ops, tb); + if (IS_ERR(dev)) + return dev; + + err = vxlan_dev_configure(net, dev, conf); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + + err = rtnl_configure_link(dev, NULL); + if (err < 0) { + LIST_HEAD(list_kill); + + vxlan_dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + return ERR_PTR(err); + } + + return dev; +} +EXPORT_SYMBOL_GPL(vxlan_dev_create); + static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, struct net_device *dev) { diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 49af62428c88..a92a0ba829f5 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -1083,7 +1083,7 @@ int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name, } ath10k_dbg_dump(ar, ATH10K_DBG_BOOT, "features", "", - ar->running_fw->fw_file.fw_features, + fw_file->fw_features, sizeof(fw_file->fw_features)); break; case ATH10K_FW_IE_FW_IMAGE: diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index cc979a4faeb0..813cdd2621a1 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -1904,7 +1904,6 @@ static void ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb) return; } } - ath10k_htt_rx_msdu_buff_replenish(htt); } static void ath10k_htt_rx_tx_fetch_resp_id_confirm(struct ath10k *ar, diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 6dd1d26b357f..4040f9413e86 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -679,10 +679,10 @@ static int ath10k_peer_create(struct ath10k *ar, peer = ath10k_peer_find(ar, vdev_id, addr); if (!peer) { + spin_unlock_bh(&ar->data_lock); ath10k_warn(ar, "failed to find peer %pM on vdev %i after creation\n", addr, vdev_id); ath10k_wmi_peer_delete(ar, vdev_id, addr); - spin_unlock_bh(&ar->data_lock); return -ENOENT; } diff --git a/drivers/net/wireless/ath/ath9k/reg.h b/drivers/net/wireless/ath/ath9k/reg.h index 9272ca90632b..80ff69f99229 100644 --- a/drivers/net/wireless/ath/ath9k/reg.h +++ b/drivers/net/wireless/ath/ath9k/reg.h @@ -1122,12 +1122,12 @@ enum { #define AR9300_NUM_GPIO 16 #define AR9330_NUM_GPIO 16 #define AR9340_NUM_GPIO 23 -#define AR9462_NUM_GPIO 10 +#define AR9462_NUM_GPIO 14 #define AR9485_NUM_GPIO 12 #define AR9531_NUM_GPIO 18 #define AR9550_NUM_GPIO 24 #define AR9561_NUM_GPIO 23 -#define AR9565_NUM_GPIO 12 +#define AR9565_NUM_GPIO 14 #define AR9580_NUM_GPIO 16 #define AR7010_NUM_GPIO 16 @@ -1139,12 +1139,12 @@ enum { #define AR9300_GPIO_MASK 0x0000F4FF #define AR9330_GPIO_MASK 0x0000F4FF #define AR9340_GPIO_MASK 0x0000000F -#define AR9462_GPIO_MASK 0x000003FF +#define AR9462_GPIO_MASK 0x00003FFF #define AR9485_GPIO_MASK 0x00000FFF #define AR9531_GPIO_MASK 0x0000000F #define AR9550_GPIO_MASK 0x0000000F #define AR9561_GPIO_MASK 0x0000000F -#define AR9565_GPIO_MASK 0x00000FFF +#define AR9565_GPIO_MASK 0x00003FFF #define AR9580_GPIO_MASK 0x0000F4FF #define AR7010_GPIO_MASK 0x0000FFFF diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index e5f267b21316..18a8474b5760 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3851,8 +3851,8 @@ static int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx, if (idx != 0) return -ENOENT; - if (fw_has_capa(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS)) + if (!fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS)) return -ENOENT; mutex_lock(&mvm->mutex); @@ -3898,8 +3898,8 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw, struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - if (fw_has_capa(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS)) + if (!fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS)) return; /* if beacon filtering isn't on mac80211 does it anyway */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index ac2c5718e454..2c61516d06ff 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -581,7 +581,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, struct iwl_rx_mpdu_desc *desc) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); + struct iwl_mvm_sta *mvm_sta; struct iwl_mvm_baid_data *baid_data; struct iwl_mvm_reorder_buffer *buffer; struct sk_buff *tail; @@ -604,6 +604,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, if (WARN_ON(IS_ERR_OR_NULL(sta))) return false; + mvm_sta = iwl_mvm_sta_from_mac80211(sta); + /* not a data packet */ if (!ieee80211_is_data_qos(hdr->frame_control) || is_multicast_ether_addr(hdr->addr1)) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 6f609dd5c222..e78fc567ff7d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1222,7 +1222,7 @@ static int iwl_mvm_check_running_scans(struct iwl_mvm *mvm, int type) return -EIO; } -#define SCAN_TIMEOUT (16 * HZ) +#define SCAN_TIMEOUT (20 * HZ) void iwl_mvm_scan_timeout(unsigned long data) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index fea4d3437e2f..b23ab4a4504f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1852,12 +1852,18 @@ static struct iwl_mvm_sta *iwl_mvm_get_key_sta(struct iwl_mvm *mvm, mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) { u8 sta_id = mvmvif->ap_sta_id; + sta = rcu_dereference_check(mvm->fw_id_to_mac_id[sta_id], + lockdep_is_held(&mvm->mutex)); + /* * It is possible that the 'sta' parameter is NULL, * for example when a GTK is removed - the sta_id will then * be the AP ID, and no station was passed by mac80211. */ - return iwl_mvm_sta_from_staid_protected(mvm, sta_id); + if (IS_ERR_OR_NULL(sta)) + return NULL; + + return iwl_mvm_sta_from_mac80211(sta); } return NULL; @@ -1955,6 +1961,14 @@ static int iwl_mvm_send_sta_igtk(struct iwl_mvm *mvm, struct ieee80211_key_seq seq; const u8 *pn; + switch (keyconf->cipher) { + case WLAN_CIPHER_SUITE_AES_CMAC: + igtk_cmd.ctrl_flags |= cpu_to_le32(STA_KEY_FLG_CCM); + break; + default: + return -EINVAL; + } + memcpy(igtk_cmd.IGTK, keyconf->key, keyconf->keylen); ieee80211_get_key_rx_seq(keyconf, 0, &seq); pn = seq.aes_cmac.pn; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c index fe19ace0d6a0..b04cf30f3959 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c @@ -1149,7 +1149,7 @@ static void rtl8192eu_phy_iqcalibrate(struct rtl8xxxu_priv *priv, for (i = 0; i < retry; i++) { path_b_ok = rtl8192eu_rx_iqk_path_b(priv); - if (path_a_ok == 0x03) { + if (path_b_ok == 0x03) { val32 = rtl8xxxu_read32(priv, REG_RX_POWER_BEFORE_IQK_B_2); result[t][6] = (val32 >> 16) & 0x3ff; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index f7718ec685fa..cea8350fbc7e 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -344,6 +344,8 @@ struct device *nd_pfn_create(struct nd_region *nd_region) int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) { u64 checksum, offset; + unsigned long align; + enum nd_pfn_mode mode; struct nd_namespace_io *nsio; struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; struct nd_namespace_common *ndns = nd_pfn->ndns; @@ -386,22 +388,50 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) return -ENXIO; } + align = le32_to_cpu(pfn_sb->align); + offset = le64_to_cpu(pfn_sb->dataoff); + if (align == 0) + align = 1UL << ilog2(offset); + mode = le32_to_cpu(pfn_sb->mode); + if (!nd_pfn->uuid) { - /* from probe we allocate */ + /* + * When probing a namepace via nd_pfn_probe() the uuid + * is NULL (see: nd_pfn_devinit()) we init settings from + * pfn_sb + */ nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL); if (!nd_pfn->uuid) return -ENOMEM; + nd_pfn->align = align; + nd_pfn->mode = mode; } else { - /* from init we validate */ + /* + * When probing a pfn / dax instance we validate the + * live settings against the pfn_sb + */ if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0) return -ENODEV; + + /* + * If the uuid validates, but other settings mismatch + * return EINVAL because userspace has managed to change + * the configuration without specifying new + * identification. + */ + if (nd_pfn->align != align || nd_pfn->mode != mode) { + dev_err(&nd_pfn->dev, + "init failed, settings mismatch\n"); + dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n", + nd_pfn->align, align, nd_pfn->mode, + mode); + return -EINVAL; + } } - if (nd_pfn->align == 0) - nd_pfn->align = le32_to_cpu(pfn_sb->align); - if (nd_pfn->align > nvdimm_namespace_capacity(ndns)) { + if (align > nvdimm_namespace_capacity(ndns)) { dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n", - nd_pfn->align, nvdimm_namespace_capacity(ndns)); + align, nvdimm_namespace_capacity(ndns)); return -EINVAL; } @@ -411,7 +441,6 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) * namespace has changed since the pfn superblock was * established. */ - offset = le64_to_cpu(pfn_sb->dataoff); nsio = to_nd_namespace_io(&ndns->dev); if (offset >= resource_size(&nsio->res)) { dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n", @@ -419,10 +448,11 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) return -EBUSY; } - if ((nd_pfn->align && !IS_ALIGNED(offset, nd_pfn->align)) + if ((align && !IS_ALIGNED(offset, align)) || !IS_ALIGNED(offset, PAGE_SIZE)) { - dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled\n", - offset); + dev_err(&nd_pfn->dev, + "bad offset: %#llx dax disabled align: %#lx\n", + offset, align); return -ENXIO; } @@ -502,7 +532,6 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn, res->start += start_pad; res->end -= end_trunc; - nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode); if (nd_pfn->mode == PFN_MODE_RAM) { if (offset < SZ_8K) return ERR_PTR(-EINVAL); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1a51584a382b..d5fb55c0a9d9 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1394,19 +1394,22 @@ static int ns_cmp(void *priv, struct list_head *a, struct list_head *b) return nsa->ns_id - nsb->ns_id; } -static struct nvme_ns *nvme_find_ns(struct nvme_ctrl *ctrl, unsigned nsid) +static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) { - struct nvme_ns *ns; - - lockdep_assert_held(&ctrl->namespaces_mutex); + struct nvme_ns *ns, *ret = NULL; + mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->ns_id == nsid) - return ns; + if (ns->ns_id == nsid) { + kref_get(&ns->kref); + ret = ns; + break; + } if (ns->ns_id > nsid) break; } - return NULL; + mutex_unlock(&ctrl->namespaces_mutex); + return ret; } static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) @@ -1415,8 +1418,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) struct gendisk *disk; int node = dev_to_node(ctrl->dev); - lockdep_assert_held(&ctrl->namespaces_mutex); - ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) return; @@ -1457,7 +1458,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (nvme_revalidate_disk(ns->disk)) goto out_free_disk; - list_add_tail_rcu(&ns->list, &ctrl->namespaces); + mutex_lock(&ctrl->namespaces_mutex); + list_add_tail(&ns->list, &ctrl->namespaces); + mutex_unlock(&ctrl->namespaces_mutex); + kref_get(&ctrl->kref); if (ns->type == NVME_NS_LIGHTNVM) return; @@ -1480,8 +1484,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) static void nvme_ns_remove(struct nvme_ns *ns) { - lockdep_assert_held(&ns->ctrl->namespaces_mutex); - if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) return; @@ -1494,8 +1496,11 @@ static void nvme_ns_remove(struct nvme_ns *ns) blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); } + + mutex_lock(&ns->ctrl->namespaces_mutex); list_del_init(&ns->list); - synchronize_rcu(); + mutex_unlock(&ns->ctrl->namespaces_mutex); + nvme_put_ns(ns); } @@ -1503,10 +1508,11 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns; - ns = nvme_find_ns(ctrl, nsid); + ns = nvme_find_get_ns(ctrl, nsid); if (ns) { if (revalidate_disk(ns->disk)) nvme_ns_remove(ns); + nvme_put_ns(ns); } else nvme_alloc_ns(ctrl, nsid); } @@ -1535,9 +1541,11 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn) nvme_validate_ns(ctrl, nsid); while (++prev < nsid) { - ns = nvme_find_ns(ctrl, prev); - if (ns) + ns = nvme_find_get_ns(ctrl, prev); + if (ns) { nvme_ns_remove(ns); + nvme_put_ns(ns); + } } } nn -= j; @@ -1552,8 +1560,6 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn) struct nvme_ns *ns, *next; unsigned i; - lockdep_assert_held(&ctrl->namespaces_mutex); - for (i = 1; i <= nn; i++) nvme_validate_ns(ctrl, i); @@ -1576,7 +1582,6 @@ static void nvme_scan_work(struct work_struct *work) if (nvme_identify_ctrl(ctrl, &id)) return; - mutex_lock(&ctrl->namespaces_mutex); nn = le32_to_cpu(id->nn); if (ctrl->vs >= NVME_VS(1, 1) && !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { @@ -1585,6 +1590,7 @@ static void nvme_scan_work(struct work_struct *work) } nvme_scan_ns_sequential(ctrl, nn); done: + mutex_lock(&ctrl->namespaces_mutex); list_sort(NULL, &ctrl->namespaces, ns_cmp); mutex_unlock(&ctrl->namespaces_mutex); kfree(id); @@ -1604,6 +1610,11 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_queue_scan); +/* + * This function iterates the namespace list unlocked to allow recovery from + * controller failure. It is up to the caller to ensure the namespace list is + * not modified by scan work while this function is executing. + */ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) { struct nvme_ns *ns, *next; @@ -1617,10 +1628,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) if (ctrl->state == NVME_CTRL_DEAD) nvme_kill_queues(ctrl); - mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) nvme_ns_remove(ns); - mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_remove_namespaces); @@ -1791,11 +1800,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - rcu_read_lock(); - list_for_each_entry_rcu(ns, &ctrl->namespaces, list) { - if (!kref_get_unless_zero(&ns->kref)) - continue; - + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { /* * Revalidating a dead namespace sets capacity to 0. This will * end buffered writers dirtying pages that can't be synced. @@ -1806,10 +1812,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) blk_set_queue_dying(ns->queue); blk_mq_abort_requeue_list(ns->queue); blk_mq_start_stopped_hw_queues(ns->queue, true); - - nvme_put_ns(ns); } - rcu_read_unlock(); + mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_kill_queues); @@ -1817,8 +1821,8 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - rcu_read_lock(); - list_for_each_entry_rcu(ns, &ctrl->namespaces, list) { + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { spin_lock_irq(ns->queue->queue_lock); queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue); spin_unlock_irq(ns->queue->queue_lock); @@ -1826,7 +1830,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl) blk_mq_cancel_requeue_work(ns->queue); blk_mq_stop_hw_queues(ns->queue); } - rcu_read_unlock(); + mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_stop_queues); @@ -1834,13 +1838,13 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - rcu_read_lock(); - list_for_each_entry_rcu(ns, &ctrl->namespaces, list) { + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns->queue); blk_mq_start_stopped_hw_queues(ns->queue, true); blk_mq_kick_requeue_list(ns->queue); } - rcu_read_unlock(); + mutex_unlock(&ctrl->namespaces_mutex); } EXPORT_SYMBOL_GPL(nvme_start_queues); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c8b4dbdd1bdd..badbddc683f0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -530,8 +530,8 @@ static const struct pci_platform_pm_ops *pci_platform_pm; int pci_set_platform_pm(const struct pci_platform_pm_ops *ops) { - if (!ops->is_manageable || !ops->set_state || !ops->choose_state - || !ops->sleep_wake) + if (!ops->is_manageable || !ops->set_state || !ops->choose_state || + !ops->sleep_wake || !ops->run_wake || !ops->need_resume) return -EINVAL; pci_platform_pm = ops; return 0; diff --git a/drivers/pci/vc.c b/drivers/pci/vc.c index dfbab61a1b47..1fa3a3219c45 100644 --- a/drivers/pci/vc.c +++ b/drivers/pci/vc.c @@ -221,9 +221,9 @@ static int pci_vc_do_save_buffer(struct pci_dev *dev, int pos, else pci_write_config_word(dev, pos + PCI_VC_PORT_CTRL, *(u16 *)buf); - buf += 2; + buf += 4; } - len += 2; + len += 4; /* * If we have any Low Priority VCs and a VC Arbitration Table Offset diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 1b8304e1efaa..140436a046c0 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -1010,8 +1010,8 @@ int arm_pmu_device_probe(struct platform_device *pdev, if (!ret) ret = init_fn(pmu); } else { - ret = probe_current_pmu(pmu, probe_table); cpumask_setall(&pmu->supported_cpus); + ret = probe_current_pmu(pmu, probe_table); } if (ret) { diff --git a/drivers/phy/phy-bcm-ns-usb2.c b/drivers/phy/phy-bcm-ns-usb2.c index 95ab6b2a0de5..58dff80e9386 100644 --- a/drivers/phy/phy-bcm-ns-usb2.c +++ b/drivers/phy/phy-bcm-ns-usb2.c @@ -109,8 +109,8 @@ static int bcm_ns_usb2_probe(struct platform_device *pdev) } usb2->phy = devm_phy_create(dev, NULL, &ops); - if (IS_ERR(dev)) - return PTR_ERR(dev); + if (IS_ERR(usb2->phy)) + return PTR_ERR(usb2->phy); phy_set_drvdata(usb2->phy, usb2); platform_set_drvdata(pdev, usb2); diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c index cc093ebfda94..8b851f718123 100644 --- a/drivers/phy/phy-exynos-mipi-video.c +++ b/drivers/phy/phy-exynos-mipi-video.c @@ -233,8 +233,12 @@ static inline int __is_running(const struct exynos_mipi_phy_desc *data, struct exynos_mipi_video_phy *state) { u32 val; + int ret; + + ret = regmap_read(state->regmaps[data->resetn_map], data->resetn_reg, &val); + if (ret) + return 0; - regmap_read(state->regmaps[data->resetn_map], data->resetn_reg, &val); return val & data->resetn_val; } diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c index 3acd2a1808df..213e2e15339c 100644 --- a/drivers/phy/phy-miphy28lp.c +++ b/drivers/phy/phy-miphy28lp.c @@ -1143,7 +1143,8 @@ static int miphy28lp_probe_resets(struct device_node *node, struct miphy28lp_dev *miphy_dev = miphy_phy->phydev; int err; - miphy_phy->miphy_rst = of_reset_control_get(node, "miphy-sw-rst"); + miphy_phy->miphy_rst = + of_reset_control_get_shared(node, "miphy-sw-rst"); if (IS_ERR(miphy_phy->miphy_rst)) { dev_err(miphy_dev->dev, diff --git a/drivers/phy/phy-rcar-gen3-usb2.c b/drivers/phy/phy-rcar-gen3-usb2.c index 76bb88f0700a..4be3f5dbbc9f 100644 --- a/drivers/phy/phy-rcar-gen3-usb2.c +++ b/drivers/phy/phy-rcar-gen3-usb2.c @@ -144,12 +144,6 @@ static void rcar_gen3_init_for_peri(struct rcar_gen3_chan *ch) extcon_set_cable_state_(ch->extcon, EXTCON_USB, true); } -static bool rcar_gen3_check_vbus(struct rcar_gen3_chan *ch) -{ - return !!(readl(ch->base + USB2_ADPCTRL) & - USB2_ADPCTRL_OTGSESSVLD); -} - static bool rcar_gen3_check_id(struct rcar_gen3_chan *ch) { return !!(readl(ch->base + USB2_ADPCTRL) & USB2_ADPCTRL_IDDIG); @@ -157,13 +151,7 @@ static bool rcar_gen3_check_id(struct rcar_gen3_chan *ch) static void rcar_gen3_device_recognition(struct rcar_gen3_chan *ch) { - bool is_host = true; - - /* B-device? */ - if (rcar_gen3_check_id(ch) && rcar_gen3_check_vbus(ch)) - is_host = false; - - if (is_host) + if (!rcar_gen3_check_id(ch)) rcar_gen3_init_for_host(ch); else rcar_gen3_init_for_peri(ch); diff --git a/drivers/phy/phy-rockchip-dp.c b/drivers/phy/phy-rockchip-dp.c index 793ecb6d87bc..8b267a746576 100644 --- a/drivers/phy/phy-rockchip-dp.c +++ b/drivers/phy/phy-rockchip-dp.c @@ -90,7 +90,7 @@ static int rockchip_dp_phy_probe(struct platform_device *pdev) return -ENODEV; dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL); - if (IS_ERR(dp)) + if (!dp) return -ENOMEM; dp->dev = dev; diff --git a/drivers/phy/phy-stih407-usb.c b/drivers/phy/phy-stih407-usb.c index 1d5ae5f8ef69..b1f44ab669fb 100644 --- a/drivers/phy/phy-stih407-usb.c +++ b/drivers/phy/phy-stih407-usb.c @@ -105,13 +105,13 @@ static int stih407_usb2_picophy_probe(struct platform_device *pdev) phy_dev->dev = dev; dev_set_drvdata(dev, phy_dev); - phy_dev->rstc = devm_reset_control_get(dev, "global"); + phy_dev->rstc = devm_reset_control_get_shared(dev, "global"); if (IS_ERR(phy_dev->rstc)) { dev_err(dev, "failed to ctrl picoPHY reset\n"); return PTR_ERR(phy_dev->rstc); } - phy_dev->rstport = devm_reset_control_get(dev, "port"); + phy_dev->rstport = devm_reset_control_get_exclusive(dev, "port"); if (IS_ERR(phy_dev->rstport)) { dev_err(dev, "failed to ctrl picoPHY reset\n"); return PTR_ERR(phy_dev->rstport); diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c index bae54f7a1f48..de3101fbbf40 100644 --- a/drivers/phy/phy-sun4i-usb.c +++ b/drivers/phy/phy-sun4i-usb.c @@ -175,7 +175,7 @@ static void sun4i_usb_phy_write(struct sun4i_usb_phy *phy, u32 addr, u32 data, { struct sun4i_usb_phy_data *phy_data = to_sun4i_usb_phy_data(phy); u32 temp, usbc_bit = BIT(phy->index * 2); - void *phyctl = phy_data->base + phy_data->cfg->phyctl_offset; + void __iomem *phyctl = phy_data->base + phy_data->cfg->phyctl_offset; int i; mutex_lock(&phy_data->mutex); @@ -514,9 +514,9 @@ static int sun4i_usb_phy_remove(struct platform_device *pdev) if (data->vbus_power_nb_registered) power_supply_unreg_notifier(&data->vbus_power_nb); - if (data->id_det_irq >= 0) + if (data->id_det_irq > 0) devm_free_irq(dev, data->id_det_irq, data); - if (data->vbus_det_irq >= 0) + if (data->vbus_det_irq > 0) devm_free_irq(dev, data->vbus_det_irq, data); cancel_delayed_work_sync(&data->detect); @@ -645,11 +645,11 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev) data->id_det_irq = gpiod_to_irq(data->id_det_gpio); data->vbus_det_irq = gpiod_to_irq(data->vbus_det_gpio); - if ((data->id_det_gpio && data->id_det_irq < 0) || - (data->vbus_det_gpio && data->vbus_det_irq < 0)) + if ((data->id_det_gpio && data->id_det_irq <= 0) || + (data->vbus_det_gpio && data->vbus_det_irq <= 0)) data->phy0_poll = true; - if (data->id_det_irq >= 0) { + if (data->id_det_irq > 0) { ret = devm_request_irq(dev, data->id_det_irq, sun4i_usb_phy0_id_vbus_det_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, @@ -660,7 +660,7 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev) } } - if (data->vbus_det_irq >= 0) { + if (data->vbus_det_irq > 0) { ret = devm_request_irq(dev, data->vbus_det_irq, sun4i_usb_phy0_id_vbus_det_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c index 0a477d24cf76..bf46844dc387 100644 --- a/drivers/phy/phy-ti-pipe3.c +++ b/drivers/phy/phy-ti-pipe3.c @@ -293,11 +293,18 @@ static int ti_pipe3_init(struct phy *x) ret = ti_pipe3_dpll_wait_lock(phy); } - /* Program the DPLL only if not locked */ + /* SATA has issues if re-programmed when locked */ val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_STATUS); - if (!(val & PLL_LOCK)) - if (ti_pipe3_dpll_program(phy)) - return -EINVAL; + if ((val & PLL_LOCK) && of_device_is_compatible(phy->dev->of_node, + "ti,phy-pipe3-sata")) + return ret; + + /* Program the DPLL */ + ret = ti_pipe3_dpll_program(phy); + if (ret) { + ti_pipe3_disable_clocks(phy); + return -EINVAL; + } return ret; } diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 6b6af6cba454..d9b10a39a2cf 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -463,7 +463,8 @@ static int twl4030_phy_power_on(struct phy *phy) twl4030_usb_set_mode(twl, twl->usb_mode); if (twl->usb_mode == T2_USB_MODE_ULPI) twl4030_i2c_access(twl, 0); - schedule_delayed_work(&twl->id_workaround_work, 0); + twl->linkstat = MUSB_UNKNOWN; + schedule_delayed_work(&twl->id_workaround_work, HZ); return 0; } @@ -537,6 +538,7 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) struct twl4030_usb *twl = _twl; enum musb_vbus_id_status status; bool status_changed = false; + int err; status = twl4030_usb_linkstat(twl); @@ -567,7 +569,9 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) pm_runtime_mark_last_busy(twl->dev); pm_runtime_put_autosuspend(twl->dev); } - musb_mailbox(status); + err = musb_mailbox(status); + if (err) + twl->linkstat = MUSB_UNKNOWN; } /* don't schedule during sleep - irq works right then */ @@ -595,7 +599,8 @@ static int twl4030_phy_init(struct phy *phy) struct twl4030_usb *twl = phy_get_drvdata(phy); pm_runtime_get_sync(twl->dev); - schedule_delayed_work(&twl->id_workaround_work, 0); + twl->linkstat = MUSB_UNKNOWN; + schedule_delayed_work(&twl->id_workaround_work, HZ); pm_runtime_mark_last_busy(twl->dev); pm_runtime_put_autosuspend(twl->dev); @@ -763,7 +768,8 @@ static int twl4030_usb_remove(struct platform_device *pdev) if (cable_present(twl->linkstat)) pm_runtime_put_noidle(twl->dev); pm_runtime_mark_last_busy(twl->dev); - pm_runtime_put_sync_suspend(twl->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); + pm_runtime_put_sync(twl->dev); pm_runtime_disable(twl->dev); /* autogate 60MHz ULPI clock, diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index e4bc1151e04f..42a5c1dddfef 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -23,7 +23,7 @@ obj-$(CONFIG_PINCTRL_PISTACHIO) += pinctrl-pistachio.o obj-$(CONFIG_PINCTRL_ROCKCHIP) += pinctrl-rockchip.o obj-$(CONFIG_PINCTRL_SINGLE) += pinctrl-single.o obj-$(CONFIG_PINCTRL_SIRF) += sirf/ -obj-$(CONFIG_PINCTRL_TEGRA) += tegra/ +obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-$(CONFIG_PINCTRL_TZ1090) += pinctrl-tz1090.o obj-$(CONFIG_PINCTRL_TZ1090_PDC) += pinctrl-tz1090-pdc.o obj-$(CONFIG_PINCTRL_U300) += pinctrl-u300.o diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c index 47ccfcc8a647..eccb47480e1d 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx.c +++ b/drivers/pinctrl/freescale/pinctrl-imx.c @@ -209,9 +209,9 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector, pin_reg = &info->pin_regs[pin_id]; if (pin_reg->mux_reg == -1) { - dev_err(ipctl->dev, "Pin(%s) does not support mux function\n", + dev_dbg(ipctl->dev, "Pin(%s) does not support mux function\n", info->pins[pin_id].name); - return -EINVAL; + continue; } if (info->flags & SHARE_MUX_CONF_REG) { diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 677a811b3a6f..7abfd42e8ffd 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -401,9 +401,9 @@ static const struct byt_simple_func_mux byt_score_sata_mux[] = { static const unsigned int byt_score_plt_clk0_pins[] = { 96 }; static const unsigned int byt_score_plt_clk1_pins[] = { 97 }; static const unsigned int byt_score_plt_clk2_pins[] = { 98 }; -static const unsigned int byt_score_plt_clk4_pins[] = { 99 }; -static const unsigned int byt_score_plt_clk5_pins[] = { 100 }; -static const unsigned int byt_score_plt_clk3_pins[] = { 101 }; +static const unsigned int byt_score_plt_clk3_pins[] = { 99 }; +static const unsigned int byt_score_plt_clk4_pins[] = { 100 }; +static const unsigned int byt_score_plt_clk5_pins[] = { 101 }; static const struct byt_simple_func_mux byt_score_plt_clk_mux[] = { SIMPLE_FUNC("plt_clk", 1), }; diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index cf9bafa10acf..bfdf720db270 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -1580,6 +1580,9 @@ static inline void pcs_irq_set(struct pcs_soc_data *pcs_soc, else mask &= ~soc_mask; pcs->write(mask, pcswi->reg); + + /* flush posted write */ + mask = pcs->read(pcswi->reg); raw_spin_unlock(&pcs->lock); } diff --git a/drivers/pinctrl/tegra/Makefile b/drivers/pinctrl/tegra/Makefile index a927379b6794..d9ea2be69cc4 100644 --- a/drivers/pinctrl/tegra/Makefile +++ b/drivers/pinctrl/tegra/Makefile @@ -1,4 +1,4 @@ -obj-y += pinctrl-tegra.o +obj-$(CONFIG_PINCTRL_TEGRA) += pinctrl-tegra.o obj-$(CONFIG_PINCTRL_TEGRA20) += pinctrl-tegra20.o obj-$(CONFIG_PINCTRL_TEGRA30) += pinctrl-tegra30.o obj-$(CONFIG_PINCTRL_TEGRA114) += pinctrl-tegra114.o diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c index 6d8ee3b15872..8abd80dbcbed 100644 --- a/drivers/platform/chrome/cros_ec_dev.c +++ b/drivers/platform/chrome/cros_ec_dev.c @@ -151,13 +151,19 @@ static long ec_device_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg) goto exit; } + if (u_cmd.outsize != s_cmd->outsize || + u_cmd.insize != s_cmd->insize) { + ret = -EINVAL; + goto exit; + } + s_cmd->command += ec->cmd_offset; ret = cros_ec_cmd_xfer(ec->ec_dev, s_cmd); /* Only copy data to userland if data was received. */ if (ret < 0) goto exit; - if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + u_cmd.insize)) + if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + s_cmd->insize)) ret = -EFAULT; exit: kfree(s_cmd); diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index c06bb85c2839..3ec0025d19e7 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -103,7 +103,6 @@ config DELL_SMBIOS config DELL_LAPTOP tristate "Dell Laptop Extras" - depends on X86 depends on DELL_SMBIOS depends on DMI depends on BACKLIGHT_CLASS_DEVICE @@ -505,7 +504,7 @@ config THINKPAD_ACPI_HOTKEY_POLL config SENSORS_HDAPS tristate "Thinkpad Hard Drive Active Protection System (hdaps)" - depends on INPUT && X86 + depends on INPUT select INPUT_POLLDEV default n help @@ -749,7 +748,7 @@ config TOSHIBA_WMI config ACPI_CMPC tristate "CMPC Laptop Extras" - depends on X86 && ACPI + depends on ACPI depends on RFKILL || RFKILL=n select INPUT select BACKLIGHT_CLASS_DEVICE @@ -848,7 +847,7 @@ config INTEL_IMR config INTEL_PMC_CORE bool "Intel PMC Core driver" - depends on X86 && PCI + depends on PCI ---help--- The Intel Platform Controller Hub for Intel Core SoCs provides access to Power Management Controller registers via a PCI interface. This @@ -860,7 +859,7 @@ config INTEL_PMC_CORE config IBM_RTL tristate "Device driver to enable PRTL support" - depends on X86 && PCI + depends on PCI ---help--- Enable support for IBM Premium Real Time Mode (PRTM). This module will allow you the enter and exit PRTM in the BIOS via @@ -894,7 +893,6 @@ config XO15_EBOOK config SAMSUNG_LAPTOP tristate "Samsung Laptop driver" - depends on X86 depends on RFKILL || RFKILL = n depends on ACPI_VIDEO || ACPI_VIDEO = n depends on BACKLIGHT_CLASS_DEVICE diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 4a23fbc66b71..d1a091b93192 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -567,6 +567,7 @@ static void ideapad_sysfs_exit(struct ideapad_private *priv) static const struct key_entry ideapad_keymap[] = { { KE_KEY, 6, { KEY_SWITCHVIDEOMODE } }, { KE_KEY, 7, { KEY_CAMERA } }, + { KE_KEY, 8, { KEY_MICMUTE } }, { KE_KEY, 11, { KEY_F16 } }, { KE_KEY, 13, { KEY_WLAN } }, { KE_KEY, 16, { KEY_PROG1 } }, @@ -809,6 +810,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) break; case 13: case 11: + case 8: case 7: case 6: ideapad_input_report(priv, vpc_bit); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index c3bfa1fe95bf..b65ce7519411 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -2043,6 +2043,7 @@ static int hotkey_autosleep_ack; static u32 hotkey_orig_mask; /* events the BIOS had enabled */ static u32 hotkey_all_mask; /* all events supported in fw */ +static u32 hotkey_adaptive_all_mask; /* all adaptive events supported in fw */ static u32 hotkey_reserved_mask; /* events better left disabled */ static u32 hotkey_driver_mask; /* events needed by the driver */ static u32 hotkey_user_mask; /* events visible to userspace */ @@ -2742,6 +2743,17 @@ static ssize_t hotkey_all_mask_show(struct device *dev, static DEVICE_ATTR_RO(hotkey_all_mask); +/* sysfs hotkey all_mask ----------------------------------------------- */ +static ssize_t hotkey_adaptive_all_mask_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "0x%08x\n", + hotkey_adaptive_all_mask | hotkey_source_mask); +} + +static DEVICE_ATTR_RO(hotkey_adaptive_all_mask); + /* sysfs hotkey recommended_mask --------------------------------------- */ static ssize_t hotkey_recommended_mask_show(struct device *dev, struct device_attribute *attr, @@ -2985,6 +2997,7 @@ static struct attribute *hotkey_attributes[] __initdata = { &dev_attr_wakeup_hotunplug_complete.attr, &dev_attr_hotkey_mask.attr, &dev_attr_hotkey_all_mask.attr, + &dev_attr_hotkey_adaptive_all_mask.attr, &dev_attr_hotkey_recommended_mask.attr, #ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL &dev_attr_hotkey_source_mask.attr, @@ -3321,20 +3334,6 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) if (!tp_features.hotkey) return 1; - /* - * Check if we have an adaptive keyboard, like on the - * Lenovo Carbon X1 2014 (2nd Gen). - */ - if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) { - if ((hkeyv >> 8) == 2) { - tp_features.has_adaptive_kbd = true; - res = sysfs_create_group(&tpacpi_pdev->dev.kobj, - &adaptive_kbd_attr_group); - if (res) - goto err_exit; - } - } - quirks = tpacpi_check_quirks(tpacpi_hotkey_qtable, ARRAY_SIZE(tpacpi_hotkey_qtable)); @@ -3357,30 +3356,70 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) A30, R30, R31, T20-22, X20-21, X22-24. Detected by checking for HKEY interface version 0x100 */ if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) { - if ((hkeyv >> 8) != 1) { - pr_err("unknown version of the HKEY interface: 0x%x\n", - hkeyv); - pr_err("please report this to %s\n", TPACPI_MAIL); - } else { + vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_HKEY, + "firmware HKEY interface version: 0x%x\n", + hkeyv); + + switch (hkeyv >> 8) { + case 1: /* * MHKV 0x100 in A31, R40, R40e, * T4x, X31, and later */ - vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_HKEY, - "firmware HKEY interface version: 0x%x\n", - hkeyv); /* Paranoia check AND init hotkey_all_mask */ if (!acpi_evalf(hkey_handle, &hotkey_all_mask, "MHKA", "qd")) { - pr_err("missing MHKA handler, " - "please report this to %s\n", + pr_err("missing MHKA handler, please report this to %s\n", TPACPI_MAIL); /* Fallback: pre-init for FN+F3,F4,F12 */ hotkey_all_mask = 0x080cU; } else { tp_features.hotkey_mask = 1; } + break; + + case 2: + /* + * MHKV 0x200 in X1, T460s, X260, T560, X1 Tablet (2016) + */ + + /* Paranoia check AND init hotkey_all_mask */ + if (!acpi_evalf(hkey_handle, &hotkey_all_mask, + "MHKA", "dd", 1)) { + pr_err("missing MHKA handler, please report this to %s\n", + TPACPI_MAIL); + /* Fallback: pre-init for FN+F3,F4,F12 */ + hotkey_all_mask = 0x080cU; + } else { + tp_features.hotkey_mask = 1; + } + + /* + * Check if we have an adaptive keyboard, like on the + * Lenovo Carbon X1 2014 (2nd Gen). + */ + if (acpi_evalf(hkey_handle, &hotkey_adaptive_all_mask, + "MHKA", "dd", 2)) { + if (hotkey_adaptive_all_mask != 0) { + tp_features.has_adaptive_kbd = true; + res = sysfs_create_group( + &tpacpi_pdev->dev.kobj, + &adaptive_kbd_attr_group); + if (res) + goto err_exit; + } + } else { + tp_features.has_adaptive_kbd = false; + hotkey_adaptive_all_mask = 0x0U; + } + break; + + default: + pr_err("unknown version of the HKEY interface: 0x%x\n", + hkeyv); + pr_err("please report this to %s\n", TPACPI_MAIL); + break; } } diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c index 456987c88baa..b13cd074c52a 100644 --- a/drivers/power/power_supply_core.c +++ b/drivers/power/power_supply_core.c @@ -565,11 +565,12 @@ static int power_supply_read_temp(struct thermal_zone_device *tzd, WARN_ON(tzd == NULL); psy = tzd->devdata; - ret = psy->desc->get_property(psy, POWER_SUPPLY_PROP_TEMP, &val); + ret = power_supply_get_property(psy, POWER_SUPPLY_PROP_TEMP, &val); + if (ret) + return ret; /* Convert tenths of degree Celsius to milli degree Celsius. */ - if (!ret) - *temp = val.intval * 100; + *temp = val.intval * 100; return ret; } @@ -612,10 +613,12 @@ static int ps_get_max_charge_cntl_limit(struct thermal_cooling_device *tcd, int ret; psy = tcd->devdata; - ret = psy->desc->get_property(psy, - POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val); - if (!ret) - *state = val.intval; + ret = power_supply_get_property(psy, + POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val); + if (ret) + return ret; + + *state = val.intval; return ret; } @@ -628,10 +631,12 @@ static int ps_get_cur_chrage_cntl_limit(struct thermal_cooling_device *tcd, int ret; psy = tcd->devdata; - ret = psy->desc->get_property(psy, - POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val); - if (!ret) - *state = val.intval; + ret = power_supply_get_property(psy, + POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val); + if (ret) + return ret; + + *state = val.intval; return ret; } diff --git a/drivers/power/tps65217_charger.c b/drivers/power/tps65217_charger.c index d9f56730c735..73dfae41def8 100644 --- a/drivers/power/tps65217_charger.c +++ b/drivers/power/tps65217_charger.c @@ -197,6 +197,7 @@ static int tps65217_charger_probe(struct platform_device *pdev) { struct tps65217 *tps = dev_get_drvdata(pdev->dev.parent); struct tps65217_charger *charger; + struct power_supply_config cfg = {}; int ret; dev_dbg(&pdev->dev, "%s\n", __func__); @@ -208,9 +209,12 @@ static int tps65217_charger_probe(struct platform_device *pdev) charger->tps = tps; charger->dev = &pdev->dev; + cfg.of_node = pdev->dev.of_node; + cfg.drv_data = charger; + charger->ac = devm_power_supply_register(&pdev->dev, &tps65217_charger_desc, - NULL); + &cfg); if (IS_ERR(charger->ac)) { dev_err(&pdev->dev, "failed: power supply register\n"); return PTR_ERR(charger->ac); diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c index 38a8bbe74810..83797d89c30f 100644 --- a/drivers/pps/clients/pps_parport.c +++ b/drivers/pps/clients/pps_parport.c @@ -195,7 +195,7 @@ static void parport_detach(struct parport *port) struct pps_client_pp *device; /* FIXME: oooh, this is ugly! */ - if (strcmp(pardev->name, KBUILD_MODNAME)) + if (!pardev || strcmp(pardev->name, KBUILD_MODNAME)) /* not our port */ return; diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index dba3843c53b8..ed337a8c34ab 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -457,7 +457,8 @@ int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state) { int err; - if (!pwm) + if (!pwm || !state || !state->period || + state->duty_cycle > state->period) return -EINVAL; if (!memcmp(state, &pwm->state, sizeof(*state))) diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c index f994c7eaf41c..14fc011faa32 100644 --- a/drivers/pwm/pwm-atmel-hlcdc.c +++ b/drivers/pwm/pwm-atmel-hlcdc.c @@ -272,7 +272,7 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev) chip->chip.of_pwm_n_cells = 3; chip->chip.can_sleep = 1; - ret = pwmchip_add(&chip->chip); + ret = pwmchip_add_with_polarity(&chip->chip, PWM_POLARITY_INVERSED); if (ret) { clk_disable_unprepare(hlcdc->periph_clk); return ret; diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index d98599249a05..01695d48dd54 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -152,7 +152,7 @@ static ssize_t enable_store(struct device *child, goto unlock; } - pwm_apply_state(pwm, &state); + ret = pwm_apply_state(pwm, &state); unlock: mutex_unlock(&export->lock); diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c index 63cd5e68c864..3a6d0290c54c 100644 --- a/drivers/regulator/anatop-regulator.c +++ b/drivers/regulator/anatop-regulator.c @@ -296,7 +296,7 @@ static int anatop_regulator_probe(struct platform_device *pdev) if (!sreg->sel && !strcmp(sreg->name, "vddpu")) sreg->sel = 22; - if (!sreg->sel) { + if (!sreg->bypass && !sreg->sel) { dev_err(&pdev->dev, "Failed to read a valid default voltage selector.\n"); return -EINVAL; } diff --git a/drivers/regulator/max77620-regulator.c b/drivers/regulator/max77620-regulator.c index 321e804aeab0..a1b49a6d538f 100644 --- a/drivers/regulator/max77620-regulator.c +++ b/drivers/regulator/max77620-regulator.c @@ -123,6 +123,9 @@ static int max77620_regulator_set_fps_src(struct max77620_regulator *pmic, unsigned int val; int ret; + if (!rinfo) + return 0; + switch (fps_src) { case MAX77620_FPS_SRC_0: case MAX77620_FPS_SRC_1: @@ -171,6 +174,9 @@ static int max77620_regulator_set_fps_slots(struct max77620_regulator *pmic, int pd = rpdata->active_fps_pd_slot; int ret = 0; + if (!rinfo) + return 0; + if (is_suspend) { pu = rpdata->suspend_fps_pu_slot; pd = rpdata->suspend_fps_pd_slot; @@ -680,7 +686,6 @@ static struct max77620_regulator_info max77620_regs_info[MAX77620_NUM_REGS] = { RAIL_SD(SD1, sd1, "in-sd1", SD1, 600000, 1550000, 12500, 0x22, SD1), RAIL_SD(SD2, sd2, "in-sd2", SDX, 600000, 3787500, 12500, 0xFF, NONE), RAIL_SD(SD3, sd3, "in-sd3", SDX, 600000, 3787500, 12500, 0xFF, NONE), - RAIL_SD(SD4, sd4, "in-sd4", SDX, 600000, 3787500, 12500, 0xFF, NONE), RAIL_LDO(LDO0, ldo0, "in-ldo0-1", N, 800000, 2375000, 25000), RAIL_LDO(LDO1, ldo1, "in-ldo0-1", N, 800000, 2375000, 25000), diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c index 56a17ec5b5ef..6c7fe4778793 100644 --- a/drivers/regulator/qcom_smd-regulator.c +++ b/drivers/regulator/qcom_smd-regulator.c @@ -140,6 +140,18 @@ static const struct regulator_ops rpm_smps_ldo_ops = { .enable = rpm_reg_enable, .disable = rpm_reg_disable, .is_enabled = rpm_reg_is_enabled, + .list_voltage = regulator_list_voltage_linear_range, + + .get_voltage = rpm_reg_get_voltage, + .set_voltage = rpm_reg_set_voltage, + + .set_load = rpm_reg_set_load, +}; + +static const struct regulator_ops rpm_smps_ldo_ops_fixed = { + .enable = rpm_reg_enable, + .disable = rpm_reg_disable, + .is_enabled = rpm_reg_is_enabled, .get_voltage = rpm_reg_get_voltage, .set_voltage = rpm_reg_set_voltage, @@ -247,7 +259,7 @@ static const struct regulator_desc pm8941_nldo = { static const struct regulator_desc pm8941_lnldo = { .fixed_uV = 1740000, .n_voltages = 1, - .ops = &rpm_smps_ldo_ops, + .ops = &rpm_smps_ldo_ops_fixed, }; static const struct regulator_desc pm8941_switch = { diff --git a/drivers/regulator/tps51632-regulator.c b/drivers/regulator/tps51632-regulator.c index 572816e30095..c139890c1514 100644 --- a/drivers/regulator/tps51632-regulator.c +++ b/drivers/regulator/tps51632-regulator.c @@ -94,11 +94,14 @@ static int tps51632_dcdc_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) { struct tps51632_chip *tps = rdev_get_drvdata(rdev); - int bit = ramp_delay/6000; + int bit; int ret; - if (bit) - bit--; + if (ramp_delay == 0) + bit = 0; + else + bit = DIV_ROUND_UP(ramp_delay, 6000) - 1; + ret = regmap_write(tps->regmap, TPS51632_SLEW_REGS, BIT(bit)); if (ret < 0) dev_err(tps->dev, "SLEW reg write failed, err %d\n", ret); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 80b1979e8d95..df036b872b05 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1051,6 +1051,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) qeth_l2_set_offline(cgdev); if (card->dev) { + netif_napi_del(&card->napi); unregister_netdev(card->dev); card->dev = NULL; } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index ac544330daeb..709b52339ff9 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3226,6 +3226,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) qeth_l3_set_offline(cgdev); if (card->dev) { + netif_napi_del(&card->napi); unregister_netdev(card->dev); card->dev = NULL; } diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index d4c285688ce9..3ddc85e6efd6 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1122,7 +1122,7 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp, } else { struct scsi_cmnd *SCp; - SCp = scsi_host_find_tag(SDp->host, SCSI_NO_TAG); + SCp = SDp->current_cmnd; if(unlikely(SCp == NULL)) { sdev_printk(KERN_ERR, SDp, "no saved request for untagged cmd\n"); @@ -1826,7 +1826,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *) slot->tag, slot); } else { slot->tag = SCSI_NO_TAG; - /* must populate current_cmnd for scsi_host_find_tag to work */ + /* save current command for reselection */ SCp->device->current_cmnd = SCp; } /* sanity check: some of the commands generated by the mid-layer diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index d6a691e27d33..d6803a9e5ab8 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -10093,6 +10093,7 @@ static int ipr_probe_ioa(struct pci_dev *pdev, ioa_cfg->intr_flag = IPR_USE_MSI; else { ioa_cfg->intr_flag = IPR_USE_LSI; + ioa_cfg->clear_isr = 1; ioa_cfg->nvectors = 1; dev_info(&pdev->dev, "Cannot enable MSI.\n"); } diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 5649c200d37c..a92a62dea793 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2548,7 +2548,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, if (!vha->flags.online) return; - if (rsp->msix->cpuid != smp_processor_id()) { + if (rsp->msix && rsp->msix->cpuid != smp_processor_id()) { /* if kernel does not notify qla of IRQ's CPU change, * then set it here. */ diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index ff41c310c900..eaccd651ccda 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -429,7 +429,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, * here, and we don't know what device it is * trying to work with, leave it as-is. */ - vmax = 8; /* max length of vendor */ + vmax = sizeof(devinfo->vendor); vskip = vendor; while (vmax > 0 && *vskip == ' ') { vmax--; @@ -439,7 +439,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, while (vmax > 0 && vskip[vmax - 1] == ' ') --vmax; - mmax = 16; /* max length of model */ + mmax = sizeof(devinfo->model); mskip = model; while (mmax > 0 && *mskip == ' ') { mmax--; @@ -455,10 +455,12 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, * Behave like the older version of get_device_flags. */ if (memcmp(devinfo->vendor, vskip, vmax) || - devinfo->vendor[vmax]) + (vmax < sizeof(devinfo->vendor) && + devinfo->vendor[vmax])) continue; if (memcmp(devinfo->model, mskip, mmax) || - devinfo->model[mmax]) + (mmax < sizeof(devinfo->model) && + devinfo->model[mmax])) continue; return devinfo; } else { diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index a8b610eaa0ca..106a6adbd6f1 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1128,7 +1128,6 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn) */ void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q) { - scmd->device->host->host_failed--; scmd->eh_eflags = 0; list_move_tail(&scmd->eh_entry, done_q); } @@ -2227,6 +2226,9 @@ int scsi_error_handler(void *data) else scsi_unjam_host(shost); + /* All scmds have been handled */ + shost->host_failed = 0; + /* * Note - if the above fails completely, the action is to take * individual devices offline and flush the queue of any diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index cd89682065b9..1026e180eed7 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -578,7 +578,7 @@ static int rockchip_spi_transfer_one( struct spi_device *spi, struct spi_transfer *xfer) { - int ret = 1; + int ret = 0; struct rockchip_spi *rs = spi_master_get_devdata(master); WARN_ON(readl_relaxed(rs->regs + ROCKCHIP_SPI_SSIENR) && @@ -627,6 +627,8 @@ static int rockchip_spi_transfer_one( spi_enable_chip(rs, 1); ret = rockchip_spi_prepare_dma(rs); } + /* successful DMA prepare means the transfer is in progress */ + ret = ret ? ret : 1; } else { spi_enable_chip(rs, 1); ret = rockchip_spi_pio_transfer(rs); diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c index 1ddd9e2309b6..cf007f3b83ec 100644 --- a/drivers/spi/spi-sun4i.c +++ b/drivers/spi/spi-sun4i.c @@ -173,13 +173,17 @@ static int sun4i_spi_transfer_one(struct spi_master *master, { struct sun4i_spi *sspi = spi_master_get_devdata(master); unsigned int mclk_rate, div, timeout; + unsigned int start, end, tx_time; unsigned int tx_len = 0; int ret = 0; u32 reg; /* We don't support transfer larger than the FIFO */ if (tfr->len > SUN4I_FIFO_DEPTH) - return -EINVAL; + return -EMSGSIZE; + + if (tfr->tx_buf && tfr->len >= SUN4I_FIFO_DEPTH) + return -EMSGSIZE; reinit_completion(&sspi->done); sspi->tx_buf = tfr->tx_buf; @@ -269,8 +273,12 @@ static int sun4i_spi_transfer_one(struct spi_master *master, sun4i_spi_write(sspi, SUN4I_BURST_CNT_REG, SUN4I_BURST_CNT(tfr->len)); sun4i_spi_write(sspi, SUN4I_XMIT_CNT_REG, SUN4I_XMIT_CNT(tx_len)); - /* Fill the TX FIFO */ - sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH); + /* + * Fill the TX FIFO + * Filling the FIFO fully causes timeout for some reason + * at least on spi2 on A10s + */ + sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH - 1); /* Enable the interrupts */ sun4i_spi_write(sspi, SUN4I_INT_CTL_REG, SUN4I_INT_CTL_TC); @@ -279,9 +287,16 @@ static int sun4i_spi_transfer_one(struct spi_master *master, reg = sun4i_spi_read(sspi, SUN4I_CTL_REG); sun4i_spi_write(sspi, SUN4I_CTL_REG, reg | SUN4I_CTL_XCH); + tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U); + start = jiffies; timeout = wait_for_completion_timeout(&sspi->done, - msecs_to_jiffies(1000)); + msecs_to_jiffies(tx_time)); + end = jiffies; if (!timeout) { + dev_warn(&master->dev, + "%s: timeout transferring %u bytes@%iHz for %i(%i)ms", + dev_name(&spi->dev), tfr->len, tfr->speed_hz, + jiffies_to_msecs(end - start), tx_time); ret = -ETIMEDOUT; goto out; } diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c index 42e2c4bd690a..7fce79a60608 100644 --- a/drivers/spi/spi-sun6i.c +++ b/drivers/spi/spi-sun6i.c @@ -160,6 +160,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master, { struct sun6i_spi *sspi = spi_master_get_devdata(master); unsigned int mclk_rate, div, timeout; + unsigned int start, end, tx_time; unsigned int tx_len = 0; int ret = 0; u32 reg; @@ -269,9 +270,16 @@ static int sun6i_spi_transfer_one(struct spi_master *master, reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG); sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH); + tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U); + start = jiffies; timeout = wait_for_completion_timeout(&sspi->done, - msecs_to_jiffies(1000)); + msecs_to_jiffies(tx_time)); + end = jiffies; if (!timeout) { + dev_warn(&master->dev, + "%s: timeout transferring %u bytes@%iHz for %i(%i)ms", + dev_name(&spi->dev), tfr->len, tfr->speed_hz, + jiffies_to_msecs(end - start), tx_time); ret = -ETIMEDOUT; goto out; } diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index 443f664534e1..29ea8d2f9824 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -646,6 +646,13 @@ free_master: static int ti_qspi_remove(struct platform_device *pdev) { + struct ti_qspi *qspi = platform_get_drvdata(pdev); + int rc; + + rc = spi_master_suspend(qspi->master); + if (rc) + return rc; + pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c index a8f533af9eca..ec12181822e6 100644 --- a/drivers/staging/iio/accel/sca3000_core.c +++ b/drivers/staging/iio/accel/sca3000_core.c @@ -594,7 +594,7 @@ static ssize_t sca3000_read_frequency(struct device *dev, goto error_ret_mut; ret = sca3000_read_ctrl_reg(st, SCA3000_REG_CTRL_SEL_OUT_CTRL); mutex_unlock(&st->lock); - if (ret) + if (ret < 0) goto error_ret; val = ret; if (base_freq > 0) diff --git a/drivers/staging/iio/adc/ad7606_spi.c b/drivers/staging/iio/adc/ad7606_spi.c index 825da0769936..9587fa86dc69 100644 --- a/drivers/staging/iio/adc/ad7606_spi.c +++ b/drivers/staging/iio/adc/ad7606_spi.c @@ -21,7 +21,7 @@ static int ad7606_spi_read_block(struct device *dev, { struct spi_device *spi = to_spi_device(dev); int i, ret; - unsigned short *data; + unsigned short *data = buf; __be16 *bdata = buf; ret = spi_read(spi, buf, count * 2); diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 9f43976f4ef2..170ac980abcb 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -444,10 +444,10 @@ static ssize_t ad5933_store(struct device *dev, st->settling_cycles = val; /* 2x, 4x handling, see datasheet */ - if (val > 511) - val = (val >> 1) | (1 << 9); - else if (val > 1022) + if (val > 1022) val = (val >> 2) | (3 << 9); + else if (val > 511) + val = (val >> 1) | (1 << 9); dat = cpu_to_be16(val); ret = ad5933_i2c_write(st->client, diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c index bbfee53cfcf5..845e49a52430 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c @@ -2521,12 +2521,13 @@ kiblnd_passive_connect(struct rdma_cm_id *cmid, void *priv, int priv_nob) return 0; failed: - if (ni) + if (ni) { lnet_ni_decref(ni); + rej.ibr_cp.ibcp_queue_depth = kiblnd_msg_queue_size(version, ni); + rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni); + } rej.ibr_version = version; - rej.ibr_cp.ibcp_queue_depth = kiblnd_msg_queue_size(version, ni); - rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni); kiblnd_reject(cmid, &rej); return -ECONNREFUSED; diff --git a/drivers/staging/rtl8188eu/core/rtw_efuse.c b/drivers/staging/rtl8188eu/core/rtw_efuse.c index c17870cddb5b..fbce1f7e68ca 100644 --- a/drivers/staging/rtl8188eu/core/rtw_efuse.c +++ b/drivers/staging/rtl8188eu/core/rtw_efuse.c @@ -102,7 +102,7 @@ efuse_phymap_to_logical(u8 *phymap, u16 _offset, u16 _size_byte, u8 *pbuf) if (!efuseTbl) return; - eFuseWord = (u16 **)rtw_malloc2d(EFUSE_MAX_SECTION_88E, EFUSE_MAX_WORD_UNIT, sizeof(*eFuseWord)); + eFuseWord = (u16 **)rtw_malloc2d(EFUSE_MAX_SECTION_88E, EFUSE_MAX_WORD_UNIT, sizeof(u16)); if (!eFuseWord) { DBG_88E("%s: alloc eFuseWord fail!\n", __func__); goto eFuseWord_failed; diff --git a/drivers/staging/rtl8188eu/hal/usb_halinit.c b/drivers/staging/rtl8188eu/hal/usb_halinit.c index 87ea3b844951..363f3a34ddce 100644 --- a/drivers/staging/rtl8188eu/hal/usb_halinit.c +++ b/drivers/staging/rtl8188eu/hal/usb_halinit.c @@ -2072,7 +2072,8 @@ void rtl8188eu_set_hal_ops(struct adapter *adapt) { struct hal_ops *halfunc = &adapt->HalFunc; - adapt->HalData = kzalloc(sizeof(*adapt->HalData), GFP_KERNEL); + + adapt->HalData = kzalloc(sizeof(struct hal_data_8188e), GFP_KERNEL); if (!adapt->HalData) DBG_88E("cant not alloc memory for HAL DATA\n"); diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index f856c4544eea..51e0d32883ba 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -667,8 +667,11 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) fsi = tty->driver_data; else fsi = tty->link->driver_data; - devpts_kill_index(fsi, tty->index); - devpts_release(fsi); + + if (fsi) { + devpts_kill_index(fsi, tty->index); + devpts_release(fsi); + } } static const struct tty_operations ptm_unix98_ops = { diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index f973bfce5d08..1e93a37e27f0 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -366,34 +366,22 @@ static void to_utf8(struct vc_data *vc, uint c) static void do_compute_shiftstate(void) { - unsigned int i, j, k, sym, val; + unsigned int k, sym, val; shift_state = 0; memset(shift_down, 0, sizeof(shift_down)); - for (i = 0; i < ARRAY_SIZE(key_down); i++) { - - if (!key_down[i]) + for_each_set_bit(k, key_down, min(NR_KEYS, KEY_CNT)) { + sym = U(key_maps[0][k]); + if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK) continue; - k = i * BITS_PER_LONG; - - for (j = 0; j < BITS_PER_LONG; j++, k++) { - - if (!test_bit(k, key_down)) - continue; + val = KVAL(sym); + if (val == KVAL(K_CAPSSHIFT)) + val = KVAL(K_SHIFT); - sym = U(key_maps[0][k]); - if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK) - continue; - - val = KVAL(sym); - if (val == KVAL(K_CAPSSHIFT)) - val = KVAL(K_SHIFT); - - shift_down[val]++; - shift_state |= (1 << val); - } + shift_down[val]++; + shift_state |= BIT(val); } } diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index dc125322f48f..5b0fe97c46ca 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -750,6 +750,7 @@ static void visual_init(struct vc_data *vc, int num, int init) vc->vc_complement_mask = 0; vc->vc_can_do_color = 0; vc->vc_panic_force_write = false; + vc->vc_cur_blink_ms = DEFAULT_CURSOR_BLINK_MS; vc->vc_sw->con_init(vc, init); if (!vc->vc_complement_mask) vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800; diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c index 9059b7dc185e..2f537bbdda09 100644 --- a/drivers/usb/common/usb-otg-fsm.c +++ b/drivers/usb/common/usb-otg-fsm.c @@ -21,6 +21,7 @@ * 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include #include #include #include @@ -450,3 +451,4 @@ int otg_statemachine(struct otg_fsm *fsm) return fsm->state_changed; } EXPORT_SYMBOL_GPL(otg_statemachine); +MODULE_LICENSE("GPL"); diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 34b837ae1ed7..d2e3f655c26f 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2598,26 +2598,23 @@ EXPORT_SYMBOL_GPL(usb_create_hcd); * Don't deallocate the bandwidth_mutex until the last shared usb_hcd is * deallocated. * - * Make sure to only deallocate the bandwidth_mutex when the primary HCD is - * freed. When hcd_release() is called for either hcd in a peer set - * invalidate the peer's ->shared_hcd and ->primary_hcd pointers to - * block new peering attempts + * Make sure to deallocate the bandwidth_mutex only when the last HCD is + * freed. When hcd_release() is called for either hcd in a peer set, + * invalidate the peer's ->shared_hcd and ->primary_hcd pointers. */ static void hcd_release(struct kref *kref) { struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref); mutex_lock(&usb_port_peer_mutex); - if (usb_hcd_is_primary_hcd(hcd)) { - kfree(hcd->address0_mutex); - kfree(hcd->bandwidth_mutex); - } if (hcd->shared_hcd) { struct usb_hcd *peer = hcd->shared_hcd; peer->shared_hcd = NULL; - if (peer->primary_hcd == hcd) - peer->primary_hcd = NULL; + peer->primary_hcd = NULL; + } else { + kfree(hcd->address0_mutex); + kfree(hcd->bandwidth_mutex); } mutex_unlock(&usb_port_peer_mutex); kfree(hcd); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 6dc810bce295..944a6dca0fcb 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -44,6 +44,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Creative SB Audigy 2 NX */ { USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME }, + /* USB3503 */ + { USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Microsoft Wireless Laser Mouse 6000 Receiver */ { USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -173,6 +176,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* MAYA44USB sound device */ { USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME }, + /* ASUS Base Station(T100) */ + { USB_DEVICE(0x0b05, 0x17e0), .driver_info = + USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Action Semiconductor flash disk */ { USB_DEVICE(0x10d6, 0x2200), .driver_info = USB_QUIRK_STRING_FETCH_255 }, @@ -188,26 +195,22 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1908, 0x1315), .driver_info = USB_QUIRK_HONOR_BNUMINTERFACES }, - /* INTEL VALUE SSD */ - { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, - - /* USB3503 */ - { USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME }, - - /* ASUS Base Station(T100) */ - { USB_DEVICE(0x0b05, 0x17e0), .driver_info = - USB_QUIRK_IGNORE_REMOTE_WAKEUP }, - /* Protocol and OTG Electrical Test Device */ { USB_DEVICE(0x1a0a, 0x0200), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Acer C120 LED Projector */ + { USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM }, + /* Blackmagic Design Intensity Shuttle */ { USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM }, /* Blackmagic Design UltraStudio SDI */ { USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM }, + /* INTEL VALUE SSD */ + { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, + { } /* terminating entry must be last */ }; diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index 3c58d633ce80..dec0b21fc626 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -64,6 +64,17 @@ DWC2_TRACE_SCHEDULER_VB(pr_fmt("%s: SCH: " fmt), \ dev_name(hsotg->dev), ##__VA_ARGS__) +#ifdef CONFIG_MIPS +/* + * There are some MIPS machines that can run in either big-endian + * or little-endian mode and that use the dwc2 register without + * a byteswap in both ways. + * Unlike other architectures, MIPS apparently does not require a + * barrier before the __raw_writel() to synchronize with DMA but does + * require the barrier after the __raw_writel() to serialize a set of + * writes. This set of operations was added specifically for MIPS and + * should only be used there. + */ static inline u32 dwc2_readl(const void __iomem *addr) { u32 value = __raw_readl(addr); @@ -90,6 +101,22 @@ static inline void dwc2_writel(u32 value, void __iomem *addr) pr_info("INFO:: wrote %08x to %p\n", value, addr); #endif } +#else +/* Normal architectures just use readl/write */ +static inline u32 dwc2_readl(const void __iomem *addr) +{ + return readl(addr); +} + +static inline void dwc2_writel(u32 value, void __iomem *addr) +{ + writel(value, addr); + +#ifdef DWC2_LOG_WRITES + pr_info("info:: wrote %08x to %p\n", value, addr); +#endif +} +#endif /* Maximum number of Endpoints/HostChannels */ #define MAX_EPS_CHANNELS 16 diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 4c5e3005e1dc..26cf09d0fe3c 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1018,7 +1018,7 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg, return 1; } -static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value); +static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now); /** * get_ep_head - return the first request on the endpoint @@ -1094,7 +1094,7 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg, case USB_ENDPOINT_HALT: halted = ep->halted; - dwc2_hsotg_ep_sethalt(&ep->ep, set); + dwc2_hsotg_ep_sethalt(&ep->ep, set, true); ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0); if (ret) { @@ -2948,8 +2948,13 @@ static int dwc2_hsotg_ep_dequeue(struct usb_ep *ep, struct usb_request *req) * dwc2_hsotg_ep_sethalt - set halt on a given endpoint * @ep: The endpoint to set halt. * @value: Set or unset the halt. + * @now: If true, stall the endpoint now. Otherwise return -EAGAIN if + * the endpoint is busy processing requests. + * + * We need to stall the endpoint immediately if request comes from set_feature + * protocol command handler. */ -static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value) +static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now) { struct dwc2_hsotg_ep *hs_ep = our_ep(ep); struct dwc2_hsotg *hs = hs_ep->parent; @@ -2969,6 +2974,17 @@ static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value) return 0; } + if (hs_ep->isochronous) { + dev_err(hs->dev, "%s is Isochronous Endpoint\n", ep->name); + return -EINVAL; + } + + if (!now && value && !list_empty(&hs_ep->queue)) { + dev_dbg(hs->dev, "%s request is pending, cannot halt\n", + ep->name); + return -EAGAIN; + } + if (hs_ep->dir_in) { epreg = DIEPCTL(index); epctl = dwc2_readl(hs->regs + epreg); @@ -3020,7 +3036,7 @@ static int dwc2_hsotg_ep_sethalt_lock(struct usb_ep *ep, int value) int ret = 0; spin_lock_irqsave(&hs->lock, flags); - ret = dwc2_hsotg_ep_sethalt(ep, value); + ret = dwc2_hsotg_ep_sethalt(ep, value, false); spin_unlock_irqrestore(&hs->lock, flags); return ret; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 7ddf9449a063..654050684f4f 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -402,6 +402,7 @@ #define DWC3_DEPCMD_GET_RSC_IDX(x) (((x) >> DWC3_DEPCMD_PARAM_SHIFT) & 0x7f) #define DWC3_DEPCMD_STATUS(x) (((x) >> 12) & 0x0F) #define DWC3_DEPCMD_HIPRI_FORCERM (1 << 11) +#define DWC3_DEPCMD_CLEARPENDIN (1 << 11) #define DWC3_DEPCMD_CMDACT (1 << 10) #define DWC3_DEPCMD_CMDIOC (1 << 8) diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index dd5cb5577dca..2f1fb7e7aa54 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -128,12 +128,6 @@ static int dwc3_exynos_probe(struct platform_device *pdev) platform_set_drvdata(pdev, exynos); - ret = dwc3_exynos_register_phys(exynos); - if (ret) { - dev_err(dev, "couldn't register PHYs\n"); - return ret; - } - exynos->dev = dev; exynos->clk = devm_clk_get(dev, "usbdrd30"); @@ -183,20 +177,29 @@ static int dwc3_exynos_probe(struct platform_device *pdev) goto err3; } + ret = dwc3_exynos_register_phys(exynos); + if (ret) { + dev_err(dev, "couldn't register PHYs\n"); + goto err4; + } + if (node) { ret = of_platform_populate(node, NULL, NULL, dev); if (ret) { dev_err(dev, "failed to add dwc3 core\n"); - goto err4; + goto err5; } } else { dev_err(dev, "no device node, failed to add dwc3 core\n"); ret = -ENODEV; - goto err4; + goto err5; } return 0; +err5: + platform_device_unregister(exynos->usb2_phy); + platform_device_unregister(exynos->usb3_phy); err4: regulator_disable(exynos->vdd10); err3: diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c index 5c0adb9c6fb2..89a2f712fdfe 100644 --- a/drivers/usb/dwc3/dwc3-st.c +++ b/drivers/usb/dwc3/dwc3-st.c @@ -129,12 +129,18 @@ static int st_dwc3_drd_init(struct st_dwc3 *dwc3_data) switch (dwc3_data->dr_mode) { case USB_DR_MODE_PERIPHERAL: - val &= ~(USB3_FORCE_VBUSVALID | USB3_DELAY_VBUSVALID + val &= ~(USB3_DELAY_VBUSVALID | USB3_SEL_FORCE_OPMODE | USB3_FORCE_OPMODE(0x3) | USB3_SEL_FORCE_DPPULLDOWN2 | USB3_FORCE_DPPULLDOWN2 | USB3_SEL_FORCE_DMPULLDOWN2 | USB3_FORCE_DMPULLDOWN2); - val |= USB3_DEVICE_NOT_HOST; + /* + * USB3_PORT2_FORCE_VBUSVALID When '1' and when + * USB3_PORT2_DEVICE_NOT_HOST = 1, forces VBUSVLDEXT2 input + * of the pico PHY to 1. + */ + + val |= USB3_DEVICE_NOT_HOST | USB3_FORCE_VBUSVALID; break; case USB_DR_MODE_HOST: @@ -227,7 +233,8 @@ static int st_dwc3_probe(struct platform_device *pdev) dev_vdbg(&pdev->dev, "glue-logic addr 0x%p, syscfg-reg offset 0x%x\n", dwc3_data->glue_base, dwc3_data->syscfg_reg_off); - dwc3_data->rstc_pwrdn = devm_reset_control_get(dev, "powerdown"); + dwc3_data->rstc_pwrdn = + devm_reset_control_get_exclusive(dev, "powerdown"); if (IS_ERR(dwc3_data->rstc_pwrdn)) { dev_err(&pdev->dev, "could not get power controller\n"); ret = PTR_ERR(dwc3_data->rstc_pwrdn); @@ -237,7 +244,8 @@ static int st_dwc3_probe(struct platform_device *pdev) /* Manage PowerDown */ reset_control_deassert(dwc3_data->rstc_pwrdn); - dwc3_data->rstc_rst = devm_reset_control_get(dev, "softreset"); + dwc3_data->rstc_rst = + devm_reset_control_get_shared(dev, "softreset"); if (IS_ERR(dwc3_data->rstc_rst)) { dev_err(&pdev->dev, "could not get reset controller\n"); ret = PTR_ERR(dwc3_data->rstc_rst); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 9a7d0bd15dc3..07248ff1be5c 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -347,6 +347,28 @@ int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep, return ret; } +static int dwc3_send_clear_stall_ep_cmd(struct dwc3_ep *dep) +{ + struct dwc3 *dwc = dep->dwc; + struct dwc3_gadget_ep_cmd_params params; + u32 cmd = DWC3_DEPCMD_CLEARSTALL; + + /* + * As of core revision 2.60a the recommended programming model + * is to set the ClearPendIN bit when issuing a Clear Stall EP + * command for IN endpoints. This is to prevent an issue where + * some (non-compliant) hosts may not send ACK TPs for pending + * IN transfers due to a mishandled error condition. Synopsys + * STAR 9000614252. + */ + if (dep->direction && (dwc->revision >= DWC3_REVISION_260A)) + cmd |= DWC3_DEPCMD_CLEARPENDIN; + + memset(¶ms, 0, sizeof(params)); + + return dwc3_send_gadget_ep_cmd(dwc, dep->number, cmd, ¶ms); +} + static dma_addr_t dwc3_trb_dma_offset(struct dwc3_ep *dep, struct dwc3_trb *trb) { @@ -1314,8 +1336,7 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) else dep->flags |= DWC3_EP_STALL; } else { - ret = dwc3_send_gadget_ep_cmd(dwc, dep->number, - DWC3_DEPCMD_CLEARSTALL, ¶ms); + ret = dwc3_send_clear_stall_ep_cmd(dep); if (ret) dev_err(dwc->dev, "failed to clear STALL on %s\n", dep->name); @@ -2247,7 +2268,6 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc) for (epnum = 1; epnum < DWC3_ENDPOINTS_NUM; epnum++) { struct dwc3_ep *dep; - struct dwc3_gadget_ep_cmd_params params; int ret; dep = dwc->eps[epnum]; @@ -2259,9 +2279,7 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc) dep->flags &= ~DWC3_EP_STALL; - memset(¶ms, 0, sizeof(params)); - ret = dwc3_send_gadget_ep_cmd(dwc, dep->number, - DWC3_DEPCMD_CLEARSTALL, ¶ms); + ret = dwc3_send_clear_stall_ep_cmd(dep); WARN_ON_ONCE(ret); } } diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d67de0d22a2b..eb648485a58c 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1868,14 +1868,19 @@ unknown: } break; } - req->length = value; - req->context = cdev; - req->zero = value < w_length; - value = composite_ep0_queue(cdev, req, GFP_ATOMIC); - if (value < 0) { - DBG(cdev, "ep_queue --> %d\n", value); - req->status = 0; - composite_setup_complete(gadget->ep0, req); + + if (value >= 0) { + req->length = value; + req->context = cdev; + req->zero = value < w_length; + value = composite_ep0_queue(cdev, req, + GFP_ATOMIC); + if (value < 0) { + DBG(cdev, "ep_queue --> %d\n", value); + req->status = 0; + composite_setup_complete(gadget->ep0, + req); + } } return value; } diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index b6f60ca8a035..70cf3477f951 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1401,6 +1401,7 @@ static const struct usb_gadget_driver configfs_driver_template = { .owner = THIS_MODULE, .name = "configfs-gadget", }, + .match_existing_only = 1, }; static struct config_group *gadgets_make( diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 73515d54e1cc..cc33d2667408 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2051,7 +2051,7 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type, if (len < sizeof(*d) || d->bFirstInterfaceNumber >= ffs->interfaces_count || - d->Reserved1) + !d->Reserved1) return -EINVAL; for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i) if (d->Reserved2[i]) @@ -2729,6 +2729,7 @@ static int _ffs_func_bind(struct usb_configuration *c, func->ffs->ss_descs_count; int fs_len, hs_len, ss_len, ret, i; + struct ffs_ep *eps_ptr; /* Make it a single chunk, less management later on */ vla_group(d); @@ -2777,12 +2778,9 @@ static int _ffs_func_bind(struct usb_configuration *c, ffs->raw_descs_length); memset(vla_ptr(vlabuf, d, inums), 0xff, d_inums__sz); - for (ret = ffs->eps_count; ret; --ret) { - struct ffs_ep *ptr; - - ptr = vla_ptr(vlabuf, d, eps); - ptr[ret].num = -1; - } + eps_ptr = vla_ptr(vlabuf, d, eps); + for (i = 0; i < ffs->eps_count; i++) + eps_ptr[i].num = -1; /* Save pointers * d_eps == vlabuf, func->eps used to kfree vlabuf later @@ -2851,7 +2849,7 @@ static int _ffs_func_bind(struct usb_configuration *c, goto error; func->function.os_desc_table = vla_ptr(vlabuf, d, os_desc_table); - if (c->cdev->use_os_string) + if (c->cdev->use_os_string) { for (i = 0; i < ffs->interfaces_count; ++i) { struct usb_os_desc *desc; @@ -2862,13 +2860,15 @@ static int _ffs_func_bind(struct usb_configuration *c, vla_ptr(vlabuf, d, ext_compat) + i * 16; INIT_LIST_HEAD(&desc->ext_prop); } - ret = ffs_do_os_descs(ffs->ms_os_descs_count, - vla_ptr(vlabuf, d, raw_descs) + - fs_len + hs_len + ss_len, - d_raw_descs__sz - fs_len - hs_len - ss_len, - __ffs_func_bind_do_os_desc, func); - if (unlikely(ret < 0)) - goto error; + ret = ffs_do_os_descs(ffs->ms_os_descs_count, + vla_ptr(vlabuf, d, raw_descs) + + fs_len + hs_len + ss_len, + d_raw_descs__sz - fs_len - hs_len - + ss_len, + __ffs_func_bind_do_os_desc, func); + if (unlikely(ret < 0)) + goto error; + } func->function.os_desc_n = c->cdev->use_os_string ? ffs->interfaces_count : 0; diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index c45104e3a64b..64706a789580 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -161,14 +161,6 @@ static struct usb_endpoint_descriptor hs_ep_out_desc = { .wMaxPacketSize = cpu_to_le16(512) }; -static struct usb_qualifier_descriptor dev_qualifier = { - .bLength = sizeof(dev_qualifier), - .bDescriptorType = USB_DT_DEVICE_QUALIFIER, - .bcdUSB = cpu_to_le16(0x0200), - .bDeviceClass = USB_CLASS_PRINTER, - .bNumConfigurations = 1 -}; - static struct usb_descriptor_header *hs_printer_function[] = { (struct usb_descriptor_header *) &intf_desc, (struct usb_descriptor_header *) &hs_ep_in_desc, diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 35fe3c80cfc0..197f73386fac 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1445,16 +1445,18 @@ static void usbg_drop_tpg(struct se_portal_group *se_tpg) for (i = 0; i < TPG_INSTANCES; ++i) if (tpg_instances[i].tpg == tpg) break; - if (i < TPG_INSTANCES) + if (i < TPG_INSTANCES) { tpg_instances[i].tpg = NULL; - opts = container_of(tpg_instances[i].func_inst, - struct f_tcm_opts, func_inst); - mutex_lock(&opts->dep_lock); - if (opts->has_dep) - module_put(opts->dependent); - else - configfs_undepend_item_unlocked(&opts->func_inst.group.cg_item); - mutex_unlock(&opts->dep_lock); + opts = container_of(tpg_instances[i].func_inst, + struct f_tcm_opts, func_inst); + mutex_lock(&opts->dep_lock); + if (opts->has_dep) + module_put(opts->dependent); + else + configfs_undepend_item_unlocked( + &opts->func_inst.group.cg_item); + mutex_unlock(&opts->dep_lock); + } mutex_unlock(&tpg_instances_lock); kfree(tpg); diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 186d4b162524..cd214ec8a601 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -598,18 +598,6 @@ static struct usb_gadget_strings *fn_strings[] = { NULL, }; -static struct usb_qualifier_descriptor devqual_desc = { - .bLength = sizeof devqual_desc, - .bDescriptorType = USB_DT_DEVICE_QUALIFIER, - - .bcdUSB = cpu_to_le16(0x200), - .bDeviceClass = USB_CLASS_MISC, - .bDeviceSubClass = 0x02, - .bDeviceProtocol = 0x01, - .bNumConfigurations = 1, - .bRESERVED = 0, -}; - static struct usb_interface_assoc_descriptor iad_desc = { .bLength = sizeof iad_desc, .bDescriptorType = USB_DT_INTERFACE_ASSOCIATION, @@ -1292,6 +1280,7 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr) if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) { struct cntrl_cur_lay3 c; + memset(&c, 0, sizeof(struct cntrl_cur_lay3)); if (entity_id == USB_IN_CLK_ID) c.dCUR = p_srate; diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c index d62683017cf3..990df221c629 100644 --- a/drivers/usb/gadget/function/storage_common.c +++ b/drivers/usb/gadget/function/storage_common.c @@ -83,9 +83,7 @@ EXPORT_SYMBOL_GPL(fsg_fs_function); * USB 2.0 devices need to expose both high speed and full speed * descriptors, unless they only run at full speed. * - * That means alternate endpoint descriptors (bigger packets) - * and a "device qualifier" ... plus more construction options - * for the configuration descriptor. + * That means alternate endpoint descriptors (bigger packets). */ struct usb_endpoint_descriptor fsg_hs_bulk_in_desc = { .bLength = USB_DT_ENDPOINT_SIZE, diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index e64479f882a5..aa3707bdebb4 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -938,8 +938,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) struct usb_ep *ep = dev->gadget->ep0; struct usb_request *req = dev->req; - if ((retval = setup_req (ep, req, 0)) == 0) - retval = usb_ep_queue (ep, req, GFP_ATOMIC); + if ((retval = setup_req (ep, req, 0)) == 0) { + spin_unlock_irq (&dev->lock); + retval = usb_ep_queue (ep, req, GFP_KERNEL); + spin_lock_irq (&dev->lock); + } dev->state = STATE_DEV_CONNECTED; /* assume that was SET_CONFIGURATION */ @@ -1457,8 +1460,11 @@ delegate: w_length); if (value < 0) break; + + spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, dev->req, - GFP_ATOMIC); + GFP_KERNEL); + spin_lock (&dev->lock); if (value < 0) { clean_req (gadget->ep0, dev->req); break; @@ -1481,11 +1487,14 @@ delegate: if (value >= 0 && dev->state != STATE_DEV_SETUP) { req->length = value; req->zero = value < w_length; - value = usb_ep_queue (gadget->ep0, req, GFP_ATOMIC); + + spin_unlock (&dev->lock); + value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL); if (value < 0) { DBG (dev, "ep_queue --> %d\n", value); req->status = 0; } + return value; } /* device stalls when value < 0 */ diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index 6e8300d6a737..e1b2dcebdc2e 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -603,11 +603,15 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver) } } - list_add_tail(&driver->pending, &gadget_driver_pending_list); - pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n", - driver->function); + if (!driver->match_existing_only) { + list_add_tail(&driver->pending, &gadget_driver_pending_list); + pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n", + driver->function); + ret = 0; + } + mutex_unlock(&udc_lock); - return 0; + return ret; found: ret = udc_bind_to_driver(udc, driver); mutex_unlock(&udc_lock); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index ae1b6e69eb96..a962b89b65a6 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -368,6 +368,15 @@ static void ehci_shutdown(struct usb_hcd *hcd) { struct ehci_hcd *ehci = hcd_to_ehci(hcd); + /** + * Protect the system from crashing at system shutdown in cases where + * usb host is not added yet from OTG controller driver. + * As ehci_setup() not done yet, so stop accessing registers or + * variables initialized in ehci_setup() + */ + if (!ehci->sbrn) + return; + spin_lock_irq(&ehci->lock); ehci->shutdown = true; ehci->rh_state = EHCI_RH_STOPPING; diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index ffc90295a95f..74f62d68f013 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -872,14 +872,22 @@ int ehci_hub_control( ) { struct ehci_hcd *ehci = hcd_to_ehci (hcd); int ports = HCS_N_PORTS (ehci->hcs_params); - u32 __iomem *status_reg = &ehci->regs->port_status[ - (wIndex & 0xff) - 1]; - u32 __iomem *hostpc_reg = &ehci->regs->hostpc[(wIndex & 0xff) - 1]; + u32 __iomem *status_reg, *hostpc_reg; u32 temp, temp1, status; unsigned long flags; int retval = 0; unsigned selector; + /* + * Avoid underflow while calculating (wIndex & 0xff) - 1. + * The compiler might deduce that wIndex can never be 0 and then + * optimize away the tests for !wIndex below. + */ + temp = wIndex & 0xff; + temp -= (temp > 0); + status_reg = &ehci->regs->port_status[temp]; + hostpc_reg = &ehci->regs->hostpc[temp]; + /* * FIXME: support SetPortFeatures USB_PORT_FEAT_INDICATOR. * HCS_INDICATOR may say we can change LEDs to off/amber/green. diff --git a/drivers/usb/host/ehci-msm.c b/drivers/usb/host/ehci-msm.c index d3afc89d00f5..2f8d3af811ce 100644 --- a/drivers/usb/host/ehci-msm.c +++ b/drivers/usb/host/ehci-msm.c @@ -179,22 +179,32 @@ static int ehci_msm_remove(struct platform_device *pdev) static int ehci_msm_pm_suspend(struct device *dev) { struct usb_hcd *hcd = dev_get_drvdata(dev); + struct ehci_hcd *ehci = hcd_to_ehci(hcd); bool do_wakeup = device_may_wakeup(dev); dev_dbg(dev, "ehci-msm PM suspend\n"); - return ehci_suspend(hcd, do_wakeup); + /* Only call ehci_suspend if ehci_setup has been done */ + if (ehci->sbrn) + return ehci_suspend(hcd, do_wakeup); + + return 0; } static int ehci_msm_pm_resume(struct device *dev) { struct usb_hcd *hcd = dev_get_drvdata(dev); + struct ehci_hcd *ehci = hcd_to_ehci(hcd); dev_dbg(dev, "ehci-msm PM resume\n"); - ehci_resume(hcd, false); + + /* Only call ehci_resume if ehci_setup has been done */ + if (ehci->sbrn) + ehci_resume(hcd, false); return 0; } + #else #define ehci_msm_pm_suspend NULL #define ehci_msm_pm_resume NULL diff --git a/drivers/usb/host/ehci-st.c b/drivers/usb/host/ehci-st.c index a94ed677d937..be4a2788fc58 100644 --- a/drivers/usb/host/ehci-st.c +++ b/drivers/usb/host/ehci-st.c @@ -206,7 +206,8 @@ static int st_ehci_platform_probe(struct platform_device *dev) priv->clk48 = NULL; } - priv->pwr = devm_reset_control_get_optional(&dev->dev, "power"); + priv->pwr = + devm_reset_control_get_optional_shared(&dev->dev, "power"); if (IS_ERR(priv->pwr)) { err = PTR_ERR(priv->pwr); if (err == -EPROBE_DEFER) @@ -214,7 +215,8 @@ static int st_ehci_platform_probe(struct platform_device *dev) priv->pwr = NULL; } - priv->rst = devm_reset_control_get_optional(&dev->dev, "softreset"); + priv->rst = + devm_reset_control_get_optional_shared(&dev->dev, "softreset"); if (IS_ERR(priv->rst)) { err = PTR_ERR(priv->rst); if (err == -EPROBE_DEFER) diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c index 4031b372008e..9a3d7db5be57 100644 --- a/drivers/usb/host/ehci-tegra.c +++ b/drivers/usb/host/ehci-tegra.c @@ -81,15 +81,23 @@ static int tegra_reset_usb_controller(struct platform_device *pdev) struct usb_hcd *hcd = platform_get_drvdata(pdev); struct tegra_ehci_hcd *tegra = (struct tegra_ehci_hcd *)hcd_to_ehci(hcd)->priv; + bool has_utmi_pad_registers = false; phy_np = of_parse_phandle(pdev->dev.of_node, "nvidia,phy", 0); if (!phy_np) return -ENOENT; + if (of_property_read_bool(phy_np, "nvidia,has-utmi-pad-registers")) + has_utmi_pad_registers = true; + if (!usb1_reset_attempted) { struct reset_control *usb1_reset; - usb1_reset = of_reset_control_get(phy_np, "usb"); + if (!has_utmi_pad_registers) + usb1_reset = of_reset_control_get(phy_np, "utmi-pads"); + else + usb1_reset = tegra->rst; + if (IS_ERR(usb1_reset)) { dev_warn(&pdev->dev, "can't get utmi-pads reset from the PHY\n"); @@ -99,13 +107,15 @@ static int tegra_reset_usb_controller(struct platform_device *pdev) reset_control_assert(usb1_reset); udelay(1); reset_control_deassert(usb1_reset); + + if (!has_utmi_pad_registers) + reset_control_put(usb1_reset); } - reset_control_put(usb1_reset); usb1_reset_attempted = true; } - if (!of_property_read_bool(phy_np, "nvidia,has-utmi-pad-registers")) { + if (!has_utmi_pad_registers) { reset_control_assert(tegra->rst); udelay(1); reset_control_deassert(tegra->rst); diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c index d029bbe9eb36..641fed609911 100644 --- a/drivers/usb/host/ohci-q.c +++ b/drivers/usb/host/ohci-q.c @@ -183,7 +183,6 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed) { int branch; - ed->state = ED_OPER; ed->ed_prev = NULL; ed->ed_next = NULL; ed->hwNextED = 0; @@ -259,6 +258,8 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed) /* the HC may not see the schedule updates yet, but if it does * then they'll be properly ordered. */ + + ed->state = ED_OPER; return 0; } diff --git a/drivers/usb/host/ohci-st.c b/drivers/usb/host/ohci-st.c index acf2eb2a5676..02816a1515a1 100644 --- a/drivers/usb/host/ohci-st.c +++ b/drivers/usb/host/ohci-st.c @@ -188,13 +188,15 @@ static int st_ohci_platform_probe(struct platform_device *dev) priv->clk48 = NULL; } - priv->pwr = devm_reset_control_get_optional(&dev->dev, "power"); + priv->pwr = + devm_reset_control_get_optional_shared(&dev->dev, "power"); if (IS_ERR(priv->pwr)) { err = PTR_ERR(priv->pwr); goto err_put_clks; } - priv->rst = devm_reset_control_get_optional(&dev->dev, "softreset"); + priv->rst = + devm_reset_control_get_optional_shared(&dev->dev, "softreset"); if (IS_ERR(priv->rst)) { err = PTR_ERR(priv->rst); goto err_put_clks; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 48672fac7ff3..c10972fcc8e4 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -37,6 +37,7 @@ /* Device for a quirk */ #define PCI_VENDOR_ID_FRESCO_LOGIC 0x1b73 #define PCI_DEVICE_ID_FRESCO_LOGIC_PDK 0x1000 +#define PCI_DEVICE_ID_FRESCO_LOGIC_FL1009 0x1009 #define PCI_DEVICE_ID_FRESCO_LOGIC_FL1400 0x1400 #define PCI_VENDOR_ID_ETRON 0x1b6f @@ -114,6 +115,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_TRUST_TX_LENGTH; } + if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC && + pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009) + xhci->quirks |= XHCI_BROKEN_STREAMS; + if (pdev->vendor == PCI_VENDOR_ID_NEC) xhci->quirks |= XHCI_NEC_HOST; diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 676ea458148b..1f3f981fe7f8 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -196,6 +196,9 @@ static int xhci_plat_probe(struct platform_device *pdev) ret = clk_prepare_enable(clk); if (ret) goto put_hcd; + } else if (PTR_ERR(clk) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto put_hcd; } xhci = hcd_to_xhci(hcd); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 52deae4b7eac..d7d502578d79 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -290,6 +290,14 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci) temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); xhci->cmd_ring_state = CMD_RING_STATE_ABORTED; + + /* + * Writing the CMD_RING_ABORT bit should cause a cmd completion event, + * however on some host hw the CMD_RING_RUNNING bit is correctly cleared + * but the completion event in never sent. Use the cmd timeout timer to + * handle those cases. Use twice the time to cover the bit polling retry + */ + mod_timer(&xhci->cmd_timer, jiffies + (2 * XHCI_CMD_DEFAULT_TIMEOUT)); xhci_write_64(xhci, temp_64 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring); @@ -314,6 +322,7 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci) xhci_err(xhci, "Stopped the command ring failed, " "maybe the host is dead\n"); + del_timer(&xhci->cmd_timer); xhci->xhc_state |= XHCI_STATE_DYING; xhci_quiesce(xhci); xhci_halt(xhci); @@ -1246,22 +1255,21 @@ void xhci_handle_command_timeout(unsigned long data) int ret; unsigned long flags; u64 hw_ring_state; - struct xhci_command *cur_cmd = NULL; + bool second_timeout = false; xhci = (struct xhci_hcd *) data; /* mark this command to be cancelled */ spin_lock_irqsave(&xhci->lock, flags); if (xhci->current_cmd) { - cur_cmd = xhci->current_cmd; - cur_cmd->status = COMP_CMD_ABORT; + if (xhci->current_cmd->status == COMP_CMD_ABORT) + second_timeout = true; + xhci->current_cmd->status = COMP_CMD_ABORT; } - /* Make sure command ring is running before aborting it */ hw_ring_state = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); if ((xhci->cmd_ring_state & CMD_RING_STATE_RUNNING) && (hw_ring_state & CMD_RING_RUNNING)) { - spin_unlock_irqrestore(&xhci->lock, flags); xhci_dbg(xhci, "Command timeout\n"); ret = xhci_abort_cmd_ring(xhci); @@ -1273,6 +1281,15 @@ void xhci_handle_command_timeout(unsigned long data) } return; } + + /* command ring failed to restart, or host removed. Bail out */ + if (second_timeout || xhci->xhc_state & XHCI_STATE_REMOVING) { + spin_unlock_irqrestore(&xhci->lock, flags); + xhci_dbg(xhci, "command timed out twice, ring start fail?\n"); + xhci_cleanup_command_queue(xhci); + return; + } + /* command timeout on stopped ring, ring can't be aborted */ xhci_dbg(xhci, "Command timeout on stopped ring\n"); xhci_handle_stopped_cmd_ring(xhci, xhci->current_cmd); @@ -2721,7 +2738,8 @@ hw_died: writel(irq_pending, &xhci->ir_set->irq_pending); } - if (xhci->xhc_state & XHCI_STATE_DYING) { + if (xhci->xhc_state & XHCI_STATE_DYING || + xhci->xhc_state & XHCI_STATE_HALTED) { xhci_dbg(xhci, "xHCI dying, ignoring interrupt. " "Shouldn't IRQs be disabled?\n"); /* Clear the event handler busy flag (RW1C); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index fa7e1ef36cd9..f2f9518c53ab 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -685,20 +685,23 @@ void xhci_stop(struct usb_hcd *hcd) u32 temp; struct xhci_hcd *xhci = hcd_to_xhci(hcd); - if (xhci->xhc_state & XHCI_STATE_HALTED) - return; - mutex_lock(&xhci->mutex); - spin_lock_irq(&xhci->lock); - xhci->xhc_state |= XHCI_STATE_HALTED; - xhci->cmd_ring_state = CMD_RING_STATE_STOPPED; - /* Make sure the xHC is halted for a USB3 roothub - * (xhci_stop() could be called as part of failed init). - */ - xhci_halt(xhci); - xhci_reset(xhci); - spin_unlock_irq(&xhci->lock); + if (!(xhci->xhc_state & XHCI_STATE_HALTED)) { + spin_lock_irq(&xhci->lock); + + xhci->xhc_state |= XHCI_STATE_HALTED; + xhci->cmd_ring_state = CMD_RING_STATE_STOPPED; + xhci_halt(xhci); + xhci_reset(xhci); + + spin_unlock_irq(&xhci->lock); + } + + if (!usb_hcd_is_primary_hcd(hcd)) { + mutex_unlock(&xhci->mutex); + return; + } xhci_cleanup_msix(xhci); @@ -4886,7 +4889,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) xhci->hcc_params2 = readl(&xhci->cap_regs->hcc_params2); xhci_print_registers(xhci); - xhci->quirks = quirks; + xhci->quirks |= quirks; get_quirks(dev, xhci); diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 39fd95833eb8..f824336def5c 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1090,29 +1090,6 @@ void musb_stop(struct musb *musb) musb_platform_try_idle(musb, 0); } -static void musb_shutdown(struct platform_device *pdev) -{ - struct musb *musb = dev_to_musb(&pdev->dev); - unsigned long flags; - - pm_runtime_get_sync(musb->controller); - - musb_host_cleanup(musb); - musb_gadget_cleanup(musb); - - spin_lock_irqsave(&musb->lock, flags); - musb_platform_disable(musb); - musb_generic_disable(musb); - spin_unlock_irqrestore(&musb->lock, flags); - - musb_writeb(musb->mregs, MUSB_DEVCTL, 0); - musb_platform_exit(musb); - - pm_runtime_put(musb->controller); - /* FIXME power down */ -} - - /*-------------------------------------------------------------------------*/ /* @@ -1702,7 +1679,7 @@ EXPORT_SYMBOL_GPL(musb_dma_completion); #define use_dma 0 #endif -static void (*musb_phy_callback)(enum musb_vbus_id_status status); +static int (*musb_phy_callback)(enum musb_vbus_id_status status); /* * musb_mailbox - optional phy notifier function @@ -1711,11 +1688,12 @@ static void (*musb_phy_callback)(enum musb_vbus_id_status status); * Optionally gets called from the USB PHY. Note that the USB PHY must be * disabled at the point the phy_callback is registered or unregistered. */ -void musb_mailbox(enum musb_vbus_id_status status) +int musb_mailbox(enum musb_vbus_id_status status) { if (musb_phy_callback) - musb_phy_callback(status); + return musb_phy_callback(status); + return -ENODEV; }; EXPORT_SYMBOL_GPL(musb_mailbox); @@ -2028,11 +2006,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) musb_readl = musb_default_readl; musb_writel = musb_default_writel; - /* We need musb_read/write functions initialized for PM */ - pm_runtime_use_autosuspend(musb->controller); - pm_runtime_set_autosuspend_delay(musb->controller, 200); - pm_runtime_enable(musb->controller); - /* The musb_platform_init() call: * - adjusts musb->mregs * - sets the musb->isr @@ -2134,6 +2107,16 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) if (musb->ops->phy_callback) musb_phy_callback = musb->ops->phy_callback; + /* + * We need musb_read/write functions initialized for PM. + * Note that at least 2430 glue needs autosuspend delay + * somewhere above 300 ms for the hardware to idle properly + * after disconnecting the cable in host mode. Let's use + * 500 ms for some margin. + */ + pm_runtime_use_autosuspend(musb->controller); + pm_runtime_set_autosuspend_delay(musb->controller, 500); + pm_runtime_enable(musb->controller); pm_runtime_get_sync(musb->controller); status = usb_phy_init(musb->xceiv); @@ -2237,13 +2220,8 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) if (status) goto fail5; - pm_runtime_put(musb->controller); - - /* - * For why this is currently needed, see commit 3e43a0725637 - * ("usb: musb: core: add pm_runtime_irq_safe()") - */ - pm_runtime_irq_safe(musb->controller); + pm_runtime_mark_last_busy(musb->controller); + pm_runtime_put_autosuspend(musb->controller); return 0; @@ -2265,7 +2243,9 @@ fail2_5: usb_phy_shutdown(musb->xceiv); err_usb_phy_init: + pm_runtime_dont_use_autosuspend(musb->controller); pm_runtime_put_sync(musb->controller); + pm_runtime_disable(musb->controller); fail2: if (musb->irq_wake) @@ -2273,7 +2253,6 @@ fail2: musb_platform_exit(musb); fail1: - pm_runtime_disable(musb->controller); dev_err(musb->controller, "musb_init_controller failed with status %d\n", status); @@ -2312,6 +2291,7 @@ static int musb_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct musb *musb = dev_to_musb(dev); + unsigned long flags; /* this gets called on rmmod. * - Host mode: host may still be active @@ -2319,17 +2299,26 @@ static int musb_remove(struct platform_device *pdev) * - OTG mode: both roles are deactivated (or never-activated) */ musb_exit_debugfs(musb); - musb_shutdown(pdev); - musb_phy_callback = NULL; - - if (musb->dma_controller) - musb_dma_controller_destroy(musb->dma_controller); - - usb_phy_shutdown(musb->xceiv); cancel_work_sync(&musb->irq_work); cancel_delayed_work_sync(&musb->finish_resume_work); cancel_delayed_work_sync(&musb->deassert_reset_work); + pm_runtime_get_sync(musb->controller); + musb_host_cleanup(musb); + musb_gadget_cleanup(musb); + spin_lock_irqsave(&musb->lock, flags); + musb_platform_disable(musb); + musb_generic_disable(musb); + spin_unlock_irqrestore(&musb->lock, flags); + musb_writeb(musb->mregs, MUSB_DEVCTL, 0); + pm_runtime_dont_use_autosuspend(musb->controller); + pm_runtime_put_sync(musb->controller); + pm_runtime_disable(musb->controller); + musb_platform_exit(musb); + musb_phy_callback = NULL; + if (musb->dma_controller) + musb_dma_controller_destroy(musb->dma_controller); + usb_phy_shutdown(musb->xceiv); musb_free(musb); device_init_wakeup(dev, 0); return 0; @@ -2429,7 +2418,8 @@ static void musb_restore_context(struct musb *musb) musb_writew(musb_base, MUSB_INTRTXE, musb->intrtxe); musb_writew(musb_base, MUSB_INTRRXE, musb->intrrxe); musb_writeb(musb_base, MUSB_INTRUSBE, musb->context.intrusbe); - musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl); + if (musb->context.devctl & MUSB_DEVCTL_SESSION) + musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl); for (i = 0; i < musb->config->num_eps; ++i) { struct musb_hw_ep *hw_ep; @@ -2612,7 +2602,6 @@ static struct platform_driver musb_driver = { }, .probe = musb_probe, .remove = musb_remove, - .shutdown = musb_shutdown, }; module_platform_driver(musb_driver); diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index b6afe9e43305..b55a776b03eb 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -215,7 +215,7 @@ struct musb_platform_ops { dma_addr_t *dma_addr, u32 *len); void (*pre_root_reset_end)(struct musb *musb); void (*post_root_reset_end)(struct musb *musb); - void (*phy_callback)(enum musb_vbus_id_status status); + int (*phy_callback)(enum musb_vbus_id_status status); }; /* @@ -312,6 +312,7 @@ struct musb { struct work_struct irq_work; struct delayed_work deassert_reset_work; struct delayed_work finish_resume_work; + struct delayed_work gadget_work; u16 hwvers; u16 intrrxe; diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 152865b36522..af2a3a7addf9 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1656,6 +1656,20 @@ static int musb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) return usb_phy_set_power(musb->xceiv, mA); } +static void musb_gadget_work(struct work_struct *work) +{ + struct musb *musb; + unsigned long flags; + + musb = container_of(work, struct musb, gadget_work.work); + pm_runtime_get_sync(musb->controller); + spin_lock_irqsave(&musb->lock, flags); + musb_pullup(musb, musb->softconnect); + spin_unlock_irqrestore(&musb->lock, flags); + pm_runtime_mark_last_busy(musb->controller); + pm_runtime_put_autosuspend(musb->controller); +} + static int musb_gadget_pullup(struct usb_gadget *gadget, int is_on) { struct musb *musb = gadget_to_musb(gadget); @@ -1663,20 +1677,16 @@ static int musb_gadget_pullup(struct usb_gadget *gadget, int is_on) is_on = !!is_on; - pm_runtime_get_sync(musb->controller); - /* NOTE: this assumes we are sensing vbus; we'd rather * not pullup unless the B-session is active. */ spin_lock_irqsave(&musb->lock, flags); if (is_on != musb->softconnect) { musb->softconnect = is_on; - musb_pullup(musb, is_on); + schedule_delayed_work(&musb->gadget_work, 0); } spin_unlock_irqrestore(&musb->lock, flags); - pm_runtime_put(musb->controller); - return 0; } @@ -1845,7 +1855,7 @@ int musb_gadget_setup(struct musb *musb) #elif IS_ENABLED(CONFIG_USB_MUSB_GADGET) musb->g.is_otg = 0; #endif - + INIT_DELAYED_WORK(&musb->gadget_work, musb_gadget_work); musb_g_init_endpoints(musb); musb->is_active = 0; @@ -1866,6 +1876,8 @@ void musb_gadget_cleanup(struct musb *musb) { if (musb->port_mode == MUSB_PORT_MODE_HOST) return; + + cancel_delayed_work_sync(&musb->gadget_work); usb_del_gadget_udc(&musb->g); } @@ -1914,8 +1926,8 @@ static int musb_gadget_start(struct usb_gadget *g, if (musb->xceiv->last_event == USB_EVENT_ID) musb_platform_set_vbus(musb, 1); - if (musb->xceiv->last_event == USB_EVENT_NONE) - pm_runtime_put(musb->controller); + pm_runtime_mark_last_busy(musb->controller); + pm_runtime_put_autosuspend(musb->controller); return 0; @@ -1934,8 +1946,7 @@ static int musb_gadget_stop(struct usb_gadget *g) struct musb *musb = gadget_to_musb(g); unsigned long flags; - if (musb->xceiv->last_event == USB_EVENT_NONE) - pm_runtime_get_sync(musb->controller); + pm_runtime_get_sync(musb->controller); /* * REVISIT always use otg_set_peripheral() here too; @@ -1963,7 +1974,8 @@ static int musb_gadget_stop(struct usb_gadget *g) * that currently misbehaves. */ - pm_runtime_put(musb->controller); + pm_runtime_mark_last_busy(musb->controller); + pm_runtime_put_autosuspend(musb->controller); return 0; } diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 2f8ad7f1f482..d227a71d85e1 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -434,7 +434,13 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb, } } - if (qh != NULL && qh->is_ready) { + /* + * The pipe must be broken if current urb->status is set, so don't + * start next urb. + * TODO: to minimize the risk of regression, only check urb->status + * for RX, until we have a test case to understand the behavior of TX. + */ + if ((!status || !is_in) && qh && qh->is_ready) { dev_dbg(musb->controller, "... next ep%d %cX urb %p\n", hw_ep->epnum, is_in ? 'R' : 'T', next_urb(qh)); musb_start_urb(musb, is_in, qh); @@ -594,14 +600,13 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, u8 epnum) musb_writew(ep->regs, MUSB_TXCSR, 0); /* scrub all previous state, clearing toggle */ - } else { - csr = musb_readw(ep->regs, MUSB_RXCSR); - if (csr & MUSB_RXCSR_RXPKTRDY) - WARNING("rx%d, packet/%d ready?\n", ep->epnum, - musb_readw(ep->regs, MUSB_RXCOUNT)); - - musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG); } + csr = musb_readw(ep->regs, MUSB_RXCSR); + if (csr & MUSB_RXCSR_RXPKTRDY) + WARNING("rx%d, packet/%d ready?\n", ep->epnum, + musb_readw(ep->regs, MUSB_RXCOUNT)); + + musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG); /* target addr and (for multipoint) hub addr/port */ if (musb->is_multipoint) { @@ -627,7 +632,7 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, u8 epnum) ep->rx_reinit = 0; } -static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma, +static void musb_tx_dma_set_mode_mentor(struct dma_controller *dma, struct musb_hw_ep *hw_ep, struct musb_qh *qh, struct urb *urb, u32 offset, u32 *length, u8 *mode) @@ -664,23 +669,18 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma, } channel->desired_mode = *mode; musb_writew(epio, MUSB_TXCSR, csr); - - return 0; } -static int musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma, - struct musb_hw_ep *hw_ep, - struct musb_qh *qh, - struct urb *urb, - u32 offset, - u32 *length, - u8 *mode) +static void musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma, + struct musb_hw_ep *hw_ep, + struct musb_qh *qh, + struct urb *urb, + u32 offset, + u32 *length, + u8 *mode) { struct dma_channel *channel = hw_ep->tx_channel; - if (!is_cppi_enabled(hw_ep->musb) && !tusb_dma_omap(hw_ep->musb)) - return -ENODEV; - channel->actual_len = 0; /* @@ -688,8 +688,6 @@ static int musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma, * to identify the zero-length-final-packet case. */ *mode = (urb->transfer_flags & URB_ZERO_PACKET) ? 1 : 0; - - return 0; } static bool musb_tx_dma_program(struct dma_controller *dma, @@ -699,15 +697,14 @@ static bool musb_tx_dma_program(struct dma_controller *dma, struct dma_channel *channel = hw_ep->tx_channel; u16 pkt_size = qh->maxpacket; u8 mode; - int res; if (musb_dma_inventra(hw_ep->musb) || musb_dma_ux500(hw_ep->musb)) - res = musb_tx_dma_set_mode_mentor(dma, hw_ep, qh, urb, - offset, &length, &mode); + musb_tx_dma_set_mode_mentor(dma, hw_ep, qh, urb, offset, + &length, &mode); + else if (is_cppi_enabled(hw_ep->musb) || tusb_dma_omap(hw_ep->musb)) + musb_tx_dma_set_mode_cppi_tusb(dma, hw_ep, qh, urb, offset, + &length, &mode); else - res = musb_tx_dma_set_mode_cppi_tusb(dma, hw_ep, qh, urb, - offset, &length, &mode); - if (res) return false; qh->segsize = length; @@ -995,9 +992,15 @@ static void musb_bulk_nak_timeout(struct musb *musb, struct musb_hw_ep *ep, if (is_in) { dma = is_dma_capable() ? ep->rx_channel : NULL; - /* clear nak timeout bit */ + /* + * Need to stop the transaction by clearing REQPKT first + * then the NAK Timeout bit ref MUSBMHDRC USB 2.0 HIGH-SPEED + * DUAL-ROLE CONTROLLER Programmer's Guide, section 9.2.2 + */ rx_csr = musb_readw(epio, MUSB_RXCSR); rx_csr |= MUSB_RXCSR_H_WZC_BITS; + rx_csr &= ~MUSB_RXCSR_H_REQPKT; + musb_writew(epio, MUSB_RXCSR, rx_csr); rx_csr &= ~MUSB_RXCSR_DATAERROR; musb_writew(epio, MUSB_RXCSR, rx_csr); @@ -1551,7 +1554,7 @@ static int musb_rx_dma_iso_cppi41(struct dma_controller *dma, struct urb *urb, size_t len) { - struct dma_channel *channel = hw_ep->tx_channel; + struct dma_channel *channel = hw_ep->rx_channel; void __iomem *epio = hw_ep->regs; dma_addr_t *buf; u32 length, res; @@ -1870,6 +1873,9 @@ void musb_host_rx(struct musb *musb, u8 epnum) status = -EPROTO; musb_writeb(epio, MUSB_RXINTERVAL, 0); + rx_csr &= ~MUSB_RXCSR_H_ERROR; + musb_writew(epio, MUSB_RXCSR, rx_csr); + } else if (rx_csr & MUSB_RXCSR_DATAERROR) { if (USB_ENDPOINT_XFER_ISOC != qh->type) { diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index c84e0322c108..0b4cec940386 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -49,97 +49,14 @@ struct omap2430_glue { enum musb_vbus_id_status status; struct work_struct omap_musb_mailbox_work; struct device *control_otghs; + bool cable_connected; + bool enabled; + bool powered; }; #define glue_to_musb(g) platform_get_drvdata(g->musb) static struct omap2430_glue *_glue; -static struct timer_list musb_idle_timer; - -static void musb_do_idle(unsigned long _musb) -{ - struct musb *musb = (void *)_musb; - unsigned long flags; - u8 power; - u8 devctl; - - spin_lock_irqsave(&musb->lock, flags); - - switch (musb->xceiv->otg->state) { - case OTG_STATE_A_WAIT_BCON: - - devctl = musb_readb(musb->mregs, MUSB_DEVCTL); - if (devctl & MUSB_DEVCTL_BDEVICE) { - musb->xceiv->otg->state = OTG_STATE_B_IDLE; - MUSB_DEV_MODE(musb); - } else { - musb->xceiv->otg->state = OTG_STATE_A_IDLE; - MUSB_HST_MODE(musb); - } - break; - case OTG_STATE_A_SUSPEND: - /* finish RESUME signaling? */ - if (musb->port1_status & MUSB_PORT_STAT_RESUME) { - power = musb_readb(musb->mregs, MUSB_POWER); - power &= ~MUSB_POWER_RESUME; - dev_dbg(musb->controller, "root port resume stopped, power %02x\n", power); - musb_writeb(musb->mregs, MUSB_POWER, power); - musb->is_active = 1; - musb->port1_status &= ~(USB_PORT_STAT_SUSPEND - | MUSB_PORT_STAT_RESUME); - musb->port1_status |= USB_PORT_STAT_C_SUSPEND << 16; - usb_hcd_poll_rh_status(musb->hcd); - /* NOTE: it might really be A_WAIT_BCON ... */ - musb->xceiv->otg->state = OTG_STATE_A_HOST; - } - break; - case OTG_STATE_A_HOST: - devctl = musb_readb(musb->mregs, MUSB_DEVCTL); - if (devctl & MUSB_DEVCTL_BDEVICE) - musb->xceiv->otg->state = OTG_STATE_B_IDLE; - else - musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON; - default: - break; - } - spin_unlock_irqrestore(&musb->lock, flags); -} - - -static void omap2430_musb_try_idle(struct musb *musb, unsigned long timeout) -{ - unsigned long default_timeout = jiffies + msecs_to_jiffies(3); - static unsigned long last_timer; - - if (timeout == 0) - timeout = default_timeout; - - /* Never idle if active, or when VBUS timeout is not set as host */ - if (musb->is_active || ((musb->a_wait_bcon == 0) - && (musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON))) { - dev_dbg(musb->controller, "%s active, deleting timer\n", - usb_otg_state_string(musb->xceiv->otg->state)); - del_timer(&musb_idle_timer); - last_timer = jiffies; - return; - } - - if (time_after(last_timer, timeout)) { - if (!timer_pending(&musb_idle_timer)) - last_timer = timeout; - else { - dev_dbg(musb->controller, "Longer idle timer already pending, ignoring\n"); - return; - } - } - last_timer = timeout; - - dev_dbg(musb->controller, "%s inactive, for idle timer for %lu ms\n", - usb_otg_state_string(musb->xceiv->otg->state), - (unsigned long)jiffies_to_msecs(timeout - jiffies)); - mod_timer(&musb_idle_timer, timeout); -} - static void omap2430_musb_set_vbus(struct musb *musb, int is_on) { struct usb_otg *otg = musb->xceiv->otg; @@ -205,16 +122,6 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on) musb_readb(musb->mregs, MUSB_DEVCTL)); } -static int omap2430_musb_set_mode(struct musb *musb, u8 musb_mode) -{ - u8 devctl = musb_readb(musb->mregs, MUSB_DEVCTL); - - devctl |= MUSB_DEVCTL_SESSION; - musb_writeb(musb->mregs, MUSB_DEVCTL, devctl); - - return 0; -} - static inline void omap2430_low_level_exit(struct musb *musb) { u32 l; @@ -234,22 +141,63 @@ static inline void omap2430_low_level_init(struct musb *musb) musb_writel(musb->mregs, OTG_FORCESTDBY, l); } -static void omap2430_musb_mailbox(enum musb_vbus_id_status status) +/* + * We can get multiple cable events so we need to keep track + * of the power state. Only keep power enabled if USB cable is + * connected and a gadget is started. + */ +static void omap2430_set_power(struct musb *musb, bool enabled, bool cable) +{ + struct device *dev = musb->controller; + struct omap2430_glue *glue = dev_get_drvdata(dev->parent); + bool power_up; + int res; + + if (glue->enabled != enabled) + glue->enabled = enabled; + + if (glue->cable_connected != cable) + glue->cable_connected = cable; + + power_up = glue->enabled && glue->cable_connected; + if (power_up == glue->powered) { + dev_warn(musb->controller, "power state already %i\n", + power_up); + return; + } + + glue->powered = power_up; + + if (power_up) { + res = pm_runtime_get_sync(musb->controller); + if (res < 0) { + dev_err(musb->controller, "could not enable: %i", res); + glue->powered = false; + } + } else { + pm_runtime_mark_last_busy(musb->controller); + pm_runtime_put_autosuspend(musb->controller); + } +} + +static int omap2430_musb_mailbox(enum musb_vbus_id_status status) { struct omap2430_glue *glue = _glue; if (!glue) { pr_err("%s: musb core is not yet initialized\n", __func__); - return; + return -EPROBE_DEFER; } glue->status = status; if (!glue_to_musb(glue)) { pr_err("%s: musb core is not yet ready\n", __func__); - return; + return -EPROBE_DEFER; } schedule_work(&glue->omap_musb_mailbox_work); + + return 0; } static void omap_musb_set_mailbox(struct omap2430_glue *glue) @@ -259,6 +207,13 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev); struct omap_musb_board_data *data = pdata->board_data; struct usb_otg *otg = musb->xceiv->otg; + bool cable_connected; + + cable_connected = ((glue->status == MUSB_ID_GROUND) || + (glue->status == MUSB_VBUS_VALID)); + + if (cable_connected) + omap2430_set_power(musb, glue->enabled, cable_connected); switch (glue->status) { case MUSB_ID_GROUND: @@ -268,7 +223,6 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) musb->xceiv->otg->state = OTG_STATE_A_IDLE; musb->xceiv->last_event = USB_EVENT_ID; if (musb->gadget_driver) { - pm_runtime_get_sync(dev); omap_control_usb_set_mode(glue->control_otghs, USB_MODE_HOST); omap2430_musb_set_vbus(musb, 1); @@ -281,8 +235,6 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) otg->default_a = false; musb->xceiv->otg->state = OTG_STATE_B_IDLE; musb->xceiv->last_event = USB_EVENT_VBUS; - if (musb->gadget_driver) - pm_runtime_get_sync(dev); omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DEVICE); break; @@ -291,11 +243,8 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) dev_dbg(dev, "VBUS Disconnect\n"); musb->xceiv->last_event = USB_EVENT_NONE; - if (musb->gadget_driver) { + if (musb->gadget_driver) omap2430_musb_set_vbus(musb, 0); - pm_runtime_mark_last_busy(dev); - pm_runtime_put_autosuspend(dev); - } if (data->interface_type == MUSB_INTERFACE_UTMI) otg_set_vbus(musb->xceiv->otg, 0); @@ -307,6 +256,9 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) dev_dbg(dev, "ID float\n"); } + if (!cable_connected) + omap2430_set_power(musb, glue->enabled, cable_connected); + atomic_notifier_call_chain(&musb->xceiv->notifier, musb->xceiv->last_event, NULL); } @@ -316,13 +268,8 @@ static void omap_musb_mailbox_work(struct work_struct *mailbox_work) { struct omap2430_glue *glue = container_of(mailbox_work, struct omap2430_glue, omap_musb_mailbox_work); - struct musb *musb = glue_to_musb(glue); - struct device *dev = musb->controller; - pm_runtime_get_sync(dev); omap_musb_set_mailbox(glue); - pm_runtime_mark_last_busy(dev); - pm_runtime_put_autosuspend(dev); } static irqreturn_t omap2430_musb_interrupt(int irq, void *__hci) @@ -389,23 +336,7 @@ static int omap2430_musb_init(struct musb *musb) return PTR_ERR(musb->phy); } musb->isr = omap2430_musb_interrupt; - - /* - * Enable runtime PM for musb parent (this driver). We can't - * do it earlier as struct musb is not yet allocated and we - * need to touch the musb registers for runtime PM. - */ - pm_runtime_enable(glue->dev); - status = pm_runtime_get_sync(glue->dev); - if (status < 0) - goto err1; - - status = pm_runtime_get_sync(dev); - if (status < 0) { - dev_err(dev, "pm_runtime_get_sync FAILED %d\n", status); - pm_runtime_put_sync(glue->dev); - goto err1; - } + phy_init(musb->phy); l = musb_readl(musb->mregs, OTG_INTERFSEL); @@ -427,20 +358,10 @@ static int omap2430_musb_init(struct musb *musb) musb_readl(musb->mregs, OTG_INTERFSEL), musb_readl(musb->mregs, OTG_SIMENABLE)); - setup_timer(&musb_idle_timer, musb_do_idle, (unsigned long) musb); - if (glue->status != MUSB_UNKNOWN) omap_musb_set_mailbox(glue); - phy_init(musb->phy); - phy_power_on(musb->phy); - - pm_runtime_put_noidle(musb->controller); - pm_runtime_put_noidle(glue->dev); return 0; - -err1: - return status; } static void omap2430_musb_enable(struct musb *musb) @@ -452,6 +373,11 @@ static void omap2430_musb_enable(struct musb *musb) struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev); struct omap_musb_board_data *data = pdata->board_data; + if (!WARN_ON(!musb->phy)) + phy_power_on(musb->phy); + + omap2430_set_power(musb, true, glue->cable_connected); + switch (glue->status) { case MUSB_ID_GROUND: @@ -487,18 +413,25 @@ static void omap2430_musb_disable(struct musb *musb) struct device *dev = musb->controller; struct omap2430_glue *glue = dev_get_drvdata(dev->parent); + if (!WARN_ON(!musb->phy)) + phy_power_off(musb->phy); + if (glue->status != MUSB_UNKNOWN) omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DISCONNECT); + + omap2430_set_power(musb, false, glue->cable_connected); } static int omap2430_musb_exit(struct musb *musb) { - del_timer_sync(&musb_idle_timer); + struct device *dev = musb->controller; + struct omap2430_glue *glue = dev_get_drvdata(dev->parent); omap2430_low_level_exit(musb); - phy_power_off(musb->phy); phy_exit(musb->phy); + musb->phy = NULL; + cancel_work_sync(&glue->omap_musb_mailbox_work); return 0; } @@ -512,9 +445,6 @@ static const struct musb_platform_ops omap2430_ops = { .init = omap2430_musb_init, .exit = omap2430_musb_exit, - .set_mode = omap2430_musb_set_mode, - .try_idle = omap2430_musb_try_idle, - .set_vbus = omap2430_musb_set_vbus, .enable = omap2430_musb_enable, @@ -639,11 +569,9 @@ static int omap2430_probe(struct platform_device *pdev) goto err2; } - /* - * Note that we cannot enable PM runtime yet for this - * driver as we need struct musb initialized first. - * See omap2430_musb_init above. - */ + pm_runtime_enable(glue->dev); + pm_runtime_use_autosuspend(glue->dev); + pm_runtime_set_autosuspend_delay(glue->dev, 500); ret = platform_device_add(musb); if (ret) { @@ -662,12 +590,14 @@ err0: static int omap2430_remove(struct platform_device *pdev) { - struct omap2430_glue *glue = platform_get_drvdata(pdev); + struct omap2430_glue *glue = platform_get_drvdata(pdev); + struct musb *musb = glue_to_musb(glue); pm_runtime_get_sync(glue->dev); - cancel_work_sync(&glue->omap_musb_mailbox_work); platform_device_unregister(glue->musb); + omap2430_set_power(musb, false, false); pm_runtime_put_sync(glue->dev); + pm_runtime_dont_use_autosuspend(glue->dev); pm_runtime_disable(glue->dev); return 0; @@ -680,12 +610,13 @@ static int omap2430_runtime_suspend(struct device *dev) struct omap2430_glue *glue = dev_get_drvdata(dev); struct musb *musb = glue_to_musb(glue); - if (musb) { - musb->context.otg_interfsel = musb_readl(musb->mregs, - OTG_INTERFSEL); + if (!musb) + return 0; - omap2430_low_level_exit(musb); - } + musb->context.otg_interfsel = musb_readl(musb->mregs, + OTG_INTERFSEL); + + omap2430_low_level_exit(musb); return 0; } @@ -696,7 +627,7 @@ static int omap2430_runtime_resume(struct device *dev) struct musb *musb = glue_to_musb(glue); if (!musb) - return -EPROBE_DEFER; + return 0; omap2430_low_level_init(musb); musb_writel(musb->mregs, OTG_INTERFSEL, @@ -738,18 +669,8 @@ static struct platform_driver omap2430_driver = { }, }; +module_platform_driver(omap2430_driver); + MODULE_DESCRIPTION("OMAP2PLUS MUSB Glue Layer"); MODULE_AUTHOR("Felipe Balbi "); MODULE_LICENSE("GPL v2"); - -static int __init omap2430_init(void) -{ - return platform_driver_register(&omap2430_driver); -} -subsys_initcall(omap2430_init); - -static void __exit omap2430_exit(void) -{ - platform_driver_unregister(&omap2430_driver); -} -module_exit(omap2430_exit); diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c index fdab4232cfbf..76500515dd8b 100644 --- a/drivers/usb/musb/sunxi.c +++ b/drivers/usb/musb/sunxi.c @@ -80,7 +80,8 @@ static struct musb *sunxi_musb; struct sunxi_glue { struct device *dev; - struct platform_device *musb; + struct musb *musb; + struct platform_device *musb_pdev; struct clk *clk; struct reset_control *rst; struct phy *phy; @@ -102,7 +103,7 @@ static void sunxi_musb_work(struct work_struct *work) return; if (test_and_clear_bit(SUNXI_MUSB_FL_HOSTMODE_PEND, &glue->flags)) { - struct musb *musb = platform_get_drvdata(glue->musb); + struct musb *musb = glue->musb; unsigned long flags; u8 devctl; @@ -112,7 +113,7 @@ static void sunxi_musb_work(struct work_struct *work) if (test_bit(SUNXI_MUSB_FL_HOSTMODE, &glue->flags)) { set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags); musb->xceiv->otg->default_a = 1; - musb->xceiv->otg->state = OTG_STATE_A_IDLE; + musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE; MUSB_HST_MODE(musb); devctl |= MUSB_DEVCTL_SESSION; } else { @@ -145,10 +146,12 @@ static void sunxi_musb_set_vbus(struct musb *musb, int is_on) { struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent); - if (is_on) + if (is_on) { set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags); - else + musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE; + } else { clear_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags); + } schedule_work(&glue->work); } @@ -264,15 +267,6 @@ static int sunxi_musb_init(struct musb *musb) if (ret) goto error_unregister_notifier; - if (musb->port_mode == MUSB_PORT_MODE_HOST) { - ret = phy_power_on(glue->phy); - if (ret) - goto error_phy_exit; - set_bit(SUNXI_MUSB_FL_PHY_ON, &glue->flags); - /* Stop musb work from turning vbus off again */ - set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags); - } - musb->isr = sunxi_musb_interrupt; /* Stop the musb-core from doing runtime pm (not supported on sunxi) */ @@ -280,8 +274,6 @@ static int sunxi_musb_init(struct musb *musb) return 0; -error_phy_exit: - phy_exit(glue->phy); error_unregister_notifier: if (musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE) extcon_unregister_notifier(glue->extcon, EXTCON_USB_HOST, @@ -323,10 +315,31 @@ static int sunxi_musb_exit(struct musb *musb) return 0; } +static int sunxi_set_mode(struct musb *musb, u8 mode) +{ + struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent); + int ret; + + if (mode == MUSB_HOST) { + ret = phy_power_on(glue->phy); + if (ret) + return ret; + + set_bit(SUNXI_MUSB_FL_PHY_ON, &glue->flags); + /* Stop musb work from turning vbus off again */ + set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags); + musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE; + } + + return 0; +} + static void sunxi_musb_enable(struct musb *musb) { struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent); + glue->musb = musb; + /* musb_core does not call us in a balanced manner */ if (test_and_set_bit(SUNXI_MUSB_FL_ENABLED, &glue->flags)) return; @@ -569,6 +582,7 @@ static const struct musb_platform_ops sunxi_musb_ops = { .exit = sunxi_musb_exit, .enable = sunxi_musb_enable, .disable = sunxi_musb_disable, + .set_mode = sunxi_set_mode, .fifo_offset = sunxi_musb_fifo_offset, .ep_offset = sunxi_musb_ep_offset, .busctl_offset = sunxi_musb_busctl_offset, @@ -721,9 +735,9 @@ static int sunxi_musb_probe(struct platform_device *pdev) pinfo.data = &pdata; pinfo.size_data = sizeof(pdata); - glue->musb = platform_device_register_full(&pinfo); - if (IS_ERR(glue->musb)) { - ret = PTR_ERR(glue->musb); + glue->musb_pdev = platform_device_register_full(&pinfo); + if (IS_ERR(glue->musb_pdev)) { + ret = PTR_ERR(glue->musb_pdev); dev_err(&pdev->dev, "Error registering musb dev: %d\n", ret); goto err_unregister_usb_phy; } @@ -740,7 +754,7 @@ static int sunxi_musb_remove(struct platform_device *pdev) struct sunxi_glue *glue = platform_get_drvdata(pdev); struct platform_device *usb_phy = glue->usb_phy; - platform_device_unregister(glue->musb); /* Frees glue ! */ + platform_device_unregister(glue->musb_pdev); usb_phy_generic_unregister(usb_phy); return 0; diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c index 24e2b3cf1867..a72e8d670adc 100644 --- a/drivers/usb/phy/phy-twl6030-usb.c +++ b/drivers/usb/phy/phy-twl6030-usb.c @@ -97,6 +97,9 @@ struct twl6030_usb { struct regulator *usb3v3; + /* used to check initial cable status after probe */ + struct delayed_work get_status_work; + /* used to set vbus, in atomic path */ struct work_struct set_vbus_work; @@ -227,12 +230,16 @@ static irqreturn_t twl6030_usb_irq(int irq, void *_twl) twl->asleep = 1; status = MUSB_VBUS_VALID; twl->linkstat = status; - musb_mailbox(status); + ret = musb_mailbox(status); + if (ret) + twl->linkstat = MUSB_UNKNOWN; } else { if (twl->linkstat != MUSB_UNKNOWN) { status = MUSB_VBUS_OFF; twl->linkstat = status; - musb_mailbox(status); + ret = musb_mailbox(status); + if (ret) + twl->linkstat = MUSB_UNKNOWN; if (twl->asleep) { regulator_disable(twl->usb3v3); twl->asleep = 0; @@ -264,7 +271,9 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl) twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_SET); status = MUSB_ID_GROUND; twl->linkstat = status; - musb_mailbox(status); + ret = musb_mailbox(status); + if (ret) + twl->linkstat = MUSB_UNKNOWN; } else { twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_CLR); twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_SET); @@ -274,6 +283,15 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl) return IRQ_HANDLED; } +static void twl6030_status_work(struct work_struct *work) +{ + struct twl6030_usb *twl = container_of(work, struct twl6030_usb, + get_status_work.work); + + twl6030_usb_irq(twl->irq2, twl); + twl6030_usbotg_irq(twl->irq1, twl); +} + static int twl6030_enable_irq(struct twl6030_usb *twl) { twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_SET); @@ -284,8 +302,6 @@ static int twl6030_enable_irq(struct twl6030_usb *twl) REG_INT_MSK_LINE_C); twl6030_interrupt_unmask(TWL6030_CHARGER_CTRL_INT_MASK, REG_INT_MSK_STS_C); - twl6030_usb_irq(twl->irq2, twl); - twl6030_usbotg_irq(twl->irq1, twl); return 0; } @@ -371,6 +387,7 @@ static int twl6030_usb_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "could not create sysfs file\n"); INIT_WORK(&twl->set_vbus_work, otg_set_vbus_work); + INIT_DELAYED_WORK(&twl->get_status_work, twl6030_status_work); status = request_threaded_irq(twl->irq1, NULL, twl6030_usbotg_irq, IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING | IRQF_ONESHOT, @@ -395,6 +412,7 @@ static int twl6030_usb_probe(struct platform_device *pdev) twl->asleep = 0; twl6030_enable_irq(twl); + schedule_delayed_work(&twl->get_status_work, HZ); dev_info(&pdev->dev, "Initialized TWL6030 USB module\n"); return 0; @@ -404,6 +422,7 @@ static int twl6030_usb_remove(struct platform_device *pdev) { struct twl6030_usb *twl = platform_get_drvdata(pdev); + cancel_delayed_work(&twl->get_status_work); twl6030_interrupt_mask(TWL6030_USBOTG_INT_MASK, REG_INT_MSK_LINE_C); twl6030_interrupt_mask(TWL6030_USBOTG_INT_MASK, diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c index 2eddbe538cda..5608af4a369d 100644 --- a/drivers/usb/serial/mos7720.c +++ b/drivers/usb/serial/mos7720.c @@ -2007,6 +2007,7 @@ static void mos7720_release(struct usb_serial *serial) urblist_entry) usb_unlink_urb(urbtrack->urb); spin_unlock_irqrestore(&mos_parport->listlock, flags); + parport_del_port(mos_parport->pp); kref_put(&mos_parport->ref_count, destroy_mos_parport); } diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 4d49fce406e1..5ef014ba6ae8 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -836,6 +836,7 @@ static int uas_slave_configure(struct scsi_device *sdev) if (devinfo->flags & US_FL_BROKEN_FUA) sdev->broken_fua = 1; + scsi_change_queue_depth(sdev, devinfo->qdepth - 2); return 0; } @@ -848,7 +849,6 @@ static struct scsi_host_template uas_host_template = { .slave_configure = uas_slave_configure, .eh_abort_handler = uas_eh_abort_handler, .eh_bus_reset_handler = uas_eh_bus_reset_handler, - .can_queue = MAX_CMNDS, .this_id = -1, .sg_tablesize = SG_NONE, .skip_settle_delay = 1, diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index fca51105974e..2e0450bec1b1 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -941,7 +941,7 @@ static void vhci_stop(struct usb_hcd *hcd) static int vhci_get_frame_number(struct usb_hcd *hcd) { - pr_err("Not yet implemented\n"); + dev_err_ratelimited(&hcd->self.root_hub->dev, "Not yet implemented\n"); return 0; } diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index b54f26c55dfd..b4b3e256491b 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -746,7 +746,7 @@ config ALIM7101_WDT config EBC_C384_WDT tristate "WinSystems EBC-C384 Watchdog Timer" - depends on X86 && ISA + depends on X86 && ISA_BUS_API select WATCHDOG_CORE help Enables watchdog timer support for the watchdog timer on the diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index d46839f51e73..e4db19e88ab1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -151,8 +151,6 @@ static DECLARE_WAIT_QUEUE_HEAD(balloon_wq); static void balloon_process(struct work_struct *work); static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); -static void release_memory_resource(struct resource *resource); - /* When ballooning out (allocating memory to return to Xen) we don't really want the kernel to try too hard since that can trigger the oom killer. */ #define GFP_BALLOON \ @@ -248,6 +246,19 @@ static enum bp_state update_schedule(enum bp_state state) } #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +static void release_memory_resource(struct resource *resource) +{ + if (!resource) + return; + + /* + * No need to reset region to identity mapped since we now + * know that no I/O can be in this region + */ + release_resource(resource); + kfree(resource); +} + static struct resource *additional_memory_resource(phys_addr_t size) { struct resource *res; @@ -286,19 +297,6 @@ static struct resource *additional_memory_resource(phys_addr_t size) return res; } -static void release_memory_resource(struct resource *resource) -{ - if (!resource) - return; - - /* - * No need to reset region to identity mapped since we now - * know that no I/O can be in this region - */ - release_resource(resource); - kfree(resource); -} - static enum bp_state reserve_additional_memory(void) { long credit; diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index 076970a54f89..4ce10bcca18b 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -423,36 +423,7 @@ upload: return 0; } -static int __init check_prereq(void) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - if (!xen_initial_domain()) - return -ENODEV; - - if (!acpi_gbl_FADT.smi_command) - return -ENODEV; - - if (c->x86_vendor == X86_VENDOR_INTEL) { - if (!cpu_has(c, X86_FEATURE_EST)) - return -ENODEV; - return 0; - } - if (c->x86_vendor == X86_VENDOR_AMD) { - /* Copied from powernow-k8.h, can't include ../cpufreq/powernow - * as we get compile warnings for the static functions. - */ -#define CPUID_FREQ_VOLT_CAPABILITIES 0x80000007 -#define USE_HW_PSTATE 0x00000080 - u32 eax, ebx, ecx, edx; - cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx); - if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE) - return -ENODEV; - return 0; - } - return -ENODEV; -} /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance __percpu *acpi_perf_data; @@ -509,10 +480,10 @@ struct notifier_block xen_acpi_processor_resume_nb = { static int __init xen_acpi_processor_init(void) { unsigned int i; - int rc = check_prereq(); + int rc; - if (rc) - return rc; + if (!xen_initial_domain()) + return -ENODEV; nr_acpi_bits = get_max_acpi_id() + 1; acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 8e67336f8ddd..6a25533da237 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -183,8 +183,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size, field_start = OFFSET(cfg_entry); field_end = OFFSET(cfg_entry) + field->size; - if ((req_start >= field_start && req_start < field_end) - || (req_end > field_start && req_end <= field_end)) { + if (req_end > field_start && field_end > req_start) { err = conf_space_read(dev, cfg_entry, field_start, &tmp_val); if (err) @@ -230,8 +229,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value) field_start = OFFSET(cfg_entry); field_end = OFFSET(cfg_entry) + field->size; - if ((req_start >= field_start && req_start < field_end) - || (req_end > field_start && req_end <= field_end)) { + if (req_end > field_start && field_end > req_start) { tmp_val = 0; err = xen_pcibk_config_read(dev, field_start, diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index ad3d17d29c81..9ead1c2ff1dd 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -145,7 +145,7 @@ static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data) /* A write to obtain the length must happen as a 32-bit write. * This does not (yet) support writing individual bytes */ - if (value == ~PCI_ROM_ADDRESS_ENABLE) + if ((value | ~PCI_ROM_ADDRESS_MASK) == ~0U) bar->which = 1; else { u32 tmpval; @@ -225,38 +225,42 @@ static inline void read_dev_bar(struct pci_dev *dev, (PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64))) { bar_info->val = res[pos - 1].start >> 32; - bar_info->len_val = res[pos - 1].end >> 32; + bar_info->len_val = -resource_size(&res[pos - 1]) >> 32; return; } } + if (!res[pos].flags || + (res[pos].flags & (IORESOURCE_DISABLED | IORESOURCE_UNSET | + IORESOURCE_BUSY))) + return; + bar_info->val = res[pos].start | (res[pos].flags & PCI_REGION_FLAG_MASK); - bar_info->len_val = resource_size(&res[pos]); + bar_info->len_val = -resource_size(&res[pos]) | + (res[pos].flags & PCI_REGION_FLAG_MASK); } static void *bar_init(struct pci_dev *dev, int offset) { - struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL); + struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL); if (!bar) return ERR_PTR(-ENOMEM); read_dev_bar(dev, bar, offset, ~0); - bar->which = 0; return bar; } static void *rom_init(struct pci_dev *dev, int offset) { - struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL); + struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL); if (!bar) return ERR_PTR(-ENOMEM); read_dev_bar(dev, bar, offset, ~PCI_ROM_ADDRESS_ENABLE); - bar->which = 0; return bar; } diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index cacf30d14747..7487971f9f78 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -316,11 +316,18 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } + } else { + list_for_each_entry(trans, &u->transactions, list) + if (trans->handle.id == u->u.msg.tx_id) + break; + if (&trans->list == &u->transactions) + return -ESRCH; } reply = xenbus_dev_request_and_reply(&u->u.msg); if (IS_ERR(reply)) { - kfree(trans); + if (msg_type == XS_TRANSACTION_START) + kfree(trans); rc = PTR_ERR(reply); goto out; } @@ -333,12 +340,7 @@ static int xenbus_write_transaction(unsigned msg_type, list_add(&trans->list, &u->transactions); } } else if (u->u.msg.type == XS_TRANSACTION_END) { - list_for_each_entry(trans, &u->transactions, list) - if (trans->handle.id == u->u.msg.tx_id) - break; - BUG_ON(&trans->list == &u->transactions); list_del(&trans->list); - kfree(trans); } diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 374b12af8812..22f7cd711c57 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -232,10 +232,10 @@ static void transaction_resume(void) void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) { void *ret; - struct xsd_sockmsg req_msg = *msg; + enum xsd_sockmsg_type type = msg->type; int err; - if (req_msg.type == XS_TRANSACTION_START) + if (type == XS_TRANSACTION_START) transaction_start(); mutex_lock(&xs_state.request_mutex); @@ -249,12 +249,8 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) mutex_unlock(&xs_state.request_mutex); - if (IS_ERR(ret)) - return ret; - if ((msg->type == XS_TRANSACTION_END) || - ((req_msg.type == XS_TRANSACTION_START) && - (msg->type == XS_ERROR))) + ((type == XS_TRANSACTION_START) && (msg->type == XS_ERROR))) transaction_end(); return ret; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index b84c291ba1eb..d7b78d531e63 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -74,7 +74,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) v9fs_proto_dotu(v9ses)); fid = file->private_data; if (!fid) { - fid = v9fs_fid_clone(file->f_path.dentry); + fid = v9fs_fid_clone(file_dentry(file)); if (IS_ERR(fid)) return PTR_ERR(fid); @@ -100,7 +100,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) * because we want write after unlink usecase * to work. */ - fid = v9fs_writeback_fid(file->f_path.dentry); + fid = v9fs_writeback_fid(file_dentry(file)); if (IS_ERR(fid)) { err = PTR_ERR(fid); mutex_unlock(&v9inode->v_mutex); @@ -516,7 +516,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma) * because we want write after unlink usecase * to work. */ - fid = v9fs_writeback_fid(filp->f_path.dentry); + fid = v9fs_writeback_fid(file_dentry(filp)); if (IS_ERR(fid)) { retval = PTR_ERR(fid); mutex_unlock(&v9inode->v_mutex); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index f4645c515262..e2e7c749925a 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -853,7 +853,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, struct p9_fid *fid, *inode_fid; struct dentry *res = NULL; - if (d_unhashed(dentry)) { + if (d_in_lookup(dentry)) { res = v9fs_vfs_lookup(dir, dentry, 0); if (IS_ERR(res)) return PTR_ERR(res); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index a34702c998f5..1b51eaa5e2dd 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -254,7 +254,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, struct posix_acl *pacl = NULL, *dacl = NULL; struct dentry *res = NULL; - if (d_unhashed(dentry)) { + if (d_in_lookup(dentry)) { res = v9fs_vfs_lookup(dir, dentry, 0); if (IS_ERR(res)) return PTR_ERR(res); diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index f0d268b97d19..a439548de785 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -70,9 +70,13 @@ struct autofs_info { }; #define AUTOFS_INF_EXPIRING (1<<0) /* dentry in the process of expiring */ -#define AUTOFS_INF_NO_RCU (1<<1) /* the dentry is being considered +#define AUTOFS_INF_WANT_EXPIRE (1<<1) /* the dentry is being considered * for expiry, so RCU_walk is - * not permitted + * not permitted. If it progresses to + * actual expiry attempt, the flag is + * not cleared when EXPIRING is set - + * in that case it gets cleared only + * when it comes to clearing EXPIRING. */ #define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */ diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 9510d8d2e9cd..b493909e7492 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -316,19 +316,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb, if (ino->flags & AUTOFS_INF_PENDING) goto out; if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { - ino->flags |= AUTOFS_INF_NO_RCU; + ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); spin_lock(&sbi->fs_lock); if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { ino->flags |= AUTOFS_INF_EXPIRING; - smp_mb(); - ino->flags &= ~AUTOFS_INF_NO_RCU; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); return root; } - ino->flags &= ~AUTOFS_INF_NO_RCU; + ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; } out: spin_unlock(&sbi->fs_lock); @@ -446,7 +444,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, while ((dentry = get_next_positive_subdir(dentry, root))) { spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(dentry); - if (ino->flags & AUTOFS_INF_NO_RCU) + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) expired = NULL; else expired = should_expire(dentry, mnt, timeout, how); @@ -455,7 +453,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, continue; } ino = autofs4_dentry_ino(expired); - ino->flags |= AUTOFS_INF_NO_RCU; + ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); spin_lock(&sbi->fs_lock); @@ -465,7 +463,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, goto found; } - ino->flags &= ~AUTOFS_INF_NO_RCU; + ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; if (expired != dentry) dput(expired); spin_unlock(&sbi->fs_lock); @@ -475,17 +473,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, found: pr_debug("returning %p %pd\n", expired, expired); ino->flags |= AUTOFS_INF_EXPIRING; - smp_mb(); - ino->flags &= ~AUTOFS_INF_NO_RCU; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); - spin_lock(&sbi->lookup_lock); - spin_lock(&expired->d_parent->d_lock); - spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&expired->d_parent->d_subdirs, &expired->d_child); - spin_unlock(&expired->d_lock); - spin_unlock(&expired->d_parent->d_lock); - spin_unlock(&sbi->lookup_lock); return expired; } @@ -496,7 +485,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) int status; /* Block on any pending expire */ - if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))) + if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE)) return 0; if (rcu_walk) return -ECHILD; @@ -554,7 +543,7 @@ int autofs4_expire_run(struct super_block *sb, ino = autofs4_dentry_ino(dentry); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = now; - ino->flags &= ~AUTOFS_INF_EXPIRING; + ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); @@ -583,7 +572,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, spin_lock(&sbi->fs_lock); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = now; - ino->flags &= ~AUTOFS_INF_EXPIRING; + ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); dput(dentry); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 78bd80298528..3767f6641af1 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -458,7 +458,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk) */ struct inode *inode; - if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)) + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) return 0; if (d_mountpoint(dentry)) return 0; diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 0146d911f468..631f1554c87b 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -66,11 +66,12 @@ static int autofs4_write(struct autofs_sb_info *sbi, set_fs(KERNEL_DS); mutex_lock(&sbi->pipe_mutex); - wr = __vfs_write(file, data, bytes, &file->f_pos); - while (bytes && wr) { + while (bytes) { + wr = __vfs_write(file, data, bytes, &file->f_pos); + if (wr <= 0) + break; data += wr; bytes -= wr; - wr = __vfs_write(file, data, bytes, &file->f_pos); } mutex_unlock(&sbi->pipe_mutex); diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index b677a6ea6001..7706c8dc5fa6 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -2645,7 +2645,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state, * This algorithm is recursive because the amount of used stack space * is very small and the max recursion depth is limited. */ - indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)", + indent_add = sprintf(buf, "%c-%llu(%s/%llu/%u)", btrfsic_get_block_type(state, block), block->logical_bytenr, block->dev_state->name, block->dev_bytenr, block->mirror_num); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 46025688f1d0..a85cf7d23309 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1554,6 +1554,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, trans->transid, root->fs_info->generation); if (!should_cow_block(trans, root, buf)) { + trans->dirty = true; *cow_ret = buf; return 0; } @@ -1785,10 +1786,12 @@ static noinline int generic_bin_search(struct extent_buffer *eb, if (!err) { tmp = (struct btrfs_disk_key *)(kaddr + offset - map_start); - } else { + } else if (err == 1) { read_extent_buffer(eb, &unaligned, offset, sizeof(unaligned)); tmp = &unaligned; + } else { + return err; } } else { @@ -2512,6 +2515,8 @@ read_block_for_search(struct btrfs_trans_handle *trans, if (!btrfs_buffer_uptodate(tmp, 0, 0)) ret = -EIO; free_extent_buffer(tmp); + } else { + ret = PTR_ERR(tmp); } return ret; } @@ -2775,8 +2780,10 @@ again: * then we don't want to set the path blocking, * so we test it here */ - if (!should_cow_block(trans, root, b)) + if (!should_cow_block(trans, root, b)) { + trans->dirty = true; goto cow_done; + } /* * must have write locks on this node and the @@ -2825,6 +2832,8 @@ cow_done: } ret = key_search(b, key, level, &prev_cmp, &slot); + if (ret < 0) + goto done; if (level != 0) { int dec = 0; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 101c3cfd3f7c..4274a7bfdaed 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2518,7 +2518,7 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, unsigned long count); int btrfs_async_run_delayed_refs(struct btrfs_root *root, - unsigned long count, int wait); + unsigned long count, u64 transid, int wait); int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len); int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 61561c2a3f96..d3aaabbfada0 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1606,15 +1606,23 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode) return 0; } -void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list, - struct list_head *del_list) +bool btrfs_readdir_get_delayed_items(struct inode *inode, + struct list_head *ins_list, + struct list_head *del_list) { struct btrfs_delayed_node *delayed_node; struct btrfs_delayed_item *item; delayed_node = btrfs_get_delayed_node(inode); if (!delayed_node) - return; + return false; + + /* + * We can only do one readdir with delayed items at a time because of + * item->readdir_list. + */ + inode_unlock_shared(inode); + inode_lock(inode); mutex_lock(&delayed_node->mutex); item = __btrfs_first_delayed_insertion_item(delayed_node); @@ -1641,10 +1649,13 @@ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list, * requeue or dequeue this delayed node. */ atomic_dec(&delayed_node->refs); + + return true; } -void btrfs_put_delayed_items(struct list_head *ins_list, - struct list_head *del_list) +void btrfs_readdir_put_delayed_items(struct inode *inode, + struct list_head *ins_list, + struct list_head *del_list) { struct btrfs_delayed_item *curr, *next; @@ -1659,6 +1670,12 @@ void btrfs_put_delayed_items(struct list_head *ins_list, if (atomic_dec_and_test(&curr->refs)) kfree(curr); } + + /* + * The VFS is going to do up_read(), so we need to downgrade back to a + * read lock. + */ + downgrade_write(&inode->i_rwsem); } int btrfs_should_delete_dir_index(struct list_head *del_list, diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 0167853c84ae..2495b3d4075f 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -137,10 +137,12 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root); void btrfs_destroy_delayed_inodes(struct btrfs_root *root); /* Used for readdir() */ -void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list, - struct list_head *del_list); -void btrfs_put_delayed_items(struct list_head *ins_list, - struct list_head *del_list); +bool btrfs_readdir_get_delayed_items(struct inode *inode, + struct list_head *ins_list, + struct list_head *del_list); +void btrfs_readdir_put_delayed_items(struct inode *inode, + struct list_head *ins_list, + struct list_head *del_list); int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index); int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1142127f6e5e..60ce1190307b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1098,7 +1098,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr) struct inode *btree_inode = root->fs_info->btree_inode; buf = btrfs_find_create_tree_block(root, bytenr); - if (!buf) + if (IS_ERR(buf)) return; read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, buf, 0, WAIT_NONE, btree_get_extent, 0); @@ -1114,7 +1114,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, int ret; buf = btrfs_find_create_tree_block(root, bytenr); - if (!buf) + if (IS_ERR(buf)) return 0; set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags); @@ -1172,8 +1172,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, int ret; buf = btrfs_find_create_tree_block(root, bytenr); - if (!buf) - return ERR_PTR(-ENOMEM); + if (IS_ERR(buf)) + return buf; ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid); if (ret) { @@ -1806,6 +1806,13 @@ static int cleaner_kthread(void *arg) if (btrfs_need_cleaner_sleep(root)) goto sleep; + /* + * Do not do anything if we might cause open_ctree() to block + * before we have finished mounting the filesystem. + */ + if (!root->fs_info->open) + goto sleep; + if (!mutex_trylock(&root->fs_info->cleaner_mutex)) goto sleep; @@ -2520,7 +2527,6 @@ int open_ctree(struct super_block *sb, int num_backups_tried = 0; int backup_index = 0; int max_active; - bool cleaner_mutex_locked = false; tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL); @@ -2800,7 +2806,7 @@ int open_ctree(struct super_block *sb, nodesize = btrfs_super_nodesize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); - stripesize = btrfs_super_stripesize(disk_super); + stripesize = sectorsize; fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids)); fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids)); @@ -2999,13 +3005,6 @@ retry_root_backup: goto fail_sysfs; } - /* - * Hold the cleaner_mutex thread here so that we don't block - * for a long time on btrfs_recover_relocation. cleaner_kthread - * will wait for us to finish mounting the filesystem. - */ - mutex_lock(&fs_info->cleaner_mutex); - cleaner_mutex_locked = true; fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root, "btrfs-cleaner"); if (IS_ERR(fs_info->cleaner_kthread)) @@ -3065,8 +3064,10 @@ retry_root_backup: ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto fail_qgroup; - /* We locked cleaner_mutex before creating cleaner_kthread. */ + + mutex_lock(&fs_info->cleaner_mutex); ret = btrfs_recover_relocation(tree_root); + mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) { btrfs_warn(fs_info, "failed to recover relocation: %d", ret); @@ -3074,8 +3075,6 @@ retry_root_backup: goto fail_qgroup; } } - mutex_unlock(&fs_info->cleaner_mutex); - cleaner_mutex_locked = false; location.objectid = BTRFS_FS_TREE_OBJECTID; location.type = BTRFS_ROOT_ITEM_KEY; @@ -3189,10 +3188,6 @@ fail_cleaner: filemap_write_and_wait(fs_info->btree_inode->i_mapping); fail_sysfs: - if (cleaner_mutex_locked) { - mutex_unlock(&fs_info->cleaner_mutex); - cleaner_mutex_locked = false; - } btrfs_sysfs_remove_mounted(fs_info); fail_fsdev_sysfs: @@ -4138,8 +4133,7 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, btrfs_super_bytes_used(sb)); ret = -EINVAL; } - if (!is_power_of_2(btrfs_super_stripesize(sb)) || - btrfs_super_stripesize(sb) != sectorsize) { + if (!is_power_of_2(btrfs_super_stripesize(sb))) { btrfs_err(fs_info, "invalid stripesize %u", btrfs_super_stripesize(sb)); ret = -EINVAL; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 689d25ac6a68..82b912a293ab 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2835,6 +2835,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans, struct async_delayed_refs { struct btrfs_root *root; + u64 transid; int count; int error; int sync; @@ -2850,6 +2851,10 @@ static void delayed_ref_async_start(struct btrfs_work *work) async = container_of(work, struct async_delayed_refs, work); + /* if the commit is already started, we don't need to wait here */ + if (btrfs_transaction_blocked(async->root->fs_info)) + goto done; + trans = btrfs_join_transaction(async->root); if (IS_ERR(trans)) { async->error = PTR_ERR(trans); @@ -2861,10 +2866,15 @@ static void delayed_ref_async_start(struct btrfs_work *work) * wait on delayed refs */ trans->sync = true; + + /* Don't bother flushing if we got into a different transaction */ + if (trans->transid > async->transid) + goto end; + ret = btrfs_run_delayed_refs(trans, async->root, async->count); if (ret) async->error = ret; - +end: ret = btrfs_end_transaction(trans, async->root); if (ret && !async->error) async->error = ret; @@ -2876,7 +2886,7 @@ done: } int btrfs_async_run_delayed_refs(struct btrfs_root *root, - unsigned long count, int wait) + unsigned long count, u64 transid, int wait) { struct async_delayed_refs *async; int ret; @@ -2888,6 +2898,7 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root, async->root = root->fs_info->tree_root; async->count = count; async->error = 0; + async->transid = transid; if (wait) async->sync = 1; else @@ -8016,8 +8027,9 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf; buf = btrfs_find_create_tree_block(root, bytenr); - if (!buf) - return ERR_PTR(-ENOMEM); + if (IS_ERR(buf)) + return buf; + btrfs_set_header_generation(buf, trans->transid); btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); btrfs_tree_lock(buf); @@ -8044,7 +8056,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, set_extent_dirty(&trans->transaction->dirty_pages, buf->start, buf->start + buf->len - 1, GFP_NOFS); } - trans->blocks_used++; + trans->dirty = true; /* this returns a buffer locked for blocking */ return buf; } @@ -8659,8 +8671,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, next = btrfs_find_tree_block(root->fs_info, bytenr); if (!next) { next = btrfs_find_create_tree_block(root, bytenr); - if (!next) - return -ENOMEM; + if (IS_ERR(next)) + return PTR_ERR(next); + btrfs_set_buffer_lockdep_class(root->root_key.objectid, next, level - 1); reada = 1; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a3412d68ad37..75533adef998 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4892,18 +4892,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, int uptodate = 1; int ret; + if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) { + btrfs_err(fs_info, "bad tree block start %llu", start); + return ERR_PTR(-EINVAL); + } + eb = find_extent_buffer(fs_info, start); if (eb) return eb; eb = __alloc_extent_buffer(fs_info, start, len); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); for (i = 0; i < num_pages; i++, index++) { p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL); - if (!p) + if (!p) { + exists = ERR_PTR(-ENOMEM); goto free_eb; + } spin_lock(&mapping->private_lock); if (PagePrivate(p)) { @@ -4948,8 +4955,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); again: ret = radix_tree_preload(GFP_NOFS); - if (ret) + if (ret) { + exists = ERR_PTR(ret); goto free_eb; + } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, @@ -5333,6 +5342,11 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv, return ret; } +/* + * return 0 if the item is found within a page. + * return 1 if the item spans two pages. + * return -EINVAL otherwise. + */ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, unsigned long min_len, char **map, unsigned long *map_start, @@ -5347,7 +5361,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, PAGE_SHIFT; if (i != end_i) - return -EINVAL; + return 1; if (i == 0) { offset = start_offset; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e0c9bd3fb02d..2234e88cf674 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1534,30 +1534,30 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes = round_up(write_bytes + sector_offset, root->sectorsize); - if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) && - check_can_nocow(inode, pos, &write_bytes) > 0) { - /* - * For nodata cow case, no need to reserve - * data space. - */ - only_release_metadata = true; - /* - * our prealloc extent may be smaller than - * write_bytes, so scale down. - */ - num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_SIZE); - reserve_bytes = round_up(write_bytes + sector_offset, - root->sectorsize); - goto reserve_metadata; - } - ret = btrfs_check_data_free_space(inode, pos, write_bytes); - if (ret < 0) - break; + if (ret < 0) { + if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) && + check_can_nocow(inode, pos, &write_bytes) > 0) { + /* + * For nodata cow case, no need to reserve + * data space. + */ + only_release_metadata = true; + /* + * our prealloc extent may be smaller than + * write_bytes, so scale down. + */ + num_pages = DIV_ROUND_UP(write_bytes + offset, + PAGE_SIZE); + reserve_bytes = round_up(write_bytes + + sector_offset, + root->sectorsize); + } else { + break; + } + } -reserve_metadata: ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes); if (ret) { if (!only_release_metadata) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8b1212e8f7a8..4421954720b8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3271,7 +3271,16 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) /* grab metadata reservation from transaction handle */ if (reserve) { ret = btrfs_orphan_reserve_metadata(trans, inode); - BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */ + ASSERT(!ret); + if (ret) { + atomic_dec(&root->orphan_inodes); + clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, + &BTRFS_I(inode)->runtime_flags); + if (insert) + clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags); + return ret; + } } /* insert an orphan item to track this unlinked/truncated file */ @@ -4549,6 +4558,7 @@ delete: BUG_ON(ret); if (btrfs_should_throttle_delayed_refs(trans, root)) btrfs_async_run_delayed_refs(root, + trans->transid, trans->delayed_ref_updates * 2, 0); if (be_nice) { if (truncate_space_check(trans, root, @@ -5748,6 +5758,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) int name_len; int is_curr = 0; /* ctx->pos points to the current index? */ bool emitted; + bool put = false; /* FIXME, use a real flag for deciding about the key type */ if (root->fs_info->tree_root == root) @@ -5765,7 +5776,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (key_type == BTRFS_DIR_INDEX_KEY) { INIT_LIST_HEAD(&ins_list); INIT_LIST_HEAD(&del_list); - btrfs_get_delayed_items(inode, &ins_list, &del_list); + put = btrfs_readdir_get_delayed_items(inode, &ins_list, + &del_list); } key.type = key_type; @@ -5912,8 +5924,8 @@ next: nopos: ret = 0; err: - if (key_type == BTRFS_DIR_INDEX_KEY) - btrfs_put_delayed_items(&ins_list, &del_list); + if (put) + btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list); btrfs_free_path(path); return ret; } @@ -10525,7 +10537,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = { static const struct file_operations btrfs_dir_file_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = btrfs_real_readdir, + .iterate_shared = btrfs_real_readdir, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_compat_ioctl, diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index e96634a725c3..aca8264f4a49 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -968,6 +968,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, struct rb_node *prev = NULL; struct btrfs_ordered_extent *test; int ret = 1; + u64 orig_offset = offset; spin_lock_irq(&tree->lock); if (ordered) { @@ -983,7 +984,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, /* truncate file */ if (disk_i_size > i_size) { - BTRFS_I(inode)->disk_i_size = i_size; + BTRFS_I(inode)->disk_i_size = orig_offset; ret = 0; goto out; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 4339b6613f19..60e7179ed4b7 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -235,7 +235,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, trans->aborted = errno; /* Nothing used. The other threads that have joined this * transaction may be able to continue. */ - if (!trans->blocks_used && list_empty(&trans->new_bgs)) { + if (!trans->dirty && list_empty(&trans->new_bgs)) { const char *errstr; errstr = btrfs_decode_error(errno); @@ -1807,6 +1807,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) } } sb->s_flags &= ~MS_RDONLY; + + fs_info->open = 1; } out: wake_up_process(fs_info->transaction_kthread); diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 10eb249ef891..02223f3f78f4 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -68,7 +68,7 @@ int btrfs_init_test_fs(void) if (IS_ERR(test_mnt)) { printk(KERN_ERR "btrfs: cannot mount test file system\n"); unregister_filesystem(&test_type); - return ret; + return PTR_ERR(test_mnt); } return 0; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index f6e24cb423ae..948aa186b353 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -818,6 +818,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, { struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_fs_info *info = root->fs_info; + u64 transid = trans->transid; unsigned long cur = trans->delayed_ref_updates; int lock = (trans->type != TRANS_JOIN_NOLOCK); int err = 0; @@ -905,7 +906,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); if (must_run_delayed_refs) { - btrfs_async_run_delayed_refs(root, cur, + btrfs_async_run_delayed_refs(root, cur, transid, must_run_delayed_refs == 1); } return err; @@ -1311,11 +1312,6 @@ int btrfs_defrag_root(struct btrfs_root *root) return ret; } -/* Bisesctability fixup, remove in 4.8 */ -#ifndef btrfs_std_error -#define btrfs_std_error btrfs_handle_fs_error -#endif - /* * Do all special snapshot related qgroup dirty hack. * @@ -1385,7 +1381,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, switch_commit_roots(trans->transaction, fs_info); ret = btrfs_write_and_wait_transaction(trans, src); if (ret) - btrfs_std_error(fs_info, ret, + btrfs_handle_fs_error(fs_info, ret, "Error while writing out transaction for qgroup"); out: diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 9fe0ec2bf0fe..c5abee4f01ad 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -110,7 +110,6 @@ struct btrfs_trans_handle { u64 chunk_bytes_reserved; unsigned long use_count; unsigned long blocks_reserved; - unsigned long blocks_used; unsigned long delayed_ref_updates; struct btrfs_transaction *transaction; struct btrfs_block_rsv *block_rsv; @@ -121,6 +120,7 @@ struct btrfs_trans_handle { bool can_flush_pending_bgs; bool reloc_reserved; bool sync; + bool dirty; unsigned int type; /* * this root is only needed to validate that the root passed to diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index b7665af471d8..c05f69a8ec42 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2422,8 +2422,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, root_owner = btrfs_header_owner(parent); next = btrfs_find_create_tree_block(root, bytenr); - if (!next) - return -ENOMEM; + if (IS_ERR(next)) + return PTR_ERR(next); if (*level == 1) { ret = wc->process_func(root, next, wc, ptr_gen); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 548faaa9e169..589f128173b1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4694,12 +4694,12 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, if (type & BTRFS_BLOCK_GROUP_RAID5) { raid_stripe_len = find_raid56_stripe_len(ndevs - 1, - btrfs_super_stripesize(info->super_copy)); + extent_root->stripesize); data_stripes = num_stripes - 1; } if (type & BTRFS_BLOCK_GROUP_RAID6) { raid_stripe_len = find_raid56_stripe_len(ndevs - 2, - btrfs_super_stripesize(info->super_copy)); + extent_root->stripesize); data_stripes = num_stripes - 2; } @@ -6607,8 +6607,8 @@ int btrfs_read_sys_array(struct btrfs_root *root) * overallocate but we can keep it as-is, only the first page is used. */ sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET); - if (!sb) - return -ENOMEM; + if (IS_ERR(sb)) + return PTR_ERR(sb); set_extent_buffer_uptodate(sb); btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0); /* diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 6e72c98162d5..1780218a48f0 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -95,10 +95,8 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) } dentry = d_obtain_alias(inode); - if (IS_ERR(dentry)) { - iput(inode); + if (IS_ERR(dentry)) return dentry; - } err = ceph_init_dentry(dentry); if (err < 0) { dput(dentry); @@ -167,10 +165,8 @@ static struct dentry *__get_parent(struct super_block *sb, return ERR_PTR(-ENOENT); dentry = d_obtain_alias(inode); - if (IS_ERR(dentry)) { - iput(inode); + if (IS_ERR(dentry)) return dentry; - } err = ceph_init_dentry(dentry); if (err < 0) { dput(dentry); @@ -210,7 +206,7 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, dout("fh_to_parent %llx\n", cfh->parent_ino); dentry = __get_parent(sb, NULL, cfh->ino); - if (IS_ERR(dentry) && PTR_ERR(dentry) == -ENOENT) + if (unlikely(dentry == ERR_PTR(-ENOENT))) dentry = __fh_to_dentry(sb, cfh->parent_ino); return dentry; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ce2f5795e44b..0daaf7ceedc5 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -394,7 +394,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); - if (d_unhashed(dentry)) { + if (d_in_lookup(dentry)) { dn = ceph_finish_lookup(req, dentry, err); if (IS_ERR(dn)) err = PTR_ERR(dn); diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 5a53ac6b1e02..02b071bf3732 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -101,6 +101,12 @@ convert_sfm_char(const __u16 src_char, char *target) case SFM_SLASH: *target = '\\'; break; + case SFM_SPACE: + *target = ' '; + break; + case SFM_PERIOD: + *target = '.'; + break; default: return false; } @@ -404,7 +410,7 @@ static __le16 convert_to_sfu_char(char src_char) return dest_char; } -static __le16 convert_to_sfm_char(char src_char) +static __le16 convert_to_sfm_char(char src_char, bool end_of_string) { __le16 dest_char; @@ -427,6 +433,18 @@ static __le16 convert_to_sfm_char(char src_char) case '|': dest_char = cpu_to_le16(SFM_PIPE); break; + case '.': + if (end_of_string) + dest_char = cpu_to_le16(SFM_PERIOD); + else + dest_char = 0; + break; + case ' ': + if (end_of_string) + dest_char = cpu_to_le16(SFM_SPACE); + else + dest_char = 0; + break; default: dest_char = 0; } @@ -469,9 +487,16 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, /* see if we must remap this char */ if (map_chars == SFU_MAP_UNI_RSVD) dst_char = convert_to_sfu_char(src_char); - else if (map_chars == SFM_MAP_UNI_RSVD) - dst_char = convert_to_sfm_char(src_char); - else + else if (map_chars == SFM_MAP_UNI_RSVD) { + bool end_of_string; + + if (i == srclen - 1) + end_of_string = true; + else + end_of_string = false; + + dst_char = convert_to_sfm_char(src_char, end_of_string); + } else dst_char = 0; /* * FIXME: We can not handle remapping backslash (UNI_SLASH) diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index bdc52cb9a676..479bc0a941f3 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -64,6 +64,8 @@ #define SFM_LESSTHAN ((__u16) 0xF023) #define SFM_PIPE ((__u16) 0xF027) #define SFM_SLASH ((__u16) 0xF026) +#define SFM_PERIOD ((__u16) 0xF028) +#define SFM_SPACE ((__u16) 0xF029) /* * Mapping mechanism to use when one of the seven reserved characters is diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5d8b7edf8a8f..5d841f39c4b7 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -87,6 +87,7 @@ extern mempool_t *cifs_req_poolp; extern mempool_t *cifs_mid_poolp; struct workqueue_struct *cifsiod_wq; +__u32 cifs_lock_secret; /* * Bumps refcount for cifs super block. @@ -1266,6 +1267,8 @@ init_cifs(void) spin_lock_init(&cifs_file_list_lock); spin_lock_init(&GlobalMid_Lock); + get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret)); + if (cifs_max_pending < 2) { cifs_max_pending = 2; cifs_dbg(FYI, "cifs_max_pending set to min of 2\n"); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index bba106cdc43c..8f1d8c1e72be 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1619,6 +1619,7 @@ void cifs_oplock_break(struct work_struct *work); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; +extern __u32 cifs_lock_secret; extern mempool_t *cifs_mid_poolp; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 66736f57b5ab..7d2b15c06090 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -428,7 +428,9 @@ cifs_echo_request(struct work_struct *work) * server->ops->need_neg() == true. Also, no need to ping if * we got a response recently. */ - if (!server->ops->need_neg || server->ops->need_neg(server) || + + if (server->tcpStatus == CifsNeedReconnect || + server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew || (server->ops->can_echo && !server->ops->can_echo(server)) || time_before(jiffies, server->lstrp + echo_interval - HZ)) goto requeue_echo; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index c3eb998a99bd..fb0903fffc22 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -445,7 +445,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, * Check for hashed negative dentry. We have already revalidated * the dentry and it is fine. No need to perform another lookup. */ - if (!d_unhashed(direntry)) + if (!d_in_lookup(direntry)) return -ENOENT; res = cifs_lookup(inode, direntry, 0); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 9793ae0bcaa2..d4890b6dc22d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1112,6 +1112,12 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return rc; } +static __u32 +hash_lockowner(fl_owner_t owner) +{ + return cifs_lock_secret ^ hash32_ptr((const void *)owner); +} + struct lock_to_push { struct list_head llist; __u64 offset; @@ -1178,7 +1184,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) else type = CIFS_WRLCK; lck = list_entry(el, struct lock_to_push, llist); - lck->pid = flock->fl_pid; + lck->pid = hash_lockowner(flock->fl_owner); lck->netfid = cfile->fid.netfid; lck->length = length; lck->type = type; @@ -1305,7 +1311,8 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, posix_lock_type = CIFS_RDLCK; else posix_lock_type = CIFS_WRLCK; - rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid, + rc = CIFSSMBPosixLock(xid, tcon, netfid, + hash_lockowner(flock->fl_owner), flock->fl_start, length, flock, posix_lock_type, wait_flag); return rc; @@ -1505,7 +1512,8 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, posix_lock_type = CIFS_UNLCK; rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid, - current->tgid, flock->fl_start, length, + hash_lockowner(flock->fl_owner), + flock->fl_start, length, NULL, posix_lock_type, wait_flag); goto out; } diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 848249fa120f..3079b38f0afb 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -133,6 +133,6 @@ typedef struct _AUTHENTICATE_MESSAGE { int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses); void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses); -int build_ntlmssp_auth_blob(unsigned char *pbuffer, u16 *buflen, +int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, const struct nls_table *nls_cp); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index af0ec2d5ad0e..538d9b55699a 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -364,19 +364,43 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, sec_blob->DomainName.MaximumLength = 0; } -/* We do not malloc the blob, it is passed in pbuffer, because its - maximum possible size is fixed and small, making this approach cleaner. - This function returns the length of the data in the blob */ -int build_ntlmssp_auth_blob(unsigned char *pbuffer, +static int size_of_ntlmssp_blob(struct cifs_ses *ses) +{ + int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len + - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2; + + if (ses->domainName) + sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN); + else + sz += 2; + + if (ses->user_name) + sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN); + else + sz += 2; + + return sz; +} + +int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, const struct nls_table *nls_cp) { int rc; - AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer; + AUTHENTICATE_MESSAGE *sec_blob; __u32 flags; unsigned char *tmp; + rc = setup_ntlmv2_rsp(ses, nls_cp); + if (rc) { + cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc); + *buflen = 0; + goto setup_ntlmv2_ret; + } + *pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL); + sec_blob = (AUTHENTICATE_MESSAGE *)*pbuffer; + memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmAuthenticate; @@ -391,7 +415,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, flags |= NTLMSSP_NEGOTIATE_KEY_XCH; } - tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE); + tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE); sec_blob->NegotiateFlags = cpu_to_le32(flags); sec_blob->LmChallengeResponse.BufferOffset = @@ -399,13 +423,9 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, sec_blob->LmChallengeResponse.Length = 0; sec_blob->LmChallengeResponse.MaximumLength = 0; - sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->NtChallengeResponse.BufferOffset = + cpu_to_le32(tmp - *pbuffer); if (ses->user_name != NULL) { - rc = setup_ntlmv2_rsp(ses, nls_cp); - if (rc) { - cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc); - goto setup_ntlmv2_ret; - } memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE, ses->auth_key.len - CIFS_SESS_KEY_SIZE); tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE; @@ -423,23 +443,23 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, } if (ses->domainName == NULL) { - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->DomainName.Length = 0; sec_blob->DomainName.MaximumLength = 0; tmp += 2; } else { int len; len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName, - CIFS_MAX_USERNAME_LEN, nls_cp); + CIFS_MAX_DOMAINNAME_LEN, nls_cp); len *= 2; /* unicode is 2 bytes each */ - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->DomainName.Length = cpu_to_le16(len); sec_blob->DomainName.MaximumLength = cpu_to_le16(len); tmp += len; } if (ses->user_name == NULL) { - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->UserName.Length = 0; sec_blob->UserName.MaximumLength = 0; tmp += 2; @@ -448,13 +468,13 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name, CIFS_MAX_USERNAME_LEN, nls_cp); len *= 2; /* unicode is 2 bytes each */ - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->UserName.Length = cpu_to_le16(len); sec_blob->UserName.MaximumLength = cpu_to_le16(len); tmp += len; } - sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->WorkstationName.Length = 0; sec_blob->WorkstationName.MaximumLength = 0; tmp += 2; @@ -463,19 +483,19 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) && !calc_seckey(ses)) { memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE); - sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE); sec_blob->SessionKey.MaximumLength = cpu_to_le16(CIFS_CPHTXT_SIZE); tmp += CIFS_CPHTXT_SIZE; } else { - sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->SessionKey.Length = 0; sec_blob->SessionKey.MaximumLength = 0; } + *buflen = tmp - *pbuffer; setup_ntlmv2_ret: - *buflen = tmp - pbuffer; return rc; } @@ -690,6 +710,8 @@ sess_auth_lanman(struct sess_data *sess_data) rc = calc_lanman_hash(ses->password, ses->server->cryptkey, ses->server->sec_mode & SECMODE_PW_ENCRYPT ? true : false, lnm_session_key); + if (rc) + goto out; memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE); bcc_ptr += CIFS_AUTH_RESP_SIZE; @@ -1266,7 +1288,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) struct cifs_ses *ses = sess_data->ses; __u16 bytes_remaining; char *bcc_ptr; - char *ntlmsspblob = NULL; + unsigned char *ntlmsspblob = NULL; u16 blob_len; cifs_dbg(FYI, "rawntlmssp session setup authenticate phase\n"); @@ -1279,19 +1301,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) /* Build security blob before we assemble the request */ pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; smb_buf = (struct smb_hdr *)pSMB; - /* - * 5 is an empirical value, large enough to hold - * authenticate message plus max 10 of av paris, - * domain, user, workstation names, flags, etc. - */ - ntlmsspblob = kzalloc(5*sizeof(struct _AUTHENTICATE_MESSAGE), - GFP_KERNEL); - if (!ntlmsspblob) { - rc = -ENOMEM; - goto out; - } - - rc = build_ntlmssp_auth_blob(ntlmsspblob, + rc = build_ntlmssp_auth_blob(&ntlmsspblob, &blob_len, ses, sess_data->nls_cp); if (rc) goto out_free_ntlmsspblob; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 8f38e33d365b..29e06db5f187 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -588,7 +588,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, u16 blob_length = 0; struct key *spnego_key = NULL; char *security_blob = NULL; - char *ntlmssp_blob = NULL; + unsigned char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ cifs_dbg(FYI, "Session Setup\n"); @@ -713,13 +713,7 @@ ssetup_ntlmssp_authenticate: iov[1].iov_len = blob_length; } else if (phase == NtLmAuthenticate) { req->hdr.SessionId = ses->Suid; - ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500, - GFP_KERNEL); - if (ntlmssp_blob == NULL) { - rc = -ENOMEM; - goto ssetup_exit; - } - rc = build_ntlmssp_auth_blob(ntlmssp_blob, &blob_length, ses, + rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses, nls_cp); if (rc) { cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n", @@ -1818,6 +1812,33 @@ SMB2_echo(struct TCP_Server_Info *server) cifs_dbg(FYI, "In echo request\n"); + if (server->tcpStatus == CifsNeedNegotiate) { + struct list_head *tmp, *tmp2; + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n"); + spin_lock(&cifs_tcp_ses_lock); + list_for_each(tmp, &server->smb_ses_list) { + ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + list_for_each(tmp2, &ses->tcon_list) { + tcon = list_entry(tmp2, struct cifs_tcon, + tcon_list); + /* add check for persistent handle reconnect */ + if (tcon && tcon->need_reconnect) { + spin_unlock(&cifs_tcp_ses_lock); + rc = smb2_reconnect(SMB2_ECHO, tcon); + spin_lock(&cifs_tcp_ses_lock); + } + } + } + spin_unlock(&cifs_tcp_ses_lock); + } + + /* if no session, renegotiate failed above */ + if (server->tcpStatus == CifsNeedNegotiate) + return -EIO; + rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req); if (rc) return rc; diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 33b7ee34eda5..bbc1252a59f5 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -357,8 +357,6 @@ configfs_write_bin_file(struct file *file, const char __user *buf, len = simple_write_to_buffer(buffer->bin_buffer, buffer->bin_buffer_size, ppos, buf, count); - if (len > 0) - *ppos += len; out: mutex_unlock(&buffer->mutex); return len; diff --git a/fs/dax.c b/fs/dax.c index 761495bf5eb9..e207f8f9b700 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -208,7 +208,12 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, dax.addr += first; size = map_len - first; } - max = min(pos + size, end); + /* + * pos + size is one past the last offset for IO, + * so pos + size can overflow loff_t at extreme offsets. + * Cast to u64 to catch this and get the true minimum. + */ + max = min_t(u64, pos + size, end); } if (iov_iter_rw(iter) == WRITE) { diff --git a/fs/dcache.c b/fs/dcache.c index 817c243c1ff1..d6847d7b123d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -507,6 +507,44 @@ void d_drop(struct dentry *dentry) } EXPORT_SYMBOL(d_drop); +static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) +{ + struct dentry *next; + /* + * Inform d_walk() and shrink_dentry_list() that we are no longer + * attached to the dentry tree + */ + dentry->d_flags |= DCACHE_DENTRY_KILLED; + if (unlikely(list_empty(&dentry->d_child))) + return; + __list_del_entry(&dentry->d_child); + /* + * Cursors can move around the list of children. While we'd been + * a normal list member, it didn't matter - ->d_child.next would've + * been updated. However, from now on it won't be and for the + * things like d_walk() it might end up with a nasty surprise. + * Normally d_walk() doesn't care about cursors moving around - + * ->d_lock on parent prevents that and since a cursor has no children + * of its own, we get through it without ever unlocking the parent. + * There is one exception, though - if we ascend from a child that + * gets killed as soon as we unlock it, the next sibling is found + * using the value left in its ->d_child.next. And if _that_ + * pointed to a cursor, and cursor got moved (e.g. by lseek()) + * before d_walk() regains parent->d_lock, we'll end up skipping + * everything the cursor had been moved past. + * + * Solution: make sure that the pointer left behind in ->d_child.next + * points to something that won't be moving around. I.e. skip the + * cursors. + */ + while (dentry->d_child.next != &parent->d_subdirs) { + next = list_entry(dentry->d_child.next, struct dentry, d_child); + if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) + break; + dentry->d_child.next = next->d_child.next; + } +} + static void __dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; @@ -532,12 +570,7 @@ static void __dentry_kill(struct dentry *dentry) } /* if it was on the hash then remove it */ __d_drop(dentry); - __list_del_entry(&dentry->d_child); - /* - * Inform d_walk() that we are no longer attached to the - * dentry tree - */ - dentry->d_flags |= DCACHE_DENTRY_KILLED; + dentry_unlist(dentry, parent); if (parent) spin_unlock(&parent->d_lock); dentry_iput(dentry); @@ -1203,6 +1236,9 @@ resume: struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; + if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); @@ -1651,6 +1687,16 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) } EXPORT_SYMBOL(d_alloc); +struct dentry *d_alloc_cursor(struct dentry * parent) +{ + struct dentry *dentry = __d_alloc(parent->d_sb, NULL); + if (dentry) { + dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR; + dentry->d_parent = dget(parent); + } + return dentry; +} + /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock @@ -2457,7 +2503,6 @@ retry: rcu_read_unlock(); goto retry; } - rcu_read_unlock(); /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), @@ -2470,8 +2515,6 @@ retry: continue; if (dentry->d_parent != parent) continue; - if (d_unhashed(dentry)) - continue; if (parent->d_flags & DCACHE_OP_COMPARE) { int tlen = dentry->d_name.len; const char *tname = dentry->d_name.name; @@ -2483,9 +2526,18 @@ retry: if (dentry_cmp(dentry, str, len)) continue; } - dget(dentry); hlist_bl_unlock(b); - /* somebody is doing lookup for it right now; wait for it */ + /* now we can try to grab a reference */ + if (!lockref_get_not_dead(&dentry->d_lockref)) { + rcu_read_unlock(); + goto retry; + } + + rcu_read_unlock(); + /* + * somebody is likely to be still doing lookup for it; + * wait for them to finish + */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* @@ -2516,6 +2568,7 @@ retry: dput(new); return dentry; } + rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 9c1c9a01b7e5..592059f88e04 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -127,7 +127,6 @@ static int open_proxy_open(struct inode *inode, struct file *filp) r = real_fops->open(inode, filp); out: - fops_put(real_fops); debugfs_use_file_finish(srcu_idx); return r; } @@ -262,8 +261,10 @@ static int full_proxy_open(struct inode *inode, struct file *filp) if (real_fops->open) { r = real_fops->open(inode, filp); - - if (filp->f_op != proxy_fops) { + if (r) { + replace_fops(filp, d_inode(dentry)->i_fop); + goto free_proxy; + } else if (filp->f_op != proxy_fops) { /* No protection against file removal anymore. */ WARN(1, "debugfs file owner replaced proxy fops: %pd", dentry); diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 0d8eb3455b34..e5e29f8c920b 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -45,7 +45,7 @@ * ecryptfs_to_hex * @dst: Buffer to take hex character representation of contents of * src; must be at least of size (src_size * 2) - * @src: Buffer to be converted to a hex string respresentation + * @src: Buffer to be converted to a hex string representation * @src_size: number of bytes to convert */ void ecryptfs_to_hex(char *dst, char *src, size_t src_size) @@ -60,7 +60,7 @@ void ecryptfs_to_hex(char *dst, char *src, size_t src_size) * ecryptfs_from_hex * @dst: Buffer to take the bytes from src hex; must be at least of * size (src_size / 2) - * @src: Buffer to be converted from a hex string respresentation to raw value + * @src: Buffer to be converted from a hex string representation to raw value * @dst_size: size of dst buffer, or number of hex characters pairs to convert */ void ecryptfs_from_hex(char *dst, char *src, int dst_size) @@ -953,7 +953,7 @@ struct ecryptfs_cipher_code_str_map_elem { }; /* Add support for additional ciphers by adding elements here. The - * cipher_code is whatever OpenPGP applicatoins use to identify the + * cipher_code is whatever OpenPGP applications use to identify the * ciphers. List in order of probability. */ static struct ecryptfs_cipher_code_str_map_elem ecryptfs_cipher_code_str_map[] = { @@ -1410,7 +1410,7 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry, * * Common entry point for reading file metadata. From here, we could * retrieve the header information from the header region of the file, - * the xattr region of the file, or some other repostory that is + * the xattr region of the file, or some other repository that is * stored separately from the file itself. The current implementation * supports retrieving the metadata information from the file contents * and from the xattr region. diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 7000b96b783e..ca4e83750214 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -169,9 +169,22 @@ out: return rc; } +static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + /* + * Don't allow mmap on top of file systems that don't support it + * natively. If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs + * allows recursive mounting, this will need to be extended. + */ + if (!lower_file->f_op->mmap) + return -ENODEV; + return generic_file_mmap(file, vma); +} + /** * ecryptfs_open - * @inode: inode speciying file to open + * @inode: inode specifying file to open * @file: Structure to return filled in * * Opens the file specified by inode. @@ -240,7 +253,7 @@ out: /** * ecryptfs_dir_open - * @inode: inode speciying file to open + * @inode: inode specifying file to open * @file: Structure to return filled in * * Opens the file specified by inode. @@ -403,7 +416,7 @@ const struct file_operations ecryptfs_main_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, #endif - .mmap = generic_file_mmap, + .mmap = ecryptfs_mmap, .open = ecryptfs_open, .flush = ecryptfs_flush, .release = ecryptfs_release, diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index e818f5ac7a26..866bb18efefe 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -25,7 +25,6 @@ #include #include #include -#include #include "ecryptfs_kernel.h" struct ecryptfs_open_req { @@ -148,7 +147,7 @@ int ecryptfs_privileged_open(struct file **lower_file, flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR; (*lower_file) = dentry_open(&req.path, flags, cred); if (!IS_ERR(*lower_file)) - goto have_file; + goto out; if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; @@ -166,16 +165,8 @@ int ecryptfs_privileged_open(struct file **lower_file, mutex_unlock(&ecryptfs_kthread_ctl.mux); wake_up(&ecryptfs_kthread_ctl.wait); wait_for_completion(&req.done); - if (IS_ERR(*lower_file)) { + if (IS_ERR(*lower_file)) rc = PTR_ERR(*lower_file); - goto out; - } -have_file: - if ((*lower_file)->f_op->mmap == NULL) { - fput(*lower_file); - *lower_file = NULL; - rc = -EMEDIUMTYPE; - } out: return rc; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 1698132d0e57..612004495141 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -738,8 +738,7 @@ static void ecryptfs_free_kmem_caches(void) struct ecryptfs_cache_info *info; info = &ecryptfs_cache_infos[i]; - if (*(info->cache)) - kmem_cache_destroy(*(info->cache)); + kmem_cache_destroy(*(info->cache)); } } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 989a2cef6b76..fe7e83a45eff 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -483,9 +483,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) goto out_free; } inode->i_state |= I_WB_SWITCH; + __iget(inode); spin_unlock(&inode->i_lock); - ihold(inode); isw->inode = inode; atomic_inc(&isw_nr_in_flight); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index ccd4971cc6c1..cca7b048c07b 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -341,8 +341,10 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, struct dentry *newent; bool outarg_valid = true; + fuse_lock_inode(dir); err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name, &outarg, &inode); + fuse_unlock_inode(dir); if (err == -ENOENT) { outarg_valid = false; err = 0; @@ -478,7 +480,7 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry, struct fuse_conn *fc = get_fuse_conn(dir); struct dentry *res = NULL; - if (d_unhashed(entry)) { + if (d_in_lookup(entry)) { res = fuse_lookup(dir, entry, 0); if (IS_ERR(res)) return PTR_ERR(res); @@ -1341,7 +1343,9 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx) fuse_read_fill(req, file, ctx->pos, PAGE_SIZE, FUSE_READDIR); } + fuse_lock_inode(inode); fuse_request_send(fc, req); + fuse_unlock_inode(inode); nbytes = req->out.args[0].size; err = req->out.h.error; fuse_put_request(fc, req); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index eddbe02c4028..929c383432b0 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -110,6 +110,9 @@ struct fuse_inode { /** Miscellaneous bits describing inode state */ unsigned long state; + + /** Lock for serializing lookup and readdir for back compatibility*/ + struct mutex mutex; }; /** FUSE inode state bits */ @@ -540,6 +543,9 @@ struct fuse_conn { /** write-back cache policy (default is write-through) */ unsigned writeback_cache:1; + /** allow parallel lookups and readdir (default is serialized) */ + unsigned parallel_dirops:1; + /* * The following bitfields are only for optimization purposes * and hence races in setting them will not cause malfunction @@ -956,4 +962,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, void fuse_set_initialized(struct fuse_conn *fc); +void fuse_unlock_inode(struct inode *inode); +void fuse_lock_inode(struct inode *inode); + #endif /* _FS_FUSE_I_H */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1ce67668a8e1..9961d8432ce3 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -97,6 +97,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&fi->queued_writes); INIT_LIST_HEAD(&fi->writepages); init_waitqueue_head(&fi->page_waitq); + mutex_init(&fi->mutex); fi->forget = fuse_alloc_forget(); if (!fi->forget) { kmem_cache_free(fuse_inode_cachep, inode); @@ -117,6 +118,7 @@ static void fuse_destroy_inode(struct inode *inode) struct fuse_inode *fi = get_fuse_inode(inode); BUG_ON(!list_empty(&fi->write_files)); BUG_ON(!list_empty(&fi->queued_writes)); + mutex_destroy(&fi->mutex); kfree(fi->forget); call_rcu(&inode->i_rcu, fuse_i_callback); } @@ -351,6 +353,18 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, return 0; } +void fuse_lock_inode(struct inode *inode) +{ + if (!get_fuse_conn(inode)->parallel_dirops) + mutex_lock(&get_fuse_inode(inode)->mutex); +} + +void fuse_unlock_inode(struct inode *inode) +{ + if (!get_fuse_conn(inode)->parallel_dirops) + mutex_unlock(&get_fuse_inode(inode)->mutex); +} + static void fuse_umount_begin(struct super_block *sb) { fuse_abort_conn(get_fuse_conn_super(sb)); @@ -898,6 +912,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->async_dio = 1; if (arg->flags & FUSE_WRITEBACK_CACHE) fc->writeback_cache = 1; + if (arg->flags & FUSE_PARALLEL_DIROPS) + fc->parallel_dirops = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fc->sb->s_time_gran = arg->time_gran; } else { @@ -928,7 +944,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | - FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT; + FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | + FUSE_PARALLEL_DIROPS; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 21dc784f66c2..9bad79fede37 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1189,7 +1189,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, struct dentry *d; bool excl = !!(flags & O_EXCL); - if (!d_unhashed(dentry)) + if (!d_in_lookup(dentry)) goto skip_lookup; d = __gfs2_lookup(dir, dentry, file, opened); diff --git a/fs/internal.h b/fs/internal.h index b71deeecea17..f57ced528cde 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -130,6 +130,7 @@ extern int invalidate_inodes(struct super_block *, bool); extern struct dentry *__d_alloc(struct super_block *, const struct qstr *); extern int d_set_mounted(struct dentry *dentry); extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); +extern struct dentry *d_alloc_cursor(struct dentry *); /* * read_write.c diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index b31852f76f46..e3ca4b4cac84 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2329,18 +2329,10 @@ void *jbd2_alloc(size_t size, gfp_t flags) BUG_ON(size & (size-1)); /* Must be a power of 2 */ - flags |= __GFP_REPEAT; - if (size == PAGE_SIZE) - ptr = (void *)__get_free_pages(flags, 0); - else if (size > PAGE_SIZE) { - int order = get_order(size); - - if (order < 3) - ptr = (void *)__get_free_pages(flags, order); - else - ptr = vmalloc(size); - } else + if (size < PAGE_SIZE) ptr = kmem_cache_alloc(get_slab(size), flags); + else + ptr = (void *)__get_free_pages(flags, get_order(size)); /* Check alignment; SLUB has gotten this wrong in the past, * and this can lead to user data corruption! */ @@ -2351,20 +2343,10 @@ void *jbd2_alloc(size_t size, gfp_t flags) void jbd2_free(void *ptr, size_t size) { - if (size == PAGE_SIZE) { - free_pages((unsigned long)ptr, 0); - return; - } - if (size > PAGE_SIZE) { - int order = get_order(size); - - if (order < 3) - free_pages((unsigned long)ptr, order); - else - vfree(ptr); - return; - } - kmem_cache_free(get_slab(size), ptr); + if (size < PAGE_SIZE) + kmem_cache_free(get_slab(size), ptr); + else + free_pages((unsigned long)ptr, get_order(size)); }; /* diff --git a/fs/libfs.c b/fs/libfs.c index 3db2721144c2..74dc8b9e7f53 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -71,9 +71,7 @@ EXPORT_SYMBOL(simple_lookup); int dcache_dir_open(struct inode *inode, struct file *file) { - static struct qstr cursor_name = QSTR_INIT(".", 1); - - file->private_data = d_alloc(file->f_path.dentry, &cursor_name); + file->private_data = d_alloc_cursor(file->f_path.dentry); return file->private_data ? 0 : -ENOMEM; } @@ -86,6 +84,61 @@ int dcache_dir_close(struct inode *inode, struct file *file) } EXPORT_SYMBOL(dcache_dir_close); +/* parent is locked at least shared */ +static struct dentry *next_positive(struct dentry *parent, + struct list_head *from, + int count) +{ + unsigned *seq = &parent->d_inode->i_dir_seq, n; + struct dentry *res; + struct list_head *p; + bool skipped; + int i; + +retry: + i = count; + skipped = false; + n = smp_load_acquire(seq) & ~1; + res = NULL; + rcu_read_lock(); + for (p = from->next; p != &parent->d_subdirs; p = p->next) { + struct dentry *d = list_entry(p, struct dentry, d_child); + if (!simple_positive(d)) { + skipped = true; + } else if (!--i) { + res = d; + break; + } + } + rcu_read_unlock(); + if (skipped) { + smp_rmb(); + if (unlikely(*seq != n)) + goto retry; + } + return res; +} + +static void move_cursor(struct dentry *cursor, struct list_head *after) +{ + struct dentry *parent = cursor->d_parent; + unsigned n, *seq = &parent->d_inode->i_dir_seq; + spin_lock(&parent->d_lock); + for (;;) { + n = *seq; + if (!(n & 1) && cmpxchg(seq, n, n + 1) == n) + break; + cpu_relax(); + } + __list_del(cursor->d_child.prev, cursor->d_child.next); + if (after) + list_add(&cursor->d_child, after); + else + list_add_tail(&cursor->d_child, &parent->d_subdirs); + smp_store_release(seq, n + 2); + spin_unlock(&parent->d_lock); +} + loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; @@ -101,25 +154,14 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) if (offset != file->f_pos) { file->f_pos = offset; if (file->f_pos >= 2) { - struct list_head *p; struct dentry *cursor = file->private_data; + struct dentry *to; loff_t n = file->f_pos - 2; - spin_lock(&dentry->d_lock); - /* d_lock not required for cursor */ - list_del(&cursor->d_child); - p = dentry->d_subdirs.next; - while (n && p != &dentry->d_subdirs) { - struct dentry *next; - next = list_entry(p, struct dentry, d_child); - spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); - if (simple_positive(next)) - n--; - spin_unlock(&next->d_lock); - p = p->next; - } - list_add_tail(&cursor->d_child, p); - spin_unlock(&dentry->d_lock); + inode_lock_shared(dentry->d_inode); + to = next_positive(dentry, &dentry->d_subdirs, n); + move_cursor(cursor, to ? &to->d_child : NULL); + inode_unlock_shared(dentry->d_inode); } } return offset; @@ -142,36 +184,25 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *p, *q = &cursor->d_child; + struct list_head *p = &cursor->d_child; + struct dentry *next; + bool moved = false; if (!dir_emit_dots(file, ctx)) return 0; - spin_lock(&dentry->d_lock); - if (ctx->pos == 2) - list_move(q, &dentry->d_subdirs); - for (p = q->next; p != &dentry->d_subdirs; p = p->next) { - struct dentry *next = list_entry(p, struct dentry, d_child); - spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); - if (!simple_positive(next)) { - spin_unlock(&next->d_lock); - continue; - } - - spin_unlock(&next->d_lock); - spin_unlock(&dentry->d_lock); + if (ctx->pos == 2) + p = &dentry->d_subdirs; + while ((next = next_positive(dentry, p, 1)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, dt_type(d_inode(next)))) - return 0; - spin_lock(&dentry->d_lock); - spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); - /* next is still alive */ - list_move(q, p); - spin_unlock(&next->d_lock); - p = q; + break; + moved = true; + p = &next->d_child; ctx->pos++; } - spin_unlock(&dentry->d_lock); + if (moved) + move_cursor(cursor, p); return 0; } EXPORT_SYMBOL(dcache_readdir); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 154a107cd376..fc4084ef4736 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -335,12 +335,17 @@ static struct notifier_block lockd_inet6addr_notifier = { }; #endif -static void lockd_svc_exit_thread(void) +static void lockd_unregister_notifiers(void) { unregister_inetaddr_notifier(&lockd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&lockd_inet6addr_notifier); #endif +} + +static void lockd_svc_exit_thread(void) +{ + lockd_unregister_notifiers(); svc_exit_thread(nlmsvc_rqst); } @@ -462,7 +467,7 @@ int lockd_up(struct net *net) * Note: svc_serv structures have an initial use count of 1, * so we exit through here on both success and failure. */ -err_net: +err_put: svc_destroy(serv); err_create: mutex_unlock(&nlmsvc_mutex); @@ -470,7 +475,9 @@ err_create: err_start: lockd_down_net(serv, net); - goto err_net; +err_net: + lockd_unregister_notifiers(); + goto err_put; } EXPORT_SYMBOL_GPL(lockd_up); diff --git a/fs/locks.c b/fs/locks.c index 7c5f91be9b65..ee1b15f6fc13 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1628,7 +1628,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr { struct file_lock *fl, *my_fl = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; diff --git a/fs/namespace.c b/fs/namespace.c index a7ec92c051f5..419f746d851d 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1562,6 +1562,7 @@ void __detach_mounts(struct dentry *dentry) goto out_unlock; lock_mount_hash(); + event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { @@ -3247,6 +3248,10 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) if (mnt->mnt.mnt_sb->s_iflags & SB_I_NOEXEC) mnt_flags &= ~(MNT_LOCK_NOSUID | MNT_LOCK_NOEXEC); + /* Don't miss readonly hidden in the superblock flags */ + if (mnt->mnt.mnt_sb->s_flags & MS_RDONLY) + mnt_flags |= MNT_LOCK_READONLY; + /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index aaf7bd0cbae2..19d93d0cd400 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -424,12 +424,17 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc, static int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) { + struct inode *inode; struct nfs_inode *nfsi; if (d_really_is_negative(dentry)) return 0; - nfsi = NFS_I(d_inode(dentry)); + inode = d_inode(dentry); + if (is_bad_inode(inode) || NFS_STALE(inode)) + return 0; + + nfsi = NFS_I(inode); if (entry->fattr->fileid == nfsi->fileid) return 1; if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0) @@ -1363,7 +1368,6 @@ EXPORT_SYMBOL_GPL(nfs_dentry_operations); struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *res; - struct dentry *parent; struct inode *inode = NULL; struct nfs_fh *fhandle = NULL; struct nfs_fattr *fattr = NULL; @@ -1393,7 +1397,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in if (IS_ERR(label)) goto out; - parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ trace_nfs_lookup_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); @@ -1482,11 +1485,13 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned open_flags, umode_t mode, int *opened) { + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct nfs_open_context *ctx; struct dentry *res; struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; unsigned int lookup_flags = 0; + bool switched = false; int err; /* Expect a negative dentry */ @@ -1501,7 +1506,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, /* NFS only supports OPEN on regular files */ if ((open_flags & O_DIRECTORY)) { - if (!d_unhashed(dentry)) { + if (!d_in_lookup(dentry)) { /* * Hashed negative dentry with O_DIRECTORY: dentry was * revalidated and is fine, no need to perform lookup @@ -1525,6 +1530,17 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, attr.ia_size = 0; } + if (!(open_flags & O_CREAT) && !d_in_lookup(dentry)) { + d_drop(dentry); + switched = true; + dentry = d_alloc_parallel(dentry->d_parent, + &dentry->d_name, &wq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + if (unlikely(!d_in_lookup(dentry))) + return finish_no_open(file, dentry); + } + ctx = create_nfs_open_context(dentry, open_flags); err = PTR_ERR(ctx); if (IS_ERR(ctx)) @@ -1536,9 +1552,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, err = PTR_ERR(inode); trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); put_nfs_open_context(ctx); + d_drop(dentry); switch (err) { case -ENOENT: - d_drop(dentry); d_add(dentry, NULL); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; @@ -1560,14 +1576,23 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); put_nfs_open_context(ctx); out: + if (unlikely(switched)) { + d_lookup_done(dentry); + dput(dentry); + } return err; no_open: res = nfs_lookup(dir, dentry, lookup_flags); - err = PTR_ERR(res); + if (switched) { + d_lookup_done(dentry); + if (!res) + res = dentry; + else + dput(dentry); + } if (IS_ERR(res)) - goto out; - + return PTR_ERR(res); return finish_no_open(file, res); } EXPORT_SYMBOL_GPL(nfs_atomic_open); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 979b3c4dee6a..c7326c2af2c3 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -353,10 +353,12 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq) result = wait_for_completion_killable(&dreq->completion); + if (!result) { + result = dreq->count; + WARN_ON_ONCE(dreq->count < 0); + } if (!result) result = dreq->error; - if (!result) - result = dreq->count; out: return (ssize_t) result; @@ -386,8 +388,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write) if (dreq->iocb) { long res = (long) dreq->error; - if (!res) + if (dreq->count != 0) { res = (long) dreq->count; + WARN_ON_ONCE(dreq->count < 0); + } dreq->iocb->ki_complete(dreq->iocb, res, 0); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 52e7d6869e3b..dda689d7a8a7 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -282,6 +282,7 @@ nfs_init_locked(struct inode *inode, void *opaque) struct nfs_fattr *fattr = desc->fattr; set_nfs_fileid(inode, fattr->fileid); + inode->i_mode = fattr->mode; nfs_copy_fh(NFS_FH(inode), desc->fh); return 0; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index de97567795a5..ff416d0e24bc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2882,12 +2882,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) call_close |= is_wronly; else if (is_wronly) calldata->arg.fmode |= FMODE_WRITE; + if (calldata->arg.fmode != (FMODE_READ|FMODE_WRITE)) + call_close |= is_rdwr; } 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); @@ -7924,8 +7923,8 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, break; } lo = NFS_I(inode)->layout; - if (lo && nfs4_stateid_match(&lgp->args.stateid, - &lo->plh_stateid)) { + if (lo && !test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) && + nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) { LIST_HEAD(head); /* @@ -7936,10 +7935,10 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0); spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&head); + status = -EAGAIN; + goto out; } else spin_unlock(&inode->i_lock); - status = -EAGAIN; - goto out; } status = nfs4_handle_exception(server, status, exception); @@ -8036,7 +8035,10 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags) .flags = RPC_TASK_ASYNC, }; struct pnfs_layout_segment *lseg = NULL; - struct nfs4_exception exception = { .timeout = *timeout }; + struct nfs4_exception exception = { + .inode = inode, + .timeout = *timeout, + }; int status = 0; dprintk("--> %s\n", __func__); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 9679f4749364..834b875900d6 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1488,9 +1488,9 @@ restart: } spin_unlock(&state->state_lock); } - nfs4_put_open_state(state); clear_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags); + nfs4_put_open_state(state); spin_lock(&sp->so_lock); goto restart; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0c7e0d45a4de..0fbe734cc38c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -361,8 +361,10 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, list_del_init(&lseg->pls_list); /* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */ atomic_dec(&lo->plh_refcount); - if (list_empty(&lo->plh_segs)) + if (list_empty(&lo->plh_segs)) { + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); + } rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); } @@ -1290,6 +1292,7 @@ alloc_init_layout_hdr(struct inode *ino, INIT_LIST_HEAD(&lo->plh_bulk_destroy); lo->plh_inode = ino; lo->plh_lc_cred = get_rpccred(ctx->cred); + lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID; return lo; } @@ -1297,6 +1300,8 @@ static struct pnfs_layout_hdr * pnfs_find_alloc_layout(struct inode *ino, struct nfs_open_context *ctx, gfp_t gfp_flags) + __releases(&ino->i_lock) + __acquires(&ino->i_lock) { struct nfs_inode *nfsi = NFS_I(ino); struct pnfs_layout_hdr *new = NULL; @@ -1565,8 +1570,7 @@ lookup_again: * stateid, or it has been invalidated, then we must use the open * stateid. */ - if (lo->plh_stateid.seqid == 0 || - test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) { + if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) { /* * The first layoutget for the file. Need to serialize per diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 0dfc476da3e1..b38e3c0dc790 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -247,7 +247,11 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages, } /* Helper function for pnfs_generic_commit_pagelist to catch an empty - * page list. This can happen when two commits race. */ + * page list. This can happen when two commits race. + * + * This must be called instead of nfs_init_commit - call one or the other, but + * not both! + */ static bool pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages, struct nfs_commit_data *data, @@ -256,7 +260,11 @@ pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages, if (list_empty(pages)) { if (atomic_dec_and_test(&cinfo->mds->rpcs_out)) wake_up_atomic_t(&cinfo->mds->rpcs_out); - nfs_commitdata_release(data); + /* don't call nfs_commitdata_release - it tries to put + * the open_context which is not acquired until nfs_init_commit + * which has not been called on @data */ + WARN_ON_ONCE(data->context); + nfs_commit_free(data); return true; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 6776d7a7839e..572e5b3b06f1 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -367,13 +367,13 @@ readpage_async_filler(void *data, struct page *page) nfs_list_remove_request(new); nfs_readpage_release(new); error = desc->pgio->pg_error; - goto out_unlock; + goto out; } return 0; out_error: error = PTR_ERR(new); -out_unlock: unlock_page(page); +out: return error; } diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index e55b5242614d..31f3df193bdb 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -290,7 +290,7 @@ out_free_buf: return error; } -#define NFSD_MDS_PR_KEY 0x0100000000000000 +#define NFSD_MDS_PR_KEY 0x0100000000000000ULL /* * We use the client ID as a unique key for the reservations. diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 1580ea6fd64d..d08cd88155c7 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -104,22 +104,21 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp, goto out; inode = d_inode(fh->fh_dentry); - if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) { - error = -EOPNOTSUPP; - goto out_errno; - } error = fh_want_write(fh); if (error) goto out_errno; - error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS); + fh_lock(fh); + + error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access); if (error) - goto out_drop_write; - error = inode->i_op->set_acl(inode, argp->acl_default, - ACL_TYPE_DEFAULT); + goto out_drop_lock; + error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default); if (error) - goto out_drop_write; + goto out_drop_lock; + + fh_unlock(fh); fh_drop_write(fh); @@ -131,7 +130,8 @@ out: posix_acl_release(argp->acl_access); posix_acl_release(argp->acl_default); return nfserr; -out_drop_write: +out_drop_lock: + fh_unlock(fh); fh_drop_write(fh); out_errno: nfserr = nfserrno(error); diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 01df4cd7c753..0c890347cde3 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -95,22 +95,20 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp, goto out; inode = d_inode(fh->fh_dentry); - if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) { - error = -EOPNOTSUPP; - goto out_errno; - } error = fh_want_write(fh); if (error) goto out_errno; - error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS); + fh_lock(fh); + + error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access); if (error) - goto out_drop_write; - error = inode->i_op->set_acl(inode, argp->acl_default, - ACL_TYPE_DEFAULT); + goto out_drop_lock; + error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default); -out_drop_write: +out_drop_lock: + fh_unlock(fh); fh_drop_write(fh); out_errno: nfserr = nfserrno(error); diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 6adabd6049b7..71292a0d6f09 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -770,9 +770,6 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, dentry = fhp->fh_dentry; inode = d_inode(dentry); - if (!inode->i_op->set_acl || !IS_POSIXACL(inode)) - return nfserr_attrnotsupp; - if (S_ISDIR(inode->i_mode)) flags = NFS4_ACL_DIR; @@ -782,16 +779,19 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_error < 0) goto out_nfserr; - host_error = inode->i_op->set_acl(inode, pacl, ACL_TYPE_ACCESS); + fh_lock(fhp); + + host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl); if (host_error < 0) - goto out_release; + goto out_drop_lock; if (S_ISDIR(inode->i_mode)) { - host_error = inode->i_op->set_acl(inode, dpacl, - ACL_TYPE_DEFAULT); + host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl); } -out_release: +out_drop_lock: + fh_unlock(fhp); + posix_acl_release(pacl); posix_acl_release(dpacl); out_nfserr: diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7389cb1d7409..04c68d900324 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -710,22 +710,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc } } -static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args) -{ - struct rpc_xprt *xprt; - - if (args->protocol != XPRT_TRANSPORT_BC_TCP) - return rpc_create(args); - - xprt = args->bc_xprt->xpt_bc_xprt; - if (xprt) { - xprt_get(xprt); - return rpc_create_xprt(args, xprt); - } - - return rpc_create(args); -} - 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); @@ -768,7 +752,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = ses->se_cb_sec.flavor; } /* Create RPC client */ - client = create_backchannel_client(&args); + client = rpc_create(&args); if (IS_ERR(client)) { dprintk("NFSD: couldn't create callback client: %ld\n", PTR_ERR(client)); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f5f82e145018..70d0b9b33031 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3480,12 +3480,17 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, } static struct nfs4_ol_stateid * -init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, - struct nfsd4_open *open) +init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_openowner *oo = open->op_openowner; struct nfs4_ol_stateid *retstp = NULL; + struct nfs4_ol_stateid *stp; + + stp = open->op_stp; + /* We are moving these outside of the spinlocks to avoid the warnings */ + mutex_init(&stp->st_mutex); + mutex_lock(&stp->st_mutex); spin_lock(&oo->oo_owner.so_client->cl_lock); spin_lock(&fp->fi_lock); @@ -3493,6 +3498,8 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, retstp = nfsd4_find_existing_open(fp, open); if (retstp) goto out_unlock; + + open->op_stp = NULL; atomic_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_OPEN_STID; INIT_LIST_HEAD(&stp->st_locks); @@ -3502,14 +3509,19 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; - init_rwsem(&stp->st_rwsem); list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&oo->oo_owner.so_client->cl_lock); - return retstp; + if (retstp) { + mutex_lock(&retstp->st_mutex); + /* To keep mutex tracking happy */ + mutex_unlock(&stp->st_mutex); + stp = retstp; + } + return stp; } /* @@ -4305,7 +4317,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf struct nfs4_client *cl = open->op_openowner->oo_owner.so_client; struct nfs4_file *fp = NULL; struct nfs4_ol_stateid *stp = NULL; - struct nfs4_ol_stateid *swapstp = NULL; struct nfs4_delegation *dp = NULL; __be32 status; @@ -4335,32 +4346,28 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf */ if (stp) { /* Stateid was found, this is an OPEN upgrade */ - down_read(&stp->st_rwsem); + mutex_lock(&stp->st_mutex); status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); if (status) { - up_read(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); goto out; } } else { - stp = open->op_stp; - open->op_stp = NULL; - swapstp = init_open_stateid(stp, fp, open); - if (swapstp) { - nfs4_put_stid(&stp->st_stid); - stp = swapstp; - down_read(&stp->st_rwsem); + /* stp is returned locked. */ + stp = init_open_stateid(fp, open); + /* See if we lost the race to some other thread */ + if (stp->st_access_bmap != 0) { status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); if (status) { - up_read(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); goto out; } goto upgrade_out; } - down_read(&stp->st_rwsem); status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); if (status) { - up_read(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); release_open_stateid(stp); goto out; } @@ -4372,7 +4379,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf } upgrade_out: nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid); - up_read(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { @@ -4977,12 +4984,12 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ * revoked delegations are kept only for free_stateid. */ return nfserr_bad_stateid; - down_write(&stp->st_rwsem); + mutex_lock(&stp->st_mutex); status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); if (status == nfs_ok) status = nfs4_check_fh(current_fh, &stp->st_stid); if (status != nfs_ok) - up_write(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); return status; } @@ -5030,7 +5037,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { - up_write(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } @@ -5062,12 +5069,12 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; if (oo->oo_flags & NFS4_OO_CONFIRMED) { - up_write(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); goto put_stateid; } oo->oo_flags |= NFS4_OO_CONFIRMED; nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); - up_write(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); @@ -5143,7 +5150,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid); status = nfs_ok; put_stateid: - up_write(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); @@ -5196,7 +5203,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); - up_write(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); nfsd4_close_open_stateid(stp); @@ -5422,7 +5429,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; - init_rwsem(&stp->st_rwsem); + mutex_init(&stp->st_mutex); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -5591,7 +5598,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &open_stp, nn); if (status) goto out; - up_write(&open_stp->st_rwsem); + mutex_unlock(&open_stp->st_mutex); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, @@ -5600,7 +5607,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); if (status == nfs_ok) - down_write(&lock_stp->st_rwsem); + mutex_lock(&lock_stp->st_mutex); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, @@ -5704,7 +5711,7 @@ out: seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; - up_write(&lock_stp->st_rwsem); + mutex_unlock(&lock_stp->st_mutex); /* * If this is a new, never-before-used stateid, and we are @@ -5874,7 +5881,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fput: fput(filp); put_stateid: - up_write(&stp->st_rwsem); + mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 986e51e5ceac..64053eadeb81 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -535,7 +535,7 @@ struct nfs4_ol_stateid { unsigned char st_access_bmap; unsigned char st_deny_bmap; struct nfs4_ol_stateid *st_openstp; - struct rw_semaphore st_rwsem; + struct mutex st_mutex; }; static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 809bd2de7ad0..e9fd241b9a0a 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -439,7 +439,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp) if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC) return 0; bytes = le16_to_cpu(sbp->s_bytes); - if (bytes > BLOCK_SIZE) + if (bytes < sumoff + 4 || bytes > BLOCK_SIZE) return 0; crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp, sumoff); diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile index e27e6527912b..4342c7ee7d20 100644 --- a/fs/ocfs2/Makefile +++ b/fs/ocfs2/Makefile @@ -1,7 +1,5 @@ ccflags-y := -Ifs/ocfs2 -ccflags-y += -DCATCH_BH_JBD_RACES - obj-$(CONFIG_OCFS2_FS) += \ ocfs2.o \ ocfs2_stackglue.o diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index fe50ded1b4ce..498641eed2db 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -139,11 +139,16 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, lock_buffer(bh); if (buffer_jbd(bh)) { +#ifdef CATCH_BH_JBD_RACES mlog(ML_ERROR, "block %llu had the JBD bit set " "while I was in lock_buffer!", (unsigned long long)bh->b_blocknr); BUG(); +#else + unlock_buffer(bh); + continue; +#endif } clear_buffer_uptodate(bh); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 22f0253a3567..5c9d2d80ff70 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -405,12 +405,21 @@ static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev, err = ovl_create_upper(dentry, inode, &stat, link, hardlink); } else { const struct cred *old_cred; + struct cred *override_cred; old_cred = ovl_override_creds(dentry->d_sb); - err = ovl_create_over_whiteout(dentry, inode, &stat, link, - hardlink); + err = -ENOMEM; + override_cred = prepare_creds(); + if (override_cred) { + override_cred->fsuid = old_cred->fsuid; + override_cred->fsgid = old_cred->fsgid; + put_cred(override_creds(override_cred)); + put_cred(override_cred); + err = ovl_create_over_whiteout(dentry, inode, &stat, + link, hardlink); + } revert_creds(old_cred); } @@ -496,6 +505,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) struct dentry *upper; struct dentry *opaquedir = NULL; int err; + int flags = 0; if (WARN_ON(!workdir)) return -EROFS; @@ -525,46 +535,39 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) if (err) goto out_dput; - whiteout = ovl_whiteout(workdir, dentry); - err = PTR_ERR(whiteout); - if (IS_ERR(whiteout)) + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) goto out_unlock; - upper = ovl_dentry_upper(dentry); - if (!upper) { - upper = lookup_one_len(dentry->d_name.name, upperdir, - dentry->d_name.len); - err = PTR_ERR(upper); - if (IS_ERR(upper)) - goto kill_whiteout; - - err = ovl_do_rename(wdir, whiteout, udir, upper, 0); - dput(upper); - if (err) - goto kill_whiteout; - } else { - int flags = 0; + err = -ESTALE; + if ((opaquedir && upper != opaquedir) || + (!opaquedir && ovl_dentry_upper(dentry) && + upper != ovl_dentry_upper(dentry))) { + goto out_dput_upper; + } - if (opaquedir) - upper = opaquedir; - err = -ESTALE; - if (upper->d_parent != upperdir) - goto kill_whiteout; + whiteout = ovl_whiteout(workdir, dentry); + err = PTR_ERR(whiteout); + if (IS_ERR(whiteout)) + goto out_dput_upper; - if (is_dir) - flags |= RENAME_EXCHANGE; + if (d_is_dir(upper)) + flags = RENAME_EXCHANGE; - err = ovl_do_rename(wdir, whiteout, udir, upper, flags); - if (err) - goto kill_whiteout; + err = ovl_do_rename(wdir, whiteout, udir, upper, flags); + if (err) + goto kill_whiteout; + if (flags) + ovl_cleanup(wdir, upper); - if (is_dir) - ovl_cleanup(wdir, upper); - } ovl_dentry_version_inc(dentry->d_parent); out_d_drop: d_drop(dentry); dput(whiteout); +out_dput_upper: + dput(upper); out_unlock: unlock_rename(workdir, upperdir); out_dput: diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 0ed7c4012437..d1cdc60dd68f 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -59,16 +59,40 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) if (err) goto out; + if (attr->ia_valid & ATTR_SIZE) { + struct inode *realinode = d_inode(ovl_dentry_real(dentry)); + + err = -ETXTBSY; + if (atomic_read(&realinode->i_writecount) < 0) + goto out_drop_write; + } + err = ovl_copy_up(dentry); if (!err) { + struct inode *winode = NULL; + upperdentry = ovl_dentry_upper(dentry); + if (attr->ia_valid & ATTR_SIZE) { + winode = d_inode(upperdentry); + err = get_write_access(winode); + if (err) + goto out_drop_write; + } + + if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) + attr->ia_valid &= ~ATTR_MODE; + inode_lock(upperdentry->d_inode); err = notify_change(upperdentry, attr, NULL); if (!err) ovl_copyattr(upperdentry->d_inode, dentry->d_inode); inode_unlock(upperdentry->d_inode); + + if (winode) + put_write_access(winode); } +out_drop_write: ovl_drop_write(dentry); out: return err; @@ -121,16 +145,18 @@ int ovl_permission(struct inode *inode, int mask) err = vfs_getattr(&realpath, &stat); if (err) - return err; + goto out_dput; + err = -ESTALE; if ((stat.mode ^ inode->i_mode) & S_IFMT) - return -ESTALE; + goto out_dput; inode->i_mode = stat.mode; inode->i_uid = stat.uid; inode->i_gid = stat.gid; - return generic_permission(inode, mask); + err = generic_permission(inode, mask); + goto out_dput; } /* Careful in RCU walk mode */ @@ -238,41 +264,27 @@ out: return err; } -static bool ovl_need_xattr_filter(struct dentry *dentry, - enum ovl_path_type type) -{ - if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER) - return S_ISDIR(dentry->d_inode->i_mode); - else - return false; -} - ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { - struct path realpath; - enum ovl_path_type type = ovl_path_real(dentry, &realpath); + struct dentry *realdentry = ovl_dentry_real(dentry); - if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) + if (ovl_is_private_xattr(name)) return -ENODATA; - return vfs_getxattr(realpath.dentry, name, value, size); + return vfs_getxattr(realdentry, name, value, size); } ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) { - struct path realpath; - enum ovl_path_type type = ovl_path_real(dentry, &realpath); + struct dentry *realdentry = ovl_dentry_real(dentry); ssize_t res; int off; - res = vfs_listxattr(realpath.dentry, list, size); + res = vfs_listxattr(realdentry, list, size); if (res <= 0 || size == 0) return res; - if (!ovl_need_xattr_filter(dentry, type)) - return res; - /* filter out private xattrs */ for (off = 0; off < res;) { char *s = list + off; @@ -302,7 +314,7 @@ int ovl_removexattr(struct dentry *dentry, const char *name) goto out; err = -ENODATA; - if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) + if (ovl_is_private_xattr(name)) goto out_drop_write; if (!OVL_TYPE_UPPER(type)) { @@ -401,12 +413,11 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, if (!inode) return NULL; - mode &= S_IFMT; - inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_flags |= S_NOATIME | S_NOCMTIME; + mode &= S_IFMT; switch (mode) { case S_IFDIR: inode->i_private = oe; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 4bd9b5ba8f42..cfbca53590d0 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -187,6 +187,7 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to) { to->i_uid = from->i_uid; to->i_gid = from->i_gid; + to->i_mode = from->i_mode; } /* dir.c */ diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index ce02f46029da..9a7693d5f8ff 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1082,11 +1082,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (err < 0) goto out_put_workdir; - if (!err) { - pr_err("overlayfs: upper fs needs to support d_type.\n"); - err = -EINVAL; - goto out_put_workdir; - } + /* + * We allowed this configuration and don't want to + * break users over kernel upgrade. So warn instead + * of erroring out. + */ + if (!err) + pr_warn("overlayfs: upper fs needs to support d_type.\n"); } } diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 8a4a266beff3..edc452c2a563 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -820,39 +820,43 @@ posix_acl_xattr_get(const struct xattr_handler *handler, return error; } -static int -posix_acl_xattr_set(const struct xattr_handler *handler, - struct dentry *unused, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) +int +set_posix_acl(struct inode *inode, int type, struct posix_acl *acl) { - struct posix_acl *acl = NULL; - int ret; - if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) return -EOPNOTSUPP; - if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) - return value ? -EACCES : 0; + if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) + return acl ? -EACCES : 0; if (!inode_owner_or_capable(inode)) return -EPERM; + if (acl) { + int ret = posix_acl_valid(acl); + if (ret) + return ret; + } + return inode->i_op->set_acl(inode, acl, type); +} +EXPORT_SYMBOL(set_posix_acl); + +static int +posix_acl_xattr_set(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) +{ + struct posix_acl *acl = NULL; + int ret; + if (value) { acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); - - if (acl) { - ret = posix_acl_valid(acl); - if (ret) - goto out; - } } - - ret = inode->i_op->set_acl(inode, acl, handler->flags); -out: + ret = set_posix_acl(inode, handler->flags, acl); posix_acl_release(acl); return ret; } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index b8f2d1e8c645..c72c16c5a60f 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1393,7 +1393,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) unsigned long safe_mask = 0; unsigned int commit_max_age = (unsigned int)-1; struct reiserfs_journal *journal = SB_JOURNAL(s); - char *new_opts = kstrdup(arg, GFP_KERNEL); + char *new_opts; int err; char *qf_names[REISERFS_MAXQUOTAS]; unsigned int qfmt = 0; @@ -1401,6 +1401,10 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) int i; #endif + new_opts = kstrdup(arg, GFP_KERNEL); + if (arg && !new_opts) + return -ENOMEM; + sync_filesystem(s); reiserfs_write_lock(s); @@ -1546,7 +1550,8 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) } out_ok_unlocked: - replace_mount_options(s, new_opts); + if (new_opts) + replace_mount_options(s, new_opts); return 0; out_err_unlock: diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 08316972ff93..7bbf420d1289 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -52,6 +52,7 @@ #include "ubifs.h" #include #include +#include static int read_block(struct inode *inode, void *addr, unsigned int block, struct ubifs_data_node *dn) @@ -1452,6 +1453,26 @@ static int ubifs_set_page_dirty(struct page *page) return ret; } +#ifdef CONFIG_MIGRATION +static int ubifs_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode) +{ + int rc; + + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0); + if (rc != MIGRATEPAGE_SUCCESS) + return rc; + + if (PagePrivate(page)) { + ClearPagePrivate(page); + SetPagePrivate(newpage); + } + + migrate_page_copy(newpage, page); + return MIGRATEPAGE_SUCCESS; +} +#endif + static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags) { /* @@ -1591,6 +1612,9 @@ const struct address_space_operations ubifs_file_address_operations = { .write_end = ubifs_write_end, .invalidatepage = ubifs_invalidatepage, .set_page_dirty = ubifs_set_page_dirty, +#ifdef CONFIG_MIGRATION + .migratepage = ubifs_migrate_page, +#endif .releasepage = ubifs_releasepage, }; diff --git a/fs/udf/partition.c b/fs/udf/partition.c index 5f861ed287c3..888c364b2fe9 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -295,7 +295,8 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block, map = &UDF_SB(sb)->s_partmaps[partition]; /* map to sparable/physical partition desc */ phyblock = udf_get_pblock(sb, eloc.logicalBlockNum, - map->s_partition_num, ext_offset + offset); + map->s_type_specific.s_metadata.s_phys_partition_ref, + ext_offset + offset); } brelse(epos.bh); @@ -317,14 +318,18 @@ uint32_t udf_get_pblock_meta25(struct super_block *sb, uint32_t block, mdata = &map->s_type_specific.s_metadata; inode = mdata->s_metadata_fe ? : mdata->s_mirror_fe; - /* We shouldn't mount such media... */ - BUG_ON(!inode); + if (!inode) + return 0xFFFFFFFF; + retblk = udf_try_read_meta(inode, block, partition, offset); if (retblk == 0xFFFFFFFF && mdata->s_metadata_fe) { udf_warn(sb, "error reading from METADATA, trying to read from MIRROR\n"); if (!(mdata->s_flags & MF_MIRROR_FE_LOADED)) { mdata->s_mirror_fe = udf_find_metadata_inode_efe(sb, - mdata->s_mirror_file_loc, map->s_partition_num); + mdata->s_mirror_file_loc, + mdata->s_phys_partition_ref); + if (IS_ERR(mdata->s_mirror_fe)) + mdata->s_mirror_fe = NULL; mdata->s_flags |= MF_MIRROR_FE_LOADED; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 5e2c8c814e1b..4942549e7dc8 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -951,13 +951,13 @@ out2: } struct inode *udf_find_metadata_inode_efe(struct super_block *sb, - u32 meta_file_loc, u32 partition_num) + u32 meta_file_loc, u32 partition_ref) { struct kernel_lb_addr addr; struct inode *metadata_fe; addr.logicalBlockNum = meta_file_loc; - addr.partitionReferenceNum = partition_num; + addr.partitionReferenceNum = partition_ref; metadata_fe = udf_iget_special(sb, &addr); @@ -974,7 +974,8 @@ struct inode *udf_find_metadata_inode_efe(struct super_block *sb, return metadata_fe; } -static int udf_load_metadata_files(struct super_block *sb, int partition) +static int udf_load_metadata_files(struct super_block *sb, int partition, + int type1_index) { struct udf_sb_info *sbi = UDF_SB(sb); struct udf_part_map *map; @@ -984,20 +985,21 @@ static int udf_load_metadata_files(struct super_block *sb, int partition) map = &sbi->s_partmaps[partition]; mdata = &map->s_type_specific.s_metadata; + mdata->s_phys_partition_ref = type1_index; /* metadata address */ udf_debug("Metadata file location: block = %d part = %d\n", - mdata->s_meta_file_loc, map->s_partition_num); + mdata->s_meta_file_loc, mdata->s_phys_partition_ref); fe = udf_find_metadata_inode_efe(sb, mdata->s_meta_file_loc, - map->s_partition_num); + mdata->s_phys_partition_ref); if (IS_ERR(fe)) { /* mirror file entry */ udf_debug("Mirror metadata file location: block = %d part = %d\n", - mdata->s_mirror_file_loc, map->s_partition_num); + mdata->s_mirror_file_loc, mdata->s_phys_partition_ref); fe = udf_find_metadata_inode_efe(sb, mdata->s_mirror_file_loc, - map->s_partition_num); + mdata->s_phys_partition_ref); if (IS_ERR(fe)) { udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n"); @@ -1015,7 +1017,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition) */ if (mdata->s_bitmap_file_loc != 0xFFFFFFFF) { addr.logicalBlockNum = mdata->s_bitmap_file_loc; - addr.partitionReferenceNum = map->s_partition_num; + addr.partitionReferenceNum = mdata->s_phys_partition_ref; udf_debug("Bitmap file location: block = %d part = %d\n", addr.logicalBlockNum, addr.partitionReferenceNum); @@ -1283,7 +1285,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block) p = (struct partitionDesc *)bh->b_data; partitionNumber = le16_to_cpu(p->partitionNumber); - /* First scan for TYPE1, SPARABLE and METADATA partitions */ + /* First scan for TYPE1 and SPARABLE partitions */ for (i = 0; i < sbi->s_partitions; i++) { map = &sbi->s_partmaps[i]; udf_debug("Searching map: (%d == %d)\n", @@ -1333,7 +1335,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block) goto out_bh; if (map->s_partition_type == UDF_METADATA_MAP25) { - ret = udf_load_metadata_files(sb, i); + ret = udf_load_metadata_files(sb, i, type1_idx); if (ret < 0) { udf_err(sb, "error loading MetaData partition map %d\n", i); diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index 27b5335730c9..c13875d669c0 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -61,6 +61,11 @@ struct udf_meta_data { __u32 s_bitmap_file_loc; __u32 s_alloc_unit_size; __u16 s_align_unit_size; + /* + * Partition Reference Number of the associated physical / sparable + * partition + */ + __u16 s_phys_partition_ref; int s_flags; struct inode *s_metadata_fe; struct inode *s_mirror_fe; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index dbca7375deef..63a6ff2cfc68 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1575,6 +1575,12 @@ xfs_ioc_swapext( goto out_put_tmp_file; } + if (f.file->f_op != &xfs_file_operations || + tmp.file->f_op != &xfs_file_operations) { + error = -EINVAL; + goto out_put_tmp_file; + } + ip = XFS_I(file_inode(f.file)); tip = XFS_I(file_inode(tmp.file)); diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h index 797ae2ec8eee..29c691265b49 100644 --- a/include/acpi/acpi_drivers.h +++ b/include/acpi/acpi_drivers.h @@ -78,6 +78,7 @@ /* ACPI PCI Interrupt Link (pci_link.c) */ +int acpi_irq_penalty_init(void); int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering, int *polarity, char **name); int acpi_pci_link_free_irq(acpi_handle handle); diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 4e4c21491c41..1ff3a76c265d 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -192,7 +192,7 @@ ACPI_INIT_GLOBAL(u8, acpi_gbl_do_not_use_xsdt, FALSE); /* * Optionally support group module level code. */ -ACPI_INIT_GLOBAL(u8, acpi_gbl_group_module_level_code, FALSE); +ACPI_INIT_GLOBAL(u8, acpi_gbl_group_module_level_code, TRUE); /* * Optionally use 32-bit FADT addresses if and when there is a conflict diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6a67ab94b553..081d0f258d4c 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -542,15 +542,19 @@ #define INIT_TEXT \ *(.init.text) \ + *(.text.startup) \ MEM_DISCARD(init.text) #define EXIT_DATA \ *(.exit.data) \ + *(.fini_array) \ + *(.dtors) \ MEM_DISCARD(exit.data) \ MEM_DISCARD(exit.rodata) #define EXIT_TEXT \ *(.exit.text) \ + *(.text.exit) \ MEM_DISCARD(exit.text) #define EXIT_CALL \ diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 9094599a1150..33466bfc6440 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -309,6 +309,7 @@ INTEL_VGA_DEVICE(0x5906, info), /* ULT GT1 */ \ INTEL_VGA_DEVICE(0x590E, info), /* ULX GT1 */ \ INTEL_VGA_DEVICE(0x5902, info), /* DT GT1 */ \ + INTEL_VGA_DEVICE(0x5908, info), /* Halo GT1 */ \ INTEL_VGA_DEVICE(0x590B, info), /* Halo GT1 */ \ INTEL_VGA_DEVICE(0x590A, info) /* SRV GT1 */ @@ -322,15 +323,12 @@ INTEL_VGA_DEVICE(0x591D, info) /* WKS GT2 */ #define INTEL_KBL_GT3_IDS(info) \ + INTEL_VGA_DEVICE(0x5923, info), /* ULT GT3 */ \ INTEL_VGA_DEVICE(0x5926, info), /* ULT GT3 */ \ - INTEL_VGA_DEVICE(0x592B, info), /* Halo GT3 */ \ - INTEL_VGA_DEVICE(0x592A, info) /* SRV GT3 */ + INTEL_VGA_DEVICE(0x5927, info) /* ULT GT3 */ #define INTEL_KBL_GT4_IDS(info) \ - INTEL_VGA_DEVICE(0x5932, info), /* DT GT4 */ \ - INTEL_VGA_DEVICE(0x593B, info), /* Halo GT4 */ \ - INTEL_VGA_DEVICE(0x593A, info), /* SRV GT4 */ \ - INTEL_VGA_DEVICE(0x593D, info) /* WKS GT4 */ + INTEL_VGA_DEVICE(0x593B, info) /* Halo GT4 */ #define INTEL_KBL_IDS(info) \ INTEL_KBL_GT1_IDS(info), \ diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index c801d9028e37..4cecb0b75b9c 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -316,6 +316,20 @@ ttm_bo_reference(struct ttm_buffer_object *bo) */ extern int ttm_bo_wait(struct ttm_buffer_object *bo, bool interruptible, bool no_wait); + +/** + * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo + * + * @placement: Return immediately if buffer is busy. + * @mem: The struct ttm_mem_reg indicating the region where the bo resides + * @new_flags: Describes compatible placement found + * + * Returns true if the placement is compatible + */ +extern bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags); + /** * ttm_bo_validate * diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index fe389ac31489..92e7e97ca8ff 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -18,13 +18,13 @@ #ifndef __ASM_ARM_KVM_PMU_H #define __ASM_ARM_KVM_PMU_H -#ifdef CONFIG_KVM_ARM_PMU - #include #include #define ARMV8_PMU_CYCLE_IDX (ARMV8_PMU_MAX_COUNTERS - 1) +#ifdef CONFIG_KVM_ARM_PMU + struct kvm_pmc { u8 idx; /* index into the pmu->pmc array */ struct perf_event *perf_event; diff --git a/include/linux/audit.h b/include/linux/audit.h index 961a417d641e..e38e3fc13ea8 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -26,7 +26,6 @@ #include #include #include -#include #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) @@ -348,23 +347,6 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk) return tsk->sessionid; } -static inline struct tty_struct *audit_get_tty(struct task_struct *tsk) -{ - struct tty_struct *tty = NULL; - unsigned long flags; - - spin_lock_irqsave(&tsk->sighand->siglock, flags); - if (tsk->signal) - tty = tty_kref_get(tsk->signal->tty); - spin_unlock_irqrestore(&tsk->sighand->siglock, flags); - return tty; -} - -static inline void audit_put_tty(struct tty_struct *tty) -{ - tty_kref_put(tty); -} - extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); @@ -522,12 +504,6 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return -1; } -static inline struct tty_struct *audit_get_tty(struct task_struct *tsk) -{ - return NULL; -} -static inline void audit_put_tty(struct tty_struct *tty) -{ } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index e6b41f42602b..3db25df396cb 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -159,6 +159,7 @@ struct bcma_host_ops { #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 +#define BCMA_CORE_SIZE 0x1000 /* Chip IDs of PCIe devices */ #define BCMA_CHIP_ID_BCM4313 0x4313 diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8ee27b8afe81..0de4de6dd43e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -111,6 +111,31 @@ enum bpf_access_type { BPF_WRITE = 2 }; +/* types of values stored in eBPF registers */ +enum bpf_reg_type { + NOT_INIT = 0, /* nothing was written into register */ + UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + PTR_TO_CTX, /* reg points to bpf_context */ + CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ + PTR_TO_MAP_VALUE, /* reg points to map element value */ + PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + FRAME_PTR, /* reg == frame_pointer */ + PTR_TO_STACK, /* reg == frame_pointer + imm */ + CONST_IMM, /* constant integer value */ + + /* PTR_TO_PACKET represents: + * skb->data + * skb->data + imm + * skb->data + (u16) var + * skb->data + (u16) var + imm + * if (range > 0) then [ptr, ptr + range - off) is safe to access + * if (id > 0) means that some 'var' was added + * if (off > 0) menas that 'imm' was added + */ + PTR_TO_PACKET, + PTR_TO_PACKET_END, /* skb->data + headlen */ +}; + struct bpf_prog; struct bpf_verifier_ops { @@ -120,7 +145,8 @@ struct bpf_verifier_ops { /* return true if 'size' wide access at offset 'off' within bpf_context * with 'type' (read or write) is allowed */ - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); + bool (*is_valid_access)(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type); u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, @@ -238,6 +264,10 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd) static inline void bpf_prog_put(struct bpf_prog *prog) { } + +static inline void bpf_prog_put_rcu(struct bpf_prog *prog) +{ +} #endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 484c8792da82..f53fa055021a 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -212,6 +212,7 @@ struct dentry_operations { #define DCACHE_OP_REAL 0x08000000 #define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */ +#define DCACHE_DENTRY_CURSOR 0x20000000 extern seqlock_t rename_lock; @@ -575,5 +576,17 @@ static inline struct inode *vfs_select_inode(struct dentry *dentry, return inode; } +/** + * d_real_inode - Return the real inode + * @dentry: The dentry to query + * + * If dentry is on an union/overlay, then return the underlying, real inode. + * Otherwise return d_inode(). + */ +static inline struct inode *d_real_inode(struct dentry *dentry) +{ + return d_backing_inode(d_real(dentry)); +} + #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 6fc31ef1da2d..8f74f3d61894 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -467,7 +467,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) } #endif /* CONFIG_DEBUG_SET_MODULE_RONX */ -int sk_filter(struct sock *sk, struct sk_buff *skb); +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); +static inline int sk_filter(struct sock *sk, struct sk_buff *skb) +{ + return sk_filter_trim_cap(sk, skb, 1); +} struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 419fb9e03447..f0a7a0320300 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -94,7 +94,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze); + unsigned long address, bool freeze, struct page *page); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -102,7 +102,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ - false); \ + false, NULL); \ } while (0) diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index d029ffac0d69..99403b19092f 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -223,6 +223,8 @@ struct st_sensor_settings { * @get_irq_data_ready: Function to get the IRQ used for data ready signal. * @tf: Transfer function structure used by I/O operations. * @tb: Transfer buffers and mutex used by I/O operations. + * @hw_irq_trigger: if we're using the hardware interrupt on the sensor. + * @hw_timestamp: Latest timestamp from the interrupt handler, when in use. */ struct st_sensor_data { struct device *dev; @@ -247,6 +249,9 @@ struct st_sensor_data { const struct st_sensor_transfer_function *tf; struct st_sensor_transfer_buffer tb; + + bool hw_irq_trigger; + s64 hw_timestamp; }; #ifdef CONFIG_IIO_BUFFER @@ -260,7 +265,8 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, const struct iio_trigger_ops *trigger_ops); void st_sensors_deallocate_trigger(struct iio_dev *indio_dev); - +int st_sensors_validate_device(struct iio_trigger *trig, + struct iio_dev *indio_dev); #else static inline int st_sensors_allocate_trigger(struct iio_dev *indio_dev, const struct iio_trigger_ops *trigger_ops) @@ -271,6 +277,7 @@ static inline void st_sensors_deallocate_trigger(struct iio_dev *indio_dev) { return; } +#define st_sensors_validate_device NULL #endif int st_sensors_init_sensor(struct iio_dev *indio_dev, diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 7c27fa1030e8..feb04ea20f11 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -52,6 +52,12 @@ struct sock *inet_diag_find_one_icsk(struct net *net, int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); +void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk); + +int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, + struct inet_diag_msg *r, int ext, + struct user_namespace *user_ns); + extern int inet_diag_register(const struct inet_diag_handler *handler); extern void inet_diag_unregister(const struct inet_diag_handler *handler); #endif /* _INET_DIAG_H_ */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index f2cb8d45513d..f8834f820ec2 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -190,7 +190,7 @@ extern struct task_group root_task_group; #define INIT_TASK(tsk) \ { \ .state = 0, \ - .stack = &init_thread_info, \ + .stack = init_stack, \ .usage = ATOMIC_INIT(2), \ .flags = PF_KTHREAD, \ .prio = MAX_PRIO-20, \ diff --git a/include/linux/isa.h b/include/linux/isa.h index 5ab85281230b..f2d0258414cf 100644 --- a/include/linux/isa.h +++ b/include/linux/isa.h @@ -6,6 +6,7 @@ #define __LINUX_ISA_H #include +#include #include struct isa_driver { @@ -22,13 +23,13 @@ struct isa_driver { #define to_isa_driver(x) container_of((x), struct isa_driver, driver) -#ifdef CONFIG_ISA +#ifdef CONFIG_ISA_BUS_API int isa_register_driver(struct isa_driver *, unsigned int); void isa_unregister_driver(struct isa_driver *); #else static inline int isa_register_driver(struct isa_driver *d, unsigned int i) { - return 0; + return -ENODEV; } static inline void isa_unregister_driver(struct isa_driver *d) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 0536524bb9eb..68904469fba1 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -117,13 +117,18 @@ struct module; #include +#ifdef HAVE_JUMP_LABEL + static inline int static_key_count(struct static_key *key) { - return atomic_read(&key->enabled); + /* + * -1 means the first static_key_slow_inc() is in progress. + * static_key_enabled() must return true, so return 1 here. + */ + int n = atomic_read(&key->enabled); + return n >= 0 ? n : 1; } -#ifdef HAVE_JUMP_LABEL - #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_MASK 1UL @@ -162,6 +167,11 @@ extern void jump_label_apply_nops(struct module *mod); #else /* !HAVE_JUMP_LABEL */ +static inline int static_key_count(struct static_key *key) +{ + return atomic_read(&key->enabled); +} + static __always_inline void jump_label_init(void) { static_key_initialized = true; diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 611927f5870d..ac4b3c46a84d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -59,14 +59,13 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object); void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); void kasan_kfree_large(const void *ptr); -void kasan_kfree(void *ptr); +void kasan_poison_kfree(void *ptr); void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags); void kasan_krealloc(const void *object, size_t new_size, gfp_t flags); void kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); bool kasan_slab_free(struct kmem_cache *s, void *object); -void kasan_poison_slab_free(struct kmem_cache *s, void *object); struct kasan_cache { int alloc_meta_offset; @@ -76,6 +75,9 @@ struct kasan_cache { int kasan_module_alloc(void *addr, size_t size); void kasan_free_shadow(const struct vm_struct *vm); +size_t ksize(const void *); +static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); } + #else /* CONFIG_KASAN */ static inline void kasan_unpoison_shadow(const void *address, size_t size) {} @@ -102,7 +104,7 @@ static inline void kasan_poison_object_data(struct kmem_cache *cache, static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {} static inline void kasan_kfree_large(const void *ptr) {} -static inline void kasan_kfree(void *ptr) {} +static inline void kasan_poison_kfree(void *ptr) {} static inline void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags) {} static inline void kasan_krealloc(const void *object, size_t new_size, @@ -114,11 +116,12 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object) { return false; } -static inline void kasan_poison_slab_free(struct kmem_cache *s, void *object) {} static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } static inline void kasan_free_shadow(const struct vm_struct *vm) {} +static inline void kasan_unpoison_slab(const void *ptr) { } + #endif /* CONFIG_KASAN */ #endif /* LINUX_KASAN_H */ diff --git a/include/linux/leds.h b/include/linux/leds.h index d2b13066e781..e5e7f2e80a54 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -42,15 +42,16 @@ struct led_classdev { #define LED_UNREGISTERING (1 << 1) /* Upper 16 bits reflect control information */ #define LED_CORE_SUSPENDRESUME (1 << 16) -#define LED_BLINK_ONESHOT (1 << 17) -#define LED_BLINK_ONESHOT_STOP (1 << 18) -#define LED_BLINK_INVERT (1 << 19) -#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 20) -#define LED_BLINK_DISABLE (1 << 21) -#define LED_SYSFS_DISABLE (1 << 22) -#define LED_DEV_CAP_FLASH (1 << 23) -#define LED_HW_PLUGGABLE (1 << 24) -#define LED_PANIC_INDICATOR (1 << 25) +#define LED_BLINK_SW (1 << 17) +#define LED_BLINK_ONESHOT (1 << 18) +#define LED_BLINK_ONESHOT_STOP (1 << 19) +#define LED_BLINK_INVERT (1 << 20) +#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 21) +#define LED_BLINK_DISABLE (1 << 22) +#define LED_SYSFS_DISABLE (1 << 23) +#define LED_DEV_CAP_FLASH (1 << 24) +#define LED_HW_PLUGGABLE (1 << 25) +#define LED_PANIC_INDICATOR (1 << 26) /* Set LED brightness level * Must not sleep. Use brightness_set_blocking for drivers @@ -72,8 +73,8 @@ struct led_classdev { * and if both are zero then a sensible default should be chosen. * The call should adjust the timings in that case and if it can't * match the values specified exactly. - * Deactivate blinking again when the brightness is set to a fixed - * value via the brightness_set() callback. + * Deactivate blinking again when the brightness is set to LED_OFF + * via the brightness_set() callback. */ int (*blink_set)(struct led_classdev *led_cdev, unsigned long *delay_on, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a805474df4ab..56e6069d2452 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -97,6 +97,11 @@ enum mem_cgroup_events_target { #define MEM_CGROUP_ID_SHIFT 16 #define MEM_CGROUP_ID_MAX USHRT_MAX +struct mem_cgroup_id { + int id; + atomic_t ref; +}; + struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; unsigned long events[MEMCG_NR_EVENTS]; @@ -172,6 +177,9 @@ enum memcg_kmem_state { struct mem_cgroup { struct cgroup_subsys_state css; + /* Private memcg ID. Used to ID objects that outlive the cgroup */ + struct mem_cgroup_id id; + /* Accounted resources */ struct page_counter memory; struct page_counter swap; @@ -330,22 +338,9 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) if (mem_cgroup_disabled()) return 0; - return memcg->css.id; -} - -/** - * mem_cgroup_from_id - look up a memcg from an id - * @id: the id to look up - * - * Caller must hold rcu_read_lock() and use css_tryget() as necessary. - */ -static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) -{ - struct cgroup_subsys_state *css; - - css = css_from_id(id, &memory_cgrp_subsys); - return mem_cgroup_from_css(css); + return memcg->id.id; } +struct mem_cgroup *mem_cgroup_from_id(unsigned short id); /** * parent_mem_cgroup - find the accounting parent of a memcg diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h index c18a4c19d6fc..ce9230af09c2 100644 --- a/include/linux/mfd/da9052/da9052.h +++ b/include/linux/mfd/da9052/da9052.h @@ -171,7 +171,7 @@ static inline int da9052_group_read(struct da9052 *da9052, unsigned char reg, static inline int da9052_group_write(struct da9052 *da9052, unsigned char reg, unsigned reg_cnt, unsigned char *val) { - int ret; + int ret = 0; int i; for (i = 0; i < reg_cnt; i++) { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 80dec87a94f8..d46a0e7f144d 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -466,6 +466,7 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, + MLX4_INTERFACE_STATE_SHUTDOWN = 1 << 2, }; #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80776d0c52dc..fd72ecf0ce9f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -629,6 +629,7 @@ struct mlx5_cmd_work_ent { void *uout; int uout_size; mlx5_cmd_cbk_t callback; + struct delayed_work cb_timeout_work; void *context; int idx; struct completion done; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 266320feb160..ab310819ac36 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -172,6 +172,7 @@ enum { enum { MLX5_FENCE_MODE_NONE = 0 << 5, MLX5_FENCE_MODE_INITIATOR_SMALL = 1 << 5, + MLX5_FENCE_MODE_FENCE = 2 << 5, MLX5_FENCE_MODE_STRONG_ORDERING = 3 << 5, MLX5_FENCE_MODE_SMALL_AND_FENCE = 4 << 5, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 5df5feb49575..ece042dfe23c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -602,7 +602,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) } void do_set_pte(struct vm_area_struct *vma, unsigned long address, - struct page *page, pte_t *pte, bool write, bool anon, bool old); + struct page *page, pte_t *pte, bool write, bool anon); #endif /* diff --git a/include/linux/net.h b/include/linux/net.h index 9aa49a05fe38..25aa03b51c4e 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -251,7 +251,8 @@ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ net_ratelimit()) \ - __dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__); \ + __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ + ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f45929ce8157..da4b33bea982 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4145,6 +4145,13 @@ static inline void netif_keep_dst(struct net_device *dev) dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); } +/* return true if dev can't cope with mtu frames that need vlan tag insertion */ +static inline bool netif_reduces_vlan_mtu(struct net_device *dev) +{ + /* TODO: reserve and use an additional IFF bit, if we get more users */ + return dev->priv_flags & IFF_MACSEC; +} + extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h index 308d6044f153..09779b0ae720 100644 --- a/include/linux/pm_clock.h +++ b/include/linux/pm_clock.h @@ -42,6 +42,7 @@ extern int pm_clk_create(struct device *dev); extern void pm_clk_destroy(struct device *dev); extern int pm_clk_add(struct device *dev, const char *con_id); extern int pm_clk_add_clk(struct device *dev, struct clk *clk); +extern int of_pm_clk_add_clk(struct device *dev, const char *name); extern int of_pm_clk_add_clks(struct device *dev); extern void pm_clk_remove(struct device *dev, const char *con_id); extern void pm_clk_remove_clk(struct device *dev, struct clk *clk); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 39285c7bd3f5..31fec858088c 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -57,7 +57,6 @@ struct generic_pm_domain { unsigned int device_count; /* Number of devices */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ - bool suspend_power_off; /* Power status before system suspend */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); struct gpd_dev_ops dev_ops; @@ -128,8 +127,8 @@ extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *target); -extern void pm_genpd_init(struct generic_pm_domain *genpd, - struct dev_power_governor *gov, bool is_off); +extern int pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -164,9 +163,10 @@ static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline void pm_genpd_init(struct generic_pm_domain *genpd, - struct dev_power_governor *gov, bool is_off) +static inline int pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off) { + return -ENOSYS; } #endif diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 5b5a80cc5926..c818772d9f9d 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -43,10 +43,8 @@ struct posix_acl_entry { }; struct posix_acl { - union { - atomic_t a_refcount; - struct rcu_head a_rcu; - }; + atomic_t a_refcount; + struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[0]; }; diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 17018f3c066e..c038ae36b10e 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -235,6 +235,9 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns, if (!pwm) return -EINVAL; + if (duty_ns < 0 || period_ns < 0) + return -EINVAL; + pwm_get_state(pwm, &state); if (state.duty_cycle == duty_ns && state.period == period_ns) return 0; @@ -461,6 +464,8 @@ static inline bool pwm_can_sleep(struct pwm_device *pwm) static inline void pwm_apply_args(struct pwm_device *pwm) { + struct pwm_state state = { }; + /* * PWM users calling pwm_apply_args() expect to have a fresh config * where the polarity and period are set according to pwm_args info. @@ -473,18 +478,20 @@ static inline void pwm_apply_args(struct pwm_device *pwm) * at startup (even if they are actually enabled), thus authorizing * polarity setting. * - * Instead of setting ->enabled to false, we call pwm_disable() - * before pwm_set_polarity() to ensure that everything is configured - * as expected, and the PWM is really disabled when the user request - * it. + * To fulfill this requirement, we apply a new state which disables + * the PWM device and set the reference period and polarity config. * * Note that PWM users requiring a smooth handover between the * bootloader and the kernel (like critical regulators controlled by * PWM devices) will have to switch to the atomic API and avoid calling * pwm_apply_args(). */ - pwm_disable(pwm); - pwm_set_polarity(pwm, pwm->args.polarity); + + state.enabled = false; + state.polarity = pwm->args.polarity; + state.period = pwm->args.period; + + pwm_apply_state(pwm, &state); } struct pwm_lookup { diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 6ae8cb4a61d3..6c876a63558d 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -49,6 +49,7 @@ struct qed_start_vport_params { bool drop_ttl0; u8 vport_id; u16 mtu; + bool clear_stats; }; struct qed_stop_rxq_params { diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index cb4b7e8cee81..eca6f626c16e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -407,6 +407,7 @@ static inline __must_check void **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; + iter->tags = 0; return NULL; } diff --git a/include/linux/reset.h b/include/linux/reset.h index ec0306ce7b92..45a4abeb6acb 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -84,8 +84,8 @@ static inline struct reset_control *__devm_reset_control_get( #endif /* CONFIG_RESET_CONTROLLER */ /** - * reset_control_get - Lookup and obtain an exclusive reference to a - * reset controller. + * reset_control_get_exclusive - Lookup and obtain an exclusive reference + * to a reset controller. * @dev: device to be reset by the controller * @id: reset line name * @@ -98,8 +98,8 @@ static inline struct reset_control *__devm_reset_control_get( * * Use of id names is optional. */ -static inline struct reset_control *__must_check reset_control_get( - struct device *dev, const char *id) +static inline struct reset_control * +__must_check reset_control_get_exclusive(struct device *dev, const char *id) { #ifndef CONFIG_RESET_CONTROLLER WARN_ON(1); @@ -107,12 +107,6 @@ static inline struct reset_control *__must_check reset_control_get( return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0); } -static inline struct reset_control *reset_control_get_optional( - struct device *dev, const char *id) -{ - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0); -} - /** * reset_control_get_shared - Lookup and obtain a shared reference to a * reset controller. @@ -141,9 +135,21 @@ static inline struct reset_control *reset_control_get_shared( return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 1); } +static inline struct reset_control *reset_control_get_optional_exclusive( + struct device *dev, const char *id) +{ + return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0); +} + +static inline struct reset_control *reset_control_get_optional_shared( + struct device *dev, const char *id) +{ + return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 1); +} + /** - * of_reset_control_get - Lookup and obtain an exclusive reference to a - * reset controller. + * of_reset_control_get_exclusive - Lookup and obtain an exclusive reference + * to a reset controller. * @node: device to be reset by the controller * @id: reset line name * @@ -151,15 +157,41 @@ static inline struct reset_control *reset_control_get_shared( * * Use of id names is optional. */ -static inline struct reset_control *of_reset_control_get( +static inline struct reset_control *of_reset_control_get_exclusive( struct device_node *node, const char *id) { return __of_reset_control_get(node, id, 0, 0); } /** - * of_reset_control_get_by_index - Lookup and obtain an exclusive reference to - * a reset controller by index. + * of_reset_control_get_shared - Lookup and obtain an shared reference + * to a reset controller. + * @node: device to be reset by the controller + * @id: reset line name + * + * When a reset-control is shared, the behavior of reset_control_assert / + * deassert is changed, the reset-core will keep track of a deassert_count + * and only (re-)assert the reset after reset_control_assert has been called + * as many times as reset_control_deassert was called. Also see the remark + * about shared reset-controls in the reset_control_assert docs. + * + * Calling reset_control_assert without first calling reset_control_deassert + * is not allowed on a shared reset control. Calling reset_control_reset is + * also not allowed on a shared reset control. + * Returns a struct reset_control or IS_ERR() condition containing errno. + * + * Use of id names is optional. + */ +static inline struct reset_control *of_reset_control_get_shared( + struct device_node *node, const char *id) +{ + return __of_reset_control_get(node, id, 0, 1); +} + +/** + * of_reset_control_get_exclusive_by_index - Lookup and obtain an exclusive + * reference to a reset controller + * by index. * @node: device to be reset by the controller * @index: index of the reset controller * @@ -167,49 +199,60 @@ static inline struct reset_control *of_reset_control_get( * in whatever order. Returns a struct reset_control or IS_ERR() condition * containing errno. */ -static inline struct reset_control *of_reset_control_get_by_index( +static inline struct reset_control *of_reset_control_get_exclusive_by_index( struct device_node *node, int index) { return __of_reset_control_get(node, NULL, index, 0); } /** - * devm_reset_control_get - resource managed reset_control_get() - * @dev: device to be reset by the controller - * @id: reset line name + * of_reset_control_get_shared_by_index - Lookup and obtain an shared + * reference to a reset controller + * by index. + * @node: device to be reset by the controller + * @index: index of the reset controller + * + * When a reset-control is shared, the behavior of reset_control_assert / + * deassert is changed, the reset-core will keep track of a deassert_count + * and only (re-)assert the reset after reset_control_assert has been called + * as many times as reset_control_deassert was called. Also see the remark + * about shared reset-controls in the reset_control_assert docs. + * + * Calling reset_control_assert without first calling reset_control_deassert + * is not allowed on a shared reset control. Calling reset_control_reset is + * also not allowed on a shared reset control. + * Returns a struct reset_control or IS_ERR() condition containing errno. * - * Managed reset_control_get(). For reset controllers returned from this - * function, reset_control_put() is called automatically on driver detach. - * See reset_control_get() for more information. + * This is to be used to perform a list of resets for a device or power domain + * in whatever order. Returns a struct reset_control or IS_ERR() condition + * containing errno. */ -static inline struct reset_control *__must_check devm_reset_control_get( - struct device *dev, const char *id) -{ -#ifndef CONFIG_RESET_CONTROLLER - WARN_ON(1); -#endif - return __devm_reset_control_get(dev, id, 0, 0); -} - -static inline struct reset_control *devm_reset_control_get_optional( - struct device *dev, const char *id) +static inline struct reset_control *of_reset_control_get_shared_by_index( + struct device_node *node, int index) { - return __devm_reset_control_get(dev, id, 0, 0); + return __of_reset_control_get(node, NULL, index, 1); } /** - * devm_reset_control_get_by_index - resource managed reset_control_get + * devm_reset_control_get_exclusive - resource managed + * reset_control_get_exclusive() * @dev: device to be reset by the controller - * @index: index of the reset controller + * @id: reset line name * - * Managed reset_control_get(). For reset controllers returned from this - * function, reset_control_put() is called automatically on driver detach. - * See reset_control_get() for more information. + * Managed reset_control_get_exclusive(). For reset controllers returned + * from this function, reset_control_put() is called automatically on driver + * detach. + * + * See reset_control_get_exclusive() for more information. */ -static inline struct reset_control *devm_reset_control_get_by_index( - struct device *dev, int index) +static inline struct reset_control * +__must_check devm_reset_control_get_exclusive(struct device *dev, + const char *id) { - return __devm_reset_control_get(dev, NULL, index, 0); +#ifndef CONFIG_RESET_CONTROLLER + WARN_ON(1); +#endif + return __devm_reset_control_get(dev, id, 0, 0); } /** @@ -227,6 +270,36 @@ static inline struct reset_control *devm_reset_control_get_shared( return __devm_reset_control_get(dev, id, 0, 1); } +static inline struct reset_control *devm_reset_control_get_optional_exclusive( + struct device *dev, const char *id) +{ + return __devm_reset_control_get(dev, id, 0, 0); +} + +static inline struct reset_control *devm_reset_control_get_optional_shared( + struct device *dev, const char *id) +{ + return __devm_reset_control_get(dev, id, 0, 1); +} + +/** + * devm_reset_control_get_exclusive_by_index - resource managed + * reset_control_get_exclusive() + * @dev: device to be reset by the controller + * @index: index of the reset controller + * + * Managed reset_control_get_exclusive(). For reset controllers returned from + * this function, reset_control_put() is called automatically on driver + * detach. + * + * See reset_control_get_exclusive() for more information. + */ +static inline struct reset_control * +devm_reset_control_get_exclusive_by_index(struct device *dev, int index) +{ + return __devm_reset_control_get(dev, NULL, index, 0); +} + /** * devm_reset_control_get_shared_by_index - resource managed * reset_control_get_shared @@ -237,10 +310,60 @@ static inline struct reset_control *devm_reset_control_get_shared( * this function, reset_control_put() is called automatically on driver detach. * See reset_control_get_shared() for more information. */ -static inline struct reset_control *devm_reset_control_get_shared_by_index( - struct device *dev, int index) +static inline struct reset_control * +devm_reset_control_get_shared_by_index(struct device *dev, int index) { return __devm_reset_control_get(dev, NULL, index, 1); } +/* + * TEMPORARY calls to use during transition: + * + * of_reset_control_get() => of_reset_control_get_exclusive() + * + * These inline function calls will be removed once all consumers + * have been moved over to the new explicit API. + */ +static inline struct reset_control *reset_control_get( + struct device *dev, const char *id) +{ + return reset_control_get_exclusive(dev, id); +} + +static inline struct reset_control *reset_control_get_optional( + struct device *dev, const char *id) +{ + return reset_control_get_optional_exclusive(dev, id); +} + +static inline struct reset_control *of_reset_control_get( + struct device_node *node, const char *id) +{ + return of_reset_control_get_exclusive(node, id); +} + +static inline struct reset_control *of_reset_control_get_by_index( + struct device_node *node, int index) +{ + return of_reset_control_get_exclusive_by_index(node, index); +} + +static inline struct reset_control *devm_reset_control_get( + struct device *dev, const char *id) +{ + return devm_reset_control_get_exclusive(dev, id); +} + +static inline struct reset_control *devm_reset_control_get_optional( + struct device *dev, const char *id) +{ + return devm_reset_control_get_optional_exclusive(dev, id); + +} + +static inline struct reset_control *devm_reset_control_get_by_index( + struct device *dev, int index) +{ + return devm_reset_control_get_exclusive_by_index(dev, index); +} #endif diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 49eb4f8ebac9..2b0fad83683f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -158,7 +158,7 @@ struct anon_vma *page_get_anon_vma(struct page *page); /* * rmap interfaces called when adding or removing pte of page */ -void page_move_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, diff --git a/include/linux/sched.h b/include/linux/sched.h index 6e42ada26345..253538f29ade 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3007,7 +3007,7 @@ static inline int object_is_on_stack(void *obj) return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } -extern void thread_info_cache_init(void); +extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE static inline unsigned long stack_not_used(struct task_struct *p) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ee38a4127475..f39b37180c41 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1062,6 +1062,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) } void __skb_get_hash(struct sk_buff *skb); +u32 __skb_get_hash_symmetric(struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen); @@ -2869,6 +2870,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb, skb->csum = csum_partial(start, len, skb->csum); } +/** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static inline unsigned char *skb_push_rcsum(struct sk_buff *skb, + unsigned int len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 4018b48f2b3b..a0596ca0e80a 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -36,6 +36,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) { switch (sk->sk_family) { case AF_INET: + if (sk->sk_type == SOCK_RAW) + return SKNLGRP_NONE; + switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET_TCP_DESTROY; @@ -45,6 +48,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) return SKNLGRP_NONE; } case AF_INET6: + if (sk->sk_type == SOCK_RAW) + return SKNLGRP_NONE; + switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET6_TCP_DESTROY; diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 19c659d1c0f8..b6810c92b8bb 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -137,8 +137,6 @@ struct rpc_create_args { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) struct rpc_clnt *rpc_create(struct rpc_create_args *args); -struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, - struct rpc_xprt *xprt); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, const struct rpc_program *, u32); struct rpc_clnt *rpc_clone_client(struct rpc_clnt *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index b7dabc4baafd..79ba50856707 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -84,6 +84,7 @@ struct svc_xprt { struct net *xpt_net; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ + struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ }; static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5aa3834619a8..5e3e1b63dbb3 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -297,6 +297,7 @@ struct xprt_create { size_t addrlen; const char *servername; struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ + struct rpc_xprt_switch *bc_xps; unsigned int flags; }; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8b6ec7ef0854..7693e39b14fe 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -18,12 +18,11 @@ static inline void pm_set_vt_switch(int do_switch) #endif #ifdef CONFIG_VT_CONSOLE_SLEEP -extern int pm_prepare_console(void); +extern void pm_prepare_console(void); extern void pm_restore_console(void); #else -static inline int pm_prepare_console(void) +static inline void pm_prepare_console(void) { - return 0; } static inline void pm_restore_console(void) diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h index 966889a20ea3..e479033bd782 100644 --- a/include/linux/usb/ehci_def.h +++ b/include/linux/usb/ehci_def.h @@ -180,11 +180,11 @@ struct ehci_regs { * PORTSCx */ /* HOSTPC: offset 0x84 */ - u32 hostpc[1]; /* HOSTPC extension */ + u32 hostpc[0]; /* HOSTPC extension */ #define HOSTPC_PHCD (1<<22) /* Phy clock disable */ #define HOSTPC_PSPD (3<<25) /* Port speed detection */ - u32 reserved5[16]; + u32 reserved5[17]; /* USBMODE_EX: offset 0xc8 */ u32 usbmode_ex; /* USB Device mode extension */ diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 457651bf45b0..fefe8b06a63d 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -1034,6 +1034,8 @@ static inline int usb_gadget_activate(struct usb_gadget *gadget) * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL, * this driver will be bound to any available UDC. * @pending: UDC core private data used for deferred probe of this driver. + * @match_existing_only: If udc is not found, return an error and don't add this + * gadget driver to list of pending driver * * Devices are disabled till a gadget driver successfully bind()s, which * means the driver will handle setup() requests needed to enumerate (and @@ -1097,6 +1099,7 @@ struct usb_gadget_driver { char *udc_name; struct list_head pending; + unsigned match_existing_only:1; }; diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index 0b3da40a525e..d315c8907869 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -142,10 +142,11 @@ enum musb_vbus_id_status { }; #if IS_ENABLED(CONFIG_USB_MUSB_HDRC) -void musb_mailbox(enum musb_vbus_id_status status); +int musb_mailbox(enum musb_vbus_id_status status); #else -static inline void musb_mailbox(enum musb_vbus_id_status status) +static inline int musb_mailbox(enum musb_vbus_id_status status) { + return 0; } #endif diff --git a/include/media/v4l2-mc.h b/include/media/v4l2-mc.h index 98a938aabdfb..7a8d6037a4bb 100644 --- a/include/media/v4l2-mc.h +++ b/include/media/v4l2-mc.h @@ -1,7 +1,7 @@ /* * v4l2-mc.h - Media Controller V4L2 types and prototypes * - * Copyright (C) 2016 Mauro Carvalho Chehab + * Copyright (C) 2016 Mauro Carvalho Chehab * Copyright (C) 2006-2010 Nokia Corporation * Copyright (c) 2016 Intel Corporation. * diff --git a/include/net/bonding.h b/include/net/bonding.h index 791800ddd6d9..6360c259da6d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -34,6 +34,9 @@ #define BOND_DEFAULT_MIIMON 100 +#ifndef __long_aligned +#define __long_aligned __attribute__((aligned((sizeof(long))))) +#endif /* * Less bad way to call ioctl from within the kernel; this needs to be * done some other way to get the call out of interrupt context. @@ -138,7 +141,9 @@ struct bond_params { struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; - u8 ad_actor_system[ETH_ALEN]; + + /* 2 bytes of padding : see ether_addr_equal_64bits() */ + u8 ad_actor_system[ETH_ALEN + 2]; }; struct bond_parm_tbl { diff --git a/include/net/gre.h b/include/net/gre.h index 5dce30a6abe3..7a54a31d1d4c 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -26,7 +26,7 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version); struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type); int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, - bool *csum_err, __be16 proto); + bool *csum_err, __be16 proto, int nhs); static inline int gre_calc_hlen(__be16 o_flags) { diff --git a/include/net/ip.h b/include/net/ip.h index 37165fba3741..08f36cd2b874 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -313,10 +313,9 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, return min(dst->dev->mtu, IP_MAX_MTU); } -static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) +static inline unsigned int ip_skb_dst_mtu(struct sock *sk, + const struct sk_buff *skb) { - struct sock *sk = skb->sk; - if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index dd78bea227c8..b6083c34ef0d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -284,6 +284,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK; } +/* jiffies until ct expires, 0 if already expired */ +static inline unsigned long nf_ct_expires(const struct nf_conn *ct) +{ + long timeout = (long)ct->timeout.expires - (long)jiffies; + + return timeout > 0 ? timeout : 0; +} + struct kernel_param; int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 092235458691..f7c291ff4074 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -167,6 +167,7 @@ struct nft_set_elem { struct nft_set; struct nft_set_iter { + u8 genmask; unsigned int count; unsigned int skip; int err; diff --git a/include/net/sock.h b/include/net/sock.h index 649d2a8c17fc..ff5be7e8ddea 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1576,7 +1576,13 @@ static inline void sock_put(struct sock *sk) */ void sock_gen_put(struct sock *sk); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested); +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, + unsigned int trim_cap); +static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested) +{ + return __sk_receive_skb(sk, skb, nested, 1); +} static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 985619a59323..1d8e158241da 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -60,7 +60,7 @@ struct switchdev_attr { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ - u32 ageing_time; /* BRIDGE_AGEING_TIME */ + clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ } u; }; diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index dc9a09aefb33..c55facd17b7e 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -36,7 +36,7 @@ struct tcf_meta_ops { int (*encode)(struct sk_buff *, void *, struct tcf_meta_info *); int (*decode)(struct sk_buff *, void *, u16 len); int (*get)(struct sk_buff *skb, struct tcf_meta_info *mi); - int (*alloc)(struct tcf_meta_info *, void *); + int (*alloc)(struct tcf_meta_info *, void *, gfp_t); void (*release)(struct tcf_meta_info *); int (*validate)(void *val, int len); struct module *owner; @@ -48,8 +48,8 @@ int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi); int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi); int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval); -int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval); -int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval); +int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp); +int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp); int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi); int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi); int ife_validate_meta_u32(void *val, int len); diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index 16274e2133cd..9c9a27d42aaa 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -203,7 +203,9 @@ struct rvt_driver_provided { /* * Allocate a private queue pair data structure for driver specific - * information which is opaque to rdmavt. + * information which is opaque to rdmavt. Errors are returned via + * ERR_PTR(err). The driver is free to return NULL or a valid + * pointer. */ void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp); diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 8bdae34d1f9a..ec10cfef166a 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -245,6 +245,7 @@ endif header-y += hw_breakpoint.h header-y += l2tp.h header-y += libc-compat.h +header-y += lirc.h header-y += limits.h header-y += llc.h header-y += loop.h diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 5974fae54e12..27e17363263a 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -105,6 +105,9 @@ * * 7.24 * - add FUSE_LSEEK for SEEK_HOLE and SEEK_DATA support + * + * 7.25 + * - add FUSE_PARALLEL_DIROPS */ #ifndef _LINUX_FUSE_H @@ -140,7 +143,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 24 +#define FUSE_KERNEL_MINOR_VERSION 25 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -234,6 +237,7 @@ struct fuse_file_lock { * FUSE_ASYNC_DIO: asynchronous direct I/O submission * FUSE_WRITEBACK_CACHE: use writeback cache for buffered writes * FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens + * FUSE_PARALLEL_DIROPS: allow parallel lookups and readdir */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -253,6 +257,7 @@ struct fuse_file_lock { #define FUSE_ASYNC_DIO (1 << 15) #define FUSE_WRITEBACK_CACHE (1 << 16) #define FUSE_NO_OPEN_SUPPORT (1 << 17) +#define FUSE_PARALLEL_DIROPS (1 << 18) /** * CUSE INIT request/reply flags diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 87cf351bab03..d6d071fc3c56 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -611,6 +611,37 @@ #define KEY_KBDINPUTASSIST_ACCEPT 0x264 #define KEY_KBDINPUTASSIST_CANCEL 0x265 +/* Diagonal movement keys */ +#define KEY_RIGHT_UP 0x266 +#define KEY_RIGHT_DOWN 0x267 +#define KEY_LEFT_UP 0x268 +#define KEY_LEFT_DOWN 0x269 + +#define KEY_ROOT_MENU 0x26a /* Show Device's Root Menu */ +/* Show Top Menu of the Media (e.g. DVD) */ +#define KEY_MEDIA_TOP_MENU 0x26b +#define KEY_NUMERIC_11 0x26c +#define KEY_NUMERIC_12 0x26d +/* + * Toggle Audio Description: refers to an audio service that helps blind and + * visually impaired consumers understand the action in a program. Note: in + * some countries this is referred to as "Video Description". + */ +#define KEY_AUDIO_DESC 0x26e +#define KEY_3D_MODE 0x26f +#define KEY_NEXT_FAVORITE 0x270 +#define KEY_STOP_RECORD 0x271 +#define KEY_PAUSE_RECORD 0x272 +#define KEY_VOD 0x273 /* Video on Demand */ +#define KEY_UNMUTE 0x274 +#define KEY_FASTREVERSE 0x275 +#define KEY_SLOWREVERSE 0x276 +/* + * Control a data application associated with the currently viewed channel, + * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.) + */ +#define KEY_DATA 0x275 + #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 #define BTN_TRIGGER_HAPPY2 0x2c1 @@ -749,6 +780,7 @@ #define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */ #define SW_LINEIN_INSERT 0x0d /* set = inserted */ #define SW_MUTE_DEVICE 0x0e /* set = device disabled */ +#define SW_PEN_INSERTED 0x0f /* set = pen inserted */ #define SW_MAX 0x0f #define SW_CNT (SW_MAX+1) diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index 01113841190d..c51494119817 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -247,6 +247,7 @@ struct input_mask { #define BUS_ATARI 0x1B #define BUS_SPI 0x1C #define BUS_RMI 0x1D +#define BUS_CEC 0x1E /* * MT_TOOL types diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild index 1d973d2ba417..cd26d7a0fd07 100644 --- a/include/uapi/linux/netfilter/Kbuild +++ b/include/uapi/linux/netfilter/Kbuild @@ -33,6 +33,7 @@ header-y += xt_NFLOG.h header-y += xt_NFQUEUE.h header-y += xt_RATEEST.h header-y += xt_SECMARK.h +header-y += xt_SYNPROXY.h header-y += xt_TCPMSS.h header-y += xt_TCPOPTSTRIP.h header-y += xt_TEE.h diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h index 2d59fbaa93c6..ca67e61d2a61 100644 --- a/include/uapi/linux/netfilter/xt_SYNPROXY.h +++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h @@ -1,6 +1,8 @@ #ifndef _XT_SYNPROXY_H #define _XT_SYNPROXY_H +#include + #define XT_SYNPROXY_OPT_MSS 0x01 #define XT_SYNPROXY_OPT_WSCALE 0x02 #define XT_SYNPROXY_OPT_SACK_PERM 0x04 diff --git a/init/Kconfig b/init/Kconfig index f755a602d4a1..c02d89777713 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1458,6 +1458,7 @@ config KALLSYMS_ALL config KALLSYMS_ABSOLUTE_PERCPU bool + depends on KALLSYMS default X86_64 && SMP config KALLSYMS_BASE_RELATIVE diff --git a/init/main.c b/init/main.c index 4c17fda5c2ff..eae02aa03c9e 100644 --- a/init/main.c +++ b/init/main.c @@ -453,7 +453,7 @@ void __init __weak smp_setup_processor_id(void) } # if THREAD_SIZE >= PAGE_SIZE -void __init __weak thread_info_cache_init(void) +void __init __weak thread_stack_cache_init(void) { } #endif @@ -627,7 +627,7 @@ asmlinkage __visible void __init start_kernel(void) /* Should be run before the first non-init thread is created */ init_espfix_bsp(); #endif - thread_info_cache_init(); + thread_stack_cache_init(); cred_init(); fork_init(); proc_caches_init(); @@ -708,11 +708,13 @@ static bool __init_or_module initcall_blacklisted(initcall_t fn) { struct blacklist_entry *entry; char fn_name[KSYM_SYMBOL_LEN]; + unsigned long addr; if (list_empty(&blacklisted_initcalls)) return false; - sprint_symbol_no_offset(fn_name, (unsigned long)fn); + addr = (unsigned long) dereference_function_descriptor(fn); + sprint_symbol_no_offset(fn_name, addr); list_for_each_entry(entry, &blacklisted_initcalls, next) { if (!strcmp(fn_name, entry->buf)) { diff --git a/kernel/audit.c b/kernel/audit.c index 22bb4f24f071..8d528f9930da 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1883,6 +1883,23 @@ out_null: audit_log_format(ab, " exe=(null)"); } +struct tty_struct *audit_get_tty(struct task_struct *tsk) +{ + struct tty_struct *tty = NULL; + unsigned long flags; + + spin_lock_irqsave(&tsk->sighand->siglock, flags); + if (tsk->signal) + tty = tty_kref_get(tsk->signal->tty); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); + return tty; +} + +void audit_put_tty(struct tty_struct *tty) +{ + tty_kref_put(tty); +} + void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) { const struct cred *cred; diff --git a/kernel/audit.h b/kernel/audit.h index cbbe6bb6496e..a492f4c4e710 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -23,6 +23,7 @@ #include #include #include +#include /* AUDIT_NAMES is the number of slots we reserve in the audit_context * for saving names from getname(). If we get more names we will allocate @@ -262,6 +263,9 @@ extern struct audit_entry *audit_dupe_rule(struct audit_krule *old); extern void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm); +extern struct tty_struct *audit_get_tty(struct task_struct *tsk); +extern void audit_put_tty(struct tty_struct *tty); + /* audit watch functions */ #ifdef CONFIG_AUDIT_WATCH extern void audit_put_watch(struct audit_watch *watch); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 62ab53d7619c..2672d105cffc 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -63,7 +63,6 @@ #include #include #include -#include #include #include #include @@ -1985,14 +1984,15 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, if (!audit_enabled) return; + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); + if (!ab) + return; + uid = from_kuid(&init_user_ns, task_uid(current)); oldloginuid = from_kuid(&init_user_ns, koldloginuid); loginuid = from_kuid(&init_user_ns, kloginuid), tty = audit_get_tty(current); - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); - if (!ab) - return; audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid); audit_log_task_context(ab); audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 668e07903c8f..eec9f90ba030 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -126,31 +126,6 @@ * are set to NOT_INIT to indicate that they are no longer readable. */ -/* types of values stored in eBPF registers */ -enum bpf_reg_type { - NOT_INIT = 0, /* nothing was written into register */ - UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ - PTR_TO_CTX, /* reg points to bpf_context */ - CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ - PTR_TO_MAP_VALUE, /* reg points to map element value */ - PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ - FRAME_PTR, /* reg == frame_pointer */ - PTR_TO_STACK, /* reg == frame_pointer + imm */ - CONST_IMM, /* constant integer value */ - - /* PTR_TO_PACKET represents: - * skb->data - * skb->data + imm - * skb->data + (u16) var - * skb->data + (u16) var + imm - * if (range > 0) then [ptr, ptr + range - off) is safe to access - * if (id > 0) means that some 'var' was added - * if (off > 0) menas that 'imm' was added - */ - PTR_TO_PACKET, - PTR_TO_PACKET_END, /* skb->data + headlen */ -}; - struct reg_state { enum bpf_reg_type type; union { @@ -695,10 +670,10 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields */ static int check_ctx_access(struct verifier_env *env, int off, int size, - enum bpf_access_type t) + enum bpf_access_type t, enum bpf_reg_type *reg_type) { if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t)) { + env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) { /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -798,21 +773,19 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, mark_reg_unknown_value(state->regs, value_regno); } else if (reg->type == PTR_TO_CTX) { + enum bpf_reg_type reg_type = UNKNOWN_VALUE; + if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose("R%d leaks addr into ctx\n", value_regno); return -EACCES; } - err = check_ctx_access(env, off, size, t); + err = check_ctx_access(env, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { mark_reg_unknown_value(state->regs, value_regno); - if (off == offsetof(struct __sk_buff, data) && - env->allow_ptr_leaks) + if (env->allow_ptr_leaks) /* note that reg.[id|off|range] == 0 */ - state->regs[value_regno].type = PTR_TO_PACKET; - else if (off == offsetof(struct __sk_buff, data_end) && - env->allow_ptr_leaks) - state->regs[value_regno].type = PTR_TO_PACKET_END; + state->regs[value_regno].type = reg_type; } } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 86cb5c6e8932..75c0ff00aca6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -837,6 +837,8 @@ static void put_css_set_locked(struct css_set *cset) static void put_css_set(struct css_set *cset) { + unsigned long flags; + /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an @@ -845,9 +847,9 @@ static void put_css_set(struct css_set *cset) if (atomic_add_unless(&cset->refcount, -1, 1)) return; - spin_lock_bh(&css_set_lock); + spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, flags); } /* @@ -1070,11 +1072,11 @@ static struct css_set *find_css_set(struct css_set *old_cset, /* First see if we already have a cgroup group that matches * the desired set */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (cset) return cset; @@ -1102,7 +1104,7 @@ static struct css_set *find_css_set(struct css_set *old_cset, * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; @@ -1128,7 +1130,7 @@ static struct css_set *find_css_set(struct css_set *old_cset, css_get(css); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return cset; } @@ -1192,7 +1194,7 @@ static void cgroup_destroy_root(struct cgroup_root *root) * Release all the links from cset_links to this hierarchy's * root cgroup */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); @@ -1200,7 +1202,7 @@ static void cgroup_destroy_root(struct cgroup_root *root) kfree(link); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (!list_empty(&root->root_list)) { list_del(&root->root_list); @@ -1600,11 +1602,11 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) ss->root = dst_root; css->cgroup = dcgrp; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; @@ -1640,10 +1642,10 @@ static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, if (!buf) return -ENOMEM; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (len >= PATH_MAX) len = -ERANGE; @@ -1897,7 +1899,7 @@ static void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); if (use_task_css_set_links) goto out_unlock; @@ -1922,8 +1924,12 @@ static void cgroup_enable_task_cg_lists(void) * entry won't be deleted though the process has exited. * Do it while holding siglock so that we don't end up * racing against cgroup_exit(). + * + * Interrupts were already disabled while acquiring + * the css_set_lock, so we do not need to disable it + * again when acquiring the sighand->siglock here. */ - spin_lock_irq(&p->sighand->siglock); + spin_lock(&p->sighand->siglock); if (!(p->flags & PF_EXITING)) { struct css_set *cset = task_css_set(p); @@ -1932,11 +1938,11 @@ static void cgroup_enable_task_cg_lists(void) list_add_tail(&p->cg_list, &cset->tasks); get_css_set(cset); } - spin_unlock_irq(&p->sighand->siglock); + spin_unlock(&p->sighand->siglock); } while_each_thread(g, p); read_unlock(&tasklist_lock); out_unlock: - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } static void init_cgroup_housekeeping(struct cgroup *cgrp) @@ -2043,13 +2049,13 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) * Link the root cgroup in this hierarchy into all the css_set * objects. */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); @@ -2256,11 +2262,11 @@ out_mount: struct cgroup *cgrp; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ns->root_cset, root); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb); @@ -2337,11 +2343,11 @@ char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, char *ret; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return ret; @@ -2369,7 +2375,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) char *path = NULL; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); @@ -2382,7 +2388,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) path = buf; } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return path; } @@ -2557,7 +2563,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, * the new cgroup. There are no failure cases after here, so this * is the commit point. */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); @@ -2568,7 +2574,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, put_css_set_locked(from_cset); } } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. @@ -2597,13 +2603,13 @@ out_cancel_attach: } } while_each_subsys_mask(); out_release_tset: - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return ret; } @@ -2634,7 +2640,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) lockdep_assert_held(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; @@ -2642,7 +2648,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) list_del_init(&cset->mg_preload_node); put_css_set_locked(cset); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } /** @@ -2783,7 +2789,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, * already PF_EXITING could be freed from underneath us unless we * take an rcu_read_lock. */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { @@ -2792,7 +2798,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, break; } while_each_thread(leader, task); rcu_read_unlock(); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return cgroup_taskset_migrate(&tset, root); } @@ -2816,7 +2822,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, return -EBUSY; /* look up all src csets */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { @@ -2826,7 +2832,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, break; } while_each_thread(leader, task); rcu_read_unlock(); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&preloaded_csets); @@ -2859,9 +2865,9 @@ static int cgroup_procs_write_permission(struct task_struct *task, struct cgroup *cgrp; struct inode *inode; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); while (!cgroup_is_descendant(dst_cgrp, cgrp)) cgrp = cgroup_parent(cgrp); @@ -2962,9 +2968,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) if (root == &cgrp_dfl_root) continue; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) @@ -3080,7 +3086,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) percpu_down_write(&cgroup_threadgroup_rwsem); /* look up all csses currently attached to @cgrp's subtree */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; @@ -3088,14 +3094,14 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) cgroup_migrate_add_src(link->cset, dsct, &preloaded_csets); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) goto out_finish; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) { struct task_struct *task, *ntask; @@ -3107,7 +3113,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_taskset_add(task, &tset); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); ret = cgroup_taskset_migrate(&tset, cgrp->root); out_finish: @@ -3908,10 +3914,10 @@ static int cgroup_task_count(const struct cgroup *cgrp) int count = 0; struct cgrp_cset_link *link; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += atomic_read(&link->cset->refcount); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return count; } @@ -4249,7 +4255,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, memset(it, 0, sizeof(*it)); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); it->ss = css->ss; @@ -4262,7 +4268,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, css_task_iter_advance_css_set(it); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } /** @@ -4280,7 +4286,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) it->cur_task = NULL; } - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, @@ -4289,7 +4295,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) css_task_iter_advance(it); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return it->cur_task; } @@ -4303,10 +4309,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) void css_task_iter_end(struct css_task_iter *it) { if (it->cur_cset) { - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } if (it->cur_task) @@ -4338,10 +4344,10 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) mutex_lock(&cgroup_mutex); /* all tasks in @from are being moved, all csets are source */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &preloaded_csets); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) @@ -5063,6 +5069,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; + css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; @@ -5150,7 +5157,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) - goto err_free_percpu_ref; + goto err_free_css; css->id = err; /* @css is ready to be brought online now, make it visible */ @@ -5174,9 +5181,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, err_list_del: list_del_rcu(&css->sibling); - cgroup_idr_remove(&ss->css_idr, css->id); -err_free_percpu_ref: - percpu_ref_exit(&css->refcnt); err_free_css: call_rcu(&css->rcu_head, css_free_rcu_fn); return ERR_PTR(err); @@ -5451,10 +5455,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) */ cgrp->self.flags &= ~CSS_ONLINE; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) @@ -5725,7 +5729,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, goto out; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; @@ -5778,7 +5782,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, retval = 0; out_unlock: - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); kfree(buf); out: @@ -5923,13 +5927,13 @@ void cgroup_post_fork(struct task_struct *child) if (use_task_css_set_links) { struct css_set *cset; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cset = task_css_set(current); if (list_empty(&child->cg_list)) { get_css_set(cset); css_set_move_task(child, NULL, cset, false); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } /* @@ -5974,9 +5978,9 @@ void cgroup_exit(struct task_struct *tsk) cset = task_css_set(tsk); if (!list_empty(&tsk->cg_list)) { - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); css_set_move_task(tsk, cset, NULL, false); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } else { get_css_set(cset); } @@ -6044,9 +6048,9 @@ static void cgroup_release_agent(struct work_struct *work) if (!pathbuf || !agentbuf) goto out; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (!path) goto out; @@ -6306,12 +6310,12 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, return ERR_PTR(-EPERM); mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); new_ns = alloc_cgroup_ns(); @@ -6435,7 +6439,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v) if (!name_buf) return -ENOMEM; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); rcu_read_lock(); cset = rcu_dereference(current->cgroups); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { @@ -6446,7 +6450,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v) c->root->hierarchy_id, name_buf); } rcu_read_unlock(); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); kfree(name_buf); return 0; } @@ -6457,7 +6461,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) struct cgroup_subsys_state *css = seq_css(seq); struct cgrp_cset_link *link; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { struct css_set *cset = link->cset; struct task_struct *task; @@ -6480,7 +6484,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) overflow: seq_puts(seq, " ...\n"); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return 0; } diff --git a/kernel/cpu.c b/kernel/cpu.c index d948e44c471e..7b61887f7ccd 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1201,6 +1201,8 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = takedown_cpu, .cant_stop = true, }, +#else + [CPUHP_BRINGUP_CPU] = { }, #endif }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 9c51ec3f0f44..43d43a2d5811 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1678,12 +1678,33 @@ static bool is_orphaned_event(struct perf_event *event) return event->state == PERF_EVENT_STATE_DEAD; } -static inline int pmu_filter_match(struct perf_event *event) +static inline int __pmu_filter_match(struct perf_event *event) { struct pmu *pmu = event->pmu; return pmu->filter_match ? pmu->filter_match(event) : 1; } +/* + * Check whether we should attempt to schedule an event group based on + * PMU-specific filtering. An event group can consist of HW and SW events, + * potentially with a SW leader, so we must check all the filters, to + * determine whether a group is schedulable: + */ +static inline int pmu_filter_match(struct perf_event *event) +{ + struct perf_event *child; + + if (!__pmu_filter_match(event)) + return 0; + + list_for_each_entry(child, &event->sibling_list, group_entry) { + if (!__pmu_filter_match(child)) + return 0; + } + + return 1; +} + static inline int event_filter_match(struct perf_event *event) { @@ -7529,7 +7550,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) prog = event->tp_event->prog; if (prog) { event->tp_event->prog = NULL; - bpf_prog_put(prog); + bpf_prog_put_rcu(prog); } } diff --git a/kernel/fork.c b/kernel/fork.c index 5c2c355aa97f..4a7ec0c6c88c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -148,18 +148,18 @@ static inline void free_task_struct(struct task_struct *tsk) } #endif -void __weak arch_release_thread_info(struct thread_info *ti) +void __weak arch_release_thread_stack(unsigned long *stack) { } -#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR +#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, @@ -172,33 +172,33 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, return page ? page_address(page) : NULL; } -static inline void free_thread_info(struct thread_info *ti) +static inline void free_thread_stack(unsigned long *stack) { - struct page *page = virt_to_page(ti); + struct page *page = virt_to_page(stack); memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, -(1 << THREAD_SIZE_ORDER)); __free_kmem_pages(page, THREAD_SIZE_ORDER); } # else -static struct kmem_cache *thread_info_cache; +static struct kmem_cache *thread_stack_cache; -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { - return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node); + return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); } -static void free_thread_info(struct thread_info *ti) +static void free_thread_stack(unsigned long *stack) { - kmem_cache_free(thread_info_cache, ti); + kmem_cache_free(thread_stack_cache, stack); } -void thread_info_cache_init(void) +void thread_stack_cache_init(void) { - thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, + thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, NULL); - BUG_ON(thread_info_cache == NULL); + BUG_ON(thread_stack_cache == NULL); } # endif #endif @@ -221,9 +221,9 @@ struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; -static void account_kernel_stack(struct thread_info *ti, int account) +static void account_kernel_stack(unsigned long *stack, int account) { - struct zone *zone = page_zone(virt_to_page(ti)); + struct zone *zone = page_zone(virt_to_page(stack)); mod_zone_page_state(zone, NR_KERNEL_STACK, account); } @@ -231,8 +231,8 @@ static void account_kernel_stack(struct thread_info *ti, int account) void free_task(struct task_struct *tsk) { account_kernel_stack(tsk->stack, -1); - arch_release_thread_info(tsk->stack); - free_thread_info(tsk->stack); + arch_release_thread_stack(tsk->stack); + free_thread_stack(tsk->stack); rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); put_seccomp_filter(tsk); @@ -343,7 +343,7 @@ void set_task_stack_end_magic(struct task_struct *tsk) static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; - struct thread_info *ti; + unsigned long *stack; int err; if (node == NUMA_NO_NODE) @@ -352,15 +352,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!tsk) return NULL; - ti = alloc_thread_info_node(tsk, node); - if (!ti) + stack = alloc_thread_stack_node(tsk, node); + if (!stack) goto free_tsk; err = arch_dup_task_struct(tsk, orig); if (err) - goto free_ti; + goto free_stack; - tsk->stack = ti; + tsk->stack = stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under @@ -392,14 +392,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - account_kernel_stack(ti, 1); + account_kernel_stack(stack, 1); kcov_task_init(tsk); return tsk; -free_ti: - free_thread_info(ti); +free_stack: + free_thread_stack(stack); free_tsk: free_task_struct(tsk); return NULL; diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index e25e92fb44fa..6a5c239c7669 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,7 @@ #include #include "gcov.h" -#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1 +#if (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) #define GCOV_COUNTERS 10 #elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9 #define GCOV_COUNTERS 9 diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 05254eeb4b4e..4b353e0be121 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key); void static_key_slow_inc(struct static_key *key) { + int v, v1; + STATIC_KEY_CHECK_USE(); - if (atomic_inc_not_zero(&key->enabled)) - return; + + /* + * Careful if we get concurrent static_key_slow_inc() calls; + * later calls must wait for the first one to _finish_ the + * jump_label_update() process. At the same time, however, + * the jump_label_update() call below wants to see + * static_key_enabled(&key) for jumps to be updated properly. + * + * So give a special meaning to negative key->enabled: it sends + * static_key_slow_inc() down the slow path, and it is non-zero + * so it counts as "enabled" in jump_label_update(). Note that + * atomic_inc_unless_negative() checks >= 0, so roll our own. + */ + for (v = atomic_read(&key->enabled); v > 0; v = v1) { + v1 = atomic_cmpxchg(&key->enabled, v, v + 1); + if (likely(v1 == v)) + return; + } jump_label_lock(); - if (atomic_inc_return(&key->enabled) == 1) + if (atomic_read(&key->enabled) == 0) { + atomic_set(&key->enabled, -1); jump_label_update(key); + atomic_set(&key->enabled, 1); + } else { + atomic_inc(&key->enabled); + } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_slow_inc); @@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc); static void __static_key_slow_dec(struct static_key *key, unsigned long rate_limit, struct delayed_work *work) { + /* + * The negative count check is valid even when a negative + * key->enabled is in use by static_key_slow_inc(); a + * __static_key_slow_dec() before the first static_key_slow_inc() + * returns is unbalanced, because all other static_key_slow_inc() + * instances block while the update is in progress. + */ if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) { WARN(atomic_read(&key->enabled) < 0, "jump label: negative count!\n"); diff --git a/kernel/kcov.c b/kernel/kcov.c index a02f2dddd1d7..8d44b3fea9d0 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -264,7 +264,12 @@ static const struct file_operations kcov_fops = { static int __init kcov_init(void) { - if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) { + /* + * The kcov debugfs file won't ever get removed and thus, + * there is no need to protect it against removal races. The + * use of debugfs_create_file_unsafe() is actually safe here. + */ + if (!debugfs_create_file_unsafe("kcov", 0600, NULL, NULL, &kcov_fops)) { pr_err("failed to create kcov in debugfs\n"); return -ENOMEM; } diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index 3ef3736002d8..9c951fade415 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -49,21 +49,21 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter) } void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti) + struct task_struct *task) { SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock)); /* Mark the current thread as blocked on the lock: */ - ti->task->blocked_on = waiter; + task->blocked_on = waiter; } void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti) + struct task_struct *task) { DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); - DEBUG_LOCKS_WARN_ON(waiter->task != ti->task); - DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter); - ti->task->blocked_on = NULL; + DEBUG_LOCKS_WARN_ON(waiter->task != task); + DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter); + task->blocked_on = NULL; list_del_init(&waiter->list); waiter->task = NULL; diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h index 0799fd3e4cfa..d06ae3bb46c5 100644 --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -20,9 +20,9 @@ extern void debug_mutex_wake_waiter(struct mutex *lock, extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); extern void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti); + struct task_struct *task); extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti); + struct task_struct *task); extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 79d2d765a75f..a70b90db3909 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -537,7 +537,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto skip_wait; debug_mutex_lock_common(lock, &waiter); - debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); + debug_mutex_add_waiter(lock, &waiter, task); /* add waiting tasks to the end of the waitqueue (FIFO): */ list_add_tail(&waiter.list, &lock->wait_list); @@ -584,7 +584,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } __set_task_state(task, TASK_RUNNING); - mutex_remove_waiter(lock, &waiter, current_thread_info()); + mutex_remove_waiter(lock, &waiter, task); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); @@ -605,7 +605,7 @@ skip_wait: return 0; err: - mutex_remove_waiter(lock, &waiter, task_thread_info(task)); + mutex_remove_waiter(lock, &waiter, task); spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip); diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 5cda397607f2..a68bae5e852a 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -13,7 +13,7 @@ do { spin_lock(lock); (void)(flags); } while (0) #define spin_unlock_mutex(lock, flags) \ do { spin_unlock(lock); (void)(flags); } while (0) -#define mutex_remove_waiter(lock, waiter, ti) \ +#define mutex_remove_waiter(lock, waiter, task) \ __list_del((waiter)->list.prev, (waiter)->list.next) #ifdef CONFIG_MUTEX_SPIN_ON_OWNER diff --git a/kernel/power/Makefile b/kernel/power/Makefile index cb880a14cc39..eb4f717705ba 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -1,6 +1,8 @@ ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG +KASAN_SANITIZE_snapshot.o := n + obj-y += qos.o obj-$(CONFIG_PM) += main.o obj-$(CONFIG_VT_CONSOLE_SLEEP) += console.o diff --git a/kernel/power/console.c b/kernel/power/console.c index aba9c545a0e3..0e781798b0b3 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -126,17 +126,17 @@ out: return ret; } -int pm_prepare_console(void) +void pm_prepare_console(void) { if (!pm_vt_switch()) - return 0; + return; orig_fgconsole = vt_move_to_console(SUSPEND_CONSOLE, 1); if (orig_fgconsole < 0) - return 1; + return; orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE); - return 0; + return; } void pm_restore_console(void) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index fca9254280ee..0ee1df0a0bd6 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -52,6 +52,7 @@ enum { #ifdef CONFIG_SUSPEND HIBERNATION_SUSPEND, #endif + HIBERNATION_TEST_RESUME, /* keep last */ __HIBERNATION_AFTER_LAST }; @@ -409,6 +410,11 @@ int hibernation_snapshot(int platform_mode) goto Close; } +int __weak hibernate_resume_nonboot_cpu_disable(void) +{ + return disable_nonboot_cpus(); +} + /** * resume_target_kernel - Restore system state from a hibernation image. * @platform_mode: Whether or not to use the platform driver. @@ -433,7 +439,7 @@ static int resume_target_kernel(bool platform_mode) if (error) goto Cleanup; - error = disable_nonboot_cpus(); + error = hibernate_resume_nonboot_cpu_disable(); if (error) goto Enable_cpus; @@ -642,12 +648,39 @@ static void power_down(void) cpu_relax(); } +static int load_image_and_restore(void) +{ + int error; + unsigned int flags; + + pr_debug("PM: Loading hibernation image.\n"); + + lock_device_hotplug(); + error = create_basic_memory_bitmaps(); + if (error) + goto Unlock; + + error = swsusp_read(&flags); + swsusp_close(FMODE_READ); + if (!error) + hibernation_restore(flags & SF_PLATFORM_MODE); + + printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n"); + swsusp_free(); + free_basic_memory_bitmaps(); + Unlock: + unlock_device_hotplug(); + + return error; +} + /** * hibernate - Carry out system hibernation, including saving the image. */ int hibernate(void) { - int error; + int error, nr_calls = 0; + bool snapshot_test = false; if (!hibernation_available()) { pr_debug("PM: Hibernation not available.\n"); @@ -662,9 +695,11 @@ int hibernate(void) } pm_prepare_console(); - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Exit; + } printk(KERN_INFO "PM: Syncing filesystems ... "); sys_sync(); @@ -697,8 +732,12 @@ int hibernate(void) pr_debug("PM: writing image.\n"); error = swsusp_write(flags); swsusp_free(); - if (!error) - power_down(); + if (!error) { + if (hibernation_mode == HIBERNATION_TEST_RESUME) + snapshot_test = true; + else + power_down(); + } in_suspend = 0; pm_restore_gfp_mask(); } else { @@ -709,12 +748,18 @@ int hibernate(void) free_basic_memory_bitmaps(); Thaw: unlock_device_hotplug(); + if (snapshot_test) { + pr_debug("PM: Checking hibernation image\n"); + error = swsusp_check(); + if (!error) + error = load_image_and_restore(); + } thaw_processes(); /* Don't bother checking whether freezer_test_done is true */ freezer_test_done = false; Exit: - pm_notifier_call_chain(PM_POST_HIBERNATION); + __pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL); pm_restore_console(); atomic_inc(&snapshot_device_available); Unlock: @@ -740,8 +785,7 @@ int hibernate(void) */ static int software_resume(void) { - int error; - unsigned int flags; + int error, nr_calls = 0; /* * If the user said "noresume".. bail out early. @@ -827,35 +871,20 @@ static int software_resume(void) } pm_prepare_console(); - error = pm_notifier_call_chain(PM_RESTORE_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Close_Finish; + } pr_debug("PM: Preparing processes for restore.\n"); error = freeze_processes(); if (error) goto Close_Finish; - - pr_debug("PM: Loading hibernation image.\n"); - - lock_device_hotplug(); - error = create_basic_memory_bitmaps(); - if (error) - goto Thaw; - - error = swsusp_read(&flags); - swsusp_close(FMODE_READ); - if (!error) - hibernation_restore(flags & SF_PLATFORM_MODE); - - printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n"); - swsusp_free(); - free_basic_memory_bitmaps(); - Thaw: - unlock_device_hotplug(); + error = load_image_and_restore(); thaw_processes(); Finish: - pm_notifier_call_chain(PM_POST_RESTORE); + __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); pm_restore_console(); atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ @@ -878,6 +907,7 @@ static const char * const hibernation_modes[] = { #ifdef CONFIG_SUSPEND [HIBERNATION_SUSPEND] = "suspend", #endif + [HIBERNATION_TEST_RESUME] = "test_resume", }; /* @@ -924,6 +954,7 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif + case HIBERNATION_TEST_RESUME: break; case HIBERNATION_PLATFORM: if (hibernation_ops) @@ -970,6 +1001,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif + case HIBERNATION_TEST_RESUME: hibernation_mode = mode; break; case HIBERNATION_PLATFORM: @@ -1115,13 +1147,16 @@ static int __init resume_offset_setup(char *str) static int __init hibernate_setup(char *str) { - if (!strncmp(str, "noresume", 8)) + if (!strncmp(str, "noresume", 8)) { noresume = 1; - else if (!strncmp(str, "nocompress", 10)) + } else if (!strncmp(str, "nocompress", 10)) { nocompress = 1; - else if (!strncmp(str, "no", 2)) { + } else if (!strncmp(str, "no", 2)) { noresume = 1; nohibernate = 1; + } else if (IS_ENABLED(CONFIG_DEBUG_RODATA) + && !strncmp(str, "protect_image", 13)) { + enable_restore_image_protection(); } return 1; } diff --git a/kernel/power/main.c b/kernel/power/main.c index 27946975eff0..5ea50b1b7595 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -38,12 +38,19 @@ int unregister_pm_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_pm_notifier); -int pm_notifier_call_chain(unsigned long val) +int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls) { - int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL); + int ret; + + ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL, + nr_to_call, nr_calls); return notifier_to_errno(ret); } +int pm_notifier_call_chain(unsigned long val) +{ + return __pm_notifier_call_chain(val, -1, NULL); +} /* If set, devices may be suspended and resumed asynchronously. */ int pm_async_enabled = 1; diff --git a/kernel/power/power.h b/kernel/power/power.h index efe1b3b17c88..242d8b827dd5 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -38,6 +38,8 @@ static inline char *check_image_kernel(struct swsusp_info *info) } #endif /* CONFIG_ARCH_HIBERNATION_HEADER */ +extern int hibernate_resume_nonboot_cpu_disable(void); + /* * Keep some memory free so that I/O operations can succeed without paging * [Might this be more than 4 MB?] @@ -59,6 +61,13 @@ extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); extern int hibernation_platform_enter(void); +#ifdef CONFIG_DEBUG_RODATA +/* kernel/power/snapshot.c */ +extern void enable_restore_image_protection(void); +#else +static inline void enable_restore_image_protection(void) {} +#endif /* CONFIG_DEBUG_RODATA */ + #else /* !CONFIG_HIBERNATION */ static inline void hibernate_reserved_size_init(void) {} @@ -200,6 +209,8 @@ static inline void suspend_test_finish(const char *label) {} #ifdef CONFIG_PM_SLEEP /* kernel/power/main.c */ +extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call, + int *nr_calls); extern int pm_notifier_call_chain(unsigned long val); #endif diff --git a/kernel/power/process.c b/kernel/power/process.c index df058bed53ce..8f27d5a8adf6 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -89,6 +89,9 @@ static int try_to_freeze_tasks(bool user_only) elapsed_msecs / 1000, elapsed_msecs % 1000, todo - wq_busy, wq_busy); + if (wq_busy) + show_workqueue_state(); + if (!wakeup) { read_lock(&tasklist_lock); for_each_process_thread(g, p) { @@ -146,6 +149,18 @@ int freeze_processes(void) if (!error && !oom_killer_disable()) error = -EBUSY; + /* + * There is a hard to fix race between oom_reaper kernel thread + * and oom_killer_disable. oom_reaper calls exit_oom_victim + * before the victim reaches exit_mm so try to freeze all the tasks + * again and catch such a left over task. + */ + if (!error) { + pr_info("Double checking all user space processes after OOM killer disable... "); + error = try_to_freeze_tasks(true); + pr_cont("\n"); + } + if (error) thaw_processes(); return error; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3a970604308f..d90df926b59f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -38,6 +38,43 @@ #include "power.h" +#ifdef CONFIG_DEBUG_RODATA +static bool hibernate_restore_protection; +static bool hibernate_restore_protection_active; + +void enable_restore_image_protection(void) +{ + hibernate_restore_protection = true; +} + +static inline void hibernate_restore_protection_begin(void) +{ + hibernate_restore_protection_active = hibernate_restore_protection; +} + +static inline void hibernate_restore_protection_end(void) +{ + hibernate_restore_protection_active = false; +} + +static inline void hibernate_restore_protect_page(void *page_address) +{ + if (hibernate_restore_protection_active) + set_memory_ro((unsigned long)page_address, 1); +} + +static inline void hibernate_restore_unprotect_page(void *page_address) +{ + if (hibernate_restore_protection_active) + set_memory_rw((unsigned long)page_address, 1); +} +#else +static inline void hibernate_restore_protection_begin(void) {} +static inline void hibernate_restore_protection_end(void) {} +static inline void hibernate_restore_protect_page(void *page_address) {} +static inline void hibernate_restore_unprotect_page(void *page_address) {} +#endif /* CONFIG_DEBUG_RODATA */ + static int swsusp_page_is_free(struct page *); static void swsusp_set_page_forbidden(struct page *); static void swsusp_unset_page_forbidden(struct page *); @@ -67,25 +104,32 @@ void __init hibernate_image_size_init(void) image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE; } -/* List of PBEs needed for restoring the pages that were allocated before +/* + * List of PBEs needed for restoring the pages that were allocated before * the suspend and included in the suspend image, but have also been * allocated by the "resume" kernel, so their contents cannot be written * directly to their "original" page frames. */ struct pbe *restore_pblist; -/* Pointer to an auxiliary buffer (1 page) */ -static void *buffer; +/* struct linked_page is used to build chains of pages */ -/** - * @safe_needed - on resume, for storing the PBE list and the image, - * we can only use memory pages that do not conflict with the pages - * used before suspend. The unsafe pages have PageNosaveFree set - * and we count them using unsafe_pages. - * - * Each allocated image page is marked as PageNosave and PageNosaveFree - * so that swsusp_free() can release it. +#define LINKED_PAGE_DATA_SIZE (PAGE_SIZE - sizeof(void *)) + +struct linked_page { + struct linked_page *next; + char data[LINKED_PAGE_DATA_SIZE]; +} __packed; + +/* + * List of "safe" pages (ie. pages that were not used by the image kernel + * before hibernation) that may be used as temporary storage for image kernel + * memory contents. */ +static struct linked_page *safe_pages_list; + +/* Pointer to an auxiliary buffer (1 page) */ +static void *buffer; #define PG_ANY 0 #define PG_SAFE 1 @@ -94,6 +138,19 @@ static void *buffer; static unsigned int allocated_unsafe_pages; +/** + * get_image_page - Allocate a page for a hibernation image. + * @gfp_mask: GFP mask for the allocation. + * @safe_needed: Get pages that were not used before hibernation (restore only) + * + * During image restoration, for storing the PBE list and the image data, we can + * only use memory pages that do not conflict with the pages used before + * hibernation. The "unsafe" pages have PageNosaveFree set and we count them + * using allocated_unsafe_pages. + * + * Each allocated image page is marked as PageNosave and PageNosaveFree so that + * swsusp_free() can release it. + */ static void *get_image_page(gfp_t gfp_mask, int safe_needed) { void *res; @@ -113,9 +170,21 @@ static void *get_image_page(gfp_t gfp_mask, int safe_needed) return res; } +static void *__get_safe_page(gfp_t gfp_mask) +{ + if (safe_pages_list) { + void *ret = safe_pages_list; + + safe_pages_list = safe_pages_list->next; + memset(ret, 0, PAGE_SIZE); + return ret; + } + return get_image_page(gfp_mask, PG_SAFE); +} + unsigned long get_safe_page(gfp_t gfp_mask) { - return (unsigned long)get_image_page(gfp_mask, PG_SAFE); + return (unsigned long)__get_safe_page(gfp_mask); } static struct page *alloc_image_page(gfp_t gfp_mask) @@ -130,11 +199,22 @@ static struct page *alloc_image_page(gfp_t gfp_mask) return page; } +static void recycle_safe_page(void *page_address) +{ + struct linked_page *lp = page_address; + + lp->next = safe_pages_list; + safe_pages_list = lp; +} + /** - * free_image_page - free page represented by @addr, allocated with - * get_image_page (page flags set by it must be cleared) + * free_image_page - Free a page allocated for hibernation image. + * @addr: Address of the page to free. + * @clear_nosave_free: If set, clear the PageNosaveFree bit for the page. + * + * The page to free should have been allocated by get_image_page() (page flags + * set by it are affected). */ - static inline void free_image_page(void *addr, int clear_nosave_free) { struct page *page; @@ -150,17 +230,8 @@ static inline void free_image_page(void *addr, int clear_nosave_free) __free_page(page); } -/* struct linked_page is used to build chains of pages */ - -#define LINKED_PAGE_DATA_SIZE (PAGE_SIZE - sizeof(void *)) - -struct linked_page { - struct linked_page *next; - char data[LINKED_PAGE_DATA_SIZE]; -} __packed; - -static inline void -free_list_of_pages(struct linked_page *list, int clear_page_nosave) +static inline void free_list_of_pages(struct linked_page *list, + int clear_page_nosave) { while (list) { struct linked_page *lp = list->next; @@ -170,30 +241,28 @@ free_list_of_pages(struct linked_page *list, int clear_page_nosave) } } -/** - * struct chain_allocator is used for allocating small objects out of - * a linked list of pages called 'the chain'. - * - * The chain grows each time when there is no room for a new object in - * the current page. The allocated objects cannot be freed individually. - * It is only possible to free them all at once, by freeing the entire - * chain. - * - * NOTE: The chain allocator may be inefficient if the allocated objects - * are not much smaller than PAGE_SIZE. - */ - +/* + * struct chain_allocator is used for allocating small objects out of + * a linked list of pages called 'the chain'. + * + * The chain grows each time when there is no room for a new object in + * the current page. The allocated objects cannot be freed individually. + * It is only possible to free them all at once, by freeing the entire + * chain. + * + * NOTE: The chain allocator may be inefficient if the allocated objects + * are not much smaller than PAGE_SIZE. + */ struct chain_allocator { struct linked_page *chain; /* the chain */ unsigned int used_space; /* total size of objects allocated out - * of the current page - */ + of the current page */ gfp_t gfp_mask; /* mask for allocating pages */ int safe_needed; /* if set, only "safe" pages are allocated */ }; -static void -chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed) +static void chain_init(struct chain_allocator *ca, gfp_t gfp_mask, + int safe_needed) { ca->chain = NULL; ca->used_space = LINKED_PAGE_DATA_SIZE; @@ -208,7 +277,8 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size) if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) { struct linked_page *lp; - lp = get_image_page(ca->gfp_mask, ca->safe_needed); + lp = ca->safe_needed ? __get_safe_page(ca->gfp_mask) : + get_image_page(ca->gfp_mask, PG_ANY); if (!lp) return NULL; @@ -222,44 +292,44 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size) } /** - * Data types related to memory bitmaps. + * Data types related to memory bitmaps. * - * Memory bitmap is a structure consiting of many linked lists of - * objects. The main list's elements are of type struct zone_bitmap - * and each of them corresonds to one zone. For each zone bitmap - * object there is a list of objects of type struct bm_block that - * represent each blocks of bitmap in which information is stored. + * Memory bitmap is a structure consiting of many linked lists of + * objects. The main list's elements are of type struct zone_bitmap + * and each of them corresonds to one zone. For each zone bitmap + * object there is a list of objects of type struct bm_block that + * represent each blocks of bitmap in which information is stored. * - * struct memory_bitmap contains a pointer to the main list of zone - * bitmap objects, a struct bm_position used for browsing the bitmap, - * and a pointer to the list of pages used for allocating all of the - * zone bitmap objects and bitmap block objects. + * struct memory_bitmap contains a pointer to the main list of zone + * bitmap objects, a struct bm_position used for browsing the bitmap, + * and a pointer to the list of pages used for allocating all of the + * zone bitmap objects and bitmap block objects. * - * NOTE: It has to be possible to lay out the bitmap in memory - * using only allocations of order 0. Additionally, the bitmap is - * designed to work with arbitrary number of zones (this is over the - * top for now, but let's avoid making unnecessary assumptions ;-). + * NOTE: It has to be possible to lay out the bitmap in memory + * using only allocations of order 0. Additionally, the bitmap is + * designed to work with arbitrary number of zones (this is over the + * top for now, but let's avoid making unnecessary assumptions ;-). * - * struct zone_bitmap contains a pointer to a list of bitmap block - * objects and a pointer to the bitmap block object that has been - * most recently used for setting bits. Additionally, it contains the - * pfns that correspond to the start and end of the represented zone. + * struct zone_bitmap contains a pointer to a list of bitmap block + * objects and a pointer to the bitmap block object that has been + * most recently used for setting bits. Additionally, it contains the + * PFNs that correspond to the start and end of the represented zone. * - * struct bm_block contains a pointer to the memory page in which - * information is stored (in the form of a block of bitmap) - * It also contains the pfns that correspond to the start and end of - * the represented memory area. + * struct bm_block contains a pointer to the memory page in which + * information is stored (in the form of a block of bitmap) + * It also contains the pfns that correspond to the start and end of + * the represented memory area. * - * The memory bitmap is organized as a radix tree to guarantee fast random - * access to the bits. There is one radix tree for each zone (as returned - * from create_mem_extents). + * The memory bitmap is organized as a radix tree to guarantee fast random + * access to the bits. There is one radix tree for each zone (as returned + * from create_mem_extents). * - * One radix tree is represented by one struct mem_zone_bm_rtree. There are - * two linked lists for the nodes of the tree, one for the inner nodes and - * one for the leave nodes. The linked leave nodes are used for fast linear - * access of the memory bitmap. + * One radix tree is represented by one struct mem_zone_bm_rtree. There are + * two linked lists for the nodes of the tree, one for the inner nodes and + * one for the leave nodes. The linked leave nodes are used for fast linear + * access of the memory bitmap. * - * The struct rtree_node represents one node of the radix tree. + * The struct rtree_node represents one node of the radix tree. */ #define BM_END_OF_MAP (~0UL) @@ -305,9 +375,8 @@ struct bm_position { struct memory_bitmap { struct list_head zones; struct linked_page *p_list; /* list of pages used to store zone - * bitmap objects and bitmap block - * objects - */ + bitmap objects and bitmap block + objects */ struct bm_position cur; /* most recently used bit position */ }; @@ -321,12 +390,12 @@ struct memory_bitmap { #endif #define BM_RTREE_LEVEL_MASK ((1UL << BM_RTREE_LEVEL_SHIFT) - 1) -/* - * alloc_rtree_node - Allocate a new node and add it to the radix tree. +/** + * alloc_rtree_node - Allocate a new node and add it to the radix tree. * - * This function is used to allocate inner nodes as well as the - * leave nodes of the radix tree. It also adds the node to the - * corresponding linked list passed in by the *list parameter. + * This function is used to allocate inner nodes as well as the + * leave nodes of the radix tree. It also adds the node to the + * corresponding linked list passed in by the *list parameter. */ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, @@ -347,12 +416,12 @@ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, return node; } -/* - * add_rtree_block - Add a new leave node to the radix tree +/** + * add_rtree_block - Add a new leave node to the radix tree. * - * The leave nodes need to be allocated in order to keep the leaves - * linked list in order. This is guaranteed by the zone->blocks - * counter. + * The leave nodes need to be allocated in order to keep the leaves + * linked list in order. This is guaranteed by the zone->blocks + * counter. */ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca) @@ -417,17 +486,18 @@ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free); -/* - * create_zone_bm_rtree - create a radix tree for one zone +/** + * create_zone_bm_rtree - Create a radix tree for one zone. * - * Allocated the mem_zone_bm_rtree structure and initializes it. - * This function also allocated and builds the radix tree for the - * zone. + * Allocated the mem_zone_bm_rtree structure and initializes it. + * This function also allocated and builds the radix tree for the + * zone. */ -static struct mem_zone_bm_rtree * -create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, - struct chain_allocator *ca, - unsigned long start, unsigned long end) +static struct mem_zone_bm_rtree *create_zone_bm_rtree(gfp_t gfp_mask, + int safe_needed, + struct chain_allocator *ca, + unsigned long start, + unsigned long end) { struct mem_zone_bm_rtree *zone; unsigned int i, nr_blocks; @@ -454,12 +524,12 @@ create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, return zone; } -/* - * free_zone_bm_rtree - Free the memory of the radix tree +/** + * free_zone_bm_rtree - Free the memory of the radix tree. * - * Free all node pages of the radix tree. The mem_zone_bm_rtree - * structure itself is not freed here nor are the rtree_node - * structs. + * Free all node pages of the radix tree. The mem_zone_bm_rtree + * structure itself is not freed here nor are the rtree_node + * structs. */ static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free) @@ -492,8 +562,8 @@ struct mem_extent { }; /** - * free_mem_extents - free a list of memory extents - * @list - list of extents to empty + * free_mem_extents - Free a list of memory extents. + * @list: List of extents to free. */ static void free_mem_extents(struct list_head *list) { @@ -506,10 +576,11 @@ static void free_mem_extents(struct list_head *list) } /** - * create_mem_extents - create a list of memory extents representing - * contiguous ranges of PFNs - * @list - list to put the extents into - * @gfp_mask - mask to use for memory allocations + * create_mem_extents - Create a list of memory extents. + * @list: List to put the extents into. + * @gfp_mask: Mask to use for memory allocations. + * + * The extents represent contiguous ranges of PFNs. */ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) { @@ -565,10 +636,10 @@ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) } /** - * memory_bm_create - allocate memory for a memory bitmap - */ -static int -memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) + * memory_bm_create - Allocate memory for a memory bitmap. + */ +static int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, + int safe_needed) { struct chain_allocator ca; struct list_head mem_extents; @@ -607,8 +678,9 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) } /** - * memory_bm_free - free memory occupied by the memory bitmap @bm - */ + * memory_bm_free - Free memory occupied by the memory bitmap. + * @bm: Memory bitmap. + */ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) { struct mem_zone_bm_rtree *zone; @@ -622,14 +694,13 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) } /** - * memory_bm_find_bit - Find the bit for pfn in the memory - * bitmap + * memory_bm_find_bit - Find the bit for a given PFN in a memory bitmap. * - * Find the bit in the bitmap @bm that corresponds to given pfn. - * The cur.zone, cur.block and cur.node_pfn member of @bm are - * updated. - * It walks the radix tree to find the page which contains the bit for - * pfn and returns the bit position in **addr and *bit_nr. + * Find the bit in memory bitmap @bm that corresponds to the given PFN. + * The cur.zone, cur.block and cur.node_pfn members of @bm are updated. + * + * Walk the radix tree to find the page containing the bit that represents @pfn + * and return the position of the bit in @addr and @bit_nr. */ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, void **addr, unsigned int *bit_nr) @@ -658,10 +729,9 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, zone_found: /* - * We have a zone. Now walk the radix tree to find the leave - * node for our pfn. + * We have found the zone. Now walk the radix tree to find the leaf node + * for our PFN. */ - node = bm->cur.node; if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) goto node_found; @@ -754,14 +824,14 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) } /* - * rtree_next_node - Jumps to the next leave node + * rtree_next_node - Jump to the next leaf node. * - * Sets the position to the beginning of the next node in the - * memory bitmap. This is either the next node in the current - * zone's radix tree or the first node in the radix tree of the - * next zone. + * Set the position to the beginning of the next node in the + * memory bitmap. This is either the next node in the current + * zone's radix tree or the first node in the radix tree of the + * next zone. * - * Returns true if there is a next node, false otherwise. + * Return true if there is a next node, false otherwise. */ static bool rtree_next_node(struct memory_bitmap *bm) { @@ -790,14 +860,15 @@ static bool rtree_next_node(struct memory_bitmap *bm) } /** - * memory_bm_rtree_next_pfn - Find the next set bit in the bitmap @bm + * memory_bm_rtree_next_pfn - Find the next set bit in a memory bitmap. + * @bm: Memory bitmap. * - * Starting from the last returned position this function searches - * for the next set bit in the memory bitmap and returns its - * number. If no more bit is set BM_END_OF_MAP is returned. + * Starting from the last returned position this function searches for the next + * set bit in @bm and returns the PFN represented by it. If no more bits are + * set, BM_END_OF_MAP is returned. * - * It is required to run memory_bm_position_reset() before the - * first call to this function. + * It is required to run memory_bm_position_reset() before the first call to + * this function for the given memory bitmap. */ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) { @@ -819,11 +890,10 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) return BM_END_OF_MAP; } -/** - * This structure represents a range of page frames the contents of which - * should not be saved during the suspend. +/* + * This structure represents a range of page frames the contents of which + * should not be saved during hibernation. */ - struct nosave_region { struct list_head list; unsigned long start_pfn; @@ -832,15 +902,42 @@ struct nosave_region { static LIST_HEAD(nosave_regions); +static void recycle_zone_bm_rtree(struct mem_zone_bm_rtree *zone) +{ + struct rtree_node *node; + + list_for_each_entry(node, &zone->nodes, list) + recycle_safe_page(node->data); + + list_for_each_entry(node, &zone->leaves, list) + recycle_safe_page(node->data); +} + +static void memory_bm_recycle(struct memory_bitmap *bm) +{ + struct mem_zone_bm_rtree *zone; + struct linked_page *p_list; + + list_for_each_entry(zone, &bm->zones, list) + recycle_zone_bm_rtree(zone); + + p_list = bm->p_list; + while (p_list) { + struct linked_page *lp = p_list; + + p_list = lp->next; + recycle_safe_page(lp); + } +} + /** - * register_nosave_region - register a range of page frames the contents - * of which should not be saved during the suspend (to be used in the early - * initialization code) + * register_nosave_region - Register a region of unsaveable memory. + * + * Register a range of page frames the contents of which should not be saved + * during hibernation (to be used in the early initialization code). */ - -void __init -__register_nosave_region(unsigned long start_pfn, unsigned long end_pfn, - int use_kmalloc) +void __init __register_nosave_region(unsigned long start_pfn, + unsigned long end_pfn, int use_kmalloc) { struct nosave_region *region; @@ -857,12 +954,13 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn, } } if (use_kmalloc) { - /* during init, this shouldn't fail */ + /* During init, this shouldn't fail */ region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL); BUG_ON(!region); - } else + } else { /* This allocation cannot fail */ region = memblock_virt_alloc(sizeof(struct nosave_region), 0); + } region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); @@ -923,10 +1021,12 @@ static void swsusp_unset_page_forbidden(struct page *page) } /** - * mark_nosave_pages - set bits corresponding to the page frames the - * contents of which should not be saved in a given bitmap. + * mark_nosave_pages - Mark pages that should not be saved. + * @bm: Memory bitmap. + * + * Set the bits in @bm that correspond to the page frames the contents of which + * should not be saved. */ - static void mark_nosave_pages(struct memory_bitmap *bm) { struct nosave_region *region; @@ -956,13 +1056,13 @@ static void mark_nosave_pages(struct memory_bitmap *bm) } /** - * create_basic_memory_bitmaps - create bitmaps needed for marking page - * frames that should not be saved and free page frames. The pointers - * forbidden_pages_map and free_pages_map are only modified if everything - * goes well, because we don't want the bits to be used before both bitmaps - * are set up. + * create_basic_memory_bitmaps - Create bitmaps to hold basic page information. + * + * Create bitmaps needed for marking page frames that should not be saved and + * free page frames. The forbidden_pages_map and free_pages_map pointers are + * only modified if everything goes well, because we don't want the bits to be + * touched before both bitmaps are set up. */ - int create_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; @@ -1007,12 +1107,12 @@ int create_basic_memory_bitmaps(void) } /** - * free_basic_memory_bitmaps - free memory bitmaps allocated by - * create_basic_memory_bitmaps(). The auxiliary pointers are necessary - * so that the bitmaps themselves are not referred to while they are being - * freed. + * free_basic_memory_bitmaps - Free memory bitmaps holding basic information. + * + * Free memory bitmaps allocated by create_basic_memory_bitmaps(). The + * auxiliary pointers are necessary so that the bitmaps themselves are not + * referred to while they are being freed. */ - void free_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; @@ -1033,11 +1133,13 @@ void free_basic_memory_bitmaps(void) } /** - * snapshot_additional_pages - estimate the number of additional pages - * be needed for setting up the suspend image data structures for given - * zone (usually the returned value is greater than the exact number) + * snapshot_additional_pages - Estimate the number of extra pages needed. + * @zone: Memory zone to carry out the computation for. + * + * Estimate the number of additional pages needed for setting up a hibernation + * image data structures for @zone (usually, the returned value is greater than + * the exact number). */ - unsigned int snapshot_additional_pages(struct zone *zone) { unsigned int rtree, nodes; @@ -1055,10 +1157,10 @@ unsigned int snapshot_additional_pages(struct zone *zone) #ifdef CONFIG_HIGHMEM /** - * count_free_highmem_pages - compute the total number of free highmem - * pages, system-wide. + * count_free_highmem_pages - Compute the total number of free highmem pages. + * + * The returned number is system-wide. */ - static unsigned int count_free_highmem_pages(void) { struct zone *zone; @@ -1072,11 +1174,12 @@ static unsigned int count_free_highmem_pages(void) } /** - * saveable_highmem_page - Determine whether a highmem page should be - * included in the suspend image. + * saveable_highmem_page - Check if a highmem page is saveable. * - * We should save the page if it isn't Nosave or NosaveFree, or Reserved, - * and it isn't a part of a free chunk of pages. + * Determine whether a highmem page should be included in a hibernation image. + * + * We should save the page if it isn't Nosave or NosaveFree, or Reserved, + * and it isn't part of a free chunk of pages. */ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) { @@ -1102,10 +1205,8 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) } /** - * count_highmem_pages - compute the total number of saveable highmem - * pages. + * count_highmem_pages - Compute the total number of saveable highmem pages. */ - static unsigned int count_highmem_pages(void) { struct zone *zone; @@ -1133,12 +1234,14 @@ static inline void *saveable_highmem_page(struct zone *z, unsigned long p) #endif /* CONFIG_HIGHMEM */ /** - * saveable_page - Determine whether a non-highmem page should be included - * in the suspend image. + * saveable_page - Check if the given page is saveable. * - * We should save the page if it isn't Nosave, and is not in the range - * of pages statically defined as 'unsaveable', and it isn't a part of - * a free chunk of pages. + * Determine whether a non-highmem page should be included in a hibernation + * image. + * + * We should save the page if it isn't Nosave, and is not in the range + * of pages statically defined as 'unsaveable', and it isn't part of + * a free chunk of pages. */ static struct page *saveable_page(struct zone *zone, unsigned long pfn) { @@ -1167,10 +1270,8 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn) } /** - * count_data_pages - compute the total number of saveable non-highmem - * pages. + * count_data_pages - Compute the total number of saveable non-highmem pages. */ - static unsigned int count_data_pages(void) { struct zone *zone; @@ -1190,7 +1291,8 @@ static unsigned int count_data_pages(void) return n; } -/* This is needed, because copy_page and memcpy are not usable for copying +/* + * This is needed, because copy_page and memcpy are not usable for copying * task structs. */ static inline void do_copy_page(long *dst, long *src) @@ -1201,12 +1303,12 @@ static inline void do_copy_page(long *dst, long *src) *dst++ = *src++; } - /** - * safe_copy_page - check if the page we are going to copy is marked as - * present in the kernel page tables (this always is the case if - * CONFIG_DEBUG_PAGEALLOC is not set and in that case - * kernel_page_present() always returns 'true'). + * safe_copy_page - Copy a page in a safe way. + * + * Check if the page we are going to copy is marked as present in the kernel + * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set + * and in that case kernel_page_present() always returns 'true'). */ static void safe_copy_page(void *dst, struct page *s_page) { @@ -1219,10 +1321,8 @@ static void safe_copy_page(void *dst, struct page *s_page) } } - #ifdef CONFIG_HIGHMEM -static inline struct page * -page_is_saveable(struct zone *zone, unsigned long pfn) +static inline struct page *page_is_saveable(struct zone *zone, unsigned long pfn) { return is_highmem(zone) ? saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn); @@ -1243,7 +1343,8 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) kunmap_atomic(src); } else { if (PageHighMem(d_page)) { - /* Page pointed to by src may contain some kernel + /* + * The page pointed to by src may contain some kernel * data modified by kmap_atomic() */ safe_copy_page(buffer, s_page); @@ -1265,8 +1366,8 @@ static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) } #endif /* CONFIG_HIGHMEM */ -static void -copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm) +static void copy_data_pages(struct memory_bitmap *copy_bm, + struct memory_bitmap *orig_bm) { struct zone *zone; unsigned long pfn; @@ -1315,12 +1416,11 @@ static struct memory_bitmap orig_bm; static struct memory_bitmap copy_bm; /** - * swsusp_free - free pages allocated for the suspend. + * swsusp_free - Free pages allocated for hibernation image. * - * Suspend pages are alocated before the atomic copy is made, so we - * need to release them after the resume. + * Image pages are alocated before snapshot creation, so they need to be + * released after resume. */ - void swsusp_free(void) { unsigned long fb_pfn, fr_pfn; @@ -1351,6 +1451,7 @@ loop: memory_bm_clear_current(forbidden_pages_map); memory_bm_clear_current(free_pages_map); + hibernate_restore_unprotect_page(page_address(page)); __free_page(page); goto loop; } @@ -1362,6 +1463,7 @@ out: buffer = NULL; alloc_normal = 0; alloc_highmem = 0; + hibernate_restore_protection_end(); } /* Helper functions used for the shrinking of memory. */ @@ -1369,7 +1471,7 @@ out: #define GFP_IMAGE (GFP_KERNEL | __GFP_NOWARN) /** - * preallocate_image_pages - Allocate a number of pages for hibernation image + * preallocate_image_pages - Allocate a number of pages for hibernation image. * @nr_pages: Number of page frames to allocate. * @mask: GFP flags to use for the allocation. * @@ -1419,7 +1521,7 @@ static unsigned long preallocate_image_highmem(unsigned long nr_pages) } /** - * __fraction - Compute (an approximation of) x * (multiplier / base) + * __fraction - Compute (an approximation of) x * (multiplier / base). */ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) { @@ -1429,8 +1531,8 @@ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) } static unsigned long preallocate_highmem_fraction(unsigned long nr_pages, - unsigned long highmem, - unsigned long total) + unsigned long highmem, + unsigned long total) { unsigned long alloc = __fraction(nr_pages, highmem, total); @@ -1443,15 +1545,15 @@ static inline unsigned long preallocate_image_highmem(unsigned long nr_pages) } static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, - unsigned long highmem, - unsigned long total) + unsigned long highmem, + unsigned long total) { return 0; } #endif /* CONFIG_HIGHMEM */ /** - * free_unnecessary_pages - Release preallocated pages not needed for the image + * free_unnecessary_pages - Release preallocated pages not needed for the image. */ static unsigned long free_unnecessary_pages(void) { @@ -1505,7 +1607,7 @@ static unsigned long free_unnecessary_pages(void) } /** - * minimum_image_size - Estimate the minimum acceptable size of an image + * minimum_image_size - Estimate the minimum acceptable size of an image. * @saveable: Number of saveable pages in the system. * * We want to avoid attempting to free too much memory too hard, so estimate the @@ -1535,7 +1637,7 @@ static unsigned long minimum_image_size(unsigned long saveable) } /** - * hibernate_preallocate_memory - Preallocate memory for hibernation image + * hibernate_preallocate_memory - Preallocate memory for hibernation image. * * To create a hibernation image it is necessary to make a copy of every page * frame in use. We also need a number of page frames to be free during @@ -1708,10 +1810,11 @@ int hibernate_preallocate_memory(void) #ifdef CONFIG_HIGHMEM /** - * count_pages_for_highmem - compute the number of non-highmem pages - * that will be necessary for creating copies of highmem pages. - */ - + * count_pages_for_highmem - Count non-highmem pages needed for copying highmem. + * + * Compute the number of non-highmem pages that will be necessary for creating + * copies of highmem pages. + */ static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem; @@ -1724,15 +1827,12 @@ static unsigned int count_pages_for_highmem(unsigned int nr_highmem) return nr_highmem; } #else -static unsigned int -count_pages_for_highmem(unsigned int nr_highmem) { return 0; } +static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { return 0; } #endif /* CONFIG_HIGHMEM */ /** - * enough_free_mem - Make sure we have enough free memory for the - * snapshot image. + * enough_free_mem - Check if there is enough free memory for the image. */ - static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) { struct zone *zone; @@ -1751,10 +1851,11 @@ static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) #ifdef CONFIG_HIGHMEM /** - * get_highmem_buffer - if there are some highmem pages in the suspend - * image, we may need the buffer to copy them and/or load their data. + * get_highmem_buffer - Allocate a buffer for highmem pages. + * + * If there are some highmem pages in the hibernation image, we may need a + * buffer to copy them and/or load their data. */ - static inline int get_highmem_buffer(int safe_needed) { buffer = get_image_page(GFP_ATOMIC | __GFP_COLD, safe_needed); @@ -1762,13 +1863,13 @@ static inline int get_highmem_buffer(int safe_needed) } /** - * alloc_highmem_image_pages - allocate some highmem pages for the image. - * Try to allocate as many pages as needed, but if the number of free - * highmem pages is lesser than that, allocate them all. + * alloc_highmem_image_pages - Allocate some highmem pages for the image. + * + * Try to allocate as many pages as needed, but if the number of free highmem + * pages is less than that, allocate them all. */ - -static inline unsigned int -alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) +static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, + unsigned int nr_highmem) { unsigned int to_alloc = count_free_highmem_pages(); @@ -1787,25 +1888,24 @@ alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) #else static inline int get_highmem_buffer(int safe_needed) { return 0; } -static inline unsigned int -alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; } +static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, + unsigned int n) { return 0; } #endif /* CONFIG_HIGHMEM */ /** - * swsusp_alloc - allocate memory for the suspend image + * swsusp_alloc - Allocate memory for hibernation image. * - * We first try to allocate as many highmem pages as there are - * saveable highmem pages in the system. If that fails, we allocate - * non-highmem pages for the copies of the remaining highmem ones. + * We first try to allocate as many highmem pages as there are + * saveable highmem pages in the system. If that fails, we allocate + * non-highmem pages for the copies of the remaining highmem ones. * - * In this approach it is likely that the copies of highmem pages will - * also be located in the high memory, because of the way in which - * copy_data_pages() works. + * In this approach it is likely that the copies of highmem pages will + * also be located in the high memory, because of the way in which + * copy_data_pages() works. */ - -static int -swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, - unsigned int nr_pages, unsigned int nr_highmem) +static int swsusp_alloc(struct memory_bitmap *orig_bm, + struct memory_bitmap *copy_bm, + unsigned int nr_pages, unsigned int nr_highmem) { if (nr_highmem > 0) { if (get_highmem_buffer(PG_ANY)) @@ -1855,7 +1955,8 @@ asmlinkage __visible int swsusp_save(void) return -ENOMEM; } - /* During allocating of suspend pagedir, new cold pages may appear. + /* + * During allocating of suspend pagedir, new cold pages may appear. * Kill them. */ drain_local_pages(NULL); @@ -1918,12 +2019,14 @@ static int init_header(struct swsusp_info *info) } /** - * pack_pfns - pfns corresponding to the set bits found in the bitmap @bm - * are stored in the array @buf[] (1 page at a time) + * pack_pfns - Prepare PFNs for saving. + * @bm: Memory bitmap. + * @buf: Memory buffer to store the PFNs in. + * + * PFNs corresponding to set bits in @bm are stored in the area of memory + * pointed to by @buf (1 page at a time). */ - -static inline void -pack_pfns(unsigned long *buf, struct memory_bitmap *bm) +static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm) { int j; @@ -1937,22 +2040,21 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm) } /** - * snapshot_read_next - used for reading the system memory snapshot. + * snapshot_read_next - Get the address to read the next image page from. + * @handle: Snapshot handle to be used for the reading. * - * On the first call to it @handle should point to a zeroed - * snapshot_handle structure. The structure gets updated and a pointer - * to it should be passed to this function every next time. + * On the first call, @handle should point to a zeroed snapshot_handle + * structure. The structure gets populated then and a pointer to it should be + * passed to this function every next time. * - * On success the function returns a positive number. Then, the caller - * is allowed to read up to the returned number of bytes from the memory - * location computed by the data_of() macro. + * On success, the function returns a positive number. Then, the caller + * is allowed to read up to the returned number of bytes from the memory + * location computed by the data_of() macro. * - * The function returns 0 to indicate the end of data stream condition, - * and a negative number is returned on error. In such cases the - * structure pointed to by @handle is not updated and should not be used - * any more. + * The function returns 0 to indicate the end of the data stream condition, + * and negative numbers are returned on errors. If that happens, the structure + * pointed to by @handle is not updated and should not be used any more. */ - int snapshot_read_next(struct snapshot_handle *handle) { if (handle->cur > nr_meta_pages + nr_copy_pages) @@ -1981,7 +2083,8 @@ int snapshot_read_next(struct snapshot_handle *handle) page = pfn_to_page(memory_bm_next_pfn(©_bm)); if (PageHighMem(page)) { - /* Highmem pages are copied to the buffer, + /* + * Highmem pages are copied to the buffer, * because we can't return with a kmapped * highmem page (we may not be called again). */ @@ -1999,53 +2102,41 @@ int snapshot_read_next(struct snapshot_handle *handle) return PAGE_SIZE; } -/** - * mark_unsafe_pages - mark the pages that cannot be used for storing - * the image during resume, because they conflict with the pages that - * had been used before suspend - */ - -static int mark_unsafe_pages(struct memory_bitmap *bm) +static void duplicate_memory_bitmap(struct memory_bitmap *dst, + struct memory_bitmap *src) { - struct zone *zone; - unsigned long pfn, max_zone_pfn; + unsigned long pfn; - /* Clear page flags */ - for_each_populated_zone(zone) { - max_zone_pfn = zone_end_pfn(zone); - for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) - if (pfn_valid(pfn)) - swsusp_unset_page_free(pfn_to_page(pfn)); + memory_bm_position_reset(src); + pfn = memory_bm_next_pfn(src); + while (pfn != BM_END_OF_MAP) { + memory_bm_set_bit(dst, pfn); + pfn = memory_bm_next_pfn(src); } - - /* Mark pages that correspond to the "original" pfns as "unsafe" */ - memory_bm_position_reset(bm); - do { - pfn = memory_bm_next_pfn(bm); - if (likely(pfn != BM_END_OF_MAP)) { - if (likely(pfn_valid(pfn))) - swsusp_set_page_free(pfn_to_page(pfn)); - else - return -EFAULT; - } - } while (pfn != BM_END_OF_MAP); - - allocated_unsafe_pages = 0; - - return 0; } -static void -duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src) +/** + * mark_unsafe_pages - Mark pages that were used before hibernation. + * + * Mark the pages that cannot be used for storing the image during restoration, + * because they conflict with the pages that had been used before hibernation. + */ +static void mark_unsafe_pages(struct memory_bitmap *bm) { unsigned long pfn; - memory_bm_position_reset(src); - pfn = memory_bm_next_pfn(src); + /* Clear the "free"/"unsafe" bit for all PFNs */ + memory_bm_position_reset(free_pages_map); + pfn = memory_bm_next_pfn(free_pages_map); while (pfn != BM_END_OF_MAP) { - memory_bm_set_bit(dst, pfn); - pfn = memory_bm_next_pfn(src); + memory_bm_clear_current(free_pages_map); + pfn = memory_bm_next_pfn(free_pages_map); } + + /* Mark pages that correspond to the "original" PFNs as "unsafe" */ + duplicate_memory_bitmap(free_pages_map, bm); + + allocated_unsafe_pages = 0; } static int check_header(struct swsusp_info *info) @@ -2063,11 +2154,9 @@ static int check_header(struct swsusp_info *info) } /** - * load header - check the image header and copy data from it + * load header - Check the image header and copy the data from it. */ - -static int -load_header(struct swsusp_info *info) +static int load_header(struct swsusp_info *info) { int error; @@ -2081,8 +2170,12 @@ load_header(struct swsusp_info *info) } /** - * unpack_orig_pfns - for each element of @buf[] (1 page at a time) set - * the corresponding bit in the memory bitmap @bm + * unpack_orig_pfns - Set bits corresponding to given PFNs in a memory bitmap. + * @bm: Memory bitmap. + * @buf: Area of memory containing the PFNs. + * + * For each element of the array pointed to by @buf (1 page at a time), set the + * corresponding bit in @bm. */ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) { @@ -2095,7 +2188,7 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) /* Extract and buffer page key for data page (s390 only). */ page_key_memorize(buf + j); - if (memory_bm_pfn_present(bm, buf[j])) + if (pfn_valid(buf[j]) && memory_bm_pfn_present(bm, buf[j])) memory_bm_set_bit(bm, buf[j]); else return -EFAULT; @@ -2104,13 +2197,9 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) return 0; } -/* List of "safe" pages that may be used to store data loaded from the suspend - * image - */ -static struct linked_page *safe_pages_list; - #ifdef CONFIG_HIGHMEM -/* struct highmem_pbe is used for creating the list of highmem pages that +/* + * struct highmem_pbe is used for creating the list of highmem pages that * should be restored atomically during the resume from disk, because the page * frames they have occupied before the suspend are in use. */ @@ -2120,7 +2209,8 @@ struct highmem_pbe { struct highmem_pbe *next; }; -/* List of highmem PBEs needed for restoring the highmem pages that were +/* + * List of highmem PBEs needed for restoring the highmem pages that were * allocated before the suspend and included in the suspend image, but have * also been allocated by the "resume" kernel, so their contents cannot be * written directly to their "original" page frames. @@ -2128,11 +2218,11 @@ struct highmem_pbe { static struct highmem_pbe *highmem_pblist; /** - * count_highmem_image_pages - compute the number of highmem pages in the - * suspend image. The bits in the memory bitmap @bm that correspond to the - * image pages are assumed to be set. + * count_highmem_image_pages - Compute the number of highmem pages in the image. + * @bm: Memory bitmap. + * + * The bits in @bm that correspond to image pages are assumed to be set. */ - static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { unsigned long pfn; @@ -2149,24 +2239,25 @@ static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) return cnt; } -/** - * prepare_highmem_image - try to allocate as many highmem pages as - * there are highmem image pages (@nr_highmem_p points to the variable - * containing the number of highmem image pages). The pages that are - * "safe" (ie. will not be overwritten when the suspend image is - * restored) have the corresponding bits set in @bm (it must be - * unitialized). - * - * NOTE: This function should not be called if there are no highmem - * image pages. - */ - static unsigned int safe_highmem_pages; static struct memory_bitmap *safe_highmem_bm; -static int -prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) +/** + * prepare_highmem_image - Allocate memory for loading highmem data from image. + * @bm: Pointer to an uninitialized memory bitmap structure. + * @nr_highmem_p: Pointer to the number of highmem image pages. + * + * Try to allocate as many highmem pages as there are highmem image pages + * (@nr_highmem_p points to the variable containing the number of highmem image + * pages). The pages that are "safe" (ie. will not be overwritten when the + * hibernation image is restored entirely) have the corresponding bits set in + * @bm (it must be unitialized). + * + * NOTE: This function should not be called if there are no highmem image pages. + */ +static int prepare_highmem_image(struct memory_bitmap *bm, + unsigned int *nr_highmem_p) { unsigned int to_alloc; @@ -2201,39 +2292,42 @@ prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) return 0; } +static struct page *last_highmem_page; + /** - * get_highmem_page_buffer - for given highmem image page find the buffer - * that suspend_write_next() should set for its caller to write to. + * get_highmem_page_buffer - Prepare a buffer to store a highmem image page. * - * If the page is to be saved to its "original" page frame or a copy of - * the page is to be made in the highmem, @buffer is returned. Otherwise, - * the copy of the page is to be made in normal memory, so the address of - * the copy is returned. + * For a given highmem image page get a buffer that suspend_write_next() should + * return to its caller to write to. * - * If @buffer is returned, the caller of suspend_write_next() will write - * the page's contents to @buffer, so they will have to be copied to the - * right location on the next call to suspend_write_next() and it is done - * with the help of copy_last_highmem_page(). For this purpose, if - * @buffer is returned, @last_highmem page is set to the page to which - * the data will have to be copied from @buffer. + * If the page is to be saved to its "original" page frame or a copy of + * the page is to be made in the highmem, @buffer is returned. Otherwise, + * the copy of the page is to be made in normal memory, so the address of + * the copy is returned. + * + * If @buffer is returned, the caller of suspend_write_next() will write + * the page's contents to @buffer, so they will have to be copied to the + * right location on the next call to suspend_write_next() and it is done + * with the help of copy_last_highmem_page(). For this purpose, if + * @buffer is returned, @last_highmem_page is set to the page to which + * the data will have to be copied from @buffer. */ - -static struct page *last_highmem_page; - -static void * -get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) +static void *get_highmem_page_buffer(struct page *page, + struct chain_allocator *ca) { struct highmem_pbe *pbe; void *kaddr; if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) { - /* We have allocated the "original" page frame and we can + /* + * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ last_highmem_page = page; return buffer; } - /* The "original" page frame has not been allocated and we have to + /* + * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct highmem_pbe)); @@ -2263,11 +2357,12 @@ get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) } /** - * copy_last_highmem_page - copy the contents of a highmem image from - * @buffer, where the caller of snapshot_write_next() has place them, - * to the right location represented by @last_highmem_page . + * copy_last_highmem_page - Copy most the most recent highmem image page. + * + * Copy the contents of a highmem image from @buffer, where the caller of + * snapshot_write_next() has stored them, to the right location represented by + * @last_highmem_page . */ - static void copy_last_highmem_page(void) { if (last_highmem_page) { @@ -2294,17 +2389,13 @@ static inline void free_highmem_data(void) free_image_page(buffer, PG_UNSAFE_CLEAR); } #else -static unsigned int -count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } +static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } -static inline int -prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) -{ - return 0; -} +static inline int prepare_highmem_image(struct memory_bitmap *bm, + unsigned int *nr_highmem_p) { return 0; } -static inline void * -get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) +static inline void *get_highmem_page_buffer(struct page *page, + struct chain_allocator *ca) { return ERR_PTR(-EINVAL); } @@ -2314,27 +2405,27 @@ static inline int last_highmem_page_copied(void) { return 1; } static inline void free_highmem_data(void) {} #endif /* CONFIG_HIGHMEM */ +#define PBES_PER_LINKED_PAGE (LINKED_PAGE_DATA_SIZE / sizeof(struct pbe)) + /** - * prepare_image - use the memory bitmap @bm to mark the pages that will - * be overwritten in the process of restoring the system memory state - * from the suspend image ("unsafe" pages) and allocate memory for the - * image. + * prepare_image - Make room for loading hibernation image. + * @new_bm: Unitialized memory bitmap structure. + * @bm: Memory bitmap with unsafe pages marked. + * + * Use @bm to mark the pages that will be overwritten in the process of + * restoring the system memory state from the suspend image ("unsafe" pages) + * and allocate memory for the image. * - * The idea is to allocate a new memory bitmap first and then allocate - * as many pages as needed for the image data, but not to assign these - * pages to specific tasks initially. Instead, we just mark them as - * allocated and create a lists of "safe" pages that will be used - * later. On systems with high memory a list of "safe" highmem pages is - * also created. + * The idea is to allocate a new memory bitmap first and then allocate + * as many pages as needed for image data, but without specifying what those + * pages will be used for just yet. Instead, we mark them all as allocated and + * create a lists of "safe" pages to be used later. On systems with high + * memory a list of "safe" highmem pages is created too. */ - -#define PBES_PER_LINKED_PAGE (LINKED_PAGE_DATA_SIZE / sizeof(struct pbe)) - -static int -prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) +static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) { unsigned int nr_pages, nr_highmem; - struct linked_page *sp_list, *lp; + struct linked_page *lp; int error; /* If there is no highmem, the buffer will not be necessary */ @@ -2342,9 +2433,7 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) buffer = NULL; nr_highmem = count_highmem_image_pages(bm); - error = mark_unsafe_pages(bm); - if (error) - goto Free; + mark_unsafe_pages(bm); error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE); if (error) @@ -2357,14 +2446,15 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) if (error) goto Free; } - /* Reserve some safe pages for potential later use. + /* + * Reserve some safe pages for potential later use. * * NOTE: This way we make sure there will be enough safe pages for the * chain_alloc() in get_buffer(). It is a bit wasteful, but * nr_copy_pages cannot be greater than 50% of the memory anyway. + * + * nr_copy_pages cannot be less than allocated_unsafe_pages too. */ - sp_list = NULL; - /* nr_copy_pages cannot be lesser than allocated_unsafe_pages */ nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages; nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE); while (nr_pages > 0) { @@ -2373,12 +2463,11 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) error = -ENOMEM; goto Free; } - lp->next = sp_list; - sp_list = lp; + lp->next = safe_pages_list; + safe_pages_list = lp; nr_pages--; } /* Preallocate memory for the image */ - safe_pages_list = NULL; nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages; while (nr_pages > 0) { lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC); @@ -2396,12 +2485,6 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) swsusp_set_page_free(virt_to_page(lp)); nr_pages--; } - /* Free the reserved safe pages so that chain_alloc() can use them */ - while (sp_list) { - lp = sp_list->next; - free_image_page(sp_list, PG_UNSAFE_CLEAR); - sp_list = lp; - } return 0; Free: @@ -2410,10 +2493,11 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) } /** - * get_buffer - compute the address that snapshot_write_next() should - * set for its caller to write to. + * get_buffer - Get the address to store the next image data page. + * + * Get the address that snapshot_write_next() should return to its caller to + * write to. */ - static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) { struct pbe *pbe; @@ -2428,12 +2512,14 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) return get_highmem_page_buffer(page, ca); if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) - /* We have allocated the "original" page frame and we can + /* + * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ return page_address(page); - /* The "original" page frame has not been allocated and we have to + /* + * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct pbe)); @@ -2450,22 +2536,21 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) } /** - * snapshot_write_next - used for writing the system memory snapshot. + * snapshot_write_next - Get the address to store the next image page. + * @handle: Snapshot handle structure to guide the writing. * - * On the first call to it @handle should point to a zeroed - * snapshot_handle structure. The structure gets updated and a pointer - * to it should be passed to this function every next time. + * On the first call, @handle should point to a zeroed snapshot_handle + * structure. The structure gets populated then and a pointer to it should be + * passed to this function every next time. * - * On success the function returns a positive number. Then, the caller - * is allowed to write up to the returned number of bytes to the memory - * location computed by the data_of() macro. + * On success, the function returns a positive number. Then, the caller + * is allowed to write up to the returned number of bytes to the memory + * location computed by the data_of() macro. * - * The function returns 0 to indicate the "end of file" condition, - * and a negative number is returned on error. In such cases the - * structure pointed to by @handle is not updated and should not be used - * any more. + * The function returns 0 to indicate the "end of file" condition. Negative + * numbers are returned on errors, in which cases the structure pointed to by + * @handle is not updated and should not be used any more. */ - int snapshot_write_next(struct snapshot_handle *handle) { static struct chain_allocator ca; @@ -2491,6 +2576,8 @@ int snapshot_write_next(struct snapshot_handle *handle) if (error) return error; + safe_pages_list = NULL; + error = memory_bm_create(©_bm, GFP_ATOMIC, PG_ANY); if (error) return error; @@ -2500,6 +2587,7 @@ int snapshot_write_next(struct snapshot_handle *handle) if (error) return error; + hibernate_restore_protection_begin(); } else if (handle->cur <= nr_meta_pages + 1) { error = unpack_orig_pfns(buffer, ©_bm); if (error) @@ -2522,6 +2610,7 @@ int snapshot_write_next(struct snapshot_handle *handle) copy_last_highmem_page(); /* Restore page key for data page (s390 only). */ page_key_write(handle->buffer); + hibernate_restore_protect_page(handle->buffer); handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); @@ -2533,22 +2622,23 @@ int snapshot_write_next(struct snapshot_handle *handle) } /** - * snapshot_write_finalize - must be called after the last call to - * snapshot_write_next() in case the last page in the image happens - * to be a highmem page and its contents should be stored in the - * highmem. Additionally, it releases the memory that will not be - * used any more. + * snapshot_write_finalize - Complete the loading of a hibernation image. + * + * Must be called after the last call to snapshot_write_next() in case the last + * page in the image happens to be a highmem page and its contents should be + * stored in highmem. Additionally, it recycles bitmap memory that's not + * necessary any more. */ - void snapshot_write_finalize(struct snapshot_handle *handle) { copy_last_highmem_page(); /* Restore page key for data page (s390 only). */ page_key_write(handle->buffer); page_key_free(); - /* Free only if we have loaded the image entirely */ + hibernate_restore_protect_page(handle->buffer); + /* Do that only if we have loaded the image entirely */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) { - memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR); + memory_bm_recycle(&orig_bm); free_highmem_data(); } } @@ -2561,8 +2651,8 @@ int snapshot_image_loaded(struct snapshot_handle *handle) #ifdef CONFIG_HIGHMEM /* Assumes that @buf is ready and points to a "safe" page */ -static inline void -swap_two_pages_data(struct page *p1, struct page *p2, void *buf) +static inline void swap_two_pages_data(struct page *p1, struct page *p2, + void *buf) { void *kaddr1, *kaddr2; @@ -2576,15 +2666,15 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf) } /** - * restore_highmem - for each highmem page that was allocated before - * the suspend and included in the suspend image, and also has been - * allocated by the "resume" kernel swap its current (ie. "before - * resume") contents with the previous (ie. "before suspend") one. + * restore_highmem - Put highmem image pages into their original locations. + * + * For each highmem page that was in use before hibernation and is included in + * the image, and also has been allocated by the "restore" kernel, swap its + * current contents with the previous (ie. "before hibernation") ones. * - * If the resume eventually fails, we can call this function once - * again and restore the "before resume" highmem state. + * If the restore eventually fails, we can call this function once again and + * restore the highmem state as seen by the restore kernel. */ - int restore_highmem(void) { struct highmem_pbe *pbe = highmem_pblist; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 5b70d64b871e..0acab9d7f96f 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -266,16 +266,18 @@ static int suspend_test(int level) */ static int suspend_prepare(suspend_state_t state) { - int error; + int error, nr_calls = 0; if (!sleep_state_supported(state)) return -EPERM; pm_prepare_console(); - error = pm_notifier_call_chain(PM_SUSPEND_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Finish; + } trace_suspend_resume(TPS("freeze_processes"), 0, true); error = suspend_freeze_processes(); @@ -286,7 +288,7 @@ static int suspend_prepare(suspend_state_t state) suspend_stats.failed_freeze++; dpm_save_failed_step(SUSPEND_FREEZE); Finish: - pm_notifier_call_chain(PM_POST_SUSPEND); + __pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL); pm_restore_console(); return error; } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 160e1006640d..51cef8432154 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -348,6 +348,12 @@ static int swsusp_swap_check(void) if (res < 0) blkdev_put(hib_resume_bdev, FMODE_WRITE); + /* + * Update the resume device to the one actually used, + * so the test_resume mode can use it in case it is + * invoked from hibernate() to test the snapshot. + */ + swsusp_resume_device = hib_resume_bdev->bd_dev; return res; } diff --git a/kernel/power/user.c b/kernel/power/user.c index 526e8911460a..35310b627388 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -47,7 +47,7 @@ atomic_t snapshot_device_available = ATOMIC_INIT(1); static int snapshot_open(struct inode *inode, struct file *filp) { struct snapshot_data *data; - int error; + int error, nr_calls = 0; if (!hibernation_available()) return -EPERM; @@ -74,9 +74,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) swap_type_of(swsusp_resume_device, 0, NULL) : -1; data->mode = O_RDONLY; data->free_bitmaps = false; - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); + error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); if (error) - pm_notifier_call_chain(PM_POST_HIBERNATION); + __pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL); } else { /* * Resuming. We may need to wait for the image device to @@ -86,13 +86,15 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->swap = -1; data->mode = O_WRONLY; - error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls); if (!error) { error = create_basic_memory_bitmaps(); data->free_bitmaps = !error; - } + } else + nr_calls--; + if (error) - pm_notifier_call_chain(PM_POST_RESTORE); + __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); } if (error) atomic_inc(&snapshot_device_available); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 017d5394f5dc..97ee9ac7e97c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1536,7 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for (;;) { /* Any allowed, online CPU? */ for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { - if (!cpu_active(dest_cpu)) + if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu)) + continue; + if (!cpu_online(dest_cpu)) continue; goto out; } @@ -2535,10 +2537,9 @@ void wake_up_new_task(struct task_struct *p) */ set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif - /* Post initialize new task's util average when its cfs_rq is set */ + rq = __task_rq_lock(p, &rf); post_init_entity_util_avg(&p->se); - rq = __task_rq_lock(p, &rf); activate_task(rq, p, 0); p->on_rq = TASK_ON_RQ_QUEUED; trace_sched_wakeup_new(p); @@ -5148,14 +5149,16 @@ void show_state_filter(unsigned long state_filter) /* * reset the NMI-timeout, listing all files on a slow * console might take a lot of time: + * Also, reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI. */ touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); if (!state_filter || (p->state & state_filter)) sched_show_task(p); } - touch_all_softlockup_watchdogs(); - #ifdef CONFIG_SCHED_DEBUG if (!state_filter) sysrq_sched_debug_show(); @@ -5391,13 +5394,15 @@ void idle_task_exit(void) /* * Since this CPU is going 'away' for a while, fold any nr_active delta * we might have. Assumes we're called after migrate_tasks() so that the - * nr_active count is stable. + * nr_active count is stable. We need to take the teardown thread which + * is calling this into account, so we hand in adjust = 1 to the load + * calculation. * * Also see the comment "Global load-average calculations". */ static void calc_load_migrate(struct rq *rq) { - long delta = calc_load_fold_active(rq); + long delta = calc_load_fold_active(rq, 1); if (delta) atomic_long_add(delta, &calc_load_tasks); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 218f8e83db73..c8c5d2d48424 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -735,8 +735,6 @@ void post_init_entity_util_avg(struct sched_entity *se) } } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); -static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); #else void init_entity_runnable_average(struct sched_entity *se) { @@ -2499,28 +2497,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) #ifdef CONFIG_FAIR_GROUP_SCHED # ifdef CONFIG_SMP -static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) +static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) { - long tg_weight; + long tg_weight, load, shares; /* - * Use this CPU's real-time load instead of the last load contribution - * as the updating of the contribution is delayed, and we will use the - * the real-time load to calc the share. See update_tg_load_avg(). + * This really should be: cfs_rq->avg.load_avg, but instead we use + * cfs_rq->load.weight, which is its upper bound. This helps ramp up + * the shares for small weight interactive tasks. */ - tg_weight = atomic_long_read(&tg->load_avg); - tg_weight -= cfs_rq->tg_load_avg_contrib; - tg_weight += cfs_rq->load.weight; + load = scale_load_down(cfs_rq->load.weight); - return tg_weight; -} - -static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) -{ - long tg_weight, load, shares; + tg_weight = atomic_long_read(&tg->load_avg); - tg_weight = calc_tg_weight(tg, cfs_rq); - load = cfs_rq->load.weight; + /* Ensure tg_weight >= load */ + tg_weight -= cfs_rq->tg_load_avg_contrib; + tg_weight += load; shares = (tg->shares * load); if (tg_weight) @@ -2539,6 +2531,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) return tg->shares; } # endif /* CONFIG_SMP */ + static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { @@ -2904,6 +2897,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) } } +/* + * Unsigned subtract and clamp on underflow. + * + * Explicitly do a load-store to ensure the intermediate value never hits + * memory. This allows lockless observations without ever seeing the negative + * values. + */ +#define sub_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + typeof(*ptr) val = (_val); \ + typeof(*ptr) res, var = READ_ONCE(*ptr); \ + res = var - val; \ + if (res > var) \ + res = 0; \ + WRITE_ONCE(*ptr, res); \ +} while (0) + /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) @@ -2913,15 +2923,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) if (atomic_long_read(&cfs_rq->removed_load_avg)) { s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); - sa->load_avg = max_t(long, sa->load_avg - r, 0); - sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); + sub_positive(&sa->load_avg, r); + sub_positive(&sa->load_sum, r * LOAD_AVG_MAX); removed_load = 1; } if (atomic_long_read(&cfs_rq->removed_util_avg)) { long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0); - sa->util_avg = max_t(long, sa->util_avg - r, 0); - sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0); + sub_positive(&sa->util_avg, r); + sub_positive(&sa->util_sum, r * LOAD_AVG_MAX); removed_util = 1; } @@ -2994,10 +3004,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s &se->avg, se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL); - cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0); - cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0); - cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0); - cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0); + sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); + sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum); + sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); + sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); cfs_rq_util_change(cfs_rq); } @@ -3246,7 +3256,7 @@ static inline void check_schedstat_required(void) trace_sched_stat_iowait_enabled() || trace_sched_stat_blocked_enabled() || trace_sched_stat_runtime_enabled()) { - pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, " + printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, " "stat_blocked and stat_runtime require the " "kernel parameter schedstats=enabled or " "kernel.sched_schedstats=1\n"); @@ -4185,6 +4195,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) if (!cfs_bandwidth_used()) return; + /* Synchronize hierarchical throttle counter: */ + if (unlikely(!cfs_rq->throttle_uptodate)) { + struct rq *rq = rq_of(cfs_rq); + struct cfs_rq *pcfs_rq; + struct task_group *tg; + + cfs_rq->throttle_uptodate = 1; + + /* Get closest up-to-date node, because leaves go first: */ + for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) { + pcfs_rq = tg->cfs_rq[cpu_of(rq)]; + if (pcfs_rq->throttle_uptodate) + break; + } + if (tg) { + cfs_rq->throttle_count = pcfs_rq->throttle_count; + cfs_rq->throttled_clock_task = rq_clock_task(rq); + } + } + /* an active group must be handled by the update_curr()->put() path */ if (!cfs_rq->runtime_enabled || cfs_rq->curr) return; @@ -4500,15 +4530,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { + /* Avoid re-evaluating load for this entity: */ + se = parent_entity(se); /* * Bias pick_next to pick a task from this cfs_rq, as * p is sleeping when it is within its sched_slice. */ - if (task_sleep && parent_entity(se)) - set_next_buddy(parent_entity(se)); - - /* avoid re-evaluating load for this entity */ - se = parent_entity(se); + if (task_sleep && se && !throttled_hierarchy(cfs_rq)) + set_next_buddy(se); break; } flags |= DEQUEUE_SLEEP; @@ -4910,19 +4939,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) return wl; for_each_sched_entity(se) { - long w, W; + struct cfs_rq *cfs_rq = se->my_q; + long W, w = cfs_rq_load_avg(cfs_rq); - tg = se->my_q->tg; + tg = cfs_rq->tg; /* * W = @wg + \Sum rw_j */ - W = wg + calc_tg_weight(tg, se->my_q); + W = wg + atomic_long_read(&tg->load_avg); + + /* Ensure \Sum rw_j >= rw_i */ + W -= cfs_rq->tg_load_avg_contrib; + W += w; /* * w = rw_i + @wl */ - w = cfs_rq_load_avg(se->my_q) + wl; + w += wl; /* * wl = S * s'_i; see (2) @@ -8496,8 +8530,9 @@ void free_fair_sched_group(struct task_group *tg) int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) { - struct cfs_rq *cfs_rq; struct sched_entity *se; + struct cfs_rq *cfs_rq; + struct rq *rq; int i; tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); @@ -8512,6 +8547,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_bandwidth(tg_cfs_bandwidth(tg)); for_each_possible_cpu(i) { + rq = cpu_rq(i); + cfs_rq = kzalloc_node(sizeof(struct cfs_rq), GFP_KERNEL, cpu_to_node(i)); if (!cfs_rq) @@ -8525,7 +8562,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_rq(cfs_rq); init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); init_entity_runnable_average(se); + + raw_spin_lock_irq(&rq->lock); post_init_entity_util_avg(se); + raw_spin_unlock_irq(&rq->lock); } return 1; diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index b0b93fd33af9..a2d6eb71f06b 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -78,11 +78,11 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) loads[2] = (avenrun[2] + offset) << shift; } -long calc_load_fold_active(struct rq *this_rq) +long calc_load_fold_active(struct rq *this_rq, long adjust) { long nr_active, delta = 0; - nr_active = this_rq->nr_running; + nr_active = this_rq->nr_running - adjust; nr_active += (long)this_rq->nr_uninterruptible; if (nr_active != this_rq->calc_load_active) { @@ -188,7 +188,7 @@ void calc_load_enter_idle(void) * We're going into NOHZ mode, if there's any pending delta, fold it * into the pending idle delta. */ - delta = calc_load_fold_active(this_rq); + delta = calc_load_fold_active(this_rq, 0); if (delta) { int idx = calc_load_write_idx(); @@ -389,7 +389,7 @@ void calc_global_load_tick(struct rq *this_rq) if (time_before(jiffies, this_rq->calc_load_update)) return; - delta = calc_load_fold_active(this_rq); + delta = calc_load_fold_active(this_rq, 0); if (delta) atomic_long_add(delta, &calc_load_tasks); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 72f1f3087b04..898c0d2f18fe 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -28,7 +28,7 @@ extern unsigned long calc_load_update; extern atomic_long_t calc_load_tasks; extern void calc_global_load_tick(struct rq *this_rq); -extern long calc_load_fold_active(struct rq *this_rq); +extern long calc_load_fold_active(struct rq *this_rq, long adjust); #ifdef CONFIG_SMP extern void cpu_load_update_active(struct rq *this_rq); @@ -437,7 +437,7 @@ struct cfs_rq { u64 throttled_clock, throttled_clock_task; u64 throttled_clock_task_time; - int throttled, throttle_count; + int throttled, throttle_count, throttle_uptodate; struct list_head throttled_list; #endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 1cafba860b08..39008d78927a 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -777,6 +777,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) timer->it.cpu.expires = 0; sample_to_timespec(timer->it_clock, timer->it.cpu.expires, &itp->it_value); + return; } else { cpu_timer_sample_group(timer->it_clock, p, &now); unlock_task_sighand(p, &flags); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 720b7bb01d43..26f603da7e26 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -209,6 +209,10 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) event->pmu->count) return -EINVAL; + if (unlikely(event->attr.type != PERF_TYPE_HARDWARE && + event->attr.type != PERF_TYPE_RAW)) + return -EINVAL; + /* * we don't know if the function is run successfully by the * return value. It can be judged in other places, such as @@ -349,7 +353,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func } /* bpf+kprobe programs can access fields of 'struct pt_regs' */ -static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type) +static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type) { /* check bounds */ if (off < 0 || off >= sizeof(struct pt_regs)) @@ -427,7 +432,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) } } -static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type) +static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index f96f0383f6c6..ad1d6164e946 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -36,6 +36,10 @@ struct trace_bprintk_fmt { static inline struct trace_bprintk_fmt *lookup_format(const char *fmt) { struct trace_bprintk_fmt *pos; + + if (!fmt) + return ERR_PTR(-EINVAL); + list_for_each_entry(pos, &trace_bprintk_fmt_list, list) { if (!strcmp(pos->fmt, fmt)) return pos; @@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end) for (iter = start; iter < end; iter++) { struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter); if (tb_fmt) { - *iter = tb_fmt->fmt; + if (!IS_ERR(tb_fmt)) + *iter = tb_fmt->fmt; continue; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e1c0e996b5ae..d12bd958077e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4369,8 +4369,8 @@ static void show_pwq(struct pool_workqueue *pwq) /** * show_workqueue_state - dump workqueue state * - * Called from a sysrq handler and prints out all busy workqueues and - * pools. + * Called from a sysrq handler or try_to_freeze_tasks() and prints out + * all busy workqueues and pools. */ void show_workqueue_state(void) { @@ -4600,15 +4600,11 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; - /* is @cpu the only online CPU? */ cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); - if (cpumask_weight(&cpumask) != 1) - return; /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, - pool->attrs->cpumask) < 0); + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } /* diff --git a/mm/compaction.c b/mm/compaction.c index 1427366ad673..7bc04778f84d 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -441,25 +441,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, /* Found a free page, break it into order-0 pages */ isolated = split_free_page(page); + if (!isolated) + break; + total_isolated += isolated; + cc->nr_freepages += isolated; for (i = 0; i < isolated; i++) { list_add(&page->lru, freelist); page++; } - - /* If a page was split, advance to the end of it */ - if (isolated) { - cc->nr_freepages += isolated; - if (!strict && - cc->nr_migratepages <= cc->nr_freepages) { - blockpfn += isolated; - break; - } - - blockpfn += isolated - 1; - cursor += isolated - 1; - continue; + if (!strict && cc->nr_migratepages <= cc->nr_freepages) { + blockpfn += isolated; + break; } + /* Advance to the end of split page */ + blockpfn += isolated - 1; + cursor += isolated - 1; + continue; isolate_fail: if (strict) @@ -469,6 +467,9 @@ isolate_fail: } + if (locked) + spin_unlock_irqrestore(&cc->zone->lock, flags); + /* * There is a tiny chance that we have read bogus compound_order(), * so be careful to not go outside of the pageblock. @@ -490,9 +491,6 @@ isolate_fail: if (strict && blockpfn < end_pfn) total_isolated = 0; - if (locked) - spin_unlock_irqrestore(&cc->zone->lock, flags); - /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) update_pageblock_skip(cc, valid_page, total_isolated, false); @@ -1011,7 +1009,6 @@ static void isolate_freepages(struct compact_control *cc) block_end_pfn = block_start_pfn, block_start_pfn -= pageblock_nr_pages, isolate_start_pfn = block_start_pfn) { - /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need @@ -1035,32 +1032,30 @@ static void isolate_freepages(struct compact_control *cc) continue; /* Found a block suitable for isolating free pages from. */ - isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, freelist, false); + isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, + freelist, false); /* - * If we isolated enough freepages, or aborted due to async - * compaction being contended, terminate the loop. - * Remember where the free scanner should restart next time, - * which is where isolate_freepages_block() left off. - * But if it scanned the whole pageblock, isolate_start_pfn - * now points at block_end_pfn, which is the start of the next - * pageblock. - * In that case we will however want to restart at the start - * of the previous pageblock. + * If we isolated enough freepages, or aborted due to lock + * contention, terminate. */ if ((cc->nr_freepages >= cc->nr_migratepages) || cc->contended) { - if (isolate_start_pfn >= block_end_pfn) + if (isolate_start_pfn >= block_end_pfn) { + /* + * Restart at previous pageblock if more + * freepages can be isolated next time. + */ isolate_start_pfn = block_start_pfn - pageblock_nr_pages; + } break; - } else { + } else if (isolate_start_pfn < block_end_pfn) { /* - * isolate_freepages_block() should not terminate - * prematurely unless contended, or isolated enough + * If isolation failed early, do not continue + * needlessly. */ - VM_BUG_ON(isolate_start_pfn < block_end_pfn); + break; } } diff --git a/mm/filemap.c b/mm/filemap.c index 00ae878b2a38..20f3b1f33f0e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2186,7 +2186,7 @@ repeat: if (file->f_ra.mmap_miss > 0) file->f_ra.mmap_miss--; addr = address + (page->index - vmf->pgoff) * PAGE_SIZE; - do_set_pte(vma, addr, page, pte, false, false, true); + do_set_pte(vma, addr, page, pte, false, false); unlock_page(page); goto next; unlock: diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9ed58530f695..343a2b7e57aa 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1624,14 +1624,9 @@ int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (next - addr != HPAGE_PMD_SIZE) { get_page(page); spin_unlock(ptl); - if (split_huge_page(page)) { - put_page(page); - unlock_page(page); - goto out_unlocked; - } + split_huge_page(page); put_page(page); unlock_page(page); - ret = 1; goto out_unlocked; } @@ -2989,7 +2984,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze) + unsigned long address, bool freeze, struct page *page) { spinlock_t *ptl; struct mm_struct *mm = vma->vm_mm; @@ -2997,8 +2992,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); ptl = pmd_lock(mm, pmd); + + /* + * If caller asks to setup a migration entries, we need a page to check + * pmd against. Otherwise we can end up replacing wrong page. + */ + VM_BUG_ON(freeze && !page); + if (page && page != pmd_page(*pmd)) + goto out; + if (pmd_trans_huge(*pmd)) { - struct page *page = pmd_page(*pmd); + page = pmd_page(*pmd); if (PageMlocked(page)) clear_page_mlock(page); } else if (!pmd_devmap(*pmd)) @@ -3025,24 +3029,8 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, return; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd))) - return; - /* - * If caller asks to setup a migration entries, we need a page to check - * pmd against. Otherwise we can end up replacing wrong page. - */ - VM_BUG_ON(freeze && !page); - if (page && page != pmd_page(*pmd)) - return; - - /* - * Caller holds the mmap_sem write mode or the anon_vma lock, - * so a huge pmd cannot materialize from under us (khugepaged - * holds both the mmap_sem write mode and the anon_vma lock - * write mode). - */ - __split_huge_pmd(vma, pmd, address, freeze); + __split_huge_pmd(vma, pmd, address, freeze, page); } void vma_adjust_trans_huge(struct vm_area_struct *vma, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 388c2bb9b55c..addfe4accc07 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1030,6 +1030,7 @@ static void destroy_compound_gigantic_page(struct page *page, int nr_pages = 1 << order; struct page *p = page + 1; + atomic_set(compound_mapcount_ptr(page), 0); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { clear_compound_head(p); set_page_refcounted(p); @@ -3382,7 +3383,7 @@ retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { - page_move_anon_rmap(old_page, vma, address); + page_move_anon_rmap(old_page, vma); set_huge_ptep_writable(vma, address, ptep); return 0; } @@ -4228,7 +4229,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr); if (spte) { - mm_inc_nr_pmds(mm); get_page(virt_to_page(spte)); break; } @@ -4243,9 +4243,9 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); + mm_inc_nr_pmds(mm); } else { put_page(virt_to_page(spte)); - mm_inc_nr_pmds(mm); } spin_unlock(ptl); out: diff --git a/mm/internal.h b/mm/internal.h index a37e5b6f9d25..2524ec880e24 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -24,7 +24,8 @@ */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ - __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC) + __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ + __GFP_ATOMIC) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 28439acda6ec..6845f9294696 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -508,7 +508,7 @@ void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags) kasan_kmalloc(cache, object, cache->object_size, flags); } -void kasan_poison_slab_free(struct kmem_cache *cache, void *object) +static void kasan_poison_slab_free(struct kmem_cache *cache, void *object) { unsigned long size = cache->object_size; unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE); @@ -626,7 +626,7 @@ void kasan_krealloc(const void *object, size_t size, gfp_t flags) kasan_kmalloc(page->slab_cache, object, size, flags); } -void kasan_kfree(void *ptr) +void kasan_poison_kfree(void *ptr) { struct page *page; @@ -636,7 +636,7 @@ void kasan_kfree(void *ptr) kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page), KASAN_FREE_PAGE); else - kasan_slab_free(page->slab_cache, ptr); + kasan_poison_slab_free(page->slab_cache, ptr); } void kasan_kfree_large(const void *ptr) diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 4973505a9bdd..65793f150d1f 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -238,30 +238,23 @@ static void qlist_move_cache(struct qlist_head *from, struct qlist_head *to, struct kmem_cache *cache) { - struct qlist_node *prev = NULL, *curr; + struct qlist_node *curr; if (unlikely(qlist_empty(from))) return; curr = from->head; + qlist_init(from); while (curr) { - struct qlist_node *qlink = curr; - struct kmem_cache *obj_cache = qlink_to_cache(qlink); - - if (obj_cache == cache) { - if (unlikely(from->head == qlink)) { - from->head = curr->next; - prev = curr; - } else - prev->next = curr->next; - if (unlikely(from->tail == qlink)) - from->tail = curr->next; - from->bytes -= cache->size; - qlist_put(to, qlink, cache->size); - } else { - prev = curr; - } - curr = curr->next; + struct qlist_node *next = curr->next; + struct kmem_cache *obj_cache = qlink_to_cache(curr); + + if (obj_cache == cache) + qlist_put(to, curr, obj_cache->size); + else + qlist_put(from, curr, obj_cache->size); + + curr = next; } } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index e6429926e957..04320d3adbef 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -307,8 +307,10 @@ static void hex_dump_object(struct seq_file *seq, len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE); seq_printf(seq, " hex dump (first %zu bytes):\n", len); + kasan_disable_current(); seq_hex_dump(seq, " ", DUMP_PREFIX_NONE, HEX_ROW_SIZE, HEX_GROUP_SIZE, ptr, len, HEX_ASCII); + kasan_enable_current(); } /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 75e74408cc8f..5339c89dff63 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4057,6 +4057,60 @@ static struct cftype mem_cgroup_legacy_files[] = { { }, /* terminate */ }; +/* + * Private memory cgroup IDR + * + * Swap-out records and page cache shadow entries need to store memcg + * references in constrained space, so we maintain an ID space that is + * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of + * memory-controlled cgroups to 64k. + * + * However, there usually are many references to the oflline CSS after + * the cgroup has been destroyed, such as page cache or reclaimable + * slab objects, that don't need to hang on to the ID. We want to keep + * those dead CSS from occupying IDs, or we might quickly exhaust the + * relatively small ID space and prevent the creation of new cgroups + * even when there are much fewer than 64k cgroups - possibly none. + * + * Maintain a private 16-bit ID space for memcg, and allow the ID to + * be freed and recycled when it's no longer needed, which is usually + * when the CSS is offlined. + * + * The only exception to that are records of swapped out tmpfs/shmem + * pages that need to be attributed to live ancestors on swapin. But + * those references are manageable from userspace. + */ + +static DEFINE_IDR(mem_cgroup_idr); + +static void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + atomic_inc(&memcg->id.ref); +} + +static void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + if (atomic_dec_and_test(&memcg->id.ref)) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + + /* Memcg ID pins CSS */ + css_put(&memcg->css); + } +} + +/** + * mem_cgroup_from_id - look up a memcg from a memcg id + * @id: the memcg id to look up + * + * Caller must hold rcu_read_lock(). + */ +struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return idr_find(&mem_cgroup_idr, id); +} + static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -4116,6 +4170,12 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (!memcg) return NULL; + memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, + 1, MEM_CGROUP_ID_MAX, + GFP_KERNEL); + if (memcg->id.id < 0) + goto fail; + memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!memcg->stat) goto fail; @@ -4142,8 +4202,11 @@ static struct mem_cgroup *mem_cgroup_alloc(void) #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); #endif + idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; fail: + if (memcg->id.id > 0) + idr_remove(&mem_cgroup_idr, memcg->id.id); mem_cgroup_free(memcg); return NULL; } @@ -4203,15 +4266,14 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) return &memcg->css; fail: mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(-ENOMEM); } -static int -mem_cgroup_css_online(struct cgroup_subsys_state *css) +static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { - if (css->id > MEM_CGROUP_ID_MAX) - return -ENOSPC; - + /* Online state pins memcg ID, memcg ID pins CSS */ + mem_cgroup_id_get(mem_cgroup_from_css(css)); + css_get(css); return 0; } @@ -4234,6 +4296,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_offline_kmem(memcg); wb_memcg_offline(memcg); + + mem_cgroup_id_put(memcg); } static void mem_cgroup_css_released(struct cgroup_subsys_state *css) @@ -5544,6 +5608,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) struct mem_cgroup *memcg; unsigned int nr_pages; bool compound; + unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); @@ -5574,10 +5639,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, false); - local_irq_disable(); + local_irq_save(flags); mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); memcg_check_events(memcg, newpage); - local_irq_enable(); + local_irq_restore(flags); } DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); @@ -5755,6 +5820,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); @@ -5773,6 +5839,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON(!irqs_disabled()); mem_cgroup_charge_statistics(memcg, page, false, -1); memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put(&memcg->css); } /* @@ -5803,11 +5872,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) !page_counter_try_charge(&memcg->swap, 1, &counter)) return -ENOMEM; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); - css_get(&memcg->css); return 0; } @@ -5836,7 +5905,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) page_counter_uncharge(&memcg->memsw, 1); } mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); + mem_cgroup_id_put(memcg); } rcu_read_unlock(); } diff --git a/mm/memory.c b/mm/memory.c index 15322b73636b..9e046819e619 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2399,8 +2399,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * Protected against the rmap code by * the page lock. */ - page_move_anon_rmap(compound_head(old_page), - vma, address); + page_move_anon_rmap(old_page, vma); } unlock_page(old_page); return wp_page_reuse(mm, vma, address, page_table, ptl, @@ -2877,7 +2876,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, * vm_ops->map_pages. */ void do_set_pte(struct vm_area_struct *vma, unsigned long address, - struct page *page, pte_t *pte, bool write, bool anon, bool old) + struct page *page, pte_t *pte, bool write, bool anon) { pte_t entry; @@ -2885,8 +2884,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, entry = mk_pte(page, vma->vm_page_prot); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (old) - entry = pte_mkold(entry); if (anon) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address, false); @@ -2900,16 +2897,8 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, update_mmu_cache(vma, address, pte); } -/* - * If architecture emulates "accessed" or "young" bit without HW support, - * there is no much gain with fault_around. - */ static unsigned long fault_around_bytes __read_mostly = -#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS - PAGE_SIZE; -#else rounddown_pow_of_two(65536); -#endif #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) @@ -3032,20 +3021,9 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!pte_same(*pte, orig_pte)) - goto unlock_out; do_fault_around(vma, address, pte, pgoff, flags); - /* Check if the fault is handled by faultaround */ - if (!pte_same(*pte, orig_pte)) { - /* - * Faultaround produce old pte, but the pte we've - * handler fault for should be young. - */ - pte_t entry = pte_mkyoung(*pte); - if (ptep_set_access_flags(vma, address, pte, entry, 0)) - update_mmu_cache(vma, address, pte); + if (!pte_same(*pte, orig_pte)) goto unlock_out; - } pte_unmap_unlock(pte, ptl); } @@ -3060,7 +3038,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, put_page(fault_page); return ret; } - do_set_pte(vma, address, fault_page, pte, false, false, false); + do_set_pte(vma, address, fault_page, pte, false, false); unlock_page(fault_page); unlock_out: pte_unmap_unlock(pte, ptl); @@ -3111,7 +3089,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, } goto uncharge_out; } - do_set_pte(vma, address, new_page, pte, true, true, false); + do_set_pte(vma, address, new_page, pte, true, true); mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); pte_unmap_unlock(pte, ptl); @@ -3164,7 +3142,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, put_page(fault_page); return ret; } - do_set_pte(vma, address, fault_page, pte, true, false, false); + do_set_pte(vma, address, fault_page, pte, true, false); pte_unmap_unlock(pte, ptl); if (set_page_dirty(fault_page)) diff --git a/mm/mempool.c b/mm/mempool.c index 9e075f829d0d..8f65464da5de 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -104,20 +104,16 @@ static inline void poison_element(mempool_t *pool, void *element) static void kasan_poison_element(mempool_t *pool, void *element) { - if (pool->alloc == mempool_alloc_slab) - kasan_poison_slab_free(pool->pool_data, element); - if (pool->alloc == mempool_kmalloc) - kasan_kfree(element); + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + kasan_poison_kfree(element); if (pool->alloc == mempool_alloc_pages) kasan_free_pages(element, (unsigned long)pool->pool_data); } static void kasan_unpoison_element(mempool_t *pool, void *element, gfp_t flags) { - if (pool->alloc == mempool_alloc_slab) - kasan_slab_alloc(pool->pool_data, element, flags); - if (pool->alloc == mempool_kmalloc) - kasan_krealloc(element, (size_t)pool->pool_data, flags); + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + kasan_unpoison_slab(element); if (pool->alloc == mempool_alloc_pages) kasan_alloc_pages(element, (unsigned long)pool->pool_data); } diff --git a/mm/migrate.c b/mm/migrate.c index 9baf41c877ff..bd3fdc202e8b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -431,6 +431,7 @@ int migrate_page_move_mapping(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } +EXPORT_SYMBOL(migrate_page_move_mapping); /* * The expected number of remaining references is the same as that @@ -586,6 +587,7 @@ void migrate_page_copy(struct page *newpage, struct page *page) mem_cgroup_migrate(page, newpage); } +EXPORT_SYMBOL(migrate_page_copy); /************************************************************ * Migration functions diff --git a/mm/oom_kill.c b/mm/oom_kill.c index acbc432d1a52..ddf74487f848 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -474,13 +474,8 @@ static bool __oom_reap_task(struct task_struct *tsk) p = find_lock_task_mm(tsk); if (!p) goto unlock_oom; - mm = p->mm; - if (!atomic_inc_not_zero(&mm->mm_users)) { - task_unlock(p); - goto unlock_oom; - } - + atomic_inc(&mm->mm_users); task_unlock(p); if (!down_read_trylock(&mm->mmap_sem)) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6903b695ebae..8b3e1341b754 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -286,7 +286,9 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat) /* Returns true if the struct page for the pfn is uninitialised */ static inline bool __meminit early_page_uninitialised(unsigned long pfn) { - if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn) + int nid = early_pfn_to_nid(pfn); + + if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) return true; return false; @@ -1273,7 +1275,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn) spin_lock(&early_pfn_lock); nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); if (nid < 0) - nid = 0; + nid = first_online_node; spin_unlock(&early_pfn_lock); return nid; diff --git a/mm/page_owner.c b/mm/page_owner.c index c6cda3e36212..fedeba88c9cb 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -207,13 +207,15 @@ void __dump_page_owner(struct page *page) .nr_entries = page_ext->nr_entries, .entries = &page_ext->trace_entries[0], }; - gfp_t gfp_mask = page_ext->gfp_mask; - int mt = gfpflags_to_migratetype(gfp_mask); + gfp_t gfp_mask; + int mt; if (unlikely(!page_ext)) { pr_alert("There is not page extension available.\n"); return; } + gfp_mask = page_ext->gfp_mask; + mt = gfpflags_to_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not active (free page?)\n"); diff --git a/mm/percpu.c b/mm/percpu.c index 0c59684f1ff2..9903830aaebb 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -112,7 +112,7 @@ struct pcpu_chunk { int map_used; /* # of map entries used before the sentry */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ - struct work_struct map_extend_work;/* async ->map[] extension */ + struct list_head map_extend_list;/* on pcpu_map_extend_chunks */ void *data; /* chunk data */ int first_free; /* no free below this */ @@ -162,10 +162,13 @@ static struct pcpu_chunk *pcpu_reserved_chunk; static int pcpu_reserved_chunk_limit; static DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ -static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop */ +static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ +/* chunks which need their map areas extended, protected by pcpu_lock */ +static LIST_HEAD(pcpu_map_extend_chunks); + /* * The number of empty populated pages, protected by pcpu_lock. The * reserved chunk doesn't contribute to the count. @@ -395,13 +398,19 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic) { int margin, new_alloc; + lockdep_assert_held(&pcpu_lock); + if (is_atomic) { margin = 3; if (chunk->map_alloc < - chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW && - pcpu_async_enabled) - schedule_work(&chunk->map_extend_work); + chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW) { + if (list_empty(&chunk->map_extend_list)) { + list_add_tail(&chunk->map_extend_list, + &pcpu_map_extend_chunks); + pcpu_schedule_balance_work(); + } + } } else { margin = PCPU_ATOMIC_MAP_MARGIN_HIGH; } @@ -435,6 +444,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc) size_t old_size = 0, new_size = new_alloc * sizeof(new[0]); unsigned long flags; + lockdep_assert_held(&pcpu_alloc_mutex); + new = pcpu_mem_zalloc(new_size); if (!new) return -ENOMEM; @@ -467,20 +478,6 @@ out_unlock: return 0; } -static void pcpu_map_extend_workfn(struct work_struct *work) -{ - struct pcpu_chunk *chunk = container_of(work, struct pcpu_chunk, - map_extend_work); - int new_alloc; - - spin_lock_irq(&pcpu_lock); - new_alloc = pcpu_need_to_extend(chunk, false); - spin_unlock_irq(&pcpu_lock); - - if (new_alloc) - pcpu_extend_area_map(chunk, new_alloc); -} - /** * pcpu_fit_in_area - try to fit the requested allocation in a candidate area * @chunk: chunk the candidate area belongs to @@ -740,7 +737,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) chunk->map_used = 1; INIT_LIST_HEAD(&chunk->list); - INIT_WORK(&chunk->map_extend_work, pcpu_map_extend_workfn); + INIT_LIST_HEAD(&chunk->map_extend_list); chunk->free_size = pcpu_unit_size; chunk->contig_hint = pcpu_unit_size; @@ -895,6 +892,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, return NULL; } + if (!is_atomic) + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ @@ -967,12 +967,9 @@ restart: if (is_atomic) goto fail; - mutex_lock(&pcpu_alloc_mutex); - if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { chunk = pcpu_create_chunk(); if (!chunk) { - mutex_unlock(&pcpu_alloc_mutex); err = "failed to allocate new chunk"; goto fail; } @@ -983,7 +980,6 @@ restart: spin_lock_irqsave(&pcpu_lock, flags); } - mutex_unlock(&pcpu_alloc_mutex); goto restart; area_found: @@ -993,8 +989,6 @@ area_found: if (!is_atomic) { int page_start, page_end, rs, re; - mutex_lock(&pcpu_alloc_mutex); - page_start = PFN_DOWN(off); page_end = PFN_UP(off + size); @@ -1005,7 +999,6 @@ area_found: spin_lock_irqsave(&pcpu_lock, flags); if (ret) { - mutex_unlock(&pcpu_alloc_mutex); pcpu_free_area(chunk, off, &occ_pages); err = "failed to populate"; goto fail_unlock; @@ -1045,6 +1038,8 @@ fail: /* see the flag handling in pcpu_blance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); + } else { + mutex_unlock(&pcpu_alloc_mutex); } return NULL; } @@ -1129,6 +1124,7 @@ static void pcpu_balance_workfn(struct work_struct *work) if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; + list_del_init(&chunk->map_extend_list); list_move(&chunk->list, &to_free); } @@ -1146,6 +1142,25 @@ static void pcpu_balance_workfn(struct work_struct *work) pcpu_destroy_chunk(chunk); } + /* service chunks which requested async area map extension */ + do { + int new_alloc = 0; + + spin_lock_irq(&pcpu_lock); + + chunk = list_first_entry_or_null(&pcpu_map_extend_chunks, + struct pcpu_chunk, map_extend_list); + if (chunk) { + list_del_init(&chunk->map_extend_list); + new_alloc = pcpu_need_to_extend(chunk, false); + } + + spin_unlock_irq(&pcpu_lock); + + if (new_alloc) + pcpu_extend_area_map(chunk, new_alloc); + } while (chunk); + /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic @@ -1644,7 +1659,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, */ schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&schunk->list); - INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn); + INIT_LIST_HEAD(&schunk->map_extend_list); schunk->base_addr = base_addr; schunk->map = smap; schunk->map_alloc = ARRAY_SIZE(smap); @@ -1673,7 +1688,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, if (dyn_size) { dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&dchunk->list); - INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn); + INIT_LIST_HEAD(&dchunk->map_extend_list); dchunk->base_addr = base_addr; dchunk->map = dmap; dchunk->map_alloc = ARRAY_SIZE(dmap); diff --git a/mm/rmap.c b/mm/rmap.c index 0ea5d9071b32..701b93fea2a0 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1084,23 +1084,20 @@ EXPORT_SYMBOL_GPL(page_mkclean); * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to - * @address: the user virtual address mapped * * When a page belongs exclusively to one process after a COW event, * that page can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling * processes. */ -void page_move_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) +void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + page = compound_head(page); + VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_VMA(!anon_vma, vma); - if (IS_ENABLED(CONFIG_DEBUG_VM) && PageTransHuge(page)) - address &= HPAGE_PMD_MASK; - VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* @@ -1427,7 +1424,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, goto out; } - pte = page_check_address(page, mm, address, &ptl, 0); + pte = page_check_address(page, mm, address, &ptl, + PageTransCompound(page)); if (!pte) goto out; diff --git a/mm/shmem.c b/mm/shmem.c index a36144909b28..171dee7a131f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2225,9 +2225,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, error = shmem_getpage(inode, index, &page, SGP_FALLOC); if (error) { /* Remove the !PageUptodate pages we added */ - shmem_undo_range(inode, - (loff_t)start << PAGE_SHIFT, - (loff_t)index << PAGE_SHIFT, true); + if (index > start) { + shmem_undo_range(inode, + (loff_t)start << PAGE_SHIFT, + ((loff_t)index << PAGE_SHIFT) - 1, true); + } goto undone; } diff --git a/mm/slab_common.c b/mm/slab_common.c index a65dad7fdcd1..82317abb03ed 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -526,8 +526,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, goto out_unlock; cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); - cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - css->id, memcg_name_buf); + cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name, + css->serial_nr, memcg_name_buf); if (!cache_name) goto out_unlock; diff --git a/mm/swap.c b/mm/swap.c index 59f5fafa6e1f..90530ff8ed16 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -242,7 +242,7 @@ void rotate_reclaimable_page(struct page *page) get_page(page); local_irq_save(flags); pvec = this_cpu_ptr(&lru_rotate_pvecs); - if (!pagevec_add(pvec, page)) + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_move_tail(pvec); local_irq_restore(flags); } @@ -296,7 +296,7 @@ void activate_page(struct page *page) struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); get_page(page); - if (!pagevec_add(pvec, page)) + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); put_cpu_var(activate_page_pvecs); } @@ -391,9 +391,8 @@ static void __lru_cache_add(struct page *page) struct pagevec *pvec = &get_cpu_var(lru_add_pvec); get_page(page); - if (!pagevec_space(pvec)) + if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); - pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } @@ -628,7 +627,7 @@ void deactivate_file_page(struct page *page) if (likely(get_page_unless_zero(page))) { struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); - if (!pagevec_add(pvec, page)) + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); put_cpu_var(lru_deactivate_file_pvecs); } @@ -648,7 +647,7 @@ void deactivate_page(struct page *page) struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); get_page(page); - if (!pagevec_add(pvec, page)) + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); put_cpu_var(lru_deactivate_pvecs); } diff --git a/mm/workingset.c b/mm/workingset.c index 8a75f8d2916a..577277546d98 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -491,7 +491,7 @@ static int __init workingset_init(void) max_order = fls_long(totalram_pages - 1); if (max_order > timestamp_bits) bucket_order = max_order - timestamp_bits; - printk("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", + pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 86ae75b77390..516b0e73263c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -146,10 +146,12 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) { - /* TODO: gotta make sure the underlying layer can handle it, - * maybe an IFF_VLAN_CAPABLE flag for devices? - */ - if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu) + struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + unsigned int max_mtu = real_dev->mtu; + + if (netif_reduces_vlan_mtu(real_dev)) + max_mtu -= VLAN_HLEN; + if (max_mtu < new_mtu) return -ERANGE; dev->mtu = new_mtu; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c92b52f37d38..1270207f3d7c 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,6 +118,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev; + unsigned int max_mtu; __be16 proto; int err; @@ -144,9 +145,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + max_mtu = netif_reduces_vlan_mtu(real_dev) ? real_dev->mtu - VLAN_HLEN : + real_dev->mtu; if (!tb[IFLA_MTU]) - dev->mtu = real_dev->mtu; - else if (dev->mtu > real_dev->mtu) + dev->mtu = max_mtu; + else if (dev->mtu > max_mtu) return -EINVAL; err = vlan_changelink(dev, tb, data); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index fbd0acf80b13..2fdebabbfacd 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -976,7 +976,8 @@ static int ax25_release(struct socket *sock) release_sock(sk); ax25_disconnect(ax25, 0); lock_sock(sk); - ax25_destroy_socket(ax25); + if (!sock_flag(ax25->sk, SOCK_DESTROY)) + ax25_destroy_socket(ax25); break; case AX25_STATE_3: diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c index 951cd57bb07d..5237dff6941d 100644 --- a/net/ax25/ax25_ds_timer.c +++ b/net/ax25/ax25_ds_timer.c @@ -102,6 +102,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25) switch (ax25->state) { case AX25_STATE_0: + case AX25_STATE_2: /* Magic here: If we listen() and a new link dies before it is accepted() it isn't 'dead' so doesn't get removed. */ if (!sk || sock_flag(sk, SOCK_DESTROY) || @@ -111,6 +112,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25) sock_hold(sk); ax25_destroy_socket(ax25); bh_unlock_sock(sk); + /* Ungrab socket and destroy it */ sock_put(sk); } else ax25_destroy_socket(ax25); @@ -213,7 +215,8 @@ void ax25_ds_t1_timeout(ax25_cb *ax25) case AX25_STATE_2: if (ax25->n2count == ax25->n2) { ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); - ax25_disconnect(ax25, ETIMEDOUT); + if (!sock_flag(ax25->sk, SOCK_DESTROY)) + ax25_disconnect(ax25, ETIMEDOUT); return; } else { ax25->n2count++; diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c index 004467c9e6e1..2c0d6ef66f9d 100644 --- a/net/ax25/ax25_std_timer.c +++ b/net/ax25/ax25_std_timer.c @@ -38,6 +38,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25) switch (ax25->state) { case AX25_STATE_0: + case AX25_STATE_2: /* Magic here: If we listen() and a new link dies before it is accepted() it isn't 'dead' so doesn't get removed. */ if (!sk || sock_flag(sk, SOCK_DESTROY) || @@ -47,6 +48,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25) sock_hold(sk); ax25_destroy_socket(ax25); bh_unlock_sock(sk); + /* Ungrab socket and destroy it */ sock_put(sk); } else ax25_destroy_socket(ax25); @@ -144,7 +146,8 @@ void ax25_std_t1timer_expiry(ax25_cb *ax25) case AX25_STATE_2: if (ax25->n2count == ax25->n2) { ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); - ax25_disconnect(ax25, ETIMEDOUT); + if (!sock_flag(ax25->sk, SOCK_DESTROY)) + ax25_disconnect(ax25, ETIMEDOUT); return; } else { ax25->n2count++; diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index 3b78e8473a01..655a7d4c96e1 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -264,7 +264,8 @@ void ax25_disconnect(ax25_cb *ax25, int reason) { ax25_clear_queues(ax25); - ax25_stop_heartbeat(ax25); + if (!sock_flag(ax25->sk, SOCK_DESTROY)) + ax25_stop_heartbeat(ax25); ax25_stop_t1timer(ax25); ax25_stop_t2timer(ax25); ax25_stop_t3timer(ax25); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 748a9ead7ce5..825a5cdf4382 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -177,10 +177,21 @@ static void batadv_backbone_gw_put(struct batadv_bla_backbone_gw *backbone_gw) static void batadv_claim_release(struct kref *ref) { struct batadv_bla_claim *claim; + struct batadv_bla_backbone_gw *old_backbone_gw; claim = container_of(ref, struct batadv_bla_claim, refcount); - batadv_backbone_gw_put(claim->backbone_gw); + spin_lock_bh(&claim->backbone_lock); + old_backbone_gw = claim->backbone_gw; + claim->backbone_gw = NULL; + spin_unlock_bh(&claim->backbone_lock); + + spin_lock_bh(&old_backbone_gw->crc_lock); + old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&old_backbone_gw->crc_lock); + + batadv_backbone_gw_put(old_backbone_gw); + kfree_rcu(claim, rcu); } @@ -418,9 +429,12 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, break; } - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb) + goto out; + } skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, soft_iface); @@ -674,8 +688,10 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid, struct batadv_bla_backbone_gw *backbone_gw) { + struct batadv_bla_backbone_gw *old_backbone_gw; struct batadv_bla_claim *claim; struct batadv_bla_claim search_claim; + bool remove_crc = false; int hash_added; ether_addr_copy(search_claim.addr, mac); @@ -689,8 +705,10 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, return; ether_addr_copy(claim->addr, mac); + spin_lock_init(&claim->backbone_lock); claim->vid = vid; claim->lasttime = jiffies; + kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; kref_init(&claim->refcount); @@ -718,15 +736,26 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, "bla_add_claim(): changing ownership for %pM, vid %d\n", mac, BATADV_PRINT_VID(vid)); - spin_lock_bh(&claim->backbone_gw->crc_lock); - claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); - spin_unlock_bh(&claim->backbone_gw->crc_lock); - batadv_backbone_gw_put(claim->backbone_gw); + remove_crc = true; } - /* set (new) backbone gw */ + + /* replace backbone_gw atomically and adjust reference counters */ + spin_lock_bh(&claim->backbone_lock); + old_backbone_gw = claim->backbone_gw; kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; + spin_unlock_bh(&claim->backbone_lock); + if (remove_crc) { + /* remove claim address from old backbone_gw */ + spin_lock_bh(&old_backbone_gw->crc_lock); + old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); + spin_unlock_bh(&old_backbone_gw->crc_lock); + } + + batadv_backbone_gw_put(old_backbone_gw); + + /* add claim address to new backbone_gw */ spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&backbone_gw->crc_lock); @@ -736,6 +765,26 @@ claim_free_ref: batadv_claim_put(claim); } +/** + * batadv_bla_claim_get_backbone_gw - Get valid reference for backbone_gw of + * claim + * @claim: claim whose backbone_gw should be returned + * + * Return: valid reference to claim::backbone_gw + */ +static struct batadv_bla_backbone_gw * +batadv_bla_claim_get_backbone_gw(struct batadv_bla_claim *claim) +{ + struct batadv_bla_backbone_gw *backbone_gw; + + spin_lock_bh(&claim->backbone_lock); + backbone_gw = claim->backbone_gw; + kref_get(&backbone_gw->refcount); + spin_unlock_bh(&claim->backbone_lock); + + return backbone_gw; +} + /** * batadv_bla_del_claim - delete a claim from the claim hash * @bat_priv: the bat priv with all the soft interface information @@ -760,10 +809,6 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, batadv_choose_claim, claim); batadv_claim_put(claim); /* reference from the hash is gone */ - spin_lock_bh(&claim->backbone_gw->crc_lock); - claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); - spin_unlock_bh(&claim->backbone_gw->crc_lock); - /* don't need the reference from hash_find() anymore */ batadv_claim_put(claim); } @@ -1216,6 +1261,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, int now) { + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1230,14 +1276,17 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; - if (!batadv_compare_eth(claim->backbone_gw->orig, + + if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) - continue; + goto skip; + if (!batadv_has_timed_out(claim->lasttime, BATADV_BLA_CLAIM_TIMEOUT)) - continue; + goto skip; batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_purge_claims(): %pM, vid %d, time out\n", @@ -1245,8 +1294,10 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, purge_now: batadv_handle_unclaim(bat_priv, primary_if, - claim->backbone_gw->orig, + backbone_gw->orig, claim->addr, claim->vid); +skip: + batadv_backbone_gw_put(backbone_gw); } rcu_read_unlock(); } @@ -1757,9 +1808,11 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, bool is_bcast) { + struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; + bool own_claim; bool ret; ethhdr = eth_hdr(skb); @@ -1794,8 +1847,12 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, } /* if it is our own claim ... */ - if (batadv_compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + own_claim = batadv_compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr); + batadv_backbone_gw_put(backbone_gw); + + if (own_claim) { /* ... allow it in any case */ claim->lasttime = jiffies; goto allow; @@ -1859,7 +1916,9 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, { struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; + bool client_roamed; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); @@ -1889,8 +1948,12 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto allow; /* check if we are responsible. */ - if (batadv_compare_eth(claim->backbone_gw->orig, - primary_if->net_dev->dev_addr)) { + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + client_roamed = batadv_compare_eth(backbone_gw->orig, + primary_if->net_dev->dev_addr); + batadv_backbone_gw_put(backbone_gw); + + if (client_roamed) { /* if yes, the client has roamed and we have * to unclaim it. */ @@ -1938,6 +2001,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->bla.claim_hash; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; struct hlist_head *head; @@ -1962,17 +2026,21 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { - is_own = batadv_compare_eth(claim->backbone_gw->orig, + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); + + is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); - spin_lock_bh(&claim->backbone_gw->crc_lock); - backbone_crc = claim->backbone_gw->crc; - spin_unlock_bh(&claim->backbone_gw->crc_lock); + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n", claim->addr, BATADV_PRINT_VID(claim->vid), - claim->backbone_gw->orig, + backbone_gw->orig, (is_own ? 'x' : ' '), backbone_crc); + + batadv_backbone_gw_put(backbone_gw); } rcu_read_unlock(); } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 278800a99c69..aee3b3991471 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1009,9 +1009,12 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, if (!skb_new) goto out; - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb_new) + goto out; + } skb_reset_mac_header(skb_new); skb_new->protocol = eth_type_trans(skb_new, @@ -1089,9 +1092,12 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, */ skb_reset_mac_header(skb_new); - if (vid & BATADV_VLAN_HAS_TAG) + if (vid & BATADV_VLAN_HAS_TAG) { skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); + if (!skb_new) + goto out; + } /* To preserve backwards compatibility, the node has choose the outgoing * format based on the incoming request packet type. The assumption is diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 7f51bc2c06eb..ab8c4f9738fe 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -765,6 +765,8 @@ static void batadv_orig_node_release(struct kref *ref) struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_orig_node_vlan *vlan; + struct batadv_orig_ifinfo *last_candidate; orig_node = container_of(ref, struct batadv_orig_node, refcount); @@ -782,8 +784,21 @@ static void batadv_orig_node_release(struct kref *ref) hlist_del_rcu(&orig_ifinfo->list); batadv_orig_ifinfo_put(orig_ifinfo); } + + last_candidate = orig_node->last_bonding_candidate; + orig_node->last_bonding_candidate = NULL; spin_unlock_bh(&orig_node->neigh_list_lock); + if (last_candidate) + batadv_orig_ifinfo_put(last_candidate); + + spin_lock_bh(&orig_node->vlan_list_lock); + hlist_for_each_entry_safe(vlan, node_tmp, &orig_node->vlan_list, list) { + hlist_del_rcu(&vlan->list); + batadv_orig_node_vlan_put(vlan); + } + spin_unlock_bh(&orig_node->vlan_list_lock); + /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index e3857ed4057f..bfac086b4d01 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -374,6 +374,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, if (skb_cow(skb, ETH_HLEN) < 0) goto out; + ethhdr = eth_hdr(skb); icmph = (struct batadv_icmp_header *)skb->data; icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmph; if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN) @@ -454,6 +455,29 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, return 0; } +/** + * batadv_last_bonding_replace - Replace last_bonding_candidate of orig_node + * @orig_node: originator node whose bonding candidates should be replaced + * @new_candidate: new bonding candidate or NULL + */ +static void +batadv_last_bonding_replace(struct batadv_orig_node *orig_node, + struct batadv_orig_ifinfo *new_candidate) +{ + struct batadv_orig_ifinfo *old_candidate; + + spin_lock_bh(&orig_node->neigh_list_lock); + old_candidate = orig_node->last_bonding_candidate; + + if (new_candidate) + kref_get(&new_candidate->refcount); + orig_node->last_bonding_candidate = new_candidate; + spin_unlock_bh(&orig_node->neigh_list_lock); + + if (old_candidate) + batadv_orig_ifinfo_put(old_candidate); +} + /** * batadv_find_router - find a suitable router for this originator * @bat_priv: the bat priv with all the soft interface information @@ -561,10 +585,6 @@ next: } rcu_read_unlock(); - /* last_bonding_candidate is reset below, remove the old reference. */ - if (orig_node->last_bonding_candidate) - batadv_orig_ifinfo_put(orig_node->last_bonding_candidate); - /* After finding candidates, handle the three cases: * 1) there is a next candidate, use that * 2) there is no next candidate, use the first of the list @@ -573,21 +593,28 @@ next: if (next_candidate) { batadv_neigh_node_put(router); - /* remove references to first candidate, we don't need it. */ - if (first_candidate) { - batadv_neigh_node_put(first_candidate_router); - batadv_orig_ifinfo_put(first_candidate); - } + kref_get(&next_candidate_router->refcount); router = next_candidate_router; - orig_node->last_bonding_candidate = next_candidate; + batadv_last_bonding_replace(orig_node, next_candidate); } else if (first_candidate) { batadv_neigh_node_put(router); - /* refcounting has already been done in the loop above. */ + kref_get(&first_candidate_router->refcount); router = first_candidate_router; - orig_node->last_bonding_candidate = first_candidate; + batadv_last_bonding_replace(orig_node, first_candidate); } else { - orig_node->last_bonding_candidate = NULL; + batadv_last_bonding_replace(orig_node, NULL); + } + + /* cleanup of candidates */ + if (first_candidate) { + batadv_neigh_node_put(first_candidate_router); + batadv_orig_ifinfo_put(first_candidate); + } + + if (next_candidate) { + batadv_neigh_node_put(next_candidate_router); + batadv_orig_ifinfo_put(next_candidate); } return router; diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index f2f125684ed9..010397650fa5 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -424,8 +424,8 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig_node; orig_node = batadv_gw_get_selected_orig(bat_priv); - return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, - orig_node, vid); + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, + BATADV_P_DATA, orig_node, vid); } void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface) diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 343d2c904399..287a3879ed7e 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1033,7 +1033,9 @@ void batadv_softif_destroy_sysfs(struct net_device *soft_iface) static void batadv_softif_destroy_netlink(struct net_device *soft_iface, struct list_head *head) { + struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_hard_iface *hard_iface; + struct batadv_softif_vlan *vlan; list_for_each_entry(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface == soft_iface) @@ -1041,6 +1043,13 @@ static void batadv_softif_destroy_netlink(struct net_device *soft_iface, BATADV_IF_CLEANUP_KEEP); } + /* destroy the "untagged" VLAN */ + vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (vlan) { + batadv_softif_destroy_vlan(bat_priv, vlan); + batadv_softif_vlan_put(vlan); + } + batadv_sysfs_del_meshif(soft_iface); unregister_netdevice_queue(soft_iface, head); } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index feaf492b01ca..57ec87f37050 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -650,8 +650,10 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, /* increase the refcounter of the related vlan */ vlan = batadv_softif_vlan_get(bat_priv, vid); - if (WARN(!vlan, "adding TT local entry %pM to non-existent VLAN %d", - addr, BATADV_PRINT_VID(vid))) { + if (!vlan) { + net_ratelimited_function(batadv_info, soft_iface, + "adding TT local entry %pM to non-existent VLAN %d\n", + addr, BATADV_PRINT_VID(vid)); kfree(tt_local); tt_local = NULL; goto out; @@ -691,7 +693,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ batadv_tt_local_entry_put(tt_local); - batadv_softif_vlan_put(vlan); goto out; } @@ -2269,6 +2270,29 @@ static u32 batadv_tt_local_crc(struct batadv_priv *bat_priv, return crc; } +/** + * batadv_tt_req_node_release - free tt_req node entry + * @ref: kref pointer of the tt req_node entry + */ +static void batadv_tt_req_node_release(struct kref *ref) +{ + struct batadv_tt_req_node *tt_req_node; + + tt_req_node = container_of(ref, struct batadv_tt_req_node, refcount); + + kfree(tt_req_node); +} + +/** + * batadv_tt_req_node_put - decrement the tt_req_node refcounter and + * possibly release it + * @tt_req_node: tt_req_node to be free'd + */ +static void batadv_tt_req_node_put(struct batadv_tt_req_node *tt_req_node) +{ + kref_put(&tt_req_node->refcount, batadv_tt_req_node_release); +} + static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) { struct batadv_tt_req_node *node; @@ -2278,7 +2302,7 @@ static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { hlist_del_init(&node->list); - kfree(node); + batadv_tt_req_node_put(node); } spin_unlock_bh(&bat_priv->tt.req_list_lock); @@ -2315,7 +2339,7 @@ static void batadv_tt_req_purge(struct batadv_priv *bat_priv) if (batadv_has_timed_out(node->issued_at, BATADV_TT_REQUEST_TIMEOUT)) { hlist_del_init(&node->list); - kfree(node); + batadv_tt_req_node_put(node); } } spin_unlock_bh(&bat_priv->tt.req_list_lock); @@ -2347,9 +2371,11 @@ batadv_tt_req_node_new(struct batadv_priv *bat_priv, if (!tt_req_node) goto unlock; + kref_init(&tt_req_node->refcount); ether_addr_copy(tt_req_node->addr, orig_node->orig); tt_req_node->issued_at = jiffies; + kref_get(&tt_req_node->refcount); hlist_add_head(&tt_req_node->list, &bat_priv->tt.req_list); unlock: spin_unlock_bh(&bat_priv->tt.req_list_lock); @@ -2613,13 +2639,19 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv, out: if (primary_if) batadv_hardif_put(primary_if); + if (ret && tt_req_node) { spin_lock_bh(&bat_priv->tt.req_list_lock); - /* hlist_del_init() verifies tt_req_node still is in the list */ - hlist_del_init(&tt_req_node->list); + if (!hlist_unhashed(&tt_req_node->list)) { + hlist_del_init(&tt_req_node->list); + batadv_tt_req_node_put(tt_req_node); + } spin_unlock_bh(&bat_priv->tt.req_list_lock); - kfree(tt_req_node); } + + if (tt_req_node) + batadv_tt_req_node_put(tt_req_node); + kfree(tvlv_tt_data); return ret; } @@ -3055,7 +3087,7 @@ static void batadv_handle_tt_response(struct batadv_priv *bat_priv, if (!batadv_compare_eth(node->addr, resp_src)) continue; hlist_del_init(&node->list); - kfree(node); + batadv_tt_req_node_put(node); } spin_unlock_bh(&bat_priv->tt.req_list_lock); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 6a577f4f8ba7..74d865a4df46 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -330,7 +330,9 @@ struct batadv_orig_node { DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); u32 last_bcast_seqno; struct hlist_head neigh_list; - /* neigh_list_lock protects: neigh_list and router */ + /* neigh_list_lock protects: neigh_list, ifinfo_list, + * last_bonding_candidate and router + */ spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; @@ -1042,6 +1044,7 @@ struct batadv_bla_backbone_gw { * @addr: mac address of claimed non-mesh client * @vid: vlan id this client was detected on * @backbone_gw: pointer to backbone gw claiming this client + * @backbone_lock: lock protecting backbone_gw pointer * @lasttime: last time we heard of claim (locals only) * @hash_entry: hlist node for batadv_priv_bla::claim_hash * @refcount: number of contexts the object is used @@ -1051,6 +1054,7 @@ struct batadv_bla_claim { u8 addr[ETH_ALEN]; unsigned short vid; struct batadv_bla_backbone_gw *backbone_gw; + spinlock_t backbone_lock; /* protects backbone_gw */ unsigned long lasttime; struct hlist_node hash_entry; struct rcu_head rcu; @@ -1137,11 +1141,13 @@ struct batadv_tt_change_node { * struct batadv_tt_req_node - data to keep track of the tt requests in flight * @addr: mac address address of the originator this request was sent to * @issued_at: timestamp used for purging stale tt requests + * @refcount: number of contexts the object is used by * @list: list node for batadv_priv_tt::req_list */ struct batadv_tt_req_node { u8 addr[ETH_ALEN]; unsigned long issued_at; + struct kref refcount; struct hlist_node list; }; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 160797722228..43d2cd862bc2 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -213,8 +213,7 @@ drop: } EXPORT_SYMBOL_GPL(br_handle_frame_finish); -/* note: already called with rcu_read_lock */ -static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +static void __br_handle_local_finish(struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); u16 vid = 0; @@ -222,6 +221,14 @@ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_bu /* 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); +} + +/* note: already called with rcu_read_lock */ +static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct net_bridge_port *p = br_port_get_rcu(skb->dev); + + __br_handle_local_finish(skb); BR_INPUT_SKB_CB(skb)->brdev = p->br->dev; br_pass_frame_up(skb); @@ -274,7 +281,9 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) if (p->br->stp_enabled == BR_NO_STP || fwd_mask & (1u << dest[5])) goto forward; - break; + *pskb = skb; + __br_handle_local_finish(skb); + return RX_HANDLER_PASS; case 0x01: /* IEEE MAC (Pause) */ goto drop; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 6852f3c7009c..43844144c9c4 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -464,8 +464,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, &ip6h->saddr)) { kfree_skb(skb); + br->has_ipv6_addr = 0; return NULL; } + + br->has_ipv6_addr = 1; ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); @@ -1745,6 +1748,7 @@ void br_multicast_init(struct net_bridge *br) br->ip6_other_query.delay_time = 0; br->ip6_querier.port = NULL; #endif + br->has_ipv6_addr = 1; spin_lock_init(&br->multicast_lock); setup_timer(&br->multicast_router_timer, diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 2d25979273a6..77e7f69bf80d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -700,7 +700,7 @@ static int br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { - unsigned int mtu = ip_skb_dst_mtu(skb); + unsigned int mtu = ip_skb_dst_mtu(sk, skb); struct iphdr *iph = ip_hdr(skb); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a5343c7232bf..85e89f693589 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1273,7 +1273,7 @@ static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, struct bridge_vlan_xstats vxi; struct br_vlan_stats stats; - if (vl_idx++ < *prividx) + if (++vl_idx < *prividx) continue; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index c7fb5d7a7218..52edecf3c294 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -314,6 +314,7 @@ struct net_bridge u8 multicast_disabled:1; u8 multicast_querier:1; u8 multicast_query_use_ifaddr:1; + u8 has_ipv6_addr:1; u32 hash_elasticity; u32 hash_max; @@ -588,10 +589,22 @@ static inline bool br_multicast_is_router(struct net_bridge *br) static inline bool __br_multicast_querier_exists(struct net_bridge *br, - struct bridge_mcast_other_query *querier) + struct bridge_mcast_other_query *querier, + const bool is_ipv6) { + bool own_querier_enabled; + + if (br->multicast_querier) { + if (is_ipv6 && !br->has_ipv6_addr) + own_querier_enabled = false; + else + own_querier_enabled = true; + } else { + own_querier_enabled = false; + } + return time_is_before_jiffies(querier->delay_time) && - (br->multicast_querier || timer_pending(&querier->timer)); + (own_querier_enabled || timer_pending(&querier->timer)); } static inline bool br_multicast_querier_exists(struct net_bridge *br, @@ -599,10 +612,12 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br, { switch (eth->h_proto) { case (htons(ETH_P_IP)): - return __br_multicast_querier_exists(br, &br->ip4_other_query); + return __br_multicast_querier_exists(br, + &br->ip4_other_query, false); #if IS_ENABLED(CONFIG_IPV6) case (htons(ETH_P_IPV6)): - return __br_multicast_querier_exists(br, &br->ip6_other_query); + return __br_multicast_querier_exists(br, + &br->ip6_other_query, true); #endif default: return false; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 03062bb763b3..7e480bf75bcf 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1260,6 +1260,115 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end) return map; } +/* + * Encoding order is (new_up_client, new_state, new_weight). Need to + * apply in the (new_weight, new_state, new_up_client) order, because + * an incremental map may look like e.g. + * + * new_up_client: { osd=6, addr=... } # set osd_state and addr + * new_state: { osd=6, xorstate=EXISTS } # clear osd_state + */ +static int decode_new_up_state_weight(void **p, void *end, + struct ceph_osdmap *map) +{ + void *new_up_client; + void *new_state; + void *new_weight_end; + u32 len; + + new_up_client = *p; + ceph_decode_32_safe(p, end, len, e_inval); + len *= sizeof(u32) + sizeof(struct ceph_entity_addr); + ceph_decode_need(p, end, len, e_inval); + *p += len; + + new_state = *p; + ceph_decode_32_safe(p, end, len, e_inval); + len *= sizeof(u32) + sizeof(u8); + ceph_decode_need(p, end, len, e_inval); + *p += len; + + /* new_weight */ + ceph_decode_32_safe(p, end, len, e_inval); + while (len--) { + s32 osd; + u32 w; + + ceph_decode_need(p, end, 2*sizeof(u32), e_inval); + osd = ceph_decode_32(p); + w = ceph_decode_32(p); + BUG_ON(osd >= map->max_osd); + pr_info("osd%d weight 0x%x %s\n", osd, w, + w == CEPH_OSD_IN ? "(in)" : + (w == CEPH_OSD_OUT ? "(out)" : "")); + map->osd_weight[osd] = w; + + /* + * If we are marking in, set the EXISTS, and clear the + * AUTOOUT and NEW bits. + */ + if (w) { + map->osd_state[osd] |= CEPH_OSD_EXISTS; + map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT | + CEPH_OSD_NEW); + } + } + new_weight_end = *p; + + /* new_state (up/down) */ + *p = new_state; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + u8 xorstate; + int ret; + + osd = ceph_decode_32(p); + xorstate = ceph_decode_8(p); + if (xorstate == 0) + xorstate = CEPH_OSD_UP; + BUG_ON(osd >= map->max_osd); + if ((map->osd_state[osd] & CEPH_OSD_UP) && + (xorstate & CEPH_OSD_UP)) + pr_info("osd%d down\n", osd); + if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && + (xorstate & CEPH_OSD_EXISTS)) { + pr_info("osd%d does not exist\n", osd); + map->osd_weight[osd] = CEPH_OSD_IN; + ret = set_primary_affinity(map, osd, + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); + if (ret) + return ret; + memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr)); + map->osd_state[osd] = 0; + } else { + map->osd_state[osd] ^= xorstate; + } + } + + /* new_up_client */ + *p = new_up_client; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + struct ceph_entity_addr addr; + + osd = ceph_decode_32(p); + ceph_decode_copy(p, &addr, sizeof(addr)); + ceph_decode_addr(&addr); + BUG_ON(osd >= map->max_osd); + pr_info("osd%d up\n", osd); + map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP; + map->osd_addr[osd] = addr; + } + + *p = new_weight_end; + return 0; + +e_inval: + return -EINVAL; +} + /* * decode and apply an incremental map update. */ @@ -1358,49 +1467,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, __remove_pg_pool(&map->pg_pools, pi); } - /* new_up */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd; - struct ceph_entity_addr addr; - ceph_decode_32_safe(p, end, osd, e_inval); - ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval); - ceph_decode_addr(&addr); - pr_info("osd%d up\n", osd); - BUG_ON(osd >= map->max_osd); - map->osd_state[osd] |= CEPH_OSD_UP | CEPH_OSD_EXISTS; - map->osd_addr[osd] = addr; - } - - /* new_state */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd; - u8 xorstate; - ceph_decode_32_safe(p, end, osd, e_inval); - xorstate = **(u8 **)p; - (*p)++; /* clean flag */ - if (xorstate == 0) - xorstate = CEPH_OSD_UP; - if (xorstate & CEPH_OSD_UP) - pr_info("osd%d down\n", osd); - if (osd < map->max_osd) - map->osd_state[osd] ^= xorstate; - } - - /* new_weight */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd, off; - ceph_decode_need(p, end, sizeof(u32)*2, e_inval); - osd = ceph_decode_32(p); - off = ceph_decode_32(p); - pr_info("osd%d weight 0x%x %s\n", osd, off, - off == CEPH_OSD_IN ? "(in)" : - (off == CEPH_OSD_OUT ? "(out)" : "")); - if (osd < map->max_osd) - map->osd_weight[osd] = off; - } + /* new_up_client, new_state, new_weight */ + err = decode_new_up_state_weight(p, end, map); + if (err) + goto bad; /* new_pg_temp */ err = decode_new_pg_temp(p, end, map); diff --git a/net/core/filter.c b/net/core/filter.c index 68adb5f52110..e759d90e8cef 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -53,9 +53,10 @@ #include /** - * sk_filter - run a packet through a socket filter + * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter + * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller @@ -64,7 +65,7 @@ * be accepted or -EPERM if the packet should be tossed. * */ -int sk_filter(struct sock *sk, struct sk_buff *skb) +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { int err; struct sk_filter *filter; @@ -85,14 +86,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) filter = rcu_dereference(sk->sk_filter); if (filter) { unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); - - err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; + err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; } rcu_read_unlock(); return err; } -EXPORT_SYMBOL(sk_filter); +EXPORT_SYMBOL(sk_filter_trim_cap); static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { @@ -2085,7 +2085,8 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type) } static bool sk_filter_is_valid_access(int off, int size, - enum bpf_access_type type) + enum bpf_access_type type, + enum bpf_reg_type *reg_type) { switch (off) { case offsetof(struct __sk_buff, tc_classid): @@ -2108,7 +2109,8 @@ static bool sk_filter_is_valid_access(int off, int size, } static bool tc_cls_act_is_valid_access(int off, int size, - enum bpf_access_type type) + enum bpf_access_type type, + enum bpf_reg_type *reg_type) { if (type == BPF_WRITE) { switch (off) { @@ -2123,6 +2125,16 @@ static bool tc_cls_act_is_valid_access(int off, int size, return false; } } + + switch (off) { + case offsetof(struct __sk_buff, data): + *reg_type = PTR_TO_PACKET; + break; + case offsetof(struct __sk_buff, data_end): + *reg_type = PTR_TO_PACKET_END; + break; + } + return __is_valid_access(off, size, type); } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a669dea146c6..61ad43f61c5e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest, } EXPORT_SYMBOL(make_flow_keys_digest); +static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; + +u32 __skb_get_hash_symmetric(struct sk_buff *skb) +{ + struct flow_keys keys; + + __flow_hash_secret_init(); + + memset(&keys, 0, sizeof(keys)); + __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, + NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + return __flow_hash_from_keys(&keys, hashrnd); +} +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); + /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from @@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { }, }; +static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v4addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v6addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, +}; + static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, @@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_dissector_symmetric, + flow_keys_dissector_symmetric_keys, + ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_buf_dissector, flow_keys_buf_dissector_keys, ARRAY_SIZE(flow_keys_buf_dissector_keys)); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 29dd8cc22bbf..510cd62fcb99 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2469,13 +2469,17 @@ int neigh_xmit(int index, struct net_device *dev, tbl = neigh_tables[index]; if (!tbl) goto out; + rcu_read_lock_bh(); neigh = __neigh_lookup_noref(tbl, addr, dev); if (!neigh) neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); - if (IS_ERR(neigh)) + if (IS_ERR(neigh)) { + rcu_read_unlock_bh(); goto out_kfree_skb; + } err = neigh->output(neigh, skb); + rcu_read_unlock_bh(); } else if (index == NEIGH_LINK_TABLE) { err = dev_hard_header(skb, dev, ntohs(skb->protocol), diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f2b77e549c03..eb12d2161fb2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3015,24 +3015,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } EXPORT_SYMBOL_GPL(skb_append_pagefrags); -/** - * skb_push_rcsum - push skb and update receive checksum - * @skb: buffer to update - * @len: length of data pulled - * - * This function performs an skb_push on the packet and updates - * the CHECKSUM_COMPLETE checksum. It should be used on - * receive path processing instead of skb_push unless you know - * that the checksum difference is zero (e.g., a valid IP header) - * or you are setting ip_summed to CHECKSUM_NONE. - */ -static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) -{ - skb_push(skb, len); - skb_postpush_rcsum(skb, skb->data, len); - return skb->data; -} - /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update diff --git a/net/core/sock.c b/net/core/sock.c index 08bf97eceeb3..25dab8b60223 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -452,11 +452,12 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sock_queue_rcv_skb); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested, unsigned int trim_cap) { int rc = NET_RX_SUCCESS; - if (sk_filter(sk, skb)) + if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; @@ -492,7 +493,7 @@ discard_and_relse: kfree_skb(skb); goto out; } -EXPORT_SYMBOL(sk_receive_skb); +EXPORT_SYMBOL(__sk_receive_skb); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { @@ -1938,6 +1939,10 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; + /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ + case SCM_RIGHTS: + case SCM_CREDENTIALS: + break; default: return -EINVAL; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5c7e413a3ae4..345a3aeb8c7e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -462,7 +462,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { - __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } @@ -527,17 +527,19 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) rxiph->daddr); skb_dst_set(skb, dst_clone(dst)); + local_bh_disable(); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, rxiph->daddr, rxiph->saddr, NULL); bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { - DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - DCCP_INC_STATS(DCCP_MIB_OUTRSTS); + __DCCP_INC_STATS(DCCP_MIB_OUTSEGS); + __DCCP_INC_STATS(DCCP_MIB_OUTRSTS); } + local_bh_enable(); out: - dst_release(dst); + dst_release(dst); } static void dccp_v4_reqsk_destructor(struct request_sock *req) @@ -866,7 +868,7 @@ lookup: goto discard_and_relse; nf_reset(skb); - return sk_receive_skb(sk, skb, 1); + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index d176f4e66369..3ff137d9471d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -732,7 +732,7 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - return sk_receive_skb(sk, skb, 1) ? -1 : 0; + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index df4803437888..a796fc7cbc35 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -41,6 +41,7 @@ #include #include #include +#include #define RT_MIN_TABLE 1 @@ -150,14 +151,13 @@ static int dn_fib_count_nhs(const struct nlattr *attr) struct rtnexthop *nhp = nla_data(attr); int nhs = 0, nhlen = nla_len(attr); - while(nhlen >= (int)sizeof(struct rtnexthop)) { - if ((nhlen -= nhp->rtnh_len) < 0) - return 0; + while (rtnh_ok(nhp, nhlen)) { nhs++; - nhp = RTNH_NEXT(nhp); + nhp = rtnh_next(nhp, &nhlen); } - return nhs; + /* leftover implies invalid nexthop configuration, discard it */ + return nhlen > 0 ? 0 : nhs; } static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr, @@ -167,21 +167,24 @@ static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr, int nhlen = nla_len(attr); change_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) + int attrlen; + + if (!rtnh_ok(nhp, nhlen)) return -EINVAL; nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags; nh->nh_oif = nhp->rtnh_ifindex; nh->nh_weight = nhp->rtnh_hops + 1; - if (attrlen) { + attrlen = rtnh_attrlen(nhp); + if (attrlen > 0) { struct nlattr *gw_attr; gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY); nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0; } - nhp = RTNH_NEXT(nhp); + + nhp = rtnh_next(nhp, &nhlen); } endfor_nexthops(fi); return 0; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 477937465a20..d95631d09248 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -23,6 +23,11 @@ struct esp_skb_cb { void *tmp; }; +struct esp_output_extra { + __be32 seqhi; + u32 esphoff; +}; + #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0])) static u32 esp4_get_mtu(struct xfrm_state *x, int mtu); @@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu); * * TODO: Use spare space in skb for this where possible. */ -static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen) +static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen) { unsigned int len; - len = seqhilen; + len = extralen; len += crypto_aead_ivsize(aead); @@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen) return kmalloc(len, GFP_ATOMIC); } -static inline __be32 *esp_tmp_seqhi(void *tmp) +static inline void *esp_tmp_extra(void *tmp) { - return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32)); + return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra)); } -static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen) + +static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen) { return crypto_aead_ivsize(aead) ? - PTR_ALIGN((u8 *)tmp + seqhilen, - crypto_aead_alignmask(aead) + 1) : tmp + seqhilen; + PTR_ALIGN((u8 *)tmp + extralen, + crypto_aead_alignmask(aead) + 1) : tmp + extralen; } static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv) @@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset) { struct ip_esp_hdr *esph = (void *)(skb->data + offset); void *tmp = ESP_SKB_CB(skb)->tmp; - __be32 *seqhi = esp_tmp_seqhi(tmp); + __be32 *seqhi = esp_tmp_extra(tmp); esph->seq_no = esph->spi; esph->spi = *seqhi; @@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset) static void esp_output_restore_header(struct sk_buff *skb) { - esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32)); + void *tmp = ESP_SKB_CB(skb)->tmp; + struct esp_output_extra *extra = esp_tmp_extra(tmp); + + esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff - + sizeof(__be32)); } static void esp_output_done_esn(struct crypto_async_request *base, int err) @@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err) static int esp_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + struct esp_output_extra *extra; struct ip_esp_hdr *esph; struct crypto_aead *aead; struct aead_request *req; @@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) int tfclen; int nfrags; int assoclen; - int seqhilen; - __be32 *seqhi; + int extralen; __be64 seqno; /* skb is pure payload to encrypt */ @@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) nfrags = err; assoclen = sizeof(*esph); - seqhilen = 0; + extralen = 0; if (x->props.flags & XFRM_STATE_ESN) { - seqhilen += sizeof(__be32); - assoclen += seqhilen; + extralen += sizeof(*extra); + assoclen += sizeof(__be32); } - tmp = esp_alloc_tmp(aead, nfrags, seqhilen); + tmp = esp_alloc_tmp(aead, nfrags, extralen); if (!tmp) { err = -ENOMEM; goto error; } - seqhi = esp_tmp_seqhi(tmp); - iv = esp_tmp_iv(aead, tmp, seqhilen); + extra = esp_tmp_extra(tmp); + iv = esp_tmp_iv(aead, tmp, extralen); req = esp_tmp_req(aead, iv); sg = esp_req_sg(aead, req); @@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) * encryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = (void *)(skb_transport_header(skb) - sizeof(__be32)); - *seqhi = esph->spi; + extra->esphoff = (unsigned char *)esph - + skb_transport_header(skb); + esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4); + extra->seqhi = esph->spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi); aead_request_set_callback(req, 0, esp_output_done_esn, skb); } @@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) goto out; ESP_SKB_CB(skb)->tmp = tmp; - seqhi = esp_tmp_seqhi(tmp); + seqhi = esp_tmp_extra(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); sg = esp_req_sg(aead, req); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d09173bf9500..539fa264e67d 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; + if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + return -EINVAL; + nexthop_nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; nexthop_nh->nh_oif = rtnh->rtnh_ifindex; @@ -1003,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (fib_props[cfg->fc_type].scope > cfg->fc_scope) goto err_inval; + if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + goto err_inval; + #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 4c39f4fd332a..de1d119a4497 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -62,26 +62,26 @@ EXPORT_SYMBOL_GPL(gre_del_protocol); /* Fills in tpi and returns header length to be pulled. */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, - bool *csum_err, __be16 proto) + bool *csum_err, __be16 proto, int nhs) { const struct gre_base_hdr *greh; __be32 *options; int hdr_len; - if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr)))) + if (unlikely(!pskb_may_pull(skb, nhs + sizeof(struct gre_base_hdr)))) return -EINVAL; - greh = (struct gre_base_hdr *)skb_transport_header(skb); + greh = (struct gre_base_hdr *)(skb->data + nhs); if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; tpi->flags = gre_flags_to_tnl_flags(greh->flags); hdr_len = gre_calc_hlen(tpi->flags); - if (!pskb_may_pull(skb, hdr_len)) + if (!pskb_may_pull(skb, nhs + hdr_len)) return -EINVAL; - greh = (struct gre_base_hdr *)skb_transport_header(skb); + greh = (struct gre_base_hdr *)(skb->data + nhs); tpi->proto = greh->protocol; options = (__be32 *)(greh + 1); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 4d2025f7ec57..1d000af7f561 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -49,12 +49,6 @@ #include #include -#if IS_ENABLED(CONFIG_IPV6) -#include -#include -#include -#endif - /* Problems & solutions -------------------- @@ -217,12 +211,14 @@ static void gre_err(struct sk_buff *skb, u32 info) * by themselves??? */ + const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; bool csum_err = false; - if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP)) < 0) { + if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), + iph->ihl * 4) < 0) { if (!csum_err) /* ignore csum errors. */ return; } @@ -338,7 +334,7 @@ static int gre_rcv(struct sk_buff *skb) } #endif - hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP)); + hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; @@ -1121,6 +1117,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; + LIST_HEAD(list_kill); struct ip_tunnel *t; int err; @@ -1136,8 +1133,10 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, t->collect_md = true; err = ipgre_newlink(net, dev, tb, NULL); - if (err < 0) - goto out; + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. @@ -1146,9 +1145,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, if (err) goto out; + err = rtnl_configure_link(dev, NULL); + if (err < 0) + goto out; + return dev; out: - free_netdev(dev); + ip_tunnel_dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(gretap_fb_dev_create); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 124bf0a66328..4bd4921639c3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -271,7 +271,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk return dst_output(net, sk, skb); } #endif - mtu = ip_skb_dst_mtu(skb); + mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); @@ -541,7 +541,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, iph = ip_hdr(skb); - mtu = ip_skb_dst_mtu(skb); + mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 2ed9dd2b5f2f..1d71c40eaaf3 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -127,7 +127,9 @@ __be32 ic_myaddr = NONE; /* My IP address */ static __be32 ic_netmask = NONE; /* Netmask for local subnet */ __be32 ic_gateway = NONE; /* Gateway IP address */ -__be32 ic_addrservaddr = NONE; /* IP Address of the IP addresses'server */ +#ifdef IPCONFIG_DYNAMIC +static __be32 ic_addrservaddr = NONE; /* IP Address of the IP addresses'server */ +#endif __be32 ic_servaddr = NONE; /* Boot server IP address */ diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 21a38e296fe2..5ad48ec77710 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -891,8 +891,10 @@ static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); - if (c) + if (c) { + c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->mfc_un.res.minvif = MAXVIFS; + } return c; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d6c8f4cd0800..42bf89aaf6a5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -87,7 +87,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); /* rfc5961 challenge ack rate limiting */ -int sysctl_tcp_challenge_ack_limit = 100; +int sysctl_tcp_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; @@ -3421,6 +3421,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, + u32 *last_oow_ack_time) +{ + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS @@ -3434,21 +3451,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; + return false; -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ + return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ @@ -3458,21 +3463,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); - u32 now; + u32 count, now; /* First check our per-socket dupack rate limit. */ - if (tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) + if (__tcp_oow_rate_limited(sock_net(sk), + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) return; - /* Then check the check host-wide RFC 5961 rate limit. */ + /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { + u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + challenge_timestamp = now; - challenge_count = 0; + WRITE_ONCE(challenge_count, half + + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + count = READ_ONCE(challenge_count); + if (count > 0) { + WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8bd9911fdd16..e00e972c4e6a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2751,7 +2751,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; struct sk_buff *hole = NULL; - u32 last_lost; + u32 max_segs, last_lost; int mib_idx; int fwd_rexmitting = 0; @@ -2771,6 +2771,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) last_lost = tp->snd_una; } + max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk)); tcp_for_write_queue_from(skb, sk) { __u8 sacked = TCP_SKB_CB(skb)->sacked; int segs; @@ -2784,6 +2785,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk) segs = tp->snd_cwnd - tcp_packets_in_flight(tp); if (segs <= 0) return; + /* In case tcp_shift_skb_data() have aggregated large skbs, + * we need to make sure not sending too bigs TSO packets + */ + segs = min_t(int, segs, max_segs); if (fwd_rexmitting) { begin_fwd: diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0ff31d97d485..4aed8fc23d32 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -391,9 +391,9 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr); } -static inline int compute_score(struct sock *sk, struct net *net, - __be32 saddr, unsigned short hnum, __be16 sport, - __be32 daddr, __be16 dport, int dif) +static int compute_score(struct sock *sk, struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum, int dif) { int score; struct inet_sock *inet; @@ -434,52 +434,6 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } -/* - * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) - */ -static inline int compute_score2(struct sock *sk, struct net *net, - __be32 saddr, __be16 sport, - __be32 daddr, unsigned int hnum, int dif) -{ - int score; - struct inet_sock *inet; - - if (!net_eq(sock_net(sk), net) || - ipv6_only_sock(sk)) - return -1; - - inet = inet_sk(sk); - - if (inet->inet_rcv_saddr != daddr || - inet->inet_num != hnum) - return -1; - - score = (sk->sk_family == PF_INET) ? 2 : 1; - - if (inet->inet_daddr) { - if (inet->inet_daddr != saddr) - return -1; - score += 4; - } - - if (inet->inet_dport) { - if (inet->inet_dport != sport) - return -1; - score += 4; - } - - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - return -1; - score += 4; - } - - if (sk->sk_incoming_cpu == raw_smp_processor_id()) - score++; - - return score; -} - static u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) @@ -492,11 +446,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, udp_ehash_secret + net_hash_mix(net)); } -/* called with read_rcu_lock() */ +/* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2, + struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; @@ -506,7 +460,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = NULL; badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - score = compute_score2(sk, net, saddr, sport, + score = compute_score(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { reuseport = sk->sk_reuseport; @@ -554,17 +508,22 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, - hslot2, slot2, skb); + hslot2, skb); if (!result) { + unsigned int old_slot2 = slot2; hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; + /* avoid searching the same slot again. */ + if (unlikely(slot2 == old_slot2)) + return result; + hslot2 = &udptable->hash2[slot2]; if (hslot->count < hslot2->count) goto begin; result = udp4_lib_lookup2(net, saddr, sport, - htonl(INADDR_ANY), hnum, dif, - hslot2, slot2, skb); + daddr, hnum, dif, + hslot2, skb); } return result; } @@ -572,8 +531,8 @@ begin: result = NULL; badness = 0; sk_for_each_rcu(sk, &hslot->head) { - score = compute_score(sk, net, saddr, hnum, sport, - daddr, dport, dif); + score = compute_score(sk, net, saddr, sport, + daddr, hnum, dif); if (score > badness) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -1624,6 +1583,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (sk_filter(sk, skb)) goto drop; + if (unlikely(skb->len < sizeof(struct udphdr))) + goto drop; udp_csum_pull_header(skb); if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { @@ -1755,8 +1716,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, return err; } - return skb_checksum_init_zero_check(skb, proto, uh->check, - inet_compute_pseudo); + /* Note, we are only interested in != 0 or == 0, thus the + * force to int. + */ + return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, + inet_compute_pseudo); } /* diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4527285fcaa2..a4fa84076969 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -98,7 +98,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!(type & ICMPV6_INFOMSG_MASK)) if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST) - ping_err(skb, offset, info); + ping_err(skb, offset, ntohl(info)); } static int icmpv6_rcv(struct sk_buff *skb); diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index b2025bf3da4a..c0cbcb259f5a 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -78,9 +78,12 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) * we accept a checksum of zero here. When we find the socket * for the UDP packet we'll check if that socket allows zero checksum * for IPv6 (set by socket option). + * + * Note, we are only interested in != 0 or == 0, thus the + * force to int. */ - return skb_checksum_init_zero_check(skb, proto, uh->check, - ip6_compute_pseudo); + return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, + ip6_compute_pseudo); } EXPORT_SYMBOL(udp6_csum_init); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1bcef2369d64..771be1fa4176 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -177,6 +177,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) } } + free_percpu(non_pcpu_rt->rt6i_pcpu); non_pcpu_rt->rt6i_pcpu = NULL; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index fdc9de276ab1..776d145113e1 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -468,7 +468,7 @@ static int gre_rcv(struct sk_buff *skb) bool csum_err = false; int hdr_len; - hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6)); + hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6), 0); if (hdr_len < 0) goto drop; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f2e2013f8346..487ef3bc7bbc 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1074,6 +1074,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void) struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (!c) return NULL; + c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->mfc_un.res.minvif = MAXMIFS; return c; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 969913da494f..520b7884d0c2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1782,7 +1782,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, }; struct fib6_table *table; struct rt6_info *rt; - int flags = 0; + int flags = RT6_LOOKUP_F_IFACE; table = fib6_get_table(net, cfg->fc_table); if (!table) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 0a5a255277e5..0619ac70836d 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -560,13 +560,13 @@ 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->parms.link, 0, IPPROTO_IPV6, 0); + t->parms.link, 0, iph->protocol, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, - IPPROTO_IPV6, 0); + iph->protocol, 0); err = 0; goto out; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f36c2d076fce..2255d2bf5f6b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -738,7 +738,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int rst, - u8 tclass, u32 label) + u8 tclass, __be32 label) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; @@ -911,7 +911,7 @@ out: static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, - u32 label) + __be32 label) { tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass, label); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f421c9f23c5b..acc09705618b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -115,11 +115,10 @@ static void udp_v6_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash); } -static inline int compute_score(struct sock *sk, struct net *net, - unsigned short hnum, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, __be16 dport, - int dif) +static int compute_score(struct sock *sk, struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned short hnum, + int dif) { int score; struct inet_sock *inet; @@ -162,54 +161,11 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } -static inline int compute_score2(struct sock *sk, struct net *net, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, - unsigned short hnum, int dif) -{ - int score; - struct inet_sock *inet; - - if (!net_eq(sock_net(sk), net) || - udp_sk(sk)->udp_port_hash != hnum || - sk->sk_family != PF_INET6) - return -1; - - if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) - return -1; - - score = 0; - inet = inet_sk(sk); - - if (inet->inet_dport) { - if (inet->inet_dport != sport) - return -1; - score++; - } - - if (!ipv6_addr_any(&sk->sk_v6_daddr)) { - if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) - return -1; - score++; - } - - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - return -1; - score++; - } - - if (sk->sk_incoming_cpu == raw_smp_processor_id()) - score++; - - return score; -} - -/* called with read_rcu_lock() */ +/* called with rcu_read_lock() */ static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2, + struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; @@ -219,7 +175,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result = NULL; badness = -1; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - score = compute_score2(sk, net, saddr, sport, + score = compute_score(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { reuseport = sk->sk_reuseport; @@ -268,17 +224,22 @@ struct sock *__udp6_lib_lookup(struct net *net, result = udp6_lib_lookup2(net, saddr, sport, daddr, hnum, dif, - hslot2, slot2, skb); + hslot2, skb); if (!result) { + unsigned int old_slot2 = slot2; hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum); slot2 = hash2 & udptable->mask; + /* avoid searching the same slot again. */ + if (unlikely(slot2 == old_slot2)) + return result; + hslot2 = &udptable->hash2[slot2]; if (hslot->count < hslot2->count) goto begin; result = udp6_lib_lookup2(net, saddr, sport, - &in6addr_any, hnum, dif, - hslot2, slot2, skb); + daddr, hnum, dif, + hslot2, skb); } return result; } @@ -286,7 +247,7 @@ begin: result = NULL; badness = -1; sk_for_each_rcu(sk, &hslot->head) { - score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif); + score = compute_score(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -659,6 +620,8 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (sk_filter(sk, skb)) goto drop; + if (unlikely(skb->len < sizeof(struct udphdr))) + goto drop; udp_csum_pull_header(skb); if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index 738008726cc6..fda7f4715c58 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -241,6 +241,7 @@ static const struct file_operations kcm_seq_fops = { .open = kcm_seq_open, .read = seq_read, .llseek = seq_lseek, + .release = seq_release_net, }; static struct kcm_seq_muxinfo kcm_seq_muxinfo = { diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 21b1fdf5d01d..6a1603bcdced 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -148,14 +148,17 @@ u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata) void mesh_sta_cleanup(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; - u32 changed; + u32 changed = 0; /* * maybe userspace handles peer allocation and peering, but in either * case the beacon is still generated by the kernel and we might need * an update. */ - changed = mesh_accept_plinks_update(sdata); + if (sdata->u.mesh.user_mpm && + sta->mesh->plink_state == NL80211_PLINK_ESTAB) + changed |= mesh_plink_dec_estab_count(sdata); + changed |= mesh_accept_plinks_update(sdata); if (!sdata->u.mesh.user_mpm) { changed |= mesh_plink_deactivate(sta); del_timer_sync(&sta->mesh->plink_timer); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 803001a45aa1..1b07578bedf3 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1545,7 +1545,8 @@ error: /* * Set up receiving multicast socket over UDP */ -static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id) +static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, + int ifindex) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1566,6 +1567,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id) set_sock_size(sock->sk, 0, result); get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); + sock->sk->sk_bound_dev_if = ifindex; result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); @@ -1868,7 +1870,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, if (state == IP_VS_STATE_MASTER) sock = make_send_sock(ipvs, id); else - sock = make_receive_sock(ipvs, id); + sock = make_receive_sock(ipvs, id, dev->ifindex); if (IS_ERR(sock)) { result = PTR_ERR(sock); goto outtinfo; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index db2312eeb2a4..9f530adad10d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -646,6 +646,7 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto->allow_clash && + !nfct_nat(ct) && !nf_ct_is_dying(ct) && atomic_inc_not_zero(&ct->ct_general.use)) { nf_ct_acct_merge(ct, ctinfo, (struct nf_conn *)skb->nfct); @@ -1544,6 +1545,8 @@ void nf_conntrack_cleanup_end(void) nf_conntrack_tstamp_fini(); nf_conntrack_acct_fini(); nf_conntrack_expect_fini(); + + kmem_cache_destroy(nf_conntrack_cachep); } /* @@ -1599,8 +1602,15 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) unsigned int nr_slots, i; size_t sz; + if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head))) + return NULL; + BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); + + if (nr_slots > (UINT_MAX / sizeof(struct hlist_nulls_head))) + return NULL; + sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7b7aa871a174..cf7c74599cbe 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1724,9 +1724,11 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err = nf_tables_newexpr(ctx, &info, expr); if (err < 0) - goto err2; + goto err3; return expr; +err3: + kfree(expr); err2: module_put(info.ops->type->owner); err1: @@ -2946,24 +2948,20 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, * jumps are already validated for that chain. */ list_for_each_entry(i, &set->bindings, list) { - if (binding->flags & NFT_SET_MAP && + if (i->flags & NFT_SET_MAP && i->chain == binding->chain) goto bind; } + iter.genmask = nft_genmask_next(ctx->net); iter.skip = 0; iter.count = 0; iter.err = 0; iter.fn = nf_tables_bind_check_setelem; set->ops->walk(ctx, set, &iter); - if (iter.err < 0) { - /* Destroy anonymous sets if binding fails */ - if (set->flags & NFT_SET_ANONYMOUS) - nf_tables_set_destroy(ctx, set); - + if (iter.err < 0) return iter.err; - } } bind: binding->chain = ctx->chain; @@ -3192,12 +3190,13 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto nla_put_failure; - args.cb = cb; - args.skb = skb; - args.iter.skip = cb->args[0]; - args.iter.count = 0; - args.iter.err = 0; - args.iter.fn = nf_tables_dump_setelem; + args.cb = cb; + args.skb = skb; + args.iter.genmask = nft_genmask_cur(ctx.net); + args.iter.skip = cb->args[0]; + args.iter.count = 0; + args.iter.err = 0; + args.iter.fn = nf_tables_dump_setelem; set->ops->walk(&ctx, set, &args.iter); nla_nest_end(skb, nest); @@ -4284,6 +4283,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, binding->chain != chain) continue; + iter.genmask = nft_genmask_next(ctx->net); iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index e9f8dffcc244..fb8b5892b5ff 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -143,7 +143,7 @@ next_rule: list_for_each_entry_continue_rcu(rule, &chain->rules, list) { /* This rule is not active, skip. */ - if (unlikely(rule->genmask & (1 << gencursor))) + if (unlikely(rule->genmask & gencursor)) continue; rulenum++; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 137e308d5b24..81fbb450783e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -54,7 +54,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, const struct nf_conn_help *help; const struct nf_conntrack_tuple *tuple; const struct nf_conntrack_helper *helper; - long diff; unsigned int state; ct = nf_ct_get(pkt->skb, &ctinfo); @@ -94,10 +93,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #endif case NFT_CT_EXPIRATION: - diff = (long)jiffies - (long)ct->timeout.expires; - if (diff < 0) - diff = 0; - *dest = jiffies_to_msecs(diff); + *dest = jiffies_to_msecs(nf_ct_expires(ct)); return; case NFT_CT_HELPER: if (ct->master == NULL) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 6fa016564f90..f39c53a159eb 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -189,7 +189,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_hash_elem *he; struct rhashtable_iter hti; struct nft_set_elem elem; - u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int err; err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); @@ -218,7 +217,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, goto cont; if (nft_set_elem_expired(&he->ext)) goto cont; - if (!nft_set_elem_active(&he->ext, genmask)) + if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; elem.priv = he; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 16c50b0dd426..f4bad9dc15c4 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -227,7 +227,7 @@ void nft_meta_set_eval(const struct nft_expr *expr, skb->pkt_type = value; break; case NFT_META_NFTRACE: - skb->nf_trace = 1; + skb->nf_trace = !!value; break; default: WARN_ON(1); diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index f762094af7c1..7201d57b5a93 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -211,7 +211,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_rbtree_elem *rbe; struct nft_set_elem elem; struct rb_node *node; - u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); spin_lock_bh(&nft_rbtree_lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { @@ -219,7 +218,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&rbe->ext, genmask)) + if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; elem.priv = rbe; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 3d5feede962d..d84312584ee4 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -818,8 +818,18 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, */ state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED; __ovs_ct_update_key(key, state, &info->zone, exp->master); - } else - return __ovs_ct_lookup(net, key, info, skb); + } else { + struct nf_conn *ct; + int err; + + err = __ovs_ct_lookup(net, key, info, skb); + if (err) + return err; + + ct = (struct nf_conn *)skb->nfct; + if (ct) + nf_ct_deliver_cached_events(ct); + } return 0; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9bff6ef16fa7..b43c4015b2f7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1341,7 +1341,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_scale(skb_get_hash(skb), num); + return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, @@ -1927,13 +1927,11 @@ retry: goto out_unlock; } - sockc.tsflags = 0; + sockc.tsflags = sk->sk_tsflags; if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); - if (unlikely(err)) { - err = -EINVAL; + if (unlikely(err)) goto out_unlock; - } } skb->protocol = proto; @@ -2678,7 +2676,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); } - sockc.tsflags = 0; + sockc.tsflags = po->sk.sk_tsflags; if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) @@ -2881,7 +2879,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; - sockc.tsflags = 0; + sockc.tsflags = sk->sk_tsflags; sockc.mark = sk->sk_mark; if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 310cabce2311..7c2a65a6af5c 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -111,7 +111,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even } } - if (conn->c_version < RDS_PROTOCOL(3,1)) { + if (conn->c_version < RDS_PROTOCOL(3, 1)) { printk(KERN_NOTICE "RDS/IB: Connection to %pI4 version %u.%u failed," " no longer supported\n", &conn->c_faddr, diff --git a/net/rds/loop.c b/net/rds/loop.c index 6b12b68541ae..814173b466d9 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -95,8 +95,9 @@ out: */ static void rds_loop_inc_free(struct rds_incoming *inc) { - struct rds_message *rm = container_of(inc, struct rds_message, m_inc); - rds_message_put(rm); + struct rds_message *rm = container_of(inc, struct rds_message, m_inc); + + rds_message_put(rm); } /* we need to at least give the thread something to succeed */ diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index c173f69e1479..e381bbcd9cc1 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -102,7 +102,8 @@ int rds_sysctl_init(void) rds_sysctl_reconnect_min = msecs_to_jiffies(1); rds_sysctl_reconnect_min_jiffies = rds_sysctl_reconnect_min; - rds_sysctl_reg_table = register_net_sysctl(&init_net,"net/rds", rds_sysctl_rds_table); + rds_sysctl_reg_table = + register_net_sysctl(&init_net, "net/rds", rds_sysctl_rds_table); if (!rds_sysctl_reg_table) return -ENOMEM; return 0; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 74ee126a6fe6..c8a7b4c90190 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -616,7 +616,7 @@ static int rds_tcp_init(void) ret = rds_tcp_recv_init(); if (ret) - goto out_slab; + goto out_pernet; ret = rds_trans_register(&rds_tcp_transport); if (ret) @@ -628,8 +628,9 @@ static int rds_tcp_init(void) out_recv: rds_tcp_recv_exit(); -out_slab: +out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); +out_slab: kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; diff --git a/net/rds/tcp.h b/net/rds/tcp.h index ec0602b0dc24..7940babf6c71 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -83,7 +83,7 @@ int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to); void rds_tcp_xmit_prepare(struct rds_connection *conn); void rds_tcp_xmit_complete(struct rds_connection *conn); int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, - unsigned int hdr_off, unsigned int sg, unsigned int off); + unsigned int hdr_off, unsigned int sg, unsigned int off); void rds_tcp_write_space(struct sock *sk); /* tcp_stats.c */ diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index fba13d0305fb..f6e95d60db54 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -54,19 +54,19 @@ void rds_tcp_state_change(struct sock *sk) rdsdebug("sock %p state_change to %d\n", tc->t_sock, sk->sk_state); - switch(sk->sk_state) { - /* ignore connecting sockets as they make progress */ - case TCP_SYN_SENT: - case TCP_SYN_RECV: - break; - case TCP_ESTABLISHED: - rds_connect_path_complete(conn, RDS_CONN_CONNECTING); - break; - case TCP_CLOSE_WAIT: - case TCP_CLOSE: - rds_conn_drop(conn); - default: - break; + switch (sk->sk_state) { + /* ignore connecting sockets as they make progress */ + case TCP_SYN_SENT: + case TCP_SYN_RECV: + break; + case TCP_ESTABLISHED: + rds_connect_path_complete(conn, RDS_CONN_CONNECTING); + break; + case TCP_CLOSE_WAIT: + case TCP_CLOSE: + rds_conn_drop(conn); + default: + break; } out: read_unlock_bh(&sk->sk_callback_lock); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 686b1d03a558..245542ca4718 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -138,7 +138,7 @@ int rds_tcp_accept_one(struct socket *sock) rds_tcp_reset_callbacks(new_sock, conn); conn->c_outgoing = 0; /* rds_connect_path_complete() marks RDS_CONN_UP */ - rds_connect_path_complete(conn, RDS_CONN_DISCONNECTING); + rds_connect_path_complete(conn, RDS_CONN_RESETTING); } } else { rds_tcp_set_callbacks(new_sock, conn); diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index c3196f9d070a..6e6a7111a034 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -171,7 +171,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, while (left) { if (!tinc) { tinc = kmem_cache_alloc(rds_tcp_incoming_slab, - arg->gfp); + arg->gfp); if (!tinc) { desc->error = -ENOMEM; goto out; diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 22d0f2020a79..618be69c9c3b 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -66,19 +66,19 @@ void rds_tcp_xmit_complete(struct rds_connection *conn) static int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len) { struct kvec vec = { - .iov_base = data, - .iov_len = len, + .iov_base = data, + .iov_len = len, + }; + struct msghdr msg = { + .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL, }; - struct msghdr msg = { - .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL, - }; return kernel_sendmsg(sock, &msg, &vec, 1, vec.iov_len); } /* the core send_sem serializes this with other xmit and shutdown */ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, - unsigned int hdr_off, unsigned int sg, unsigned int off) + unsigned int hdr_off, unsigned int sg, unsigned int off) { struct rds_tcp_connection *tc = conn->c_transport_data; int done = 0; @@ -196,7 +196,7 @@ void rds_tcp_write_space(struct sock *sk) tc->t_last_seen_una = rds_tcp_snd_una(tc); rds_send_drop_acked(conn, rds_tcp_snd_una(tc), rds_tcp_is_acked); - if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) + if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) queue_delayed_work(rds_wq, &conn->c_send_w, 0); out: diff --git a/net/rds/transport.c b/net/rds/transport.c index f3afd1d60d3c..2ffd3e30c643 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -140,8 +140,7 @@ unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, rds_info_iter_unmap(iter); down_read(&rds_trans_sem); - for (i = 0; i < RDS_TRANS_COUNT; i++) - { + for (i = 0; i < RDS_TRANS_COUNT; i++) { trans = transports[i]; if (!trans || !trans->stats_info_copy) continue; diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 79c4abcfa6b4..0a6394754e81 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -164,7 +164,8 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety rose_frames_acked(sk, nr); if (ns == rose->vr) { rose_start_idletimer(sk); - if (sock_queue_rcv_skb(sk, skb) == 0) { + if (sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN) == 0 && + __sock_queue_rcv_skb(sk, skb) == 0) { rose->vr = (rose->vr + 1) % ROSE_MODULUS; queued = 1; } else { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 336774a535c3..c7a0b0d481c0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1118,7 +1118,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) nla_nest_end(skb, nest); ret = skb->len; } else - nla_nest_cancel(skb, nest); + nlmsg_trim(skb, b); nlh->nlmsg_len = skb_tail_pointer(skb) - b; if (NETLINK_CB(cb->skb).portid && ret) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 658046dfe02d..ea4a2fef1b71 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -106,9 +106,9 @@ int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi) } EXPORT_SYMBOL_GPL(ife_get_meta_u16); -int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval) +int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp) { - mi->metaval = kmemdup(metaval, sizeof(u32), GFP_KERNEL); + mi->metaval = kmemdup(metaval, sizeof(u32), gfp); if (!mi->metaval) return -ENOMEM; @@ -116,9 +116,9 @@ int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval) } EXPORT_SYMBOL_GPL(ife_alloc_meta_u32); -int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval) +int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp) { - mi->metaval = kmemdup(metaval, sizeof(u16), GFP_KERNEL); + mi->metaval = kmemdup(metaval, sizeof(u16), gfp); if (!mi->metaval) return -ENOMEM; @@ -240,10 +240,10 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) } /* called when adding new meta information - * under ife->tcf_lock + * under ife->tcf_lock for existing action */ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, - void *val, int len) + void *val, int len, bool exists) { struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; @@ -251,11 +251,13 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (!ops) { ret = -ENOENT; #ifdef CONFIG_MODULES - spin_unlock_bh(&ife->tcf_lock); + if (exists) + spin_unlock_bh(&ife->tcf_lock); rtnl_unlock(); request_module("ifemeta%u", metaid); rtnl_lock(); - spin_lock_bh(&ife->tcf_lock); + if (exists) + spin_lock_bh(&ife->tcf_lock); ops = find_ife_oplist(metaid); #endif } @@ -272,10 +274,10 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, } /* called when adding new meta information - * under ife->tcf_lock + * under ife->tcf_lock for existing action */ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len) + int len, bool atomic) { struct tcf_meta_info *mi = NULL; struct tcf_meta_ops *ops = find_ife_oplist(metaid); @@ -284,7 +286,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, if (!ops) return -ENOENT; - mi = kzalloc(sizeof(*mi), GFP_KERNEL); + mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL); if (!mi) { /*put back what find_ife_oplist took */ module_put(ops->owner); @@ -294,7 +296,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, mi->metaid = metaid; mi->ops = ops; if (len > 0) { - ret = ops->alloc(mi, metaval); + ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL); if (ret != 0) { kfree(mi); module_put(ops->owner); @@ -313,11 +315,13 @@ static int use_all_metadata(struct tcf_ife_info *ife) int rc = 0; int installed = 0; + read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo(ife, o->metaid, NULL, 0); + rc = add_metainfo(ife, o->metaid, NULL, 0, true); if (rc == 0) installed += 1; } + read_unlock(&ife_mod_lock); if (installed) return 0; @@ -385,8 +389,9 @@ static void tcf_ife_cleanup(struct tc_action *a, int bind) spin_unlock_bh(&ife->tcf_lock); } -/* under ife->tcf_lock */ -static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb) +/* under ife->tcf_lock for existing action */ +static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, + bool exists) { int len = 0; int rc = 0; @@ -398,11 +403,11 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb) val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(ife, i, val, len); + rc = load_metaops_and_vet(ife, i, val, len, exists); if (rc != 0) return rc; - rc = add_metainfo(ife, i, val, len); + rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; } @@ -474,7 +479,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, saddr = nla_data(tb[TCA_IFE_SMAC]); } - spin_lock_bh(&ife->tcf_lock); + if (exists) + spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; if (parm->flags & IFE_ENCODE) { @@ -504,11 +510,12 @@ metadata_parse_err: if (ret == ACT_P_CREATED) _tcf_ife_cleanup(a, bind); - spin_unlock_bh(&ife->tcf_lock); + if (exists) + spin_unlock_bh(&ife->tcf_lock); return err; } - err = populate_metalist(ife, tb2); + err = populate_metalist(ife, tb2, exists); if (err) goto metadata_parse_err; @@ -523,12 +530,14 @@ metadata_parse_err: if (ret == ACT_P_CREATED) _tcf_ife_cleanup(a, bind); - spin_unlock_bh(&ife->tcf_lock); + if (exists) + spin_unlock_bh(&ife->tcf_lock); return err; } } - spin_unlock_bh(&ife->tcf_lock); + if (exists) + spin_unlock_bh(&ife->tcf_lock); if (ret == ACT_P_CREATED) tcf_hash_insert(tn, a); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 9f002ada7074..d4bd19ee5822 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -121,10 +121,13 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, } td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); - if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) + if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) { + if (exists) + tcf_hash_release(a, bind); return -EINVAL; + } - if (!tcf_hash_check(tn, index, a, bind)) { + if (!exists) { ret = tcf_hash_create(tn, index, est, a, sizeof(*ipt), bind, false); if (ret) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 128942bc9e42..1f5bd6ccbd2c 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -181,7 +181,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, if (!(at & AT_EGRESS)) { if (m->tcfm_ok_push) - skb_push(skb2, skb->mac_len); + skb_push_rcsum(skb2, skb->mac_len); } /* mirror is always swallowed */ diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 2177eac0a61e..2e4bd2c0a50c 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -37,14 +37,18 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch) { + unsigned int prev_backlog; + if (likely(skb_queue_len(&sch->q) < sch->limit)) return qdisc_enqueue_tail(skb, sch); + prev_backlog = sch->qstats.backlog; /* queue full, remove one skb to fulfill the limit */ __qdisc_queue_drop_head(sch, &sch->q); qdisc_qstats_drop(sch); qdisc_enqueue_tail(skb, sch); + qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog); return NET_XMIT_CN; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index d4b4218af6b1..052f84d6cc23 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1007,7 +1007,9 @@ static void htb_work_func(struct work_struct *work) struct htb_sched *q = container_of(work, struct htb_sched, work); struct Qdisc *sch = q->watchdog.qdisc; + rcu_read_lock(); __netif_schedule(qdisc_root(sch)); + rcu_read_unlock(); } static int htb_init(struct Qdisc *sch, struct nlattr *opt) @@ -1138,8 +1140,10 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) if (!cl->level && cl->un.leaf.q) qlen = cl->un.leaf.q->q.qlen; - cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens); - cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens); + cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), + INT_MIN, INT_MAX); + cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens), + INT_MIN, INT_MAX); if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 || diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 205bed00dd34..178f1630a036 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -650,14 +650,14 @@ deliver: #endif if (q->qdisc) { + unsigned int pkt_len = qdisc_pkt_len(skb); int err = qdisc_enqueue(skb, q->qdisc); - if (unlikely(err != NET_XMIT_SUCCESS)) { - if (net_xmit_drop_count(err)) { - qdisc_qstats_drop(sch); - qdisc_tree_reduce_backlog(sch, 1, - qdisc_pkt_len(skb)); - } + if (err != NET_XMIT_SUCCESS && + net_xmit_drop_count(err)) { + qdisc_qstats_drop(sch); + qdisc_tree_reduce_backlog(sch, 1, + pkt_len); } goto tfifo_dequeue; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 4b0a82191bc4..a356450b747b 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -172,8 +172,9 @@ prio_destroy(struct Qdisc *sch) static int prio_tune(struct Qdisc *sch, struct nlattr *opt) { struct prio_sched_data *q = qdisc_priv(sch); + struct Qdisc *queues[TCQ_PRIO_BANDS]; + int oldbands = q->bands, i; struct tc_prio_qopt *qopt; - int i; if (nla_len(opt) < sizeof(*qopt)) return -EINVAL; @@ -187,62 +188,42 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) return -EINVAL; } + /* Before commit, make sure we can allocate all new qdiscs */ + for (i = oldbands; i < qopt->bands; i++) { + queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, i + 1)); + if (!queues[i]) { + while (i > oldbands) + qdisc_destroy(queues[--i]); + return -ENOMEM; + } + } + sch_tree_lock(sch); q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); - for (i = q->bands; i < TCQ_PRIO_BANDS; i++) { + for (i = q->bands; i < oldbands; i++) { struct Qdisc *child = q->queues[i]; - q->queues[i] = &noop_qdisc; - if (child != &noop_qdisc) { - qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); - qdisc_destroy(child); - } - } - sch_tree_unlock(sch); - for (i = 0; i < q->bands; i++) { - if (q->queues[i] == &noop_qdisc) { - struct Qdisc *child, *old; - - child = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, - TC_H_MAKE(sch->handle, i + 1)); - if (child) { - sch_tree_lock(sch); - old = q->queues[i]; - q->queues[i] = child; - - if (old != &noop_qdisc) { - qdisc_tree_reduce_backlog(old, - old->q.qlen, - old->qstats.backlog); - qdisc_destroy(old); - } - sch_tree_unlock(sch); - } - } + qdisc_tree_reduce_backlog(child, child->q.qlen, + child->qstats.backlog); + qdisc_destroy(child); } + + for (i = oldbands; i < q->bands; i++) + q->queues[i] = queues[i]; + + sch_tree_unlock(sch); return 0; } static int prio_init(struct Qdisc *sch, struct nlattr *opt) { - struct prio_sched_data *q = qdisc_priv(sch); - int i; - - for (i = 0; i < TCQ_PRIO_BANDS; i++) - q->queues[i] = &noop_qdisc; - - if (opt == NULL) { + if (!opt) return -EINVAL; - } else { - int err; - if ((err = prio_tune(sch, opt)) != 0) - return err; - } - return 0; + return prio_tune(sch, opt); } static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sctp/input.c b/net/sctp/input.c index a701527a9480..47cf4604d19c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -112,7 +112,6 @@ int sctp_rcv(struct sk_buff *skb) struct sctp_ep_common *rcvr; struct sctp_transport *transport = NULL; struct sctp_chunk *chunk; - struct sctphdr *sh; union sctp_addr src; union sctp_addr dest; int family; @@ -127,8 +126,6 @@ int sctp_rcv(struct sk_buff *skb) if (skb_linearize(skb)) goto discard_it; - sh = sctp_hdr(skb); - /* Pull up the IP and SCTP headers. */ __skb_pull(skb, skb_transport_offset(skb)); if (skb->len < sizeof(struct sctphdr)) @@ -230,7 +227,7 @@ int sctp_rcv(struct sk_buff *skb) chunk->rcvr = rcvr; /* Remember the SCTP header. */ - chunk->sctp_hdr = sh; + chunk->sctp_hdr = sctp_hdr(skb); /* Set the source and destination addresses of the incoming chunk. */ sctp_init_addrs(chunk, &src, &dest); diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index 1ce724b87618..f69edcf219e5 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -3,12 +3,6 @@ #include #include -extern void inet_diag_msg_common_fill(struct inet_diag_msg *r, - struct sock *sk); -extern int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, - struct inet_diag_msg *r, int ext, - struct user_namespace *user_ns); - static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, void *info); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 06b4df9faaa1..2808d550d273 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -446,16 +446,27 @@ out_no_rpciod: return ERR_PTR(err); } -struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, +static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, struct rpc_xprt *xprt) { struct rpc_clnt *clnt = NULL; struct rpc_xprt_switch *xps; - xps = xprt_switch_alloc(xprt, GFP_KERNEL); - if (xps == NULL) - return ERR_PTR(-ENOMEM); - + if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) { + WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + xps = args->bc_xprt->xpt_bc_xps; + xprt_switch_get(xps); + } else { + xps = xprt_switch_alloc(xprt, GFP_KERNEL); + if (xps == NULL) { + xprt_put(xprt); + return ERR_PTR(-ENOMEM); + } + if (xprt->bc_xprt) { + xprt_switch_get(xps); + xprt->bc_xprt->xpt_bc_xps = xps; + } + } clnt = rpc_new_client(args, xps, xprt, NULL); if (IS_ERR(clnt)) return clnt; @@ -483,7 +494,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, return clnt; } -EXPORT_SYMBOL_GPL(rpc_create_xprt); /** * rpc_create - create an RPC client and transport with one call @@ -509,6 +519,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) }; char servername[48]; + if (args->bc_xprt) { + WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + xprt = args->bc_xprt->xpt_bc_xprt; + if (xprt) { + xprt_get(xprt); + return rpc_create_xprt(args, xprt); + } + } + if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS) xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS; if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index f5572e31d518..4f01f63102ee 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -136,6 +136,8 @@ static void svc_xprt_free(struct kref *kref) /* See comment on corresponding get in xs_setup_bc_tcp(): */ if (xprt->xpt_bc_xprt) xprt_put(xprt->xpt_bc_xprt); + if (xprt->xpt_bc_xps) + xprt_switch_put(xprt->xpt_bc_xps); xprt->xpt_ops->xpo_free(xprt); module_put(owner); } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2d3e0c42361e..7e2b2fa189c3 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -3057,6 +3057,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) return xprt; args->bc_xprt->xpt_bc_xprt = NULL; + args->bc_xprt->xpt_bc_xps = NULL; xprt_put(xprt); ret = ERR_PTR(-EINVAL); out_err: diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 6f11c62bc8f9..a597708ae381 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -330,6 +330,21 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b) return 0; } +/* tipc_bearer_reset_all - reset all links on all bearers + */ +void tipc_bearer_reset_all(struct net *net) +{ + struct tipc_net *tn = tipc_net(net); + struct tipc_bearer *b; + int i; + + for (i = 0; i < MAX_BEARERS; i++) { + b = rcu_dereference_rtnl(tn->bearer_list[i]); + if (b) + tipc_reset_bearer(net, b); + } +} + /** * bearer_disable * @@ -405,7 +420,7 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb, return 0; /* Send RESET message even if bearer is detached from device */ - tipc_ptr = rtnl_dereference(dev->tipc_ptr); + tipc_ptr = rcu_dereference_rtnl(dev->tipc_ptr); if (unlikely(!tipc_ptr && !msg_is_reset(buf_msg(skb)))) goto drop; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index f686e41b5abb..60e49c3be19c 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -198,6 +198,7 @@ void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); struct tipc_media *tipc_media_find(const char *name); +void tipc_bearer_reset_all(struct net *net); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); diff --git a/net/tipc/link.c b/net/tipc/link.c index 7059c94f33c5..7d89f8713d49 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -349,6 +349,8 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l, u16 ack = snd_l->snd_nxt - 1; snd_l->ackers--; + rcv_l->bc_peer_is_up = true; + rcv_l->state = LINK_ESTABLISHED; tipc_link_bc_ack_rcv(rcv_l, ack, xmitq); tipc_link_reset(rcv_l); rcv_l->state = LINK_RESET; @@ -704,7 +706,8 @@ static void link_profile_stats(struct tipc_link *l) */ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) { - int mtyp, rc = 0; + int mtyp = 0; + int rc = 0; bool state = false; bool probe = false; bool setup = false; @@ -1558,7 +1561,12 @@ void tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, if (!msg_peer_node_is_up(hdr)) return; - l->bc_peer_is_up = true; + /* Open when peer ackowledges our bcast init msg (pkt #1) */ + if (msg_ack(hdr)) + l->bc_peer_is_up = true; + + if (!l->bc_peer_is_up) + return; /* Ignore if peers_snd_nxt goes beyond receive window */ if (more(peers_snd_nxt, l->rcv_nxt + l->window)) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 8740930f0787..17201aa8423d 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -41,6 +41,8 @@ #include "name_table.h" #define MAX_FORWARD_SIZE 1024 +#define BUF_HEADROOM (LL_MAX_HEADER + 48) +#define BUF_TAILROOM 16 static unsigned int align(unsigned int i) { @@ -505,6 +507,10 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) msg_set_hdr_sz(hdr, BASIC_H_SIZE); } + if (skb_cloned(_skb) && + pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_KERNEL)) + goto exit; + /* Now reverse the concerned fields */ msg_set_errcode(hdr, err); msg_set_origport(hdr, msg_destport(&ohdr)); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 024da8af91f0..7cf52fb39bee 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -94,17 +94,6 @@ struct plist; #define TIPC_MEDIA_INFO_OFFSET 5 -/** - * TIPC message buffer code - * - * TIPC message buffer headroom reserves space for the worst-case - * link-level device header (in case the message is sent off-node). - * - * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields - * are word aligned for quicker access - */ -#define BUF_HEADROOM (LL_MAX_HEADER + 48) - struct tipc_skb_cb { void *handle; struct sk_buff *tail; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 3ad9fab1985f..1fd464764765 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -604,7 +604,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg, link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]); link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP])); - nla_strlcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]), + nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME], TIPC_MAX_LINK_NAME); return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO, diff --git a/net/tipc/node.c b/net/tipc/node.c index e01e2c71b5a1..23d4761842a0 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1297,10 +1297,6 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id rc = tipc_bcast_rcv(net, be->link, skb); - /* Broadcast link reset may happen at reassembly failure */ - if (rc & TIPC_LINK_DOWN_EVT) - tipc_node_reset_links(n); - /* Broadcast ACKs are sent on a unicast link */ if (rc & TIPC_LINK_SND_BC_ACK) { tipc_node_read_lock(n); @@ -1320,6 +1316,17 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id spin_unlock_bh(&be->inputq2.lock); tipc_sk_mcast_rcv(net, &be->arrvq, &be->inputq2); } + + if (rc & TIPC_LINK_DOWN_EVT) { + /* Reception reassembly failure => reset all links to peer */ + if (!tipc_link_is_up(be->link)) + tipc_node_reset_links(n); + + /* Retransmission failure => reset all links to all peers */ + if (!tipc_link_is_up(tipc_bc_sndlink(net))) + tipc_bearer_reset_all(net); + } + tipc_node_put(n); } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 88bfcd707064..c49b8df438cb 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -796,9 +796,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, * @tsk: receiving socket * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) +static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct sock *sk = &tsk->sk; + u32 onode = tsk_own_node(tsk); struct tipc_msg *hdr = buf_msg(skb); int mtyp = msg_type(hdr); bool conn_cong; @@ -811,7 +813,8 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) if (mtyp == CONN_PROBE) { msg_set_type(hdr, CONN_PROBE_REPLY); - tipc_sk_respond(sk, skb, TIPC_OK); + if (tipc_msg_reverse(onode, &skb, TIPC_OK)) + __skb_queue_tail(xmitq, skb); return; } else if (mtyp == CONN_ACK) { conn_cong = tsk_conn_cong(tsk); @@ -1686,7 +1689,8 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) * * Returns true if message was added to socket receive queue, otherwise false */ -static bool filter_rcv(struct sock *sk, struct sk_buff *skb) +static bool filter_rcv(struct sock *sk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct socket *sock = sk->sk_socket; struct tipc_sock *tsk = tipc_sk(sk); @@ -1696,7 +1700,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb) int usr = msg_user(hdr); if (unlikely(msg_user(hdr) == CONN_MANAGER)) { - tipc_sk_proto_rcv(tsk, skb); + tipc_sk_proto_rcv(tsk, skb, xmitq); return false; } @@ -1739,7 +1743,8 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb) return true; reject: - tipc_sk_respond(sk, skb, err); + if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err)) + __skb_queue_tail(xmitq, skb); return false; } @@ -1755,9 +1760,24 @@ reject: static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { unsigned int truesize = skb->truesize; + struct sk_buff_head xmitq; + u32 dnode, selector; - if (likely(filter_rcv(sk, skb))) + __skb_queue_head_init(&xmitq); + + if (likely(filter_rcv(sk, skb, &xmitq))) { atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); + return 0; + } + + if (skb_queue_empty(&xmitq)) + return 0; + + /* Send response/rejected message */ + skb = __skb_dequeue(&xmitq); + dnode = msg_destnode(buf_msg(skb)); + selector = msg_origport(buf_msg(skb)); + tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); return 0; } @@ -1771,12 +1791,13 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) * Caller must hold socket lock */ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, - u32 dport) + u32 dport, struct sk_buff_head *xmitq) { + unsigned long time_limit = jiffies + 2; + struct sk_buff *skb; unsigned int lim; atomic_t *dcnt; - struct sk_buff *skb; - unsigned long time_limit = jiffies + 2; + u32 onode; while (skb_queue_len(inputq)) { if (unlikely(time_after_eq(jiffies, time_limit))) @@ -1788,7 +1809,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - filter_rcv(sk, skb); + filter_rcv(sk, skb, xmitq); continue; } @@ -1801,7 +1822,9 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, continue; /* Overload => reject message back to sender */ - tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD); + onode = tipc_own_addr(sock_net(sk)); + if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD)) + __skb_queue_tail(xmitq, skb); break; } } @@ -1814,12 +1837,14 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, */ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { + struct sk_buff_head xmitq; u32 dnode, dport = 0; int err; struct tipc_sock *tsk; struct sock *sk; struct sk_buff *skb; + __skb_queue_head_init(&xmitq); while (skb_queue_len(inputq)) { dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); @@ -1827,9 +1852,14 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) if (likely(tsk)) { sk = &tsk->sk; if (likely(spin_trylock_bh(&sk->sk_lock.slock))) { - tipc_sk_enqueue(inputq, sk, dport); + tipc_sk_enqueue(inputq, sk, dport, &xmitq); spin_unlock_bh(&sk->sk_lock.slock); } + /* Send pending response/rejected messages, if any */ + while ((skb = __skb_dequeue(&xmitq))) { + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, dport); + } sock_put(sk); continue; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 80aa6a3e6817..735362c26c8e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -315,7 +315,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i) &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) { struct dentry *dentry = unix_sk(s)->path.dentry; - if (dentry && d_backing_inode(dentry) == i) { + if (dentry && d_real_inode(dentry) == i) { sock_hold(s); goto found; } @@ -911,7 +911,7 @@ static struct sock *unix_find_other(struct net *net, err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path); if (err) goto fail; - inode = d_backing_inode(path.dentry); + inode = d_real_inode(path.dentry); err = inode_permission(inode, MAY_WRITE); if (err) goto put_fail; @@ -1048,7 +1048,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); + hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); u->path = u_path; list = &unix_socket_table[hash]; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b5f1221f48d4..b96ac918e0ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -61,6 +61,14 @@ * function will also cleanup rejected sockets, those that reach the connected * state but leave it before they have been accepted. * + * - Lock ordering for pending or accept queue sockets is: + * + * lock_sock(listener); + * lock_sock_nested(pending, SINGLE_DEPTH_NESTING); + * + * Using explicit nested locking keeps lockdep happy since normally only one + * lock of a given class may be taken at a time. + * * - Sockets created by user action will be cleaned up when the user process * calls close(2), causing our release implementation to be called. Our release * implementation will perform some cleanup then drop the last reference so our @@ -443,7 +451,7 @@ void vsock_pending_work(struct work_struct *work) cleanup = true; lock_sock(listener); - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (vsock_is_pending(sk)) { vsock_remove_pending(listener, sk); @@ -1292,7 +1300,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) if (connected) { listener->sk_ack_backlog--; - lock_sock(connected); + lock_sock_nested(connected, SINGLE_DEPTH_NESTING); vconnected = vsock_sk(connected); /* If the listener socket has received an error, then we should diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d7599014055d..7d72283901a3 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3487,16 +3487,16 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.smps_mode = NL80211_SMPS_OFF; } + params.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); + if (params.pbss && !rdev->wiphy.bands[NL80211_BAND_60GHZ]) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_ACL_POLICY]) { params.acl = parse_acl_data(&rdev->wiphy, info); if (IS_ERR(params.acl)) return PTR_ERR(params.acl); } - params.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); - if (params.pbss && !rdev->wiphy.bands[NL80211_BAND_60GHZ]) - return -EOPNOTSUPP; - wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { diff --git a/net/wireless/util.c b/net/wireless/util.c index 4e809e978b7d..b7d1592bd5b8 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -509,7 +509,7 @@ static int __ieee80211_data_to_8023(struct sk_buff *skb, struct ethhdr *ehdr, * replace EtherType */ hdrlen += ETH_ALEN + 2; else - tmp.h_proto = htons(skb->len); + tmp.h_proto = htons(skb->len - hdrlen); pskb_pull(skb, hdrlen); @@ -721,6 +721,8 @@ __ieee80211_amsdu_copy(struct sk_buff *skb, unsigned int hlen, * alignment since sizeof(struct ethhdr) is 14. */ frame = dev_alloc_skb(hlen + sizeof(struct ethhdr) + 2 + cur_len); + if (!frame) + return NULL; skb_reserve(frame, hlen + sizeof(struct ethhdr) + 2); skb_copy_bits(skb, offset, skb_put(frame, cur_len), cur_len); diff --git a/scripts/analyze_suspend.py b/scripts/analyze_suspend.py index 93e1fd40f430..a0ba48fa2c5e 100755 --- a/scripts/analyze_suspend.py +++ b/scripts/analyze_suspend.py @@ -19,6 +19,17 @@ # Authors: # Todd Brandt # +# Links: +# Home Page +# https://01.org/suspendresume +# Source repo +# https://github.com/01org/suspendresume +# Documentation +# Getting Started +# https://01.org/suspendresume/documentation/getting-started +# Command List: +# https://01.org/suspendresume/documentation/command-list +# # Description: # This tool is designed to assist kernel and OS developers in optimizing # their linux stack's suspend/resume time. Using a kernel image built @@ -35,6 +46,8 @@ # CONFIG_FTRACE=y # CONFIG_FUNCTION_TRACER=y # CONFIG_FUNCTION_GRAPH_TRACER=y +# CONFIG_KPROBES=y +# CONFIG_KPROBES_ON_FTRACE=y # # For kernel versions older than 3.15: # The following additional kernel parameters are required: @@ -52,6 +65,7 @@ import re import platform from datetime import datetime import struct +import ConfigParser # ----------------- CLASSES -------------------- @@ -60,8 +74,15 @@ import struct # A global, single-instance container used to # store system values and test parameters class SystemValues: - version = 3.0 + ansi = False + version = '4.2' verbose = False + addlogs = False + mindevlen = 0.001 + mincglen = 1.0 + srgap = 0 + cgexp = False + outdir = '' testdir = '.' tpath = '/sys/kernel/debug/tracing/' fpdtpath = '/sys/firmware/acpi/tables/FPDT' @@ -71,26 +92,21 @@ class SystemValues: 'device_pm_callback_end', 'device_pm_callback_start' ] - modename = { - 'freeze': 'Suspend-To-Idle (S0)', - 'standby': 'Power-On Suspend (S1)', - 'mem': 'Suspend-to-RAM (S3)', - 'disk': 'Suspend-to-disk (S4)' - } + testcommand = '' mempath = '/dev/mem' powerfile = '/sys/power/state' suspendmode = 'mem' hostname = 'localhost' prefix = 'test' teststamp = '' + dmesgstart = 0.0 dmesgfile = '' ftracefile = '' htmlfile = '' + embedded = False rtcwake = False rtcwaketime = 10 rtcpath = '' - android = False - adb = 'adb' devicefilter = [] stamp = 0 execcount = 1 @@ -98,16 +114,90 @@ class SystemValues: usecallgraph = False usetraceevents = False usetraceeventsonly = False + usetracemarkers = True + usekprobes = True + usedevsrc = False notestrun = False - altdevname = dict() + devprops = dict() postresumetime = 0 + devpropfmt = '# Device Properties: .*' tracertypefmt = '# tracer: (?P.*)' firmwarefmt = '# fwsuspend (?P[0-9]*) fwresume (?P[0-9]*)$' postresumefmt = '# post resume time (?P[0-9]*)$' stampfmt = '# suspend-(?P[0-9]{2})(?P[0-9]{2})(?P[0-9]{2})-'+\ '(?P[0-9]{2})(?P[0-9]{2})(?P[0-9]{2})'+\ ' (?P.*) (?P.*) (?P.*)$' + kprobecolor = 'rgba(204,204,204,0.5)' + synccolor = 'rgba(204,204,204,0.5)' + debugfuncs = [] + tracefuncs = { + 'sys_sync': dict(), + 'pm_prepare_console': dict(), + 'pm_notifier_call_chain': dict(), + 'freeze_processes': dict(), + 'freeze_kernel_threads': dict(), + 'pm_restrict_gfp_mask': dict(), + 'acpi_suspend_begin': dict(), + 'suspend_console': dict(), + 'acpi_pm_prepare': dict(), + 'syscore_suspend': dict(), + 'arch_enable_nonboot_cpus_end': dict(), + 'syscore_resume': dict(), + 'acpi_pm_finish': dict(), + 'resume_console': dict(), + 'acpi_pm_end': dict(), + 'pm_restore_gfp_mask': dict(), + 'thaw_processes': dict(), + 'pm_restore_console': dict(), + 'CPU_OFF': { + 'func':'_cpu_down', + 'args_x86_64': {'cpu':'%di:s32'}, + 'format': 'CPU_OFF[{cpu}]', + 'mask': 'CPU_.*_DOWN' + }, + 'CPU_ON': { + 'func':'_cpu_up', + 'args_x86_64': {'cpu':'%di:s32'}, + 'format': 'CPU_ON[{cpu}]', + 'mask': 'CPU_.*_UP' + }, + } + dev_tracefuncs = { + # general wait/delay/sleep + 'msleep': { 'args_x86_64': {'time':'%di:s32'} }, + 'udelay': { 'func':'__const_udelay', 'args_x86_64': {'loops':'%di:s32'} }, + 'acpi_os_stall': dict(), + # ACPI + 'acpi_resume_power_resources': dict(), + 'acpi_ps_parse_aml': dict(), + # filesystem + 'ext4_sync_fs': dict(), + # ATA + 'ata_eh_recover': { 'args_x86_64': {'port':'+36(%di):s32'} }, + # i915 + 'i915_gem_restore_gtt_mappings': dict(), + 'intel_opregion_setup': dict(), + 'intel_dp_detect': dict(), + 'intel_hdmi_detect': dict(), + 'intel_opregion_init': dict(), + } + kprobes_postresume = [ + { + 'name': 'ataportrst', + 'func': 'ata_eh_recover', + 'args': {'port':'+36(%di):s32'}, + 'format': 'ata{port}_port_reset', + 'mask': 'ata.*_port_reset' + } + ] + kprobes = dict() + timeformat = '%.3f' def __init__(self): + # if this is a phoronix test run, set some default options + if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ): + self.embedded = True + self.addlogs = True + self.htmlfile = os.environ['LOG_FILE'] self.hostname = platform.node() if(self.hostname == ''): self.hostname = 'localhost' @@ -118,6 +208,12 @@ class SystemValues: if os.path.exists(rtc) and os.path.exists(rtc+'/date') and \ os.path.exists(rtc+'/time') and os.path.exists(rtc+'/wakealarm'): self.rtcpath = rtc + if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()): + self.ansi = True + def setPrecision(self, num): + if num < 0 or num > 6: + return + self.timeformat = '%.{0}f'.format(num) def setOutputFile(self): if((self.htmlfile == '') and (self.dmesgfile != '')): m = re.match('(?P.*)_dmesg\.txt$', self.dmesgfile) @@ -129,32 +225,37 @@ class SystemValues: self.htmlfile = m.group('name')+'.html' if(self.htmlfile == ''): self.htmlfile = 'output.html' - def initTestOutput(self, subdir): - if(not self.android): - self.prefix = self.hostname - v = open('/proc/version', 'r').read().strip() - kver = string.split(v)[2] - else: - self.prefix = 'android' - v = os.popen(self.adb+' shell cat /proc/version').read().strip() - kver = string.split(v)[2] - testtime = datetime.now().strftime('suspend-%m%d%y-%H%M%S') + def initTestOutput(self, subdir, testpath=''): + self.prefix = self.hostname + v = open('/proc/version', 'r').read().strip() + kver = string.split(v)[2] + n = datetime.now() + testtime = n.strftime('suspend-%m%d%y-%H%M%S') + if not testpath: + testpath = n.strftime('suspend-%y%m%d-%H%M%S') if(subdir != "."): - self.testdir = subdir+"/"+testtime + self.testdir = subdir+"/"+testpath else: - self.testdir = testtime + self.testdir = testpath self.teststamp = \ '# '+testtime+' '+self.prefix+' '+self.suspendmode+' '+kver + if(self.embedded): + self.dmesgfile = \ + '/tmp/'+testtime+'_'+self.suspendmode+'_dmesg.txt' + self.ftracefile = \ + '/tmp/'+testtime+'_'+self.suspendmode+'_ftrace.txt' + return self.dmesgfile = \ self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_dmesg.txt' self.ftracefile = \ self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_ftrace.txt' self.htmlfile = \ self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html' - os.mkdir(self.testdir) + if not os.path.isdir(self.testdir): + os.mkdir(self.testdir) def setDeviceFilter(self, devnames): self.devicefilter = string.split(devnames) - def rtcWakeAlarm(self): + def rtcWakeAlarmOn(self): os.system('echo 0 > '+self.rtcpath+'/wakealarm') outD = open(self.rtcpath+'/date', 'r').read().strip() outT = open(self.rtcpath+'/time', 'r').read().strip() @@ -172,9 +273,361 @@ class SystemValues: nowtime = int(datetime.now().strftime('%s')) alarm = nowtime + self.rtcwaketime os.system('echo %d > %s/wakealarm' % (alarm, self.rtcpath)) + def rtcWakeAlarmOff(self): + os.system('echo 0 > %s/wakealarm' % self.rtcpath) + def initdmesg(self): + # get the latest time stamp from the dmesg log + fp = os.popen('dmesg') + ktime = '0' + for line in fp: + line = line.replace('\r\n', '') + idx = line.find('[') + if idx > 1: + line = line[idx:] + m = re.match('[ \t]*(\[ *)(?P[0-9\.]*)(\]) (?P.*)', line) + if(m): + ktime = m.group('ktime') + fp.close() + self.dmesgstart = float(ktime) + def getdmesg(self): + # store all new dmesg lines since initdmesg was called + fp = os.popen('dmesg') + op = open(self.dmesgfile, 'a') + for line in fp: + line = line.replace('\r\n', '') + idx = line.find('[') + if idx > 1: + line = line[idx:] + m = re.match('[ \t]*(\[ *)(?P[0-9\.]*)(\]) (?P.*)', line) + if(not m): + continue + ktime = float(m.group('ktime')) + if ktime > self.dmesgstart: + op.write(line) + fp.close() + op.close() + def addFtraceFilterFunctions(self, file): + fp = open(file) + list = fp.read().split('\n') + fp.close() + for i in list: + if len(i) < 2: + continue + self.tracefuncs[i] = dict() + def getFtraceFilterFunctions(self, current): + rootCheck(True) + if not current: + os.system('cat '+self.tpath+'available_filter_functions') + return + fp = open(self.tpath+'available_filter_functions') + master = fp.read().split('\n') + fp.close() + if len(self.debugfuncs) > 0: + for i in self.debugfuncs: + if i in master: + print i + else: + print self.colorText(i) + else: + for i in self.tracefuncs: + if 'func' in self.tracefuncs[i]: + i = self.tracefuncs[i]['func'] + if i in master: + print i + else: + print self.colorText(i) + def setFtraceFilterFunctions(self, list): + fp = open(self.tpath+'available_filter_functions') + master = fp.read().split('\n') + fp.close() + flist = '' + for i in list: + if i not in master: + continue + if ' [' in i: + flist += i.split(' ')[0]+'\n' + else: + flist += i+'\n' + fp = open(self.tpath+'set_graph_function', 'w') + fp.write(flist) + fp.close() + def kprobeMatch(self, name, target): + if name not in self.kprobes: + return False + if re.match(self.kprobes[name]['mask'], target): + return True + return False + def basicKprobe(self, name): + self.kprobes[name] = {'name': name,'func': name,'args': dict(),'format': name,'mask': name} + def defaultKprobe(self, name, kdata): + k = kdata + for field in ['name', 'format', 'mask', 'func']: + if field not in k: + k[field] = name + archargs = 'args_'+platform.machine() + if archargs in k: + k['args'] = k[archargs] + else: + k['args'] = dict() + k['format'] = name + self.kprobes[name] = k + def kprobeColor(self, name): + if name not in self.kprobes or 'color' not in self.kprobes[name]: + return '' + return self.kprobes[name]['color'] + def kprobeDisplayName(self, name, dataraw): + if name not in self.kprobes: + self.basicKprobe(name) + data = '' + quote=0 + # first remvoe any spaces inside quotes, and the quotes + for c in dataraw: + if c == '"': + quote = (quote + 1) % 2 + if quote and c == ' ': + data += '_' + elif c != '"': + data += c + fmt, args = self.kprobes[name]['format'], self.kprobes[name]['args'] + arglist = dict() + # now process the args + for arg in sorted(args): + arglist[arg] = '' + m = re.match('.* '+arg+'=(?P.*) ', data); + if m: + arglist[arg] = m.group('arg') + else: + m = re.match('.* '+arg+'=(?P.*)', data); + if m: + arglist[arg] = m.group('arg') + out = fmt.format(**arglist) + out = out.replace(' ', '_').replace('"', '') + return out + def kprobeText(self, kprobe): + name, fmt, func, args = kprobe['name'], kprobe['format'], kprobe['func'], kprobe['args'] + if re.findall('{(?P[a-z,A-Z,0-9]*)}', func): + doError('Kprobe "%s" has format info in the function name "%s"' % (name, func), False) + for arg in re.findall('{(?P[a-z,A-Z,0-9]*)}', fmt): + if arg not in args: + doError('Kprobe "%s" is missing argument "%s"' % (name, arg), False) + val = 'p:%s_cal %s' % (name, func) + for i in sorted(args): + val += ' %s=%s' % (i, args[i]) + val += '\nr:%s_ret %s $retval\n' % (name, func) + return val + def addKprobes(self): + # first test each kprobe + print('INITIALIZING KPROBES...') + rejects = [] + for name in sorted(self.kprobes): + if not self.testKprobe(self.kprobes[name]): + rejects.append(name) + # remove all failed ones from the list + for name in rejects: + vprint('Skipping KPROBE: %s' % name) + self.kprobes.pop(name) + self.fsetVal('', 'kprobe_events') + kprobeevents = '' + # set the kprobes all at once + for kp in self.kprobes: + val = self.kprobeText(self.kprobes[kp]) + vprint('Adding KPROBE: %s\n%s' % (kp, val.strip())) + kprobeevents += self.kprobeText(self.kprobes[kp]) + self.fsetVal(kprobeevents, 'kprobe_events') + # verify that the kprobes were set as ordered + check = self.fgetVal('kprobe_events') + linesout = len(kprobeevents.split('\n')) + linesack = len(check.split('\n')) + if linesack < linesout: + # if not, try appending the kprobes 1 by 1 + for kp in self.kprobes: + kprobeevents = self.kprobeText(self.kprobes[kp]) + self.fsetVal(kprobeevents, 'kprobe_events', 'a') + self.fsetVal('1', 'events/kprobes/enable') + def testKprobe(self, kprobe): + kprobeevents = self.kprobeText(kprobe) + if not kprobeevents: + return False + try: + self.fsetVal(kprobeevents, 'kprobe_events') + check = self.fgetVal('kprobe_events') + except: + return False + linesout = len(kprobeevents.split('\n')) + linesack = len(check.split('\n')) + if linesack < linesout: + return False + return True + def fsetVal(self, val, path, mode='w'): + file = self.tpath+path + if not os.path.exists(file): + return False + try: + fp = open(file, mode) + fp.write(val) + fp.close() + except: + pass + return True + def fgetVal(self, path): + file = self.tpath+path + res = '' + if not os.path.exists(file): + return res + try: + fp = open(file, 'r') + res = fp.read() + fp.close() + except: + pass + return res + def cleanupFtrace(self): + if(self.usecallgraph or self.usetraceevents): + self.fsetVal('0', 'events/kprobes/enable') + self.fsetVal('', 'kprobe_events') + def setupAllKprobes(self): + for name in self.tracefuncs: + self.defaultKprobe(name, self.tracefuncs[name]) + for name in self.dev_tracefuncs: + self.defaultKprobe(name, self.dev_tracefuncs[name]) + def isCallgraphFunc(self, name): + if len(self.debugfuncs) < 1 and self.suspendmode == 'command': + return True + if name in self.debugfuncs: + return True + funclist = [] + for i in self.tracefuncs: + if 'func' in self.tracefuncs[i]: + funclist.append(self.tracefuncs[i]['func']) + else: + funclist.append(i) + if name in funclist: + return True + return False + def initFtrace(self, testing=False): + tp = self.tpath + print('INITIALIZING FTRACE...') + # turn trace off + self.fsetVal('0', 'tracing_on') + self.cleanupFtrace() + # set the trace clock to global + self.fsetVal('global', 'trace_clock') + # set trace buffer to a huge value + self.fsetVal('nop', 'current_tracer') + self.fsetVal('100000', 'buffer_size_kb') + # go no further if this is just a status check + if testing: + return + if self.usekprobes: + # add tracefunc kprobes so long as were not using full callgraph + if(not self.usecallgraph or len(self.debugfuncs) > 0): + for name in self.tracefuncs: + self.defaultKprobe(name, self.tracefuncs[name]) + if self.usedevsrc: + for name in self.dev_tracefuncs: + self.defaultKprobe(name, self.dev_tracefuncs[name]) + else: + self.usedevsrc = False + self.addKprobes() + # initialize the callgraph trace, unless this is an x2 run + if(self.usecallgraph): + # set trace type + self.fsetVal('function_graph', 'current_tracer') + self.fsetVal('', 'set_ftrace_filter') + # set trace format options + self.fsetVal('print-parent', 'trace_options') + self.fsetVal('funcgraph-abstime', 'trace_options') + self.fsetVal('funcgraph-cpu', 'trace_options') + self.fsetVal('funcgraph-duration', 'trace_options') + self.fsetVal('funcgraph-proc', 'trace_options') + self.fsetVal('funcgraph-tail', 'trace_options') + self.fsetVal('nofuncgraph-overhead', 'trace_options') + self.fsetVal('context-info', 'trace_options') + self.fsetVal('graph-time', 'trace_options') + self.fsetVal('0', 'max_graph_depth') + if len(self.debugfuncs) > 0: + self.setFtraceFilterFunctions(self.debugfuncs) + elif self.suspendmode == 'command': + self.fsetVal('', 'set_graph_function') + else: + cf = ['dpm_run_callback'] + if(self.usetraceeventsonly): + cf += ['dpm_prepare', 'dpm_complete'] + for fn in self.tracefuncs: + if 'func' in self.tracefuncs[fn]: + cf.append(self.tracefuncs[fn]['func']) + else: + cf.append(fn) + self.setFtraceFilterFunctions(cf) + if(self.usetraceevents): + # turn trace events on + events = iter(self.traceevents) + for e in events: + self.fsetVal('1', 'events/power/'+e+'/enable') + # clear the trace buffer + self.fsetVal('', 'trace') + def verifyFtrace(self): + # files needed for any trace data + files = ['buffer_size_kb', 'current_tracer', 'trace', 'trace_clock', + 'trace_marker', 'trace_options', 'tracing_on'] + # files needed for callgraph trace data + tp = self.tpath + if(self.usecallgraph): + files += [ + 'available_filter_functions', + 'set_ftrace_filter', + 'set_graph_function' + ] + for f in files: + if(os.path.exists(tp+f) == False): + return False + return True + def verifyKprobes(self): + # files needed for kprobes to work + files = ['kprobe_events', 'events'] + tp = self.tpath + for f in files: + if(os.path.exists(tp+f) == False): + return False + return True + def colorText(self, str): + if not self.ansi: + return str + return '\x1B[31;40m'+str+'\x1B[m' sysvals = SystemValues() +# Class: DevProps +# Description: +# Simple class which holds property values collected +# for all the devices used in the timeline. +class DevProps: + syspath = '' + altname = '' + async = True + xtraclass = '' + xtrainfo = '' + def out(self, dev): + return '%s,%s,%d;' % (dev, self.altname, self.async) + def debug(self, dev): + print '%s:\n\taltname = %s\n\t async = %s' % (dev, self.altname, self.async) + def altName(self, dev): + if not self.altname or self.altname == dev: + return dev + return '%s [%s]' % (self.altname, dev) + def xtraClass(self): + if self.xtraclass: + return ' '+self.xtraclass + if not self.async: + return ' sync' + return '' + def xtraInfo(self): + if self.xtraclass: + return ' '+self.xtraclass + if self.async: + return ' async' + return ' sync' + # Class: DeviceNode # Description: # A container used to create a device hierachy, with a single root node @@ -228,6 +681,7 @@ class Data: html_device_id = 0 stamp = 0 outfile = '' + dev_ubiquitous = ['msleep', 'udelay'] def __init__(self, num): idchar = 'abcdefghijklmnopqrstuvwxyz' self.testnumber = num @@ -257,6 +711,9 @@ class Data: 'row': 0, 'color': '#FFFFCC', 'order': 9} } self.phases = self.sortedPhases() + self.devicegroups = [] + for phase in self.phases: + self.devicegroups.append([phase]) def getStart(self): return self.dmesg[self.phases[0]]['start'] def setStart(self, time): @@ -273,51 +730,61 @@ class Data: for dev in list: d = list[dev] if(d['pid'] == pid and time >= d['start'] and - time <= d['end']): + time < d['end']): return False return True - def addIntraDevTraceEvent(self, action, name, pid, time): - if(action == 'mutex_lock_try'): - color = 'red' - elif(action == 'mutex_lock_pass'): - color = 'green' - elif(action == 'mutex_unlock'): - color = 'blue' - else: - # create separate colors based on the name - v1 = len(name)*10 % 256 - v2 = string.count(name, 'e')*100 % 256 - v3 = ord(name[0])*20 % 256 - color = '#%06X' % ((v1*0x10000) + (v2*0x100) + v3) - for phase in self.phases: + def targetDevice(self, phaselist, start, end, pid=-1): + tgtdev = '' + for phase in phaselist: list = self.dmesg[phase]['list'] - for dev in list: - d = list[dev] - if(d['pid'] == pid and time >= d['start'] and - time <= d['end']): - e = TraceEvent(action, name, color, time) - if('traceevents' not in d): - d['traceevents'] = [] - d['traceevents'].append(e) - return d - break - return 0 - def capIntraDevTraceEvent(self, action, name, pid, time): - for phase in self.phases: - list = self.dmesg[phase]['list'] - for dev in list: - d = list[dev] - if(d['pid'] == pid and time >= d['start'] and - time <= d['end']): - if('traceevents' not in d): - return - for e in d['traceevents']: - if(e.action == action and - e.name == name and not e.ready): - e.length = time - e.time - e.ready = True - break - return + for devname in list: + dev = list[devname] + if(pid >= 0 and dev['pid'] != pid): + continue + devS = dev['start'] + devE = dev['end'] + if(start < devS or start >= devE or end <= devS or end > devE): + continue + tgtdev = dev + break + return tgtdev + def addDeviceFunctionCall(self, displayname, kprobename, proc, pid, start, end, cdata, rdata): + machstart = self.dmesg['suspend_machine']['start'] + machend = self.dmesg['resume_machine']['end'] + tgtdev = self.targetDevice(self.phases, start, end, pid) + if not tgtdev and start >= machstart and end < machend: + # device calls in machine phases should be serial + tgtdev = self.targetDevice(['suspend_machine', 'resume_machine'], start, end) + if not tgtdev: + if 'scsi_eh' in proc: + self.newActionGlobal(proc, start, end, pid) + self.addDeviceFunctionCall(displayname, kprobename, proc, pid, start, end, cdata, rdata) + else: + vprint('IGNORE: %s[%s](%d) [%f - %f] | %s | %s | %s' % (displayname, kprobename, + pid, start, end, cdata, rdata, proc)) + return False + # detail block fits within tgtdev + if('src' not in tgtdev): + tgtdev['src'] = [] + title = cdata+' '+rdata + mstr = '\(.*\) *(?P.*) *\((?P.*)\+.* arg1=(?P.*)' + m = re.match(mstr, title) + if m: + c = m.group('caller') + a = m.group('args').strip() + r = m.group('ret') + if len(r) > 6: + r = '' + else: + r = 'ret=%s ' % r + l = '%0.3fms' % ((end - start) * 1000) + if kprobename in self.dev_ubiquitous: + title = '%s(%s) <- %s, %s(%s)' % (displayname, a, c, r, l) + else: + title = '%s(%s) %s(%s)' % (displayname, a, r, l) + e = TraceEvent(title, kprobename, start, end - start) + tgtdev['src'].append(e) + return True def trimTimeVal(self, t, t0, dT, left): if left: if(t > t0): @@ -353,11 +820,11 @@ class Data: cg.end = self.trimTimeVal(cg.end, t0, dT, left) for line in cg.list: line.time = self.trimTimeVal(line.time, t0, dT, left) - if('traceevents' in d): - for e in d['traceevents']: + if('src' in d): + for e in d['src']: e.time = self.trimTimeVal(e.time, t0, dT, left) def normalizeTime(self, tZero): - # first trim out any standby or freeze clock time + # trim out any standby or freeze clock time if(self.tSuspended != self.tResumed): if(self.tResumed > tZero): self.trimTime(self.tSuspended, \ @@ -365,29 +832,6 @@ class Data: else: self.trimTime(self.tSuspended, \ self.tResumed-self.tSuspended, False) - # shift the timeline so that tZero is the new 0 - self.tSuspended -= tZero - self.tResumed -= tZero - self.start -= tZero - self.end -= tZero - for phase in self.phases: - p = self.dmesg[phase] - p['start'] -= tZero - p['end'] -= tZero - list = p['list'] - for name in list: - d = list[name] - d['start'] -= tZero - d['end'] -= tZero - if('ftrace' in d): - cg = d['ftrace'] - cg.start -= tZero - cg.end -= tZero - for line in cg.list: - line.time -= tZero - if('traceevents' in d): - for e in d['traceevents']: - e.time -= tZero def newPhaseWithSingleAction(self, phasename, devname, start, end, color): for phase in self.phases: self.dmesg[phase]['order'] += 1 @@ -417,6 +861,7 @@ class Data: {'list': list, 'start': start, 'end': end, 'row': 0, 'color': color, 'order': order} self.phases = self.sortedPhases() + self.devicegroups.append([phasename]) def setPhase(self, phase, ktime, isbegin): if(isbegin): self.dmesg[phase]['start'] = ktime @@ -442,7 +887,10 @@ class Data: for devname in phaselist: dev = phaselist[devname] if(dev['end'] < 0): - dev['end'] = end + for p in self.phases: + if self.dmesg[p]['end'] > dev['start']: + dev['end'] = self.dmesg[p]['end'] + break vprint('%s (%s): callback didnt return' % (devname, phase)) def deviceFilter(self, devicefilter): # remove all by the relatives of the filter devnames @@ -472,22 +920,58 @@ class Data: # if any calls never returned, clip them at system resume end for phase in self.phases: self.fixupInitcalls(phase, self.getEnd()) - def newActionGlobal(self, name, start, end): + def isInsideTimeline(self, start, end): + if(self.start <= start and self.end > start): + return True + return False + def phaseOverlap(self, phases): + rmgroups = [] + newgroup = [] + for group in self.devicegroups: + for phase in phases: + if phase not in group: + continue + for p in group: + if p not in newgroup: + newgroup.append(p) + if group not in rmgroups: + rmgroups.append(group) + for group in rmgroups: + self.devicegroups.remove(group) + self.devicegroups.append(newgroup) + def newActionGlobal(self, name, start, end, pid=-1, color=''): + # if event starts before timeline start, expand timeline + if(start < self.start): + self.setStart(start) + # if event ends after timeline end, expand the timeline + if(end > self.end): + self.setEnd(end) # which phase is this device callback or action "in" targetphase = "none" + htmlclass = '' overlap = 0.0 + phases = [] for phase in self.phases: pstart = self.dmesg[phase]['start'] pend = self.dmesg[phase]['end'] o = max(0, min(end, pend) - max(start, pstart)) - if(o > overlap): + if o > 0: + phases.append(phase) + if o > overlap: + if overlap > 0 and phase == 'post_resume': + continue targetphase = phase overlap = o + if pid == -2: + htmlclass = ' bg' + if len(phases) > 1: + htmlclass = ' bg' + self.phaseOverlap(phases) if targetphase in self.phases: - self.newAction(targetphase, name, -1, '', start, end, '') - return True + newname = self.newAction(targetphase, name, pid, '', start, end, '', htmlclass, color) + return (targetphase, newname) return False - def newAction(self, phase, name, pid, parent, start, end, drv): + def newAction(self, phase, name, pid, parent, start, end, drv, htmlclass='', color=''): # new device callback for a specific phase self.html_device_id += 1 devid = '%s%d' % (self.idstr, self.html_device_id) @@ -495,8 +979,19 @@ class Data: length = -1.0 if(start >= 0 and end >= 0): length = end - start + if pid == -2: + i = 2 + origname = name + while(name in list): + name = '%s[%d]' % (origname, i) + i += 1 list[name] = {'start': start, 'end': end, 'pid': pid, 'par': parent, 'length': length, 'row': 0, 'id': devid, 'drv': drv } + if htmlclass: + list[name]['htmlclass'] = htmlclass + if color: + list[name]['color'] = color + return name def deviceIDs(self, devlist, phase): idlist = [] list = self.dmesg[phase]['list'] @@ -536,10 +1031,21 @@ class Data: vprint(' %16s: %f - %f (%d devices)' % (phase, \ self.dmesg[phase]['start'], self.dmesg[phase]['end'], dc)) vprint(' test end: %f' % self.end) + def deviceChildrenAllPhases(self, devname): + devlist = [] + for phase in self.phases: + list = self.deviceChildren(devname, phase) + for dev in list: + if dev not in devlist: + devlist.append(dev) + return devlist def masterTopology(self, name, list, depth): node = DeviceNode(name, depth) for cname in list: - clist = self.deviceChildren(cname, 'resume') + # avoid recursions + if name == cname: + continue + clist = self.deviceChildrenAllPhases(cname) cnode = self.masterTopology(cname, clist, depth+1) node.children.append(cnode) return node @@ -580,7 +1086,8 @@ class Data: list = self.dmesg[phase]['list'] for dev in list: pdev = list[dev]['par'] - if(re.match('[0-9]*-[0-9]*\.[0-9]*[\.0-9]*\:[\.0-9]*$', pdev)): + pid = list[dev]['pid'] + if(pid < 0 or re.match('[0-9]*-[0-9]*\.[0-9]*[\.0-9]*\:[\.0-9]*$', pdev)): continue if pdev and pdev not in real and pdev not in rootlist: rootlist.append(pdev) @@ -589,22 +1096,33 @@ class Data: rootlist = self.rootDeviceList() master = self.masterTopology('', rootlist, 0) return self.printTopology(master) + def selectTimelineDevices(self, widfmt, tTotal, mindevlen): + # only select devices that will actually show up in html + self.tdevlist = dict() + for phase in self.dmesg: + devlist = [] + list = self.dmesg[phase]['list'] + for dev in list: + length = (list[dev]['end'] - list[dev]['start']) * 1000 + width = widfmt % (((list[dev]['end']-list[dev]['start'])*100)/tTotal) + if width != '0.000000' and length >= mindevlen: + devlist.append(dev) + self.tdevlist[phase] = devlist # Class: TraceEvent # Description: # A container for trace event data found in the ftrace file class TraceEvent: - ready = False - name = '' + text = '' time = 0.0 - color = '#FFFFFF' length = 0.0 - action = '' - def __init__(self, a, n, c, t): - self.action = a - self.name = n - self.color = c + title = '' + row = 0 + def __init__(self, a, n, t, l): + self.title = a + self.text = n self.time = t + self.length = l # Class: FTraceLine # Description: @@ -623,11 +1141,14 @@ class FTraceLine: fcall = False freturn = False fevent = False + fkprobe = False depth = 0 name = '' type = '' - def __init__(self, t, m, d): + def __init__(self, t, m='', d=''): self.time = float(t) + if not m and not d: + return # is this a trace event if(d == 'traceevent' or re.match('^ *\/\* *(?P.*) \*\/ *$', m)): if(d == 'traceevent'): @@ -644,6 +1165,18 @@ class FTraceLine: self.type = emm.group('call') else: self.name = msg + km = re.match('^(?P.*)_cal$', self.type) + if km: + self.fcall = True + self.fkprobe = True + self.type = km.group('n') + return + km = re.match('^(?P.*)_ret$', self.type) + if km: + self.freturn = True + self.fkprobe = True + self.type = km.group('n') + return self.fevent = True return # convert the duration to seconds @@ -662,7 +1195,7 @@ class FTraceLine: # includes comment with function name match = re.match('^} *\/\* *(?P.*) *\*\/$', m) if(match): - self.name = match.group('n') + self.name = match.group('n').strip() # function call else: self.fcall = True @@ -670,19 +1203,19 @@ class FTraceLine: if(m[-1] == '{'): match = re.match('^(?P.*) *\(.*', m) if(match): - self.name = match.group('n') + self.name = match.group('n').strip() # function call with no children (leaf) elif(m[-1] == ';'): self.freturn = True match = re.match('^(?P.*) *\(.*', m) if(match): - self.name = match.group('n') + self.name = match.group('n').strip() # something else (possibly a trace marker) else: self.name = m def getDepth(self, str): return len(str)/2 - def debugPrint(self, dev): + def debugPrint(self, dev=''): if(self.freturn and self.fcall): print('%s -- %f (%02d): %s(); (%.3f us)' % (dev, self.time, \ self.depth, self.name, self.length*1000000)) @@ -692,6 +1225,33 @@ class FTraceLine: else: print('%s -- %f (%02d): %s() { (%.3f us)' % (dev, self.time, \ self.depth, self.name, self.length*1000000)) + def startMarker(self): + global sysvals + # Is this the starting line of a suspend? + if not self.fevent: + return False + if sysvals.usetracemarkers: + if(self.name == 'SUSPEND START'): + return True + return False + else: + if(self.type == 'suspend_resume' and + re.match('suspend_enter\[.*\] begin', self.name)): + return True + return False + def endMarker(self): + # Is this the ending line of a resume? + if not self.fevent: + return False + if sysvals.usetracemarkers: + if(self.name == 'RESUME COMPLETE'): + return True + return False + else: + if(self.type == 'suspend_resume' and + re.match('thaw_processes\[.*\] end', self.name)): + return True + return False # Class: FTraceCallGraph # Description: @@ -705,54 +1265,124 @@ class FTraceCallGraph: list = [] invalid = False depth = 0 - def __init__(self): + pid = 0 + def __init__(self, pid): self.start = -1.0 self.end = -1.0 self.list = [] self.depth = 0 - def setDepth(self, line): + self.pid = pid + def addLine(self, line, debug=False): + # if this is already invalid, just leave + if(self.invalid): + return False + # invalidate on too much data or bad depth + if(len(self.list) >= 1000000 or self.depth < 0): + self.invalidate(line) + return False + # compare current depth with this lines pre-call depth + prelinedep = line.depth + if(line.freturn and not line.fcall): + prelinedep += 1 + last = 0 + lasttime = line.time + virtualfname = 'execution_misalignment' + if len(self.list) > 0: + last = self.list[-1] + lasttime = last.time + # handle low misalignments by inserting returns + if prelinedep < self.depth: + if debug and last: + print '-------- task %d --------' % self.pid + last.debugPrint() + idx = 0 + # add return calls to get the depth down + while prelinedep < self.depth: + if debug: + print 'MISALIGN LOW (add returns): C%d - eC%d' % (self.depth, prelinedep) + self.depth -= 1 + if idx == 0 and last and last.fcall and not last.freturn: + # special case, turn last call into a leaf + last.depth = self.depth + last.freturn = True + last.length = line.time - last.time + if debug: + last.debugPrint() + else: + vline = FTraceLine(lasttime) + vline.depth = self.depth + vline.name = virtualfname + vline.freturn = True + self.list.append(vline) + if debug: + vline.debugPrint() + idx += 1 + if debug: + line.debugPrint() + print '' + # handle high misalignments by inserting calls + elif prelinedep > self.depth: + if debug and last: + print '-------- task %d --------' % self.pid + last.debugPrint() + idx = 0 + # add calls to get the depth up + while prelinedep > self.depth: + if debug: + print 'MISALIGN HIGH (add calls): C%d - eC%d' % (self.depth, prelinedep) + if idx == 0 and line.freturn and not line.fcall: + # special case, turn this return into a leaf + line.fcall = True + prelinedep -= 1 + else: + vline = FTraceLine(lasttime) + vline.depth = self.depth + vline.name = virtualfname + vline.fcall = True + if debug: + vline.debugPrint() + self.list.append(vline) + self.depth += 1 + if not last: + self.start = vline.time + idx += 1 + if debug: + line.debugPrint() + print '' + # process the call and set the new depth if(line.fcall and not line.freturn): - line.depth = self.depth self.depth += 1 elif(line.freturn and not line.fcall): self.depth -= 1 - line.depth = self.depth - else: - line.depth = self.depth - def addLine(self, line, match): - if(not self.invalid): - self.setDepth(line) + if len(self.list) < 1: + self.start = line.time + self.list.append(line) if(line.depth == 0 and line.freturn): if(self.start < 0): self.start = line.time self.end = line.time - self.list.append(line) + if line.fcall: + self.end += line.length + if self.list[0].name == virtualfname: + self.invalid = True return True - if(self.invalid): - return False - if(len(self.list) >= 1000000 or self.depth < 0): - if(len(self.list) > 0): - first = self.list[0] - self.list = [] - self.list.append(first) - self.invalid = True - if(not match): - return False - id = 'task %s cpu %s' % (match.group('pid'), match.group('cpu')) - window = '(%f - %f)' % (self.start, line.time) - if(self.depth < 0): - print('Too much data for '+id+\ - ' (buffer overflow), ignoring this callback') - else: - print('Too much data for '+id+\ - ' '+window+', ignoring this callback') - return False - self.list.append(line) - if(self.start < 0): - self.start = line.time return False + def invalidate(self, line): + if(len(self.list) > 0): + first = self.list[0] + self.list = [] + self.list.append(first) + self.invalid = True + id = 'task %s' % (self.pid) + window = '(%f - %f)' % (self.start, line.time) + if(self.depth < 0): + vprint('Too much data for '+id+\ + ' (buffer overflow), ignoring this callback') + else: + vprint('Too much data for '+id+\ + ' '+window+', ignoring this callback') def slice(self, t0, tN): - minicg = FTraceCallGraph() + minicg = FTraceCallGraph(0) count = -1 firstdepth = 0 for l in self.list: @@ -764,13 +1394,26 @@ class FTraceCallGraph: firstdepth = l.depth count = 0 l.depth -= firstdepth - minicg.addLine(l, 0) + minicg.addLine(l) if((count == 0 and l.freturn and l.fcall) or (count > 0 and l.depth <= 0)): break count += 1 return minicg - def sanityCheck(self): + def repair(self, enddepth): + # bring the depth back to 0 with additional returns + fixed = False + last = self.list[-1] + for i in reversed(range(enddepth)): + t = FTraceLine(last.time) + t.depth = i + t.freturn = True + fixed = self.addLine(t) + if fixed: + self.end = last.time + return True + return False + def postProcess(self, debug=False): stack = dict() cnt = 0 for l in self.list: @@ -779,98 +1422,317 @@ class FTraceCallGraph: cnt += 1 elif(l.freturn and not l.fcall): if(l.depth not in stack): + if debug: + print 'Post Process Error: Depth missing' + l.debugPrint() return False + # transfer total time from return line to call line stack[l.depth].length = l.length - stack[l.depth] = 0 + stack.pop(l.depth) l.length = 0 cnt -= 1 if(cnt == 0): + # trace caught the whole call tree return True - return False - def debugPrint(self, filename): - if(filename == 'stdout'): - print('[%f - %f]') % (self.start, self.end) - for l in self.list: - if(l.freturn and l.fcall): - print('%f (%02d): %s(); (%.3f us)' % (l.time, \ - l.depth, l.name, l.length*1000000)) - elif(l.freturn): - print('%f (%02d): %s} (%.3f us)' % (l.time, \ - l.depth, l.name, l.length*1000000)) - else: - print('%f (%02d): %s() { (%.3f us)' % (l.time, \ - l.depth, l.name, l.length*1000000)) - print(' ') - else: - fp = open(filename, 'w') - print(filename) - for l in self.list: - if(l.freturn and l.fcall): - fp.write('%f (%02d): %s(); (%.3f us)\n' % (l.time, \ - l.depth, l.name, l.length*1000000)) - elif(l.freturn): - fp.write('%f (%02d): %s} (%.3f us)\n' % (l.time, \ - l.depth, l.name, l.length*1000000)) - else: - fp.write('%f (%02d): %s() { (%.3f us)\n' % (l.time, \ - l.depth, l.name, l.length*1000000)) - fp.close() + elif(cnt < 0): + if debug: + print 'Post Process Error: Depth is less than 0' + return False + # trace ended before call tree finished + return self.repair(cnt) + def deviceMatch(self, pid, data): + found = False + # add the callgraph data to the device hierarchy + borderphase = { + 'dpm_prepare': 'suspend_prepare', + 'dpm_complete': 'resume_complete' + } + if(self.list[0].name in borderphase): + p = borderphase[self.list[0].name] + list = data.dmesg[p]['list'] + for devname in list: + dev = list[devname] + if(pid == dev['pid'] and + self.start <= dev['start'] and + self.end >= dev['end']): + dev['ftrace'] = self.slice(dev['start'], dev['end']) + found = True + return found + for p in data.phases: + if(data.dmesg[p]['start'] <= self.start and + self.start <= data.dmesg[p]['end']): + list = data.dmesg[p]['list'] + for devname in list: + dev = list[devname] + if(pid == dev['pid'] and + self.start <= dev['start'] and + self.end >= dev['end']): + dev['ftrace'] = self + found = True + break + break + return found + def newActionFromFunction(self, data): + name = self.list[0].name + if name in ['dpm_run_callback', 'dpm_prepare', 'dpm_complete']: + return + fs = self.start + fe = self.end + if fs < data.start or fe > data.end: + return + phase = '' + for p in data.phases: + if(data.dmesg[p]['start'] <= self.start and + self.start < data.dmesg[p]['end']): + phase = p + break + if not phase: + return + out = data.newActionGlobal(name, fs, fe, -2) + if out: + phase, myname = out + data.dmesg[phase]['list'][myname]['ftrace'] = self + def debugPrint(self): + print('[%f - %f] %s (%d)') % (self.start, self.end, self.list[0].name, self.pid) + for l in self.list: + if(l.freturn and l.fcall): + print('%f (%02d): %s(); (%.3f us)' % (l.time, \ + l.depth, l.name, l.length*1000000)) + elif(l.freturn): + print('%f (%02d): %s} (%.3f us)' % (l.time, \ + l.depth, l.name, l.length*1000000)) + else: + print('%f (%02d): %s() { (%.3f us)' % (l.time, \ + l.depth, l.name, l.length*1000000)) + print(' ') # Class: Timeline # Description: -# A container for a suspend/resume html timeline. In older versions -# of the script there were multiple timelines, but in the latest -# there is only one. +# A container for a device timeline which calculates +# all the html properties to display it correctly class Timeline: html = {} - scaleH = 0.0 # height of the row as a percent of the timeline height - rowH = 0.0 # height of each row in percent of the timeline height - row_height_pixels = 30 - maxrows = 0 - height = 0 - def __init__(self): + height = 0 # total timeline height + scaleH = 20 # timescale (top) row height + rowH = 30 # device row height + bodyH = 0 # body height + rows = 0 # total timeline rows + phases = [] + rowmaxlines = dict() + rowcount = dict() + rowheight = dict() + def __init__(self, rowheight): + self.rowH = rowheight self.html = { + 'header': '', 'timeline': '', 'legend': '', - 'scale': '' } - def setRows(self, rows): - self.maxrows = int(rows) - self.scaleH = 100.0/float(self.maxrows) - self.height = self.maxrows*self.row_height_pixels - r = float(self.maxrows - 1) - if(r < 1.0): - r = 1.0 - self.rowH = (100.0 - self.scaleH)/r + # Function: getDeviceRows + # Description: + # determine how may rows the device funcs will take + # Arguments: + # rawlist: the list of devices/actions for a single phase + # Output: + # The total number of rows needed to display this phase of the timeline + def getDeviceRows(self, rawlist): + # clear all rows and set them to undefined + lendict = dict() + for item in rawlist: + item.row = -1 + lendict[item] = item.length + list = [] + for i in sorted(lendict, key=lendict.get, reverse=True): + list.append(i) + remaining = len(list) + rowdata = dict() + row = 1 + # try to pack each row with as many ranges as possible + while(remaining > 0): + if(row not in rowdata): + rowdata[row] = [] + for i in list: + if(i.row >= 0): + continue + s = i.time + e = i.time + i.length + valid = True + for ritem in rowdata[row]: + rs = ritem.time + re = ritem.time + ritem.length + if(not (((s <= rs) and (e <= rs)) or + ((s >= re) and (e >= re)))): + valid = False + break + if(valid): + rowdata[row].append(i) + i.row = row + remaining -= 1 + row += 1 + return row + # Function: getPhaseRows + # Description: + # Organize the timeline entries into the smallest + # number of rows possible, with no entry overlapping + # Arguments: + # list: the list of devices/actions for a single phase + # devlist: string list of device names to use + # Output: + # The total number of rows needed to display this phase of the timeline + def getPhaseRows(self, dmesg, devlist): + # clear all rows and set them to undefined + remaining = len(devlist) + rowdata = dict() + row = 0 + lendict = dict() + myphases = [] + for item in devlist: + if item[0] not in self.phases: + self.phases.append(item[0]) + if item[0] not in myphases: + myphases.append(item[0]) + self.rowmaxlines[item[0]] = dict() + self.rowheight[item[0]] = dict() + dev = dmesg[item[0]]['list'][item[1]] + dev['row'] = -1 + lendict[item] = float(dev['end']) - float(dev['start']) + if 'src' in dev: + dev['devrows'] = self.getDeviceRows(dev['src']) + lenlist = [] + for i in sorted(lendict, key=lendict.get, reverse=True): + lenlist.append(i) + orderedlist = [] + for item in lenlist: + dev = dmesg[item[0]]['list'][item[1]] + if dev['pid'] == -2: + orderedlist.append(item) + for item in lenlist: + if item not in orderedlist: + orderedlist.append(item) + # try to pack each row with as many ranges as possible + while(remaining > 0): + rowheight = 1 + if(row not in rowdata): + rowdata[row] = [] + for item in orderedlist: + dev = dmesg[item[0]]['list'][item[1]] + if(dev['row'] < 0): + s = dev['start'] + e = dev['end'] + valid = True + for ritem in rowdata[row]: + rs = ritem['start'] + re = ritem['end'] + if(not (((s <= rs) and (e <= rs)) or + ((s >= re) and (e >= re)))): + valid = False + break + if(valid): + rowdata[row].append(dev) + dev['row'] = row + remaining -= 1 + if 'devrows' in dev and dev['devrows'] > rowheight: + rowheight = dev['devrows'] + for phase in myphases: + self.rowmaxlines[phase][row] = rowheight + self.rowheight[phase][row] = rowheight * self.rowH + row += 1 + if(row > self.rows): + self.rows = int(row) + for phase in myphases: + self.rowcount[phase] = row + return row + def phaseRowHeight(self, phase, row): + return self.rowheight[phase][row] + def phaseRowTop(self, phase, row): + top = 0 + for i in sorted(self.rowheight[phase]): + if i >= row: + break + top += self.rowheight[phase][i] + return top + # Function: calcTotalRows + # Description: + # Calculate the heights and offsets for the header and rows + def calcTotalRows(self): + maxrows = 0 + standardphases = [] + for phase in self.phases: + total = 0 + for i in sorted(self.rowmaxlines[phase]): + total += self.rowmaxlines[phase][i] + if total > maxrows: + maxrows = total + if total == self.rowcount[phase]: + standardphases.append(phase) + self.height = self.scaleH + (maxrows*self.rowH) + self.bodyH = self.height - self.scaleH + for phase in standardphases: + for i in sorted(self.rowheight[phase]): + self.rowheight[phase][i] = self.bodyH/self.rowcount[phase] + # Function: createTimeScale + # Description: + # Create the timescale for a timeline block + # Arguments: + # m0: start time (mode begin) + # mMax: end time (mode end) + # tTotal: total timeline time + # mode: suspend or resume + # Output: + # The html code needed to display the time scale + def createTimeScale(self, m0, mMax, tTotal, mode): + timescale = '
{1}
\n' + rline = '
Resume
\n' + output = '
\n' + # set scale for timeline + mTotal = mMax - m0 + tS = 0.1 + if(tTotal <= 0): + return output+'
\n' + if(tTotal > 4): + tS = 1 + divTotal = int(mTotal/tS) + 1 + divEdge = (mTotal - tS*(divTotal-1))*100/mTotal + for i in range(divTotal): + htmlline = '' + if(mode == 'resume'): + pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal)) + val = '%0.fms' % (float(i)*tS*1000) + htmlline = timescale.format(pos, val) + if(i == 0): + htmlline = rline + else: + pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal) - divEdge) + val = '%0.fms' % (float(i-divTotal+1)*tS*1000) + if(i == divTotal - 1): + val = 'Suspend' + htmlline = timescale.format(pos, val) + output += htmlline + output += '\n' + return output -# Class: TestRun +# Class: TestProps # Description: -# A container for a suspend/resume test run. This is necessary as -# there could be more than one, and they need to be separate. -class TestRun: +# A list of values describing the properties of these test runs +class TestProps: + stamp = '' + tracertype = '' + S0i3 = False + fwdata = [] ftrace_line_fmt_fg = \ '^ *(?P